JP7753808B2 - Traffic congestion determination device, traffic congestion determination method, and program - Google Patents

Description

The present invention relates to a congestion detection device, a congestion detection method, and a program.

In recent years, various techniques have become known for determining whether a traffic jam has occurred due to moving objects. As an example, the moving object may be a vehicle. For example, a technique has been proposed that determines whether a traffic jam has occurred due to vehicles based on information obtained by detecting vehicles on a road, such as the number of vehicles, vehicle speed, and the space occupancy rate of vehicles on the road.

For example, a traffic control system has been proposed that acquires observational information such as the number of vehicles based on surveillance footage from the road or radio waves from in-vehicle devices, calculates the space occupancy rate of vehicles on the road and the average vehicle speed based on the observational information, and determines the level of congestion based on the combination of space occupancy rate and average vehicle speed (see, for example, Patent Document 1).

Patent No. 6192980

However, it would be desirable to provide technology that can more accurately determine whether a traffic jam caused by a moving object has occurred.

In order to solve the above problem, one aspect of the present invention provides a congestion determination device comprising: a detection unit that detects one or more moving objects based on sensor data and obtains detection results; an extraction unit that extracts the movement paths of the moving objects based on the detection results; a setting unit that sets a determination area based on the movement paths of the moving objects; and a determination unit that determines whether congestion has occurred based on the movement paths of the moving objects and the determination area.

In addition, according to another aspect of the present invention, there is provided a congestion determination method executed by a congestion determination device, the congestion determination method comprising the steps of: detecting one or more moving objects based on sensor data and obtaining a detection result; extracting the movement path of the moving objects based on the detection result; setting a determination area based on the movement path of the moving objects; and determining whether congestion has occurred based on the movement path of the moving objects and the determination area.

In addition, according to another aspect of the present invention, there is provided a program that causes a computer to function as a congestion determination device that includes a detection unit that detects one or more moving objects based on sensor data and obtains detection results, an extraction unit that extracts the movement paths of the moving objects based on the detection results, a setting unit that sets a determination area based on the movement paths of the moving objects, and a determination unit that determines whether congestion has occurred based on the movement paths of the moving objects and the determination area.

As described above, the present invention provides technology that makes it possible to determine with greater accuracy whether or not a traffic jam has occurred due to a moving object.

1 is a diagram illustrating an example of a functional configuration of a traffic congestion determination system according to a first embodiment of the present invention. FIG. 10 is a diagram showing an example of a frame obtained by the imaging device. 4 is a flowchart illustrating an example of the overall operation of the traffic congestion determination device according to the embodiment. 10 is a flowchart illustrating an example of the operation of a vehicle information creation unit according to the embodiment. FIG. 10 is a diagram illustrating an example of extraction of a flow line. 10 is a flowchart illustrating an example of the operation of a movement line statistics unit according to the embodiment. FIG. 10 is a diagram illustrating an example of grouping according to the embodiment. 10A and 10B are diagrams illustrating an example of setting a congestion determination area according to the embodiment; 10 is a flowchart illustrating an example of the operation of a traffic condition determination unit according to the embodiment. 10A and 10B are diagrams for explaining an example of identifying a vehicle entering a congestion determination area according to the embodiment; 10A and 10B are diagrams for explaining an example of calculating a space occupancy rate according to the embodiment; 10A and 10B are diagrams for explaining an example in which it is determined that a traffic jam has occurred in the embodiment; FIG. 10 is a diagram illustrating an example of a functional configuration of a traffic congestion determination system according to a second embodiment of the present invention. FIG. 10 is a diagram illustrating an example of grouping according to the embodiment. 10A and 10B are diagrams illustrating an example of setting a congestion determination area according to the embodiment; 10 is a flowchart illustrating an example of the operation of a traffic condition determination unit according to the embodiment. 10A and 10B are diagrams for explaining an example of identifying a vehicle entering a congestion determination area according to the embodiment; 10A and 10B are diagrams for explaining an example of calculating a space occupancy rate according to the embodiment; 10A and 10B are diagrams for explaining an example in which it is determined that a traffic jam has occurred in the embodiment; 10A and 10B are diagrams for explaining the effects of the embodiment. 1 is a diagram illustrating a hardware configuration of an information processing device as an example of a traffic congestion determination device according to an embodiment of the present invention.

Preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Note that in this specification and drawings, components having substantially the same functional configuration will be designated by the same reference numerals, and redundant explanations will be omitted.

In addition, in this specification and drawings, multiple components having substantially the same functional configuration may be distinguished by adding different numbers after the same reference symbol. However, if there is no need to particularly distinguish between multiple components having substantially the same functional configuration, only the same reference symbol will be used. Furthermore, similar components in different embodiments may be distinguished by adding different letters after the same reference symbol. However, if there is no need to particularly distinguish between similar components in different embodiments, only the same reference symbol will be used.

(0. Overview)
First, an outline of the embodiment of the present invention will be described.

In recent years, various techniques have become known for determining whether a traffic jam has occurred due to a moving object. For example, the technique disclosed in Patent Document 1, as mentioned above, can be cited. With techniques like this one that use video-based vehicle detection, vehicles may not be detected because they appear small at the back of the road in the video. Furthermore, depending on conditions such as the time of day or weather, the video may be too dark, in which case vehicles may not be detected.

Despite this possibility, if a determination area for determining whether a traffic jam has occurred (hereinafter simply referred to as a "traffic jam determination area") is manually set on the image, areas where vehicles may not be detected may end up being included in the traffic jam determination area. This may result in the calculated vehicle space occupancy rate being low, and it may not be possible to accurately determine whether a traffic jam has occurred.

This specification therefore mainly describes a technology that enables more accurate determination of whether or not a traffic jam due to a moving object has occurred. More specifically, this specification mainly describes a technology that automatically sets a traffic jam determination area based on the detection results of a moving object, and by using the automatically set traffic jam determination area, enables more accurate determination of whether or not a traffic jam due to a moving object has occurred.

In this specification, we will mainly assume that the moving object for which it is determined whether a traffic jam has occurred is a vehicle. In such cases, the movement of the moving object can also be expressed as the vehicle running. However, moving objects are not limited to vehicles. For example, moving objects may be vehicles other than vehicles (e.g., ships, aircraft, etc.), or may be people, robots, etc.

The above provides an overview of an embodiment of the present invention.

(1. First embodiment)
First, a first embodiment of the present invention will be described.

(1-1. Configuration of the congestion judgment system)
First, an example of the configuration of a traffic congestion determination system according to a first embodiment of the present invention will be described. Fig. 1 is a diagram showing an example of the functional configuration of the traffic congestion determination system according to the first embodiment of the present invention. The traffic congestion determination system according to the first embodiment of the present invention includes a traffic congestion determination device 1, an imaging device 2, a storage device 3, and an output device 4.

The traffic congestion determination device 1 can be realized by a computer. As shown in FIG. 1, the traffic congestion determination device 1 is connected to a camera device 2, a storage device 3, and an output device 4 via wired or wireless connections. The traffic congestion determination device 1 also includes an image acquisition unit 11, a vehicle information creation unit 12, a traffic flow statistics unit 13, a traffic situation determination unit 14, and a result output unit 15.

The video acquisition unit 11, vehicle information creation unit 12, traffic line statistics unit 13, traffic situation determination unit 14, and result output unit 15 each include a computing device such as a CPU (Central Processing Unit), and their functions can be realized by the computing device expanding a program stored in ROM (Read Only Memory) into RAM and executing it. In this case, a computer-readable recording medium on which the program is recorded can also be provided.

Alternatively, the image acquisition unit 11, vehicle information creation unit 12, traffic line statistics unit 13, traffic condition determination unit 14, and result output unit 15 may be configured as dedicated hardware, or may be configured as a combination of multiple hardware components. Data required for calculations by the calculation device is stored appropriately in the storage device 3.

(Photographing device 2)
The image capturing device 2 may be configured with a camera. The camera may include an image sensor that captures images continuously in time series to obtain video data (hereinafter simply referred to as "video"). The video may include multiple images (multiple frames) captured continuously in time series. For example, the image capturing device 2 may be installed above or beside a road, and capture images of the road surface to continuously output frames to the congestion determination device 1. Here, examples of frames that may be included in the video will be described.

Figure 2 is a diagram showing an example of a frame captured by the image capture device 2. Referring to Figure 2, frame E1 captured by the image capture device 2 is shown. Frame E1 shows a road with two vehicles traveling on the road. The vehicle's travel area may include one or more lines (hereinafter referred to as "lanes") set for each direction the vehicle is traveling.

In the example shown in Figure 2, the road shown in frame E1 has two lanes, lane K1 and lane K2. However, the number of lanes is not limited to two. For example, the number of lanes may be one, or three or more. Lane K1 is a lane on which vehicles travel from the front to the back based on the position of the image capture device 2. On the other hand, lane K2 is a lane on which vehicles travel from the back to the front based on the position of the image capture device 2.

Furthermore, a lane may include one or more lanes. In the example shown in FIG. 2, lane K1 includes two driving lanes, driving lane L1 and driving lane L2, and lane K2 includes one driving lane, driving lane L3. However, the number of driving lanes is not limited to one or two. For example, the number of driving lanes may be three or more.

Note that detection frame F1 is an example of the detection result of a vehicle traveling in driving lane L1, and detection frame F2 is an example of the detection result of a vehicle traveling in driving lane L3.

Furthermore, traffic line V1 is a line that shows the movement of vehicles traveling in driving lane L1. Furthermore, traffic line V2 is a line that shows the movement of vehicles traveling in driving lane L2.

Here, "trajectory" can be said to be a line showing the "path" that a moving object has taken. Trajectory may include not only lines showing the path that a moving object has taken in the past, but also lines showing the path that a moving object is estimated to take in the future.

Furthermore, in an embodiment of the present invention, a "traffic line" may include not only lines showing the trajectory of a vehicle, but also lines showing the trajectory of a moving object other than a vehicle, such as a person. Furthermore, a traffic line may include not only lines showing the trajectory of a moving object on a road, but also lines showing the trajectory of a moving object outside of a road, such as inside a building.

Returning to Figure 1, the explanation continues. The image captured by the image capture device 2 is an example of sensor data obtained by a sensor. Therefore, sensor data other than image may be used instead of image. For example, an ultrasonic sensor, radar, or LiDAR (Light Detection and Ranging) may be used instead of the image capture device 2. In this case, the sensor data may be detection data detected by the ultrasonic sensor, radar, or LiDAR.

In the example shown in FIG. 1, the camera device 2 and the traffic congestion determination device 1 exist separately. However, the camera device 2 and the traffic congestion determination device 1 may be integrated. In other words, the camera device 2 may be incorporated into the traffic congestion determination device 1.

(Storage device 3)
The storage device 3 is a storage device capable of storing programs and various information for operating the traffic congestion determination device 1. For example, the storage device 3 may be configured with a non-volatile memory. For example, the storage device 3 may store in advance actual size conversion parameters 34, lane parameters 35a, and traffic congestion determination parameters 36. Furthermore, the storage device 3 may store images 31, vehicle information 32, and statistical information 33. The storage device 3 may also temporarily store data required during the operation of the traffic congestion determination device 1.

In the example shown in FIG. 1, the storage device 3 and the congestion detection device 1 exist separately. However, the storage device 3 and the congestion detection device 1 may be integrated. In other words, the storage device 3 may be incorporated into the congestion detection device 1. The image 31, vehicle information 32, statistical information 33, actual size conversion parameters 34, lane parameters 35a, and congestion detection parameters 36 will be described in detail later.

(Output device 4)
The output device 4 outputs the determination result obtained by the traffic congestion determination device 1 determining whether or not a traffic congestion has occurred. For example, the output device 4 may be configured with a display. In this case, the output device 4 may display the determination result as visual information so that the determination result can be perceived by the user's eyesight. However, the form of the output device 4 is not limited. For example, the output device 4 may include a speaker or the like. In this case, the output device 4 may output the determination result as auditory information so that the determination result can be perceived by the user's ears.

In the example shown in FIG. 1, the output device 4 and the congestion judgment device 1 exist separately. However, the output device 4 and the congestion judgment device 1 may be integrated. In other words, the output device 4 may be incorporated into the congestion judgment device 1.

(Example of operation of traffic congestion determination device 1)
FIG. 3 is a flowchart showing an example of the overall operation of the traffic congestion determination device 1 according to the first embodiment of the present invention.

As shown in FIG. 3, the video acquisition unit 11 acquires video captured by the imaging device 2 from the imaging device 2 (S10). If the video acquisition unit 11 has not yet acquired a certain amount of video (NO in S11), the operation proceeds to S10. On the other hand, if the video acquisition unit 11 has acquired a certain amount of video (YES in S11), the operation proceeds to S12.

Next, the vehicle information creation unit 12 executes processing (S12), the traffic line statistics unit 13 executes processing (S13), and the traffic situation determination unit 14 executes processing (S14).

The result output unit 15 outputs the determination result obtained by the traffic condition determination unit 14 to the output device 4 (S15). If the traffic congestion determination device 1 continues to determine whether traffic congestion has occurred (NO in S16), it proceeds to S10. On the other hand, if the traffic congestion determination device 1 ends its determination of whether traffic congestion has occurred (YES in S16), it ends its processing.

(Video Acquisition Unit 11)
1 , we will continue to explain the details of the exemplary configuration of the congestion determination device 1. The image acquisition unit 11 acquires the image captured by the image capture device 2 from the image capture device 2. The image acquisition unit 11 then stores the image acquired from the image capture device 2 as image 31 in the storage device 3.

(Vehicle information creation unit 12)
The vehicle information creating unit 12 creates vehicle information, which is information relating to the vehicle, based on the video 31 , and stores the created vehicle information in the storage device 3 as vehicle information 32 .

The vehicle information creation unit 12 includes a vehicle detection unit 121, a vehicle identification unit 122, a vehicle classification unit 123, a traffic flow extraction unit 124, a vehicle speed estimation unit 125, and a vehicle length estimation unit 126.

(Example of operation of vehicle information creation unit 12)
FIG. 4 is a flowchart showing an example of the operation of the vehicle information creation unit 12 according to the first embodiment of the present invention.

As shown in FIG. 4, the vehicle detection unit 121 detects vehicles from frames acquired by the video acquisition unit 11 (S121). If the vehicle detection unit 121 has not yet detected vehicles for a certain number of frames ("NO" in S122), the operation proceeds to S121. On the other hand, if the vehicle detection unit 121 has detected vehicles for a certain number of frames ("YES" in S122), the operation proceeds to S123.

The vehicle identification unit 122 identifies identical vehicles from the detection frames obtained by vehicle detection over a certain number of frames (S123). The vehicle classification unit 123 identifies the vehicle type (hereinafter also referred to as "model") for each identical vehicle from the detection frames obtained by vehicle detection over a certain number of frames (S124). The traffic flow extraction unit 124 extracts traffic flows for each identical vehicle from the detection frames obtained by vehicle detection over a certain number of frames (S125).

The vehicle speed estimation unit 125 estimates the speed (vehicle speed) of each vehicle from the traffic line of each vehicle (S126). The vehicle length estimation unit 126 estimates the vehicle length (hereinafter also referred to as "vehicle length") of each vehicle from the vehicle type classification results by the vehicle classification unit 123 (S127). Then, the processing of the vehicle information creation unit 12 ends.

(Vehicle detection unit 121)
Returning to Fig. 1, the detailed description of the exemplary configuration of the vehicle information creation unit 12 will continue. The vehicle detection unit 121 (detection unit) detects one or more vehicles based on the video 31. As a result, the vehicle detection unit 121 obtains one or more detection frames from each of a certain number of frames included in the video 31 as an example of the detection result. The vehicle detection unit 121 stores the detection frame for each frame in the storage device 3 as vehicle information 32.

More specifically, the vehicle detection unit 121 receives the video 31 as input and outputs one or more detection frames corresponding to each of a certain number of frames contained in the video 31. For example, the detection frame may be a frame that surrounds the pixels of a vehicle appearing in the frame, and may be expressed by the coordinates of a predetermined position on the frame. For example, the coordinates of the predetermined position on the frame may be the coordinates of each of the four corners of the frame, or the coordinates of the top left and bottom right of the frame, or the coordinates of the top right and bottom left of the frame.

The specific method for vehicle detection is not particularly limited. For example, vehicle detection may be performed using a neural network or pattern matching.

(Vehicle Identification Unit 122)
The vehicle identification unit 122 (identification unit) performs vehicle identification to identify detection frames corresponding to the same vehicle based on a certain number of detection frames contained in the vehicle information 32. This identifies a series of detection frames for each vehicle. The vehicle identification unit 122 then adds information indicating the correspondence between frames of the series of detection frames for each vehicle to the vehicle information 32.

More specifically, the vehicle identification unit 122 performs vehicle identification by identifying the same vehicle that appears consecutively across multiple frames based on a detection window of a certain number of frames contained in the vehicle information 32. Note that the specific method for vehicle identification is not particularly limited.

For example, the vehicle identification unit 122 may estimate the detection frames of the same vehicle between frames based on the overlap rate between the detection frames in the previous and next frames. More specifically, the vehicle identification unit 122 may estimate that the detection frames of the same vehicle between the previous and next frames have an overlap rate greater than a predetermined rate.

Alternatively, the vehicle identification unit 122 may acquire pixel values within a certain number of detection frames from a certain number of frames of video 31, and estimate the detection frames of the same vehicle between frames based on the similarity between the detection frames, which is based on the pixel values within the detection frames. Here, the similarity may be calculated in any way.

More specifically, the vehicle identification unit 122 may estimate, as the detection frames of the same vehicle, detection frames in which the difference between their average pixel values is smaller than a predetermined value. Alternatively, the vehicle identification unit 122 may estimate, as the detection frames of the same vehicle, detection frames in which the similarity between the component distributions of pixel values (e.g., RGB distributions) is larger than a predetermined value. Alternatively, the vehicle identification unit 122 may estimate, as the detection frames of the same vehicle, detection frames in which the difference between the feature amounts calculated from pixel values is smaller than a predetermined value.

(Vehicle Classification Unit 123)
The vehicle classification unit 123 (classification unit) identifies the vehicle model for each vehicle based on the detection frame for each vehicle included in the vehicle information 32. More specifically, the vehicle classification unit 123 performs vehicle model classification based on a certain number of frames of video 31 and the detection frame for each vehicle included in the vehicle information 32, and obtains the vehicle model for each vehicle as a vehicle model classification result. The vehicle classification unit 123 then adds the vehicle model for each vehicle to the vehicle information 32.

Here, the vehicle type classification method is not particularly limited. As an example, the vehicle classification unit 123 may input pixel values enclosed by at least one detection frame for each vehicle into the vehicle type classifier, and obtain the vehicle type for each vehicle from the vehicle type classifier. Examples of vehicle types include passenger cars, buses, trucks, and motorcycles. Furthermore, in cases where the vehicle length estimation unit 126 does not estimate the vehicle length, the vehicle information creation unit 12 does not need to be equipped with the vehicle classification unit 123.

(Flow line extraction unit 124)
The flow line extraction unit 124 (extraction unit) extracts a flow line for each vehicle based on the detection frame for each vehicle included in the vehicle information 32. Then, the flow line extraction unit 124 adds the flow line for each vehicle to the vehicle information 32. Here, the flow line may be represented by a collection of points in which the positions of the same vehicle that appear consecutively across multiple frames of video are arranged in chronological order. For example, the flow line extraction unit 124 may obtain the flow line by chronologically arranging the coordinate values of a series of detection frames for the same vehicle.

Figure 5 is a diagram showing an example of extracted traffic lines. Referring to Figure 5, frames E11 to E13 are shown in chronological order of the time they were captured by the image capture device 2. The vehicle detection unit 121 then detects detection frames F11 to F13 from frames E11 to E13 as detection results for the same vehicle traveling in lane K1. As an example, the traffic line extraction unit 124 may obtain a vehicle traffic line V1 by connecting specific points (e.g., midpoints P11 to P13 of the bottom sides) of the detection frames F11 to F13 for the same vehicle.

It is possible that the detection frame of the same vehicle may be lost for several frames due to being hidden by other objects, etc. In such cases, the traffic line extraction unit 124 may interpolate the coordinate values of the detection frame by equally dividing the line connecting the coordinate values of the detection frame in the frames immediately before and after the number of frames in which the detection frame is lost, by the number of frames in which the detection frame is lost.

(Vehicle speed estimation unit 125)
The vehicle speed estimation unit 125 (speed estimation unit) estimates the speed of each vehicle based on the traffic line of each vehicle contained in the vehicle information 32 and the actual size conversion parameter 34 set in advance in the storage device 3, and obtains an estimated speed for each vehicle. Then, the vehicle speed estimation unit 125 adds the estimated speed (vehicle speed) for each vehicle to the vehicle information 32. The actual size conversion parameter 34 is a conversion parameter that indicates conversion from a length in the video to a length in real space.

The method for estimating vehicle speed is not particularly limited. For example, the vehicle speed estimation unit 125 may convert the length of the flow line for each vehicle into an actual flow line length, which is the length of the flow line in real space, using the actual size conversion parameter 34, and may use the difference in detection times corresponding to the start and end points of the flow line as the vehicle travel time, and the value obtained by dividing the actual flow line length by the vehicle travel time as the estimated speed (vehicle speed) for each vehicle.

(Vehicle length estimation unit 126)
The vehicle length estimation unit 126 (size estimation unit) estimates the size of each vehicle based on the vehicle type of each vehicle contained in the vehicle information 32. In the embodiment of the present invention, the case where vehicle length is estimated will be mainly described as an example of vehicle size. However, the size of a vehicle is not limited to vehicle length. For example, the size of a vehicle may be the area that the vehicle occupies on the road. The vehicle length estimation unit 126 adds the vehicle length of each vehicle to the vehicle information 32.

The method for estimating vehicle length is not particularly limited. For example, if a correspondence table between vehicle types and vehicle lengths is set in advance as a parameter in the storage device 3, the vehicle length estimation unit 126 may obtain the vehicle length corresponding to the vehicle type identified by the vehicle classification unit 123 from the correspondence table. For example, the correspondence table may set 5 meters as the vehicle length of a passenger car, and 12 meters as the vehicle length of a bus and a truck. Alternatively, a uniform length that is independent of the vehicle type may be used as the vehicle length. In this case, the vehicle information creation unit 12 may not be equipped with the vehicle length estimation unit 126.

(Flow line statistics department 13)
The flow line statistics unit 13 creates statistical information based on the vehicle information 32 and stores the created statistical information as statistical information 33 in the storage device 3. More specifically, the flow line statistics unit 13 obtains information (hereinafter also referred to as "group information") indicating which flow line belongs to which group (hereinafter also referred to as "flow line group"), as well as congestion determination areas and average flow line lengths, based on the vehicle information 32 stored in the storage device 3. Then, the flow line statistics unit 13 stores the group information, congestion determination areas, and average flow line lengths as statistical information 33 in the storage device 3.

The traffic flow statistics unit 13 includes a traffic flow grouping unit 131, a congestion determination area setting unit 132, and an average traffic flow length calculation unit 133.

(Example of operation of the movement line statistics unit 13)
FIG. 6 is a flowchart showing an example of the operation of the movement line statistics unit 13 according to the first embodiment of the present invention.

As shown in FIG. 6, the flow line grouping unit 131 groups the flow lines extracted by the flow line extraction unit 124 (S131). If the flow line grouping unit 131 has not yet completed grouping of flow lines for a certain period of time or a certain number of vehicles ("NO" in S132), the operation proceeds to S131. On the other hand, if the flow line grouping unit 131 has completed grouping of flow lines for a certain period of time or a certain number of vehicles ("YES" in S132), the operation proceeds to S133.

Next, the congestion determination area setting unit 132 sets a congestion determination area for each flow line group (S133). Next, the average flow line length calculation unit 133 calculates the average flow line length for each flow line group (S134). If the congestion determination area setting unit 132 and the average flow line length calculation unit 133 have not processed all flow line groups (NO in S135), the operation proceeds to S131. On the other hand, if the congestion determination area setting unit 132 and the average flow line length calculation unit 133 have processed all flow line groups (YES in S135), the processing of the flow line statistics unit 13 ends.

(Flow Line Grouping Unit 131)
Returning to FIG. 1 , the detailed configuration example of the flow line grouping unit 131 will be described. The flow line grouping unit 131 performs grouping of flow lines in units of lanes based on the flow lines of each vehicle contained in the vehicle information 32 and the lane parameters 35a pre-set in the storage device 3. In other words, grouping is a process of dividing which vehicles have traveled in which lanes into flow line groups. This allows flow lines for each lane to be extracted. The flow line grouping unit 131 then records information (group information) indicating which flow lines belong to which flow line group as statistical information 33 in the storage device 3.

Figure 7 is a diagram showing an example of grouping according to the first embodiment of the present invention. Referring to Figure 7, frame E20 captured by the image capture device 2 is shown. The flow lines of vehicles traveling in lane K1, extracted by the flow line extraction unit 124, are indicated by dashed arrows. As shown in Figure 7, the flow line grouping unit 131 groups the flow lines of vehicles traveling in lane K1 into flow line group G1.

The grouping method is not particularly limited. For example, if the position of the lane in the video is set as the lane parameter 35a, the flow line grouping unit 131 may divide the flow lines into flow line groups of lanes with the longest flow lines based on the flow lines of each vehicle and the position of the lane in the video. Alternatively, if the lane parameter 35a is set for each lane in the video as a line that crosses the lane, the flow line grouping unit 131 may divide the flow lines into flow line groups of lanes that pass through the crossing line.

(Traffic congestion determination area setting unit 132)
The congestion determination area setting unit 132 (setting unit) sets a congestion determination area based on the flow line of each vehicle contained in the vehicle information 32. More specifically, the congestion determination area setting unit 132 sets a congestion determination area for each lane based on the flow line of each vehicle contained in the vehicle information 32 and the group information contained in the statistical information 33. The congestion determination area setting unit 132 then adds the congestion determination area to the statistical information 33. The congestion determination area can be represented by a collection of points on the outline of the area, for example.

Figure 8 is a diagram showing an example of setting a congestion determination area according to the first embodiment of the present invention. Referring to Figure 8, a congestion determination area A1 corresponding to lane K1 is shown. In more detail, the congestion determination area setting unit 132 sets the congestion determination area A1 corresponding to lane K1 based on the traffic lines belonging to traffic line group G1 (Figure 7).

The method for setting the congestion determination area A1 is not particularly limited. For example, the congestion determination area setting unit 132 may obtain the congestion determination area A1 by aggregating the traffic lines belonging to the traffic line group G1 for a certain period of time or for a certain number of vehicles.

More specifically, the congestion determination area setting unit 132 may image the traffic lines belonging to a traffic line group for a certain period of time or for a certain number of vehicles. For example, the congestion determination area setting unit 132 may image the traffic lines by arranging pixel values with a certain brightness at the positions of the traffic lines. The congestion determination area setting unit 132 may then add up the pixel values of each pixel in the generated image to calculate the sum of the pixel values for each pixel, and set the set of pixels whose sum of pixel values is equal to or greater than a threshold as the congestion determination area A1.

At this time, the congestion determination area setting unit 132 may set a congestion determination area A1 of the desired size by changing the thickness of the traffic lines relative to the size of the image. For example, the congestion determination area setting unit 132 may allocate pixel values at the position of a traffic line that is thicker than the traffic line extracted by the traffic line extraction unit 124. Alternatively, the congestion determination area setting unit 132 may allocate pixel values in an image that is smaller than the video captured by the image capture device 2.

(Average flow line length calculation unit 133)
The average flow line length calculation unit 133 calculates an average flow line length for a vehicle based on the flow line for each vehicle included in the vehicle information 32. More specifically, the average flow line length calculation unit 133 calculates an average flow line length corresponding to a flow line group based on the flow line for each vehicle included in the vehicle information 32 and the group information included in the statistical information 33. The average flow line length calculation unit 133 then adds the average flow line length corresponding to the flow line group to the statistical information 33 as an average flow line length for each lane.

The average flow line length calculation unit 133 may calculate the average value of the lengths of the flow lines for a certain period of time or a certain number of vehicles belonging to the same flow line group as the average flow line length corresponding to the flow line group. Here, the same flow line group may be the most recent (closest in time) same flow line group corresponding to the statistical information 33 added as the average flow line length. Note that the average value is an example of a representative value, and therefore other representative values (such as the median) may be used instead of the average value.

(Traffic Condition Determination Unit 14)
The traffic condition determination unit 14 determines whether or not a traffic jam due to vehicles has occurred based on the vehicle information 32 and the statistical information 33. More specifically, the traffic condition determination unit 14 determines whether or not a traffic jam due to vehicles has occurred for each lane based on the vehicle information 32 and the statistical information 33. Then, the traffic condition determination unit 14 outputs the determination result obtained by determining whether or not a traffic jam has occurred to the result output unit 15.

The traffic condition determination unit 14 includes a space occupancy calculation unit 141, a time average vehicle speed calculation unit 142, and a congestion determination unit 143.

(Example of operation of traffic condition determination unit 14)
FIG. 9 is a flowchart showing an example of the operation of the traffic condition determination unit 14 according to the first embodiment of the present invention.

As shown in FIG. 9, the space occupancy calculation unit 141 calculates the space occupancy for each flow line group based on the congestion determination area (S141). The hourly average vehicle speed calculation unit 142 calculates the average vehicle speed (hereinafter also referred to as "hourly average vehicle speed") for each flow line group based on the group information (S142). If the space occupancy and hourly average vehicle speed have not been calculated for all flow line groups ("NO" in S143), the process proceeds to S141 and S142.

On the other hand, if the space occupancy rate and hourly average vehicle speed have been calculated for all flow line groups ("YES" in S143), the congestion determination unit 143 determines whether congestion has occurred for each lane based on the space occupancy rate and hourly average vehicle speed for each flow line group (S144). If it has not been determined whether congestion has occurred for all lanes ("NO" in S145), operation proceeds to S144.

On the other hand, if it has been determined whether congestion has occurred for all lanes ("YES" in S145), the processing of the traffic condition determination unit 14 ends.

(Space occupancy calculation unit 141)
The space occupancy rate calculation unit 141 identifies, for each lane, one or more vehicles (hereinafter also referred to as “intruding vehicles”) that have intruded into the congestion determination area based on the detection frame (detected position of the vehicle) included in the vehicle information 32 and the congestion determination area included in the statistical information 33. Then, the space occupancy rate calculation unit 141 calculates, for each lane, a space occupancy rate, which is the proportion of the space occupied by the intruding vehicle, based on the vehicle length of the intruding vehicle included in the vehicle information 32. For example, the space occupancy rate calculation unit 141 calculates the space occupancy rate for each lane based on the vehicle length of the intruding vehicle included in the vehicle information 32 and the average traffic line length included in the statistical information 33.

Figure 10 is a diagram illustrating an example of identifying a vehicle entering a congestion determination area according to the first embodiment of the present invention. Referring to Figure 10, frame E40 is shown. Frame E40 is a frame captured by the image capture device 2 at the time when the traffic condition determination unit 14 determines whether or not a congestion has occurred.

The vehicle information 32 obtained from frame E40 has already been created by the vehicle information creation unit 12. Furthermore, at the time the traffic condition determination unit 14 determines whether a traffic jam has occurred, the traffic congestion determination area A1 corresponding to lane K1 has already been created by the traffic line statistics unit 13. The traffic congestion determination area corresponding to lane K2 has also already been created by the traffic line statistics unit 13, but is not shown in the figure.

The space occupancy calculation unit 141 identifies one or more intruding vehicles that have entered the congestion determination area for each lane based on the detection frame obtained from frame E40 and the congestion determination area. For example, the space occupancy calculation unit 141 may identify a vehicle whose midpoint of the lower edge of the detection frame is located inside the congestion determination area as a vehicle that has entered the congestion determination area. On the other hand, the space occupancy calculation unit 141 may not identify a vehicle whose midpoint of the lower edge of the detection frame is located outside the congestion determination area as a vehicle that has entered the congestion determination area.

In the example shown in FIG. 10, the midpoint of the bottom edge of detection frame F1 is located inside the congestion determination area A1 corresponding to lane K1, and the midpoint of the bottom edge of detection frame F2 is located outside the congestion determination area A1 corresponding to lane K1. Therefore, the space occupancy calculation unit 141 may identify the vehicle corresponding to detection frame F1 as a vehicle that has entered the congestion determination area A1, but may not identify the vehicle corresponding to detection frame F2 as a vehicle that has entered the congestion determination area A1.

For example, the space occupancy rate calculation unit 141 calculates the sum of the vehicle lengths of the intruding vehicles contained in the vehicle information 32 for each lane. Then, the space occupancy rate calculation unit 141 calculates the space occupancy rate for each lane based on the sum of the vehicle lengths of the intruding vehicles and the average traffic line length contained in the statistical information 33. More specifically, the space occupancy rate can be calculated using the following formula (1):

Space occupancy rate = total vehicle length / average traffic flow length ... (1)

Figure 11 is a diagram illustrating an example of calculating the space occupancy rate according to the first embodiment of the present invention. Referring to Figure 11, vehicles corresponding to detection frames F1 to F3 are identified as vehicles that have entered the congestion determination area A1 corresponding to lane K1. In this case, the ratio (space occupancy rate) of the sum of vehicle lengths M1 to M3 corresponding to detection frames F1 to F3 to the average traffic line length B1 corresponding to lane K1 is shown as in the graph in Figure 11.

(Time average vehicle speed calculation unit 142)
The hourly average vehicle speed calculation unit 142 (average speed calculation unit) calculates the hourly average vehicle speed based on the estimated vehicle speed for a certain period of time contained in the vehicle information 32. More specifically, the hourly average vehicle speed calculation unit 142 calculates the hourly average vehicle speed of the estimated vehicle speed for a certain period of time for each flow line group based on the group information contained in the statistical information 33, thereby calculating the hourly average vehicle speed for each lane.

(Traffic congestion determination unit 143)
The congestion determination unit 143 determines whether congestion has occurred for each lane based on the space occupancy rate for each lane and the hourly average vehicle speed for each lane. For example, the congestion determination unit 143 determines whether congestion has occurred for each lane using a space occupancy threshold and a hourly average vehicle speed threshold that are set in advance in the storage device 3 as congestion determination parameters 36. More specifically, if there is a lane whose space occupancy rate is equal to or greater than the space occupancy threshold and whose hourly average vehicle speed is equal to or less than the hourly average vehicle speed threshold, the congestion determination unit 143 determines that congestion has occurred in that lane.

Figure 12 is a diagram illustrating an example of how a traffic jam is determined to have occurred in the first embodiment of the present invention. As shown in Figure 12, the traffic jam determination unit 143 determines that a traffic jam has occurred in lane K1 when the space occupancy rate of lane K1 is equal to or greater than the space occupancy rate threshold and the time-average vehicle speed of lane K1 is equal to or less than the time-average vehicle speed threshold. On the other hand, the traffic jam determination unit 143 determines that a traffic jam has not occurred in lane K1 when the space occupancy rate of lane K1 is below the space occupancy rate threshold or when the time-average vehicle speed of lane K1 is above the time-average vehicle speed threshold.

(Result output unit 15)
The result output unit 15 outputs the determination result obtained by the traffic condition determination unit 14 to the output device 4. For example, the determination result may include information indicating whether or not congestion has occurred for each lane. More specifically, the result output unit 15 performs processing to convert the determination result obtained by the traffic condition determination unit 14 into a format suitable for output by the output device 4, and outputs the determination result in the converted format to the output device 4.

The above describes an example configuration of a congestion determination system according to the first embodiment of the present invention.

(1-2. Effects)
The traffic congestion determination device 1 according to the first embodiment of the present invention has a function as a determination unit that determines whether or not traffic congestion has occurred based on the flow lines of vehicles stored in the vehicle information 32 and the traffic congestion determination area stored in the statistical information 33. For example, the determination unit determines whether or not traffic congestion has occurred for each lane based on the flow lines of vehicles and the traffic congestion determination area for each lane.

With this configuration, a congestion determination area can be set based on the actual vehicle detection situation. This allows areas where no vehicles are detected to be excluded from the congestion determination area, making it possible to more accurately determine whether congestion has occurred.

Furthermore, with this configuration, the vehicle flow line is extracted by the flow line extraction unit 124 based on the vehicle detection frame, and is therefore drawn within the area where the vehicle is actually detected. Furthermore, the congestion determination area is obtained by the congestion determination area setting unit 132 based on the accumulation of recent flow lines. Therefore, the congestion determination area is set to the area where the vehicle was most recently detected.

In other words, areas at the back of the road shown in the image, or areas where the time of day or weather is not suitable for vehicle detection, will not detect vehicles in the immediate vicinity and will be excluded from the congestion determination area. This allows for more accurate determination of whether congestion has occurred, and in particular, allows for more accurate calculation of the space occupancy rate of vehicles.

The above describes the first embodiment of the present invention.

(2. Second embodiment)
Next, a second embodiment of the present invention will be described.

(2-1. Configuration of the congestion judgment system)
First, an example of the configuration of a traffic congestion determination system according to a second embodiment of the present invention will be described. Fig. 13 is a diagram showing an example of the functional configuration of the traffic congestion determination system according to the second embodiment of the present invention. The traffic congestion determination system according to the second embodiment of the present invention includes a traffic congestion determination device 1, an imaging device 2, a storage device 3, and an output device 4, similar to the traffic congestion determination system according to the second embodiment of the present invention.

However, the storage device 3 according to the second embodiment of the present invention differs from the storage device 3 according to the first embodiment of the present invention mainly in that it additionally stores the driving lane parameter 35b. The following mainly describes the configuration of the congestion determination device 1 related to the driving lane parameter 35b and the driving lane parameter 35b. Detailed descriptions of other components will be omitted.

(Flow Line Grouping Unit 131)
The flow line grouping unit 131 groups the flow lines by driving lane based on the flow lines for each vehicle contained in the vehicle information 32 and the driving lane parameters 35b pre-set in the storage device 3. The grouping here is a process of dividing which vehicles have traveled in which driving lanes into flow line groups. This makes it possible to extract flow lines for each driving lane. The flow line grouping unit 131 then records information (group information) indicating which flow lines belong to which flow line group as statistical information 33 in the storage device 3.

Figure 14 is a diagram showing an example of grouping according to the second embodiment of the present invention. Referring to Figure 14, frame E60 captured by the image capture device 2 is shown. The flow lines of vehicles traveling in driving lane L1, extracted by the flow line extraction unit 124, are indicated by dashed arrows. As shown in Figure 14, the flow line grouping unit 131 groups the flow lines of vehicles traveling in driving lane L1 into flow line group G1.

The grouping method is not particularly limited. For example, if the position of the driving lane in the video is set as the driving lane parameter 35b, the flow line grouping unit 131 may divide the traffic lines into traffic line groups for the driving lane with the longest traffic line based on the traffic lines for each vehicle and the position of the driving lane in the video. Alternatively, if a line that crosses the driving lane in the video is set for each driving lane as the driving lane parameter 35b, the flow line grouping unit 131 may divide the traffic lines into traffic line groups for the driving lanes that pass through the crossing line.

(Traffic congestion determination area setting unit 132)
The congestion determination area setting unit 132 sets a congestion determination area for each driving lane based on the flow line of each vehicle contained in the vehicle information 32 and the group information contained in the statistical information 33. Then, the congestion determination area setting unit 132 adds the congestion determination area to the statistical information 33.

Figure 15 is a diagram showing an example of setting a congestion determination area according to the second embodiment of the present invention. Referring to Figure 15, a congestion determination area A1 corresponding to driving lane L1 is shown. In more detail, the congestion determination area setting unit 132 sets the congestion determination area A1 corresponding to driving lane L1 based on the traffic lines belonging to traffic line group G1 (Figure 14). Note that, as with the first embodiment of the present invention, the method for setting the congestion determination area A1 is not particularly limited.

(Average flow line length calculation unit 133)
The average flow line length calculation unit 133 calculates an average flow line length corresponding to a flow line group based on the flow lines of each vehicle included in the vehicle information 32 and the group information included in the statistical information 33. The average flow line length calculation unit 133 then adds the average flow line length corresponding to the flow line group to the statistical information 33 as an average flow line length for each travel lane. As with the first embodiment of the present invention, the method for calculating the average flow line length corresponding to a flow line group is not particularly limited.

(Traffic Condition Determination Unit 14)
The traffic condition determination unit 14 determines whether or not a traffic jam due to vehicles has occurred for each travel lane based on the vehicle information 32 and the statistical information 33. Then, the traffic condition determination unit 14 outputs the determination result obtained by determining whether or not a traffic jam has occurred to the result output unit 15.

(Example of operation of traffic condition determination unit 14)
16 is a flowchart showing an example of the operation of the traffic condition determination unit 14 according to the second embodiment of the present invention. As shown in Fig. 16, the operations S141 to S143 of the traffic condition determination unit 14 according to the second embodiment of the present invention are executed in the same manner as the operations S141 to S143 of the traffic condition determination unit 14 according to the first embodiment of the present invention (Fig. 9).

When the space occupancy rate and hourly average vehicle speed have been calculated for all flow line groups ("YES" in S143), the congestion determination unit 143 determines whether congestion has occurred for each travel lane based on the space occupancy rate and hourly average vehicle speed for each flow line group (S244). When it has not been determined whether congestion has occurred for all travel lanes ("NO" in S245), the operation proceeds to S244.

On the other hand, if it has been determined whether congestion has occurred for all driving lanes ("YES" in S245), the processing of the traffic condition determination unit 14 ends.

(Space occupancy calculation unit 141)
The space occupancy rate calculation unit 141 identifies one or more intruding vehicles into the congestion determination area for each driving lane based on the detection frame (detected position of the vehicle) included in the vehicle information 32 and the congestion determination area included in the statistical information 33. Then, the space occupancy rate calculation unit 141 calculates a space occupancy rate, which is the ratio of the intruding vehicle to the space, for each driving lane based on the vehicle length of the intruding vehicle included in the vehicle information 32. For example, the space occupancy rate calculation unit 141 calculates the space occupancy rate for each driving lane based on the vehicle length of the intruding vehicle included in the vehicle information 32 and the average traffic line length included in the statistical information 33.

Figure 17 is a diagram illustrating an example of identifying a vehicle entering a congestion determination area according to the second embodiment of the present invention. Referring to Figure 17, frame E80 is shown. Frame E80 is a frame captured by the image capture device 2 at the time when the traffic condition determination unit 14 determines whether or not a congestion has occurred.

The space occupancy calculation unit 141 identifies one or more intruding vehicles that have entered the congestion determination area for each driving lane based on the detection frame obtained from frame E80 and the congestion determination area. Note that the method for identifying intruding vehicles into the congestion determination area may be the same as in the first embodiment of the present invention.

In the example shown in FIG. 17, the midpoint of the bottom edge of detection frame F1 is located inside the congestion determination area A1 corresponding to driving lane L1, and the midpoint of the bottom edge of detection frame F2 is located outside the congestion determination area A1 corresponding to driving lane L1. Therefore, the space occupancy calculation unit 141 may identify the vehicle corresponding to detection frame F1 as a vehicle that has entered the congestion determination area A1, but may not identify the vehicle corresponding to detection frame F2 as a vehicle that has entered the congestion determination area A1.

For example, the space occupancy calculation unit 141 calculates the space occupancy for each travel lane based on the total vehicle length of the intruding vehicles and the average traffic line length contained in the statistical information 33. More specifically, the space occupancy can be calculated using the above formula (1).

Figure 18 is a diagram illustrating an example of calculating the space occupancy rate according to the second embodiment of the present invention. Referring to Figure 18, vehicles corresponding to detection frames F1 to F3 are identified as vehicles that have entered the congestion determination area A1 corresponding to driving lane L1. In this case, the ratio (space occupancy rate) of the sum of the vehicle lengths M1 to M3 corresponding to detection frames F1 to F3 to the average traffic line length B1 corresponding to driving lane L1 is shown as in the graph in Figure 18.

(Time average vehicle speed calculation unit 142)
The hourly average vehicle speed calculation unit 142 (average speed calculation unit) calculates the hourly average vehicle speed based on the estimated vehicle speed for a certain period of time contained in the vehicle information 32. More specifically, the hourly average vehicle speed calculation unit 142 calculates the hourly average vehicle speed of the estimated vehicle speed for a certain period of time for each flow line group based on the group information contained in the statistical information 33, thereby calculating the hourly average vehicle speed for each travel lane.

(Traffic congestion determination unit 143)
The congestion determination unit 143 determines whether congestion has occurred for each driving lane based on the space occupancy rate for each driving lane and the time average vehicle speed for each driving lane, and also determines whether congestion has occurred for each lane. For example, the congestion determination unit 143 determines whether congestion has occurred for each driving lane based on the congestion determination parameters 36, and also determines whether congestion has occurred for each lane based on information indicating the association between lanes and driving lanes that is set in advance in the storage device 3 as the lane parameters 35a.

More specifically, the congestion determination unit 143 determines that congestion has occurred in a driving lane when there is a driving lane whose space occupancy rate is equal to or greater than the space occupancy rate threshold and whose hourly average vehicle speed is equal to or less than the hourly average vehicle speed threshold. The congestion determination unit 143 then determines that congestion has occurred in a lane when all of the determination results corresponding to one or more driving lanes corresponding to the lane indicate that congestion has occurred.

On the other hand, the congestion determination unit 143 determines that no congestion has occurred in the lane if at least one of the determination results corresponding to the driving lanes corresponding to the lane does not indicate the occurrence of congestion. The congestion determination unit 143 also determines that no congestion has occurred in the lane if at least one of the determination results corresponding to each of one or more driving lanes corresponding to the lane does not indicate the occurrence of congestion.

Figure 19 is a diagram illustrating an example of how a traffic jam is determined to have occurred in the second embodiment of the present invention. As shown in Figure 19, the traffic jam determination unit 143 determines that a traffic jam has occurred in the lane K1 corresponding to the driving lanes L1 and L2 if the space occupancy rate of the driving lane L1 is equal to or greater than the space occupancy rate threshold set in advance in the storage device 3, and the time-average vehicle speed of the driving lane L1 is equal to or less than the time-average vehicle speed threshold set in advance in the storage device 3, and if the space occupancy rate of the driving lane L2 is equal to or greater than the space occupancy rate threshold set in advance in the storage device 3, and the time-average vehicle speed of the driving lane L2 is equal to or less than the time-average vehicle speed threshold set in advance in the storage device 3.

(Result output unit 15)
The result output unit 15 outputs the determination results obtained by the traffic condition determination unit 14 to the output device 4. For example, the determination results may include information indicating whether or not congestion has occurred for each driving lane. Alternatively, the determination results may include information indicating whether or not congestion has occurred for each lane, instead of or in addition to the determination results for each driving lane.

The above describes an example configuration of a congestion determination system according to the second embodiment of the present invention.

(2-2. Effects)
In the second embodiment of the present invention, it is assumed that a lane includes multiple driving lanes, as described above. In this case, the congestion determination device 1 according to the second embodiment of the present invention calculates the space occupancy rate and the hourly average vehicle speed for each driving lane, and determines whether congestion has occurred in the lane based on the space occupancy rate and the hourly average vehicle speed for each driving lane, thereby providing more detailed determination results than the first embodiment of the present invention.

Note that not all of the multiple driving lanes included in a lane need to be used to determine whether congestion has occurred in the lane. In other words, in the driving lane parameter 35b, only some of the multiple driving lanes included in the lane may be associated with the lane.

Therefore, the traffic line grouping unit 131 may group the traffic lines of each vehicle into units of one or more lanes, at least a portion of the multiple lanes included in the lane, and extract the traffic lines of the vehicle for each lane. This makes it possible to exclude desired lane(s) from the lane(s) that are used to determine whether congestion has occurred in the lane.

Figure 20 is a diagram illustrating the effects of the second embodiment of the present invention. Figure 20 is an example of the road shown in Figure 2 viewed from above, with the rectangles in the figure representing the top surfaces of vehicles C11 to C13, C21, and C22. For example, in lane K1, if driving lane L1 is congested but driving lane L2 is allowed for normal driving, it is considered that lane K1 does not need to be determined to be congested.

In the determination by the congestion determination unit 143 according to the first embodiment of the present invention, one traffic line group corresponds to one lane, and therefore the space occupancy rate and average vehicle speed per travel lane are not taken into consideration. Therefore, in road conditions such as those shown in Figure 2, the first embodiment of the present invention may erroneously determine whether or not congestion has occurred in lane K1.

On the other hand, according to the second embodiment of the present invention, one traffic line group corresponds to one driving lane, so the space occupancy rate and average vehicle speed per hour are taken into consideration for each driving lane. As a result, according to the second embodiment of the present invention, it is possible to more precisely determine whether congestion has occurred in a lane.

The above describes the second embodiment of the present invention.

(3. Hardware configuration example)
Next, an example of the hardware configuration of the traffic congestion determination device 1 according to the embodiment of the present invention will be described.

Below, an example of the hardware configuration of an information processing device 900 will be described as an example of the hardware configuration of a traffic congestion determination device 1 according to an embodiment of the present invention. Note that the example of the hardware configuration of the information processing device 900 described below is merely one example of the hardware configuration of the traffic congestion determination device 1. Therefore, the hardware configuration of the traffic congestion determination device 1 may be such that unnecessary components are deleted from the hardware configuration of the information processing device 900 described below, or new components may be added.

Figure 21 is a diagram showing the hardware configuration of an information processing device 900 as an example of a traffic congestion determination device 1 according to an embodiment of the present invention. The information processing device 900 includes a CPU (Central Processing Unit) 901, a ROM (Read Only Memory) 902, a RAM (Random Access Memory) 903, a host bus 904, a bridge 905, an external bus 906, an interface 907, an input device 908, an output device 909, a storage device 910, and a communication device 911.

The CPU 901 functions as an arithmetic processing device and control device, and controls the overall operation of the information processing device 900 in accordance with various programs. The CPU 901 may also be a microprocessor. The ROM 902 stores programs used by the CPU 901, calculation parameters, etc. The RAM 903 temporarily stores programs used in the execution of the CPU 901, and parameters that change as appropriate during the execution. These are interconnected by a host bus 904, which is composed of a CPU bus, etc.

The host bus 904 is connected to an external bus 906, such as a PCI (Peripheral Component Interconnect/Interface) bus, via a bridge 905. Note that the host bus 904, bridge 905, and external bus 906 do not necessarily need to be configured separately; these functions may be implemented on a single bus.

The input device 908 is composed of input means for the user to input information, such as a mouse, keyboard, touch panel, buttons, microphone, switches, and levers, and an input control circuit that generates input signals based on user input and outputs them to the CPU 901. By operating this input device 908, the user operating the information processing device 900 can input various data to the information processing device 900 and instruct processing operations.

The output device 909 includes, for example, display devices such as a CRT (Cathode Ray Tube) display device, a liquid crystal display (LCD) device, an OLED (Organic Light Emitting Diode) device, a lamp, and an audio output device such as a speaker.

The storage device 910 is a device for storing data. The storage device 910 may include a storage medium, a recording device that records data on the storage medium, a reading device that reads data from the storage medium, and a deletion device that deletes data recorded on the storage medium. The storage device 910 is configured, for example, with an HDD (Hard Disk Drive). This storage device 910 drives the hard disk and stores programs executed by the CPU 901 and various data.

The communication device 911 is, for example, a communication interface configured with a communication device for connecting to a network. Furthermore, the communication device 911 may support either wireless communication or wired communication.

The above describes an example of the hardware configuration of the congestion determination device 1 according to an embodiment of the present invention.

(4. Summary)
Although the preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings, the present invention is not limited to these examples. It is clear that a person skilled in the art to which the present invention pertains can conceive of various modifications and alterations within the scope of the technical ideas set forth in the claims, and it is understood that these also naturally fall within the technical scope of the present invention.

For example, the above description mainly covers the case where the congestion determination unit 143 determines whether or not a congestion has occurred based on both the space occupancy rate and the time-average vehicle speed. However, the congestion determination unit 143 does not necessarily need to use both the space occupancy rate and the time-average vehicle speed in its determination. For example, the congestion determination unit 143 may determine whether or not a congestion has occurred based on the space occupancy rate.

In more detail, the congestion determination unit 143 may determine whether congestion has occurred based on whether the space occupancy rate is equal to or greater than a space occupancy rate threshold set in advance in the storage device 3. For example, the congestion determination unit 143 may determine that congestion has occurred if the space occupancy rate is equal to or greater than a space occupancy rate threshold set in advance in the storage device 3. Alternatively, the congestion determination unit 143 may determine that congestion has not occurred if the space occupancy rate is below the space occupancy rate threshold set in advance in the storage device 3.

Alternatively, the traffic congestion determination unit 143 may determine whether traffic congestion has occurred based on whether the hourly average vehicle speed is equal to or less than a threshold value for the hourly average vehicle speed that has been set in advance in the storage device 3. The traffic congestion determination unit 143 may determine that traffic congestion has occurred if the hourly average vehicle speed is equal to or less than a threshold value for the hourly average vehicle speed that has been set in advance in the storage device 3. Alternatively, the traffic congestion determination unit 143 may determine that traffic congestion has not occurred if the hourly average vehicle speed exceeds a threshold value for the hourly average vehicle speed that has been set in advance in the storage device 3.

At this time, the time-average vehicle speed may be calculated taking into account the congestion determination area. That is, the time-average vehicle speed calculation unit 142 may calculate the time-average vehicle speed of one or more intruding vehicles into the congestion determination area based on the estimated speed of the one or more intruding vehicles into the congestion determination area. At this time, the congestion determination unit 143 may determine whether or not congestion has occurred based on the time-average vehicle speed of the intruding object.

Furthermore, the above description mainly focuses on an example in which the average flow line length calculation unit 133 calculates the average flow line length without taking into account the congestion determination area. However, the average flow line length calculation unit 133 may calculate the average flow line length by taking into account the congestion determination area. The average flow line length of an intruding object may be calculated based on the flow lines of one or more intruding vehicles into the congestion determination area. The space occupancy rate calculation unit 141 may then calculate the space occupancy rate based on the vehicle length of the intruding vehicle and the average flow line length of the intruding vehicle.

The above mainly describes an example in which the vehicle detection unit 121 creates vehicle information 32 based on the image 31 acquired from the imaging device 2. However, if sensor data is obtained from other sensors (such as an ultrasonic sensor), the congestion determination device 1 can also acquire data such as vehicle driving position, number of vehicles, and vehicle speed based on the sensor data obtained from the other sensors, and correct the vehicle information based on this acquired data. Alternatively, multiple sensors may be used depending on the calculation target. For example, the space occupancy rate may be calculated based on the image 31 acquired from the imaging device 2, and the time-average vehicle speed may be calculated based on ultrasonic waves acquired from an ultrasonic sensor.

Furthermore, the above description mainly focuses on an example in which the congestion determination unit 143 determines two states: a state in which congestion has occurred (a congestion state) and a state in which congestion has not occurred (a non-congestion state). However, the congestion determination unit 143 can also divide the congestion level into several stages. For example, the congestion determination unit 143 may determine three states: a congestion state, a crowded state, and a normal state.

REFERENCE SIGNS LIST 1 congestion determination device 11 video acquisition unit 12 vehicle information creation unit 121 vehicle detection unit 122 vehicle identification unit 123 vehicle classification unit 124 flow line extraction unit 125 vehicle speed estimation unit 126 vehicle length estimation unit 13 flow line statistics unit 131 flow line grouping unit 132 congestion determination area setting unit 133 average flow line length calculation unit 14 traffic situation determination unit 141 space occupancy rate calculation unit 142 hourly average vehicle speed calculation unit 143 congestion determination unit 15 result output unit 2 imaging device 3 storage device 4 output device

Claims (23)

a detection unit that detects one or more moving objects based on sensor data and obtains a detection result;
an extraction unit that extracts a flow line of the moving object based on the detection result;
a setting unit that sets a determination area based on the movement line of the moving object;
a determination unit that determines whether or not a traffic jam has occurred based on the flow line of the moving object and the determination area;
A congestion determination device comprising:
The determination unit
a space occupancy calculation unit that identifies one or more intruding objects that have invaded the determination area among the moving objects based on the detected positions of the moving objects and the determination area, and calculates a space occupancy that is the ratio of the intruding objects to the space based on the sizes of the intruding objects;
a congestion determination unit that determines whether or not the congestion has occurred based on the space occupancy rate;
Equipped with
The congestion determination device
a classification unit that identifies the type of the moving object based on the detection result;
a size estimation unit that estimates a size of the intruding object based on the type of the intruding object;
A congestion determination device comprising: a detection unit that detects one or more moving objects based on sensor data and obtains a detection result;
an extraction unit that extracts a flow line of the moving object based on the detection result;
a setting unit that sets a determination area based on the movement line of the moving object;
a determination unit that determines whether or not a traffic jam has occurred based on the flow line of the moving object and the determination area;
A congestion determination device comprising:
The determination unit
a space occupancy calculation unit that identifies one or more intruding objects that have invaded the determination area among the moving objects based on the detected positions of the moving objects and the determination area, and calculates a space occupancy that is the ratio of the intruding objects to the space based on the sizes of the intruding objects;
a congestion determination unit that determines whether or not the congestion has occurred based on the space occupancy rate;
Equipped with
the congestion determination device includes an average flow line length calculation unit that calculates an average flow line length of the moving object based on the flow line of the moving object;
the space occupancy calculation unit calculates the space occupancy based on a size of the intruding object and an average movement line length of the moving object;
Traffic congestion detection device. a detection unit that detects one or more moving objects based on sensor data and obtains a detection result;
an extraction unit that extracts a flow line of the moving object based on the detection result;
a setting unit that sets a determination area based on the movement line of the moving object;
a determination unit that determines whether or not a traffic jam has occurred based on the flow line of the moving object and the determination area;
A congestion determination device comprising:
The determination unit
a space occupancy calculation unit that identifies one or more intruding objects that have invaded the determination area among the moving objects based on the detected positions of the moving objects and the determination area, and calculates a space occupancy that is the ratio of the intruding objects to the space based on the sizes of the intruding objects;
a congestion determination unit that determines whether or not the congestion has occurred based on the space occupancy rate;
Equipped with
the congestion determination device includes an average flow line length calculation unit that calculates an average flow line length of one or more intruding objects that have invaded the determination area based on the detected positions of the moving objects and the determination area, and
the space occupancy calculation unit calculates the space occupancy based on a size of the intruding object and an average movement line length of the intruding object.
Traffic congestion detection device. the determination unit includes an average speed calculation unit that calculates an average speed of the moving object based on the estimated speed of the moving object;
the congestion determination unit determines whether the congestion has occurred based on the average speed of the moving object and the space occupancy rate;
The congestion determination device according to any one of claims 1 to 3 . The congestion determination unit determines whether the congestion has occurred based on whether the space occupancy rate is equal to or greater than a threshold.
The congestion determination device according to any one of claims 1 to 4 . a detection unit that detects one or more moving objects based on sensor data and obtains a detection result;
an extraction unit that extracts a flow line of the moving object based on the detection result;
a setting unit that sets a determination area based on the movement line of the moving object;
a determination unit that determines whether or not a traffic jam has occurred based on the flow line of the moving object and the determination area;
A congestion determination device comprising:
The determination unit
an average speed calculation unit that calculates an average speed of one or more intruding objects that have invaded the judgment area among the moving objects based on the flow line of the moving object and the judgment area;
a congestion determination unit that determines whether or not the congestion has occurred based on the average speed of the intruding object;
Equipped with
The congestion determination device includes a speed estimation unit that estimates a speed of the intruding object based on a path of movement of the intruding object and a transformation parameter that indicates a transformation from a length of the moving object in the sensor data to a length in real space, and obtains an estimated speed of the intruding object.
Traffic congestion detection device. the traffic congestion determination unit determines whether the traffic congestion has occurred based on whether the average speed of the intruding object is equal to or less than a threshold value.
The congestion determination device according to claim 6 . a detection unit that detects one or more moving objects based on sensor data and obtains a detection result;
an extraction unit that extracts a flow line of the moving object based on the detection result;
a setting unit that sets a determination area based on the movement line of the moving object;
a determination unit that determines whether or not a traffic jam has occurred based on the flow line of the moving object and the determination area;
A congestion determination device comprising:
The congestion determination device
an identification unit that identifies the detection results for each identical moving object based on the detection results;
the extraction unit extracts a flow line for each of the moving objects based on a detection result for each of the moving objects;
the setting unit sets the determination area based on a line of movement of each of the moving objects;
the determination unit determines whether the congestion has occurred based on the flow line of each moving object and the determination area.
Traffic congestion detection device. The movement area of the moving object is divided into a plurality of lines according to the direction of movement of the moving object,
the congestion determination device includes a flow line grouping unit that performs grouping of the flow lines of the moving objects in units of the plurality of lines to extract the flow lines of the moving objects for each line,
the setting unit sets the determination area for each line based on a line of movement of the moving object for each line;
the determination unit determines whether or not the congestion has occurred for each of the lines based on the line of movement of the moving object for each of the lines and the determination area.
The traffic congestion determination device according to any one of claims 1 to 8 . the line includes a plurality of lanes;
the flow line grouping unit performs grouping of the flow lines of the moving object in units of one or more lanes included in at least a portion of the plurality of lanes to extract the flow lines of the moving object for each lane;
the setting unit sets the determination area for each lane based on a line of movement of the moving object for each lane;
the determination unit determines whether or not the congestion has occurred for each lane based on the flow line of the moving object for each lane and the determination area.
The congestion determination device according to claim 9 . The traffic congestion determination device includes a result output unit that outputs a determination result indicating whether or not the traffic congestion has occurred.
The traffic congestion determination device according to any one of claims 1 to 10 . The sensor data is video data.
The traffic congestion determination device according to any one of claims 1 to 11 . The moving object is a vehicle.
The traffic congestion determination device according to any one of claims 1 to 12 . A congestion determination method executed by a congestion determination device,
detecting one or more moving objects based on the sensor data to obtain a detection result;
extracting a line of movement of the moving object based on the detection result;
setting a judgment area based on the movement line of the moving object;
determining whether or not a traffic jam has occurred based on the flow line of the moving object and the determination area;
Equipped with
The determining step includes:
a step of identifying one or more intruding objects that have invaded the judgment area among the moving objects based on the detected positions of the moving objects and the judgment area, and calculating a space occupancy rate that is a ratio of the intruding objects to the space based on the sizes of the intruding objects;
determining whether or not the congestion has occurred based on the space occupancy rate;
Equipped with
The congestion determination method includes:
identifying the type of the moving object based on the detection result;
estimating a size of the intruding object based on the type of the intruding object;
A congestion determination method comprising : A congestion determination method executed by a congestion determination device,
detecting one or more moving objects based on the sensor data to obtain a detection result;
extracting a line of movement of the moving object based on the detection result;
setting a judgment area based on the movement line of the moving object;
determining whether or not a traffic jam has occurred based on the flow line of the moving object and the determination area;
Equipped with
The determining step includes:
a step of identifying one or more intruding objects that have invaded the judgment area among the moving objects based on the detected positions of the moving objects and the judgment area, and calculating a space occupancy rate that is a ratio of the intruding objects to the space based on the sizes of the intruding objects;
determining whether or not the congestion has occurred based on the space occupancy rate;
Equipped with
The congestion determination method includes a step of calculating an average flow line length of the moving object based on the flow line of the moving object,
the step of calculating the space occupancy rate includes a step of calculating the space occupancy rate based on a size of the intruding object and an average movement line length of the moving object.
Method for determining congestion. A congestion determination method executed by a congestion determination device,
detecting one or more moving objects based on the sensor data to obtain a detection result;
extracting a line of movement of the moving object based on the detection result;
setting a judgment area based on the movement line of the moving object;
determining whether or not a traffic jam has occurred based on the flow line of the moving object and the determination area;
Equipped with
The determining step includes:
a step of identifying one or more intruding objects that have invaded the judgment area among the moving objects based on the detected positions of the moving objects and the judgment area, and calculating a space occupancy rate that is a ratio of the intruding objects to the space based on the sizes of the intruding objects;
determining whether or not the congestion has occurred based on the space occupancy rate;
Equipped with
The congestion determination method includes a step of calculating an average flow line length of one or more intruding objects that have invaded the determination area based on the detected positions of the moving objects and the determination area, and
the step of calculating the space occupancy rate includes a step of calculating the space occupancy rate based on a size of the intruding object and an average movement line length of the intruding object.
Method for determining congestion. A congestion determination method executed by a congestion determination device,
detecting one or more moving objects based on the sensor data to obtain a detection result;
extracting a line of movement of the moving object based on the detection result;
setting a judgment area based on the movement line of the moving object;
determining whether or not a traffic jam has occurred based on the flow line of the moving object and the determination area;
Equipped with
The determining step includes:
calculating an average speed of one or more intruding objects among the moving objects that have invaded the judgment area based on the flow line of the moving object and the judgment area;
determining whether the traffic jam has occurred based on an average speed of the intruding object;
Equipped with
The congestion determination method includes:
a step of estimating a speed of the intruding object based on a line of movement of the intruding object and a transformation parameter indicating a transformation from a length in the sensor data of the moving object to a length in real space, to obtain an estimated speed of the intruding object;
Method for determining congestion. A congestion determination method executed by a congestion determination device,
detecting one or more moving objects based on the sensor data to obtain a detection result;
extracting a line of movement of the moving object based on the detection result;
setting a judgment area based on the movement line of the moving object;
determining whether or not a traffic jam has occurred based on the flow line of the moving object and the determination area;
Equipped with
The congestion determination method includes:
a step of identifying the detection results for each of the same moving objects based on the detection results;
the extracting step includes a step of extracting a flow line for each of the moving objects based on a detection result for each of the moving objects;
the setting step includes a step of setting the determination area based on a flow line of each of the moving objects;
the determining step includes a step of determining whether or not the congestion has occurred based on the flow line of each of the moving objects and the determination area.
Method for determining congestion. Computer,
a detection unit that detects one or more moving objects based on sensor data and obtains a detection result;
an extraction unit that extracts a flow line of the moving object based on the detection result;
a setting unit that sets a determination area based on the movement line of the moving object;
a determination unit that determines whether or not a traffic jam has occurred based on the flow line of the moving object and the determination area;
and functioning as a congestion determination device comprising :
The determination unit
a space occupancy calculation unit that identifies one or more intruding objects that have invaded the determination area among the moving objects based on the detected positions of the moving objects and the determination area, and calculates a space occupancy that is the ratio of the intruding objects to the space based on the sizes of the intruding objects;
a congestion determination unit that determines whether or not the congestion has occurred based on the space occupancy rate;
Equipped with
The congestion determination device
a classification unit that identifies the type of the moving object based on the detection result;
a size estimation unit that estimates a size of the intruding object based on the type of the intruding object;
A program that includes : Computer,
a detection unit that detects one or more moving objects based on sensor data and obtains a detection result;
an extraction unit that extracts a flow line of the moving object based on the detection result;
a setting unit that sets a determination area based on the movement line of the moving object;
a determination unit that determines whether or not a traffic jam has occurred based on the flow line of the moving object and the determination area;
and functioning as a congestion determination device comprising :
The determination unit
a space occupancy calculation unit that identifies one or more intruding objects that have invaded the determination area among the moving objects based on the detected positions of the moving objects and the determination area, and calculates a space occupancy that is the ratio of the intruding objects to the space based on the sizes of the intruding objects;
a congestion determination unit that determines whether or not the congestion has occurred based on the space occupancy rate;
Equipped with
the congestion determination device includes an average flow line length calculation unit that calculates an average flow line length of the moving object based on the flow line of the moving object;
the space occupancy calculation unit calculates the space occupancy based on a size of the intruding object and an average movement line length of the moving object;
program. Computer,
a detection unit that detects one or more moving objects based on sensor data and obtains a detection result;
an extraction unit that extracts a flow line of the moving object based on the detection result;
a setting unit that sets a determination area based on the movement line of the moving object;
a determination unit that determines whether or not a traffic jam has occurred based on the flow line of the moving object and the determination area;
and functioning as a congestion determination device comprising :
The determination unit
a space occupancy calculation unit that identifies one or more intruding objects that have invaded the determination area among the moving objects based on the detected positions of the moving objects and the determination area, and calculates a space occupancy that is the ratio of the intruding objects to the space based on the sizes of the intruding objects;
a congestion determination unit that determines whether or not the congestion has occurred based on the space occupancy rate;
Equipped with
the congestion determination device includes an average flow line length calculation unit that calculates an average flow line length of one or more intruding objects that have invaded the determination area based on the detected positions of the moving objects and the determination area, and
the space occupancy calculation unit calculates the space occupancy based on a size of the intruding object and an average movement line length of the intruding object.
program. Computer,
a detection unit that detects one or more moving objects based on sensor data and obtains a detection result;
an extraction unit that extracts a flow line of the moving object based on the detection result;
a setting unit that sets a determination area based on the movement line of the moving object;
a determination unit that determines whether or not a traffic jam has occurred based on the flow line of the moving object and the determination area;
and functioning as a congestion determination device comprising :
The determination unit
an average speed calculation unit that calculates an average speed of one or more intruding objects that have invaded the judgment area among the moving objects based on the flow line of the moving object and the judgment area;
a congestion determination unit that determines whether or not the congestion has occurred based on the average speed of the intruding object;
Equipped with
The congestion determination device includes a speed estimation unit that estimates a speed of the intruding object based on a path of movement of the intruding object and a transformation parameter that indicates a transformation from a length of the moving object in the sensor data to a length in real space, and obtains an estimated speed of the intruding object.
program. Computer,
a detection unit that detects one or more moving objects based on sensor data and obtains a detection result;
an extraction unit that extracts a flow line of the moving object based on the detection result;
a setting unit that sets a determination area based on the movement line of the moving object;
a determination unit that determines whether or not a traffic jam has occurred based on the flow line of the moving object and the determination area;
and functioning as a congestion determination device comprising:
The congestion determination device
an identification unit that identifies the detection results for each identical moving object based on the detection results;
the extraction unit extracts a flow line for each of the moving objects based on a detection result for each of the moving objects;
the setting unit sets the determination area based on a line of movement of each of the moving objects;
the determination unit determines whether the congestion has occurred based on the flow line of each moving object and the determination area.
program.