JP2970028B2 - Vehicle dynamics measurement device - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention measures the speed of vehicles, the number of vehicles passing, and the traffic information such as the type of small vehicles and large vehicles, and measures vehicle dynamics for obtaining collected vehicle dynamics data. Related to the device.

[0002]

2. Description of the Related Art Conventionally, a vehicle dynamics measuring apparatus of this type processes an original image data and a background data obtained by photographing a trend of a vehicle on a road, and processes the speed, the number of vehicles passing, and the size of a small vehicle or a large vehicle. It is configured to measure the vehicle type and the like and output the information.

Further, the vehicle speed is obtained by extracting the front edge of the vehicle and calculating the amount of movement of the front edge, that is, the difference between the current front edge position and the previous front edge position, and the processing time. .

[0004]

However, in the above-mentioned conventional vehicle dynamics measuring device, if the vehicle cannot be temporarily extracted during the tracking of the vehicle, the tracking and the measurement are terminated. If the vehicle can be extracted, tracking and measurement will be started as a new vehicle, and there is a problem that vehicle information of the same vehicle is recorded as data of two vehicles.

[0005] In addition, if the extraction of the front edge of the vehicle is temporarily shifted from the actual front edge position, the speed of the vehicle may be immediately affected.

[0006] The present invention is to solve the above problems,
It is an object of the present invention to provide an excellent vehicle dynamics measurement device capable of accurately measuring traffic information such as the vehicle speed, the number of vehicles passing therethrough, and the types of small vehicles / large vehicles and obtaining collected vehicle dynamics data.

[0007]

SUMMARY OF THE INVENTION In order to achieve the above-mentioned object, the present invention relates to a vehicle type or the like of a vehicle to which an individual number has been previously assigned.
Store vehicle information and obtain from vehicle in new original image data
By comparing vehicle information, you can determine whether or not the vehicle is the same.
It is something that has been done.

In addition, an accurate vehicle speed is calculated for each processing screen based on the position information of the past several screens for each processing screen, and the speeds are weighted and smoothed.

[0009]

The present invention has the following functions by the above-mentioned structure.

By being able to store vehicle information in time series,
Vehicle information and ratios obtained from vehicles in the new original image data
In comparison, if the vehicle was taken in the past, it can be tracked.
And double detection can be prevented. Also, be it a new vehicle
For example, an individual number can be assigned and managed.

Further, even if the actual position of the vehicle front edge is temporarily shifted from the actual position, the computer can minimize the influence on the speed measurement and perform accurate tracking and measurement processing. Further, even when the vehicle cannot be temporarily extracted, the tracking and the measurement of the vehicle can be continued without interruption, and more accurate measurement and collection of the vehicle information can be performed.

[0012]

Embodiments of the present invention will be described below in detail with reference to the drawings.

FIG. 1 shows the configuration of the embodiment. In FIG. 1, 11 is a video camera, 12 is a vehicle dynamics measurement device main body, 13 is an image memory (input image 1), 14 is an image memory (input image 2), 15 is an image memory (input image 3), and 16 is an image Memory (input image 4), 17 is A / D
A conversion unit, 18 is an image data processing unit, 19 is a data input / output unit, and 20 is a computer.

Next, the operation of the above configuration will be described. In the above embodiment, the video information (signal) obtained by imaging the vehicle M on the road is transmitted to the vehicle dynamics measurement device main body 12 using the video camera 11.

The vehicle dynamics measuring device main body 12 converts the supplied video information into digital data (signal) using an A / D converter 17.

Then, digital data for two screens captured at certain intervals are stored in the image memories 13 and 14. The image memory 15 stores background data (signal) in a state where no vehicle exists.

The image memories 13, 14, 1
The image data processing unit 18 performs image processing using the data of No. 5, writes a processing result in the image memory 16, and extracts a vehicle from the image data. By continuously processing the extraction of the vehicle, vehicle dynamics data such as vehicle tracking and running speed are output from the data input / output unit 19,
The state on the current road is determined, and the background data is updated based on this information.

The image data of the image memory 16 is transferred to a computer 20 connected to the data input / output unit 19, and the computer 20 analyzes the vehicle dynamics data in detail. Next, the vehicle information storage process will be described.

FIG. 2 shows the processing of the vehicle information. First, a vehicle is extracted from the image data in the image memory by a frame difference, a background difference, a differentiation process or the like (step 21).

Next, the position of the front edge of the vehicle is extracted from the vehicle extraction data (step 22). Then, the front edge position is compared with the vehicle information up to the previous time, and it is determined whether or not this data is for a vehicle that is already being tracked (step 24).

If the determination is No for the first vehicle, the tracking result, that is, the position of the leading edge, the vehicle width, and the positions of both ends of the vehicle in the measurement area of the vehicle are measured (step 25). . Then, a new ID number (individual number) is assigned (step 26). Then, it is newly created as vehicle information in the memory area designated by the ID number (step 27).

If the front edge is determined to be that of the vehicle being tracked from the vehicle information in step 24,
First, the current tracking result is measured (step 28),
This data is added as vehicle information to a memory area specified by the ID number of the tracked vehicle (step 2).
9). This is performed for all the extracted leading edges (step 23).

As described above, vehicle information can be stored in a memory in a time-series manner.
0, and the computer 20 can analyze the dynamics of the vehicle in more detail.

Further, when the vehicle cannot be temporarily extracted based on this data, the vehicle dynamics can be predicted and the measurement of the vehicle can be continued.

Next, a process for calculating a vehicle speed from the above-mentioned vehicle dynamic data will be described. FIG. 3 shows the amount of movement of the leading edge position in the processing result. At this time, 1
It is assumed that three screens are processed per second.

In FIG. 3, n, n-1, n-2,..., N-7
Is the processing screen number, _1n , _1n-1 , _1n-2 , ..., _1n-7
Are the distances d _n , d from the measurement end area to the front edge of the vehicle
_n-1 , dn _-2 , dn _-3 , dn _-4 are the distances that the front edge of the vehicle has moved per second. First, the distance d advanced in one second
_n is expressed by the following equation (1) for the processing screen n. d _n = 1 _n−3 −1 _n (1) Accordingly, the vehicle speed v _n at this time is expressed by the following equation (2). _{v n [km / h] =} d n /1[sec]*3.6 ... (2) Then, the processing of the vehicle speed calculation screen n-1, n-2, n-3, also moves the n-4 distance d _n , D _n−1 , d _n−2 , d _n−3 , d _n−4
And the respective vehicle speeds are referred to as v _n , v _n-1 , v
_n-2 , v _n-3 and v _n-4 . Then, using these vehicle speeds, the vehicle speed v at the time of the screen n is expressed by the following equation (3). _{v n [km / h] =} (8 * v n +4 * v n-1 +2 * v n-2 + v n-3 + v n-4) / 16 ... (3) weighted in this manner to each speed of the After that, the vehicle speed v at the time of the screen n can be obtained by smoothing.

Next, a process for calculating the vehicle speed from the vehicle information storage will be described. FIG. 4 shows this vehicle speed calculation process.

First, a vehicle is extracted from the image memory in the image memory by a frame difference, a background difference, a differentiation process or the like (step 41). Next, the position of the front edge of the vehicle is extracted from the vehicle extraction data (step 42). Next, the aforementioned vehicle information storage processing is performed (step 43),
The tracking result (the position of the leading edge, the width of the vehicle, and the positions of both ends of the vehicle in the measurement area of the vehicle) is stored as vehicle information. And
Based on this information, the vehicle speed is calculated for each tracked vehicle (step 44).

As described above, even if the actual position of the front edge of the vehicle is temporarily shifted from the actual position, the influence on the speed measurement can be minimized, and accurate tracking and measurement processing can be performed. it can. Further, the vehicle speed calculation is performed from the vehicle information storage, and the vehicle prediction tracking based on the calculation will be described.

FIG. 5 shows the process of this vehicle prediction tracking. First, a vehicle is extracted from the image data in the image memory by a background difference of a frame difference, a differentiation process, and the like (step 51). Next, the position of the front edge of the vehicle is extracted from the vehicle extraction data (step 52).

Next, the above-described vehicle information storage processing is performed (step 53), and the tracking result, that is, the position of the front edge, the vehicle width, and the positions of both ends of the vehicle in the measurement area of the vehicle are stored as vehicle information. Then, it is determined whether the vehicle has been tracked this time, that is, whether the leading edge of the vehicle has been extracted (step 56). If tracking is not possible, the unextracted counter stored in the vehicle information of each ID number is incremented (step 57). It is determined whether or not it is (step 58). If Yes three times or less, the current position and speed are estimated from the vehicle information (vehicle position data) up to the previous time and the vehicle speed calculated using the above-described vehicle speed calculation (step 60), and the tracked vehicle is calculated. Is added as vehicle information to the memory area designated by the ID number (step 61). If unextracted four consecutive times No
In the case of, the ID number is deleted and the memory area storing the vehicle information is cleared (step 59).

In step 56, Ye which could be tracked this time
In the case of s, the unextracted counter is cleared (step 6).
2). This is performed for all vehicles to which an ID number is assigned (steps 54, 55, 63).

As described above, even when the vehicle cannot be extracted temporarily, the tracking and measurement of the vehicle can be continued.

Further, since vehicle tracking and measurement can be continued without interruption, vehicle dynamic data can be obtained by more accurate measurement and collection of vehicle information.

[0035]

As is clear from the above embodiment, the present invention assigns an individual number to a tracked and measured vehicle, and the tracking result, that is, the position, speed, acceleration, and position of both ends of the vehicle in the measurement area. . Thus to series stored when the vehicle type or the like as vehicle information, new computer
By comparing the stored vehicle information with the stored data,
This has the effect that the vehicle can be determined .

Further, an accurate vehicle speed is stored since a one-second speed is calculated for each processing screen from the position information of the past several screens, and the speeds are weighted and smoothed. When the vehicle cannot be temporarily extracted based on the data, it is possible to predict the dynamic state of the vehicle by the computer and to continue the measurement of the vehicle.
Furthermore, even if there is a temporary deviation from the actual position in the extraction of the front edge of the vehicle, the computer can minimize the effect on the speed measurement and perform accurate tracking and measurement processing. Even if the target vehicle cannot be extracted, the vehicle tracking and measurement can be continued without interruption.
There is an effect that more accurate measurement and collection of vehicle information can be performed.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a configuration of one embodiment of a vehicle dynamics measurement device according to the present invention.

FIG. 2 is a flowchart showing a process of storing vehicle information in the embodiment.

FIG. 3 is a diagram illustrating a movement amount of a leading edge position in a processing result, which is provided for describing an operation of the embodiment.

FIG. 4 is a flowchart illustrating a vehicle speed calculation process according to the embodiment;

FIG. 5 is a flowchart showing a vehicle prediction tracking process in the embodiment.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 11 Video camera, 12 Vehicle dynamics measurement device main body, 13, 14, 15, 16 Image memory 17 A / D conversion part, 18 Image data processing part 19 Data input / output part 20 Computer

Claims (3)

(57) [Claims] 1. A video camera for outputting image information of a vehicle on a road, and original image data and a vehicle
A storage means for storing both non-existent background data, image processing and analysis of the stored original image data or background data, measuring the speed and the number of vehicles passing and the type of vehicle,
Image processing means for outputting as vehicle information; means for extracting a tracked vehicle in time series from the vehicle information and assigning an individual number to each tracked vehicle; and a leading edge of the vehicle in a measurement area for each tracked vehicle. Means for storing vehicle information such as position, vehicle width, position change of both ends of the vehicle , and assigned individual numbers in a time-series manner ;
Processing the image information stored by the storage means,
Vehicle information stored in chronological order with the vehicle in the original image data
A vehicle dynamics measurement device, comprising: a computer for comparing the same vehicle and determining the same vehicle . 2. Based on the position information of the leading edge of the tracked vehicle in the past several screens measured by the image processing means and stored in the storage means, the computer calculates the position of each tracked vehicle for one second from the position information based on the position information. Means for processing and calculating the speed for each screen, and means for weighting each of the calculation results of the speed, leveling and calculating the vehicle speed by leveling,
The vehicle dynamics measurement device according to claim 1, wherein the vehicle speed is obtained from the vehicle information measured by the means. 3. When the tracking and measurement of a vehicle is temporarily interrupted, the vehicle tracking is performed by predicting the dynamics of the vehicle from the vehicle speed obtained from the measured data when the vehicle is not interrupted and continuing the tracking. The vehicle dynamics measurement device according to claim 2, wherein: