JP7303852B2 - Determination device, program, and determination method - Google Patents

Description

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

Patent Literature 1 describes a technique for counting the number of people waiting to register based on an image captured by a camera.
[Prior art documents]
[Patent Literature]
[Patent Document 1] JP 2019-145022 A

According to one embodiment of the present invention, a determination device is provided. The determination device may include a captured image storage unit that stores captured images. The determination device may include a detection target detection unit that detects a predetermined detection target from the captured image. The determination device may include a specified region acquisition unit that acquires a specified region specified by a user of the determination device with respect to the captured image. The determination device determines whether or not the ratio of the overlap region, which is the region where the detection target region and the specified region overlap, to the detection target region, which is the region including the detection target, is higher than a predetermined overlap ratio threshold. It may be provided with an area determination unit for determining. The determining device counts the detection target when the area determination unit determines that the ratio of the overlap area to the detection target area is higher than the overlap ratio threshold, and determines the area when the ratio of the overlap area to the detection target area is lower than the overlap ratio threshold. A detection object count unit may be provided that does not count the detection objects when the unit determines.

The determination device may further include a situation determination section that determines a situation of the specified area based on the number of detection targets counted by the detection target counting section. The situation determination unit may determine that the designated area is in a used state when the detection target counting unit counts the detection targets. The situation determination unit may determine that the specified area is in a congested state when the number of detection targets counted by the detection target counting unit is greater than a predetermined congestion threshold. The captured image storage unit may store the captured image and the angle of view at which the captured image is captured in association with each other. The determination device may further include a congestion threshold setting unit that sets the congestion threshold based on the angle of view. The determination device may further include a congestion threshold setting unit that sets the congestion threshold based on the size of the designated area.

The specified area acquiring unit may acquire the specified area specified by the user as a prohibited area in which the presence of the detection target is prohibited. The situation determination section may determine that the detection target exists in the prohibited area when the detection target counting section counts the detection target. The captured image storage unit may store a plurality of captured images. The determination device may further include a captured image analysis unit that analyzes the captured image. The determination device is a candidate for determining a candidate area that is a candidate area for the specified area based on an analysis result obtained by analyzing the plurality of captured images stored in the captured image storage unit by the captured image analysis unit. A region determination unit may be further provided. The determination device may further include a candidate area presenting unit that presents the candidate areas to the user.

The specified area acquisition unit may acquire a plurality of specified areas specified by the user with respect to the captured image. The area determination unit may determine, for each designated area of the plurality of designated areas, whether or not a ratio of the overlap area to the detection target area is higher than the overlap ratio threshold. The detection target counting unit counts the detection targets when the region determination unit determines that the ratio of the overlap region to the detection target region is higher than the overlap ratio threshold for each of the specified regions, and counts the detection targets. The detection target may not be counted when the area determination unit determines that the ratio of the overlap area to the area is lower than the overlap ratio threshold. The detection target detection unit may detect the detection target that continues to be in a stopped state for a predetermined period. The detection target detection unit may detect a person as the detection target. The detection target detection unit may detect a vehicle as the detection target.

According to one embodiment of the present invention, there is provided a program for causing a computer to function as the determination device.

According to one embodiment of the present invention, a computer-implemented method of determination is provided. The determination method may include a detection step of detecting a predetermined detection target from the captured image. The determination method may comprise a designated area obtaining step of obtaining a designated area designated by a user of the computer for the captured image. The determination method is to determine whether or not the ratio of the overlap region, which is the region where the detection target region and the specified region overlap, to the detection target region, which is the region including the detection target, is higher than a predetermined overlap ratio threshold. A region determination step may be provided to determine the The determination method counts the detection target when it is determined in the region determination step that the ratio of the overlapping region to the detection target region is higher than the overlap ratio threshold, and the region determination is performed when the ratio of the overlapping region to the detection target region is lower than the overlap ratio threshold. A detectable object counting step may be provided in which the detectable objects are not counted if determined in the step.

It should be noted that the above summary of the invention does not list all the necessary features of the invention. Subcombinations of these feature groups can also be inventions.

An example system 10 is shown schematically. An example of a captured image 400 is shown schematically. Another example of the captured image 400 is schematically shown. Another example of the captured image 400 is schematically shown. Another example of the captured image 400 is schematically shown. Another example of the captured image 400 is schematically shown. Another example of the captured image 400 is schematically shown. An example of the functional configuration of the determination device 100 is shown schematically. An example of the flow of processing by the determination device 100 is shown schematically. 1 schematically shows an example of a hardware configuration of a computer 1200 functioning as the determination device 100. FIG.

Assuming that the number of detection targets within a specified region specified by a user in a captured image is counted, a technique that can appropriately handle cases where the detection target straddles the boundary of the specified region is proposed. It is desirable to provide For example, the determination device according to the present embodiment can set the ratio of the overlap region, which is the region where the detection target region and the specified region overlap with respect to the detection target region in which the detection target exists in the captured image, to a predetermined overlap region. Count only detections above the percentage threshold.

Hereinafter, the present invention will be described through embodiments of the invention, but the following embodiments do not limit the invention according to the claims. Also, not all combinations of features described in the embodiments are essential for the solution of the invention.

FIG. 1 schematically illustrates an example system 10 . The system 10 has a determination device 100 . System 10 may include camera 200 . System 10 may include multiple cameras 200 . FIG. 1 shows an example in which system 10 includes one camera 200 .

The determination device 100 acquires a captured image. The determination device 100 acquires a captured image captured by the camera 200, for example. The determination device 100 acquires a captured image from the camera 200 by communicating with the camera 200 via the network 20, for example. Network 20 includes, for example, the Internet. The network 20 includes, for example, a LAN (Local Area Network). Network 20 may include a mobile communication network. The mobile communication network, for example, conforms to any of the 3G (3rd Generation) communication method, the LTE (Long Term Evolution) communication method, the 5G (5th Generation) communication method, and the 6G (6th Generation) communication method and later communication methods. may

The determination device 100 may acquire the captured image from the camera 200 by communicating directly with the camera 200 . The determination device 100 acquires a captured image from the camera 200 by wirelessly communicating with the camera 200, for example. Examples of wireless communication systems include Wi-Fi (registered trademark), Bluetooth (registered trademark), ZigBee (registered trademark), and the like. The determination device 100 may acquire the captured image from the camera 200 by wire communication with the camera 200 . Note that the determination device 100 may acquire a captured image captured by a camera incorporated in the determination device 100 .

A captured image is, for example, a still image. The captured image may be a moving image.

The determination device 100 acquires a specified region specified by the user of the determination device 100 with respect to the captured image. The user of the determination device 100 designates, for example, an area for which the number of detection targets 300 is desired to be grasped as the designated area. The user of the determination device 100 may be a person who directly uses the determination device 100 or a person who uses the service provided by the determination device 100 .

The determination device 100 detects a predetermined detection target 300 from the captured image. For example, the determination device 100 first counts the detection targets 300 in which the entire detection target region, which is a region including the detection targets 300, is included in the designated region. When there is a detection target region that partially overlaps with the specified region, the determination device 100 determines in advance, for example, the ratio of the overlapping region, which is the region where the detection target region and the specified region overlap, to the detection target region. It is determined whether or not to count the detection target 300 by determining whether or not it is higher than the overlapping ratio threshold.

Camera 200 may be any imaging device. Camera 200 is, for example, a network camera. Camera 200 may be a web camera.

Conventionally, the number of detection targets has been counted for the entire captured image, but there have been cases where detection targets that should not be counted are erroneously counted. The possibility of such erroneous detection can be reduced by adjusting the angle of view, position, etc. of the camera, but the adjustment of the camera becomes a burden on the user. On the other hand, the determination apparatus 100 according to the present embodiment counts the detection targets by limiting to the specified area specified by the user in the captured image, so detection targets that should not be counted are counted by mistake. can be reduced, and the need for camera adjustments can be reduced.

FIG. 2 schematically shows an example of a captured image 400. As shown in FIG. In the example shown in FIG. 2 , the captured image 400 includes a detection target area 310 and a detection target area 320 .

The determination device 100 detects a detection target region 310 and a detection target region 320 . The determination device 100 acquires the designated area 450 from the user of the determination device 100 . Here, the description will be continued assuming that the detection target regions 310 and 320 and the specified region 450 are rectangular regions.

Here, the feature amount of a rectangular area in the image coordinate system with the point O at the upper left corner of the captured image 400 as the origin is expressed as [x coordinate of the starting point of the area, y coordinate of the starting point of the area, length of the area in the x direction, y-direction length of the region]. The starting point of the region is, for example, the upper left corner point of the region. The size of the region is (the length of the region in the x direction)×(the length of the region in the y direction).

In FIG. 2, the feature amount of the detection target area 310 is [500, 200, 200, 500]. The starting point of the detection target area 310 is point A (500, 200), and the size of the detection target area 310 is 200×500.

In FIG. 2, the feature amount of the detection target area 320 is [1000, 400, 600, 300]. The starting point of the detection target area 320 is point B (1000, 400), and the size of the detection target area 320 is 600×300.

In FIG. 2, the feature amount of the designated area 450 is [100, 300, 1100, 600]. The starting point of the designated area 450 is the point S (100, 300), and the size of the designated area 450 is 1100×600.

The determination device 100 derives an overlapping area 315 where the detection target area 310 and the specified area 450 overlap from the detection target area 310 and the specified area 450 . In FIG. 2, the feature quantity of the overlapping area 315 is [500, 300, 200, 400]. The starting point of overlapping area 315 is point A'(500, 300), and the size of overlapping area 315 is 200×400.

The determination device 100 derives an overlapping region 325 where the detection target region 320 and the designated region 450 overlap from the overlapping region 325 and the designated region 450 . In FIG. 2, the feature quantity of the overlapping area 325 is [1000, 400, 200, 300]. The starting point of the overlapping area 325 is B(1000, 400) and the size of the overlapping area 325 is 200×300.

The determination device 100 derives the ratio of the overlap region 315 to the detection target region 310 from the size of the detection target region 310 and the size of the overlap region 315 . In FIG. 2, the size of the detection target area 310 is 200×500, and the size of the overlapping area 315 is 200×400. (200*500)*100=80%.

The determination device 100 derives the ratio of the overlap region 325 to the detection target region 320 from the size of the detection target region 320 and the size of the overlap region 325 . In FIG. 2, the size of the detection target area 320 is 600×300, and the size of the overlapping area 325 is 200×300. (600×300)×100≈33%.

The determination device 100 determines whether the ratio of the overlap region 315 to the detection target region 310 and the ratio of the overlap region 325 to the detection target region 320 are each higher than the overlap ratio threshold, thereby determining whether the detection target region 310 and the detection target region 310 It is determined whether or not each of the target regions 320 is treated as being positioned within the specified region. Here, the description will be continued assuming that the overlapping ratio threshold is 70%.

The determination device 100 determines that the detection target region 310 is positioned within the specified region because the ratio (=80%) of the overlap region 315 to the detection target region 310 is higher than the overlap ratio threshold (=70%). . In this case, the determination device 100 counts the detection targets included in the detection target region 310 . On the other hand, the determination device 100 treats the detection target region 320 as not being positioned within the designated region because the ratio of the overlap region 325 to the detection target region 320 (≈33%) is lower than the overlap ratio threshold (=70%). I judge. In this case, the determination device 100 does not count the detection targets included in the detection target region 320 .

FIG. 3 schematically shows another example of the captured image 400. As shown in FIG. A captured image 400 in FIG. 3 is a captured image of a conference room.

The user of the determination device 100 designates the designated area 450 from the captured image 400 to count the number of people in the conference room. The determination device 100 acquires the designated area 450 designated by the user.

The determination device 100 detects a detection target 301 , a detection target 302 , and a detection target 303 from the captured image 400 . Here, the detection target 301 and the detection target 302 are people in the conference room. On the other hand, the detection target 303 is a person outside the window 30 . That is, the detection target 303 is a person outside the conference room.

The determination device 100 counts the detection targets 301 whose detection target regions entirely overlap with the designated region 450 . Next, the determination device 100 determines whether to count each of the detection targets 302 and 303 whose detection target regions partly overlap with the designated region 450 . The determination device 100 determines to count the detection targets 302 whose detection target regions mostly overlap with the specified region 450 . The determination device 100 determines not to count detection targets 303 in which most of the detection target regions do not overlap with the designated region 450 .

Based on the determination result described above, the determination device 100 determines that the number of people in the conference room is two, the detection target 301 and the detection target 302 . The determination device 100 determines that the detection targets 303 whose detection target regions do not mostly overlap with the designated region 450 are not counted, thereby erroneously counting people outside the conference room that should not be counted. can be prevented.

FIG. 4 schematically shows another example of the captured image 400. As shown in FIG. A captured image 400 in FIG. 4 is a captured image of the vicinity of the supermarket cash register 40 .

The user of the determination device 100 designates the designated area 450 in order to count the number of people lined up at the register 40 . The determination device 100 acquires the designated area 450 designated by the user.

The determination device 100 detects a detection target 301 , a detection target 302 , a detection target 303 , and a detection target 304 from the captured image 400 . Here, the detection target 301 , the detection target 302 , and the detection target 303 are people standing in line at the register 40 . On the other hand, the detection target 304 is a person who is shopping.

The determination device 100 counts the detection targets 302 whose entire detection target region overlaps the specified region 450 . Next, the determination device 100 determines whether or not to count the detection targets 301, 303, and 304 whose detection target regions partly overlap with the designated region 450. FIG. The determination device 100 determines to count the detection targets 301 and the detection targets 303 whose detection target regions mostly overlap with the designated region 450 . The determination device 100 determines not to count detection targets 304 in which most of the detection target regions do not overlap with the designated region 450 .

Based on the determination results described above, the determination device 100 determines that the number of people lined up at the cash register 40 is three, the detection targets 301 , the detection targets 302 , and the detection targets 303 . The determination device 100 prevents erroneous counting of shoppers who should not be counted by determining that detection targets 304 whose detection target regions do not mostly overlap with the designated region 450 are not counted. be able to.

FIG. 5 schematically shows another example of the captured image 400. As shown in FIG. A captured image 400 in FIG. 5 is a captured image of a parking lot.

The user of the determination device 100 designates the designated area 450 from the captured image 400 to count the number of cars parked in the parking lot. The determination device 100 acquires the designated area 450 designated by the user.

The determination device 100 detects a detection target 351 , a detection target 353 , a detection target 354 , and a detection target 355 from the captured image 400 . Here, the detection target 351, the detection target 353, and the detection target 355 are cars parked in a parking lot. Detected object 354, on the other hand, is a car exiting a parking space.

The determination device 100 counts detection targets 351 , detection targets 353 , and detection targets 355 whose detection target regions entirely overlap with the designated region 450 . Next, the determination device 100 determines whether or not to count the detection targets 354 whose detection target regions partly overlap with the designated region 450 . The determination device 100 determines not to count detection targets 354 in which most of the detection target regions do not overlap with the designated region 450 .

Based on the determination results described above, the determination device 100 determines that the number of vehicles parked in the parking lot is three, that is, the detection targets 351 , 353 , and 355 . The determination device 100 erroneously counts a vehicle exiting a parking space that should not be counted by determining that the detection target 354 whose detection target region does not mostly overlap with the designated region 450 is not counted. can be prevented.

FIG. 6 schematically shows another example of the captured image 400. As shown in FIG. A captured image 400 in FIG. 6 is a captured image of a parking lot.

The user of the determination device 100 selects a designated region 451, a designated region 452, a designated region 453, a designated region 454, a designated region 455, and a designated region 456 in order to count the number of cars parked in the parking lot from the captured image 400. specify. The determination device 100 acquires the designated area 451, designated area 452, designated area 453, designated area 454, designated area 455, and designated area 456 designated by the user.

The determination device 100 detects a detection target 351 , a detection target 353 , a detection target 354 , and a detection target 355 from the captured image 400 . Here, the detection target 351, the detection target 353, and the detection target 355 are cars parked in a parking lot. Detected object 354, on the other hand, is a car exiting a parking space.

The determination device 100 determines a detection target 351 whose entire detection target region overlaps with the specified region 451, a detection target 353 whose entire detection target region overlaps with the specified region 453, and a detection target 353 whose entire detection target region is specified. Detected objects 355 that overlap region 455 are counted. Next, the determination device 100 determines whether or not to count the detection targets 354 whose detection target regions partly overlap with the designated region 450 . The determination device 100 determines not to count detection targets 354 in which most of the detection target regions do not overlap with the designated region 450 .

Based on the determination results described above, the determination device 100 determines that the number of vehicles parked in the parking lot is three, that is, the detection targets 351 , 353 , and 355 . The determination device 100 erroneously counts a vehicle exiting a parking space that should not be counted by determining that the detection target 354 whose detection target region does not mostly overlap with the designated region 454 is not counted. can be prevented.

FIG. 7 schematically shows another example of the captured image 400. As shown in FIG. A captured image 400 in FIG. 7 is a captured image of a road.

A user of the determination device 100 designates a designated area 450 as a no-parking zone in order to count the number of parking violation vehicles from the captured image 400 . The determination device 100 acquires the designated area 450 designated by the user.

The determination device 100 detects a detection target 351 , a detection target 353 , and a detection target 355 from the captured image 400 . Here, the detection target 351 is a car parked in a no-parking zone. On the one hand, detection object 353 and detection object 355 are cars in motion.

The determination device 100 counts the detection targets 351 whose entire detection target region overlaps the specified region 450 . Next, the determination device 100 determines whether or not to count the detection targets 353 whose detection target regions partly overlap with the designated region 450 . The determination device 100 determines not to count detection targets 353 in which most of the detection target regions do not overlap with the designated region 450 . The determination device 100 does not count detection targets 355 that do not entirely overlap with the designated region 450 .

Based on the determination results described above, the determination device 100 determines that the number of vehicles parked in the no-parking zone is one of the detection targets 351 . The determination device 100 prevents erroneous counting of running cars that should not be counted by determining that detection targets 353 whose detection target regions do not mostly overlap with the designated region 450 are not counted. be able to.

FIG. 8 schematically shows an example of the functional configuration of the determination device 100. As shown in FIG. The determination device 100 includes a captured image storage unit 102, a captured image acquisition unit 104, a display control unit 106, a detection target setting unit 107, a detection target detection unit 108, a specified area acquisition unit 110, a threshold storage unit 112, and an overlap ratio threshold setting unit. 114, an area determination unit 116, a detection target count unit 118, a situation determination unit 120, a situation notification unit 122, a congestion threshold setting unit 124, a captured image analysis unit 126, a candidate area determination unit 128, and a candidate area presentation unit 130. It should be noted that it is not essential for the determination device 100 to have all of these configurations.

The captured image storage unit 102 stores the captured image 400 . The captured image storage unit 102 stores, for example, a plurality of captured images 400 . The captured image storage unit 102 may store the captured image 400 in association with the angle of view at which the captured image 400 is captured.

The captured image 400 is, for example, an image of a conference room. A captured image 400 is, for example, an image captured around a supermarket cash register. The captured image 400 is, for example, an image captured around a shop or a toilet at an event venue. The captured image 400 is, for example, a captured image of a dangerous area or a restricted area in a factory. The captured image 400 is, for example, an image of a parking lot. The captured image 400 may be, for example, an image of a road.

The captured image acquisition unit 104 acquires the captured image 400 . The captured image acquisition unit 104 acquires the captured image 400 from the camera 200, for example. The captured image acquisition unit 104 may acquire the captured image 400 captured by the imaging unit included in the determination device 100 . The captured image acquisition unit 104 stores the acquired captured image 400 in the captured image storage unit 102 .

The display control unit 106 controls display on the display unit. The display control unit 106 controls display of the display unit to display the captured image 400, for example.

The display control unit 106 controls display of a display unit included in the determination device 100, for example. The display control unit 106 may control the display of the display unit of the communication terminal owned by the user of the determination device 100 . In this case, the display control unit 106 may transmit the captured image 400 to the communication terminal owned by the user of the determination device 100 . The display unit displays the captured image 400 under the control of the display control unit 106 .

A user of the determination device 100 is, for example, a manager of a conference room. A user of the determination device 100 is, for example, a manager of a supermarket. A user of the determination device 100 is, for example, a manager of an event site. A user of the determination device 100 is, for example, a factory manager. A user of the determination device 100 is, for example, a parking lot manager. A user of the determination device 100 may be a road manager.

A detection target setting unit 107 sets a detection target to be detected from the captured image 400 . The detection target setting unit 107 sets the detection target by, for example, receiving an input from the user of the determination device 100 using an input device included in the determination device 100 . The detection target setting unit 107 sets, for example, the detection target selected by the user from among the detection target options displayed on the display unit of the determination device 100 . The detection target setting unit 107 may set the detection target by receiving information for setting the detection target from the communication terminal owned by the user of the determination device 100 . The communication terminal, for example, displays options for the detection target and transmits information for setting the detection target selected by the user to the determination device 100 . Examples of detection target options include, but are not limited to, people and vehicles.

The detection target detection unit 108 detects the detection target set by the detection target setting unit 107 from the captured image 400 . The detection target detection unit 108 may specify a detection target region in which the detection target exists in the captured image 400 .

The detection target area may be an area of any shape. For example, a polygonal area. The detection target area is, for example, a rectangular area. The detection target area may be a circular area. The detection target area may be an elliptical area.

The detection target detection unit 108 detects, for example, a person as a detection target. The detection target detection unit 108 detects, for example, a car as a detection target.

The detection target detection unit 108 detects, for example, a detection target that continues to be in a stopped state for a predetermined period. A detection target that continues to be stationary for a predetermined period is, for example, a person standing in line. A detection target that continues to be stationary for a predetermined period of time may be a parked car.

The specified area acquisition unit 110 acquires a specified area 450 specified by the user of the determination device 100 with respect to the captured image 400 . The specified area acquisition unit 110 acquires the specified area 450 by, for example, receiving input from the user of the determination device 100 using an input device included in the determination device 100 . The specified area acquiring unit 110 may acquire the specified area 450 by receiving the specified area 450 from the communication terminal owned by the user of the determination device 100 .

The specified area acquisition unit 110 acquires, for example, one specified area 450 specified by the user of the determination device 100 from the captured image 400 . The specified area acquisition unit 110 may acquire a plurality of specified areas 450 specified by the user of the determination device 100 with respect to the captured image 400 .

The specified area acquisition unit 110 may acquire the specified area 450 specified by the user of the determination device 100 as a prohibited area in which presence of the detection target is prohibited. Restricted areas are, for example, hazardous areas or restricted areas of a factory. The prohibited area may be a no parking area.

Designated area 450 may be an area of any shape. The designated area 450 is, for example, a polygonal area. The designated area 450 is, for example, a rectangular area. Designated area 450 may be a circular area. Designated area 450 may be an elliptical area.

The threshold storage unit 112 stores thresholds. The threshold storage unit 112 stores, for example, an overlap ratio threshold that is a threshold for determining whether to count detection targets. The threshold storage unit 112 may store a congestion threshold that is a threshold for determining the congestion state of the designated area 450 .

The overlap ratio threshold setting unit 114 sets an overlap ratio threshold. The overlap ratio threshold setting unit 114 sets the overlap ratio threshold by, for example, receiving input from the user of the determination device 100 using an input device included in the determination device 100 . The overlap ratio threshold setting unit 114 may set the overlap ratio threshold by receiving information for setting the overlap ratio threshold from the communication terminal owned by the user of the determination device 100 . The overlap ratio threshold setting unit 114 stores the set overlap ratio threshold in the threshold storage unit 112 .

The area determination unit 116 determines whether the ratio of the specified area 450 to the detection target area of the detection target is higher than the overlapping ratio threshold value stored in the threshold storage unit 112 . For example, when the user of the determination device 100 designates a plurality of designated regions 450 in the captured image 400, the region determination unit 116 determines, for each designated region of the plurality of designated regions, the ratio of the overlapping region to the detection target region is It is determined whether or not it is higher than the overlapping ratio threshold.

The detection target counting unit 118 counts the detection targets. For example, the detection target counting unit 118 counts detection targets in which the entire detection target region includes the specified region 450 .

The detection target counting unit 118 determines whether or not to count detection targets whose detection target regions partly overlap with the specified region 450 based on the determination result of the determination of the specified region 450 by the region determination unit 116 . For example, the detection target counting unit 118 counts the detection target when the region determination unit 116 determines that the ratio of the overlapping region to the detection target region is higher than the overlap ratio threshold, and the ratio of the overlapping region to the detection target region reaches the overlap ratio. If the region determination unit 116 determines that the threshold is lower than the threshold, the detection target is not counted.

For example, the detection target count unit 118 counts the detection targets when the region determination unit 116 determines that the ratio of the overlap region to the detection target region is the same as the overlap ratio threshold. The detection target counting unit 118 does not have to count the detection targets when the region determination unit 116 determines that the ratio of the overlap region to the detection target region is the same as the overlap ratio threshold.

When the user of the determination device 100 designates a plurality of specified regions 450, the detection target counting unit 118 counts the detection target regions based on the determination result of the region determination unit 116 determining each specified region 450 of the plurality of specified regions 450. It is determined whether or not to count detection targets that partially overlap with any of the plurality of specified regions 450 . For example, the detection target counting unit 118 counts the detection target when the region determination unit 116 determines that the ratio of the overlap region to the detection target region is higher than the overlap ratio threshold for each specified region, and counts the detection target region. is lower than the overlap ratio threshold value, detection targets are not counted.

The status determination unit 120 determines the status of the designated area 450 . The status determination unit 120 determines the status of the specified region 450 based on the number of detection targets counted by the detection target counting unit 118, for example.

The status determination unit 120 determines the usage status of the designated area 450, for example. For example, when the detection target count unit 118 counts the detection targets, the status determination unit 120 determines that the designated area 450 is in the use state.

The usage state is, for example, a state in which a person exists in the designated area 450 when the detection target is a person. For example, when the detection target is a car, the usage state is a state where the car is parked in the designated area 450 .

The situation determination unit 120 determines, for example, the congestion status of the designated area 450 . For example, when the number of detection targets counted by the detection target counting unit 118 is greater than the congestion threshold value stored in the threshold storage unit 112, the status determination unit 120 determines that the designated area 450 is in a congested state.

The congestion state is, for example, a state in which a queue is generated in the designated area 450 when the detection target is a person. The congestion state is, for example, a state in which vehicles cannot be parked in the designated area 450 when the detection target is a vehicle.

The situation determination unit 120 may determine the situation of the prohibited area when the user of the determination device 100 designates the designated area as the prohibited area. For example, when the detection target counting unit 118 counts the detection targets, the situation determination unit 120 may determine that the detection target exists in the prohibited area.

A state in which the detection target exists in the prohibited area is, for example, a state in which the person is entering the prohibited area when the detection target is a person. A state in which the detection target exists in the prohibited area is, for example, a state in which the vehicle is parked in the prohibited area when the detection target is a car.

The status notification unit 122 notifies the status of the designated area 450 . The status notification unit 122 notifies the status of the specified area 450 by displaying the status of the specified area 450 on the display part of the determination device 100, for example. The status notification unit 122 notifies the status of the specified area 450 by, for example, transmitting the status of the specified area 450 to the communication terminal owned by the user of the determination device 100 . The status notification unit 122 notifies the status of the specified area 450 by, for example, uploading the status of the specified area 450 to an internal company site. The status notification unit 122 notifies the status of the specified area 450 by displaying the status of the specified area 450 on a display installed, for example, at the entrance of a building or parking lot. The status notification unit 122 may notify the status of the designated area 450 by broadcasting the status of the designated area 450 through in-house broadcasting.

The status notification unit 122 notifies, for example, the status of the specified area 450 determined by the status determination unit 120 . The status notification unit 122 notifies, for example, the usage status of the designated area 450 . The threshold storage unit 112 notifies the congestion status of the designated area 450, for example. The status notification unit 122 notifies, for example, that the detection target exists in the prohibited area. The status notification unit 122 may notify the number of detection targets counted by the detection target counting unit 118 .

The congestion threshold setting unit 124 sets a congestion threshold. The congestion threshold setting unit 124 sets the congestion threshold by, for example, receiving input from the user of the determination device 100 using an input device included in the determination device 100 . The congestion threshold setting unit 124 may set the congestion threshold by receiving information for setting the congestion threshold from the communication terminal owned by the user of the determination device 100 . The congestion threshold setting unit 124 stores the set congestion threshold in the threshold storage unit 112 .

The congestion threshold setting unit 124 sets the congestion threshold based on, for example, the angle of view stored in the captured image storage unit 102 in association with the captured image 400 . For example, the narrower the angle of view, the higher the congestion threshold setting unit 124 sets the congestion threshold.

The congestion threshold setting unit 124 may set the congestion threshold based on the size of the designated region 450, for example. The congestion threshold setting unit 124 sets the congestion threshold higher, for example, as the ratio of the specified region 450 to the region of the captured image 400 increases.

The captured image analysis unit 126 analyzes the captured image 400 stored in the captured image storage unit 102 . The captured image analysis unit 126 analyzes, for example, a plurality of captured images 400 stored in the captured image storage unit 102 . For example, when the detection target is a person, the captured image analysis unit 126 analyzes the plurality of captured images 400 to identify the positions and sizes of the plurality of matrix regions that occurred in the past.

Candidate area determination unit 128 determines candidate areas that are candidates for designated area 450 . The candidate area determination unit 128 determines the candidate area based on the analysis result of the captured image analysis unit 126 analyzing the plurality of captured images 400 stored in the captured image storage unit 102, for example. The candidate area determination unit 128 determines, for example, the average position and size of the plurality of matrix areas identified by analyzing the plurality of captured images 400 by the captured image analysis unit 126 as the candidate area.

Candidate area presenting section 130 presents the candidate area determined by candidate area determining section 128 to the user of determination device 100 . The candidate area presenting unit 130 presents the candidate area to the user of the determination device 100 by, for example, superimposing the candidate area on the captured image 400 displayed by the display unit.

FIG. 9 schematically shows an example of the flow of processing by the determination device 100. As shown in FIG. In FIG. 9, a state in which the designated area 450 is not designated is described as a start state.

In step (the step may be abbreviated as S) 102 , the specified area acquisition unit 110 acquires the specified area 450 specified by the user of the determination device 100 . The user of the determination device 100 specifies the specified region 450 while checking the captured image 400 captured in the past, for example.

In S104, the captured image acquisition unit 104 acquires a captured image. In S<b>106 , the detection target detection unit 108 detects a plurality of detection targets from the captured image 400 .

In S<b>108 , the area determination unit 116 determines whether or not the entire detection target area including the detection target is included in the specified area 450 . If the entire detection target area is included in the specified area 450, the process proceeds to S114. If the entire detection target area is not included in the specified area 450, the process proceeds to S110.

In S<b>110 , the specified area obtaining unit 110 determines whether or not part of the detection target area is included in the specified area 450 . If part of the detection target area is included in the specified area 450, the process proceeds to S112. If the entire detection target area is not included in the designated area 450, the process proceeds to S116.

In S112, the area determination unit 116 determines whether or not the ratio of the specified area 450 to the detection target area is higher than the overlapping ratio threshold. If the ratio of the designated area 450 to the detection target area is higher than the overlapping ratio threshold, the process proceeds to S114. If the ratio of the designated area 450 to the detection target area is lower than the overlapping ratio threshold, the process proceeds to S116.

In S114, the detection target count unit 118 counts the detection targets. In S116, the detection target counting unit 118 does not count detection targets.

In S<b>118 , the area determination unit 116 determines whether or not it has been determined whether the ratio of the designated area 450 to the detection target area is higher than the overlapping ratio threshold for all detection target areas. If all detection target areas have been determined, the process proceeds to S120. If all detection target areas have not been determined, the process returns to S108.

In S120, the detection target count unit 118 determines the number of detection targets counted in S114. After that, the process ends.

FIG. 10 schematically shows an example of a hardware configuration of a computer 1200 functioning as the determination device 100. As shown in FIG. Programs installed on the computer 1200 cause the computer 1200 to act as one or more "parts" of the apparatus of the above embodiments, or cause the computer 1200 to operate or perform operations associated with the apparatus of the above embodiments. Multiple "units" can be executed and/or the computer 1200 can be caused to execute the processes or steps of the processes according to the above embodiments. Such programs may be executed by CPU 1212 to cause computer 1200 to perform certain operations associated with some or all of the blocks in the flowcharts and block diagrams described herein.

Computer 1200 according to this embodiment includes CPU 1212 , RAM 1214 , and graphics controller 1216 , which are interconnected by host controller 1210 . Computer 1200 also includes input/output units such as communication interface 1222 , storage device 1224 , DVD drive 1226 , and IC card drive, which are connected to host controller 1210 via input/output controller 1220 . DVD drive 1226 may be a DVD-ROM drive, a DVD-RAM drive, and the like. Storage devices 1224 may be hard disk drives, solid state drives, and the like. Computer 1200 also includes legacy input/output units, such as ROM 1230 and keyboard 1242 , which are connected to input/output controller 1220 via input/output chip 1240 .

The CPU 1212 operates according to programs stored in the ROM 1230 and RAM 1214, thereby controlling each unit. Graphics controller 1216 retrieves image data generated by CPU 1212 into a frame buffer or the like provided in RAM 1214 or itself, and causes the image data to be displayed on display device 1218 .

Communication interface 1222 communicates with other electronic devices over a network. Storage device 1224 stores programs and data used by CPU 1212 within computer 1200 . DVD drive 1226 reads programs or data from DVD-ROM 1227 or the like and provides them to storage device 1224 . The IC card drive reads programs and data from IC cards and/or writes programs and data to IC cards.

ROM 1230 stores therein programs that are dependent on the hardware of computer 1200, such as a boot program that is executed by computer 1200 upon activation. Input/output chip 1240 may also connect various input/output units to input/output controller 1220 via USB ports, parallel ports, serial ports, keyboard ports, mouse ports, and the like.

The program is provided by a computer-readable storage medium such as DVD-ROM 1227 or IC card. The program is read from a computer-readable storage medium, installed in storage device 1224 , RAM 1214 , or ROM 1230 , which are also examples of computer-readable storage media, and executed by CPU 1212 . The information processing described within these programs is read by computer 1200 to provide coordination between the programs and the various types of hardware resources described above. An apparatus or method may be configured by implementing information operations or processing according to the use of computer 1200 .

For example, when communication is performed between the computer 1200 and an external device, the CPU 1212 executes a communication program loaded into the RAM 1214 and sends communication processing to the communication interface 1222 based on the processing described in the communication program. you can command. Under the control of the CPU 1212, the communication interface 1222 reads transmission data stored in a transmission buffer area provided in a recording medium such as a RAM 1214, a storage device 1224, a DVD-ROM 1227, or an IC card, and transmits the read transmission data. Data is transmitted to the network, or received data received from the network is written in a receive buffer area or the like provided on the recording medium.

In addition, the CPU 1212 causes the RAM 1214 to read all or necessary portions of files or databases stored in external recording media such as the storage device 1224, DVD drive 1226 (DVD-ROM 1227), IC card, etc. Various types of processing may be performed on the data. CPU 1212 may then write back the processed data to an external recording medium.

Various types of information, such as various types of programs, data, tables, and databases, may be stored on recording media and subjected to information processing. CPU 1212 performs various types of operations on data read from RAM 1214, information processing, conditional decisions, conditional branching, unconditional branching, and information retrieval, which are described throughout this disclosure and are specified by instruction sequences of programs. Various types of processing may be performed, including /replace, etc., and the results written back to RAM 1214 . In addition, the CPU 1212 may search for information in a file in a recording medium, a database, or the like. For example, when a plurality of entries each having an attribute value of a first attribute associated with an attribute value of a second attribute are stored in the recording medium, the CPU 1212 selects the first attribute from among the plurality of entries. search for an entry that matches the specified condition of the attribute value of the attribute, read the attribute value of the second attribute stored in the entry, and thereby determine the first attribute that satisfies the predetermined condition An attribute value of the associated second attribute may be obtained.

The programs or software modules described above may be stored in a computer-readable storage medium on or near computer 1200 . Also, a recording medium such as a hard disk or RAM provided in a server system connected to a dedicated communication network or the Internet can be used as a computer-readable storage medium, whereby the program can be transferred to the computer 1200 via the network. offer.

The blocks in the flowcharts and block diagrams in this embodiment may represent steps in the process in which the operations are performed or "parts" of the apparatus responsible for performing the operations. Certain steps and "sections" may be provided with dedicated circuitry, programmable circuitry provided with computer readable instructions stored on a computer readable storage medium, and/or computer readable instructions provided with computer readable instructions stored on a computer readable storage medium. It may be implemented by a processor. Dedicated circuitry may include digital and/or analog hardware circuitry, and may include integrated circuits (ICs) and/or discrete circuitry. Programmable circuits, such as Field Programmable Gate Arrays (FPGAs), Programmable Logic Arrays (PLAs), etc., perform AND, OR, EXCLUSIVE OR, NOT AND, NOT OR, and other logical operations. , flip-flops, registers, and memory elements.

A computer-readable storage medium may comprise any tangible device capable of storing instructions to be executed by a suitable device, such that a computer-readable storage medium having instructions stored thereon may be illustrated in flowchart or block diagram form. It will comprise an article of manufacture containing instructions that can be executed to create means for performing specified operations. Examples of computer-readable storage media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, and the like. More specific examples of computer readable storage media include floppy disks, diskettes, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory) , electrically erasable programmable read only memory (EEPROM), static random access memory (SRAM), compact disc read only memory (CD-ROM), digital versatile disc (DVD), Blu-ray disc, memory stick , integrated circuit cards, and the like.

The computer readable instructions may be assembler instructions, Instruction Set Architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state configuration data, or instructions such as Smalltalk, JAVA, C++, etc. any source or object code written in any combination of one or more programming languages, including object-oriented programming languages, and conventional procedural programming languages such as the "C" programming language or similar programming languages; may include

Computer readable instructions are used to produce means for a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, or programmable circuits to perform the operations specified in the flowchart or block diagrams. A general purpose computer, special purpose computer, or other programmable data processor, locally or over a wide area network (WAN) such as the Internet, etc., to execute such computer readable instructions. It may be provided in the processor of the device or in a programmable circuit. Examples of processors include computer processors, processing units, microprocessors, digital signal processors, controllers, microcontrollers, and the like.

Although the invention according to the present disclosure has been described above using the embodiments, the technical scope of the invention according to the present disclosure is not limited to the scope described in the above embodiments. It is obvious to those skilled in the art that various modifications or improvements can be made to the above embodiments. It is clear from the description of the scope of claims that forms with such modifications or improvements can also be included in the technical scope of the present invention.

The execution order of each process such as actions, procedures, steps, and stages in the devices, systems, programs, and methods shown in the claims, the specification, and the drawings is etc., and it should be noted that they can be implemented in any order unless the output of the previous process is used in the subsequent process. Regarding the operation flow in the claims, the specification, and the drawings, even if the description is made using "first," "next," etc. for convenience, it means that it is essential to carry out in this order. not a thing

10 system, 20 network, 30 window, 40 register, 100 determination device, 102 captured image storage unit, 104 captured image acquisition unit, 106 display control unit, 107 detection target setting unit, 108 detection target detection unit, 110 specified area acquisition unit , 112 threshold storage unit, 114 overlap ratio threshold setting unit, 116 area determination unit, 118 detection target counting unit, 120 situation determination unit, 122 situation notification unit, 124 congestion threshold setting unit, 126 captured image analysis unit, 128 candidate area determination Unit 130 Candidate area presenting unit 200 Camera 300 Detection target 301 Detection target 302 Detection target 303 Detection target 304 Detection target 310 Detection target area 315 Overlapping area 320 Detection target area 325 Overlapping area 351 detection target, 353 detection target, 354 detection target, 355 detection target, 400 captured image, 450 specified area, 451 specified area, 452 specified area, 453 specified area, 454 specified area, 455 specified area, 456 specified area, 1200 computer, 1210 host controller, 1212 CPU, 1214 RAM, 1216 graphic controller, 1218 display device, 1220 input/output controller, 1222 communication interface, 1224 storage device, 1226 DVD drive, 1227 DVD-ROM, 1230 ROM, 1240 input/output chip

Claims (16)

A determination device ,
a captured image storage unit that stores a plurality of captured images ;
a captured image analysis unit that analyzes a captured image;
Based on the analysis result obtained by the captured image analysis unit analyzing the plurality of captured images stored in the captured image storage unit, a candidate area, which is a candidate area for the specified area specified by the user of the determination device, is determined. a candidate area determination unit to determine;
a candidate area presentation unit that presents the candidate area to the user;
a detection target detection unit that detects a predetermined detection target from a captured image;
a specified area acquiring unit that acquires a specified area specified by the user with respect to the captured image;
Determining whether or not a ratio of an overlap area, which is an area where the detection target area and the specified area overlap, to a detection target area, which is an area including the detection target, is higher than a predetermined overlap ratio threshold. an area determination unit;
counting the detection target when the area determining unit determines that the ratio of the overlap area to the detection target area is higher than the overlap ratio threshold, and the ratio of the overlap area to the detection target area is higher than the overlap ratio threshold a detection target count unit that does not count the detection target when the area determination unit determines that the area is low ,
The candidate region determination unit determines the average position and size of the plurality of matrix regions identified by analyzing the plurality of captured images by the captured image analysis unit as the candidate region.
judgment device. 2. The determination device according to claim 1, further comprising a situation determination section that determines a situation of said specified area based on the number of said detection targets counted by said detection target counting section. 3. The determination device according to claim 2, wherein said status determination unit determines that said specified area is in a used state when said detection target counting unit counts said detection targets. 3. The determination according to claim 2, wherein the situation determining unit determines that the specified area is in a congested state when the number of detection targets counted by the detection target counting unit is greater than a predetermined congestion threshold. Device. The captured image storage unit stores the captured image and an angle of view of the captured image in association with each other,
The determination device further includes a congestion threshold setting unit that sets the congestion threshold based on the angle of view.
The determination device according to claim 4. The determination device according to claim 5, wherein the congestion threshold setting unit sets the congestion threshold higher as the angle of view is narrower. 5. The determination device according to claim 4, further comprising a congestion threshold setting unit that sets said congestion threshold based on the size of said designated area. The determination device according to claim 7, wherein the congestion threshold setting unit sets the congestion threshold higher as the ratio of the designated area to the area of the captured image increases. The specified area acquiring unit acquires the specified area specified by the user as a prohibited area in which the presence of the detection target is prohibited;
The situation determination unit determines that the detection target exists in the prohibited area when the detection target counting unit counts the detection target.
The determination device according to claim 2. The specified area acquisition unit acquires a plurality of specified areas specified by the user with respect to the captured image,
The area determination unit determines whether a ratio of the overlap area to the detection target area is higher than the overlap ratio threshold for each of the plurality of designated areas, and
The detection target counting unit counts the detection targets when the region determination unit determines that the ratio of the overlap region to the detection target region is higher than the overlap ratio threshold value for each of the specified regions, and counts the detection targets. The determination device according to any one of claims 1 to 9 , wherein the detection target is not counted when the area determining unit determines that the ratio of the overlapping area to the area is lower than the overlapping ratio threshold. The determination device according to any one of claims 1 to 10 , wherein the detection target detection unit detects the detection target that continues to be in a stopped state for a predetermined period. The determination device according to any one of claims 1 to 11 , wherein the detection target detection unit detects a person as the detection target. 13. The method of claim 1, wherein the captured image analysis unit analyzes the captured image in order to specify the position and size of a queue area formed by people standing in line in the captured image that occurred in the past. A determination device according to any one of claims 1 to 3. The determination device according to any one of claims 1 to 11 , wherein the detection target detection unit detects a vehicle as the detection target. A program for causing a computer to function as the determination device according to any one of claims 1 to 14 . A computer-implemented determination method comprising :
an analysis step of analyzing a plurality of captured images stored in the computer;
a determination step of determining a candidate area, which is a candidate area for a specified area specified by a user of the computer, based on the analysis result obtained by analyzing the plurality of captured images in the analysis step;
a presenting step of presenting the candidate area to the user;
a detection step of detecting a predetermined detection target from the captured image;
a specified area acquiring step of acquiring a specified area specified by the user with respect to the captured image;
Determining whether or not a ratio of an overlap area, which is an area where the detection target area and the specified area overlap, to a detection target area, which is an area including the detection target, is higher than a predetermined overlap ratio threshold. a region determination step;
counting the detection target when it is determined in the region determination step that the ratio of the overlap region to the detection target region is higher than the overlap ratio threshold, and the ratio of the overlap region to the detection target region is higher than the overlap ratio threshold and a detection target counting step in which the detection target is not counted when it is determined in the region determination step that it is low ,
The determining step includes determining the average position and size of the plurality of matrix regions identified by analyzing the plurality of captured images in the analyzing step as the candidate region,
judgment method.

Images