TW202241114A - Method for determining degree of crowding in vehicle, and system for determining degree of crowding in vehicle - Google Patents

Abstract

This method for determining the degree of crowding in a vehicle comprises: a step for acquiring an image obtained by capturing the interior 101 of a vehicle transporting passengers; a step for detecting people P3, P4, P5 from the image and generating, for the detected people, rectangular detection regions DA3, DA4, DA5 that surround the people, respectively; and a step for determining the degree of crowding in the vehicle on the basis of a subject region Tg of the image and the detection regions DA3, DA4, DA5. The subject region is a partial region of the image, and a region in which passengers standing in an aisle 103 of the vehicle are imaged. In the determining step, the degree of crowding in the vehicle is determined on the basis of the number of detection regions that overlap with the subject region.

Description

Vehicle congestion degree judgment method, and vehicle congestion degree judgment system

The present invention relates to a vehicle congestion degree judging method and a vehicle congestion degree judging system.

Heretofore, there have been devices for monitoring the number of occupants of a vehicle. Patent Document 1 discloses a vehicle occupancy monitoring device that includes a first imaging device and a processing unit, is installed in a vehicle body, and monitors the number of occupants in the vehicle body. The motion detection module of Patent Document 1 determines that there is a person in the identification block when the image variation value is greater than the threshold value.

[Prior Art Literature] [Patent Document] [Patent Document 1] JP-A-2015-7953

[Problems to be Solved by the Invention] From the viewpoint of countermeasures against infectious diseases such as the new coronavirus (COVID-19) in recent years (coronavirus infection/post-coronavirus infection), technology that can appropriately determine the degree of congestion of vehicles transporting passengers is also desired. For example, even when many passengers are standing on the aisle, it is preferable to appropriately determine the degree of congestion based on the captured in-vehicle images.

An object of the present invention is to provide a vehicle congestion degree determination method and a vehicle congestion degree determination system which can appropriately determine the congestion degree of vehicles transporting passengers.

[Means to solve the problem] The method for judging vehicle congestion degree of the present invention is characterized in that it includes: the step of obtaining the photographed in-vehicle image of the vehicle transporting passengers, detecting people from the aforementioned image, and generating a rectangle surrounding the person for each detected aforementioned person The step of detecting the detection area, and the step of determining the degree of congestion of the aforementioned vehicle based on the target area of the aforementioned image and the aforementioned detection area, the aforementioned target area is a part of the aforementioned image, and is where passengers standing on the aisle of the aforementioned vehicle are captured For the captured area, in the determining step, the degree of congestion of the vehicles is determined based on the number of the detection areas overlapping with the target area.

[Effect of Invention] The method for judging the degree of congestion of a vehicle according to the present invention includes: detecting a person from an image and generating a rectangular detection area surrounding the person for each detected person; A step of determining the degree of congestion of vehicles. The target area is a part of the image, and is an area in which a passenger standing on the aisle of the vehicle is photographed. In the determining step, the degree of congestion of vehicles is determined based on the number of detection areas overlapping with the target area. According to the method of judging the degree of congestion of vehicles related to the present invention, it is possible to appropriately determine the degree of congestion of vehicles transporting passengers.

Hereinafter, the vehicle congestion level judging method and the vehicle congestion level judging system according to the embodiments of the present invention will be described in detail with reference to the drawings. In addition, this invention is not limited by this embodiment. In addition, among the components in the following embodiments, those with ordinary knowledge in the technical field may be easily substituted or those that are substantially the same are included.

[Implementation form] Embodiments will be described with reference to FIGS. 1 to 5 . This embodiment relates to a vehicle congestion degree judging method and a vehicle congestion degree judging system. Fig. 1 is a block diagram showing a system for judging the degree of congestion of a vehicle according to an embodiment, Fig. 2 is a diagram showing images captured by a first camera, and Fig. 3 is a diagram showing images captured by a second camera In the diagram of the image, FIG. 4 is a diagram for explaining the determination of the overlapping degree, and FIG. 5 is a flow chart showing the operation of the embodiment.

As shown in FIG. 1 , a system 1 for judging the degree of congestion of a vehicle includes a vehicle-mounted device 2 , a camera 3 , and a workstation PC7. The vehicle-mounted device 2 and the camera 3 are installed in a vehicle 100 for transporting passengers. The vehicle 100 of this embodiment is a public bus, for example, a route bus running a predetermined route. Vehicles 100 pick and drop passengers at various stops along the route. The vehicle 100 is equipped with a door sensor 4 in addition to the vehicle-mounted device 2 and the camera 3 .

The on-vehicle device 2 is, for example, a driving recorder or a digital driving recorder that records the operating conditions of the vehicle 100 . The vehicle-mounted device 2 has a CPU 21 , a memory 22 , a GPS receiving unit 23 , and a communication unit 24 . The CPU 21 is a calculation device that performs various calculations. The CPU 21 executes the operations of the present embodiment according to programs stored in the memory 22, for example.

The memory 22 is a memory unit including a volatile memory and a nonvolatile memory. The GPS receiver 23 calculates the current position of the vehicle 100 based on a signal transmitted from a satellite. The communication unit 24 is a communication module for communicating with the wireless base station 5 . The communication unit 24 performs wireless communication with the wireless base station 5 through the antenna of the vehicle 100 according to the instruction of the CPU 21 .

The camera 3 is an imaging device that captures the interior of the vehicle 100 and outputs images G1 and G2. The position of the camera 3 and the angle of view of the camera 3 are set so as to be able to photograph passengers in the car. The vehicle 100 of the present embodiment has a first camera 31 and a second camera 32 as the camera 3 . The first camera 31 photographs the vicinity of the exit gate inside the vehicle. The second camera 32 photographs the vicinity of the boarding gate inside the vehicle. The in-vehicle device 2 acquires images captured by the camera 3 and stores them in the memory 22 .

The door sensor 4 is a sensor that detects the state of opening and closing the door of the vehicle 100 . The door sensor 4 detects whether the door is fully closed, for example. The door sensors 4 are arranged, for example, on each of the entrance door and the exit door. The detection result of the door sensor 4 is delivered to the CPU21.

The vehicle-mounted device 2 transmits the data for judging the degree of congestion to the outside through the communication unit 24 . The transmitted data includes, for example, an image captured by the camera 3 , the shooting time of the image, the position of the vehicle 100 at the shooting time, the identification code of the vehicle 100 , and the like. The image data transmitted by the communication unit 24 is, for example, still image data. The transmitted data is stored in the server 6 connected to the Internet NW, for example.

The workstation PC7 is constituted by, for example, a general-purpose computer device installed in a workstation of a company or the like. The workstation PC7 has a function of managing the operation status of the vehicle 100 to be managed and a function of determining the degree of congestion of the vehicle 100 . The workstation PC7 has a CPU 71 , a memory 72 , a communication unit 73 , and an external input interface 74 . The workstation PC7 communicates with the server 6 and the wireless base station 5 respectively through the communication unit 73 and the Internet NW. The workstation PC7 executes the management of the operation status and the determination of the degree of congestion, for example, according to the program read from the memory 72 to the CPU 71 .

In FIG. 2 , an example of the image G1 captured by the first camera 31 is shown. In the image G1, the interior 101 of the vehicle 100 is photographed. More specifically, in the image G1, the driver's seat 102, the aisle 103, and the exit 105 are photographed. The drop gate 105 is disposed at the front of the vehicle 100 and is opened and closed by the drop door 104 .

In FIG. 3 , an example of the image G2 captured by the second camera 32 is shown. In the image G2, the interior 101 of the vehicle 100 is photographed. More specifically, in the image G2, the aisle 103, the boarding gate 107, the rear seats 108, and the front seats 109 are photographed. The entrance door 107 is arranged in the middle of the vehicle 100 and is opened and closed by the entrance door 106 . The rear seat 108 is a seat arranged at the rear of the vehicle than the boarding gate 107 . The rear seats 108 face toward the front of the vehicle. The front seat 109 is a seat arranged in front of the vehicle than the boarding gate 107 . The front seats 109 face the vehicle width direction.

The vehicle-mounted device 2 sends the images G1 and G2 captured after the passengers get on and off the vehicle. For example, the in-vehicle device 2 transmits the images G1 and G2 captured when the lower door 104 and the upper door 106 are fully closed to the Internet NW. The images G1 and G2 captured when the flow of passengers is small can estimate the degree of congestion in the car 101 with high precision.

The workstation PC7 acquires data for determining the degree of congestion of the vehicle 100 from the server 6 . The workstation PC7 acquires data through the communication unit 73 and saves the acquired data in the memory 72 . The CPU 71 has a detection unit 71a, an extraction unit 71b, and a determination unit 71c.

The detecting unit 71a, the extracting unit 71b, and the determining unit 71c may be part of a program executed by the CPU 71, may be part of a circuit included in the CPU 71, or may be a chip mounted on the CPU 71 or the like. That is, the CPU 71 may be configured to be able to execute the function as the detection unit 71a, the function as the extraction unit 71b, and the function as the determination unit 71c.

The vehicle congestion degree judging system of the present embodiment judges the congestion degree of the vehicle 100 based on two indexes. The first indicator is the density of passengers. The CPU 71 detects people from the images G1 and G2 and calculates the density of passengers in the aisle 103 . The second indicator is the total number of passenger detections. The CPU 71 calculates the total number of passengers detected from the image G2. That is, the density is calculated from both the images G1 and G2, and the total number of detections is calculated from the image G2. The vehicle congestion degree judging system 1 of this embodiment can judge the congestion degree of the vehicle 100 more accurately based on the density of passengers and the total number of passengers detected.

The detection part 71a detects a person from the images G1 and G2, and generates a detection area DA for each detected person. For example, the detection unit 71a, as shown in FIG. 2 , generates a detection area DA for each detected person. The detection area DA is a so-called bounding box. In FIG. 2, three persons are detected, person P0, person P1, and person P2. The detection unit 71a generates a detection area DA0 surrounding the person P0, a detection area DA1 surrounding the person P1, and a detection area DA2 surrounding the person P2. The detection unit 71a detects all persons including standing persons and sitting persons, and generates a detection area DA for all detected persons.

As shown in FIG. 3 , the detecting unit 71 a generates detection areas DA3 , DA4 , and DA5 for P3 , P4 , and P5 detected from the image G2 . In addition, the detection area DA is an area recognized as a person captured in the video, and may not be an area surrounding all the people.

The extraction unit 71b extracts the detection area DA to be calculated as the density and the detection area DA to be calculated as the total number of detections from all the generated detection areas DA. The driver of the vehicle 100 is excluded from the calculation object of the density, and is also excluded from the calculation object of the total detection number. The person P0 detected in FIG. 2 is the driver of the vehicle 100 . The extraction unit 71b recognizes the driver and excludes the driver from the calculation target as described below.

As shown in FIG. 2 , the image G1 is equally divided into nine regions A11 to A19 . The shape of each area is a rectangle. In the illustrated image G1, the number of pixels in the horizontal direction of the image in each region is 240, and the number of pixels in the vertical direction of the image is 160. That is, each area is constituted by 38,400 pixels.

In the image G1, areas A11, A14, and A17 are set as areas where the driver is photographed. When the central coordinates of the detection area DA are located in any of the areas A11, A14, and A17, the extracting unit 71b judges that the detection area DA corresponds to the driver. In FIG. 2 , the center of the detection area DA0 is located in the area A14 . That is, it can be determined that the person A0 corresponding to the detection area DA0 is the driver. Therefore, the extraction unit 71b excludes the detection area DA0 from the calculation target of the density and the total number of detections. On the other hand, the centers of the detection areas DA1, DA2 are not located in any of the areas A11, A14, A17. The extraction unit 71b uses the detection areas DA1 and DA2 as objects of density calculation. Since the detection areas DA1 and DA2 are the areas of the image G1, they are not the calculation objects of the total detection number.

As shown in FIG. 3 , the image G2 is equally divided into nine regions A21 to A29 . The shape of each area is a rectangle. In the illustrated image G2, the number of pixels in the horizontal direction of the image in each region is 240, and the number of pixels in the vertical direction of the image is 160. That is, each area is constituted by 38,400 pixels.

Image G2 does not contain the area where the driver is photographed. Therefore, the extraction unit 71b does not perform the determination of whether the detection area DA corresponds to the driver for the image G2. In the image G2, the areas A23, A26, and A29 are the areas where the sitting passengers are photographed. In the following description, the area where the sitting passenger is photographed is referred to as "the first area". When the center coordinate of the detection area DA is located in the first area, the extracting unit 71b judges that the detection area DA is an area corresponding to the seated passenger. In FIG. 3 , the center of the detection area DA5 is located in the area A29 . That is, it can be determined that the detected person P5 is a seated passenger.

The correlation between the sitting passengers and the density of the aisle 103 is low. The extraction unit 71b excludes the detection area DA5 from the density calculation target. On the other hand, the extraction unit 71 adopts the detection area DA5 as the calculation object of the total detection number.

The centers of the detection areas DA3, DA4 are not located in any of the areas A23, A26, A29. Therefore, the extraction unit 71b adopts the detection areas DA3 and DA4 as calculation objects of the density and the total number of detections.

The determination unit 71c calculates the density and the total number of detections, and determines the degree of congestion of the vehicles 100 based on the calculation results. The density of this embodiment is calculated as follows. In the image G1 shown in FIG. 2 , the area where the density is calculated is the area A15 . The area A15 is an area where passengers standing at the end of the aisle 103 on the side of the exit gate 105 are photographed.

The determination unit 71c sets the area A15 as the target area Tg. The determination unit 71c determines whether or not the number of pixels overlapping the target area Tg is equal to or greater than a threshold value Th1 for each detection area DA. For example, as shown in FIG. 4 , the determination unit 71 c detects an area Ov1 in which the target area Tg overlaps with the detection area DA1 . When the number of pixels in the region Ov1 is equal to or greater than the threshold Th1, the determination unit 71c increases the count number C0 in the target region Tg. The initial value of the count number C0 is 0. The threshold Th1 is, for example, 1,024 [pixels]. That is, when the number of pixels of the area Ov1 is 1,024 or more, the detection area DA1 is counted as one of the densely packed components.

The determination unit 71c similarly detects an area overlapping with the target area Tg with respect to another detection area DA, and increases the count number C0 of the target area Tg when the number of pixels in the overlapping area is equal to or greater than the threshold Th1. The determination part 71c determines the degree of overlap with the target area Tg with respect to all the detection areas DA which are the calculation target of density|concentration. The determination unit 71c stores the calculated count number C0 as the count number C15 in the area A15. Thereafter, the determination unit 71c initializes the count number C0.

Furthermore, the determination unit 71c determines the degree of overlap with respect to the video G2. In the image G2 shown in FIG. 3 , the target area Tg is an area A25 and an area A28 . Area A25 and area A28 are areas where passengers standing near boarding gate 107 in aisle 103 are photographed.

The determination unit 71c sets one area A25 as the target area Tg. The judging unit 71c judges whether or not the number of pixels in which each detection area DA of the image G2 overlaps with the target area Tg is equal to or greater than a threshold Th2. The threshold Th2 is, for example, 3,072 [pixels]. When the number of pixels in the overlapping area of the target area Tg and the detection area DA is equal to or greater than the threshold Th2, the determination unit 71c increases the count number C0 of the target area Tg. The determination unit 71c determines the degree of overlap with the target area Tg in all the detection areas DA that are the calculation target of the density. The determination unit 71c stores the calculated count number C0 as the count number C25 in the area A25. Thereafter, the determination unit 71c initializes the count number C0.

The determination unit 71c sets the area A28 as the target area Tg, and similarly calculates the count number C0. The determination unit 71c stores the calculated count number C0 as the count number C28 in the area A28. The determination unit 71c calculates the total detection number of passengers with respect to the image G2. The total detection number CA is the number of detection areas DA generated for the image G2. In the image G2 illustrated in FIG. 3 , the detection areas DA3 , DA4 , and DA5 are the calculation objects of the total detection number. That is, the total number of detections CA is three.

The CPU 71 determines the degree of congestion based on the flowchart shown in FIG. 5 . After the CPU 71 executes the steps of acquiring the images G1 and G2, the flowchart in FIG. 5 is executed.

In step S10, the detection unit 71a performs object detection on the images G1 and G2, and calculates the detection area DA. Step S10 is a step of detecting persons from the images G1 and G2, and generating a rectangular detection area DA surrounding the persons detected respectively. When step S10 is executed, proceed to step S20.

In step S20, the extraction part 71b extracts the detection area DA which is the calculation object of density|concentration, and the detection area DA which is the calculation object of the total number of detections. When step S20 is executed, proceed to step S30.

In step S30, the determination unit 71c calculates the overlap between the detection area DA and the target area Tg. The determination unit 71c calculates the count numbers C15, C25, and C28 for the respective areas A15, A25, and A28. When step S30 is executed, proceed to step S40.

In step S40, the determination part 71c determines whether the index of congestion degree satisfies the condition of level II. The congestion degree judging system 1 for vehicles according to the present embodiment classifies the congestion degree into three types: level I, level II, and level III. Level I is the least congested level, and Level III is the most congested level. Level I, for example, the crowding degree of standing passengers is less than 2. In addition, baby strollers, passengers who want to sit down, and employees of bus companies are not included in the object of "standing passengers". In level II, for example, there are more than 3 passengers standing, and the central part of the aisle 103 is unused. Level III, for example, the central part of the aisle 103 has congestion of passengers standing. Also, the central portion of the aisle 103 is, for example, an intermediate portion between the upper door 106 and the lower door 104 in the aisle 103 .

The condition of level II is referred to as the first condition. The first condition is a condition that the following formula (1) holds. That is, in the case of "the total value of the count number C15 of the area A15 and the count number C28 of the area A28 is 2 or more", it is determined that the degree of congestion is level II or more. The condition of the level I is "the total value of the count number C15 and the count number C28 is less than 2". When the first condition is satisfied, the determination unit 71c makes an affirmative determination in step S40 and proceeds to step S50. If the determination part 71c makes a negative determination in step S40, it progresses to step S80. C15＋C28≧2 (1)

In step S50, the determination unit 71c determines whether or not the index of the degree of congestion satisfies the condition of level III. The condition of level III is that the second condition must be satisfied in addition to the first condition. The second condition is that all of the following formula (2), formula (3), formula (4), and formula (5) are satisfied. That is, if the first condition is satisfied, and "the count number C15 of the area A15 is 1 or more, the count number C25 of the area A25 and the count number C28 of the area A28 are both 2 or more, and the total detection number CA is 11 or more", The degree of congestion is judged to be level III. C15≧1 (2) C25≧2 (3) C28≧2 (4) CA≧11 (5)

When the second condition is satisfied, the determination unit 71c makes an affirmative determination in step S50 and proceeds to step S60. When the determination part 71c makes a negative determination in step S50, it progresses to step S70.

In step S60, the determination unit 71c substitutes the value of the level III for the level Lv of the degree of congestion. When step S60 is executed, the flow chart ends.

In step S70, the determination unit 71c substitutes the value of the level II for the level Lv of the degree of congestion. When step S70 is executed, the flowchart ends.

In step S80, the determination unit 71c substitutes the value of the level I for the level Lv of the degree of congestion. When step S80 is executed, the flowchart ends.

The CPU 71 can transmit information on the congestion level Lv to the outside. For example, the congestion level Lv can be wirelessly transmitted to the bus stop. In this case, the level Lv of the degree of congestion of the vehicles 100 arriving at the station from that moment on is displayed on the display at the station. For example, the congestion level Lv can be sent to the user's mobile terminal. In this case, on the user's mobile terminal, the congestion level Lv of the vehicle 100 can be displayed by the application. For example, the congestion level Lv may be sent to other route buses traveling the same route as the vehicle 100 . The level Lv of the degree of congestion can also be used in the management of the operating schedule of the route bus including the vehicle 100 .

As described above, the vehicle congestion level judging method according to the present embodiment includes an acquiring step, a generating step, and a judging step. In the acquisition step, images G1 and G2 of the interior 101 of the vehicle 100 transporting passengers are acquired. In the generating step, a person is detected from the images G1 and G2, and a rectangular detection area DA surrounding the person is generated for each detected person. In the flowchart of FIG. 5, step S10 corresponds to a generating step.

In the determining step, the congestion degree of the vehicle 100 is determined based on the target area Tg and the detection area DA of the images G1 and G2. In the flowchart of FIG. 5 , steps S30 to S80 correspond to a determination step. The target area Tg is an area of a part of the images G1 and G2, and is an area where a passenger standing in the aisle 103 of the vehicle 100 is photographed. In the determination step, the degree of congestion of the vehicle 100 is determined based on the number of detection areas DA overlapping with the target area Tg.

The number of detection areas DA overlapping with the target area Tg indicates the density of passengers standing on the aisle 103 . Therefore, the vehicle congestion degree judging method according to the present embodiment can appropriately judge the congestion degree of vehicles transporting passengers. In addition, good detection accuracy can be achieved by comparing the detection of persons from the entire wide range images G1 and G2 with the detection of persons from the target region Tg.

The method of judging the degree of congestion of vehicles as above is also useful, for example, from the viewpoint of countermeasures against infectious diseases such as the novel coronavirus (COVID-19) in recent years. For example, it is possible to prompt the user to grasp the degree of congestion of the vehicle 100 timely and accurately so as not to use it densely, and also to improve the operation plan for the operator to use in a less dense manner. Also, in the vehicle congestion degree determination method of this embodiment, the congestion degree is determined based on a still image. Therefore, it is possible to suppress an increase in the load on each section related to determination. For example, since the amount of communication in the case of sending an image captured by the camera 3 to the Internet NW is small, the communication load is reduced. Also, when the on-vehicle device 2 performs the determination of the degree of congestion, the calculation load on the on-vehicle device 2 is reduced.

The target area Tg of the present embodiment is an area where passengers standing near the entrance and exit of the vehicle 100 are photographed. The vehicle 100 is considered to be crowded, and it is considered that many passengers are standing near the boarding gate. Therefore, the congestion degree of the vehicle 100 can be appropriately determined in the method for judging the degree of congestion of the vehicle according to the present embodiment.

The image G2 of this embodiment has the first area where the sitting passengers are photographed. The detection area DA having the center coordinates in the first area is excluded from the calculation target of the count number C0 of the detection area overlapping with the target area Tg. Therefore, with regard to the method for judging the degree of congestion of vehicles in this embodiment, the density of the aisle 103 can be accurately calculated by excluding passengers sitting.

In the method for judging the degree of congestion of a vehicle according to the present embodiment, in the judging step, the vehicle 100 is judged based on the counted number of detection areas DA overlapping with the target area Tg and the total number of detections CA of people detected from the image G2. the degree of congestion. Therefore, based on the density of the walkways 103 and the total number of detections CA, the degree of congestion of the vehicles 100 can be properly determined.

In the method for judging the degree of congestion of a vehicle according to the present embodiment, in the obtaining step, the first image and the second image are obtained. The first image corresponds to an image G1 of a passenger standing near the exit gate 105 in the aisle 103 . The second image corresponds to the image G2 of passengers standing near the boarding gate 107 in the aisle 103 . In the determination step, the degree of congestion of the vehicle 100 is determined based on the first image and the second image. Based on the two images, it becomes possible to determine the degree of congestion of the vehicle 100 with better accuracy.

The vehicle congestion degree judging system 1 of the present embodiment includes a camera 3, a detection unit 71a, and a judging unit 71c. The determination unit 71c determines the degree of congestion of the vehicle 100 based on the number of detection areas DA overlapping with the target area Tg. Therefore, the congestion degree judging system 1 can appropriately judge the congestion degree of vehicles transporting passengers.

The vehicle congestion level judging method and the congestion level judging system 1 according to the present embodiment can accurately judge the congestion level of the vehicle 100 . For example, by detecting a person not only in the target area Tg but also in the entirety of the images G1 and G2 , it is possible to suppress missed detection and false detection. As a comparative example, the angle of view of the camera 3 is set to determine only the imaging target area Tg. In this case, when there are many tourists, it becomes difficult to detect the people who are hiding behind because of the overlap of multiple people. On the other hand, in the present embodiment, the angle of view of the camera 3 is determined to capture a wider range than the target area Tg. Accordingly, it is difficult for human omission and false detection to occur.

The camera 3 of the present embodiment is arranged to take pictures overlooking the interior of the vehicle 101 . Accordingly, even if there are many passengers in the aisle 103, it is easy to detect individual passengers.

In addition, the angle of view of the camera 3 is set to photograph not only passengers standing in the aisle 103 but also passengers sitting in the seats 108 and 109 . Therefore, based on both the density and the total number of detections, it is possible to determine the degree of congestion with high accuracy.

According to the system 1 for judging the degree of congestion of vehicles and the method for judging the degree of congestion of vehicles related to the present embodiment, it is possible to alleviate the congestion of the vehicle 100 . For example, if information related to the degree of congestion of vehicles 100 is provided to users in real time, it is difficult for passengers to concentrate on a specific vehicle 100 . As a result, crowding of passengers in the vehicle 100 can be prevented in advance, and virus infection in the vehicle can be suppressed.

In addition, the determination unit 71c may set a plurality of areas collectively as one target area Tg. For example, the determination unit 71c may set the area A25 and the area A28 together as one target area Tg in the image G2. In this case, when the number of pixels in the area where the target area Tg and the detection area DA overlap is equal to or greater than the threshold Th3, the count numbers for the areas A25 and A28 are increased.

The congestion level judging system 1 of the present embodiment is easily applicable to the vehicle to be installed. For example, the position and angle of view of the camera 3 may vary depending on the type of vehicle 100 and the operating company. The congestion degree judging system 1 of the present embodiment can easily adjust the density judgment accuracy by selecting the optimum target region Tg from plural regions included in the images G1 and G2. In addition, the determination accuracy of density can be easily adjusted according to the thresholds Th1 and Th2. In addition, by setting an exclusion area for the driver and an exclusion area for passengers sitting on the seat, it is possible to easily adjust the determination accuracy of the density. Thus, the congestion degree determination system 1 of this embodiment is a highly versatile system.

In addition, the number of areas in the video images G1 and G2 is not limited to the illustrated number. In addition, the shapes of the regions in the video images G1 and G2 are not limited to the illustrated shapes. The images G1, G2 may not be equally divided.

The CPU 71 can determine the degree of congestion based on any one of the images G1 and G2. For example, the CPU 71 can determine any one of Level I, Level II, and Level III based on one of the images G1 and G2.

At least one of the operation of the detection unit 71a, the operation of the extraction unit 71b, and the operation of the determination unit 71c can be executed in the on-vehicle device 2 or the server 6 on the cloud. For example, the CPU 21 of the vehicle-mounted device 2 may have a detection unit 71a, an extraction unit 71b, and a determination unit 71c. In this case, the CPU 21 may transmit information on the congestion level Lv to the Internet NW.

The contents disclosed in the above-mentioned embodiments can be implemented in combination as appropriate.

1: vehicle congestion degree judgment system 2: On-board device 3: camera 4: Door sensor 5: Wireless Base Station 6: Server 7: Workstation PC 21:CPU 22: Memory 23:GPS receiving department 24: Department of Communications 31: First camera 32: Second camera 71:CPU 71a: Detection department 71b: extraction part 71c: Judgment Department 72: memory 73: Department of Communications 74: External input interface 100:vehicle 101: Inside the car 102: Driver's seat 103: aisle 104: get off the door 105: Get off the gate 106: on the door 107: boarding gate 108: rear seat 109: Front seat A11~A19: area A21~A29: area C0: Count number of target area C15, C25, C28: the number of counts in the area CA: total detections DA0~DA5: detection area G1,G2: Image NW: Internet P0~P5: People S10~S80: steps

FIG. 1 is a block diagram of a vehicle congestion degree judging system according to an embodiment. FIG. 2 is a diagram showing images captured by the first camera. FIG. 3 is a diagram showing images captured by a second camera. FIG. 4 is a diagram illustrating the determination of the degree of overlap. Fig. 5 is a flowchart showing the operation of the embodiment.

none

101: Inside the car

103: aisle

106: on the door

107: boarding gate

108: rear seat

109: Front seat

A21: Area

A22: Area

A23: Area

A24: Area

A25(Tg): area

A26: Area

A27: Area

A28(Tg): area

A29: Area

DA3: Detection area

DA4: Detection area

DA5: Detection area

G2: Image

P3: people

P4: people

P5: people

Claims (6)

A method for judging the degree of congestion of a vehicle, characterized in that it comprises: Steps of obtaining the captured image of the interior of the vehicle transporting passengers, a step of detecting a person from the aforementioned image and generating, for each detected aforementioned person, a rectangular detection area enclosing the person, a step of determining the degree of congestion of the aforementioned vehicle based on the target area of the aforementioned image and the aforementioned detection area, wherein the aforementioned target area is an area of a part of the aforementioned image, and is an area where passengers standing on the aisle of the aforementioned vehicle are photographed, In the aforementioned determining step, the degree of congestion of the aforementioned vehicles is determined based on the number of the aforementioned detection areas overlapping with the aforementioned target area. The method for judging the degree of congestion of a vehicle according to claim 1, wherein the target area is an area in which passengers standing near the entrance and exit of the vehicle are photographed. The method for judging the degree of congestion of a vehicle as described in claim 1 or 2, wherein the aforementioned image has a first area in which a sitting passenger is photographed, The detection area having the center coordinates in the first area is excluded from the calculation object of the number of the detection areas overlapping with the target area. The method for judging the degree of congestion of vehicles according to any one of claims 1 to 3, wherein in the judging step, based on the number of the aforementioned detection areas overlapping with the aforementioned target area and the number of the aforementioned people detected from the aforementioned images The total number of detections is used to determine the degree of congestion of the aforementioned vehicles. The vehicle congestion degree determination method described in any one of Claims 1 to 4, Wherein in the aforementioned obtaining step, the first image of the passenger standing near the exit gate in the aforesaid aisle and the second image of the passenger standing near the abort gate in the aforesaid aisle are obtained, In the aforementioned determining step, based on the aforementioned first image and the aforementioned second image, the degree of congestion of the aforementioned vehicles is determined. A system for judging the congestion degree of a vehicle, which has: A camera that takes pictures of the inside of a vehicle transporting passengers and outputs the images, a detecting unit that detects a person from the image and generates a rectangular detection area surrounding the person for each detected person, A judging unit for judging the degree of congestion of the aforementioned vehicles based on the target area of the aforementioned image and the aforementioned detection area; The aforementioned target area is an area of a part of the aforementioned image, and is an area where passengers standing on the aisle of the aforementioned vehicle are photographed, The determining unit determines the degree of congestion of the vehicles based on the number of the detection areas overlapping with the target area.

Images