Crime prevention device and crime prevention method

Abstract

Crime prevention device and crime prevention system that can more effectively prevent crimes using mobile devices A method is provided. A pedestrian detection unit receives a captured image transmitted from a vehicle and detects pedestrians from the captured image. The pedestrian attribute estimation unit estimates the attributes of pedestrians from the captured image. The area estimation unit estimates a pedestrian travel area in which a pedestrian is walking based on the captured image. The quantity calculation unit calculates the volume of vehicle traffic within the pedestrian travel area. The risk calculation unit calculates the pedestrian attribute. Calculates the risk of pedestrians becoming involved in crime based on the amount of vehicle traffic within the pedestrian's travel area. The patrol command unit patrols the pedestrian movement area when the risk level is higher than a preset threshold. A patrol command is sent to the mobile unit to instruct it to patrol.

Description

[Technical Field]

[0001] The present invention relates to a crime prevention device and a crime prevention method. [Background technology]

[0002] Patent Document 1 describes a system that acquires external information of multiple mobile objects that automatically patrol based on operation commands. Then, based on the information acquired by each mobile object that moves in the same area, a patrol command for each area is generated. The autonomous driving system determines the route and generates driving instructions according to the determined route policy for the area. It is written. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2019-117574 Summary of the Invention [Problem to be solved by the invention]

[0004] The automated driving system described in Patent Document 1 acquires the number of people as external information, The patrol policy will be determined so that areas with fewer people will be patrolled more frequently than areas with more people. However, when deciding on a patrol policy, the attributes of people and the volume of vehicle traffic (hereinafter referred to as vehicle traffic volume) are taken into consideration. This does not take into account the fact that children or the elderly are more likely to become involved in crime. Pedestrians are less likely to be involved in crime, such as people with high risk of being injured walking in areas with low vehicle traffic. It is not possible to detect situations where there is a high risk of being injured and prioritize patrols in such situations.

[0005] The present invention relates to a crime prevention device and a crime prevention method that can more effectively prevent crimes by using a mobile object. The purpose is to provide a method for prevention. [Means for solving the problem]

[0006] The present invention relates to a pedestrian detection system that receives captured images transmitted from a vehicle and detects pedestrians from the captured images. a pedestrian detection unit, a pedestrian attribute estimation unit that estimates the attributes of pedestrians from the captured image, and a pedestrian attribute estimation unit that estimates the attributes of pedestrians from the captured image. a pedestrian travel area estimation unit that estimates a pedestrian travel area in which a pedestrian is walking; a vehicle traffic volume calculation unit that calculates the volume of vehicle traffic within the pedestrian travel area; a risk calculation unit that calculates the risk of a pedestrian being involved in a crime based on the amount of traffic; If the degree of the movement is higher than a preset threshold, a patrol command is issued to patrol the pedestrian movement area. A crime prevention device is provided that includes a patrol command unit that transmits to moving objects.

[0007] The present invention receives captured images transmitted from a vehicle, detects pedestrians from the captured images, and The attributes of pedestrians are estimated from the images, and the pedestrian movement area is estimated based on the captured images. The pedestrian movement area is determined, the amount of vehicle traffic within the pedestrian movement area is calculated, and the attributes of pedestrians and the vehicles within the pedestrian movement area are calculated. Based on the traffic volume, the risk of pedestrians being involved in crime is calculated and the risk level is set in advance. A crime prevention method for transmitting a patrol command to patrol an area where pedestrians are moving when the threshold value is higher than the threshold value. Provide the law. [Effects of the Invention]

[0008] According to the crime prevention device and crime prevention method of the present invention, it is possible to more effectively utilize a mobile object. It can prevent crime. [Brief explanation of the drawings]

[0009] [Figure 1]FIG. 1 is a diagram showing a schematic configuration of a crime prevention system 1 including a crime prevention device according to one embodiment of the present invention. [Figure 2] FIG. 2 is a block diagram showing an example of the configuration of the crime prevention system 1 shown in FIG. [Figure 3] FIG. 3 is a diagram for explaining the main contents stored in the location information database 221 provided in the storage device 22. As shown in FIG. [Figure 4] FIG. 4 is a diagram for explaining the main contents stored in the attribute information database 222 provided in the storage device 22. As shown in FIG. [Figure 5] 2 is a diagram for explaining the main contents stored in a risk value database 223 provided in a storage device 22. FIG. [Figure 6] FIG. 6 is a diagram for explaining the function of a crime prevention device according to one embodiment of the present invention. [Figure 7] FIG. 7 is a flowchart illustrating an example of the operation of the crime prevention device according to one embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0010] Specific embodiments of the present invention will be described below with reference to the drawings. In the following, the same parts are denoted by the same reference numerals and the description thereof will be omitted.

[0011] [Crime Prevention System Overview] For an overview of a crime prevention system 1 including a crime prevention device according to this embodiment, see FIG. 1. FIG. 1 is a diagram showing the schematic configuration of a crime prevention system 1. The crime prevention system 1 according to the present invention is a system for detecting a vehicle 40 traveling on a road and a vehicle 40 traveling on a road based on a given patrol command. and a plurality of autonomously driven vehicles 50 that perform autonomous driving using the vehicle 40 and the autonomously driven vehicles 50. and a server 20 that collects and manages information and issues patrol commands to the autonomous vehicle 50. In this embodiment, the crime prevention device is a CPU (Central Processor) of the server 20. It is implemented as Rosessing Unit 23.

[0012] The server 20 and the vehicle 40, and the server 20 and the plurality of autonomously driven vehicles 50 are connected via a network 3. In this embodiment, the server 20, the vehicle 40, and the autonomous driving vehicle Both 50 are connected to the network 30 by a wireless communication system. The crime prevention system 1 illustratively includes one vehicle 40 and two autonomous vehicles 50. However, there may be two or more vehicles 40, and there may be three or more autonomous vehicles 50. The number of vehicles 40 and autonomously driven vehicles 50 is not particularly limited. For example, the vehicle may be a vehicle that patrols roads according to a predetermined route for crime prevention purposes. Alternatively, it may be a vehicle that is waiting at a designated waiting location and begins patrolling upon receiving a patrol command. Instead of multiple autonomous vehicles 50, drones or other vehicles that can be remotely controlled or autonomously driven may be used. The server 20 may be mounted on a vehicle 40 or an autonomous vehicle 50. The vehicle 40 or the autonomous vehicle 50 may be integrally configured.

[0013] The vehicle 40 acquires captured images while traveling. The vehicle 40 may further acquire information related to crime prevention, such as information about the brightness of lighting. The captured image and various information acquired by the vehicle 40 are transmitted to the server 20. The vehicle may be a manually operated vehicle or an autonomous vehicle.

[0014] The server 20 detects pedestrians from the captured image transmitted from the vehicle 40, and The server 20 calculates the risk of a person being involved in a crime. If the value is higher than the threshold, a patrol command is generated to patrol within the pedestrian movement area of the detected pedestrian. The autonomous vehicle 50 receives the patrol command and transmits it to the autonomous vehicle 50. An operation plan is generated according to the above, and the vehicle travels according to this operation plan.

[0015] [Configuration of crime prevention system] Next, each component of the crime prevention system 1 will be described in detail with reference to FIG. FIG. 2 is a block diagram showing an example of the configuration of the crime prevention system 1 shown in FIG. In FIG. 2, one vehicle 40 and one autonomous vehicle 50 are shown as examples. The crime prevention system 1 according to this embodiment has a plurality of pre-registered The vehicle 40 and the autonomous vehicle 50 can be individually identified. Individual vehicle IDs are managed to identify each of the vehicles 40 and the autonomously driven vehicle 50. The crime prevention system 1 transmits the ID of the information transmitting device 400 mounted on each vehicle 40 to the vehicle 4 0 vehicle ID, and the autonomous driving vehicle ID installed in each autonomous driving vehicle 50 The ID of the control device 500 may be managed as the vehicle ID of the automatically driven vehicle 50.

[0016] The server 20 manages information on the vehicle 40 and a plurality of automatically driven vehicles 50, and The server 20 is a device that transmits a patrol command to each of the vehicles 10 via the network 30. The server 20 communicates with the vehicle 40 and a plurality of autonomously driven vehicles 50. The server 20 includes a communication device 21 and a storage device The device 22, the CPU 23, and a memory (not shown) are included. The server 20 is electrically connected via a bus or the like. The installation location of the server 20 is not particularly limited. For example, the server 20 may be a business that provides local crime prevention services using an autonomous vehicle 50. It will be installed at the management center of the user.

[0017] In this embodiment, the server 20, the vehicle 40, and the autonomous driving vehicle 50 communicate with each other by wireless communication. The network 30 is connected to the network 30 .

[0018] The communication device 21 communicates with the vehicle 40 and the autonomously driven vehicle 50 via the network 30. The communication device 21 has a mobile communication function such as 4G / LTE. It may be a device equipped with a wireless LAN communication function. .

[0019] The storage device 22 stores various information and databases required for the security service. The device 22 is a storage medium such as a hard disk drive (HDD). 22 includes, for example, a location information database 221, an attribute information database 222, and a list and a metric value database 223. For details of the various databases, see FIGS. 3 to 5. This will be described later with reference to

[0020] The CPU 23 controls the server 20. The CPU 23 stores the It loads various programs into memory and executes the various instructions contained in the programs. Memory is divided into ROM (Read Only Memory), RAM (Random Access Memory), and storage media such as access memory.

[0021] The CPU 23 includes, as an example of a functional configuration, a location information management unit 231 and a pedestrian detection unit 232. a pedestrian attribute estimation unit 233, a pedestrian travel area estimation unit 234, and a vehicle traffic volume calculation unit 23 5, a risk calculation unit 236, and a patrol command unit 237. This will be described later with reference to FIG.

[0022] The vehicle 40 includes a communication device 41, a camera 42, a storage device 43, and a GPS receiver 44. The information transmitting device 400 includes:

[0023] The communication device 41 has the same configuration as the communication device 21, and communicates via the network 30. The server 20 communicates with the computer 10.

[0024] The camera 42 is an imaging device that captures images of the outside of the vehicle 40. The camera 42 is, for example, a CC D (Charge Coupled Device) image sensor or CMOS (Co Complementary Metal Oxide Semiconductor The image of the subject is captured using an image sensor such as a camera sensor. The camera 42 may be mounted, for example, behind the windshield of the vehicle. The camera 42 captures images of at least the direction of travel (forward) of the vehicle 40. The direction is not limited to a specific direction, and the camera 42 may capture images in all directions of the vehicle 40. The captured image is stored in the storage device 43 and sent to the server 20 at any time. The storage device 43 stores various information. The storage device 43 includes RAM, magnetic disk, The storage medium may be any storage medium such as a hard disk, flash memory, etc.

[0025] The position information of the vehicle 40 acquired by the GPS receiver 44 is transmitted to the server at any time. The GPS receiver 44 receives signals from multiple satellites and transmits the received signals to the GPS receiver 20. The signal is supplied to a CPU (not shown) mounted on the GPS receiver to calculate the position of the vehicle 4 on the ground. Calculates the location information of 0. Note that "GPS" stands for "Global Positioning System: An abbreviation for "Global Positioning System."

[0026] The autonomous vehicle 50 is a vehicle that travels autonomously based on a travel command received from the server 20. The autonomous vehicle 50 includes a communication device 51, a camera 52, a storage device 53, and a GPS receiver. a vehicle ECU (Electronic Control Unit) 55; The vehicle is equipped with an autonomous driving vehicle control device 500 including a communication device 51, a camera 52, and a storage device. The configuration of the communication device 41 of the information transmitting device 400 of the vehicle 40, the camera 53, and the GPS receiver 54 is The configuration of the camera 42, storage device 43, and GPS receiver 44 is the same as that of the camera 42, storage device 43, and GPS receiver 44, so the description will be omitted. .

[0027] The vehicle ECU 53 is a computer for controlling the driving of the autonomous vehicle 50. Both ECUs 53 receive a patrol command from the server 20 via the network 30. Based on the patrol command, the autonomous vehicle 50 is controlled to travel in an appropriate manner. CU53 operates various actuators (brake actuator, actuator) based on the patrol command. The controller controls the steering actuator, accelerator actuator, etc.

[0028] Next, various databases in the storage device 22 will be described with reference to FIGS. 3 to 5. Although not shown in the figure, the storage device 22 stores the vehicle ID and the vehicle ID assigned thereto. The server 20 may further include a database for managing the vehicle information in association with the vehicle information. Each vehicle ID can identify the vehicle 40 and the autonomously driven vehicle 50.

[0029] The location information database 221 manages the location information of each of the vehicles 40 and the autonomously driven vehicles 50. The location information database 221 is a database for managing location information. In this way, the vehicle IDs of the vehicle 40 and the autonomously driven vehicle 50, and the vehicle IDs of the vehicle 40 and the autonomously driven vehicle 50 are stored. 50, and store the position coordinate information received from each of them in real time. It has been done.

[0030] The attribute information database 222 stores the information of pedestrians detected from the captured image captured by the vehicle 40. The attribute information database 222 stores information about the following: For each pedestrian detected from the captured image, the pedestrian ID, gender, age, whether or not they are accompanied, and The information on the position coordinates of each pedestrian is stored in the memory. The gender and age of a pedestrian are sometimes called pedestrian attributes. The method for estimating the pedestrian's attributes and whether or not they are accompanied will be described later. Age is recorded in four categories: child, adult (young), adult (not young), and elderly. Age classification is not limited to this.

[0031] As an example, the risk value database 223 includes information on gender, age, and For each combination of whether or not the person is accompanied, the level of crime risk is shown under each pre-set condition. The risk value is stored in the storage unit. For example, the risk value is set to be higher for children and high-risk individuals than for adults. It is set to be higher for older people and higher for women than for men. The risk value is set to be higher for unaccompanied people than for accompanied people. For example, the risk is set highest for women, children, and unaccompanied passengers. For example, the database 223 gives 4 points for children, 3 points for women, 2 points for the elderly, and 2 points for unaccompanied people. As shown in the two figures, the system uses preset lists based on factors such as the pedestrian's gender, age, and whether or not they are accompanied. The method for setting the risk value is not particularly limited. Instead, the risk level may be set according to the attributes of pedestrians based on data on past crimes, etc.

[0032] Next, the details of each function of the CPU 23 of the server 20 will be described with reference to FIG. 6. In the example of FIG. 6, autonomous vehicles 50a to 50c are patrolling a certain area, and vehicle 40 is The vehicle 40 is traveling on a road, and a pedestrian 60 is present near the vehicle 40. The image shows a pedestrian 60. In FIG. 6, the vehicle 40 is the same as the vehicle 4 shown in FIG. 0, and the position information of each vehicle 40 and the images captured by the vehicle 40 are transmitted to the network. The autonomously driven vehicles 50a to 50c transmit the information to the server 20 via the network 30. The position information of each of the automatically driven vehicles 50a to 50c is transmitted to the network. The data is transmitted to the server 20 via the network 30.

[0033] The location information management unit 231 of the CPU 23 is configured to manage the location information of the pre-registered vehicles 40 and the automatically driven vehicles 50. The location information management unit 231 collects and manages location information of the locations a to 50c. At this time, position information is received from the vehicle 40 and the automatically driven vehicles 50a to 50c, and the vehicle 40 and the automatically driven vehicles 50a to 50c are The vehicle IDs of the vehicles 50a to 50c are stored in the location information database 221 in association with the vehicle IDs of the vehicles 50a to 50c. Can.

[0034] The pedestrian detection unit 232 receives the captured image captured by the vehicle 40 and transmitted from the vehicle 40. In this embodiment, the pedestrian detection unit 232 detects a pedestrian 60 from the captured image. 0 detects a pedestrian 60 by analyzing the captured image. A known method can be adopted. The position information of the pedestrian 60 is detected based on the position information of the vehicle 40 at the time the image is acquired. do.

[0035] When the pedestrian detection unit 232 detects the pedestrian 60, the pedestrian attribute estimation unit 233 The pedestrian attribute estimation unit 233 estimates the attributes of the pedestrian 60 from the captured image. The presence or absence of an accompanying person, that is, whether the pedestrian 60 is singular or plural, is estimated. The attribute estimation unit 233 further analyzes the captured image in which the pedestrian 60 is detected, thereby The attributes of the ascetic 60 are estimated. A known method can be used for this image analysis.

[0036] The pedestrian attribute estimation unit 233 detects, for example, the face of the detected pedestrian 60 and The pedestrian attribute estimation unit 233 estimates the gender and age of the pedestrian, for example, if the age of the pedestrian is a child, The system estimates whether the person is an adult (young), an adult (not young), or an elderly person. In cases where the face of the pedestrian 60 cannot be detected from the captured image, such as when the face of the pedestrian 60 is not clearly visible, In this case, the pedestrian attribute estimation unit 233 estimates the height, posture, hair color, and belongings such as a cane of the pedestrian 60. The gender and age of the pedestrian 60 may be estimated from the detected characteristics, clothing, etc. If the captured image is a video, the walking speed of the pedestrian 60 is further estimated, as well as the gender and age. May be added to an element.

[0037] The pedestrian attribute estimation unit 233 estimates the attribute of the pedestrian 60 and information on whether or not the pedestrian is accompanied by a person. The location information of the pilgrim 60 is stored in the attribute information database 222 .

[0038] The pedestrian travel area estimation unit 234 estimates the pedestrian travel area in which the pedestrian 60 is walking based on the captured image. The pedestrian travel area estimation unit 234 estimates the area A of the pedestrian 60 from the captured image, for example. The direction of the body of the pedestrian 60 is estimated as the direction of travel of the pedestrian. When the image is a moving image, the pedestrian travel area estimation unit 234 estimates the direction in which the pedestrian 60 is moving. In this embodiment, the pedestrian travel area estimation unit 234 estimates the direction of travel of the pedestrian 60. By further analyzing the captured image in which the pedestrian 60 is detected, the moving direction of the pedestrian 60 can be determined. A known method can be used for this image analysis.

[0039] The pedestrian travel area estimation unit 234 estimates the travel area of the pedestrian 60 based on the point where the pedestrian 60 is detected. The walking path in which the pedestrian 60 is assumed to walk is an area of radius X km on the side of the pedestrian 60's direction of travel. The pedestrian travel area estimation unit 234 estimates the pedestrian travel area A as the pedestrian travel area A. Using the point where the pedestrian was detected as the base point, the area with a radius of 2 km on the side of the direction of travel of the estimated pedestrian 60 is It is assumed that 60 is pedestrian movement area A where pedestrians are expected to walk. The method of determining the distance is not particularly limited. For example, it is assumed that the pedestrian 60 walks for 10 to 15 minutes. It is sufficient to be able to estimate a region that includes the region.

[0040] The vehicle traffic volume calculation unit 235 calculates the volume of vehicle traffic within the pedestrian travel area A. The calculation unit 235 refers to the position information database 221 and calculates the position information of the pedestrians present in the pedestrian travel area A. The number of vehicles 40 and the number of autonomous vehicles 50 are calculated as the vehicle traffic volume. The unit 235 determines the number of vehicles 40 and automatically driven vehicles 50 present in the pedestrian travel area A simply from the number of vehicles 40 and automatically driven vehicles 50 present in the pedestrian travel area A. The number of vehicles 40 and autonomous vehicles 50 per location area may be calculated as the vehicle traffic volume. The method for calculating the vehicle traffic volume is not particularly limited. For example, the vehicle traffic volume calculation unit 235 may calculate the vehicle traffic volume by The vehicle information is transmitted from each of the plurality of vehicles 40 and the plurality of automatically driven vehicles 50 managed by the server 20. By detecting vehicles from the captured images and storing the position information of the detected vehicles, The amount of vehicle traffic within the pedestrian travel area A may be calculated.

[0041] The risk calculation unit 236 calculates the risk based on the attributes of the pedestrian 60 and the amount of vehicle traffic in the pedestrian travel area A. The risk calculation unit 236 calculates the risk of a pedestrian being involved in a crime by using the risk value data. The database 223 is referred to, and the pedestrian 60 is identified based on the attributes of the pedestrian 60 and whether or not the pedestrian is accompanied by another person. For example, the risk calculation unit 236 calculates the risk value by determining whether the pedestrian's gender is "female" and whether the pedestrian's age is "100%." If the person is “elderly” and “unaccompanied,” refer to the risk value database 223 in Figure 5. Pedestrian 60 receives a risk value of "3".

[0042] The risk calculation unit 236 also calculates the risk of a pedestrian based on the sex, age, whether or not the pedestrian is accompanied, and other factors described with reference to FIG. The score for each element of the pedestrian 60 is calculated by referring to the risk value set in advance for each element. In this way, the risk value of the pedestrian 60 may be calculated.

[0043] The risk calculation unit 236 calculates, for example, the risk of a pedestrian traveling in the pedestrian traveling area A based on a predetermined amount of vehicle traffic. It is then determined whether the volume of vehicle traffic in the pedestrian travel area A is greater than the threshold value. If the number is greater than the threshold, the risk value of pedestrian 60 is multiplied by 0.5 to increase the risk. On the other hand, when the amount of vehicle traffic in the pedestrian travel area A is equal to or less than the threshold, the The risk level is calculated by multiplying the risk value by 1.2. For example, the risk value of pedestrian 60 is calculated by multiplying the vehicle traffic volume per unit area within the pedestrian travel area A by The risk level may be calculated by multiplying the reciprocal of the above. The method for calculating the risk level is not particularly limited. First, the risk level calculation unit 236 calculates whether the risk value of the pedestrian 60 is high and whether the pedestrian is within the pedestrian travel area A. The risk level may be calculated so that it is higher when the amount of vehicle traffic is low. In addition to the pedestrian's attributes, whether they are accompanied or not, and the amount of vehicle traffic, the location where the pedestrian 60 is detected, Other factors such as time of day, illuminance, etc. may also be used. In addition, the risk level may be calculated based on the occurrence of past crimes. The data may be used.

[0044] When the risk level is higher than a preset threshold, the patrol command unit 237 The patrol command unit 237 transmits a patrol command to the automatically driven vehicle 50 to instruct the patrol of the degree of danger. Whether the risk calculated by the calculation unit 236 is higher than a preset threshold value of the risk is determined. If the risk level is higher than the threshold, the location information database 221 is referenced. Among the self-driving vehicles 50a to 50c, the one patrolling the position closest to the pedestrian travel area A is The patrol command unit 237 specifies the automatically driven vehicle 50a. A patrol command is generated to instruct the patrol of the pedestrian progress area A. The patrol command includes the specified automatic driver. The travel route from the current position of the vehicle 50a to the pedestrian travel area A and the pedestrian travel area A are The route command unit 237 instructs the autonomous vehicle 50a to The generated patrol command is transmitted to instruct the pedestrian to patrol the pedestrian travel area A. [Crime prevention device processing flow] Next, referring to the flowchart of FIG. 7, the flow of processing by the CPU 23 according to this embodiment will be explained. 7, the vehicle 40 receives position information of the vehicle 40 and an image captured by the vehicle 40. The captured images are transmitted to a server 20 via a network 30. 50a to 50c transmit the position information of each of the automatically driven vehicles 50a to 50c to the network 30. The server 20 transmits the information to the vehicle 40 and the automatically driven vehicles 50a to We collect and manage 50c location information.

[0045] In step S10 of FIG. 7, the pedestrian detection unit 232 detects the vehicle 40 40 receives the captured image.

[0046] The process proceeds to step S11, where the pedestrian detection unit 232 detects the image captured by the vehicle 40 as By analyzing the image, a pedestrian 60 is detected.

[0047] If the pedestrian 60 is detected by the pedestrian detection unit 232, the process proceeds to step S12. The pedestrian detection unit 232 detects the pedestrian 60 from the vehicle 40 at the time of acquiring the captured image. Based on the position information, the position information of the pedestrian 60 is detected.

[0048] The process proceeds to step S13, where the pedestrian attribute estimation unit 233 estimates the pedestrian 60's The pedestrian attribute estimation unit 233 estimates whether the pedestrian 60 is accompanied by anyone. The pedestrian attribute estimation unit 233 estimates the attributes of the pedestrian 60 and information on whether or not the pedestrian is accompanied by a person. The location information of 60 is stored in the attribute information database 222.

[0049] The process proceeds to step S14, where the pedestrian travel area estimation unit 234 detects a pedestrian 6 The direction of the body of pedestrian 60 is estimated as the direction of travel of the pedestrian. When the image is a moving image, the pedestrian travel area estimation unit 234 estimates the direction in which the pedestrian 60 is moving. It may be assumed to be the direction of travel of the pilgrim 60.

[0050] The process proceeds to step S15, where the pedestrian travel area estimation unit 234 determines whether the pedestrian 60 is detected. Using the point where the pedestrian 60 was detected as the base point, an area of radius X km in the direction of travel of the estimated pedestrian 60 is defined as the area of radius X km in the direction of travel of the estimated pedestrian 60. 0 is estimated to be the pedestrian travel area A where walking is expected.

[0051] The process proceeds to step S16, where the vehicle traffic volume calculation unit 235 calculates the number of vehicles in the pedestrian travel area A. The vehicle traffic volume calculation unit 235 calculates the traffic volume by using, for example, the location information database 221. The number of vehicles 40 and autonomous vehicles 50 present in the pedestrian travel area A is calculated based on the vehicle traffic volume. In addition, the vehicle traffic volume calculation unit 235 calculates the number of vehicles present in the pedestrian travel area A as follows: From the number of vehicles 40 and automated driving vehicles 50, the number of vehicles 40 and automated driving vehicles 50 per unit area The number may be calculated as the volume of vehicle traffic.

[0052] The process proceeds to step S17, where the risk calculation unit 236 calculates the risk level based on the attributes of the pedestrian 60 and the pedestrian progress. Based on the amount of vehicle traffic in area A, the risk of pedestrians becoming involved in a crime is calculated. The risk calculation unit 236 refers to the risk value database 223, for example, to calculate the attribute of the pedestrian 60. The risk calculation unit 236 acquires a risk value for the pedestrian 60 based on whether or not the pedestrian is accompanied by another person. For example, whether the amount of vehicle traffic in the pedestrian travel area A is greater than a preset threshold value of vehicle traffic volume. If the amount of vehicle traffic in the pedestrian travel area A is greater than the threshold, The risk level is calculated by multiplying the risk value of 60 by 0.5. If the amount of vehicle traffic in area A is below the threshold, the risk value of pedestrian 60 is multiplied by 1.2. The risk is calculated as follows.

[0053] The process proceeds to step S18, and the patrol command unit 237 determines whether the hazard calculated in step S17 is It is determined whether the degree of danger is higher than a preset threshold value. If the determination in step S18 is YES, the process proceeds to step S19. In the following cases (NO in step S18), the CPU 23 ends the processing of FIG.

[0054] In step S19, the patrol command unit 237 refers to the position information database 221. Among the self-driving vehicles 50a to 50c, the one patrolling the position closest to the pedestrian travel area A is The autonomously driven vehicle 50a is identified.

[0055] The process proceeds to step S20, where the patrol command unit 237 instructs the autonomously driven vehicle 50a to The patrol command is generated to instruct the autonomous vehicle 50a to patrol the autonomous vehicle travel area A. The route from the current position of the vehicle to pedestrian movement area A and the route to patrol within pedestrian movement area A It includes information on the route of the route.

[0056] The process proceeds to step S21, where the patrol command unit 237 sends the generated patrol command to the autonomously driven vehicle. 50, and the CPU 23 ends the process of FIG. 7. The vehicle receives the route command, generates an operation plan based on the received route command, and runs according to this operation plan. To carry out. (Variation 1) In the above description, the vehicle traffic volume calculation unit 235 calculates the vehicle traffic volume within the pedestrian travel area A. However, when the risk level is higher than a preset threshold, the patrol command unit 237 A patrol command to command A to patrol was sent to the autonomous driving vehicle 50a. The unit 235 divides the pedestrian travel area A into a plurality of areas, and The patrol command unit 237 may further calculate the amount of vehicle traffic in each area. If the threshold is higher than the threshold, the vehicle traffic volume within each divided pedestrian travel area A is In response to the request, the autonomous vehicle 50a is instructed to patrol each of the divided pedestrian travel areas. A command may be sent.

[0057] The patrol command unit 237 may, for example, Based on the amount of traffic, the number of vehicles patrolling each of the divided pedestrian movement areas A may be adjusted. For example, the patrol command unit 237 may be configured to The amount of vehicle traffic in other areas is greater than the predetermined threshold. In cases where the number of vehicles is small, patrols in areas with high vehicle traffic may be unnecessary. Two autonomous vehicles 50a are given a patrol command to patrol only areas with low vehicle traffic volume. , 50b. This allows the range of the pedestrian travel area A to be set wider. In this case, a patrol command is issued to increase the number of mobile units patrolling in an area with particularly low vehicle traffic. This allows for more efficient crime prevention.

[0058] The patrol command unit 237 may, for example, Based on the amount, the area to be patrolled may be limited within the divided pedestrian travel area A. For example, the patrol command unit 237 may be configured to control the vehicle movement within one of the divided pedestrian movement areas A. The amount of vehicle traffic in the area is greater than a preset threshold, and the amount of vehicle traffic in other areas is greater than a preset threshold. In cases where the number of vehicles traveling is less than the number of vehicles traveling in the area, patrol of areas with high vehicle traffic may be unnecessary. A patrol command is generated to instruct the autonomous vehicle 50a to patrol only within the other two areas. This makes it possible to reduce the amount of vehicle traffic when the pedestrian travel area A is set to a wide range. It is possible to generate patrol commands to patrol only a small area, enabling more efficient crime prevention. Cut. (Variation 2) In the above description, the crime prevention device according to this embodiment transmits a patrol command. The case where an autonomous vehicle 50 is used as the moving body has been described as an example. However, if a pedestrian is involved, Depending on the type of crime likely to occur, other types of vehicles may be more appropriate. For example, to prevent crimes such as calling out to people, dragging them around, and molesting, self-driving vehicles equipped with cameras5 On the other hand, to prevent crimes such as snatching, A mobile object with tracking capabilities such as a drone is suitable.

[0059] In addition, the types of crimes in which pedestrians are likely to be involved can be roughly estimated from the pedestrian's attributes. For example, children are more likely to be approached and dragged around, and young women are more likely to be molested. There is a high possibility that elderly people and women carrying luggage are more likely to be the victims of snatch theft. As mentioned above, it is possible to estimate the type of crime that a pedestrian is likely to be involved in based on the pedestrian's attributes. This can be done.

[0060] Therefore, in a case where the crime prevention system 1 has multiple types of mobile units that transmit patrol commands, In this case, the patrol command unit 237 determines whether or not a pedestrian is present on the basis of the type of crime that is preset in accordance with the attributes of the pedestrian. The type of mobile unit to which the patrol command is to be sent may be determined, and the patrol command may be sent to the mobile unit. In addition, when the captured image is a video, the pedestrian detection unit 232 detects blackmail, assault, It may also be possible to detect the occurrence of incidents such as blackmail, assault, or obstruction. In this case, the Patrol Command Unit 237 will dispatch a manned vehicle with a person who can arrest the criminal. A patrol command may be sent to direct the robot to the location where an incident is detected. In this way, the types of crimes in which pedestrians are likely to be involved can be estimated from pedestrian attributes. By sending patrol commands to mobile units that are appropriate for the type of mobile unit, mobile units can be used more effectively. It can prevent crime.

[0061] In addition, depending on the type of crime in which pedestrians are likely to be involved, multiple mobile vehicles may be used. Therefore, the patrol command unit 237 may be configured to The number of the mobile units to which a patrol command is to be sent is determined based on a preset type of crime, and It may also send patrol commands to other mobile units. By sending patrol commands to the corresponding number of mobile units, the mobile units can be used more effectively. This can be used to prevent crime. [Action and effect] As described above, according to this embodiment, the following advantageous effects can be obtained.

[0062] The crime prevention device according to this embodiment includes a pedestrian detection unit, a pedestrian attribute estimation unit, and a pedestrian movement detection unit. The system includes an area estimation unit, a vehicle traffic volume calculation unit, a risk calculation unit, and a patrol command unit. The detection unit receives the captured image transmitted from the vehicle and detects pedestrians from the captured image. The pedestrian attribute estimation unit estimates the attributes of pedestrians from the captured image. The pedestrian advancement area where the pedestrian is walking is estimated based on the image. The risk calculation unit calculates the amount of vehicle traffic within the travel area. Based on the volume of vehicle traffic, the pedestrian risk of being involved in a crime is calculated. If the risk level is higher than a preset threshold, a patrol command is issued to patrol the area where pedestrians are moving. The command is transmitted to the mobile unit.

[0063] This allows pedestrians to be identified as committing crimes based on their attributes and the amount of vehicle traffic within their pedestrian movement area. It is possible to calculate the risk of pedestrians being involved in crimes. When walking in an area with low vehicle traffic, the risk level can be increased. If the vehicle is located in a higher position than the pedestrian, a patrol command can be sent to the vehicle to patrol the pedestrian advance area. This allows for more effective crime prevention using mobile objects.

[0064] Furthermore, the vehicle traffic volume calculation unit of the crime prevention device according to this embodiment divides the pedestrian travel area into a plurality of The area is divided into regions, and the amount of vehicle traffic within each divided pedestrian movement region is further calculated. The patrol command unit controls the divided pedestrian movement areas when the risk level is higher than a preset threshold. Depending on the amount of vehicle traffic in each area, the mobile object is assigned to each of the divided pedestrian movement areas. A patrol command is sent to instruct the patrol.

[0065] This allows the patrol to be carried out based on the amount of vehicle traffic within each divided pedestrian travel area. It is possible to generate a patrol command that adjusts the number of moving objects to be moved. When this is set, the number of mobile units patrolling in areas with particularly low vehicle traffic volume will be increased. In addition, the pedestrian movement area can be divided into two areas, and the pedestrian movement area can be divided into two areas. Based on this, a patrol command can be generated to limit the area in which the mobile object patrols. When the range of the area is set to be wide, the robot will patrol only areas with particularly low vehicle traffic. Patrol commands can be generated, and crime prevention can be carried out more efficiently using mobile devices.

[0066] In addition, the patrol command unit of the crime prevention device according to this embodiment has a preset function corresponding to the attributes of pedestrians. Based on the type of crime identified, the type of mobile to which the patrol command is sent is determined.

[0067] This allows for the identification of types of mobility that correspond to the types of crimes in which pedestrians are likely to be involved. It is suitable for preventing crimes that are likely to involve pedestrians. This allows the mobile unit to patrol the area where pedestrians are moving. This will enable more effective crime prevention.

[0068] In addition, the patrol command unit of the crime prevention device according to this embodiment has a preset function corresponding to the attributes of pedestrians. The number of mobile units to send patrol orders to is determined based on the type of crime identified.

[0069] This allows for a number of vehicles corresponding to the types of crimes in which pedestrians are likely to be involved. It can send patrol commands. It is suitable for preventing crimes that are likely to involve pedestrians. This allows the number of mobile units to be instructed to patrol the pedestrian movement area. This will enable more effective crime prevention.

[0070] As described above, the embodiments of the present invention have been described. The descriptions and drawings that form part of this disclosure This disclosure should not be construed as limiting the invention, and various alternatives will become apparent to those skilled in the art. Alternative embodiments, implementations and operational techniques will become apparent. [Explanation of symbols]

[0071] 23 Crime Prevention Device (CPU) 232 Pedestrian detection unit 233 Pedestrian attribute estimation unit 234 Pedestrian movement area estimation unit 235 Vehicle Traffic Calculation Unit 236 Risk Calculation Unit 237 Patrol Command Department 40 vehicles 50 Mobile (Autonomous Vehicles) 60 Pedestrians A Pedestrian movement area

Claims

1. a pedestrian detection unit that detects pedestrians from the captured image; a pedestrian attribute estimation unit that estimates attributes of the pedestrian from the captured image; A pedestrian movement area in which the pedestrian is walking is estimated based on the captured image. an estimation unit; a patrol command unit that determines the number of mobile units to send patrol commands to instruct the mobile units to patrol the pedestrian travel area based on a type of crime that is preset corresponding to the attributes of the pedestrian; A crime prevention device comprising:

2. Receives captured images transmitted from a vehicle, Detecting a pedestrian from the captured image; Estimating attributes of the pedestrian from the captured image; estimating a pedestrian travel area in which the pedestrian is walking based on the captured image; The number of mobile units to which a patrol command for instructing the mobile units to patrol the pedestrian movement area is determined based on a type of crime that is preset in accordance with the attributes of the pedestrian. Crime prevention methods.

Images