WO2022153407A1

WO2022153407A1 - Information processing device, information processing method, and program

Info

Publication number: WO2022153407A1
Application number: PCT/JP2021/000892
Authority: WO
Inventors: 和也川上
Original assignee: 日本電気株式会社
Priority date: 2021-01-13
Filing date: 2021-01-13
Publication date: 2022-07-21
Also published as: JPWO2022153407A1

Abstract

This information processing device (100) comprises: an event information generating unit (102) that detects the occurrence of an event by processing images, and generates event information relating to the event; and a route generating unit (104) that generates an estimated movement route using the difference between the generated event information and assumed event information predetermined for that event.

Description

Information processing equipment, information processing methods, and programs

The present invention relates to an information processing device, an information processing method, and a program, and more particularly to an information processing device, an information processing method, and a program for monitoring the occurrence of an event such as a crime.

In Patent Document 1, an image captured by an imaging means mounted on a vehicle is used to detect an event such as a tilting operation or a width shift, determine the level of the detected event, and set the level to the determined level. A system that sends the corresponding information to the communication device is described. Furthermore, it is described that by saving the events that occurred in the area as mapping information, it can be used for tracking the perpetrator and predicting the escape route.

International Publication No. 2020/031924

In the system described in Patent Document 1, events that occur in the area are stored as mapping information, and when a similar event occurs, the perpetrator is tracked and the escape route is predicted. However, unless the perpetrator causes a similar event in the same area, the perpetrator cannot be tracked or the escape route cannot be predicted.

The present invention has been made in view of the above circumstances, and an object of the present invention is to be able to accurately estimate the escape route of a criminal.

In each aspect of the present invention, the following configurations are adopted in order to solve the above-mentioned problems.

The first aspect relates to an information processing device.
The information processing device related to the first aspect is
An event information generation means that detects the occurrence of an event and generates event information related to the event by processing an image, and
It has a route generation means for generating an estimated movement route by using the difference between the generated event information and the assumed event information predetermined for the event.

The second aspect relates to information processing methods performed by at least one computer.
The information processing method related to the second aspect is
Information processing equipment
By processing the image, the occurrence of an event is detected, and event information related to the event is generated.
It includes generating an estimated movement route by using the difference between the generated event information and the assumed event information predetermined for the event.

As another aspect of the present invention, it may be a program that causes at least one computer to execute the method of the second aspect, or a recording medium that can be read by a computer that records such a program. You may. This recording medium includes non-temporary tangible media.
This computer program includes computer program code that causes the computer to perform its information processing method on an information processing device when executed by the computer.

It should be noted that any combination of the above components and the conversion of the expression of the present invention between methods, devices, systems, recording media, computer programs, etc. are also effective as aspects of the present invention.

Further, the various components of the present invention do not necessarily have to be independent of each other, and a plurality of components are formed as one member, and one component is formed of a plurality of members. It may be that a certain component is a part of another component, a part of a certain component overlaps with a part of another component, and the like.

Further, although the method and the computer program of the present invention describe a plurality of procedures in order, the order of description does not limit the order in which the plurality of procedures are executed. Therefore, when implementing the method and computer program of the present invention, the order of the plurality of procedures can be changed within a range that does not hinder the contents.

Furthermore, the method of the present invention and the plurality of procedures of the computer program are not limited to being executed at different timings. Therefore, another procedure may occur during the execution of a certain procedure, a part or all of the execution timing of the certain procedure and the execution timing of the other procedure may overlap, and the like.

According to each of the above aspects, it is possible to provide a technique that can accurately estimate the escape route of a criminal.

It is a figure which shows typically the outline of the monitoring system which concerns on embodiment. It is a block diagram which illustrates the hardware configuration of the computer which realizes the information processing apparatus of the monitoring system shown in FIG. 1 and the image processing apparatus, respectively. It is a functional block diagram which shows the logical configuration example of the information processing apparatus of embodiment. It is a figure for demonstrating the data stored in a storage device. It is a flowchart which shows the operation example of the information processing apparatus of embodiment. It is a flowchart which shows the operation example of the information processing apparatus of embodiment. It is a functional block diagram which shows the logical configuration example of the information processing apparatus of embodiment.

Hereinafter, embodiments of the present invention will be described with reference to the drawings. In all drawings, similar components are designated by the same reference numerals, and description thereof will be omitted as appropriate. Further, in each of the following figures, the configuration of a portion not related to the essence of the present invention is omitted and is not shown.

In the embodiment, "acquisition" means that the own device retrieves data or information stored in another device or storage medium (active acquisition), and is output to the own device from the other device. Includes at least one of entering data or information (passive acquisition). Examples of active acquisition include making a request or inquiry to another device and receiving the reply, and accessing and reading another device or storage medium. In addition, an example of passive acquisition may be receiving information to be delivered (or transmitted, push notification, etc.). Further, the “acquisition” may be to select and acquire the received data or information, or to select and receive the delivered data or information.

(First Embodiment)
<System overview>
FIG. 1 is a diagram schematically showing an outline of the monitoring system 1 according to the embodiment. The monitoring system 1 includes an information processing device 100, an image processing device 200, and at least one camera 5. In the monitoring system 1, for example, an image processing device 200 processes an image captured by a camera 5 installed in the city to recognize a person or the like, and the information processing device 100 uses the processing result of the image processing device 200. The occurrence of an event (for example, a criminal act) is detected, and the escape route of the criminal (person 10) is estimated.

The camera 5 may be specialized for the surveillance system 1, or may use, for example, a camera that has been installed before. Alternatively, the camera 5 may be an in-vehicle camera. Further, the monitoring system 1 may further include a sensor 7 such as an odor sensor for detecting an odor, a temperature sensor, a smoke detector, a gas leak detector, or a sensor for detecting the pressing of a notification button. The sensor 7 is not limited to these, and a sensor 7 that acquires information that can be used to identify an event to be detected can be used. Further, the camera 5 may be provided with a microphone (not shown), and the surveillance system 1 may be provided with a microphone (not shown) installed separately from the camera 5. Further, the monitoring system 1 includes a storage device 300.

The storage device 300 may be a device included inside at least one of the information processing device 100 and the image processing device 200, or may be a device separate from the information processing device 100 and the image processing device 200. However, these combinations may be used.

The camera 5 generates a captured image. The camera 5 includes an image sensor such as a lens and a CCD (Charge Coupled Device) image sensor. The camera 5 may include a mechanism that controls the orientation of the camera body and the lens, zooms, focuses, and the like by following the movement of a person entering the angle of view.

The camera 5 preferably captures a range including a place where an event targeted by the information processing device 100 can occur. Further, the camera 5 may set a date and time or a period during which an event targeted by the information processing device 100 is likely to occur as a shooting time.

For example, the camera 5 can be used for streets, roads, aisles, vacant lots, back alleys, stores, etc. in times and areas where crime is frequent (for example, places with low traffic, insecure areas, tourist spots, etc.) You may take a picture of a building such as a facility, the site, a specific floor in the building, the area around the store's cash register, and so on. Alternatively, at a venue such as an event or festival that is crowded with people, the number of cameras 5, the shooting location, the shooting range, and the like may be changed according to the date and time of the event.

The image generated by the camera 5 is transmitted to the information processing device 100 or the image processing device 200 via the communication network 3. The image may be transmitted from the camera 5 to the information processing device 100 and transmitted from the information processing device 100 to the image processing device 200 for image processing, or may be transmitted from the camera 5 to the image processing device 200 and transmitted to the image processing device 200. The result of image processing may be transmitted from 200 to the information processing apparatus 100, or a combination thereof may be used.

The connection method between the camera 5 or the sensor 7 and the information processing device 100 or the image processing device 200 may be wireless or wired. In the case of wireless connection, it is assumed that the camera 5 or the sensor 7, the information processing device 100, and the image processing device 200 each have a wireless communication function. The camera 5 may be a network camera such as an IP (Internet Protocol) camera.

The methods of using the image generated by the camera 5 include (a1) learning the normal state of the shooting location, (a2) detecting the occurrence of an event, and (a3) learning the event detected in (a2).

For example, when an image is used to detect the occurrence of the event (a2), it is preferable that the image is transmitted to the information processing device 100 or the image processing device 200 in real time. However, the image transmitted to the information processing device 100 or the image processing device 200 does not have to be immediately transmitted from the camera 5, and may be an image delayed by a predetermined time. The image generated by the camera 5 is temporarily stored in a storage device (may be a storage device 300 or another storage device (including a recording medium)), and is stored in the information processing device 100 or image processing. The device 200 may read from the storage device sequentially or at predetermined intervals. Further, the image transmitted to the information processing device 100 or the image processing device 200 is preferably a moving image, but may be a frame image at predetermined intervals or a still image.

On the other hand, when the image is used for learning the occurrence event of (a3) or learning the normal state of the area in (a1), the image does not have to be transmitted to the information processing device 100 or the image processing device 200 in real time. After being once stored in the storage device (including the recording medium), the information processing device 100 or the image processing device 200 may read the image from the storage device and process it. When using an image for learning the normal state of the area in (a1), it is preferable to consider environmental information such as seasonal factors. Environmental information is, for example, forecast information of bad weather (especially rain, snow, fog, typhoon, squall, etc.) in the area, information indicating the damage situation due to natural disasters, sunset sunrise time, information indicating mass outbreak of insects. , Information indicating the occurrence status of fires (including wildfires) may be included.

For example, images that correspond to times when crimes are likely to occur (such as at night), images that distinguish between weekdays and holidays (or by day of the week), and specific occasions such as events, festivals, gatherings, and events. You may learn the corresponding place and the image corresponding to the date and time or the period respectively.

Further, after it is detected that an event has occurred, a plurality of cameras 5 may be switched and photographed so as to track the movement of a person (that is, a criminal) related to the event. Alternatively, images captured by a plurality of cameras 5 may be used to track the movement of a person associated with an event. Further, the movement of a person related to the event may be tracked by using the captured images of a plurality of cameras 5 existing along the estimated movement path generated by the path generation unit 104 described later. The person associated with the event may include the victim, for example, the accomplice may pretend to be the victim, so all persons associated with the event at that location may be tracked. ..

<Hardware configuration example>
FIG. 2 is a block diagram illustrating a hardware configuration of a computer 1000 that realizes the information processing device 100 and the image processing device 200 of the monitoring system 1 shown in FIG. 1, respectively.

The computer 1000 has a bus 1010, a processor 1020, a memory 1030, a storage device 1040, an input / output interface 1050, and a network interface 1060.

The bus 1010 is a data transmission path for the processor 1020, the memory 1030, the storage device 1040, the input / output interface 1050, and the network interface 1060 to transmit and receive data to and from each other. However, the method of connecting the processors 1020 and the like to each other is not limited to the bus connection.

The processor 1020 is a processor realized by a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or the like.

The memory 1030 is a main storage device realized by a RAM (Random Access Memory) or the like.

The storage device 1040 is an auxiliary storage device realized by an HDD (Hard Disk Drive), an SSD (Solid State Drive), a memory card, a ROM (Read Only Memory), or the like. The storage device 1040 is a program that realizes each function of the information processing device 100 of the monitoring system 1 (for example, the event information generation unit 102 and the route generation unit 104 of FIG. 3, which will be described later, or the output processing unit 106 of FIG. 7). Remember the module. When the processor 1020 reads each of these program modules into the memory 1030 and executes them, each function corresponding to the program module is realized. The storage device 1040 also functions as a storage unit (not shown) for storing various information used by the information processing device 100 or the image processing device 200. Further, the storage device 300 may also be realized by the storage device 1040.

The program module may be recorded on a recording medium. The recording medium for recording the program module includes a medium that can be used by the non-temporary tangible computer 1000, and the program code that can be read by the computer 1000 (processor 1020) may be embedded in the medium.

The input / output interface 1050 is an interface for connecting the computer 1000 and various input / output devices.

The network interface 1060 is an interface for connecting the computer 1000 to the communication network 3. The communication network 3 is, for example, a LAN (Local Area Network) or a WAN (Wide Area Network). The method of connecting the network interface 1060 to the communication network 3 may be a wireless connection or a wired connection. However, the network interface 1060 may not be used.

Then, the computer 1000 is connected to necessary devices (for example, camera 5, sensor 7, microphone (not shown), display (not shown), speaker (not shown), etc. via the input / output interface 1050 or network interface 1060). Connecting.

Since the monitoring system 1 is realized by the combination of the information processing device 100 and the image processing device 200, it is realized by a plurality of computers 1000 constituting each of them. The information processing device 100 is, for example, a server computer. The image processing device 200 may be a device separate from the information processing device 100, a device included inside the information processing device 100, or a combination thereof.

Each component of the information processing apparatus 100 of the present embodiment shown in FIG. 3 to be described later is realized by an arbitrary combination of hardware and software of the computer 1000 shown in FIG. And, it is understood by those skilled in the art that there are various modifications of the realization method and the device. The functional block diagram showing the information processing apparatus 100 of each embodiment shows blocks of logical functional units, not configurations of hardware units.

<Function configuration example>
In FIG. 3, the information processing apparatus 100 of FIG. 1 includes an event information generation unit 102 and a route generation unit 104.
The event information generation unit 102 detects the occurrence of an event and generates event information related to the event by processing the image. The route generation unit 104 generates an estimated movement route by using the difference between the generated event information and the assumed event information predetermined for the event.

Image processing is performed by the image processing device 200. The image processing device 200 analyzes an image using an image recognition model 340 described later, recognizes a person, a vehicle, etc., recognizes the behavior of the person (behavior of the criminal) and the surrounding situation (damage situation), and within the image. Identify what is happening in.

The predetermined event is, for example, a crime or an incident. Predetermined events include, for example, theft, robbery, thrilling, deportation, hit-and-run, blackmail, quarrel, violence, assault, injury or fatal injury, kidnapping, blasting, murder, street demon, terrorism, hit-and-run, fire, traffic accident ( Hit-and-run, hit-and-run, runaway, etc.), destruction of structures (damage to property), etc.

Note that, in FIGS. 1, 3, and 7, which will be described later, the information processing device 100 and the image processing device 200 are each composed of one piece of hardware (for example, a server). However, the information processing device 100 and the image processing device 200 may each be composed of a plurality of hardware (for example, a plurality of servers). For example, the event information generation unit 102 of the image processing device 200 and the information processing device 100 is realized by the first server, the route generation unit 104 is realized by the second server, and the output processing unit 106 is realized by the third server. It may be realized. Further, the image processing device 200, the event information generation unit 102 of the information processing device 100, and the route generation unit 104 may be realized by the first server and may be realized by the output processing unit 106 and the second server.

FIG. 4 is a diagram for explaining data stored in the storage device 300. The storage device 300 includes a crime database 310, an area database 320, a map database 330, an image recognition model 340, and a crime model 350. Here, the event to be detected is limited to a crime, but an event other than a crime may be included.

The crime database 310 relates to the location of the crime scene, the number of criminals, clothes, age, time taken for the crime, weapons, belongings of the criminal, the presence or absence of a victim, and damage according to the type of the above-mentioned predetermined event (crime). Stores information about a crime, including information, the criminal's actions at the time of the crime, interaction with the victim of the crime, and information such as sounds (for example, explosion sounds) and odors generated at the time of the crime.

The crime database 310 may be constructed by machine learning using past crime images and the like. Further, when a criminal act is shown in the image generated by the camera 5, the criminal database 310 may register information on the crime obtained by machine learning using the image. Further, the crime database 310 may be provided for each region. By setting it by region, it will be possible to accurately identify crimes specific to the region.

For example, in a robbery crime for tourists using firearms, a criminal riding a motorcycle or vehicle threatens the victim (tourist) with a firearm, removes the bag or money, robs it, and puts it on the motorcycle or vehicle. Get on and run away. The time required for the crime is about 30 seconds. Crime database 310 by analyzing information such as the behavior when a criminal gets off, the number of criminals, the standing position of each criminal and victim, speaking time, how to put out a weapon, time to put out a weapon, etc. You may register in.

The area database 320 stores information indicating a normal state for each area or each building. Information indicating the normal state for each area is, for example, information on people in the area (people who live in daily life, people who come to work, people who visit for short-term sightseeing or business, etc.). Gender, age, physique (height and body shape (slender, tall, petite, large, obese, etc.)), information such as vehicles traveling or parked in the area (vehicle type, color, vehicle number area) Information to be shown, etc.), or noise information, odor level information, etc. of the area concerned may be included.

The image processing device 200 collects images captured by the camera 5 for each predetermined area and each building in advance at a predetermined timing, and recognizes and learns information indicating a normal state for each predetermined area and each building. , Stored in the area database 320. The predetermined timing for collecting images is, for example, periodic, and the shooting time zone, shooting cycle, shooting day of the week, and the like may be changed depending on the shooting location.

The image processing device 200 recognizes an object such as a person, a vehicle, or dust included in the captured image, extracts a feature amount, and learns about the recognized person and the vehicle. For example, in the case of humans, image processing includes age (age), gender, clothing (dress (light clothing, full dress, heavy equipment, dirty, barefoot, etc.)), ornaments, hairstyle, hair color, physique (skeleton), etc. It is learned by the device 200 and registered in the area database 320 in association with the area or building. In the case of a vehicle, the vehicle type, the area information written on the license plate, the color of the vehicle, the color of the window (smoke), the number of passengers, etc. are learned by the image processing device 200, and are associated with the area or building in the area database 320. be registered.

Furthermore, voice is collected from the microphone (not shown) of the camera 5 for each area or building, and voice analysis is performed using a voice processing device (not shown) to perform language, noise level, emergency vehicle notification sound, and emergency bell sound. , In-house broadcasting, chimes, etc. may be learned. You may learn by acquiring the odor information for each area or each building from the odor sensor. The learned voice information and odor level information are registered in the area database 320 in association with the area or building.

The map database 330 is used not only for generating the estimated movement route, but also for displaying the generated estimated movement route described in the embodiment described later on the map. Map information includes information such as roads, passages, and means of transportation. In addition, the map information may include, for example, information on an area that neither the police nor the military can control if the criminal escapes. Since it is preferable that the criminal can be arrested before escaping to the area, it is preferable to indicate the area as well for alerting when displaying the estimated travel route.

The image recognition model 340 is used by the image processing device 200 to recognize a person or a vehicle from an image. The image recognition model 340 stores characteristic information of various people and vehicles. The image recognition model 340 may be provided for each area. By providing each area, image recognition accuracy can be achieved with high accuracy.

Similar to the area database 320, the image processing device 200 collects images captured by the camera 5 for each predetermined area and each building in advance at a predetermined timing, recognizes a person, a vehicle, or the like from the images, and has a feature amount thereof. May be registered in the image recognition model 340. The predetermined timing for collecting images is, for example, periodical or arbitrary timing, and the shooting time zone, shooting cycle, shooting day of the week, and the like may be changed according to the shooting location.

The crime model 350 stores assumed event information. Assumed event information includes, for example, the time required for a crime, the type of money stolen and the scale of damage, the presence or absence of weapons, the clothes (equipment) of the criminal, the age and gender of the criminal, and the criminal involved in the crime. Includes information such as the number of people and how to interact with the victims.

Returning to FIG. 3, the image processing device 200 recognizes a person, a vehicle, an object, etc. included in the captured image based on the normal state learned for each predetermined area and each predetermined building, and the event information generation unit 102. Uses the image recognition result to collate with the crime database 310 and detects the occurrence of a predetermined event. In addition, the type of detected event can be identified using the crime database 310.

As a method of identifying a predetermined event based on the image recognition result image-analyzed by the image processing device 200, for example, a method of determining which event (type of crime, etc.) the event is under a predetermined condition can be considered. .. The event discrimination conditions are illustrated below.

For example, in order to determine that an event is a "robbery", the following determination conditions may be used.
(B1) A weapon (learning a gun, a knife, etc.) is detected from the image, and one person A points the weapon at the other person B.
(B2) In the image, the person B raises one or both hands.
(B3) In the image, the money or thing is stolen by the person B or another person C who seems to be a collaborator, or the person B or another person D is passing it to the person A or the person C.

For example, the following determination conditions may be used to determine that an event is "theft damage by tourists (stealing of tourists)".
(C1) In the image, the person A approaches the person B and enters within a radius of 1 meter of the person B, and the person A talks to the person B.
(C2) In the image, the person A takes out something and puts something on the person B. (For example, I'm wearing a smelly thing)
(C3) In the image, person A or another person C who seems to be a collaborator is robbing the thing held by person B.
(C4) The time taken for the crime is within 30 seconds.
(C5) Nothing was destroyed by the crime.

The event information generation unit 102 may determine that the corresponding crime has occurred when the result of the image analysis satisfies all of the plurality of conditions, or may have occurred even if all the conditions are not satisfied. You may determine a crime. The event information generation unit 102 may calculate the probability (percentage, etc.) of the possibility of occurrence of an event.

When an event is detected, the event information generation unit 102 generates event information related to the event from the recognition result of the image in which the event is detected. The event information generated by the event information generation unit 102 is information indicating the detailed contents of the determined crime, accident, and incident. The event information includes, for example, the type of crime or incident, information about the characters (number of people, classification of criminal and victim, information showing the characteristics of each person), presence / absence of weapons, type of weapons, and time of crime (crime time). Time), presence / absence and scale of destroyed objects, presence / absence and condition of injured (state of lying down, sitting, movement, open eyes, bleeding, etc.) Includes at least one of the number of people, whether or not the vehicle is used, and information indicating the characteristics of the vehicle used.

The event information includes information indicating the scale of the event, but at least a part of the scale of the event is determined by using the difference between the images at the time before and after the occurrence of the event. In addition, the magnitude of the event includes the duration of the event (ie, the time taken to commit the crime). For example, it is estimated that the larger the difference between the images before and after the occurrence of the event, the larger the scale of damage caused by the event. In addition, the time taken for the crime can be calculated by measuring the time from the time when the criminal appears in the image to the time when the criminal escapes and disappears from the image.

The estimated movement route generated by the route generation unit 104 is information indicating a movement destination where a person or a vehicle related to the event detected from the image is considered to move after that, a route from the place where the event occurs to the movement destination, and the like. including. For example, if the event is a crime, the presumed travel route indicates where the criminal escapes and the route from the location of the crime to the destination. That is, when a crime occurs, the route generation unit 104 estimates the destination of the criminal's movement and the route from the place where the event occurs to the destination, and generates an estimated movement route.

The person who is the target of route estimation is not limited to criminals. Victims may be included as persons involved in the event. For example, an accomplice may pretend to be a victim or a bystander, so all persons related to the event at that location (all persons included in the image) are targeted for route estimation. May be. Alternatively, it is possible that the victim accidentally committed an injury or death to the criminal in self-defense, so all the persons related to the event at that location (all included in the image). It is preferable that the person) is the target of the route estimation.

When a criminal commits a crime, for example, an unexpected event occurs and he is in a hurry, the crime takes a long time and he is impatient, he is frustrated because he cannot take as much money as he expected, and an alarm sounds and he becomes anxious. You may fall into a situation where you do. In such a state, the criminal's thinking ability is weakened, and it is highly likely that he / she will try to act in a manner similar to his / her daily lifestyle. In other words, it can be estimated that criminals flee to places where they are likely to live on a daily basis.

In this embodiment, assumed event information indicating the content of the assumed crime is created for each type of crime and registered in the crime model 350. Then, the route generation unit 104 compares the crime model 350 with the event information generated by processing the image acquired from the camera 5, and obtains the difference. That is, the route generation unit 104 finds as a difference whether or not there is a discrepancy between the content of the assumed crime and the content of the actual crime, and sets it as the degree of excitement indicating the psychological state of the criminal. The degree of excitement may be shown, for example, in five stages from level 1 to level 5. For example, a high degree of excitement may be level 5, and a low degree of excitement may be level 1. Alternatively, the degree of excitement may be, for example, a numerical value represented by 1 to 100, and is not particularly limited.

Multiple items of criminal information can be used as judgment criteria when calculating the degree of excitement. For example, the time taken for the crime, the scale of destruction at the crime scene, and physical information indicating the physical strength of the criminal, which will be described later, are used as judgment criteria. The degree of excitement can be calculated by calculating the difference between the estimated crime event information and the actually occurring crime event information using at least one of these items. When a plurality of items are used, the difference may be totaled and divided by the number of items to obtain the degree of excitement. Alternatively, a predetermined weighting coefficient (for example, the time taken for the crime is the coefficient k1 = 0.4, the scale of destruction at the crime scene is the coefficient k2 = 0.4, and the physical information is the coefficient k3 = 0.2) for each item. You may multiply and add up.

On the other hand, in the case of a planned or organized crime, the criminal often acts calmly and there are few mistakes, so the crime ends in a short time. That is, since the crime is executed in the same manner as the assumed event information, there is no discrepancy between the assumed event information and the event information indicating the actual crime. That is, the difference between the assumed event information and the event information calculated by the route generation unit 104 becomes small, and the degree of excitement also becomes low.

From the above, the route generation unit 104 generates an estimated movement route according to the degree of excitement as follows. For example, if a criminal has a high degree of excitement, his or her thinking ability is weakened, and it is highly likely that he or she will try to act in a manner similar to his or her daily lifestyle. That is, the route generation unit 104 estimates that the criminal escapes to a place where he / she is likely to live on a daily basis, starts from the place where the crime was committed, and generates a route with this place as the destination. , Generate an estimated travel path. On the other hand, if the criminal's excitement is low, he / she can act based on calm judgment, so the escape route is likely to be in line with the plan, and there is a possibility that he / she will escape to a place farther from the crime scene or abroad. be. Therefore, when the degree of excitement is low, the route generation unit 104 estimates the bus stop or station of public transportation such as an airport or a bus or train to the airport as a destination, and uses the place where the crime was committed as the starting point. An estimated travel route is generated by generating a route with the destination as the destination.

<Operation example>
FIG. 5 is a flowchart showing an operation example of the information processing apparatus 100 of the present embodiment. When the event information generation unit 102 detects the occurrence of an event by processing the image (YES in step S101), the event information generation unit 102 generates event information regarding the detected event (step S103). Then, the route generation unit 104 generates an estimated movement route by using the difference between the generated event information and the assumed event information predetermined for the event (step S105).

More specifically, in step S101, the event information generation unit 102 causes the image processing device 200 to process the image acquired from the camera 5. The image processing device 200 uses the image recognition model 340 to recognize a person, a vehicle, a weapon, a surrounding situation, and the like from an image. The event information generation unit 102 collates the image recognition result of the image processing device 200 with the crime database 310, detects the occurrence of a crime, and identifies the type of the crime. Further, in step S103, the event information generation unit 102 generates event information using the image recognition result.

Then, in step S105, the route generation unit 104 acquires the assumed event information corresponding to the type of crime specified by the event information generation unit 102 from the crime model 350, and the assumed event information and the event information generation unit 102 Compare with the generated event information and find the difference. When the degree of excitement of the criminal indicated by the obtained difference is higher than the threshold value, for example, when the threshold value is set to level 4, the degree of excitement is level 5, the criminal's escape destination is the criminal's daily life. Estimated to be an area. In the present embodiment, for example, if the crime place is a store in a downtown area, the destination of the criminal may be a residential area in the suburbs of the crime place. Also, if the degree of excitement is level 1, there is a high possibility that the crime is organized and planned, so the criminal's destination is, for example, a nearby airport to fly high, or a limousine bus to go to the airport. It may be a platform. The route generation unit 104 generates a route to the airport or the limousine bus stop.

According to the present embodiment, the event information generation unit 102 detects the occurrence of an event by processing the image, and also generates event information regarding the detected event, and the route generation unit 104 generates the above-mentioned thing. An estimated movement route is generated using the difference between the elephant information and the assumed event information predetermined for the event. As a result, when an event such as a crime is detected from the image, it is possible to generate an estimated escape route for the criminal involved in the crime.

(Second Embodiment)
The information processing apparatus 100 of the present embodiment is the same as the above-described embodiment except that it has a configuration for generating an estimated movement path using attribute information of a person related to an event included in the captured image. Since the information processing apparatus 100 of the present embodiment has the same configuration as that of the first embodiment, it will be described with reference to FIG. However, the information processing apparatus 100 of the present embodiment may be combined within a range that does not cause a contradiction with at least one of the configurations of the other embodiments.

<Function configuration example>
The event information generation unit 102 processes an image to generate related persons related to the event and their attribute information. The route generation unit 104 generates an estimated movement route using the generated related person and its attribute information.

The related person related to the event is at least the criminal. Further, the victim or all persons present at the site, in other words, all persons included in the image or at least some of them may be related persons. Attribute information of related persons includes, for example, the number of related persons, age (age), gender, clothes (dress), ornaments (including hat, glasses, mask, mask, etc.), hairstyle, hair color, and physique (height). Includes at least one piece of information such as body shape (slender, tall, petite, large, obese, etc.). In addition, the event information generation unit 102 may include information indicating the characteristics of the vehicle used by the criminal in the attribute information of the related person. The information indicating the characteristics of the vehicle includes, for example, at least one of the vehicle type, the area information written on the license plate, the color of the vehicle, the color of the window (smoke), the number of passengers, and the like.

The route generation unit 104 uses the area database 320 to collate with the attribute information of the related person generated by the event information generation unit 102, so that the area in which the related person lives or the related person is working. Identify the building, etc. Then, as in the first embodiment, the route generation unit 104 compares the assumed event information with the event information generated from the image, obtains the difference, and uses it as the degree of excitement. Then, when the degree of excitement is high (for example, level 5), the route generation unit 104 identifies the area where the specified related person is living in daily life as the movement destination, and the route generation unit 104 identifies the area where the specified related person lives as a movement destination, and the estimated movement route from the crime scene to the movement destination. To generate. Further, as other destinations, for example, a hangout, an entertainment facility, a bar, etc. where the same age group gathers from the age group of the criminal may be the destination.

<Operation example>
FIG. 6 is a flowchart showing an operation example of the information processing apparatus 100 of the present embodiment. Step S101 of FIG. 1 corresponds to step S201 and step S205 of FIG. 6, step S103 of FIG. 1 corresponds to step S203 of FIG. 6, and step S105 of FIG. 1 corresponds to steps S209 to S215 of FIG. Is equivalent.

First, the event information generation unit 102 acquires an captured image from the camera 5 and causes the image processing device 200 to process the image (step S201). and. The event information generation unit 102 compares the crime database 310 with the image acquired from the camera 5, identifies the type of crime, and further generates the event information (step S203). Then, when the event information generation unit 102 detects the occurrence of a crime (YES in step S205), the route generation unit 104 uses the feature amount of the person extracted from the image by the image processing device 200 to use the image and the area. By comparing with the database 320, the place where the person seems to live on a daily basis (indicated as the living area of the person) is specified (step S207).

For example, in other ethnic nations, culture, language, clothes, etc. differ depending on the region. Also, in certain areas such as the Tokyo metropolitan area, people from other areas often live together in the same area. Therefore, the route generation unit 104 may be able to identify the living area of the person by identifying the language used by the person by voice analysis or by identifying clothes and the like by image processing.

Then, the route generation unit 104 acquires the crime information corresponding to the crime specified in step S203 from the crime model 350, obtains the difference from the event information generated in step S203, and calculates the degree of excitement (step S209). .. Then, when the excitement degree calculated in step S209 is equal to or higher than the threshold value, that is, when the excitement degree is high (YES in step S211), the route generation unit 104 selects the living area of the related person as the movement destination and commits the crime. An estimated movement route from the site to the movement destination is generated (step S213). Further, when the degree of excitement calculated in step S209 is less than the threshold value, that is, when the degree of excitement is low (NO in step S211), the route generation unit 104 selects an airport or the like as the destination and moves from the crime scene. The estimated movement route up to the point is generated (step S215).

For example, the event information generation unit 102 may identify from the clothes of the criminal whether or not the person uses public transportation such as a train or a bus, and whether or not the person is in an office district or a high-class residential district on a daily basis. ..

According to the present embodiment, the event information generation unit 102 generates event information using the related person related to the generated event and its attribute information, and the route generation unit 104 uses this event information to generate an estimated movement route. To generate. With this configuration, the area of the escape destination can be specified, so that the escape route can be estimated with high accuracy.

(Third Embodiment)
The information processing apparatus 100 of the present embodiment has a configuration in which the physical strength of the person is estimated by using the attribute information of the person related to the event and the estimated movement route is generated in consideration of the escapeable range. It differs from the second embodiment. Since the information processing apparatus 100 of the present embodiment has the same configuration as that of the first embodiment, it will be described with reference to FIG. However, the information processing apparatus 100 of the present embodiment may be combined within a range that does not cause a contradiction with at least one of the configurations of the other embodiments.

The storage device 300 stores standard physical information. The standard physical information includes a standard value of a person's walking speed (for example, stride length) and escape range (physical strength) in association with attribute information such as the person's face, physical information (height, weight), clothes, and gender. ..

For example, as standard physical information, a standard height of 180 cm, weight of 80 kg, age of 20s, and a male person have a stride of 1.2 meters and an escapeable range of 30 minutes. It is remembered.

This standard physical information may be included in the crime model 350. Then, the route generation unit 104 obtains the difference between this standard physical information and the physical information included in the event information generated by the event information generation unit 102, and uses the difference between this physical information and the difference between other event information. And calculate the degree of excitement.

However, it is preferable to consider the weather, country, geographical conditions, etc. in the standard physical information. That is, in rainy weather, the walking speed of the standard physical information may be slowed down, and when the movement route is uphill, the walking range (physical strength) of the standard physical information may be shortened. As the weather information, the weather forecast information of the area where the crime has occurred or the area including the estimated travel route may be obtained from a predetermined website. Moreover, it is preferable that the geographical information is registered in advance in the map database 330.

In the present embodiment, since physical information is included as event information, the event information generation unit 102 calculates the degree of excitement of the criminal in consideration of the escape ability due to the physique of the criminal and the like. As a result, an appropriate movement route can be estimated more accurately.

(Fourth Embodiment)
FIG. 7 is a functional block diagram showing a logical configuration example of the information processing apparatus 100 of the present embodiment. The information processing apparatus 100 of the present embodiment is different from the other embodiments in that it has a configuration for outputting information on a detected event and an estimated movement route. The information processing device 100 further includes an output processing unit 106 in addition to the configuration of the information processing device 100 of FIG. However, the information processing apparatus 100 of the present embodiment may be combined within a range that does not cause a contradiction with at least one of the configurations of the other embodiments.

The output processing unit 106 outputs the estimated movement route generated by the route generation unit 104 to a predetermined output destination. The output destination can be various, but for example, it may be a monitor screen for monitoring the display device 110 of the monitoring center, or a terminal (not shown) carried by a police officer or a security guard. Alternatively, it may be a monitor screen for monitoring a display device (not shown) of a police station. The output method includes at least one of display on a monitor screen, transmission of an email, and output of a voice or alarm sound from a speaker (not shown). At least one of the e-mail address to which the e-mail is sent, the IP address of the mobile terminal, and the mobile phone number may be registered in advance, or input may be accepted at the time of transmission.

Terminals include mobile phones, smartphones, tablet terminals, PDAs (Personal Digital Assistants), notebook PCs (Personal Computer) personal computers, etc.

The output content is information about the detected event, such as the time when the event occurred, the place where the event occurred, the content of the crime, the damage situation, the number of criminals, and the criminal information (face photo or attribute information analyzed from the image (for example,). Information such as gender, age, appearance, clothes, etc.)), estimated travel route, etc. may be output. The estimated movement route may output a plurality of candidates. A plurality of candidates may be output as the estimated movement destination.

Further, the output processing unit 106 may display a map showing the estimated movement route and the image of the camera 5 installed on the estimated movement route in a multi-display on the display of the monitoring center.

Further, the output processing unit 106 transmits the event information related to the crime and the information of the estimated movement route to the terminals of the police personnel who are in the vicinity of the movement destination or the route based on the estimated movement destination and the estimated movement route. May be good. By promptly reporting the crime occurrence status and escape route to the police in this way, it is possible to support the criminal to secure the criminal before the criminal escapes to an armed area where the police and the army cannot invade.

Further, the information processing device 100 may further include an operation reception unit (not shown). The operation reception unit receives the operation of the administrator of the monitoring system 1 on the various setting screens displayed on the display device 110. For example, the operation reception unit accepts a registration operation of crime information registered in the crime database 310. For example, the types and methods of crimes that occur vary from country to region. Therefore, it is preferable to construct the crime database 310 according to the area.

For example, the administrator can input a video of a past crime in the area using the operation reception unit, perform machine learning, and register it in the crime database 310. Similarly, the other area database 320, the map database 330, the image recognition model 340, and the crime model 350 can also register information specific to the area. This information is preferably updated from time to time as circumstances change.

Furthermore, in the configuration of transmitting the information of the estimated movement route to the terminal of the police official described above, when a plurality of crimes have occurred, the operation reception unit specifies the crime for which the police official is requested to support. You may also accept input of information on the scene where the crime occurred and the time when the crime occurred. For the designated crime, the output processing unit 106 identifies the terminal of the police officer existing in the vicinity of the estimated travel route, and transmits the information of the estimated travel route to the terminal of the identified police officer. May be good.

The current position of the police officer may be specified by acquiring the position information acquired by the GPS (Global Positioning System) reception function of the terminal of the police officer.

According to the present embodiment, the output processing unit 106 can output the estimated movement route generated by the route generation unit 104 to a predetermined output destination. As a result, after detecting the occurrence of an event (crime), the escape route of the criminal can be transmitted to the terminal of the police official, so that the prompt arrest of the criminal can be supported.

Although the embodiments of the present invention have been described above with reference to the drawings, these are examples of the present invention, and various configurations other than the above can be adopted.
For example, the camera 5 may acquire an image of the road from the camera 5 installed on the road that is likely to be the escape route of the criminal, and generate information indicating the congestion status of the road. The route generation unit 104 may change the movement estimation route in consideration of the road congestion situation (traffic jam information) when the criminal is escaping by using a vehicle.

In the above embodiment, the route generation unit 104 estimates one movement destination and generates an estimated movement route. In another form, the route generation unit 104 may estimate a plurality of candidates as the destination. The output processing unit 106 may plot a plurality of candidates on a map in order of proximity to the crime occurrence location and display them on the screen of the display device 110. Of the plurality of candidates for the destination, the higher the degree of excitement, the closer the destination to the crime scene may be selected, and if the degree of excitement is low, the destination far from the crime scene may be selected.

Also, multiple candidates may be estimated for the route from the place where the crime occurred to the destination. When a plurality of estimated movement routes are generated, a route having a shorter distance may be selected as the degree of excitement is higher than a plurality of candidates for the route, and a route having a longer distance may be selected when the degree of excitement is lower.

When a plurality of destinations and / or a plurality of estimated travel routes are generated, the output processing unit 106 may display all the plurality of destinations and / or the plurality of estimated travel routes on the screen of the display device 110. , Some selected destinations and / or estimated travel routes may be displayed.

Further, the route generation unit 104 may further use the event information when generating the estimated movement route. Specifically, for example, an estimated travel route may be generated according to the type of crime. For example, when the type of crime is a robbery case considered to be an organized crime, the route generation unit 104 may generate an estimated travel route with the hiding place or hideout of the organized crime group as the destination.

In addition, since it is considered to be a systematic crime when there are a plurality of related persons related to the crime, the route generation unit 104 generates an estimated movement route using the hiding place or hideout of the organized crime group as the destination. You may.

Although the present invention has been described above with reference to the embodiments and examples, the present invention is not limited to the above embodiments and examples. Various changes that can be understood by those skilled in the art can be made within the scope of the present invention in terms of the structure and details of the present invention.
When acquiring and / or using information about a user in the present invention, this shall be done legally.

Hereinafter, an example of the reference form will be added.
1. 1. An event information generation means that detects the occurrence of an event and generates event information related to the event by processing an image, and
A route generation means for generating an estimated movement route by using the difference between the generated event information and the assumed event information predetermined for the event.
Information processing device.
2. 1. 1. In the information processing apparatus described in
The event information generating means processes the image to generate related persons related to the event and their attribute information.
The route generation means is an information processing device that generates the estimated movement route using the generated related person and the attribute information thereof.
3. 3. 1. 1. Or 2. In the information processing apparatus described in
The event information is an information processing device including the scale of the event.
4. 3. 3. In the information processing apparatus described in
An information processing device in which at least a part of the scale of the event is determined by using the difference between the images at the time before and after the occurrence of the event.
5. 3. 3. Or 4. In the information processing apparatus described in
The scale of the event is an information processing device including the duration of the event.
6. 1. 1. From 5. In the information processing apparatus described in any one of
The route generation means is an information processing device that further uses the event information when generating the estimated movement route.
7. 6. In the information processing apparatus described in
The event information is an information processing device including the type of the event.
8. 6. Or 7. In the information processing apparatus described in
The scale of the event is an information processing device including the number of related persons.
9. Information processing equipment
By processing the image, the occurrence of an event is detected, and event information related to the event is generated.
An estimated movement route is generated by using the difference between the generated event information and the assumed event information predetermined for the event.
Information processing method.
10. 9. In the information processing method described in
The information processing device
The image is processed to generate related persons related to the event and their attribute information.
An information processing method for generating the estimated movement route using the generated related person and the attribute information thereof.
11. 9. Or 10. In the information processing method described in
The event information is an information processing method including the scale of the event.
12. 11. In the information processing method described in
An information processing method in which at least a part of the scale of the event is determined by using the difference between the images at the time before and after the occurrence of the event.
13. 11. Or 12. In the information processing method described in
The scale of the event is an information processing method including the duration of the event.
14. 9. To 13. In the information processing method described in any one of
The information processing device
An information processing method that further uses the event information when generating the estimated movement route.
15. 14. In the information processing method described in
The event information is an information processing method including the type of the event.
16. 14. Or 15. In the information processing method described in
The scale of the event is an information processing method including the number of related persons.
17. On the computer
A procedure for detecting the occurrence of an event by processing an image and generating event information related to the event.
A program for executing a procedure for generating an estimated movement route using the difference between the generated event information and the assumed event information predetermined for the event.
18. 17. In the program described in
A procedure for processing the image to generate related persons related to the event and their attribute information,
A program for causing a computer to execute a procedure for generating the estimated movement route using the generated related person and the attribute information thereof.
19. 17. Or 18. In the program described in
The event information is a program including the scale of the event.
20. 19. In the program described in
A program in which at least a portion of the scale of the event is determined using the difference between the images at the time before and after the event occurred.
21. 19. Or 20. In the program described in
The scale of the event is a program that includes the duration of the event.
22. 17. From 21. In the program described in any one of
A program for causing a computer to perform a procedure using the event information when generating the estimated movement route.
23. 22. In the program described in
The event information is a program including the type of the event.
24. 22. Or 23. In the program described in
The scale of the event is a program that includes the number of related persons.

1 Surveillance system 3 Communication network 5 Camera 7 Sensor 10 People 100 Information processing device 102 Event information generation unit 104 Route generation unit 106 Output processing unit 110 Display device 200 Image processing device 300 Storage device 310 Crime database 320 Area database 330 Map database 340 images Recognition Model 350 Crime Model 1000 Computer 1010 Bus 1020 Processor 1030 Memory 1040 Storage Device 1050 I / O Interface 1060 Network Interface

Claims

An event information generation means that detects the occurrence of an event and generates event information related to the event by processing an image, and
A route generation means for generating an estimated movement route by using the difference between the generated event information and the assumed event information predetermined for the event.
Information processing device.
In the information processing apparatus according to claim 1,
The event information generating means processes the image to generate related persons related to the event and their attribute information.
The route generation means is an information processing device that generates the estimated movement route using the generated related person and the attribute information thereof.
In the information processing apparatus according to claim 1 or 2.
The event information is an information processing device including the scale of the event.
In the information processing apparatus according to claim 3,
An information processing device in which at least a part of the scale of the event is determined by using the difference between the images at the time before and after the occurrence of the event.
In the information processing apparatus according to claim 3 or 4.
The scale of the event is an information processing device including the duration of the event.
In the information processing apparatus according to any one of claims 1 to 5,
The route generation means is an information processing device that further uses the event information when generating the estimated movement route.
In the information processing apparatus according to claim 6,
The event information is an information processing device including the type of the event.
In the information processing apparatus according to claim 6 or 7.
The scale of the event is an information processing device including the number of related persons.
Information processing equipment
By processing the image, the occurrence of an event is detected, and event information related to the event is generated.
An estimated movement route is generated by using the difference between the generated event information and the assumed event information predetermined for the event.
Information processing method.
In the information processing method according to claim 9,
The information processing device
The image is processed to generate related persons related to the event and their attribute information.
An information processing method for generating the estimated movement route using the generated related person and the attribute information thereof.
In the information processing method according to claim 9 or 10.
The event information is an information processing method including the scale of the event.
In the information processing method according to claim 11,
An information processing method in which at least a part of the scale of the event is determined by using the difference between the images at the time before and after the occurrence of the event.
In the information processing method according to claim 11 or 12,
The scale of the event is an information processing method including the duration of the event.
In the information processing method according to any one of claims 9 to 13.
The information processing device
An information processing method that further uses the event information when generating the estimated movement route.
In the information processing method according to claim 14,
The event information is an information processing method including the type of the event.
In the information processing method according to claim 14 or 15.
The scale of the event is an information processing method including the number of related persons.
On the computer
A procedure for detecting the occurrence of an event by processing an image and generating event information related to the event.
A program for executing a procedure for generating an estimated movement route using the difference between the generated event information and the assumed event information predetermined for the event.
In the program of claim 17,
A procedure for processing the image to generate related persons related to the event and their attribute information,
A program for causing a computer to execute a procedure for generating the estimated movement route using the generated related person and the attribute information thereof.
In the program of claim 17 or 18.
The event information is a program including the scale of the event.
In the program of claim 19.
A program in which at least a portion of the scale of the event is determined using the difference between the images at the time before and after the event occurred.
In the program of claim 19 or 20
The scale of the event is a program that includes the duration of the event.
In the program according to any one of claims 17 to 21,
A program for causing a computer to perform a procedure using the event information when generating the estimated movement route.
In the program of claim 22,
The event information is a program including the type of the event.
In the program of claim 22 or 23
The scale of the event is a program that includes the number of related persons.