JP2022031494A - Search system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a search system which allows an object person not to have necessity to possess a terminal or the like and also can efficiently search the object person.

SOLUTION: A search system 100 comprises: a server device 10 which acquires a face image of a search object person and acquires a search start range of the search object person; and camera devices 20 which are arranged in a structure such as a traffic light S and a vehicle C and each include a processing section 22 for recognizing a face included in an image and authenticating whether the recognized face coincides with a face included in the face image. The server device 10 allows the camera device 20 included in a search range to perform an imaging operation and an authentication operation, and outputs the place, time and the captured image to a terminal 30 when the recognized face coincides with the face included in the face image as a result of the authentication.

SELECTED DRAWING: Figure 1

COPYRIGHT: (C)2022,JPO&INPIT

Description

The present invention relates to a search system for searching a target person such as a wandering person.

Conventionally, in facilities such as long-term care facilities and hospitals, a system for detecting the wandering of a target person such as a facility user is already known (see, for example, Patent Document 1).

In Patent Document 1, the wearable terminal 1 identifies the area information of the facility using the position information from the beacons B1 ... Bn, and transmits the area information and the protected person information stored in advance to the face recognition verification device. .. Then, when the face recognition verification device 2 receives the captured image and the camera identification information from the cameras C1 ... Cn, it refers to the movement history database 27 and identifies the protected person who has passed through the monitored area of the cameras C1 ... Cn. It is described that it is specified by using the protection target person DB and it is determined by face recognition collation whether or not the image of the protection target person and the captured image match.

Further, Patent Document 2 describes a watching system that facilitates the search for a missing person outdoors. In Patent Document 2, face recognition data of a person to be watched is registered in a camera having a face recognition function, and when the camera detects the person to be watched in a captured image, a moving image is recorded for a certain period of time, and the moving image is recorded on the Internet. It is transmitted to the information processing device via. Then, the information processing device stores the moving image received from the camera in the storage unit, generates access information for accessing the moving image in the storage unit from the Internet, and is registered in the information processing device in association with the camera. It is stated that an e-mail containing access information will be sent to the e-mail address.

Japanese Patent No. 5876920 Japanese Unexamined Patent Publication No. 2017-11156

In the invention described in Patent Document 1, it is necessary to give the protected person a wearable terminal. However, if the protected person does not carry the wearable terminal, the area in the facility cannot be specified.

In the invention described in Patent Document 2, the face recognition data of the watching target person is registered in all the cameras having the face recognition function, and the watching target person is detected. Therefore, if the number of cameras is increased so that the search can be performed in the city, for example, the face recognition data of the person to be watched must be transmitted to many cameras, which increases the load on the information processing device and the network. .. Therefore, the efficiency of searching for the person to be watched may decrease.

Therefore, an object of the present invention is to provide a search system capable of efficiently searching the target person without the need for the target person to possess a terminal or the like.

The invention described in claim 1 made to solve the above problems includes a first acquisition unit for acquiring a face image of a target person, a second acquisition unit for acquiring a search range of the target person, and a roadside. The image pickup unit provided on at least one of the structure fixed to the body and the moving body moving on the road recognizes the face included in the image, and the recognized face matches the face included in the face image. The authentication unit to be authenticated is installed at least in a place different from the image pickup unit and the authentication unit, and the image pickup unit included in the search range is instructed to perform an image pickup operation, and the image pickup unit instructed to perform the image pickup operation performs image pickup. The subject was found when the control unit that gives an authentication instruction to the authentication unit using the image and the face image, and the face recognized as a result of the authentication by the authentication unit and the face included in the face image match. The moving body is a vehicle that patrols a specific range, and the image pickup unit provided in the vehicle includes a position acquisition unit that acquires a current position. In addition, the patrol range of the vehicle is registered in advance in the control unit, and the control unit selects the vehicle based on the patrol range, gives an instruction of the image pickup operation and the authentication, and performs the image pickup. The image pickup unit, which has received instructions for operation and authentication, is a search system characterized in that the image pickup operation and the authentication are performed based on the current position.

The invention according to claim 2 is characterized in that, in the invention according to claim 1, the search range is designated as an initial search range centered on the place of residence of the subject. do.

The invention according to claim 3 is the invention according to claim 1 or 2, in which the control unit matches the face recognized as a result of the authentication by the authentication unit with the face included in the face image. Is characterized in that a new search range is set based on the location where the image pickup unit that has captured the image of the matching face is located.

The invention according to claim 4 is the invention according to claim 1 or 2, wherein the control unit changes the search range according to the passage of time.

The invention according to claim 5 further comprises a third acquisition unit for acquiring information indicating the end of the search of the subject in the invention according to any one of claims 1 to 4, and the control thereof. The unit is characterized in that the search range is changed until the information indicating the end of the search of the target person is acquired, and the authentication unit is made to perform the authentication.

The invention according to claim 6 is the case where there are a plurality of the authentication units in which the recognized face and the face included in the face image match in the invention according to any one of claims 1 to 5. The control unit causes the requester to select one image from a plurality of recognized facial images, and sets a new search range based on the location of the authentication unit corresponding to the selected image. It is characterized by doing.

The invention according to claim 7 is the invention according to any one of claims 1 to 6, wherein the structure includes a street light or a traffic signal installed along a road. And.

The invention according to claim 8 is the invention according to any one of claims 1 to 7, wherein the image pickup unit is provided in the headlight of the vehicle.

The invention according to claim 9 is characterized in that, in the invention according to any one of claims 1 to 8, the image pickup unit is installed so as to take an image centering on a sidewalk. ..

According to this embodiment, it is not necessary for the search target person to possess a wearable terminal or the like. Further, since only the image pickup unit and the authentication unit instructed by the control unit can be operated, only the image pickup unit in the search range operates. Therefore, the position of the subject can be easily grasped and the search can be made efficient.

It is a schematic block diagram of the search system which concerns on one Embodiment of this invention. It is a functional block diagram of the server apparatus shown in FIG. It is a functional block diagram of the camera apparatus shown in FIG. It is explanatory drawing when the camera device is installed in a vehicle. It is a front view when the camera device is installed in the headlight of a vehicle. It is a flowchart of the operation of the search system shown in FIG. It is a flowchart of the operation of another search system.

Hereinafter, an embodiment of the present invention will be described with reference to FIGS. 1 to 7. FIG. 1 is a schematic configuration diagram of a search system according to an embodiment of the present invention. The search system 100 shown in FIG. 1 includes a server device 10 and a camera device 20. In the following description, a wandering person such as a dementia patient is mainly described as a search target person (target person), but a child, a criminal, or the like may be a search target person.

The server device 10 is a well-known server computer installed in a business establishment or the like of a business operator or the like that provides a service related to the search system 100. As shown in FIG. 1, the server device 10 is communicably connected to a network N such as the Internet. The functional configuration of the server device 10 is shown in FIG.

As shown in FIG. 2, the server device 10 includes a communication unit 11, a processing unit 12, and a storage unit 13. In the communication unit 11, for example, the network interface of the server device 10 functions, and the processing result of the processing unit 12 and the like are transmitted to the camera device 20 described later, and various data transmitted from the camera device 20 and the terminal 30 described later and the like. To receive.

For example, the CPU (Central Processing Unit) of the server device 10 functions in the processing unit 12, performs predetermined processing based on the information received by the communication unit 11 and stores it in the storage unit 13, or via the communication unit 11. And send it to the camera device 20 and so on. The processing performed by the processing unit 12 includes, for example, registration of the face image of the search target person and the search start area, which will be described later, transmission of the registered face image to the camera device 20 in the search target area, and transmission of the search result to the terminal 30. Etc. That is, the server device 10 functions as a first acquisition unit for acquiring the face image of the target person and a second acquisition unit for acquiring the search range of the target person.

For example, the storage device of the server device 10 functions in the storage unit 13, and the processing result or the like by the processing unit 12 is stored as described above. For example, the face image of the search target person to be registered, the search start area, and the like are stored.

As shown in FIG. 1, the camera device 20 is composed of a device provided in the traffic signal S (camera device 20a) and a camera device 20 provided in the vehicle C (camera device 20b). That is, the camera device 20 functions as an image pickup unit provided in a structure fixed along the road and a moving body moving on the road. Further, as will be described later, the camera device 20 also functions as an authentication unit that recognizes the face included in the image and authenticates whether the recognized face matches the face included in the face image.

The camera device 20a is installed in a structure fixed along the road such as a traffic signal S and a street light. In FIG. 1, the traffic signal S is a pedestrian traffic light, but it may be a vehicle traffic light. The camera device 20a may be installed in a sign, a signboard, a roadside tree or a wall, a building such as a building or a house, a vending machine, or the like, as long as it is a structure fixed along the road. .. The camera device 20a is installed so as to take an image centering on a sidewalk provided on the road. In the case of a road without a sidewalk, it is installed so as to image the end of the road. In short, it suffices if it is installed so that the face of a pedestrian passing through the road can be imaged.

The functional configuration of the camera device 20a is shown in FIG. 3 (a). As shown in FIG. 3A, the camera device 20a includes a communication unit 21, a processing unit 22, and a camera unit 23. The communication unit 21 is composed of a wireless communication interface or the like for communicating with the server device 10 via the network N. The communication unit 21 receives information such as a face image and a search area transmitted from the server device 10, and transmits information such as a face authentication result in the processing unit 22 described later to the server device 10.

The processing unit 22 performs face recognition processing of the face included in the image captured by the camera unit 23, which will be described later, based on the face image received by the communication unit 21 and the search area. The camera unit 23 includes an image pickup element such as a CCD (Charge Coupled Device) image sensor or a CMOS (Complementary Metal Oxide Semiconductor) image sensor, and has a function of taking an image of the camera device 20a.

As shown in FIG. 1, the camera device 20b is provided on the vehicle C as a moving body. Here, the vehicle on which the camera device 20b is installed is a vehicle of a business operator such as a delivery company, a postal service company, a taxi business operator, or the like, which delivers and patrols an area within a predetermined range. Further, the area under the jurisdiction may be a vehicle (police car, fire engine, ambulance, etc.) such as a police or fire engine whose jurisdiction is predetermined. The type of vehicle is not limited to automobiles, but may be motorcycles, bicycles, or the like.

The functional configuration of the camera device 20b is shown in FIG. 3 (b). As shown in FIG. 3B, the configuration of the camera device 20b is the same as that in FIG. 3A, but since it is installed in a mobile body, the current position of the GPS (Global Positioning System) receiver 25 or the like can be determined. The current position information is acquired from a device that can detect it, or it has a current position detection function.

Further, the camera device 20b is installed, for example, above the windshield or on the dashboard so as to take an image of the front of the vehicle. Then, as shown in FIG. 4, the camera device 20b is installed so as to take an image centering on the direction in which a pedestrian such as a sidewalk passes. FIG. 4 is a view of the vehicle C traveling on the roadway RW as viewed from above. In FIG. 4, the road is provided with a roadway RW and a sidewalk SW. Then, the vehicle C is traveling on the roadway RW in the direction of the arrow in the figure. At this time, the camera device 20b is installed in the vehicle C so as to focus on the sidewalk SW instead of the roadway RW, and faces the left front in FIG. 4, and images the range indicated by the reference numeral A. ing.

The camera device 20b may be configured as a part of the drive recorder by using, for example, a wide-angle lens, but it is preferable to provide the camera device 20b separately from the drive recorder because the purpose is to capture the face of a pedestrian. Further, the camera device 20b is not limited to taking an image of the front of the vehicle as shown in FIG. 4, and may be installed so as to take an image of the direction of the sidewalk SW, for example, the left side of the vehicle C.

Further, the camera device 20b may be provided in the headlight of the vehicle C. FIG. 5 shows an example in which the camera device 20b is provided in the headlight. FIG. 5 is a front view of the headlight 50. The headlight 50 includes a lamp body 51, a front cover 52, a high beam headlight unit 53, and a low beam headlight unit 54. The lamp body 51 has an opening on the front side of the vehicle C, and the front cover 52 is made of a translucent resin, glass, or the like, and is attached to the opening of the lamp body 51 to form a lamp chamber inside. To form. The high beam headlight unit 53 and the low beam headlight unit 54 are arranged inside the lighting chamber.

The camera device 20b is installed between the high beam headlight unit 53 and the low beam headlight unit 54. The installation position of the camera device 20b in the headlight 50 is not limited to between the high beam headlight unit 53 and the low beam headlight unit 54. It may be at least within the range of the lamp body 51.

The terminal 30 is composed of, for example, a mobile device such as a smartphone, a personal computer, or the like. In the terminal 30, the search requester transmits a face image such as a face photograph of the search target person to the server device 10. Further, the search start area of the search target person is designated and transmitted to the server device 10. The search start area can be, for example, the place of residence (address) of the person to be searched. Alternatively, the search target area may be any place (missing place) such as a station or a facility.

Further, when the search target person is found, the terminal 30 is notified of the information that the search target is found from the server device 10. This information may be notified by e-mail by registering an e-mail address in the server device 10 in advance, or may be notified by other means such as SNS (Social Networking Service).

Next, the operation of the search system 100 having the above-described configuration will be described with reference to the flowchart of FIG.

First, the face image of the search target person and the search start area are registered in the server device 10 from the terminal 30 (step S11). The face image transmitted from the terminal 30 and the search start area are stored in the storage unit 13 of the server device 10 in association with a predetermined user ID or the like. Further, the face image is preferably an image viewed from the front because it is used for face recognition described later. Further, a plurality of facial images may be registered for each search target person.

The search start area is an area where the search is started when a search start request, which will be described later, is received. This area can be designated, for example, in units of cities, wards, towns and villages such as "Chuo-ku, Tokyo" and in units of town names such as "Ginza, Chuo-ku, Tokyo". However, if the range is too wide, the number of operating camera devices 20 will increase, the load of the search process will increase, and the search efficiency will decrease. Therefore, it is desirable not to make the range too wide. When the registration of the search start area is set as the place of residence, a predetermined range such as a radius of 500 m may be set as the actual search start area around the place of residence.

Further, when the terminal 30 has a function of detecting the current position, the server device 10 may acquire the current position of the terminal 30 and set a predetermined range such as a radius of 500 m around the current position as a search start area. The case of setting the search start area from the current position of the terminal 30 is effective when the user is out of the office.

Since step S11 basically needs to be performed once, it can be omitted if the face image or the like has already been registered.

Next, the server device 10 determines whether or not there is a search request from the requester (terminal 30) (step S12). If there is no search request (step S12; N), step S12 is repeated. On the other hand, when there is a search request (step S12; Y), the processing unit 12 of the server device 10 reads the face image of the search target person and the information of the search start area from the storage unit 13 and sets the read search start area. A face image of the search target person is transmitted to the located camera device 20 to instruct the start of the imaging operation and the face recognition operation (step S13). That is, the server device 10 functions as a control unit that instructs the image pickup unit included in the search range to perform an image pickup operation and gives an authentication instruction to the authentication unit based on the image and the face image captured by the image pickup unit that has instructed the image pickup operation.

In step S13, the position of the structure fixed along the road such as the traffic signal S does not change. Therefore, if the position information of the structure in which the camera device 20 is installed is registered in the server device 10 in advance, the search start area can be reached. You can judge whether it is located. On the other hand, since a moving body such as a vehicle C moves, accurate position information cannot be registered in the server device 10 in advance like a structure. Therefore, in the present embodiment, for example, the delivery of a moving body equipped with the camera device 20b, the range to be patrolled, the area under the jurisdiction, etc. are registered in advance for each prefecture, city, ward, town, village, etc., and the registered delivery and patrolling are performed. If the range or the area under the jurisdiction includes even a part of the search start area, the face image and the search start area may be transmitted as an operation target to instruct the imaging operation and the face recognition operation.

Then, in the camera device 20b to which the face image and the search start area are transmitted, the current position detected by the GPS receiver 25 and the search start area are collated, and if they match, the process proceeds to the next step, and if they do not match, the process proceeds to the next step. Discards the face image and the like and stops the operation.

For example, when the search start area is "Ginza, Chuo-ku, Tokyo", the face image and the search start area are transmitted to the vehicle C of the delivery company whose delivery range is "Chuo-ku, Tokyo", and the image pickup operation and face recognition operation are performed. Is instructed. Then, when the current position of the vehicle C is "Ginza, Chuo-ku, Tokyo", the next step is executed in the camera device 20b, but when the current position is "Tsukiji, Chuo-ku, Tokyo", the camera device is executed. 20b discards the face image and the like and stops the operation. That is, after narrowing down the target camera device 20b on the server device 10 side, a face image or the like is transmitted, and the camera device 20b side finally determines whether or not it is the target based on the current position.

That is, the camera device 20 also functions as a position acquisition unit for acquiring the current position. Then, the patrol range of the vehicle is registered in the server device 10 in advance, and the image pickup operation and the authentication are instructed based on the patrol range, and the camera device 20 receiving the instruction takes an image based on the current position. It is operating and authenticating.

Next, the camera device 20 to which the face image is transmitted in step S13 starts collation (face recognition) between the received face image and the camera image (image captured by the camera unit 23) (step S14). That is, a face is recognized from the image captured by the camera unit 23, and the recognized face and the face image are collated to determine whether they are the same face. The algorithm for face recognition is not particularly limited as long as a well-known method is used.

Next, the camera device 20 in which the face image and the captured image match in step S14 transmits the location, time, and the collated image (captured image) to the server device 10 (step S15). In step S15, since the location is registered in the server device 10 in the case of a structure, it may be an identifier (ID) or the like that can identify the structure. Further, in the case of a moving body, information on the current position is transmitted by the GPS receiver 25 or the like. That is, the place, the time, and the captured image are included in the information indicating that the subject has been found.

Next, the server device 10 transmits the location, time, and captured image received from the camera device 20 to the terminal 30 (search requester). Then, a new search area is set centering on the place received from the camera device 20 (the place where it is detected that the face recognition matches) (step S16). As described above, it may be transmitted to the terminal 30 by e-mail, SNS, or the like. Further, it may be transmitted to an administrative agency such as the police in addition to the terminal 30. The new search area shall be, for example, within a radius of 500 m centered on the location. Alternatively, it may be the range of the town name indicated by the place.

That is, the server device 10 functions as an output unit that outputs information indicating that the target person has been found when the face recognized as a result of the authentication by the authentication unit matches the face included in the face image. Further, when the face recognized as a result of the authentication by the authentication unit matches the face included in the face image, the server device 10 is newly based on the location where the image pickup unit that captured the image of the matched face is located. The search range is set.

Next, the server device 10 outputs a collation end (operation end) instruction to the operating camera device 20 that is out of the new search range installed in step S16 (step S17). In the case of a moving object, information indicating a new search range is transmitted from the server device 10 to the camera device 20b to which the operation instruction is transmitted, and the camera device 20b determines whether or not the search range is out of the search range based on the current position. good.

Next, the server device 10 determines whether or not the search is completed (step S18). The determination of the end of the search may be made based on whether or not the information indicating the end of the search has been received from the terminal 30. This is because, for example, when the search requester can meet the search target person, or when the police or other related parties can protect the search target person, information indicating the end of the search is transmitted from the terminal 30. If.

If the search is not completed as a result of the determination in step S18 (step S18; N), the process returns to step S13, and a face image is transmitted to the camera device 20 included in the search range based on the new search area. .. On the other hand, when the search is completed as a result of the determination in step S18 (step S18; Y), the flowchart is terminated.

That is, the server device 10 functions as a third acquisition unit that acquires information indicating the end of the search for the target person, and changes the search range until the information indicating the end of the search for the target person is acquired, and the authentication unit. To authenticate.

According to the present embodiment, the search system 100 is provided in a server device 10 that acquires a face image of a search target person and acquires a search start range of the search target person, a structure such as a traffic signal S, and a vehicle C. A camera device 20 having a processing unit 22 that recognizes a face included in an image and authenticates whether or not the recognized face matches the face included in the face image. Then, the server device 10 causes the camera device 20 included in the search range to perform an imaging operation and the above-mentioned authentication operation, and when the face recognized as a result of the authentication matches the face included in the face image, the location thereof. , Time and the captured image are output to the terminal 30.

By configuring the search system 100 as described above, it is not necessary for the search target person to possess a wearable terminal or the like. Further, since only the camera device 20 instructed by the processing unit 12 of the server device 10 can be operated, only the camera device 20 included in the search range is operated. Therefore, the position of the person to be searched can be easily grasped and the search can be made efficient. In addition, by finding and protecting the search target at an early stage in this way, it is possible to reduce traffic accidents and railway accidents.

In addition, the area centered on the place of residence of the person to be searched may be the search start area. By doing so, for example, when a dementia patient or the like wanders outside the home and goes missing, the search can be started from a range centered on the home.

Further, when the face captured as a result of face authentication by the processing unit 22 of the camera device 20 and the face included in the face image match, the server device 10 is located at a place where the camera device 20 that has detected the match is located. A new search range is set based on this. By doing so, when the search target person is found by face recognition, the search range can be reset based on the found place. Therefore, it is possible to track the person to be searched even if the person to be searched moves.

Further, the server device 10 acquires information indicating the end of the search of the search target person, changes the search range until the information indicating the end of the search is acquired, and operates the camera device 20 included in the search range. .. By doing so, the search target person can be tracked until the end of the search.

Further, since the camera device 20a is provided on the traffic signal S installed along the road, it is easy to take an image of a pedestrian passing on a sidewalk or the like. Moreover, since the existing infrastructure equipment can be used, the introduction cost can be reduced.

Further, the patrol range of the vehicle C is registered in advance in the server device 10, and the camera device 20b is instructed to perform an imaging operation and the authentication based on the patrol range, and the camera device is provided in the vehicle C. The camera device 20b has acquired the current position, and the camera device 20b, which has been instructed to perform the imaging operation and the authentication, performs the imaging operation and the authentication based on the current position. By doing so, only the camera device 20b installed in the vehicle C traveling in the search range can be operated. Therefore, the processing load of the server device 10 and the traffic on the network N can be reduced.

Further, since the moving body is a vehicle that patrols a specific range, unlike a private car or a long-distance truck, there are many opportunities to travel in the search range and the possibility of finding a search target person is high. Moreover, since the existing vehicle can be used, the introduction cost can be reduced.

Further, since the camera device 20 is installed so as to take an image centering on the sidewalk, it is easy to take an image of the face of a pedestrian passing through the sidewalk even when the camera device 20 is installed on a moving body such as a vehicle. Will be.

Further, the camera device 20 may be provided in the headlight of a vehicle or the like. By doing so, the installation position of the camera device 20 can be lowered, so that even a pedestrian walking with his face facing down can easily recognize his face.

Depending on the accuracy of face recognition, in the search area, a place, a time, and an image may be received from a plurality of camera devices 20, that is, information indicating that a search target person has been found in a plurality of places may be received. In that case, instead of automatically setting a new search area in step S16, a plurality of images are transmitted to the terminal 30 (search requester), and one image is selected by the search requester from among them. , A new search area may be set based on the location where the selected image was captured.

FIG. 7 shows a flowchart when a plurality of information indicating that the search target person has been found is received. In the flowchart shown in FIG. 7, steps S16a to S16d are added to the flowchart shown in FIG. In FIG. 7, as a result of step S15, it is determined whether the server device 10 has received a plurality of places, times, and camera images, that is, whether a search target person has been found at a plurality of places (step S16a). If it is not found at a plurality of places (step S16a; N), the process proceeds to step S16 and the operation is the same as the flowchart of FIG. On the other hand, if it is found at a plurality of places (step S16a; Y), the server device 10 transmits the plurality of places, times, and camera images to the terminal 30 (step S16b).

Then, the terminal 30 that has received the plurality of places, times, and camera images presents the information to the search requester to select one image. The server device 10 receives the selection result in the terminal 30 (step S16c), and sets a new search area based on the location indicated by the selection result (step S16d).

That is, when there are a plurality of authentication units in which the recognized face and the face included in the face image match, the control unit selects one image from the plurality of recognized face images, and selects one image as the selected image. A new search range may be set based on the location of the corresponding authentication unit. By doing so, even if the search target person is found in a plurality of places, it is possible to select a more appropriate place by asking the search requester for instructions. Therefore, it can contribute to the early detection of the person to be searched.

Further, in the above-described embodiment, when a search target person is found, a new search area is set based on the discovery location. For example, the search request is delayed and the search target person sets the search start area. If it is exceeded, it cannot be found in the search start area. Therefore, the adjacent area may be set as a new search area according to the passage of time. For example, one hour after the start of the search, the area adjacent to the search start area is set as a new search area. Then, one hour after the start of the search in the new search area, the adjacent area is set as the new search area. That is, the search range may be changed according to the passage of time. The time for changing the search area may be appropriately set according to the size of the search range (town name unit, city / ward / town / village unit). Note that the change is not limited to changing to an area that does not include the current search area, but also includes adding a new area to the current search area. Further, in the explanation of the flowchart shown in FIG. 6, the new search area may be added to the current search area in the same manner.

Further, in the above-described embodiment, face authentication is performed by the camera device 20, but it may be performed by the server device 10. When face recognition is performed by the server device 10, only an instruction indicating the start of imaging is transmitted instead of transmitting a face image or the like to the camera device 20 included in the search area. Upon receiving the instruction indicating the start of imaging, the camera device 20 starts imaging and transmits an image capable of recognizing the face of a pedestrian to the server device 10. Then, the server device 10 performs face recognition based on the received image and the face image.

Further, the camera device 20 may be provided in either a structure or a vehicle (moving body). However, it is preferable to provide both of them because the search target can be found earlier.

The present invention is not limited to the above embodiment. That is, those skilled in the art can carry out various modifications according to conventionally known knowledge within a range that does not deviate from the gist of the present invention. As long as the search system of the present invention is still provided by such a modification, it is, of course, included in the category of the present invention.

10 Server device (1st acquisition unit, 2nd acquisition unit, control unit, output unit, 3rd acquisition unit)
11 Communication unit 12 Processing unit 13 Storage unit 20 Camera device (imaging unit, authentication unit, position acquisition unit)
21 Communication unit 22 Processing unit 23 Camera unit 100 Imaging system C Vehicle (mobile)
S Traffic signal (structure)

Claims (9)

The first acquisition unit that acquires the face image of the target person,
The second acquisition unit that acquires the search range of the target person,
An image pickup unit provided in at least one of a structure fixed along the road and a moving body moving along the road.
An authentication unit that recognizes the face included in the image and authenticates whether the recognized face matches the face included in the face image.
The image and the face image taken by the image pickup unit, which is installed at least in a place different from the image pickup unit and the authentication unit, instructs the image pickup unit included in the search range to perform an image pickup operation, and instructs the image pickup operation, are used. A control unit that gives an authentication instruction to the authentication unit,
An output unit that outputs information indicating that the target person has been found when the face recognized as a result of authentication by the authentication unit matches the face included in the face image, and an output unit.
Equipped with
The moving body is a vehicle that patrols a specific range and moves.
The image pickup unit provided in the vehicle includes a position acquisition unit that acquires a current position.
The patrol range of the vehicle is registered in advance in the control unit.
The control unit selects the vehicle based on the patrol range, gives instructions for the imaging operation and the authentication, and gives instructions.
The image pickup unit that has received the instruction of the image pickup operation and the authentication performs the image pickup operation and the authentication based on the current position.
A search system characterized by that. The search system according to claim 1, wherein the search range is designated as an initial search range centered on the place of residence of the subject. When the face recognized as a result of the authentication by the authentication unit matches the face included in the face image, the control unit is newly based on the location where the image pickup unit that captured the image of the matched face is located. The search system according to claim 1 or 2, wherein the search range is set. The search system according to claim 1 or 2, wherein the control unit changes the search range according to the passage of time. Further provided with a third acquisition unit for acquiring information indicating the end of the search for the subject.
The control unit changes the search range until information indicating the end of the search for the target person is acquired, and causes the authentication unit to perform the authentication.
The search system according to any one of claims 1 to 4, wherein the search system is characterized in that. When there are a plurality of the authentication units in which the recognized face and the face included in the face image match, the control unit causes the client to select one image from the plurality of recognized face images and select the image. The search system according to any one of claims 1 to 5, wherein a new search range is set based on the location where the authentication unit corresponding to the image is located. The search system according to any one of claims 1 to 6, wherein the structure includes a street light or a traffic signal installed along a road. The search system according to any one of claims 1 to 7, wherein the image pickup unit is provided in the headlight of the vehicle. The search system according to any one of claims 1 to 8, wherein the image pickup unit is installed so as to take an image centering on a sidewalk.

Images