JP2021036646A - Information collection system, camera terminal device, information collection method and information collection program - Google Patents

Abstract

To provide an information collection system capable of collecting additional information on the basis of an image of a search object person, a camera terminal device, an information collection method and an information collection program.SOLUTION: An information collection system 100 includes a camera terminal device 1, and a server device 7. The camera terminal device 1 includes an object information acquisition part for acquiring object face image information on a face image of a search object person, and an image recognition part for recognizing an image coincident with the object face image information from a photographed video. The server device 7 includes an object information transmission part for transmitting the object face image information to the camera terminal device 1, and an image processing part for detecting face images reflected around the face image coincident with the object face image information in the video acquired from the camera terminal device 1 in the case that the image recognition part of the camera terminal device 1 recognizes the coincident image.SELECTED DRAWING: Figure 1

Description

The present invention relates to, for example, an information collecting system, a camera terminal device, an information collecting method, and an information collecting program for collecting information about a search target person.

In recent years, a system has been developed that searches for a target person from images taken by a surveillance camera installed indoors or outdoors in a store or the like.

For example, Patent Document 1 discloses a person search system that can confirm the whereabouts of group members. In this person search system, registration information including facial images of all group members is recorded in a mobile terminal possessed by each member when entering an amusement park or the like. When a member wants to know the whereabouts of other members, search for an image of a person's face image that matches the member's face image recorded on the mobile terminal from the images taken by each surveillance camera in the facility. I try to do it.

Japanese Unexamined Patent Publication No. 2004-177997

In the conventional person search system described in Patent Document 1, for example, a member's face image is photographed and registered at the time of admission, and the search is performed based on the registered face image. It was not suitable for the case of searching for the person. When searching for a specific person in a case, it takes time to search if there is insufficient information that can be used as a clue, such as the face image to be collated is an old one taken in the past.

The present invention has been made in view of such circumstances, and an object of the present invention is an information collection system, a camera terminal device, an information collection method, and an information collection system capable of collecting additional information based on an image of a search target person. It is to provide an information gathering program.

The information collecting system according to an aspect of the present invention includes a target information acquisition unit that acquires target face image information related to the face image of the search target person, and an image recognition unit that recognizes an image that matches the target face image information from the captured image. When a matching image is recognized by the camera terminal device having the above, the target information transmitting unit for transmitting the target face image information to the camera terminal device, and the image recognition unit, the image acquired from the camera terminal device. Among them, a server device having an image processing unit for detecting a face image appearing around the face image matching the target face image information is provided.

The information collecting system of another aspect of the present invention includes a target information acquisition unit that acquires target face image information related to the face image of the search target person, and image recognition that recognizes an image that matches the target face image information from the captured image. A predetermined distance from the camera terminal device when a matching image is recognized by the camera terminal device having the unit, the target information transmitting unit that transmits the target face image information to the camera terminal device, and the image recognition unit. The present invention includes a server device having an image processing unit that acquires video data from another camera terminal device existing within the range and recognizes an image that matches the target face image information among the earned video data.

Another aspect of the present invention is a camera terminal device. This camera terminal device includes a target information acquisition unit that acquires target face image information related to the face image of the search target person, an image recognition unit that recognizes an image that matches the target face image information from the captured image, and the image recognition. It is provided with an image processing unit that detects a face image appearing around the face image that matches the target face image information when a matching image is recognized by the unit.

Another aspect of the present invention is an information gathering method. This information collecting method includes a target information acquisition step of acquiring target face image information related to a search target person's face image, an image recognition step of recognizing an image matching the target face image information from a captured image, and the image recognition. When a matching image is recognized by the step, an image processing step of detecting a face image appearing around the face image matching the target face image information in the video is provided.

According to the present invention, additional information can be collected based on the image of the search target person.

It is a schematic diagram for demonstrating the communication connection in the information gathering system which concerns on Embodiment 1. FIG. It is a block diagram which shows the structure of a camera terminal apparatus. It is a block diagram which shows the structure of a server apparatus. It is a flowchart which shows the procedure of the update processing of the parameter for image inference processing. It is a flowchart which shows the procedure of the information collection processing when the search target person is recognized in the image. It is a flowchart which shows the procedure of the information extraction processing which extracts additional information in a server apparatus. It is a flowchart which shows the procedure of the information extraction processing which extracts additional information in a server apparatus. It is a flowchart which shows the procedure of the information gathering processing which concerns on Embodiment 2. It is a flowchart which shows the procedure of other information collection processing. It is a block diagram which shows the structure of the camera terminal apparatus which concerns on Embodiment 3. It is a schematic diagram which shows the procedure of the information gathering processing which concerns on Embodiment 4.

Hereinafter, the present invention will be described with reference to FIGS. 1 to 11 based on a preferred embodiment. The same or equivalent components and members shown in the drawings shall be designated by the same reference numerals, and redundant description will be omitted as appropriate. In addition, some of the members that are not important for explaining the embodiment in each drawing are omitted and displayed.

(Embodiment 1)
FIG. 1 is a schematic diagram for explaining a communication connection in the information collection system 100 according to the first embodiment. The information collection system 100 includes a camera terminal device 1, a display terminal 6, a server device 7, a management device 8, and the like, and can collect information for searching for a specific person and provide information to a searcher. In order to search for a specific person who is a search target person, the information collection system 100 uses information about the face image of the person (hereinafter, referred to as target face image information).

The camera terminal device 1 is, for example, a drive recorder 1a, a body warn camera 1b, or the like. The drive recorder 1a is a device that generally records an image of the outside of the vehicle, such as the front, as seen from the vehicle 5 being driven, and recognizes a specific face image by being provided with an image inference processing function. The drive recorder 1a is installed in, for example, a police vehicle, a vehicle of a security company cooperating in a search, a taxi, a truck, or the like, and exchanges video and audio information through a communication network 9 such as a mobile phone network.

The body warn camera 1b records an image in the same manner as the drive recorder 1a, and recognizes a specific face image by providing an image inference processing function. The body warn camera 1b can be worn on the body such as the upper body by police officers, security guards who cooperate in the search, and the like, and exchanges video and audio information through a communication network 9 such as a mobile phone network.

The display terminal 6 is, for example, a smartphone 6a, an HMD (head-mounted display) device 6b, or the like. The smartphone 6a and the HMD device 6b are carried by the searcher, receive a face image, collected information, and the like of the search target person via the communication network 9, and display the images and information. The HMD device 6b is, for example, a glasses-type device, and the searcher can search while watching the projected image by wearing the HMD device 6b on his face.

The server device 7 generates a parameter for image inference processing for recognizing the face image in the camera terminal device 1 with respect to the face image of the search target person. The parameters for image inference processing are included in the above-mentioned target face image information. The server device 7 has a function of transmitting the target face image information including the generated parameters for image inference processing to the camera terminal device 1 via the communication network 9. Further, the server device 7 has a function of receiving information such as an image (hereinafter, referred to as collected information) acquired by the camera terminal device 1 in recognition of the face image via the communication network 9.

Further, the server device 7 has a function of delivering a face image of the search target person, collected information, and the like to the display terminal 6 carried by the searcher via the communication network 9. The management device 8 sets information such as a face image of the search target person in the server device 7, and controls information notification to the searcher.

FIG. 2 is a block diagram showing the configuration of the camera terminal device 1. The camera terminal device 1 includes a video input unit 11, an image recognition unit 12, a control unit 13, a communication unit 14, a collected information generation unit 15, and the like. Each part of the camera terminal device 1 can be realized by an electronic element such as a computer CPU or a mechanical component in terms of hardware, and can be realized by a computer program or the like in terms of software. It depicts a functional block realized by. Therefore, it is understood by those skilled in the art that these functional blocks can be realized in various forms by combining hardware and software.

In the camera terminal device 1, an image is captured by a detector such as a CCD to generate an image signal, and the image signal is input to the image input unit 11. The video signal input to the video input unit 11 is output to the image recognition unit 12 and the video / audio compression unit 16.

The image recognition unit 12 has an image inference processing circuit, and recognizes whether the face image of the search target person exists in the image in the video signal by image inference based on the target face image information acquired from the server device 7. Is executing the process to be performed. As described above, the target face image information includes parameters for image inference processing. The image inference processing circuit included in the image recognition unit 12 constitutes a learning type model such as a neural network, and determines whether or not an image matching the face image of the search target person exists in the input image. Image recognition by inferring. The server device 7 generates parameters for image inference processing in the learning model by learning an equivalent learning model in advance based on the face image of the search target person, and gives the parameters to the camera terminal device 1. The parameters for image inference processing represent each parameter set in the image inference processing circuit included in the image recognition unit 12. For the image inference processing in the image recognition unit 12 and the face image information generation unit 72 of the server device 7 described later, various image inference processing methods that have been researched and developed in various technical fields or are used can be used.

The video / audio compression unit 16 performs data compression processing on the input video signal and the audio signal input to the audio input unit 18 to generate video data and audio data to be recorded. The video data and audio data compressed by the video / audio compression unit 16 are recorded in the video / audio recording unit 17. The video / audio recording unit 17 has a storage medium such as a USB memory or an SD card, and records video data and audio data in the storage medium.

The control unit 13 controls the entire operation of the camera terminal device 1 from the start of shooting a video, the recording of video data and audio data, to the end of shooting. Further, the control unit 13 acquires various sensor information from the sensor input unit 19 and outputs the various sensor information to the collected information generation unit 15. In the sensor input unit 19, position information by GPS or the like and 9-axis sensor information are input as information accompanying video and audio. The 9-axis sensor information is, for example, information on acceleration in the three-axis direction, and angular velocity and angle of rotation around the three axes.

The communication unit 14 communicates with the server device 7 via the communication network 9 and transmits / receives data. The communication unit 14 receives the target face image information including the parameters for image inference processing used in the image recognition unit 12 and the control signal for controlling the camera terminal device 1, and outputs the control signal to the image recognition unit 12 and the control unit 13. To do. When the image recognition unit 12 recognizes a face image that matches the face image of the search target person, the collection information generation unit 15 obtains the image in which the face image of the search target person is recognized, the collected information including the position information, and the like. Generate and output to the communication unit 14. The communication unit 14 transmits the collected information input from the collected information generation unit 15 to the server device 7.

FIG. 3 is a block diagram showing the configuration of the server device 7. The server device 7 includes a communication unit 71, a face image information generation unit 72, an image processing unit 73, a data storage unit 74, and a control unit 75. The communication unit 71 communicates with the camera terminal device 1, the display terminal 6, and the management device 8 via the communication network 9, and transmits and receives various information. The communication unit 71 transmits the target face image information and the control signal to the camera terminal device 1 to the camera terminal device 1, and receives the collected information from the camera terminal device 1. In addition, the communication unit 71 receives the face image of the search target person and various control signals from the management device 8. In addition, the communication unit 71 distributes information about the current search target person to the display terminal 6.

The face image information generation unit 72 generates parameters for image inference processing used by the image recognition unit 12 of the camera terminal device 1 based on the face image of the search target person received from the management device 8. Here, the management device 8 is composed of, for example, a PC (personal computer) or the like, and provides an environment in which the search of the search target person can be managed by the operation of the operator. The management device 8 can, for example, input the face image data of the search target person and send it to the server device 7, control the information notification to the searcher, and receive and display the information collected in the search up to now. Execute the process.

The image processing unit 73 extracts new additional information useful for the search of the search target person by image recognition based on the image included in the collected information received from the camera terminal device 1. The additional information is, for example, a face image of the search target person in the video, which is the latest face image of the search target person. In addition, the additional information includes an image cut out in a range larger than the range of the face image in the video, information such as the type and color of the clothes of the search target person, and the person appearing around the face image of the search target person. It is an image etc.

The data storage unit 74 stores the face image of the search target person received from the management device 8, the collected information received from the camera terminal device 1, and the additional information extracted by the image processing unit 73. The information accumulated in the data storage unit 74 is transmitted to the display terminal 6. The control unit 75 controls the operation of each unit in the server device 7 by the control from the management device 8 or the control by itself.

Next, the operation of the information collection system will be described. FIG. 4 is a flowchart showing a procedure for updating parameters for image inference processing. The server device 7 receives the face image of the search target person transmitted from the management device 8 (S1). The face image information generation unit 72 learns the face image of the search target person for the image inference processing used in the image recognition unit 12 of the camera terminal device 1 and generates parameters for the image inference processing (S2). The server device 7 transmits the target face image information including the generated parameters for image inference processing from the communication unit 71 to the camera terminal device 1 (S3).

The camera terminal device 1 receives the target face image information transmitted from the server device 7, and uses the parameters for image inference processing included in the target face image information to obtain the image inference processing circuit of the image recognition unit 12. The parameter is updated (S4), and the process ends. The camera terminal device 1 infers whether or not a face image of the search target person exists in the captured image by the image inference circuit of the image recognition unit 12.

FIG. 5 is a flowchart showing a procedure of information collection processing when a search target person is recognized in the video. When the face image of the search target person is shown in the captured image, the camera terminal device 1 recognizes that the face image matching the face image of the search target person exists in the image recognition unit 12 (S11). ). The image recognition unit 12 cuts out a face image portion including the recognized face image from the original entire image (S12). The image recognition unit 12 cuts out at least the range of the horizontal width and the vertical width of the recognized face image, and it is preferable to cut out the range in which the horizontal width and the vertical width are increased by about 1 to 1.5 times, for example.

In addition, the collected information may include the original whole image in which a face image matching the face image of the search target person is found. Further, the collected information includes an image cut out by the collected information generation unit 15 with a width of X times the width of the face and a height of Y times the height of the face, instead of the original whole image. You may. The width of the cropped image should extend in both the left and right directions, and the height of the image should extend downward from the top of the face. It should be noted that X and Y may be values in the range of, for example, about 2 to 5, but are not limited to this range.

The collected information generation unit 15 generates the collected information including the face image portion cut out by the image recognition unit 12 and the position information, and transmits the collected information to the server device 7 via the communication unit 14 (S13). The server device 7 stores the collected information transmitted from the camera terminal device 1 in the data storage unit 74 (S14).

The management device 8 receives the collected information by accessing the server device 7, and is within a certain distance range from the camera terminal device 1 which is the source of recognizing the face image of the search target person and transmitting the collected information. The searcher (that is, the display terminal 6) in the above is extracted (S15). The management device 8 transmits the information of the extracted display terminal 6 to the server device 7, and the server device 7 sends the extracted face image portion and the search target person to the extracted searcher (display terminal 6). The recognized position information of the camera terminal device 1 is distributed (S16), and the process ends. The searcher can improve the efficiency of the search work by acquiring the current image of the search target person who may exist around him and the approximate position information as additional information.

FIG. 6 is a flowchart showing a procedure of information extraction processing for extracting additional information in the server device 7. It is assumed that the collected information transmitted from the camera terminal device 1 to the server device 7 includes the original whole image in which the face image matching the face image of the search target person is found, and the whole image is the server. It is stored in the data storage unit 74 of the device 7.

The image processing unit 73 of the server device 7 detects the face image in the image around the search target person in the whole image (S21). The detected face image is stored in the data storage unit 74. The image processing unit 73 can detect a face image by using various known face image detection methods.

The server device 7 distributes the face image detected by the image processing unit 73 to the searcher (S22), and ends the processing. If, instead of the entire image, an image cut out with a width X times the width of the face and a height Y times the height of the face is stored in the data storage unit 74, the image is included in the image. The face image may be detected in the image around the person to be searched for.

In addition to the current image of the search target person, the searcher can also find a person who existed in the vicinity of the search target person and obtain a clue of the search target person from the person. The area around the search target is within the range of the entire image or the cut-out image, but if it is too wide, the usefulness tends to decrease, and within a predetermined range, for example, about several meters to 10 m from the face image of the search target. By setting it within the range, the usefulness in the search of the face image other than the newly detected search target person is increased. It is assumed that the scale of the whole image or the cut-out image is known, but as described above, the image range of X times the width of the face and Y times the height of the face is defined. It may be a range.

FIG. 7 is a flowchart showing a procedure of information extraction processing for extracting additional information in the server device 7. In this information extraction process, a face image of a person that is commonly shown in a plurality of overall images is extracted. The image processing unit 73 of the server device 7 detects the face image in the image around the search target person in the whole image (S31).

The image processing unit 73 compares with a face image other than the search target person saved before a predetermined time (S32), and the image processing unit 73 determines whether or not the person is the same person (S33). If it is determined in step S33 that the person is the same person (S33: YES), the face image detected by the image processing unit 73 is delivered to the searcher (S34), and the process ends. If it is determined in step S33 that the person is not the same person (S33: NO), the process ends.

In addition to the current image of the search target person, the searcher searches for the person in addition to the search target person by acquiring information on the person who exists in the vicinity of the search target person and is detected twice or more. At the same time, it is possible to obtain clues to the search target. A person who exists in the vicinity of the person to be searched and may be detected more than once may be involved in the case or may be accompanied by the person to be searched, and the information of the person is provided as additional information. This makes it possible to improve the efficiency of the search work.

(Embodiment 2)
In the second embodiment, an example of extracting additional information to be delivered to the searcher is shown. The information collection system 100 according to the second embodiment has the same configuration as the information collection system 100 according to the first embodiment. FIG. 8 is a flowchart showing the procedure of the information collection process according to the second embodiment. Steps S41 to S44 are the same as steps S11 to S14 in FIG. The image processing unit 73 of the server device 7 generates a cut-out image including the face image of the search target person X times the width of the face and Y times the vertical width of the face downward from the entire image (S45).

Similar to step S15 in FIG. 5, the searcher within a certain distance range is extracted from the camera terminal device 1 which is the transmission source that recognizes the face image of the search target person and transmits the collected information (S46). The server device 7 distributes the cut-out image and the position information generated in step S45 to the extracted searcher (S47), and ends the process. In addition to the latest facial image of the search target person, the searcher can grasp the clothes and possessions of the search target person by the cut-out image, and it is possible to improve the efficiency of the search work. Become.

FIG. 9 is a flowchart showing the procedure of other information collection processing. Steps S51 to S55 are the same as steps S41 to S45 in FIG. The image processing unit 73 of the server device 7 determines the type of clothing by the object recognition process (S56). The image processing unit 73 can recognize the clothes and determine the type by using various known object recognition methods. The image processing unit 73 converts the text information, which is the result of determining the clothes, into voice data (S57). The text information and voice data of the clothes are stored in the data storage unit 74.

Similar to step S46 in FIG. 8, the searcher within a certain distance range is extracted from the camera terminal device 1 which is the transmission source that recognizes the face image of the search target person and transmits the collected information (S58). The server device 7 distributes the cut-out image generated in step S55, the voice data generated in step S57, and the position information to the extracted searcher (S59), and ends the process. It is assumed that the display terminal 6 carried by the searcher has a voice reproduction function.

In addition to the latest facial image of the search target person, the searcher can grasp information about the search target person's clothing by voice, and can improve the efficiency of the search work. The information collecting system 100 can recognize not only the type of clothes but also the information about clothes including the color of clothes from the cut-out image in the image processing unit 73 of the server device 7, and provide the information to the searcher.

(Embodiment 3)
The camera terminal device 1 according to the third embodiment includes an image processing unit 20 corresponding to the image processing unit 73 in the server device 7. FIG. 10 is a block diagram showing the configuration of the camera terminal device 1 according to the third embodiment. The image processing unit 20 provided in the camera terminal device 1 cuts out an image in the image processing unit 73 described in the above-described first and second embodiments, performs face image detection processing of a person around the search target person, and performs the same person a plurality of times. Detection processing, information extraction processing related to clothing, etc. are executed.

The above-mentioned additional information extracted by the image processing unit 20 of the camera terminal device 1 is transmitted from the collection information generation unit 15 to the server device 7, and is stored in the data storage unit 74 of the server device 7. Similar to the first and second embodiments, the server device 7 distributes information to the searcher including additional information stored in the data storage unit 74. The searcher can improve the efficiency of the search work by acquiring the latest facial image of the search target person and additional information of the person appearing around the search target person.

(Embodiment 4)
In the fourth embodiment, when the face image of the search target person is recognized by one camera terminal device 1, control is performed to collect information from the surrounding camera terminal devices 1 as well. The information collection system 100 according to the fourth embodiment has the same configuration as the information collection system 100 according to the first embodiment.

FIG. 11 is a schematic diagram showing a procedure of information collection processing according to the fourth embodiment. The camera terminal device 1 transmits the position information or the like acquired by GPS or the like to the server device 7 (S61). It is preferable that all the camera terminal devices 1 execute the transmission of the position information and the like every predetermined time (for example, several seconds to several minutes). Further, the control unit 75 of the server device 7 sequentially stores the position information and the like received by the communication unit 71 in the data storage unit 74.

When the face image of the search target person is displayed in the captured image in one camera terminal device 1, the image recognition unit 12 recognizes that the face image matching the face image of the search target person exists. (S62). The camera terminal device 1 that recognizes the face image that matches the face image of the search target person transmits the collected information to the server device 7 in the same manner as in steps S12 and S13 of FIG. Similarly, the collected information is stored in the data storage unit 74.

The control unit 75 of the server device 7 steps the camera terminal device 1 that recognizes the face image that matches the face image of the search target person, that is, the camera terminal device 1 located within a predetermined distance range from the position of the search target person. Extraction is performed based on the position information of each camera terminal device 1 received in S61 (S63). The predetermined distance range is, for example, several km to several tens of km, but is not limited to this range.

The control unit 75 of the server device 7 requests the extracted camera terminal device 1 to transmit the video data captured between Z (predetermined value) minutes before and the current time, and acquires the video data ( S64). The predetermined value of Z is, for example, several minutes to several tens of minutes, but is not limited to this range.

The image processing unit 73 of the server device 7 executes the recognition process of the face image of the search target person on the video data acquired in step S64 (S65), and determines whether or not the search target person is recognized (S66). ). The face image recognition process executed by the server device 7 has more system resources (processing capacity) during the recognition process than the face image recognition process performed by the camera terminal device 1, but the face image recognition. The method and system configuration should be such that the accuracy is high.

When it is determined in step S66 that the search target person is recognized (S66: YES), the searcher (that is, the display terminal 6) within a certain distance range from the camera terminal device 1 that recognizes the search target person in step S62 On the other hand, the position information of the camera terminal device 1 that transmitted the video data recognized by the search target person in step S65, the time on the video data recognized by the search target person, and the image of the face portion cut out from the video data. Is delivered (S67), and the process is terminated. When it is determined in step S66 that the search target person is not recognized (S66: NO), the process ends.

The image processing unit 73 of the server device 7 acquires the video data from Z minutes before from the camera terminal device 1 within a predetermined distance range, so that the image processing unit 73 is photographed by the surrounding camera terminal device 1 by the current time. You can find out who you are searching for. Thereby, when searching for the search target person, it is possible to suppress the communication band with respect to the communication network 9 between the camera terminal device 1 and the server device 7, reduce the communication amount, and improve the recognition rate of the search target person. It becomes.

Next, the features of the information collection system 100, the camera terminal device 1, the information collection method, and the information collection program according to each of the above-described embodiments will be described.
The information collection system 100 according to the embodiment includes a camera terminal device 1 and a server device 7. The camera terminal device 1 has a communication unit 14 as a target information acquisition unit that acquires target face image information related to the face image of the search target person, and an image recognition unit 12 that recognizes an image that matches the target face image information from the captured video. Has. The server device 7 is acquired from the camera terminal device 1 when a matching image is recognized by the communication unit 71 as the target information transmission unit for transmitting the target face image information to the camera terminal device 1 and the image recognition unit 12. It has an image processing unit 73 that detects a face image appearing around a face image that matches the target face image information in the video. As a result, the information collection system 100 can detect a person existing in the vicinity of the search target person and collect additional information based on the image of the search target person.

Further, the image processing unit 73 detects a face image existing within a predetermined range from the position of the face image that matches the target face image information. As a result, the information collecting system 100 detects a person existing in the vicinity of the search target person within a predetermined range, and thus becomes more useful in the search for a face image other than the newly detected search target person.

Further, the image processing unit 73 is commonly displayed in the image in which the face image matching the target face image information is recognized and the image in which the face image matching the target face image information is recognized after a predetermined time has elapsed. Detects a face image. As a result, the information collecting system 100 can detect a person who is detected twice or more in the vicinity of the search target person, and can improve the efficiency of the search work.

Further, the image processing unit 73 cuts out an image in a range larger than the range of the face image that matches the target face image information. As a result, the information collecting system 100 can grasp the clothes and possessions of the person to be searched, and can improve the efficiency of the search work.

Further, the image processing unit 73 extracts information about clothes reflected in the cut-out image. As a result, the information collecting system 100 can grasp the clothes of the search target person, and can improve the efficiency of the search work.

The information collection system 100 according to the embodiment includes a camera terminal device 1 and a server device 7. The camera terminal device 1 has a communication unit 14 as a target information acquisition unit that acquires target face image information related to the face image of the search target person, and an image recognition unit 12 that recognizes an image that matches the target face image information from the captured video. Has. The server device 7 is determined by the camera terminal device 1 when a matching image is recognized by the communication unit 71 as the target information transmission unit that transmits the target face image information to the camera terminal device 1 and the image recognition unit 12. It has an image processing unit 73 that acquires video data from another camera terminal device 1 existing within a distance range and recognizes an image that matches the target face image information among the income video data. As a result, when searching for the search target person, the information collection system 100 suppresses the communication band with respect to the communication network 9 between the camera terminal device 1 and the server device 7, reduces the communication amount, and recognizes the search target person. Can be improved.

The camera terminal device 1 according to the embodiment includes a communication unit 14 as a target information acquisition unit, an image recognition unit 12, and an image processing unit 20. The communication unit 14 acquires the target face image information regarding the face image of the search target person. The image recognition unit 12 recognizes an image that matches the target face image information from the captured image. When the image recognition unit 12 recognizes a matching image, the image processing unit 20 detects a face image appearing around the face image that matches the target face image information. As a result, the camera terminal device 1 can detect a person existing around the search target person and collect additional information.

The information collecting method includes a target information acquisition step, an image recognition step, and an image processing step. The target information acquisition step acquires target face image information regarding the face image of the search target person. The image recognition step recognizes an image that matches the target face image information from the captured image. When the matching image is recognized by the image recognition step, the image processing step detects a face image appearing around the face image matching the target face image information in the video. According to this information gathering method, it is possible to detect a person existing around the search target person and collect additional information.

The information collection program causes a computer to execute a target information acquisition step, an image recognition step, and an image processing step. The target information acquisition step acquires target face image information regarding the face image of the search target person. The image recognition step recognizes an image that matches the target face image information from the captured image. When the matching image is recognized by the image recognition step, the image processing step detects a face image appearing around the face image matching the target face image information in the video. According to this information gathering program, it is possible to detect the person who existed around the search target person and collect additional information.

The above description has been made based on the embodiment of the present invention. It will be appreciated by those skilled in the art that these embodiments are exemplary and that various modifications and modifications are possible within the claims of the invention, and that such modifications and modifications are also within the claims of the present invention. It is about to be done. Therefore, the descriptions and drawings herein should be treated as exemplary rather than limiting.

1 camera terminal device, 12 image recognition unit, 14 communication unit (target information acquisition unit),
20 Image processing unit, 7 Server device, 71 Communication unit (target information transmission unit),
73 Image processing unit, 100 Information collection system.

Claims (7)

A camera terminal device having a target information acquisition unit that acquires target face image information related to the face image of the search target person, and an image recognition unit that recognizes an image that matches the target face image information from the captured image.
When a matching image is recognized by the target information transmitting unit that transmits the target face image information to the camera terminal device and the image recognition unit, the target face image information is included in the image acquired from the camera terminal device. A server device having an image processing unit that detects a face image appearing around the face image that matches
An information gathering system characterized by being equipped with. The image processing unit is commonly displayed on an image in which a face image matching the target face image information is recognized and an image in which a face image matching the target face image information is recognized after a lapse of a predetermined time. The information gathering system according to claim 1, wherein the face image is detected. Claim 1 or 2 is characterized in that the image processing unit cuts out an image in a range larger than the range of the face image matching the target face image information, and extracts information on clothes reflected in the cut out image. Information gathering system described in. A camera terminal device having a target information acquisition unit that acquires target face image information related to the face image of the search target person, and an image recognition unit that recognizes an image that matches the target face image information from the captured image.
When the target information transmitting unit that transmits the target face image information to the camera terminal device and the image recognition unit recognize a matching image, another camera existing within a predetermined distance range from the camera terminal device. A server device having an image processing unit that acquires video data from a terminal device and recognizes an image that matches the target face image information in the income video data.
An information gathering system characterized by being equipped with. The target information acquisition unit that acquires the target face image information related to the face image of the search target person,
An image recognition unit that recognizes an image that matches the target face image information from the captured image,
When a matching image is recognized by the image recognition unit, an image processing unit that detects a face image appearing around the face image that matches the target face image information, and an image processing unit.
A camera terminal device characterized by being provided with. Target information acquisition step to acquire target face image information related to the face image of the search target person,
An image recognition step that recognizes an image that matches the target face image information from the captured image, and
When a matching image is recognized by the image recognition step, an image processing step of detecting a face image appearing around the face image matching the target face image information in the video, and an image processing step.
An information gathering method characterized by providing. Target information acquisition step to acquire target face image information related to the face image of the search target person,
An image recognition step that recognizes an image that matches the target face image information from the captured image, and
When a matching image is recognized by the image recognition step, an image processing step of detecting a face image appearing around the face image matching the target face image information in the video, and an image processing step.
An information gathering program characterized by having a computer execute.

Images