Monitoring service management method and management system

Abstract

The invention provides a monitoring service management method and management system. [Problem] To reliably acquire a posture image and a face image of an object to be monitored, which are necessary to track the object to be monitored every day, and to appropriately operate a monitoring service. A system for managing a monitoring service for providing a user with an image including an object to be monitored captured using an infrastructure camera is provided with a first infrastructure camera, a second infrastructure camera, and a processing device. The first and second infrastructure cameras are included in infrastructure cameras. The first infrastructure camera captures a face image of a person passing through an entrance / exit of a building. The second infrastructure camera captures a posture image of a person passing through the same entrance and exit as the entrance and exit captured by the first infrastructure camera. The processing device uses a first frame group from the first infrastructure camera and a second frame group from the second infrastructure camera to perform monitoring processing of the monitored object.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to a method and a system for managing a service of providing a user with an image of a ward taken by an infrastructure camera. BACKGROUND

[0002] Japanese Patent Application Publication No. 2022-030846 discloses a person tracking system. The system periodically acquires a monitoring image by a plurality of monitoring cameras, detects at least one of a face image similar to a registered face image of a tracking target person and a full-body image similar to a registered full-body image of the tracking target person. In a case where an image similar to at least one of the registered face image and the registered full-body image of the tracking target person is detected, the detected image is output.

[0003] As documents indicating the technical level of the technical field related to the present disclosure, in addition to Japanese Patent Application Publication No. 2022-030846, Japanese Patent Application Publication No. 2020-178167 and Japanese Patent Application Publication No. 2007-329627 can be exemplified.

[0004] Patent Document 1: Japanese Patent Application Publication No. 2022-030846

[0005] Patent Document 2: Japanese Patent Application Publication No. 2020-178167

[0006] Patent Document 3: Japanese Patent Application Publication No. 2007-329627

[0007] In a service of providing a user with an image of a ward taken by an infrastructure camera (hereinafter also referred to as a “ward service”), a camera system including the infrastructure camera performs tracking of the ward. In order to perform the tracking, it is necessary for the camera system to grasp a posture image of the ward determined by face authentication.

[0008] Here, it is considered that the clothing of the ward changes every day. Therefore, in order to grasp the posture image of the ward, it is considered to set a camera at the entrance of one’s home in addition to the infrastructure camera. In this case, when the ward goes out every day, it is possible to acquire the posture image of the ward. However, in this case, it is possible that a face image cannot be acquired by the camera for the posture image, or face authentication using the face image fails. Thus, it is desirable to make improvements for reliably acquiring a posture image of the ward including clothing and a face image required for face authentication, which enables appropriate use of the ward service. SUMMARY

[0009] One object of the present disclosure is to provide a technology that enables appropriate use of a ward service by reliably acquiring a posture image of a ward and a face image required for tracking the ward every day.

[0010] The first aspect of the present disclosure is a system that manages a monitoring service that provides a user with an image containing a monitoring target that is captured using an infrastructure camera, and has the following features.

[0011] The system described above includes a first infrastructure camera, a second infrastructure camera, and a processing device. The first and second infrastructure cameras are included in the infrastructure camera. The first infrastructure camera captures a face image of a person who passes through a doorway of a building. The second infrastructure camera captures a posture image of a person who passes through the doorway. The processing device performs monitoring processing of the monitoring target using a first frame group from the first infrastructure camera and a second frame group from the second infrastructure camera.

[0012] The second aspect of the present disclosure is a method that manages a monitoring service that provides a user with an image containing a monitoring target that is captured using an infrastructure camera, and has the following features.

[0013] The method described above includes: acquiring a first frame group from a first camera included in the infrastructure camera, which captures a face image of a person who passes through a doorway of a building; acquiring a second frame group from a second camera included in the infrastructure camera, which captures a posture image of a person who passes through the doorway; and performing monitoring processing of the monitoring target using the first and second frame groups.

[0014] According to the present disclosure, a first infrastructure camera is used to capture a face image of a person who passes through a doorway of a building. In addition, a second infrastructure camera is used to acquire a posture image of a person who passes through the doorway of the building. Therefore, if a monitoring target passes through the doorway of the building, a posture image and a face image of the monitoring target that are required for daily tracking of the monitoring target can be reliably acquired.

[0015] According to the present disclosure, monitoring processing using a first frame group and a second frame group from the first and second infrastructure cameras is additionally performed. According to the monitoring processing using the first frame group, for example, a face image of a person who coincides with a face image of a monitoring target can be determined. In addition, according to the monitoring processing using the second frame group, for example, a posture image of a person whose face image coincides with a face image of a monitoring target can be determined. That is, according to the monitoring processing using the first and second frame groups, a posture image of a monitoring target can be determined. If a posture image of a monitoring target can be determined, the monitoring target can be tracked based on the posture image and a frame group from an infrastructure camera other than the first and second infrastructure cameras. Thus, according to the present disclosure, appropriate use of a monitoring service is also possible. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 is a diagram that explains an outline of the monitoring service.

[0017] Figure 2 is a flowchart that shows one example of information processing performed when a frame group including an image of a monitoring target is provided to a user terminal.

[0018] Figure 3 is a diagram that explains features of monitoring processing of a monitoring target performed in the embodiment.

[0019] Figure 4 is a diagram that explains a first example when monitoring processing is shared by two or more data processing devices.

[0020] Figure 5 is a diagram that explains a second example when monitoring processing is shared by two or more data processing devices.

[0021] Explanation of Reference Numerals:

[0022] 10 … management server; 10A … local server; 10B … remote server; 11, 11A, 11B … data processing device; 12, 12A, 12B … database; 20 … infrastructure camera group; 21, 22, 23 … infrastructure camera; 30 … user terminal; 40 … target terminal; TG … monitoring target; US … user of the monitoring service; AFU … application for use; CAM … camera data; FPS, FTG … feature amount; RFW … monitoring request; RFT … end request of monitoring; FR_CA, FR_CA21, FR_CA22, FR_CA23 … frame group; IMG_PSF … face image of person PS; IMG_PSS … posture image of person PS; IMG_TGF … face image of monitoring target TG; IMG_TGS … posture image of monitoring target TG. DETAILED DESCRIPTION

[0023] Hereinafter, an embodiment of the present disclosure will be explained with reference to the drawings. In each drawing, the same reference numerals are attached to the same or equivalent portions, and the explanation thereof will be simplified or omitted.

[0024] 1. Monitoring service

[0025] Figure 1 is a diagram that explains an outline of the monitoring service. The monitoring service is a service that determines a frame group FR_CA including an image IMG_TG of a monitoring target TG from among frame groups FR_CA acquired from a plurality of infrastructure cameras that constitute an infrastructure camera group 20 (in the example shown in FIG. 1, a frame group FR_CA23 including an image IMG_TG of a monitoring target TG is determined from among frame groups FR_CA21, FR_CA22, and FR_CA23 acquired from infrastructure cameras 21, 22, and 23 that constitute the infrastructure camera group 20). Figure 1In the example shown, a posture image (full-body image) IMG_TGS) is provided to a service of a communication terminal (hereinafter also referred to as "user terminal") 30 of the user US, and the determined frame group FR_CA is provided to the user US. Here, the user US is a person who uses a guardianship service. The guardianship target TG is a person whom the user US wishes to guard (for example, a family member of the user US, a friend of the user US, a person who is cared for by the user US).

[0026] Figure 1 Also, the drawing is a drawing showing an example of the overall configuration of a management system of the guardianship service to which the embodiments relate. In the example shown, the management system is provided with a management server 10, an infrastructure camera group 20, a user terminal 30, and a communication terminal (hereinafter also referred to as "target terminal") 40 of a guardianship target TG. The infrastructure camera group 20, the user terminal 30, and the target terminal 40 communicate with the management server 10 via a communication line network (not shown). Among them, the communication line network is not particularly limited, and a wired and wireless network can be used. Figure 1

[0027] The management server 10 is provided with a data processing device 11 and a database 12. The data processing device 11 is provided with at least one processor and at least one memory. As the processor, a general-purpose processor, a purpose-dedicated processor, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), an integrated circuit, and / or a combination thereof can be exemplified. The memory is a volatile memory such as a DDR memory, and performs expansion of various programs used in various processes performed by the processor and temporary storage of various data. The various data used by the processor include data stored in the database 12.

[0028] The database 12 is formed in a prescribed storage device (for example, a hard disk, a flash memory). In the database 12, user data USR and camera data CAM are stored. The user data USR is transmitted from the user terminal 30 to the management server 10. The user data USR includes identification information of the user US, identification information of the guardianship target TG, and the like. The camera data CAM includes identification information of each of the plurality of infrastructure cameras that constitute the infrastructure camera group 20, position information of these infrastructure cameras, frame groups FR_CA respectively acquired by these infrastructure cameras, and the like.

[0029] ​The infrastructure camera group 20 includes a plurality of infrastructure cameras. These infrastructure cameras include not only infrastructure cameras disposed outdoors but also infrastructure cameras disposed indoors. A part or all of the photographing ranges of two or more infrastructure cameras can overlap. Each infrastructure camera acquires a frame group FR_CA. The frame group FR_CA is a collection of still images (frames) that constitute an image (i.e., a camera image) acquired by the infrastructure camera. In addition, each infrastructure camera transmits the acquired frame group FR_CA and its own identification information to the management server 10.

[0030] The user terminal 30 is, for example, a terminal such as a smartphone, a tablet, or a notebook personal computer that the user US carries and has a communication function. The user terminal 30 is used when the user US initially uses the watch service. At the initial use, an application for use AFU of the watch service is transmitted from the user terminal 30 to the management server 10. The user data US including identification information of the user US, identification information of the guardian object TG, and the like are included in the application for use AFU. If the user data US is registered in the database 12, the watch service can be used.

[0031] As the identification information of the user US, attribute information (e.g., name, sex, age) of the user US and identification information of the user terminal 30 can be exemplified. As the identification information of the guardian object TG, a face image IMG_TGF of the guardian object TG and attribute information (e.g., name, sex, age) of the guardian object TG can be exemplified. The identification information of the guardian object TG can also include identification information of the object terminal 40 and relationship information (e.g., family, friend, person to be watched by the user US) of the user US and the guardian object TG.

[0032] In addition, the user terminal 30 is also used when the user US uses the watch service for the second time or later. At the second time or later use, a watch request RFW is transmitted from the user terminal 30 to the management server 10. The watch request RFW includes, for example, login information of the user US for accessing the database 12. To the watch request RFW, information for updating a part or all of the user data USR registered in the database 12 can also be transmitted. In a case where the watch request RFW includes such update information, the user data USR registered in the database 12 is updated.

[0033] The object terminal 40 is, for example, a terminal with a communication function such as a smartphone or a wearable device that the guardian object TG carries. In addition, the object terminal 40 has a GPS (Global Positioning System) function. By having the GPS function, the object terminal 40 transmits position information of the object terminal 40 to an external device (for example, the management server 10, the user terminal 30). Note that the object terminal 40 is arbitrary in the management system according to the present disclosure. That is, the management system according to the present disclosure can be constituted by the management server 10, the infrastructure camera group 20, and the user terminal 30.

[0034] 2. Provision of camera images

[0035] Figure 2 is a flowchart showing one example of information processing performed when the frame group FR_CA containing the image IMG_TG is provided to the user terminal 30. Figure 2 The routine shown in FIG. 8 is repeatedly executed by the data processing device 11 shown in FIG. 1, for example. Figure 1

[0036] In the routine shown in FIG. 8, first, as the process of step S11, it is determined whether or not the guardian request RFW is received. As has been described, the guardian request RFW includes login information of the user US for accessing the database 12. In the case where the determination result of step S11 is affirmative, the process of step S12 is performed. Figure 2 In the process of step S12, the guardian object TG search using the frame group FR_CA stored in the database 12 is performed. At this time, the database 12 is referred to with the login information received by the process of step S11 as a key, to determine the feature amount FTG of the guardian object TG included in the user data USR corresponding to the login information.

[0037] Here, the feature amount FTG of the guardian object TG is extracted based on the posture image IMG_TGS of the guardian object TG. The feature amount FTG is used for the guardian object TG search. The feature amount FTG is also used to perform re-identification of the guardian object TG. The feature amount FTG is one example of the feature amount FPS of the person PS. For example, the feature amount FPS is extracted by applying a bounding box group representing the same person in a plurality of time steps to a Re-ID model based on machine learning. Note that the extraction of the feature amount FPS itself is a known technology, and the method of extraction applied in the process of step S15 is not particularly limited.

[0038]

[0039] ​​If the feature quantity FTG is determined, a posture image having a feature quantity consistent with the feature quantity FTG can be determined. Then, a frame group FR_CA containing the posture image and an infrastructure camera that has acquired the frame group FR_CA are determined. The determination of the frame group FR_CA containing the posture image is performed, for example, by comparing the feature quantities FPS extracted from the frame groups FR_CA acquired from the respective infrastructure cameras with the feature quantity FTG. For example, a frame group FR_CA containing a posture image from which a feature quantity FPS having a similarity to the feature quantity FTG of a threshold value or more is extracted is determined as a frame group FR_CA containing a posture image having a feature quantity consistent with the feature quantity FTG. The determined frame group FR_CA is a frame group containing a frame closest to the current time t.

[0040] The process of step S12 is performed at a prescribed time. If the prescribed time elapses from the start of the process of step S12, the process of step S13 is performed. In the process of step S13, it is determined whether the guardian TG is determined. That is, it is determined whether a frame group FR_CA containing a posture image having a feature quantity consistent with the feature quantity FTG and an infrastructure camera that has acquired the frame group FR_CA are determined. In the case where the determination result of step S13 is negative, the process of step S14 is performed.

[0041] In the process of step S14, re-search of the guardian TG using the frame groups FR_CA stored in the database 12 is performed. The method of the re-search is basically the same as the method explained in the process of step S12. As in the process of step S12, the process of step S14 is performed at a prescribed time. However, in the process of step S12, the search is performed with focus on the frame of the current time t, whereas in the process of step S14, the search is performed with focus on the frames of the current time t and the time t-k (k≥1).

[0042] In the case where the determination result of step S13 is affirmative, the processes of steps S15 and S16 are performed. In the process of step S15, tracking of the guardian TG is performed. The tracking refers to a technique of automatically tracking the same person included in the frame group based on a tracking algorithm. The tracking in one infrastructure camera is performed, for example, by inferring that a person PS whose feature quantities FPS extracted from the frame group FR_CA are consistent is the same person. The tracking in two or more infrastructure cameras is performed, for example, by inferring that a person PS whose feature quantities FPS are consistent between the infrastructure cameras is the same person by comparing the feature quantities FPS between the infrastructure cameras.

[0043] The tracking of the guardian object TG is performed by tracking a person who can be inferred as the same person as the guardian object TG using the feature quantity FTG. By performing the tracking of the guardian object TG, the image IMG_TG (pose image IMG_TGS) of the guardian object TG is determined. In the process of step S16, the frame group FR_CA including the image IMG_TG thus determined is transmitted to the terminal (i.e., the user terminal 30) of the transmission source of the guardian request RFW.

[0044] The process of step S17 is performed immediately after the process of step S16. In the process of step S17, it is determined whether or not a termination request RFT (Request For Termination) for the guardianship is received. In the case where the determination result of step S17 is affirmative, the transmission of the frame group FR_CA including the image IMG_TG is terminated. Otherwise, the processes of steps S15 and S16 are performed. That is, the processes of steps S15 to S17 are repeatedly executed until the termination request RFT is accepted.

[0045] 3. Features of Embodiments

[0046] In the tracking of the guardian object TG using the feature quantity FTG, the pose image IMG_TGS of the guardian object TG is required in order to extract the feature quantity FTG. However, the appearance (clothing) of the guardian object TG changes every day. In addition, even within one day, if the guardian object TG changes clothes, the appearance changes, and even if the upper garment is removed, the appearance changes. Therefore, it is not possible to ensure the accuracy of the tracking by the pose image IMG_TGS registered in advance.

[0047] In view of this, in the embodiment, in order to acquire the latest pose image IMG_TGS of the guardian object TG, two infrastructure cameras for face photographing and for pose photographing are provided at the entrance of the building. Further, a face authentication process using the face image IMG_PSF of the person PS acquired using the infrastructure camera for face photographing and the face image IMG_TGF registered in advance is performed to determine the guardian object TG. On this basis, the pose image IMG_PSS of the person PS determined as the guardian object TG by the face authentication process among the pose images IMG_PSS of the person PS acquired using the infrastructure camera for pose photographing is inferred as the pose image IMG_TGS of the guardian object TG.

[0048] Figure 3 is a diagram for explaining the features of the guardianship process of the guardian object TG performed in the embodiment. In Figure 3In the present embodiment, the infrastructure cameras 21, 22, and 23 are depicted. These infrastructure cameras are all cameras belonging to the infrastructure camera group 20. The infrastructure camera 21 is one example of the "first infrastructure camera" of the present disclosure, the infrastructure camera 22 is one example of the "second infrastructure camera" of the present disclosure, and the infrastructure camera 23 is one example of the "third infrastructure camera" of the present disclosure.

[0049] The infrastructure cameras 21 and 22 are provided, for example, at the entrance 60 of a building (for example, a residential house, a public facility such as a school, a hospital, a commercial facility such as a store, an office, and the like). The infrastructure cameras 21 and 22 are provided as one set of two. The total number of sets of the infrastructure cameras 21 and 22 is one or more.

[0050] The infrastructure camera 21 is a camera for face photographing, and, in contrast, the infrastructure camera 22 is a camera for posture photographing. For example, the infrastructure camera 21 is provided at a position and a height at which a face of a person passing through the entrance 60 can be photographed. The infrastructure camera 21 can also be adjusted in focal length so as to perform zoom photographing of the face of the person passing through the entrance 60. The infrastructure camera 22 is provided at a position and a height at which the entire posture of the person passing through the entrance 60 can be photographed. The infrastructure camera 22 can use a wide-angle lens or a fisheye lens that photographs the entire posture of the person passing through the entrance 60.

[0051] The infrastructure camera 23 is provided at a place other than the entrance 60. As the place other than the entrance 60, a structure (for example, an inner wall such as a wall surface of a passageway, a wall surface of a room, and the like) in a building in which the infrastructure cameras 21 and 22 are provided, and a structure (for example, an outer wall of a structure around the building) outside the building can be exemplified. The total number of infrastructure cameras 23 provided at the same site is one or more. The infrastructure camera 23 has the same configuration as that of the infrastructure camera 22. That is, the infrastructure camera 23 is a camera for posture photographing.

[0052] The guardian processing includes (I) face authentication processing, (II) association establishment processing, and (III) search processing. In the (I) face authentication processing, the face image IMG PSF extracted from the frame group FR CA from the infrastructure camera 21 and the face image IMG TGF of the guardian TG registered in advance are collated. Then, in a case where the collation result that these face images coincide is obtained, it is determined that the face image IMG PSF is the face image of the guardian TG.

[0053] In the association process (II), the pose image IMG_PSS extracted from the frame group FR_CA22 of infrastructure camera 22 is associated with the facial image IMG_PSF extracted from the frame group FR_CA21 of infrastructure camera 21. Since the installation positions and viewing angles of infrastructure cameras 21 and 22 are known, it is possible to identify the person PS whose pose image IMG_PSS was located at the coordinates (x, y) of the frame captured by infrastructure camera 22 at the time infrastructure camera 21 captured the facial image IMG_PSF. If multiple facial images IMG_PSF are captured at the same coordinates (x, y), the pose image IMG_PSS associated with the facial image IMG_PSF can be determined based on the positional relationship between infrastructure cameras 21 and 22.

[0054] In the association process (II), the frame group FR_CA22 containing the gesture image IMG_PSS associated with the facial image IMG_PSF and the frame group FR_CA21 containing the facial image IMG_PSF are combined with information about the timestamp, the position coordinates of the facial image IMG_PSF on the frame, and the position coordinates of the gesture image IMG_PSS on the frame, and recorded. In the association process (II), information about the feature value FPS extracted from the gesture image IMG_PSS may also be combined.

[0055] By performing (I) facial recognition and (II) association, the posture image IMG_PSS associated with the facial image IMG_TGF of the monitored subject TG can be identified from the posture images IMG_PSS. The identified posture image IMG_PSS can be inferred to be the most recent posture image IMG_TGS of the monitored subject TG. Furthermore, the feature value FPS extracted from the identified posture image IMG_PSS can be inferred to be the most recent feature value FTG of the monitored subject TG.

[0056] (III) Retrieval Processing Figure 1The data processing device 11 shown is performed when a monitoring request RFW is received. Even when a monitoring request RFW is not received, the retrieval process (III) may be performed. In the retrieval process (III), the posture image IMG_PSS is extracted from the frame group FR_CA23 of the infrastructure camera 23, and the feature quantity FPS is extracted from the posture image IMG_PSS. In the retrieval process (III), the posture image IMG_TGS is extracted from the frame group FR_CA22 containing the posture image IMG_TGS, and the feature quantity FTG is extracted from the posture image IMG_TSG. However, when the feature quantity FTG is extracted in the association process (II), the feature quantity FTG is not extracted in the retrieval process (III).

[0057] In the search process (III), the feature quantity FPS and the feature quantity FTG are also compared. If a feature quantity FPS that matches the feature quantity FTG is detected, the frame group FR_CA containing the posture image IMG_PSS having the feature quantity FPS and the infrastructure camera 23 that obtained the frame group FR_CA are identified. When the data processing device 11 receives a monitoring request RFW, the frame group FR_CA23 of the infrastructure camera 23 thus identified is transmitted to the terminal (i.e., the user terminal 30) that sent the monitoring request RFW.

[0058] 4. Decentralization of custody and treatment

[0059] Figure 4 and Figure 5 This figure explains an example in which monitoring processing is shared by two or more data processing devices. Figure 4 In the first example shown, Figure 1 The management server 10 shown is composed of a local server 10A and a remote server 10B. The local server 10A is an example of the "first processing device" in this disclosure, and the remote server 10B is an example of the "second processing device" in this disclosure. The local server 10A is connected to infrastructure cameras 21 and 22. Meanwhile, the remote server 10B is connected to infrastructure camera 23. The local server 10A performs a portion of the monitoring process. The remote server 10B manages the entire monitoring service.

[0060] The local server 10A includes a data processing device 11A and a database 12A. Figure 1The data processing apparatus 11A performs the same processing as the data processing apparatus 11 explained in (II) in association with the processing. That is, the data processing apparatus 11A extracts the face image IMG PSF from the frame group FR CA21 stored in the database 12A, and extracts the posture image IMG PSS from the frame group FR CA22 stored in the database 12A. In addition, the data processing apparatus 11A associates the face image IMG PSF with the posture image IMG PSS. The frame groups FR CA21 & CA22 shown in the database 12A indicate a data set of the frame group after the association.

[0061] The remote server 10B is provided with a data processing apparatus 11B and a database 12B. The data processing apparatus 11B performs the same processing as the data processing apparatus 11 explained in (II) in association with the processing. That is, the data processing apparatus 11A extracts the face image IMG PSF from the frame group FR CA21 stored in the database 12A, and extracts the posture image IMG PSS from the frame group FR CA22 stored in the database 12A. In addition, the data processing apparatus 11A associates the face image IMG PSF with the posture image IMG PSS. The frame groups FR CA21 & CA22 shown in the database 12A indicate a data set of the frame group after the association. Figure 1

[0062] In the case where the face image IMG PSF identical to the face image IMG TGF is determined, the processing in association with the (III) search processing is performed. That is, the data processing apparatus 11B determines whether or not the guardianship request RFW is received, and performs the (III) search processing in the case where the determination result is affirmative. Alternatively, the data processing apparatus 11B performs the (III) search processing without determining whether or not the guardianship request RFW is received. In the (III) search processing, the face image IMG PSF is extracted from the frame group FR CA23 included in the camera data CAM, and the feature amount FPS is extracted from the face image IMG PSF.

[0063] ​In the (III) search processing, the attitude image IMG PSS that has been associated with the face image IMG PSF coincident with the face image IMG TGF of the guardian object TG is regarded as the attitude image IMG TGS, and the attitude image IMG PSS regarded as the attitude image IMG TGS is determined based on the information of the frame group FR CA21 & CA22 and the position coordinates of the attitude image IMG PSS on the frame. Then, the feature amount FTG is extracted from the determined attitude image IMG PSS, and compared with the feature amount FPS extracted from the frame group FR CA23. In the case where the comparison result is that the feature amount FPS coincident with the feature amount FTG is detected, the frame group FR CA23 containing the attitude image IMG PSS having the feature amount FPS and the infrastructure camera 23 that has acquired the frame group FR CA23 are determined.

[0064] Thus, in the first example, the (II) association establishing processing is performed in the local server 10A. Therefore, compared with the case where the (II) association establishing processing is performed by the remote server 10B, the processing load of the remote server 10B can be reduced. In addition, in the case where the frame groups FR CA21 and FR CA22 are respectively transmitted to the remote server 10B, when the frame group of the side that cannot transmit, it is possible to cause an obstacle to the (II) association establishing processing and the (III) search processing. In view of this point, according to the first example, since the frame groups FR CA21 & CA22 are transmitted to the remote server 10B, it is also possible to prevent the generation of such a bad situation in advance.

[0065] In the second example shown in FIG. 8, the same as the first example, the (II) association establishing processing is performed in the local server 10A. Figure 5 In the second example shown in FIG. 8, the same as the first example, the (II) association establishing processing is performed in the local server 10A. Figure 1 The management server 10 shown in FIG. 8 is also composed of the local server 10A and the remote server 10B. Unlike the first example, in the second example, the data processing device 11A performs the processing related to the (I) face authentication processing in addition to the processing related to the (II) association establishing processing, and the data processing device 11B performs only the processing related to the (III) search processing.

[0066] In the case where the data processing device 11A performs the processing related to the (I) face authentication processing, it is necessary to acquire the face image IMG TGF of the guardian object TG by the data processing device 11A. Therefore, it is required that the face image IMG TGF is stored in advance in the database 12B, or the face image IMG TGF is acquired from the database 12A every time of the (I) face authentication processing.

[0067] However, in the second case, it is possible to determine in the local server 10A that the posture image IMG PSS that has been associated with the face image IMG PSF coincident with the face image IMG TGF has been established. Therefore, it is possible to perform the following processing: instead of the frame groups FR CA21 & CA22, only the frame group FR CA22 containing the posture image IMG PSS that has been associated with the face image IMG PSF coincident with the face image IMG TGF is transmitted to the remote server 10B. Since this relates to a reduction in the communication volume between the local server 10A and the remote server 10B, it can be said that this is an advantage involved in the second case.

Claims

1. A management system of a monitoring service that manages a monitoring service that provides a user with an image containing a monitoring target that is captured by an infrastructure camera, characterized by comprising: a monitoring service management unit that manages the monitoring service; and a monitoring service management database that stores information about the monitoring service, wherein the monitoring service management unit manages the monitoring service by referring to the information about the monitoring service stored in the monitoring service management database. Possessing: a first infrastructure camera that includes, in the infrastructure camera, a function of capturing a face image of a person who passes through an entrance of a building; a second infrastructure camera that includes, in the infrastructure camera, a function of capturing a posture image of a person who passes through the entrance; and a processing device that performs a monitoring process of the monitoring target using a first frame group from the first infrastructure camera and a second frame group from the second infrastructure camera.

2. The monitoring service management system according to claim 1, characterized in that: a third infrastructure camera that includes, in the infrastructure camera, a function of acquiring a third frame group is further possessed, the monitoring process includes: an association process that associates a face image of a person extracted from the first frame group with a posture image of a person extracted from the second frame group; a face authentication process that is a face authentication process using a face image of a person extracted from the first frame group, determines a face image of a person that coincides with a face image of the monitoring target; and a search process that uses results of the association process and the face authentication process to infer a posture image that is associated with the face image that coincides with the face image of the monitoring target as a posture image of the monitoring target, and searches for the monitoring target by comparing with a posture image of a person extracted from the third frame group.

3. The monitoring service management system according to claim 2, characterized in that: the processing device includes: a first processing device that is connected to the first infrastructure camera and the second infrastructure camera and performs a part of the monitoring process; and a second processing device that is connected to the first processing device and the third infrastructure camera and manages the entire monitoring service, the monitoring process performed by the first processing device includes the association process, the monitoring process performed by the second processing device includes the face authentication process and the search process.

4. The monitoring service management system according to claim 2, characterized in that: the processing device includes: a first processing device that is connected to the first infrastructure camera and the second infrastructure camera and performs a part of the monitoring process; and a second processing device that is connected to the first processing device and the third infrastructure camera and manages the entire monitoring service, the monitoring process performed by the first processing device includes the association process and the face authentication process, the monitoring process performed by the second processing device includes the search process.

5. A method for managing a monitoring service, wherein an image of a monitored object captured by an infrastructure camera is provided to a user, characterized in that: including: acquiring a first frame group from a first infrastructure camera that includes, in the infrastructure camera, a function of capturing a face image of a person who passes through an entrance of a building; acquiring a second frame group from a second infrastructure camera that includes, in the infrastructure camera, a function of capturing a posture image of a person who passes through the entrance; and performing a monitoring process of the monitoring target using the first frame group and the second frame group.

Images