JP7653134B2 - Surveillance camera installation support system, surveillance camera installation support device, and surveillance camera installation support program - Google Patents

Description

The present invention relates to a surveillance camera installation support system, a surveillance camera installation support device, and a surveillance camera installation support program.

Conventionally, devices and systems have been known that place surveillance cameras, such as so-called AI (Artificial Intelligence) cameras, in stores and the like and analyze frame images captured by the surveillance cameras (detecting objects such as people captured in the frame images using a trained object detection neural network, or recognizing objects using a trained object recognition neural network, etc.) (see, for example, Patent Document 1).

JP 2018-093283 A

However, in devices and systems that analyze frame images captured by conventional surveillance cameras such as those described in Patent Document 1, the accuracy of the analysis results (e.g., the accuracy of detection and recognition of objects such as people) may not be sufficient due to the influence of the installation position and angle of the surveillance camera, the light source around the surveillance camera, etc. Therefore, in order to ensure the accuracy of the analysis results in this type of device or system, it is necessary to make it easy to check changes in the accuracy of the analysis results (e.g., the accuracy of detection and recognition of objects such as people) when the installer adjusts (changes) the installation position or angle of the surveillance camera at the installation site.

The present invention aims to solve the above problems and provide a surveillance camera installation support system, a surveillance camera installation support device, and a surveillance camera installation support program that enable an installer to easily check the change in accuracy of analysis results due to adjustments to the installation conditions, such as the installation position and installation angle, when the installer adjusts (changes) the installation conditions of the surveillance camera at the installation site.

In order to solve the above-mentioned problems, a surveillance camera installation support system according to a first aspect of the present invention is a surveillance camera installation support system for supporting the installation of a surveillance camera that shoots a specified shooting area, comprising: installation information acquisition means for acquiring camera installation information including information on the height from the floor when the surveillance camera was shooting; image analysis means for analyzing each frame image input from the surveillance camera at the height from the floor; analysis result superimposition means for generating a superimposed image in which information on the analysis result of each frame image by the image analysis means is superimposed on each of the frame images; superimposed image storage means for storing a superimposed image composed of each superimposed image generated by the analysis result superimposition means at the height from the floor; the surveillance camera installation support system includes an installation information storage means for storing camera installation information linked to the superimposed image stored in the superimposed image storage means, an image display means for displaying the superimposed image stored in the superimposed image storage means together with camera installation information stored in the installation information storage means linked to the superimposed image, and a camera installation information search means for searching for camera installation information corresponding to a height from the floor similar to the height from the floor of the surveillance camera to be currently installed, from among the camera installation information stored in the installation information storage means in another surveillance camera installation support system installed in a location different from that of the surveillance camera installation support system, and the image display means displays the superimposed image linked to the camera installation information searched for by the camera installation information search means, together with the searched camera installation information .

In this surveillance camera installation assistance system, it is preferable that the image display means displays overlapping images of the surveillance cameras at a plurality of heights from the floor side by side.

In this surveillance camera installation support system, it is preferable that the image display means displays, side by side, each of the superimposed images linked to the multiple camera installation information searched for by the camera installation information search means.

A surveillance camera installation support system according to a second aspect of the present invention is a surveillance camera installation support system for supporting the installation of a surveillance camera that photographs a specified photographing area, comprising: installation information acquisition means for acquiring camera installation information indicating an installation situation at the time of photographing the surveillance camera; image analysis means for analyzing each frame image input from the surveillance camera in the installation situation; analysis result superimposition means for generating a superimposed image in which information on the analysis result of each frame image by the image analysis means is superimposed on each of the frame images; superimposed image storage means for storing a superimposed image composed of each superimposed image generated by the analysis result superimposition means in the installation situation ; The surveillance camera installation support system includes an installation information storage means for storing camera installation information at the time of shooting by the surveillance camera acquired by the acquisition means, linked to the superimposed image stored in the superimposed image storage means, and an image display means for displaying the superimposed image stored in the superimposed image storage means together with the camera installation information stored in the installation information storage means and linked to the superimposed image, wherein the camera installation information includes information on the installation position and installation angle of the surveillance camera, and the installation information acquisition means acquires the information on the installation position and installation angle of the surveillance camera based on information obtained from sensors including a camera mounted on the mobile terminal.

A surveillance camera installation support system according to a third aspect of the present invention is a surveillance camera installation support system for supporting the installation of a surveillance camera which photographs a specified photographing area, comprising: installation information acquisition means for acquiring camera installation information indicating an installation situation at the time of photographing the surveillance camera; image analysis means for analyzing each frame image input from the surveillance camera in said installation situation; analysis result superimposition means for generating a superimposed image in which information on the analysis result of each frame image by the image analysis means is superimposed on each of the frame images; and superimposed image storage means for storing a superimposed image composed of each of the superimposed images generated by the analysis result superimposition means in said installation situation. the installation information storage means for storing the camera installation information at the time of shooting by the surveillance camera acquired by the installation information acquisition means in association with the superimposed image stored in the superimposed image storage means; and an image display means for displaying the superimposed image stored in the superimposed image storage means together with the camera installation information stored in the installation information storage means and linked to the superimposed image, wherein the camera installation information includes information on the installation position and installation angle of the surveillance camera, and the installation information acquisition means acquires the information on the installation position and installation angle of the surveillance camera based on an image captured by the surveillance camera of a two-dimensional barcode board installed within the shooting area .

In this surveillance camera installation support system, the installation information acquisition means may estimate the installation height position and installation angle of the surveillance camera based on the image of each mark in the two-dimensional barcode.

A surveillance camera installation support program according to a fourth aspect of the present invention is a surveillance camera installation support program for a surveillance camera installation support system for supporting the installation of a surveillance camera that photographs a specified photographing area, comprising a computer, installation information acquisition means for acquiring camera installation information including information on the height from the floor when the surveillance camera photographs, image analysis means for analyzing each frame image input from the surveillance camera at the height from the floor, analysis result superimposition means for generating a superimposed image in which information on the analysis result of each frame image by the image analysis means is superimposed on each of the frame images, superimposed image storage means for storing a superimposed image composed of each superimposed image generated by the analysis result superimposition means at the height from the floor, and information on the photographed image of the surveillance camera acquired by the installation information acquisition means. The system includes an installation information storage means for storing the current camera installation information in association with the superimposed image stored in the superimposed image storage means, a video display means for displaying the superimposed image stored in the superimposed image storage means together with the camera installation information stored in the installation information storage means and linked to the superimposed image, and a camera installation information search means for searching for camera installation information corresponding to a height from the floor similar to the height from the floor of the surveillance camera to be currently installed from among camera installation information stored in the installation information storage means in another surveillance camera installation support system installed in a location different from that of the surveillance camera installation support system, and the video display means displays the superimposed image linked to the camera installation information searched for by the camera installation information search means together with the searched camera installation information.
A surveillance camera installation support program according to a fifth aspect of the present invention is a surveillance camera installation support program for supporting the installation of a surveillance camera that photographs a specified photographing area, comprising: installation information acquisition means for acquiring camera installation information indicating the installation situation at the time of photographing the surveillance camera; image analysis means for analyzing each frame image input from the surveillance camera in the installation situation; analysis result superimposition means for generating a superimposed image in which information on the analysis result of each frame image by the image analysis means is superimposed on each of the frame images; and a superimposed video composed of each of the superimposed images generated by the analysis result superimposition means in the installation situation. the installation information acquisition means for acquiring information on the installation position and angle of the surveillance camera based on information obtained from sensors including a camera mounted on a mobile terminal, and storing the information on the installation position and angle of the surveillance camera based on information obtained from sensors including a camera mounted on the mobile terminal, the installation information acquisition means for acquiring ...
A surveillance camera installation support program according to a sixth aspect of the present invention is a surveillance camera installation support program for supporting the installation of a surveillance camera that photographs a specified photographing area, comprising: installation information acquisition means for acquiring camera installation information indicating an installation situation at the time of photographing the surveillance camera; image analysis means for analyzing each frame image input from the surveillance camera in the installation situation; analysis result superimposition means for generating a superimposed image in which information on an analysis result of each frame image by the image analysis means is superimposed on each of the frame images; and a superimposed image storage means for storing a superimposed image composed of each of the superimposed images generated by the analysis result superimposition means in the installation situation. The surveillance camera functions as a storage means, an installation information storage means for storing camera installation information at the time of shooting by the surveillance camera acquired by the installation information acquisition means in association with the superimposed image stored in the superimposed image storage means, and an image display means for displaying the superimposed image stored in the superimposed image storage means together with the camera installation information stored in the installation information storage means and linked to the superimposed image, the camera installation information including information on the installation position and installation angle of the surveillance camera, and the installation information acquisition means acquires information on the installation position and installation angle of the surveillance camera based on an image captured by the surveillance camera of a two-dimensional barcode board installed within the shooting area.

According to the surveillance camera installation support system according to the first aspect of the present invention and the surveillance camera installation support program according to the fourth aspect, the camera installation information stored in the installation information storage means of another surveillance camera installation support system installed in a different location (e.g., another store) is searched for camera installation information corresponding to a height from the floor similar to the height from the floor of the surveillance camera to be installed this time, and the superimposed image linked to the searched camera installation information is displayed together with the searched camera installation information ( information on the height from the floor of the surveillance camera). This allows the (surveillance camera) installer at the surveillance camera installation site to refer to the height from the floor of the surveillance camera in a different location (e.g., another store) and the analysis result of the superimposed image at that height from the floor to determine the height from the floor of the surveillance camera that he or she is currently attempting to install .

1 is a block diagram showing a schematic configuration of a surveillance camera installation support system according to an embodiment of the present invention; FIG. 2 is a block diagram showing a schematic hardware configuration of an analysis box in FIG. 1 . FIG. 2 is a block diagram showing a schematic hardware configuration of the smartphone in FIG. 1 . FIG. 2 is a block diagram showing a schematic hardware configuration of the tablet in FIG. 1 . FIG. 2 is a functional block diagram of the surveillance camera, analysis box, smartphone, and tablet in FIG. 1 . 6 is a diagram illustrating a first superimposed image storage sequence performed by the image acquisition unit, the image analysis unit, and the analysis result superimposition unit in FIG. 5 . FIG. 11 is a second explanatory diagram of the above-mentioned superimposed image storage sequence. 6 is an explanatory diagram of a superimposed image search and display sequence performed by the image acquisition unit, the analysis result superimposition unit, and the image confirmation unit in FIG. 5 . An explanatory diagram of an example of a method for acquiring the installation position and installation angle of a surveillance camera when an installation information acquisition unit is provided on the smartphone. 13 is an explanatory diagram of an example of a method for acquiring the three-dimensional position of lighting when an installation information acquisition unit is provided in the smartphone. An explanatory diagram of an example of a method for acquiring information such as lighting type, intensity, and color when an installation information acquisition unit is provided on the smartphone. FIG. 1A is a diagram showing a captured image of a board on which a two-dimensional barcode is printed, and FIG. 1B is an explanatory diagram of the XYZ coordinates of the installation position of a surveillance camera. FIG. 13 is a diagram showing a superimposed image generation search screen displayed on a tablet. FIG. 13 is a diagram showing a superimposed video recording screen displayed on a tablet when a superimposed video is recorded. FIG. 13 is a diagram showing a superimposed video recording completion screen displayed on the tablet when recording of the superimposed video is completed. 14 is a diagram showing an in-store camera installation status selection screen displayed on the tablet when the button for displaying similar camera images of the main store in FIG. 13 is pressed. FIG. FIG. 17 is a diagram showing an in-store camera video search result display screen displayed on the tablet when the installation situation in FIG. 16 is selected. FIG. 14 is a diagram showing a selection screen for selecting camera installation status at other stores that is displayed on the tablet when the button for displaying images from similar cameras at other stores in FIG. 13 is pressed. 19 is a diagram showing a search result display screen for camera footage from other stores that is displayed on the tablet when the installation status in FIG. 18 is selected.

Hereinafter, a surveillance camera installation support system, a surveillance camera installation support device, and a surveillance camera installation support program according to an embodiment of the present invention will be described with reference to the drawings. FIG. 1 is a block diagram showing the general configuration of a surveillance camera installation support system 1 according to this embodiment. In this embodiment, a plurality of surveillance cameras 2, which are network cameras (IP (Internet Protocol) cameras) for monitoring a predetermined shooting area, and an analysis box 3 (corresponding to the "surveillance camera installation support device" in the claims) to which these surveillance cameras 2 are connected, are installed in a store S such as a chain store. As shown in FIG. 1, the surveillance camera installation support system 1 includes, in addition to the surveillance cameras 2 and the analysis box 3, a smartphone (hereinafter abbreviated as "smartphone") 4 (corresponding to the "mobile terminal" in the claims), a tablet 5, a WiFi AP (WiFi Access Point) 6, a hub 7, and a router 8 in the store S.

The analysis box 3 is connected to the smartphone 4 and tablet 5 via the Wi-Fi AP 6 and the hub 7, and is also connected to multiple surveillance cameras 2 via the LAN (Local Area Network) 20 and the hub 7 to analyze images input from each of these surveillance cameras 2. Specifically, the analysis box 3 performs object detection processing (e.g., detection processing of people (customers) and faces) on images input from each of the surveillance cameras 2, and object recognition processing (e.g., recognition processing of attributes such as the gender and age of people (customers)) on images of objects detected by this object detection processing. In addition, when the surveillance camera 2 is installed or adjusted, the analysis box 3 generates a superimposed image in which information on the analysis results of each frame image (e.g., detection results and recognition results of people, etc.) is superimposed on each frame image input from the surveillance camera 2, and the superimposed image composed of these superimposed images is output to the tablet 5 together with camera installation information (e.g., information on the installation position and installation angle of the surveillance camera 2) linked to the superimposed image to be displayed. When the installation information acquisition unit (see FIG. 5) is provided in the analysis box 3, the analysis box 3 and the tablet 5 correspond to the "computer" in the claims. When the installation information acquisition unit is provided in the smartphone 4, the analysis box 3, the smartphone 4, and the tablet 5 correspond to the "computer" in the claims. When the installation information acquisition unit is provided in the surveillance camera 2 to be installed (or adjusted), the surveillance camera 2, the analysis box 3, and the tablet 5 correspond to the "computer" in the claims.

The surveillance camera installation support system 1 also includes an AI analysis server 9 on the cloud C, and a management server 10. The AI analysis server 9 analyzes, for example, the behavior of people in each store based on the object detection results and object recognition results from the analysis box 3, and converts the information on the analysis results into data that is easy to use for applications for various purposes such as marketing and crime prevention, and outputs it.

The management server 10 manages the numerous analysis boxes 3 arranged in each store and the surveillance cameras 2 connected to these analysis boxes 3. Specifically, the management server 10 installs application packages in the analysis boxes 3 in each store and controls the starting and stopping of the surveillance cameras 2 connected to these analysis boxes 3. This application package is a package program that includes a trained neural network model for object detection (hereinafter referred to as the "NN model for object detection"), a trained neural network model for object recognition (hereinafter referred to as the "NN model for object recognition"), and a control script that describes how to use these neural network models (hereinafter referred to as the "NN model") (the order of processing), and includes a program to support the installation of surveillance cameras.

Next, the hardware configuration of the analysis box 3 will be described with reference to FIG. 2. The analysis box 3 includes a CPU 11 that controls the entire device and performs various calculations, a hard disk 12 that stores various data and programs, a RAM (Random Access Memory) 13, inference chips (hereinafter abbreviated as "chips") 14a to 14h that are DNN inference processors, and a communication control IC 15. The CPU 11 is a general-purpose CPU, or a CPU designed to improve parallel processing performance in order to simultaneously process a large number of video streams. The data stored in the hard disk 12 includes various DBs (Data Bases) such as the video DB 54 (see FIG. 5) described later. The programs stored in the hard disk 12 include the above-mentioned application package 17 (the main part of the "surveillance camera installation support program" in the claims), as well as the program of the analysis box OS. In addition, the "surveillance camera installation support program" in the claims is composed of the above-mentioned application package 17, as well as an installation information acquisition application 32 for the smartphone 4 and a superimposed image generation confirmation program 47 for the tablet 5, which will be described later.

The above (inference) chips 14a to 14h are preferably processors (chips dedicated to inference) optimized for DNN (Deep Neural Networks) inference, but may also be general-purpose GPUs (Graphics Processing Units) used for general purposes, or other processors. Also, each of the above chips 14a to 14h may be a device in which multiple chips (inference processors) are integrated (mounted) on a single board computer.

As shown in FIG. 2, the (inference) chips 14a to 14h are connected to the CPU 11 via PCI Express or USB. The communication control IC 15 also has a LAN port 16, which is a port for connecting to an Ethernet-standard LAN.

Next, referring to FIG. 3, the hardware configuration of the smartphone 4 and the installation information acquisition application 32 installed in the smartphone 4 will be described. The smartphone 4 includes a SoC (System-on-a-Chip) 21, a built-in camera 24, a microphone 25, a touch panel display 26, a speaker 27, a memory 28 for storing various data and programs, a communication unit 29, a secondary battery 30, and a charging terminal 31. The SoC 21 includes a CPU 22 for controlling the entire device and performing various calculations, and a GPU 23 used for inference processing of the NN model for object detection and the NN model for object recognition. The touch panel display 26 is also used as a pointing device for the user (the person installing the surveillance camera 2) to specify the position of a light source (such as lighting) around the surveillance camera 2 in the input image from the built-in camera 24 displayed on the touch panel display 26.

The programs stored in the memory 28 include an installation information acquisition application 32 downloaded from the management server 10 to the smartphone 4 and installed. In the example shown in FIG. 3, the installation information acquisition application 32 includes a camera detection model 33 and an AR application 34. The AR application 34 is a program for an AR engine using existing technology such as ARKit (a framework for AR-compatible applications for iPhone (registered trademark) and iPad (registered trademark)). However, as described below, when the user manually inputs camera installation information indicating the installation status at the time of shooting the surveillance camera 2 using the UI of the smartphone 4, the installation information acquisition application 32 does not need to include the above camera detection model 33 and AR application 34, and only needs to include a program for realizing a UI for inputting camera installation information.

The communication unit 29 includes a communication IC and an antenna. The smartphone 4 is connected to the management server 10 via the communication unit 29 and a network. The secondary battery 30 is a battery that can be used repeatedly by charging, such as a lithium-ion battery, and stores power from a commercial power source after it is converted to DC power by an AC/DC converter, and supplies the power to each part of the smartphone 4.

Next, the hardware configuration of the tablet 5 will be described with reference to FIG. 4. The tablet 5 includes a built-in camera 40, a SoC (System-on-a-Chip) 41, a touch panel display 44, a speaker 45, a memory 46 that stores various data and programs, a communication unit 48, a secondary battery 49, and a charging terminal 39. The SoC 41 includes a CPU 42 that controls the entire device and performs various calculations, and a GPU 43 that is used for inference processing of various trained DNN (Deep Neural Networks) models.

The programs stored in the memory 46 include a superimposed image generation confirmation program 47, which is a program for realizing the functions of the image confirmation unit 63 described later in FIG. 5. This superimposed image generation confirmation program 47 is a program for realizing a function of instructing and inputting a generation process of a superimposed image in which information on the analysis result is superimposed on the frame images input from each of the surveillance cameras 2, a function of instructing and inputting a search and display of a superimposed image of a surveillance camera 2 installed in a similar installation situation to the surveillance camera 2 to be installed this time from among the surveillance cameras 2 installed in the same store, and a function of instructing and inputting a search and display of a superimposed image of a surveillance camera 2 installed in a similar installation situation to the surveillance camera 2 to be installed this time from among the surveillance cameras 2 installed in other stores.

The communication unit 48 includes a communication IC and an antenna. The tablet 5 is connected to the analysis box 3 and the management server 10 on the cloud C via the communication unit 48 and a network. The secondary battery 49 is a battery that can be used repeatedly by charging, such as a lithium-ion battery, and stores power from a commercial power source after it is converted to DC power by an AC/DC converter, and supplies the power to each part of the tablet 5.

Figure 5 shows an example of the functional blocks of the above-mentioned surveillance camera 2, analysis box 3, smartphone 4, and tablet 5. The analysis box 3 has, as its main functional blocks, a video acquisition unit 53, an image analysis unit 55, and an analysis result superimposition unit 57. The above-mentioned analysis result superimposition unit 57 has a superimposition unit 58, an installation information linking unit 59, and a query reception unit 61. The query reception unit 61 has a video output unit 62. The above-mentioned video acquisition unit 53, image analysis unit 55, superimposition unit 58, installation information linking unit 59, and query reception unit 61 are functional blocks possessed by the CPU 11 of the analysis box 3. The CPU 11 of the analysis box 3 realizes these functions using the above-mentioned application package 17. In addition, the analysis box 3 has a video DB 54, an analysis result DB 56, and an installation information DB 60 in the hard disk 12 (see Figure 2). The image analysis unit 55, the analysis result superimposition unit 57, the video DB 54, the installation information DB 60, and the video output unit 62 correspond to the image analysis means, the analysis result superimposition means, the superimposed video storage means, the installation information storage means, and the video output means, respectively, in the claims.

The above surveillance camera 2 includes an imaging unit 50. In the example shown in FIG. 5, the smartphone 4 includes an installation information acquisition unit 52. However, as shown by the dashed line in FIG. 5, the surveillance camera 2 may include the installation information acquisition unit 51, and the analysis box 3 may include the installation information acquisition unit 68. The above installation information acquisition unit 51, the installation information acquisition unit 52, or the installation information acquisition unit 68 corresponds to the installation information acquisition means in the claims. The installation information acquisition unit 51, the installation information acquisition unit 52, or the installation information acquisition unit 68 acquires camera installation information indicating the installation status at the time of shooting of the surveillance camera 2. The above installation information acquisition unit 52 is a functional block possessed by the SoC 21 (see FIG. 3) of the smartphone 4, and the installation information acquisition unit 68 is a functional block possessed by the CPU 11 (see FIG. 2) of the analysis box 3. The above installation information acquisition unit 51 is a functional block possessed by the CPU (not shown) of the surveillance camera 2. The following explanation mainly focuses on an example in which the smartphone 4 is equipped with an installation information acquisition unit 52.

The video acquisition unit 53 in the above-mentioned analysis box 3 is a function realized by a so-called VMS (Video Management System), which decodes the video stream input from the surveillance camera 2 via the hub 7, stores the decoded frame images (data) in the video DB 54 on the hard disk 12, and outputs them to the image analysis unit 55 via the bus in the analysis box 3. This video acquisition unit 53, together with the video DB 54, constitutes a VMS server.

The image analysis unit 55 analyzes each frame image input from the surveillance camera 2. The analysis result DB 56 stores (stores) information on the analysis result of each frame image by the image analysis unit 55. The analysis result superimposition unit 57 generates a superimposed image by superimposing information on the analysis result of each frame image by the image analysis unit 55 on each frame image input from the surveillance camera 2. The video DB 54 stores a superimposed image composed of each superimposed image generated by the analysis result superimposition unit 57 in addition to the decoded frame image input from the surveillance camera 2. More precisely, the superimposition unit 58 in the analysis result superimposition unit 57 generates a superimposed image by superimposing information on the analysis result of each frame image stored in the analysis result DB 56 on each frame image from the surveillance camera 2 stored in the video DB 54, and stores the superimposed image composed of each generated superimposed image in the video DB 54. The installation information linking unit 59 also writes the camera installation information sent from the installation information acquisition unit 52 of the smartphone 4 to the installation information DB 60 together with the video start time of the superimposed image generated by the superimposition unit 58 (the start time of generation of the superimposed image). As a result, the installation information DB 60 stores the camera installation information at the time of shooting by the surveillance camera 2, acquired by the installation information acquisition unit 52 on the smartphone 4 side, in association with the superimposed image stored in the image DB 54.

The tablet 5 also includes a video confirmation unit 63. The video confirmation unit 63 includes a display unit 64, a condition input unit 66, and a query issuing unit 67. The display unit 64 (corresponding to the video display means in the claims) displays the superimposed video stored in the video DB 54 together with the camera installation information associated with the superimposed video stored in the installation information DB 60.

As shown in FIG. 5, the surveillance camera installation support system 1 includes a camera installation information search unit 65 (corresponding to the camera installation information search means in the claims). The camera installation information search unit 65 is composed of a condition input unit 66 and a query issuing unit 67 on the tablet 5 side, and a query receiving unit 61 on the analysis box 3 side.

The camera installation information search unit 65 has a function of searching for camera installation information corresponding to an installation situation similar to that of the surveillance camera 2 to be installed this time from among the camera installation information stored in the installation information DB 60 of the analysis box 3 in FIG. 5 installed in the same store S. In other words, the camera installation information search unit 65 has a function of searching for a superimposed image of a surveillance camera 2 in an installation situation similar to that of the surveillance camera 2 to be installed this time from among the superimposed images based on the images of the surveillance cameras 2 installed in the same store S. In addition, the camera installation information search unit 65 has a function of searching for camera installation information corresponding to an installation situation similar to that of the surveillance camera 2 to be installed this time from among the camera installation information stored in the installation information DB 60 in another store (the installation information DB 60 in another surveillance camera installation support system 1 installed in a different place from the surveillance camera installation support system 1 in FIG. 1 and FIG. 5) via the network. In other words, the camera installation information search unit 65 has the function of searching for superimposed images based on the images of surveillance cameras 2 installed in other stores, for superimposed images of surveillance cameras 2 with installation conditions similar to that of the surveillance camera 2 to be installed this time.

The display unit 64 displays the superimposed images linked to the camera installation information searched for by the camera installation information search unit 65 together with the searched camera installation information. In addition, although details will be described later, when the search result by the camera installation information search unit 65 is a plurality of pieces of camera installation information, the display unit 64 displays each of the superimposed images linked to the plurality of pieces of camera installation information side by side (see Figures 17 and 19).

Next, referring to FIG. 6 and FIG. 7, the superimposed image storage sequence performed mainly by the image acquisition unit 53, the image analysis unit 55, and the analysis result superimposition unit 57 will be described. First, the analysis result superimposition unit 57 in the analysis box 3 inputs the camera installation information indicating the installation situation at the time of shooting of the surveillance camera 2 acquired by the installation information acquisition unit 52 of the smartphone 4 in FIG. 5 from the smartphone 4. This camera installation information is information indicating the installation situation such as the installation position, installation angle, light source situation around the surveillance camera 2, and detection location of the detection target at the time of shooting of the surveillance camera 2. The installation information acquisition unit 52 may be realized by the user manually inputting the camera installation information using the UI of the smartphone 4. When the user presses the superimposed image generation button 79 on the superimposed image generation search screen 78 (see FIG. 13) displayed on the touch panel display 44 of the tablet 5, the analysis result superimposition unit 57 stores the camera installation information such as the installation position of the surveillance camera 2 together with the video start time (the start time of generating the superimposed image) in the installation information DB 60 (S1).

On the other hand, when the superimposed image generation button 79 (see FIG. 13) is pressed, the image acquisition unit 53 acquires the image (stream) from the surveillance camera 2 (S2), decodes it, and transmits the decoded frame images to the image analysis unit 55 (S3), while also saving the camera image composed of the frame images in the image DB 54 (S4).

When the image analysis unit 55 acquires the frame image sent from the video acquisition unit 53 (VMS) in S3 above, it inputs this frame image into various trained DNN models to acquire information (inference information) such as the detection results of people, faces, etc., and the recognition results of gender, age, etc. (S6). After acquiring this inference information, the image analysis unit 55 transmits this inference information and the frame image acquired in S5 above to the analysis result superimposition unit 57 (S7).

When the analysis result superimposition unit 57 acquires the frame images and inference information (inference results) transmitted from the image analysis unit 55 in S7 above (S8), it generates superimposed images in which the inference results are superimposed on each of the acquired frame images (S9), generates superimposed videos from these superimposed images, and transmits them to the video acquisition unit 53 (VMS) (S10). The video acquisition unit 53 stores this superimposed video in the video DB 54 (S11).

After the processing of S10, the analysis result superimposition unit 57 calculates statistical information such as the number of people detected based on the inference results received from the image analysis unit 55, and stores the information in the analysis result DB 56 (S12). This statistical information is statistical information such as the total number of people or faces detected in each superimposed video for a predetermined time period (e.g., 1 to 2 minutes) stored in the video DB 54, and the inference accuracy, and does not necessarily have to be calculated automatically by the analysis result superimposition unit 57, but may be manually entered by an operator using, for example, the smartphone 4 or tablet 5.

Next, referring to FIG. 8, the superimposed image search and display sequence performed mainly by the image acquisition unit 53 and the analysis result superimposition unit 57 on the analysis box 3 side and the image confirmation unit 63 on the tablet 5 side will be described. When the user inputs camera installation information such as the camera installation position as a search key from the condition input unit 66 (see FIG. 5) in the image confirmation unit 63 on the tablet 5 side to search for superimposed images of the surveillance camera 2 in an installation situation similar to that of the surveillance camera 2 being installed (or adjusted) work, the query issuing unit 67 issues a query to the analysis result superimposition unit 57 on the analysis box 3 side using the input camera installation information as a key (S21). Note that when searching for superimposed images of the surveillance camera 2 in an installation situation similar to that of the surveillance camera 2 to be installed this time from superimposed images based on the images of the surveillance cameras 2 installed in the same store S, the query issuing unit 67 issues a query to the analysis result superimposition unit 57 of the analysis box 3 installed in the same store S. Furthermore, when searching for superimposed video of a surveillance camera 2 installed in a similar installation situation to that of the surveillance camera 2 to be installed, from among superimposed video based on the video of the surveillance camera 2 installed in another store, the query issuing unit 67 issues a query to the analysis result superimposing unit 57 of the analysis box 3 installed in the other store.

When the analysis result superimposition unit 57 on the analysis box 3 side receives the query issued by the query issuing unit 67 on the tablet 5 side through the query receiving unit 61, it searches the camera installation information stored in the installation information DB 60 for camera installation information similar to the camera installation information included as a key in the query (S22). Then, it reads out the video start time of the superimposed video linked to the camera installation information that is the search result from the installation information DB 60, and issues a superimposed video acquisition query with this video start time as a key to the video acquisition unit 53 (S23). The video acquisition unit 53 searches the superimposed video stored in the video DB 54 for a superimposed video having a video start time that corresponds to the video start time included in the superimposed video acquisition query (S24), and sends the searched superimposed video to the video confirmation unit 63 on the tablet 5 side (S25).

After completing the process of S23, the analysis result superimposition unit 57 acquires from the analysis result DB 56 the statistical information of the superimposed image searched by the image acquisition unit 53 in S24, and transmits the acquired statistical information together with the camera installation information searched in S22 to the image confirmation unit 63 on the tablet 5 side (S26). The image confirmation unit 63 on the tablet 5 side receives the superimposed image, camera installation information, and statistical information transmitted from the analysis box 3 side in S25 and S26 above (S27 and S28), and displays the received superimposed image, camera installation information, and statistical information on the display unit 64 (S29).

Next, referring to FIG. 9, an example of a method for acquiring camera installation information when the smartphone 4 is provided with an installation information acquisition unit 52 (see FIG. 5) will be described. Before executing the camera installation information acquisition process by this acquisition method, the installer of the surveillance camera 2 downloads and installs the installation information acquisition application 32 (see FIG. 3) from the management server 10 (see FIG. 1) to the smartphone 4. Then, when installing or adjusting the surveillance camera 2, the installer starts the installation information acquisition application 32 and points the smartphone 4 toward the surveillance camera 2. The SoC 21 of the smartphone 4 detects the surveillance camera 2 using the camera detection model 33 included in the installation information acquisition application 32 shown in FIG. 3, and then acquires the three-dimensional position of the surveillance camera 2 by the AR function of the AR application 34 (see FIG. 3). For example, the three-dimensional position (installation position) and installation angle of the surveillance camera 2 are acquired using the built-in camera 24 (see FIG. 3), a GPS (Global Positioning System) sensor, an electronic compass, and an acceleration sensor that the smartphone 4 has. Specifically, in addition to the image 69 captured by the built-in camera 24 of the smartphone 4, the three-dimensional position (installation position) and installation angle of the surveillance camera 2 are obtained based on the position information of the smartphone 4 captured by the GPS sensor (GPS module), the direction of the image captured by the built-in camera 24 obtained using an electronic compass, and the inclination of the smartphone 4 obtained using an acceleration sensor. Note that 70 in FIG. 9 indicates lighting, which is a light source around the surveillance camera 2, and 2a and 70a respectively indicate the image of the surveillance camera 2 (camera image) and the image of the lighting 70 (lighting image).

When the above-mentioned process of acquiring the three-dimensional position of the surveillance camera 2 is completed and the installer of the surveillance camera 2 taps on the lighting image 70a in the captured image 69 displayed on the touch panel display 26 of the smartphone 4 as shown in FIG. 10, the SoC 21 of the smartphone 4 acquires the three-dimensional position of the lighting 70 by the AR function of the AR application 34 (see FIG. 3) based on the installation information acquisition application 32. Specifically, in addition to the captured image 69 captured by the built-in camera 24 of the smartphone 4, the three-dimensional position of the lighting 70 is acquired based on the position on the touch panel display 26 where the installer tapped as detected by the touch panel display 26, the position information of the smartphone 4 captured by the GPS sensor, the direction of the image captured by the built-in camera 24 acquired using the electronic compass, and the tilt of the smartphone 4 acquired using the acceleration sensor.

Furthermore, when the process of acquiring the three-dimensional position of the light 70 is completed, the SoC 21 of the smartphone 4 displays a lighting information input window 71 on the touch panel display 26, superimposed on the captured image 69, as shown in FIG. 11, based on the installation information acquisition application 32. The person installing the surveillance camera 2 can input information about the type, intensity, color, etc. of the light 70 by pointing with a finger at the lighting information input window 71 displayed on the touch panel display 26.

Next, referring to Figures 12(a) and (b), an example of a method for acquiring camera installation information when the installation information acquisition unit 51 (see Figure 5) is provided in the surveillance camera 2 will be described. When installing or adjusting the surveillance camera 2, the installer places a board 72 on which a two-dimensional barcode 73 shown in Figure 12(a) is printed on the floor in the area captured by the surveillance camera 2 in the store S, and captures it with the surveillance camera 2. At this time, the installer installs the two-dimensional barcode 73 so that the up-down direction is aligned with the Z axis (see Figure 12(b)) of the store floor map, and the left-right direction of the two-dimensional barcode 73 is aligned with the X axis of the store floor map, and captures the image. In this state, the CPU (installation information acquisition unit 51) of the surveillance camera 2 recognizes the two-dimensional barcode 73 in the captured image, and estimates the installation height position (height from the floor) and installation angle of the surveillance camera 2. The image of the board 72 (on which the two-dimensional barcode 73 is printed) captured by the surveillance camera 2 is displayed on the touch panel display 44 (display unit 64) of the tablet 5. When the CPU of the surveillance camera 2 recognizes the two-dimensional barcode 73 in the captured image, it displays the id (in the example of FIG. 12(a), id=[0, 4, 11, 12]) assigned to the recognized two-dimensional barcode 73, as shown in FIG. 12(a), and also displays detection marks 75 in the upper right corners of each mark 74 arranged at the top, bottom, left, and right positions of the two-dimensional barcode 73. The id=[0, 4, 11, 12] of the above two-dimensional barcode 73 indicates that the ids of the marks 74 at the top, bottom, left, and right of the two-dimensional barcode 73 are 0, 4, 11, and 12, respectively.

The CPU of the surveillance camera 2 estimates the installation height position and installation angle (tilt) of the surveillance camera 2 based on how the up, down, left and right marks 74 of the two-dimensional barcode 73 are displayed in the captured image on the touch panel display 44 of the tablet 5. More specifically, the CPU of the surveillance camera 2 (the installation information acquisition unit 51) estimates the installation height position (Y coordinate) and installation angle (tilt) of the surveillance camera 2 based on how the up, down, left and right marks 74 of the two-dimensional barcode 73 are displayed in the captured image (the size, tilt and shape of the up, down, left and right marks 74 in the captured image). In addition, the CPU of the surveillance camera 2 (the installation information acquisition unit 51) displays the store plan map on the touch panel display 44 of the tablet 5 for the position of the surveillance camera 2 on the XZ coordinate plane (on the store plan map) among the installation positions of the surveillance camera 2, and prompts the installer of the surveillance camera 2 to specify and input the position (X coordinate and Z coordinate) of the surveillance camera 2 on the store plan map. In response to this, the installer of the surveillance camera 2 inputs the position (X and Z coordinates) of the surveillance camera 2, and the CPU of the surveillance camera 2 (the installation information acquisition unit 51) can obtain the X and Z coordinates of the surveillance camera 2.

The CPU of the above surveillance camera 2 can perform camera calibration using the captured image of the chessboard. The CPU 11 of the analysis box 3 may also perform the above camera calibration using the image of the chessboard captured by the surveillance camera 2.

Next, referring to FIG. 13, the process instructed from the superimposed image generation search screen 78 displayed on the touch panel display 44 of the tablet 5 will be described. The superimposed image generation search screen 78 is provided with a superimposed image generation button 79, a display similar camera image of the main store (same store S) button 80, and a display similar camera image of other stores button 81.

First, the superimposed image generation process that is performed when the superimposed image generation button 79 is pressed will be described. When the installer of the surveillance camera 2 presses the superimposed image generation button 79, the superimposition unit 58 of the analysis box 3 generates a superimposed image by superimposing information on the analysis results of each frame image by the image analysis unit 55 onto each frame image input from the surveillance camera 2, and stores (stores) the superimposed image composed of the superimposed image in the image DB 54. At the same time, the installation information linking unit 59 of the analysis box 3 writes the camera installation information sent from the installation information acquisition unit 52 of the smartphone 4 into the installation information DB 60, associating it with the video start time of the superimposed image generated by the superimposition unit 58. When the analysis box 3 is storing (recording) the above-mentioned superimposed image in the image DB 54, the SoC 41 of the tablet 5 (see FIG. 4) displays the superimposed image recording screen 83 shown in FIG. 14 on the touch panel display 44, and when the recording of the above-mentioned superimposed image in the image DB 54 is completed, the SoC 41 of the tablet 5 displays the superimposed image recording completion screen 84 shown in FIG. 15 on the touch panel display 44.

Next, the process of displaying similar camera images in the same store, which is performed when the button 80 for displaying similar camera images in the main store in FIG. 13 is pressed, will be described. When the installer of the surveillance camera 2 presses the button 80 for displaying similar camera images in the main store, the SoC 41 of the tablet 5 displays the in-store camera installation status selection screen 85 shown in FIG. 16 based on the superimposed image generation confirmation program 47 (see FIG. 4). The in-store camera installation status selection screen 85 is a screen that displays superimposed images 86 in a plurality of installation statuses of the surveillance camera 2 installed in the store where the tablet 5 is placed. The in-store camera installation status selection screen 85 is a screen for the installer of the surveillance camera 2 to select which installation status is closest to the image of the surveillance camera 2 by looking at the inference results (results of human detection and face detection) displayed in the superimposed images 86 in each installation status of the surveillance camera 2 (in the example of FIG. 16, installation status 1, installation status 2, etc.). Additionally, each superimposed image 86 displayed on the in-store camera installation status selection screen 85 is a superimposed image generated when the security camera 2 installer presses the superimposed image generation button 79 (see FIG. 13) on the superimposed image generation search screen 78 in each installation status while adjusting (changing) the installation status of the same security camera 2, such as the installation position and installation angle, or is a superimposed image generated when the superimposed image generation button 79 is pressed during installation adjustment of another security camera 2 in the same store (in each installation status).

When the operator installing the surveillance camera 2 presses the play button 86d below the superimposed image 86 on the in-store camera installation status selection screen 85, the superimposed image 86 is played. In each frame image constituting the superimposed image 86, a person detection (bounding) box 86a indicating the detection of a person and a face detection (bounding) box 86b indicating the detection of a face are displayed. The person detection (bounding) box 86a and the face detection (bounding) box 86b indicating the detection of a face are the "inference results" described in S9 of FIG. 7, and the person detection box 86a and the face detection box 86b indicate the inference results of the person detection and the inference results of the face detection, respectively. These inference results (the person detection box 86a and the face detection box 86b) correspond to the "information of the analysis results of each frame image" in the claims. Note that 86c in the superimposed image 86 indicates a false detection face (bounding) box corresponding to a face erroneously detected by the image analysis unit 55.

On the in-store camera installation status selection screen 85, below each superimposed image 86, camera installation information 87 indicating the installation status of the surveillance camera 2 at the time each superimposed image 86 was generated, and statistical information 88 for each superimposed image 86 are displayed. The SoC 41 of the tablet 5 targets the image DB 54, installation information DB 60, and analysis result DB 56 of the analysis box 3 installed in the same store S as the tablet 5, and displays the superimposed image 86, camera installation information 87, and statistical information 88 based on the superimposed image acquired from the image DB 54, the camera installation information acquired from the installation information DB 60, and the statistical information acquired from the analysis result DB 56.

In the example of Figure 16, the camera installation information 87 on the in-store camera installation status selection screen 85 is composed of the installation position (height) and installation angle (roll angle, pitch angle, and yaw angle) of the surveillance camera 2, but the camera installation information on the in-store camera installation status selection screen may also include information such as the light source conditions around the surveillance camera 2 and the detection location of the detection target. Also, in the example of Figure 16, the statistical information 88 on the in-store camera installation status selection screen 85 is composed of the number of people detected, the number of faces detected, and the number of upward detections (the number of people detected moving from bottom to top), but the statistical information displayed on the in-store camera installation status selection screen 85 is not limited to these. For example, if the installer of the surveillance camera 2 manually inputs the person detection rate, face detection rate, and upward direction detection rate (detection rate of people moving from bottom to top) for the corresponding superimposed image 86 from the UI screen on the touch panel display 44 of the tablet 5, the SoC 41 of the tablet 5 may input this statistical information into the analysis result DB 56 and display it as statistical information on the in-store camera installation status selection screen 85. Also, if the installer of the surveillance camera 2 manually inputs an evaluation value for the corresponding superimposed image 86 from the UI screen on the touch panel display 44 of the tablet 5, the SoC 41 of the tablet 5 may input this evaluation value as statistical information into the analysis result DB 56 and display it as statistical information on the in-store camera installation status selection screen 85.

When the installer of the surveillance camera 2 taps to select an installation situation (such as installation situation 1 or installation situation 2 in FIG. 16) that is close to the installation situation of the surveillance camera 2 that he or she wants to adopt from among the multiple installation situations displayed on the touch panel display 44 of the tablet 5, the SoC 41 (query issuing unit 67) of the tablet 5 issues a query to the analysis box 3 (query receiving unit 61) installed in the same store S as the tablet 5, using the camera installation information corresponding to the installation situation selected by the installer as a key. As a result, the CPU 11 of the analysis box 3 searches for camera installation information similar to the key camera installation information from the camera installation information stored in the installation information DB 60, reads out the superimposed video linked to this camera installation information from the video DB 54 using the video start time (the start time of generation of the superimposed video) as a key, and sends the read superimposed video to the tablet 5 together with the searched camera installation information and statistical information corresponding to the superimposed video. Then, when the SoC 41 of the tablet 5 receives the above-mentioned superimposed image, camera installation information, and statistical information, it displays the in-store camera image search result display screen 89 shown in FIG. 17 on the touch panel display 44 of the tablet 5 based on this data.

The in-store camera video search result display screen 89 displays one or more superimposed images 91 of installation situations similar to the installation situation selected on the in-store camera installation situation selection screen 85, together with camera installation information corresponding to the installation situation at the time of generation of the superimposed images 91, and statistical information corresponding to the superimposed images. In addition to information similar to that of the in-store camera installation situation selection screen 85 (superimposed images 91, camera installation information 92, and statistical information 93), the in-store camera video search result display screen 89 displays a search key 90, which is camera installation information corresponding to the installation situation selected on the in-store camera installation situation selection screen 85, the "search results" (number of results) when a query is issued using the search key 90 as a key, and video identification information 94. The video identification information 94 includes camera identification information (in the example shown, "entrance" (camera)), the identification number of the superimposed video taken by the surveillance camera 2 corresponding to the camera identification information, and the similarity (in the example shown, 100%, 98.5%, and 99%). The installer of the surveillance camera 2 can determine which (surveillance camera 2) installation situation is preferable by looking at the inference results (human detection and face detection results) and statistical information 93 for each superimposed image 91 displayed on the in-store camera image search result display screen 89. In addition, the installer of the surveillance camera 2 can easily coordinate with the customer how to install the surveillance camera 2 (how to set the installation situation, such as the installation position and installation angle of the surveillance camera 2) by showing the inference results and statistical information 93 for each superimposed image 91 to the person in charge of the store S where the surveillance cameras 2 are to be installed (hereinafter referred to as the "customer").

Next, the similar camera image display process of other stores, which is performed when the similar camera image display button 81 of other stores in FIG. 13 is pressed, will be described. When the installer of the surveillance camera 2 presses the similar camera image display button 81 of other stores, the SoC 41 of the tablet 5 displays the other store camera installation status selection screen 95 shown in FIG. 18 based on the superimposed image generation confirmation program 47 (see FIG. 4). The other store camera installation status selection screen 95 is a screen that displays superimposed images 86 in a plurality of installation statuses of the surveillance camera 2 installed in other stores (at locations different from the store S) other than the store S where the tablet 5 is placed. The other store camera installation status selection screen 95 is a screen for the installer of the surveillance camera 2 to select which installation status is closest to the image of the surveillance camera 2 to search for by looking at the inference results (results of human detection and face detection) displayed on the superimposed images 96 in each installation status of the surveillance camera 2 installed in the other store. In addition, each superimposed image 96 displayed on the other store camera installation status selection screen 95 is a superimposed image that the installer of the surveillance camera 2 at the other store instructed to generate when adjusting the installation of the surveillance camera 2 installed at the other store.

The other store camera installation status selection screen 95 displays the same information (overlapping image 96, camera installation information 97, and statistical information 98) as the in-store camera installation status selection screen 85. Note that 96c in the overlapping image 96 indicates a false detection face (bounding) box corresponding to a face that has been falsely detected by the analysis box 3 (of the image analysis unit 55) of the other store.

When the installer of the surveillance camera 2 taps to select an installation status (such as installation status 1 or installation status 2 in FIG. 18) that is similar to the installation status of the surveillance camera 2 that he or she wishes to adopt from among the multiple installation statuses of the surveillance camera 2 in other stores displayed on the touch panel display 44 of the tablet 5, the SoC 41 (query issuing unit 67) of the tablet 5 issues a query to the analysis box 3 (query receiving unit 61) installed in a store (other store) different from the tablet 5, using the camera installation information corresponding to the installation status selected by the installer as a key. As a result, the CPU 11 of the analysis box 3 of the other store searches for camera installation information similar to the key camera installation information from the camera installation information stored in the installation information DB 60 of the analysis box 3, reads out the superimposed video linked to this camera installation information from the video DB 54 using the video start time as a key, and sends the read superimposed video to the tablet 5 together with the searched camera installation information and statistical information corresponding to the superimposed video. Then, when the SoC 41 of the tablet 5 receives the above-mentioned superimposed images, camera installation information, and statistical information of other stores, it displays the other store camera image search result display screen 99 shown in FIG. 19 on the touch panel display 44 of the tablet 5 based on this data.

The other store camera video search result display screen 99 is a screen that displays one or more superimposed images 101 generated in an installation situation similar to the installation situation selected in the other store camera installation situation selection screen 95, together with camera installation information 103 corresponding to the installation situation at the time of generation of the superimposed image 101, and statistical information 104 corresponding to the superimposed image 101. The other store camera video search result display screen 99 displays information similar to that of the in-store camera video search result display screen 89 (search key 100, superimposed image 101, video identification information 102, camera installation information 103, and statistical information 104). The installer of the surveillance camera 2 can determine which (surveillance camera 2) installation situation is preferable by looking at the inference results (human detection and face detection results) and statistical information 104 for each superimposed image 101 displayed on the other store camera video search result display screen 99. Therefore, once a certain amount of data has been accumulated in the databases (video DB 54, analysis results DB 56, and installation information DB 60) of the analysis boxes 3 of other stores, the installer of the surveillance camera 2 can use this data (superimposed video, camera installation information, statistical information) to search for the camera installation angle and other factors that will achieve high accuracy in the installation environment of the surveillance camera 2 that he or she is currently attempting to install (the installation position of the surveillance camera 2 (height from the floor), the light source conditions around the surveillance camera 2, and the detection location of the detection target, etc.).

As described above, according to the surveillance camera installation support system 1 of this embodiment, a superimposed image is generated by superimposing information on the analysis results of each frame image on each frame image input from the surveillance camera 2, and a superimposed video composed of these superimposed images is displayed together with the camera installation information (e.g., information on the installation position and installation angle of the surveillance camera 2) linked to this superimposed video. As a result, when the person installing the surveillance camera 2 at the installation site of the surveillance camera 2 adjusts (changes) the installation status of the surveillance camera 2, such as the installation position and installation angle of the surveillance camera 2, the person installing the surveillance camera 2 can easily check the change in the accuracy of the analysis results due to the adjustment of the installation status of the surveillance camera 2 by looking at the information on the analysis results (e.g., the (inference) results of human detection and face detection) superimposed on each frame image of the superimposed video together with the camera installation information indicating the installation status.

In addition, according to the surveillance camera installation support system 1 of this embodiment, as shown in each screen of Figures 16 to 19 (in-store camera installation status selection screen 85, in-store camera video search result display screen 89, other store camera installation status selection screen 95, and other store camera video search result display screen 99), superimposed images in multiple installation statuses of the surveillance cameras 2 are displayed side by side. This allows the person installing the surveillance cameras 2 to compare and check the accuracy of the analysis results in multiple installation statuses of the surveillance cameras 2.

In addition, according to the surveillance camera installation support system 1 of this embodiment, camera installation information corresponding to an installation situation similar to that of the surveillance camera 2 to be installed is searched for among the camera installation information stored in the installation information DB 60 of another surveillance camera installation support system 1 installed in another store (different location), and the superimposed image linked to the searched camera installation information is displayed on the touch panel display 44 of the tablet 5 together with the searched camera installation information. This allows the installer of the surveillance camera 2 to refer to the installation situation of the surveillance camera 2 in the other store and the analysis result (inference result) of the superimposed image in that installation situation to determine the installation situation (installation position and installation angle) of the surveillance camera 2 that he or she is currently attempting to install.

In addition, according to the surveillance camera installation support system 1 of this embodiment, it is possible to obtain information on the installation position and installation angle of the surveillance camera 2 based on information obtained from various sensors (built-in camera 40, GPS sensor, electronic compass, and acceleration sensor) mounted on the smartphone 4. This improves convenience for the installer of the surveillance camera 2 compared to when the installer manually inputs information on the installation position and installation angle of the surveillance camera 2 from the touch panel display 26 of the smartphone 4 (or the touch panel display 44 of the tablet 5).

In addition, according to the surveillance camera installation support system 1 of this embodiment, information on the installation position and installation angle of the surveillance camera 2 is obtained based on an image captured by the surveillance camera 2 of a board 72 (see FIG. 12(a)) with a two-dimensional barcode 73 installed within the shooting area of the surveillance camera 2. This improves convenience for the installer of the surveillance camera 2 compared to when the installer manually inputs the information on the installation position and installation angle of the surveillance camera 2 from the touch panel display 26 of the smartphone 4 (or the touch panel display 44 of the tablet 5).

Furthermore, according to the surveillance camera installation support system 1 of this embodiment, the installation information acquisition unit 51 of the surveillance camera 2 can estimate the installation height position and installation angle of the surveillance camera 2 based on the images of each mark 74 of the two-dimensional barcode 73. This improves convenience for the installer of the surveillance camera 2 compared to when the installer manually inputs the information on the installation height position and installation angle of the surveillance camera 2 from the touch panel display 26 of the smartphone 4 (or the touch panel display 44 of the tablet 5).

Furthermore, according to the analysis box 3 of this embodiment, a superimposed image is generated by superimposing information on the analysis results of each frame image on each frame image input from the surveillance camera 2, and the superimposed video composed of these superimposed images is output and displayed on the tablet 5 (touch panel display 44) together with the camera installation information (e.g., information on the installation position and installation angle of the surveillance camera 2) linked to this superimposed video. As a result, when the person installing the surveillance camera 2 at the installation site of the surveillance camera 2 adjusts (changes) the installation conditions of the surveillance camera 2, such as the installation position and installation angle of the surveillance camera 2, the person installing the surveillance camera 2 can view the information on the analysis results (e.g., the (inference) results of human detection and face detection) superimposed on each frame image of the superimposed video together with the camera installation information indicating the installation conditions on the touch panel display 44, and can easily confirm the change in the accuracy of the analysis results due to the adjustment of the installation conditions of the surveillance camera 2.

Variations:
The present invention is not limited to the configurations of the above-described embodiments, and various modifications are possible without departing from the spirit of the invention.

Variation 1:
In the above embodiment, an example in which the smartphone 4 includes the installation information acquisition unit 52 has been described, but an application similar to the installation information acquisition application 32 (see FIG. 3) may be installed on the tablet so that the tablet includes the installation information acquisition unit. This allows the SoC of the tablet to acquire the camera installation information by using the tablet's UI to manually input camera installation information indicating the installation status at the time of shooting with the surveillance camera, or by using the methods shown in FIGS. 9 to 11. Note that if the tablet includes the installation information acquisition unit, the surveillance camera installation support system 1 does not need to include the smartphone 4.

Variation 2:
In addition, in the above embodiment, an example has been described in which the CPU of the surveillance camera 2 estimates the installation height position and installation angle of the surveillance camera 2 based on how the top, bottom, left and right marks 74 of the two-dimensional barcode 73 are displayed in the captured image on the touch panel display 44 of the tablet 5. However, the surveillance camera may be provided with sensors (GPS sensor, electronic compass, acceleration sensor, angular velocity sensor, etc.) for detecting the installation position and installation angle, and the installation position and installation angle of the surveillance camera may be estimated based on the output values of these sensors.

Variation 3:
In the above embodiment, an example has been shown in which the CPU of the surveillance camera 2 estimates the installation height and installation angle of the surveillance camera 2 based on the images of the marks 74 of the two-dimensional barcode 73. However, the CPU of the surveillance camera may estimate the installation height and installation angle of the surveillance camera based on images of marks other than the two-dimensional barcode.

Variation 4:
In the above embodiment, the analysis box 3 is configured to include the video acquisition unit 53 and the image analysis unit 55, but the present invention is not limited to this configuration. For example, the surveillance camera installed in each store may be an AI (Artificial Intelligence) camera having a so-called edge computing function, and an application package including a trained DNN model for inference processing such as human detection processing and face detection processing may be installed in the AI camera, so that the AI camera has the functions of the video acquisition unit and image analysis unit. In addition, the AI camera may have the functions of the video acquisition unit, video DB, image analysis unit, analysis result DB, and analysis result superimposition unit that the analysis box has in the above embodiment.

Variation 5:
In the above embodiment, an example is shown in which the tablet 5 is equipped with the video confirmation unit 63, but the surveillance camera installation support system may also be equipped with a smartphone having a large touch panel display, and this smartphone may be equipped with the video confirmation unit.

1 Surveillance camera installation support system 2 Surveillance camera 3 Analysis box (surveillance camera installation support device)
4. Smartphone (mobile device)
17. App Package (Main part of the "Surveillance Camera Installation Support Program")
24 Built-in camera ("camera" on "mobile device")
32 Installation information acquisition application (part of the "Surveillance camera installation support program")
47 Overlay image generation confirmation program (part of the "Surveillance camera installation support program")
51 Installation information acquisition unit (installation information acquisition means)
52 Installation information acquisition unit (installation information acquisition means)
54 Video DB (superimposed video storage means)
55 Image analysis unit (image analysis means)
57 Analysis result superimposition unit (analysis result superimposition means)
60 Installation information DB (installation information storage means)
64 Display unit (video display means)
65 Camera installation information search unit (camera installation information search means)
68 Installation information acquisition unit (installation information acquisition means)
72 Board 73 2D barcode 74 Mark

Claims (9)

A surveillance camera installation support system for supporting installation of a surveillance camera that photographs a predetermined photographing area, comprising:
an installation information acquisition means for acquiring camera installation information including information on the height from the floor when the surveillance camera is photographed;
an image analysis means for analyzing each frame image input from the surveillance camera at the height from the floor ;
an analysis result superimposing means for generating a superimposed image by superimposing information on the analysis result of each of the frame images by the image analysis means on each of the frame images;
a superimposed image storage means for storing a superimposed image composed of each superimposed image generated by the analysis result superimposition means at the height from the floor ;
an installation information storage means for storing camera installation information acquired by the installation information acquisition means at the time of shooting of the surveillance camera in association with the superimposed image stored in the superimposed image storage means;
a video display means for displaying the superimposed video stored in the superimposed video storage means together with camera installation information associated with the superimposed video stored in the installation information storage means ;
a camera installation information retrieval means for retrieving camera installation information corresponding to a height from the floor similar to the height from the floor of the surveillance camera to be currently installed from among the camera installation information stored in the installation information storage means in another surveillance camera installation support system installed at a different location from the surveillance camera installation support system,
The video display means displays a superimposed video linked to the camera installation information searched for by the camera installation information search means, together with the searched camera installation information . 2. The surveillance camera installation support system according to claim 1, wherein said image display means displays overlapping images of said surveillance cameras at a plurality of heights from the floor side by side . The surveillance camera installation support system according to claim 1, characterized in that the image display means displays, side by side, each of the superimposed images linked to the multiple camera installation information searched for by the camera installation information search means. A surveillance camera installation support system for supporting installation of a surveillance camera that photographs a predetermined photographing area, comprising:
an installation information acquisition means for acquiring camera installation information indicating an installation status of the surveillance camera at the time of shooting;
an image analysis means for analyzing each frame image input from the surveillance camera in the installation situation;
an analysis result superimposing means for generating a superimposed image by superimposing information on the analysis result of each of the frame images by the image analysis means on each of the frame images;
a superimposed image storage means for storing a superimposed image composed of each superimposed image generated by the analysis result superimposing means in the installation situation;
an installation information storage means for storing camera installation information acquired by the installation information acquisition means at the time of shooting of the surveillance camera in association with the superimposed image stored in the superimposed image storage means;
a video display means for displaying the superimposed video stored in the superimposed video storage means together with camera installation information associated with the superimposed video stored in the installation information storage means,
The camera installation information includes information on the installation position and installation angle of the surveillance camera,
The surveillance camera installation support system includes a mobile terminal,
The installation information acquisition means is a surveillance camera installation support system that acquires information on the installation position and installation angle of the surveillance camera based on information obtained from sensors, including a camera, mounted on the mobile terminal. A surveillance camera installation support system for supporting installation of a surveillance camera that photographs a predetermined photographing area, comprising:
an installation information acquisition means for acquiring camera installation information indicating an installation status of the surveillance camera at the time of shooting;
an image analysis means for analyzing each frame image input from the surveillance camera in the installation situation;
an analysis result superimposing means for generating a superimposed image by superimposing information on the analysis result of each of the frame images by the image analysis means on each of the frame images;
a superimposed image storage means for storing a superimposed image composed of each superimposed image generated by the analysis result superimposing means in the installation situation;
an installation information storage means for storing camera installation information acquired by the installation information acquisition means at the time of shooting of the surveillance camera in association with the superimposed image stored in the superimposed image storage means;
a video display means for displaying the superimposed video stored in the superimposed video storage means together with camera installation information associated with the superimposed video stored in the installation information storage means,
The camera installation information includes information on the installation position and installation angle of the surveillance camera,
The installation information acquisition means is a surveillance camera installation support system that acquires information on the installation position and installation angle of the surveillance camera based on an image captured by the surveillance camera of a two-dimensional barcode board installed within the shooting area. 6. The surveillance camera installation support system according to claim 5 , wherein the installation information acquisition means estimates an installation height position and an installation angle of the surveillance camera based on an image of each mark of the two-dimensional barcode. A surveillance camera installation support program for a surveillance camera installation support system for supporting installation of a surveillance camera that photographs a predetermined photographing area, comprising:
Computer,
an installation information acquisition means for acquiring camera installation information including information on the height from the floor when the surveillance camera is photographed;
an image analysis means for analyzing each frame image input from the surveillance camera at the height from the floor;
an analysis result superimposing means for generating a superimposed image by superimposing information on the analysis result of each of the frame images by the image analysis means on each of the frame images;
a superimposed image storage means for storing a superimposed image composed of each superimposed image generated by the analysis result superimposition means at the height from the floor;
an installation information storage means for storing camera installation information acquired by the installation information acquisition means at the time of shooting of the surveillance camera in association with the superimposed image stored in the superimposed image storage means;
a video display means for displaying the superimposed video stored in the superimposed video storage means together with camera installation information associated with the superimposed video stored in the installation information storage means;
functioning as a camera installation information retrieval means for retrieving camera installation information corresponding to a height from the floor similar to the height from the floor of the surveillance camera to be currently installed, from among camera installation information stored in the installation information storage means in another surveillance camera installation support system installed in a different location from the surveillance camera installation support system;
The surveillance camera installation support program, wherein the image display means displays an overlay image linked to the camera installation information searched for by the camera installation information search means, together with the searched camera installation information. A surveillance camera installation support program for supporting installation of a surveillance camera that photographs a predetermined photographing area, comprising:
Computer,
An installation information acquisition means for acquiring camera installation information indicating an installation status of the surveillance camera at the time of shooting;
an image analysis means for analyzing each frame image input from the surveillance camera in the installation situation;
an analysis result superimposing means for generating a superimposed image by superimposing information on the analysis result of each of the frame images by the image analysis means on each of the frame images;
a superimposed image storage means for storing a superimposed image composed of each superimposed image generated by the analysis result superimposing means in the installation situation;
an installation information storage means for storing camera installation information acquired by the installation information acquisition means at the time of shooting of the surveillance camera in association with the superimposed image stored in the superimposed image storage means;
functioning as an image display means for displaying the superimposed image stored in the superimposed image storage means together with camera installation information associated with the superimposed image stored in the installation information storage means;
The camera installation information includes information on the height of the surveillance camera from the floor,
The installation information acquisition means is a surveillance camera installation support program that acquires information on the height of the surveillance camera from the floor based on information obtained from a sensor, including a camera, mounted on a mobile terminal. A surveillance camera installation support program for supporting installation of a surveillance camera that photographs a predetermined photographing area, comprising:
Computer,
an installation information acquisition means for acquiring camera installation information indicating an installation status of the surveillance camera at the time of shooting;
an image analysis means for analyzing each frame image input from the surveillance camera in the installation situation;
an analysis result superimposing means for generating a superimposed image by superimposing information on the analysis result of each of the frame images by the image analysis means on each of the frame images;
a superimposed image storage means for storing a superimposed image composed of each superimposed image generated by the analysis result superimposing means in the installation situation;
an installation information storage means for storing camera installation information acquired by the installation information acquisition means at the time of shooting of the surveillance camera in association with the superimposed image stored in the superimposed image storage means;
functioning as an image display means for displaying the superimposed image stored in the superimposed image storage means together with camera installation information associated with the superimposed image stored in the installation information storage means;
The camera installation information includes information on the installation position and installation angle of the surveillance camera,
The installation information acquisition means is a surveillance camera installation support program that acquires information on the installation position and installation angle of the surveillance camera based on an image captured by the surveillance camera of a two-dimensional barcode board installed within the shooting area.

Images