Processing device, processing method, and program

Abstract

The present invention provides a processing device (10) having an acquisition unit (11) which acquires images subject to management, and a specification unit (12) which specifies equipment included in an image by using layout information of equipment under management.

Description

[Technical Field]

[0001] The present invention relates to a processing device, a processing method, and a program. [Background technology]

[0002] Patent Document 1 discloses a technique for associating a store's position (coordinates) on a map with a position (coordinates) on an image based on the positions of markers attached to the floor of the store and markers in the image.

[0003] Patent Document 2 discloses a technique for setting a target area on a facility map image that depicts the layout of the facility. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2016-149654 [Patent Document 2] Japanese Patent Application Publication No. 2017-182654 Summary of the Invention [Problem to be solved by the invention]

[0005] The present inventors have studied a technology for monitoring the status of store facilities using images generated by cameras (such as surveillance cameras) installed in the store. Examples of monitoring content include, but are not limited to, monitoring the status of product shelves (whether or not there are missing items, whether or not there are foreign objects, etc.). As a result of studying this technology, the following new problem has been discovered.

[0006] To monitor the above-mentioned equipment, it is necessary to identify which equipment is included in the images generated by each camera. Without this identification, even if a certain event (missing equipment, presence of foreign matter, etc.) is detected through image analysis, it will be unclear which equipment the event occurred in. If a person has to view the images, identify the equipment included in each image, and input the details, this places a heavy burden on the person. Patent Documents 1 and 2 do not disclose this problem or a solution to it.

[0007] An object of the present invention is to provide a technology for identifying equipment included in an image generated by a camera (such as a surveillance camera) installed in a store. [Means for solving the problem]

[0008] According to the present invention, an acquisition means for acquiring images to be managed; an identification means for identifying the equipment included in the image by using layout information of the equipment in the management target; A processing device is provided having:

[0009] Further, according to the present invention, The computer Retrieve the images to be managed, A processing method is provided for identifying the equipment included in the image using layout information of the equipment in the management target.

[0010] Further, according to the present invention, Computer, acquisition means for acquiring images to be managed; an identification means for identifying the equipment included in the image by using layout information of the equipment in the management target; A program is provided to function as a [Effects of the Invention]

[0011] According to the present invention, a technique is realized for identifying equipment included in an image generated by a camera (such as a surveillance camera) installed in a store. [Brief explanation of the drawings]

[0012] [Figure 1] FIG. 2 is a diagram illustrating an example of a hardware configuration of a processing device according to the present embodiment. [Figure 2] FIG. 2 is a functional block diagram of a processing apparatus according to an embodiment of the present invention; [Figure 3] FIG. 2 is a diagram schematically illustrating an example of information processed by the processing device of the present embodiment. [Figure 4] FIG. 2 is a diagram schematically illustrating an example of information processed by the processing device of the present embodiment. [Figure 5] 10 is a flowchart showing an example of a processing flow of the processing device of the present embodiment. [Figure 6] 10 is a flowchart showing an example of a processing flow of the processing device of the present embodiment. [Figure 7] FIG. 2 is a functional block diagram of a processing apparatus according to an embodiment of the present invention; [Figure 8] FIG. 2 is a diagram schematically illustrating an example of information processed by the processing device of the present embodiment. [Figure 9] FIG. 2 is a functional block diagram of a processing apparatus according to an embodiment of the present invention; [Figure 10] FIG. 2 is a functional block diagram of a processing apparatus according to an embodiment of the present invention; [Figure 11] FIG. 2 is a functional block diagram of a processing apparatus according to an embodiment of the present invention; DETAILED DESCRIPTION OF THE INVENTION

[0013] First Embodiment The processing device of this embodiment acquires an image of a managed object (such as a store) generated by a camera (such as a surveillance camera) installed in the managed object, and identifies the equipment included in the image using layout information of the equipment in the managed object. The configuration of the processing device will be described in detail below.

[0014] First, an example of the hardware configuration of the processing device will be described. The functional units of the processing device of this embodiment are realized by any combination of hardware and software, centered on a CPU (Central Processing Unit) of any computer, memory, programs loaded into the memory, a storage unit such as a hard disk that stores the programs (this can store programs that are pre-loaded when the device is shipped, as well as programs downloaded from storage media such as CDs (Compact Discs) or servers on the Internet), and a network connection interface. Those skilled in the art will understand that there are many variations in the implementation methods and devices.

[0015] FIG. 1 is a block diagram illustrating an example of the hardware configuration of a processing device of this embodiment. As shown in FIG. 1, the processing device has a processor 1A, a memory 2A, an input / output interface 3A, a peripheral circuit 4A, and a bus 5A. The peripheral circuit 4A includes various modules. Note that the peripheral circuit 4A may not be included. Note that the processing device may be configured as a single device that is physically and / or logically integrated, or may be configured as multiple devices that are physically and / or logically separated. When configured as multiple devices that are physically and / or logically separated, each of the multiple devices may have the above hardware configuration.

[0016] The bus 5A is a data transmission path for the processor 1A, memory 2A, peripheral circuit 4A, and input / output interface 3A to transmit and receive data to and from each other. The processor 1A is an arithmetic processing device such as a CPU or a GPU (Graphics Processing Unit). The memory 2A is a memory such as a RAM (Random Access Memory) or a ROM (Read Only Memory). The input / output interface 3A includes interfaces for acquiring information from input devices, external devices, external servers, external sensors, cameras, etc., and interfaces for outputting information to output devices, external devices, external servers, etc. Examples of input devices include a keyboard, mouse, microphone, touch panel, physical buttons, camera, etc. Examples of output devices include a display, speaker, printer, mailer, etc. The processor 1A can issue commands to each module and perform calculations based on the results of those calculations.

[0017] Next, the functional configuration of the processing device will be described. Fig. 2 shows an example of a functional block diagram of the processing device 10. As shown in the figure, the processing device 10 has an acquisition unit 11 and an identification unit 12. Note that the processing device 10 may be installed for each management target (i.e., for each store, etc.) and may be a device that manages each management target. Alternatively, the processing device 10 may be installed in a center or the like and may be a server that manages multiple management targets.

[0018] The acquisition unit 11 acquires images of the managed object. The managed object has installed therein a plurality of pieces of equipment that are the target of detecting predetermined events through image analysis. In this embodiment, the managed object is a store. The equipment includes, for example, product shelves, counters, aisles, copy machines, chairs and tables in the eat-in corner, parking lots, etc. The predetermined events include missing items, the presence of foreign objects, etc. Note that the examples of the managed object, equipment, and predetermined events given here are merely examples and are not limited to these. For example, the managed object may be a warehouse, an office, etc. The predetermined events may also be other events that can be detected from images.

[0019] A camera is installed in the managed object to capture images of the managed object. The images generated by the camera include the equipment installed in the managed object. The acquisition unit 11 acquires the images generated by the camera. Note that a plurality of cameras may be installed in the managed object. The acquisition unit 11 may then acquire images generated by each of the plurality of cameras.

[0020] The camera is assumed to continuously generate moving images, but may also generate still images at predetermined timings. The camera may also be equipped with a fisheye lens or a standard lens (e.g., with an angle of view of approximately 40° to 60°).

[0021] In this specification, "acquisition" may include "a device going to retrieve data stored in another device or storage medium (active acquisition)" based on user input or program instructions, such as receiving data by making a request or inquiry to another device, or accessing and reading out another device or storage medium. Furthermore, "acquisition" may also include "inputting data output from another device to a device (passive acquisition)" based on user input or program instructions, such as receiving data that is distributed (or transmitted, push notification, etc.). Furthermore, "acquisition" may also include selecting and acquiring data or information from received data or information, and "generating new data by editing data (converting it to text, rearranging data, extracting some data, changing the file format, etc.), and acquiring the new data."

[0022] The identification unit 12 identifies the equipment included in the image using layout information of the equipment in the management target.

[0023] The image processed by the identification unit 12 may be an image taken with a standard lens, an image taken with a fisheye lens (see Figure 4), or an image obtained by flattening the image taken with a fisheye lens (see Figure 4).

[0024] An example of layout information is shown in Figure 3. The layout information shown in the figure indicates the installation positions of equipment (product shelves, cash register counters, copy machines, and terminals) in the managed area. The layout information also indicates the installation positions of nine cameras with symbols C1 to C9. The layout information also indicates the positions of 18 markers installed in the managed area with symbols M1 to M18.

[0025] Here, an example of a process for identifying equipment included in an image using layout information will be described.

[0026] First, the identification unit 12 extracts markers installed in the management target from the image to be processed. The feature amounts of the appearance of each of the multiple markers are registered in advance, and the identification unit 12 extracts each marker from the image based on the feature amounts. Note that the appearances of the multiple markers are different from each other, making it possible to distinguish the multiple markers from each other based on their appearances.

[0027] Furthermore, the identification unit 12 extracts an object from the image to be processed. Object extraction techniques are widely known, and therefore will not be described here.

[0028] The identification unit 12 then identifies to which equipment the extracted object corresponds based on the relative positional relationship between the extracted marker and the object. For example, the image generated by the camera C4 shown in FIG. 3 may include product shelves 10, 11, 14, and 15, as well as markers M8 and M9. As shown in FIG. 3, the marker M9 is installed near the boundary between the product shelves 10 and 11 and the boundary between the product shelves 14 and 15. The product shelves 10 and 11 are installed on the same side of an aisle, and the product shelves 14 and 15 are installed on the same side of the aisle. The product shelves 10 and 11 are installed on opposite sides of the aisle from the product shelves 14 and 15. The markers M8 and M9 are installed in the aisle. The camera C4 is installed closer to the product shelf 10 than the product shelf 11, and closer to the product shelf 14 than the product shelf 15.

[0029] In this case, for example, the product shelves 10 and 14 can be distinguished from the product shelves 11 and 15 depending on whether they are located closer to the camera or farther away from the marker M9. Then, for example, the product shelves 10 and 14 can be distinguished, and the product shelves 11 and 15 can be distinguished depending on whether they are located to the right or left of the line connecting the markers M8 and M9 as seen from the camera. Therefore, for example, the identification unit 12 can identify to which product shelf the multiple objects extracted from the image generated by the camera C4 correspond, based on the analysis results such as whether the multiple objects extracted from the image generated by the camera C4 are located closer to the camera than the marker M9 or whether they are located to the right or left of the line connecting the markers M8 and M9 as seen from the camera.

[0030] As another example, the identification unit 12 may associate store coordinates defined in layout information such as that shown in Fig. 3 with coordinates on the image based on markers included in the image. This correspondence enables the identification unit 12 to convert the store coordinates in the layout information into coordinates on the image. Therefore, the identification unit 12 may convert the position coordinates of each piece of equipment indicated in the layout information into coordinates on the image, thereby identifying the equipment included in the image and identifying the position of each piece of equipment within the image.

[0031] As another example, a marker for identifying each of the pieces of equipment may be attached to each piece of equipment, and the identification unit 12 may identify which piece of equipment the object extracted from the image is based on the marker attached to the object extracted from the image.

[0032] Alternatively, instead of placing a special marker on the managed object, the managed equipment may be used as a marker.

[0033] The algorithm described here is merely an example and is not limiting.

[0034] Such processing by the identification unit 12 identifies the equipment included in the image. Also, the position of the equipment in the image (the area it occupies) is identified. Furthermore, when the acquisition unit 11 acquires images generated by each of the multiple cameras, the equipment included in each of the images generated by each of the multiple cameras is identified, and the position of the equipment in each image (the area it occupies) is identified.

[0035] Next, an example of the processing flow of the processing device 10 will be described with reference to the flowchart of Fig. 5. When the acquisition unit 11 acquires an image of the management target (S10), the identification unit 12 identifies the equipment included in the image using layout information of the equipment in the management target (see Fig. 3) (S20).

[0036] An example of the processing flow of S20 will be described using the flowchart of Fig. 6. The identification unit 12 extracts markers from the image based on the feature amounts of each of a plurality of pre-registered markers (S21). The identification unit 12 also extracts objects from the image using any object detection technology (S22). Note that the processing order of S21 and S22 is not limited to that shown in the figure.

[0037] Thereafter, the identification unit 12 compares the relative positional relationship between the extracted objects and markers with the layout information, and identifies which of the facilities indicated in the layout information each of the extracted objects is (S23).

[0038] According to the processing device 10 of the present embodiment described above, equipment included in an image of the managed object is identified based on layout information of the equipment in the managed object. Furthermore, according to the processing device 10, the position (occupied area) of the equipment in the image of the managed object is identified. Furthermore, according to the processing device 10, the equipment included in each image generated by each of the multiple cameras is identified. Furthermore, according to the processing device 10, the position (occupied area) of the equipment in each image generated by each of the multiple cameras is identified. According to the processing device 10, there is no need for a person to view the images, identify the equipment included in each image, and input the details, thereby reducing the burden on the person.

[0039] <Second embodiment> 7 shows an example of a functional block diagram of the processing device 10 of this embodiment. As shown in the figure, the processing device 10 has an acquisition unit 11, an identification unit 12, and a storage unit 13.

[0040] The identification unit 12 links information identifying the camera, information identifying the equipment identified as being included in the image generated by each camera, and information indicating the position of the equipment within the image, and stores the results in the memory unit 13.

[0041] 8 schematically shows an example of information stored in the storage unit 13. In the example shown, camera identification information and facility information are linked. The facility information shown includes information identifying the facility included in the image generated by each camera and information indicating the position (area occupied) of each facility within the image. In the example shown, the position (area occupied) of each facility within the image is indicated by the coordinates of a point on the outline of each facility within the image, but is not limited to this.

[0042] The other configurations of the processing device 10 are the same as those in the first embodiment.

[0043] As described above, the processing device 10 of this embodiment achieves the same effects as those of the first embodiment. Furthermore, the processing device 10 of this embodiment can generate a database (see FIG. 8) that includes information identifying equipment included in images generated by each of multiple cameras installed in the managed area and information indicating the position (area occupied) of each piece of equipment in the image. By referring to this database, it is possible to easily identify the equipment included in images generated by each of multiple cameras installed in the managed area. Furthermore, it is possible to easily identify the position (area occupied) of each piece of equipment in images generated by each of the multiple cameras.

[0044] <Third embodiment> The processing device 10 of this embodiment executes various processes based on the database generated by the processing device 10 of the second embodiment. An example of a functional block diagram of the processing device 10 of this embodiment is shown in Fig. 9. As shown in the figure, the processing device 10 has an acquisition unit 11, an identification unit 12, a storage unit 13, and an output unit 15.

[0045] The output unit 15 outputs images generated by the multiple cameras to a display. For example, the output unit 15 can output the images generated by the multiple cameras to a display by switching between them one by one. When a facility is designated based on a user input, the output unit 15 can identify a camera that generates an image including the designated facility based on the database such as that shown in FIG. 8 generated by the identification unit 12, and output the images generated by the identified camera by switching between them one by one.

[0046] For example, assume that "Product Shelf 01" is specified based on user input, and "Camera C1," "Camera C2," and "Camera C4" are identified as cameras that generate images including the specified facility "Product Shelf 01" based on a database such as that shown in FIG. 8. In this case, the output unit 15 outputs only images generated by some of the multiple cameras, "Camera C1," "Camera C2," and "Camera C4," by switching between them in order to the display. For example, the output unit 15 may output images generated by "Camera C1," "Camera C2," and "Camera C4" by switching between them in order to the display based on user input.

[0047] There are various ways for the user to specify equipment. For example, the output unit 15 may output layout information of the equipment as shown in Fig. 3 to a display. Then, a single piece of equipment may be specified by selecting a display area of ​​the single piece of equipment on the layout information. Alternatively, the identification information of the equipment may be directly input or selected and input using any UI (user interface) component.

[0048] The other configurations of the processing device 10 are the same as those of the first and second embodiments.

[0049] As described above, the processing device 10 of this embodiment achieves the same effects as those of the first and second embodiments. Furthermore, the processing device 10 of this embodiment can provide information in a distinctive manner based on the information generated by the identification unit 12 (see FIG. 8).

[0050] Specifically, when receiving an input from a user specifying one facility to be viewed, the processing device 10 identifies a camera that generates an image including the specified facility based on the information generated by the identification unit 12, and can output images from the identified camera while switching between them in order. This display method allows the user to check the facility they want to check based on images generated by multiple cameras. Furthermore, because images that do not include the facility they want to check are not displayed, the user can perform the checking work efficiently and without waste.

[0051] <Fourth embodiment> The processing device 10 of this embodiment executes various processes based on the database generated by the processing device 10 of the second embodiment. An example of a functional block diagram of the processing device 10 of this embodiment is shown in FIG.

[0052] Based on the identification result (see FIG. 8) by the identification unit 12, the output unit 15 identifies equipment included in the layout information that is not included in any of the images generated by the cameras, and outputs the identification result. The output is realized via various output devices such as a display, a printer, a mailer, etc.

[0053] The other configurations of the processing device 10 are the same as those of the first to third embodiments.

[0054] As described above, the processing device 10 of this embodiment achieves the same effects as those of the first to third embodiments. Furthermore, the processing device 10 of this embodiment can identify equipment that is not included in any of the images generated by any of the cameras among the equipment included in the layout information based on the identification result by the identification unit 12 (see FIG. 8), and output the identification result. Based on the output result, the user can identify the equipment that is not included in the targets of monitoring based on the images generated by the cameras.

[0055] <Fifth embodiment> The processing device 10 of this embodiment detects specified events (missing items, presence of foreign objects, etc.) by monitoring based on images generated by a camera (surveillance camera, etc.) installed in the managed area, and identifies which equipment the event is occurring in based on the identification results by the identification unit 12.

[0056] 10 shows an example of a functional block diagram of the processing device 10 of this embodiment. As shown in the figure, the processing device 10 has an acquisition unit 11, an identification unit 12, a detection unit 14, and an output unit 15. Note that, as shown in FIG. 11, the processing device 10 may further have a storage unit 13.

[0057] The detection unit 14 detects a predetermined event based on the image of the managed object. For example, the detection unit 14 may detect at least one of the presence of a foreign object and a missing part. The detection unit 14 may also detect other events.

[0058] Although the method for detecting foreign objects using image analysis is not particularly limited, an example will be described below. For example, color information of equipment may be registered in advance. Then, when a color different from the color of each piece of equipment is present at the position (occupied area) of each piece of equipment in the image, the detection unit 14 may detect it as a foreign object. Furthermore, for each piece of equipment, the appearance features of objects that are not foreign objects, i.e., objects permitted to be present there (hereinafter referred to as "permitted objects"), may be registered in advance. Permitted objects include, for example, products displayed on a store shelf. Then, when the detection unit 14 detects an area where a color different from the color of each piece of equipment is present, the detection unit 14 may use the information to determine whether a permitted object is present in that area. Then, when it is determined that a permitted object is not present, the detection unit 14 may detect it as a foreign object. Based on the identification result by the identification unit 12, the detection unit 14 can recognize the equipment included in the image generated by each camera and the position (occupied area) of each piece of equipment in the image.

[0059] Alternatively, a lower limit value for the size of a piece of equipment to be detected as a foreign object may be specified in advance. Then, the detection unit 14 may detect an object that is equal to or larger than the lower limit value as a foreign object. There are various techniques for estimating the size of an object detected in an image. For example, the actual size (width, height, depth, etc.) of each piece of equipment may be registered in layout information such as that shown in FIG. 3. Then, the detection unit 14 may estimate the actual size of the foreign object by performing a calculation using a ratio based on the size in the image of the foreign object candidate detected in the image, the size of any piece of equipment in the image, and the actual dimensions of the equipment indicated in the layout information.

[0060] While there are no particular limitations on the method for detecting out-of-stock items using image analysis, an example will be described below. For example, color information of shelves on which products are displayed on a product shelf may be registered in advance. The detection unit 14 may then determine whether an item is out of stock based on the size of an area (exposed shelf area) in the position (occupied area) of each product shelf in the image where the same color as the product shelf exists. When there is no out-of-stock item, the product shelf portion is less exposed due to the presence of products, while when there is an out-of-stock item, the product shelf portion is more exposed. Therefore, the out-of-stock status can be determined based on the size of an area (exposed shelf area) in the image where the same color as the product shelf exists. For example, the detection unit 14 may determine that there is an out-of-stock item if the size of the area is equal to or larger than a certain standard, and may determine that there is no out-of-stock item if the size of the area is less than the certain standard.

[0061] When a predetermined event is detected at the location of equipment in the image, the output unit 15 outputs the detection result in association with information identifying the equipment. The output is realized via various output devices such as a display, a printer, a mailer, etc. For example, the information may be output to a display of a device installed in the store (such as a POS (point of sale) register or a device installed in the backroom). Alternatively, the contact information (such as an email address) of the store manager or owner may be registered in advance. The information may then be sent to that contact information.

[0062] The other configurations of the processing device 10 are the same as those of the first to fourth embodiments.

[0063] As described above, the processing device 10 of this embodiment achieves the same effects as those of the first to fourth embodiments. Furthermore, the processing device 10 of this embodiment can detect a predetermined event (missing items, presence of foreign matter, etc.) through monitoring based on images generated by a camera (monitoring camera, etc.) installed in the managed area, and can identify the equipment in which the event has occurred based on the identification result by the identification unit 12. Furthermore, the processing device 10 can identify the position of the equipment in the image based on the identification result by the identification unit 12, and use the result to detect various events.

[0064] Such a processing device 10 allows the user to understand in which facility a detected event is occurring. Furthermore, since the processing device 10 can perform processing to detect various events after identifying the facility included in the image and the position of the facility within the image, it is expected that the range of detection algorithms will be expanded (for example, use of color information of each product shelf, use of information indicating the products displayed on each product shelf, etc.), and detection accuracy will be improved.

[0065] Below, examples of reference forms are added. 1. An acquisition means for acquiring images to be managed; an identification means for identifying the equipment included in the image by using layout information of the equipment in the management target; A processing device having: 2. The processing device described in 1, wherein the identification means links information identifying the equipment identified as being included in the image with information indicating the position of the equipment within the image and stores the linked information in a storage means. 3. A detection means for detecting a predetermined event based on the image; an output means for outputting, when the predetermined event is detected at the position of the facility in the image, the detection result and information for identifying the facility in association with each other; 3. The processing device according to 1 or 2, comprising: 4. A processing device according to any one of 1 to 3, wherein the identification means identifies which area of ​​the management object is included in the image based on the identification result of the equipment included in the image. 5. The processing device described in 4, wherein the identification means links information identifying the camera that generated the image with information indicating a partial area of ​​the managed object contained in the image and stores the linked information in the storage means. 6. A detection means for detecting a predetermined event based on the image; an output means for outputting, when the predetermined event is detected, a detection result and information indicating a partial area of ​​the managed object included in the image in association with each other; 6. The processing device according to claim 4 or 5, 7. The acquisition means acquires the images generated by each of the plurality of cameras, 7. The processing device according to any one of 1 to 6, wherein the identification means identifies which of the facilities is included in the images generated by each of a plurality of cameras. 8. The processing device according to 7, wherein the identification means identifies which area of ​​the management target is included in the image generated by each of a plurality of cameras. 9. The computer Retrieve the images to be managed, A processing method for identifying the equipment included in the image using layout information of the equipment in the management target. 10. Computer acquisition means for acquiring images to be managed; an identification means for identifying the equipment included in the image by using layout information of the equipment in the management target; A program that functions as a

[0066] Although the present invention has been described above with reference to the embodiments (and examples), the present invention is not limited to the above-described embodiments (and examples). Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

[0067] This application claims priority based on Japanese Patent Application No. 2020-044091, filed on March 13, 2020, the disclosure of which is incorporated herein in its entirety. [Explanation of symbols]

[0068] 1A processor 2A Memory 3A input / output I / F 4A peripheral circuit 5A Bus 10 Processing equipment 11 Acquisition Department 12 Specific section 13 Storage section 14 Detector 15 Output section C1 to C9 cameras M1 to M18 markers

Claims

1. an acquisition means for acquiring images to be managed; an identification means for identifying the facilities included in the image using layout information indicating a relative positional relationship between a plurality of facilities installed in the management target area and a plurality of landmarks installed at positions distant from the facilities; A processing device having:

2. The processing device according to claim 1 , wherein the identification means links information identifying the equipment identified as being included in the image with information indicating the position of the equipment within the image and stores the linked information in a storage means.

3. a detection means for detecting a predetermined event based on the image; an output means for outputting, when the predetermined event is detected at the position of the facility in the image, the detection result and information for identifying the facility in association with each other; 3. The processing device according to claim 1, further comprising:

4. The processing device according to claim 1 , wherein the identifying unit identifies which area of ​​the management target is included in the image based on an identification result of the equipment included in the image.

5. The processing device according to claim 4 , wherein the specifying unit associates information for identifying a camera that generated the image with information indicating a partial area of ​​the managed object included in the image, and stores the associated information in a storage unit.

6. a detection means for detecting a predetermined event based on the image; an output means for outputting, when the predetermined event is detected, a detection result and information indicating a partial area of ​​the managed object included in the image in association with each other; 6. The processing device according to claim 4, further comprising:

7. the acquisition means acquires the images generated by each of the plurality of cameras; The processing device according to claim 1 , wherein the identifying unit identifies which of the facilities is included in the image generated by each of a plurality of cameras.

8. The processing device according to claim 7 , wherein the specifying unit specifies which area of ​​the management target is included in the image generated by each of a plurality of cameras.

9. The computer Retrieve the images to be managed, A processing method for identifying the equipment included in the image using layout information that indicates the relative positional relationship between multiple pieces of equipment installed in the managed area and multiple landmarks installed at locations distant from the equipment.

10. Computer, acquisition means for acquiring images to be managed; an identification means for identifying the facilities included in the image using layout information indicating a relative positional relationship between a plurality of facilities installed in the management target and a plurality of landmarks installed at positions distant from the facilities; A program that functions as a

Images