Processing device, processing method, and program

Abstract

The present invention provides a processing device including a lost item information acquisition unit that acquires lost item information indicating an area in which an owner of a lost item has lost the lost item and appearance characteristics of the lost item, a photographing point identifying unit that identifies a photographing point on a passageway connected to the area on the basis of map information, a finder identifying unit that detects a person bearing an object having the appearance characteristics from among images photographed at the identified photographing point, and an output unit that outputs information indicating the detected person.

Description

Processing device, processing method, and recording medium

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

[0002] A technique related to the present invention is disclosed in Patent Document 1.

[0003] Japanese Patent Application Laid-Open No. 2003-144992 discloses a technique for searching for lost items from within an image and identifying the finder who found the lost item.

[0004] This technology accepts input of image data of the person who lost the item, information indicating the time and location when the lost item was in their possession, and information about the lost item (size, color, shape, brand name, etc.). Based on this information, the technology searches for images that show the person who is holding the lost item. Next, the technology searches for images that show the lost item by performing an image search using the part of the searched image that shows the lost item as a key.

[0005] Furthermore, Patent Document 1 indicates that if it is confirmed that a person who lost an item had the item in their possession at a certain time and place, and that they did not have the item in their possession at a later time and place, it is possible that the item was lost between those two times and places.

[0006] Furthermore, Patent Document 1 discloses that if a person is included in the last image data of the lost item that can be found within the search range, that person is identified as the finder.

[0007] Japanese Patent Application Laid-Open No. 2019-16255

[0008] The method for identifying the finder of a lost item disclosed in Patent Document 1 does not have sufficient accuracy. For example, a person who happens to be passing by when the finder takes the lost item may be included in the last image data that can be found within the search range of the lost item. This may result in such a person being mistakenly identified as the finder.

[0009] In view of the above-mentioned problems, an example of an object of the present disclosure is to provide a processing device, a processing method, and a program that can accurately identify the finder of a lost item.

[0010] According to one aspect of the present disclosure, there is provided a processing device having: a lost item information acquisition means for acquiring lost item information indicating the area where the owner lost the item and the external characteristics of the lost item; a photographing location identification means for identifying a photographing location on a passageway leading to the area based on map information; a finder identification means for detecting a person holding an object having the external characteristics from an image photographed at the identified photographing location; and an output means for outputting information indicating the detected person.

[0011] According to one aspect of the present disclosure, a processing method is provided in which one or more computers acquire lost property information indicating the area where the owner lost the item and the external characteristics of the lost property, identify a photography location on a passageway leading to the area based on map information, detect a person holding an object with the external characteristics from an image taken at the identified photography location, and output information indicating the detected person.

[0012] According to one aspect of the present disclosure, a program is provided that causes a computer to function as: a lost item information acquisition means that acquires lost item information indicating the area where the owner lost the item and the external characteristics of the lost item; a photography location identification means that identifies a photography location on a passageway leading to the area based on map information; a finder identification means that detects a person holding an object with the external characteristics from an image taken at the identified photography location; and an output means that outputs information indicating the detected person.

[0013] According to one aspect of the present disclosure, a processing device, a processing method, and a program are realized that accurately identify the finder of a lost item.

[0014] The above and other objects, features and advantages will become more apparent from the following preferred embodiments and the accompanying drawings.

[0015] Fig. 1 is a diagram showing an example of a functional block diagram of a processing device; Fig. 2 is a diagram showing an example of a hardware configuration of a processing device; Fig. 3 is a diagram for explaining a process for identifying a lost area and a lost timing; Fig. 4 is a diagram for explaining a process for identifying a photography point on a passage leading to a lost area; Fig. 5 is another diagram for explaining a process for identifying a photography point on a passage leading to a lost area; Fig. 6 is a flowchart showing an example of a processing flow of a processing device;

[0016] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In all the drawings, like components are designated by like reference numerals, and the description thereof will be omitted as appropriate.

[0017] 1 is a functional block diagram showing an overview of a processing device 10 according to a first embodiment. The processing device 10 includes a lost item information acquisition unit 11, a photography location identification unit 12, a finder identification unit 13, and an output unit 14.

[0018] The lost item information acquiring unit 11 acquires lost item information, which indicates the area where the owner lost the item and the external appearance characteristics of the lost item.

[0019] The photographing point specifying unit 12 specifies, based on the map information, a photographing point on a passageway leading to the area where the owner has lost the item.

[0020] The finder specifying unit 13 detects, from images taken at the photography location specified by the photography location specifying unit 12, a person who is carrying an object having the appearance characteristics indicated in the lost item information.

[0021] The output unit 14 outputs information indicating the person detected by the finder identification unit 13 .

[0022] In this way, the processing device 10 identifies a photographing point on the passageway leading to the area where the owner left the lost item, and detects a person holding an object with the appearance characteristics indicated in the lost item information from images taken at the identified photographing point. With this processing device 10, it is possible to detect with high accuracy all finders who leave the area where the owner left the lost item with the lost item.

[0023] Second Embodiment Overview A processing apparatus 10 according to a second embodiment is a specific embodiment of the processing apparatus 10 according to the first embodiment. The configuration of the processing apparatus 10 will be described in detail below.

[0024] "Hardware Configuration" An example of the hardware configuration of the processing device 10 will be described. Each functional unit of the processing device 10 is realized by any combination of hardware and software. Those skilled in the art will understand that there are various variations in the realization method and device. Software includes programs that are pre-loaded in the device before shipping, and programs downloaded from recording media such as CDs (Compact Discs) or servers on the Internet.

[0025] FIG. 2 is a block diagram illustrating an example of the hardware configuration of a processing device 10. As shown in FIG. 2, the processing device 10 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. The processing device 10 does not necessarily have to have the peripheral circuit 4A. Note that the processing device 10 may be composed of multiple devices that are physically and / or logically separated. In this case, each of the multiple devices may have the above hardware configuration.

[0026] The bus 5A is a data transmission path for the processor 1A, memory 2A, peripheral circuit 4A, and input / output interface 3A to mutually transmit and receive data. The processor 1A is, for example, a processing unit such as a CPU or a graphics processing unit (GPU). The memory 2A is, for example, a random access memory (RAM) or a read-only memory (ROM). 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. The input / output interface 3A also includes an interface for connecting to a communication network such as the Internet. Examples of input devices include a keyboard, mouse, microphone, physical buttons, touch panel, 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.

[0027] "Functional Configuration" Next, the functional configuration of the processing device 10 of this embodiment will be described in detail. Fig. 1 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 of this embodiment has a lost item information acquisition unit 11, a photography location identification unit 12, a finder identification unit 13, and an output unit 14.

[0028] The lost item information acquisition unit 11 acquires lost item information.

[0029] The "lost information" indicates the area where the owner lost the item (hereinafter, sometimes referred to as the "lost area") and the external characteristics of the lost item. The lost information may also indicate the timing at which the owner lost the item (hereinafter, sometimes referred to as the "lost timing").

[0030] A "lost person" is a person who has lost a possession they had in their possession.

[0031] "Lost property" refers to belongings that have been lost by the owner. The concept of belongings includes not only items that are held by a person, such as a bag, umbrella, or magazine, but also items that are worn by a person, such as a hat, glasses, watch, or jacket.

[0032] The "lost area" is the area where the person lost the item. The lost area is designated to include the location where the person lost the item. There is no particular limit to the size of the lost area. However, it is preferable to designate a smaller area as the lost area, as this narrows down the shooting locations that are the subject of image analysis to detect the finder.

[0033] For example, a section within a facility may be designated as a lost area. Specifically, "Hall A," "first theater room," "conference room," "cafe," etc. within a facility may be designated as a lost area. Alternatively, a part of a corridor within a facility may be designated as a lost area. Specifically, "the corridor between the café and the flower shop," "the corridor between the shooting point of the first camera and the shooting point of the second camera," etc. may be designated as a lost area. The first and second cameras are surveillance cameras installed within the facility.

[0034] Alternatively, a certain facility may be designated as the lost area. Specifically, "XX station," "XX airport," "XX shopping mall," etc. may be designated as the lost area. Alternatively, a part of a road may be designated as the lost area. Specifically, "the passage between XX intersection and XX intersection," "the passage between the photographing point of the third camera and the photographing point of the fourth camera," etc. may be designated as the lost area. The third and fourth cameras are surveillance cameras installed on the road.

[0035] "Appearance characteristics of lost items" are information used to detect lost items in an image using image analysis. Information that can achieve this purpose is the appearance characteristics of lost items. For example, information indicating the type of lost item, such as a bag or hat, or the shape, color, pattern, size, brand name, etc. of the lost item are appearance characteristics of lost items. The concept of images includes both moving images and still images.

[0036] The appearance features of the lost item may be appearance features extracted from an image of the lost item. Alternatively, the appearance features of the lost item may be appearance features extracted from an image of the same product as the lost item. An "image of the same product as the lost item" is not an image of the lost item itself, but an image of another item that matches the lost item in terms of model number, product name, etc. Such images can be obtained, for example, by an internet search. Any technology can be used to extract the appearance features of the object depicted in the image. These images can be input by an operator into the processing device 10. The lost item information acquisition unit 11 may then analyze the image to extract the appearance features of the lost item.

[0037] Alternatively, the external characteristics of the lost item may be information received from the owner rather than information extracted from an image. The operator can then input the information received from the owner into the processing device 10. If the owner himself acts as the operator, he or she will input information he or she has stored into the processing device 10.

[0038] The "time of loss" is the time when the owner lost the item. The time of loss is specified as a time period with a certain range. The time of loss is specified so as to include the time when the owner lost the item. For example, the time of loss is specified as "April 20, 2023, 1:00 PM to 2:00 PM."

[0039] Next, a specific means by which the lost item information acquiring unit 11 acquires the lost item information as described above will be described.

[0040] Acquisition Example 1 As an example, the lost item information acquisition unit 11 can acquire lost item information input by an operator.

[0041] In this example, an operator inputs the lost item information described above into the processing device 10. That is, the operator inputs information indicating the area where the item was lost, the external characteristics of the lost item, and the time it was lost. The information indicating the external characteristics of the lost item may be an image of the lost item or an image of a product identical to the lost item, or may be text data expressing the external characteristics of the lost item. When an image of the lost item or an image of a product identical to the lost item is input, the lost item information acquisition unit 11 analyzes the image and extracts the external characteristics of the lost item.

[0042] The operator can input the lost item information via an input device such as a keyboard, mouse, microphone, physical buttons, or touch panel connected to the processing device 10. Alternatively, the processing device 10 may be a server. The operator can input the lost item information via a client terminal and transmit the input lost item information to the processing device 10 (server).

[0043] The operator may be the person who lost the item, or may be a worker of an organization that provides a lost item detection service using the processing device 10.

[0044] Acquisition Example 2 As another example, the lost item information acquisition unit 11 may analyze an image to generate information indicating at least part of the lost item information, specifically, at least one of the lost area and the lost time.

[0045] In this example, the operator inputs an image of the person who lost the item and information indicating the external characteristics of the lost item into the processing device 10. The information indicating the external characteristics of the lost item may be an image of the lost item or an image of a product identical to the lost item, or may be text data expressing the external characteristics of the lost item. When an image of the lost item or an image of a product identical to the lost item is input, the lost item information acquisition unit 11 analyzes the image and extracts the external characteristics of the lost item.

[0046] Based on this input information, the lost item information acquisition unit 11 searches for the lost person and the lost item from the images generated by the camera. The search for the lost person is realized based on the appearance characteristics of the lost person, specifically, the face, clothing, belongings, body shape, gait, etc. The search for the lost item is realized based on the appearance characteristics of the lost item. The search for the lost person and the lost item is realized using various technologies such as face recognition and object detection. The camera is a surveillance camera installed on the road or in the facility. The camera captures moving images.

[0047] While all images generated by all cameras may be searched, this increases the processing load on the computer. Therefore, the operator may input information indicating the approximate lost area into the processing device 10. The lost item information acquisition unit 11 may then search for the owner and lost item using images from cameras installed within or around this approximate lost area. In this case, the lost item information acquisition unit 11 may narrow down the lost area to a portion of the approximate lost area and generate lost item information indicating the narrowed lost area. Even if the owner does not know the exact location where the lost item was lost, they may be able to estimate the approximate location of the lost item.

[0048] Information indicating the installation location (photography location) of each of the multiple cameras is registered in advance in the processing device 10 or in a storage device accessible from the processing device 10. Based on this information, the lost item information acquisition unit 11 can identify cameras installed within or around the general lost area.

[0049] Similarly, the operator may input information indicating the approximate time (time period) when the item was lost into the processing device 10. The lost item information acquisition unit 11 may then use images taken within or around this approximate time period (time period) as the subject of processing to search for the person who lost the item and the lost item. In this case, the lost item information acquisition unit 11 can narrow down the time period within the approximate time period (time period) as the time period when the item was lost, and generate lost item information indicating the narrowed down time period. Even if the person who lost the item does not know the specific time period when the item was lost, they may be able to estimate the approximate time period when the item was lost.

[0050] Similarly, the operator may input information indicating the route traveled by the owner into the processing device 10. The lost item information acquisition unit 11 may then search for the owner and the lost item using images taken by cameras installed on or around the route. The owner may remember the route taken even if they do not know the exact location where they lost the item.

[0051] After searching for the owner and the lost item, the lost item information acquisition unit 11 identifies the following images based on the search results: "The last image of the owner holding the lost item (hereinafter referred to as the first image)" "The first image of the owner not holding the lost item after the first image (hereinafter referred to as the second image)"

[0052] The lost item information acquisition unit 11 can determine that the person who lost the item is in possession of the lost item if certain conditions are met, such as, for example, "the person is holding the lost item in their hand," "the person is wearing the lost item," or "the lost item is located within a certain distance from the person who lost the item."

[0053] After identifying the first image and the second image, the lost item information acquisition unit 11 identifies the lost area and the lost time based on the identification results.

[0054] Specifically, the lost item information acquisition unit 11 identifies the lost area based on the first photographing location where the first image was taken and the second photographing location where the second image was taken. For example, the lost item information acquisition unit 11 may identify the area between the first photographing location and the second photographing location as the lost area. As an example, the lost item information acquisition unit 11 may identify the route connecting the first photographing location and the second photographing location as the lost area.

[0055] The lost item information acquisition unit 11 also identifies the time of loss based on the first time point when the first image was captured and the second time point when the second image was captured. For example, the lost item information acquisition unit 11 can identify the time period between the first time point and the second time point as the time of loss.

[0056] An example will be explained using Figure 3. Figure 3 shows cameras A to C installed along a passageway. Also shown is a person carrying a bag (lost property) along the passageway. The person is photographed by camera A at 12:00, by camera B at 12:30, and by camera C at 1:00. The person is carrying the bag when photographed by camera A and camera B, but is not carrying the bag when photographed by camera C.

[0057] In this example, the lost item information acquisition unit 11 identifies the area between the shooting locations of camera B and camera C as the lost area. The lost item information acquisition unit 11 then identifies the time between 12:30 and 13:00 as the time of loss.

[0058] Returning to FIG. 1, the photography location specifying unit 12 specifies a photography location on a passageway leading to the lost area indicated by the lost item information, based on the map information.

[0059] "Map information" is information that indicates the contents of a map. The concept of a map includes floor maps that show the locations, sizes, shapes, etc. of passages and sections within a facility, and road maps that show the locations, sizes, shapes, etc. of roads and facilities.

[0060] Map information is registered in advance in the processing device 10 or in a storage device accessible from the processing device 10. Information indicating the installation positions (photography locations) of each of the multiple cameras is also registered in advance in the processing device 10 or in a storage device accessible from the processing device 10. Based on this information, the photography location identification unit 12 identifies the photography location on the passageway leading to the lost property area.

[0061] A "pathway leading to a lost area" is a path that has one end connected to the lost area. A "pathway leading to a lost area" can also be expressed as a path that extends from the lost area as a base point. There may be one path or multiple paths leading to such a lost area. The photography location identification unit 12 identifies all such "pathways leading to a lost area" based on map information.

[0062] Then, the photography location identifying unit 12 identifies photography locations on the identified "passageway leading to the lost item area" based on information indicating the installation positions (photography locations) of each of the multiple cameras. For example, the photography location identifying unit 12 may identify a predetermined number (e.g., 1, 2, etc.) of photography locations on the "passageway leading to the lost item area" that are closest to the lost item area. Note that if there are multiple "passageways leading to the lost item area," the photography location identifying unit 12 may identify, for each passage, a predetermined number (e.g., 1, 2, etc.) of photography locations on each passageway that are closest to the lost item area.

[0063] A specific example will be described with reference to Fig. 4. Fig. 4 shows three cameras C and the shooting points C of each camera C. １ ~C ３ And, the shooting point C １ and C ２ The straight passages between are designated as lost areas. In this case, the "passages leading to the lost area" are the passage extending from the lost area to the left in the figure, the passage extending from the lost area to the right in the figure, and the passage extending from the lost area to the top in the figure. The photography point identification unit 12 identifies these three passages as "passages leading to the lost area" and identifies the photography points on each of the three passages.

[0064] Here, the photographing point specifying unit 12 specifies, for each passage, one photographing point (the photographing point closest to the lost-item area) from among the photographing points on each passage that is closest to the lost-item area.

[0065] In this case, the photographing point specifying unit 12 identifies the photographing point C closest to the lost-item area in the "pathway leading to the lost-item area" extending from the lost-item area to the left in the figure. １ In addition, the photography point specifying unit 12 specifies the photography point C closest to the lost-item area in the "pathway leading to the lost-item area" extending from the lost-item area to the right in the figure. ２ In addition, the photography point specifying unit 12 specifies the photography point C closest to the lost-item area in the "pathway leading to the lost-item area" extending from the lost-item area in the upward direction in the figure. ３ Identify.

[0066] Another specific example will be described with reference to Fig. 5. Fig. 5 shows four cameras C and the shooting points C of each camera C. １ ~C ４ is shown. Section F is designated as the lost area. In this case, the "paths leading to the lost area" are four: a path extending from the lost area to the left in the figure, a path extending from the lost area downward in the figure, a path extending from the lost area to the right in the figure, and a path extending from the lost area upward in the figure. The photography point identification unit 12 identifies these four paths as "paths leading to the lost area" and identifies the photography point on each of the four paths.

[0067] Here too, the photography point specifying unit 12 specifies, for each passage, one photography point (the photography point closest to the lost area) from among the photography points on each passage that is closest to the lost area.

[0068] In this case, the photographing point specifying unit 12 identifies the photographing point C closest to the lost-item area in the "pathway leading to the lost-item area" extending from the lost-item area to the left in the figure. １ In addition, the photography point specifying unit 12 specifies the photography point C closest to the lost-item area in the "pathway leading to the lost-item area" extending downward from the lost-item area in the figure. ２ In addition, the photography point specifying unit 12 specifies the photography point C closest to the lost-item area in the "pathway leading to the lost-item area" extending from the lost-item area to the right in the figure. ３ In addition, the photography point specifying unit 12 specifies the photography point C closest to the lost-item area in the "pathway leading to the lost-item area" extending from the lost-item area in the upward direction in the figure. ４ Identify.

[0069] Returning to Figure 1, the finder identification unit 13 detects a person who is holding an object having the external characteristics of the lost item indicated in the lost information from among the images taken at the photography location identified by the photography location identification unit 12. The finder identification unit 13 can, for example, target images taken after the time the item was lost (including images taken at the time the item was lost) from among the images taken at each photography location for this detection process. For example, the finder identification unit 13 can target images taken after the time the item was lost up to the present time (including images taken at the time the item was lost) for this detection process.

[0070] The finder identification unit 13 can detect, for example, a person who satisfies any of the following conditions as "a person who possesses an object having the external characteristics of the lost item indicated in the lost item information."

[0071] - Holding an object in your hand that has the external characteristics of the lost item indicated in the lost information. - Wearing an object that has the external characteristics of the lost item indicated in the lost information. - Being within a predetermined distance from an object that has the external characteristics of the lost item indicated in the lost information for a predetermined period of time or more.

[0072] The output unit 14 outputs information indicating the person detected by the finder identification unit 13. The output unit 14 can output any of the following information:

[0073] - An image of a person detected by the finder identification unit 13. - An image including a person detected by the finder identification unit 13 and an object that the person is carrying that has the external characteristics of the lost item indicated in the lost item information. - A photographing location where a person was detected (photographed) carrying an object that has the external characteristics of the lost item indicated in the lost item information. - A photographing date and time where a person was detected (photographed) carrying an object that has the external characteristics of the lost item indicated in the lost item information.

[0074] Furthermore, if no person is detected by the finder identification unit 13, the output unit 14 may output "information indicating that a lost item may have been left in the lost item area."

[0075] The output unit 14 can output the information via an output device such as a display, a projector, a printer, or a speaker connected to the processing device 10. Alternatively, the processing device 10 may be a server. The output unit 14 may then transmit the information to a client terminal.

[0076] Next, an example of the processing flow of the processing device 10 will be described with reference to the flowchart of FIG.

[0077] First, the processing device 10 acquires lost property information indicating the area where the owner left the lost property and the appearance characteristics of the lost property (S10). Next, the processing device 10 identifies a photographing location on a passageway leading to the lost property based on map information (S11). Next, the processing device 10 detects a person holding an object with the appearance characteristics indicated in the lost property information acquired in S10 from images taken at the photographing location identified in S11 (S12). Then, the processing device 10 outputs information indicating the person detected in S12 (S13).

[0078] The processing device 10 of the second embodiment identifies a photographing point on a passageway leading to the lost area where the owner left the lost item, and detects a person holding an object having the appearance characteristics indicated in the lost item information from images taken at the identified photographing point. This processing device 10 can accurately detect all finders who leave the area where the owner left the lost item with the lost item.

[0079] Furthermore, the processing device 10 of the second embodiment can identify the area and time of loss by, for example, image analysis, which is preferable because it reduces the input work of the operator.

[0080] <Third Embodiment> The processing device 10 of the third embodiment includes a means for identifying potential finders from among the people detected using the method described in the second embodiment. If the lost item is a mass-produced product, there is a possibility that another person possesses the same product (a different item from the lost item). According to the method described in the second embodiment, such a person can also be detected as "a person possessing an object that has the appearance characteristics of the lost item indicated in the lost item information." Therefore, the processing device 10 of the third embodiment includes a means for narrowing down the potential finders from among the people detected using the method described in the second embodiment. This will be described in detail below.

[0081] The finder identification unit 13 uses the method described in the second embodiment to detect, from images taken at the photography location identified by the photography location identification unit 12, people who are holding an object that has the external characteristics of the lost item indicated in the lost item information.The finder identification unit 13 then identifies, from the detected people, candidates for the finder who found the lost item.From the detected people, the finder identification unit 13 identifies people who meet any of the following conditions as "candidates for the finder who found the lost item."

[0082] - When entering the lost area, the user does not have in their possession an object with the external characteristics of the lost item indicated in the lost information, and when leaving the lost area, the user has in their possession an object with the external characteristics of the lost item indicated in the lost information. - When leaving the lost area after the timing of loss, and when leaving the lost area, the user has in their possession an object with the external characteristics of the lost item indicated in the lost information. - When leaving the lost area after the timing of loss, the user does not have in their possession an object with the external characteristics of the lost item indicated in the lost information when entering the lost area, and when leaving the lost area, the user has in their possession an object with the external characteristics of the lost item indicated in the lost information.

[0083] The actions of a person such as "entering the lost area" and "leaving the lost area" can be identified based on the direction of movement of each person in the image taken at the shooting location identified by the shooting location identification unit 12.

[0084] As explained in the second embodiment, the "time of loss" is specified as a time period with a certain width. The above "after the time of loss" means after a predetermined point in the time period of loss. The predetermined point may be the beginning of the time period of loss, the end of the time period of loss, a point between the beginning and end of the time period of loss, or some other point.

[0085] In this way, the finder specifying unit 13 can exclude from candidates for finders of the lost item a person who is in possession of an object having the external characteristics of the lost item indicated in the lost information when leaving the lost area, but who is also in possession of the object when entering the lost area.

[0086] The output unit 14 outputs information indicating the finder candidates identified by the finder identifying unit 13. The output unit 14 can output any of the following information:

[0087] - An image of a candidate for the finder of the lost item. - An image including a candidate for the recipient of the lost item and an object possessed by the candidate that has the external characteristics of the lost item indicated in the lost item information. - A photographing location where a candidate for the finder of the lost item who is in possession of an object having the external characteristics of the lost item indicated in the lost item information was detected (photographed). - A photographing date and time where a candidate for the finder of the lost item who is in possession of an object having the external characteristics of the lost item indicated in the lost item information was detected (photographed).

[0088] Furthermore, the output unit 14 may output "information indicating that the lost item may have been left in the lost item area" if no candidate finder is identified by the finder identification unit 13. "No candidate finder is identified" means that no candidate finder is identified.

[0089] Other configurations of the processing apparatus 10 of the third embodiment are similar to those of the processing apparatus 10 of the first and second embodiments.

[0090] The processing device 10 of the third embodiment achieves the same effects as the processing devices 10 of the first and second embodiments. Furthermore, the processing device 10 of the third embodiment can identify and output candidates for the finder of a lost item with high accuracy.

[0091] <Modifications> "Modification 1" The finder identification unit 13 may track the detected person or the identified candidate finder within the image as a person to be tracked. The output unit 14 may further output the movement trajectory of the person to be tracked.

[0092] The finder identification unit 13 may also use image analysis to identify the area and timing at which the person being tracked lost an object having the appearance characteristics of the lost item indicated in the lost information. The output unit 14 may then output information indicating the area and timing at which the person being tracked lost an object having the appearance characteristics of the lost item indicated in the lost information. Identification of the area and timing at which the person being tracked lost an object having the appearance characteristics of the lost item indicated in the lost information is achieved in the same manner as the "process of identifying the area and timing at which the object was lost by the person being tracked using image analysis" described in the second embodiment.

[0093] "Variation 2" In the above embodiment, the finder is searched for in response to an action from the owner of the item (such as inputting lost item information or notifying an operator of the lost item information). As a variation, the processing device 10 may search for the finder without any action from the owner of the item. In this case, the lost item information acquisition unit 11 detects a person in the image. The person detection can be achieved using any person detection technology. The lost item information acquisition unit 11 then tracks the person detected in the image and detects changes in the person's belongings, more specifically, the loss of the belongings.

[0094] Loss of belongings is detected by comparing two images taken at different times. If an image taken at a certain time shows a person carrying a certain item, but an image taken at a later time does not show the person carrying the item, the lost item information acquisition unit 11 determines that the person has lost the item. The lost item information acquisition unit 11 may also determine that the person has lost the item if the person continues to be without the item for a predetermined period of time or more. Furthermore, if a person is moving, the person will be continuously photographed by multiple cameras. The lost item information acquisition unit 11 may also determine that the person has lost the item if the person continues to be without the item in images continuously photographed by a predetermined number of cameras or more. The predetermined number is an integer greater than or equal to 2.

[0095] After detecting the loss of a person's belongings, the lost item information acquisition unit 11 identifies the area where the item was lost, the time of loss, etc., using the same process as in Acquisition Example 2 described in the second embodiment. The lost item information acquisition unit 11 also extracts the appearance characteristics of the lost item from an image of the lost item (an image taken before the item was lost). The other configurations of the processing device 10 are the same as those of the above embodiment.

[0096] Note that contact information for each of a plurality of people may be registered in advance in the processing device 10. Then, the output unit 14 may notify the owner of information indicating the detected person and information indicating potential finders. Notification to the owner may be made by email, using an application, or the like, but is not limited to these. For example, contact information for each of a plurality of people may be registered in the processing device 10, linked to each person's facial information. The processing device 10 can identify the owner of the item through facial recognition processing using the facial information.

[0097] Although the embodiments of the present invention have been described above with reference to the drawings, these are merely examples of the present invention, and various other configurations may be adopted. The configurations of the above-described embodiments may be combined with each other, or some of the configurations may be replaced with other configurations. Furthermore, various modifications may be made to the configurations of the above-described embodiments without departing from the spirit of the invention. Furthermore, the configurations and processes disclosed in the above-described embodiments and modified examples may be combined with each other.

[0098] In addition, in the flowcharts used in the above explanation, multiple steps (processes) are described in order. However, the order of execution of the steps performed in each embodiment is not limited to the order described. In each embodiment, the order of the steps shown in the figures can be changed to the extent that the content is not affected. Furthermore, each of the above-mentioned embodiments can be combined to the extent that the content is not contradictory.

[0099] Some or all of the above embodiments may be described as, but are not limited to, the following supplementary notes: 1. A processing device comprising: lost item information acquisition means for acquiring lost item information indicating an area where a person lost an item and the external characteristics of the lost item; photography location identification means for identifying a photography location on a passageway leading to the area based on map information; finder identification means for detecting a person holding an object with the external characteristics from an image taken at the identified photography location; and output means for outputting information indicating the detected person. 2. The processing device according to 1, wherein the finder identification means identifies a candidate finder who found the lost item from the detected people, and the output means outputs information indicating the candidate finder. 3. The processing device according to 2, wherein the finder identification means identifies a person holding an object with the external characteristics as a candidate finder when leaving the area. 4. The processing device according to any one of claims 2 to 5, wherein the lost information further indicates a time when the person who lost the item lost it, and the finder identification means identifies as the candidate finder a person who left the area after the time when the item was lost and who was carrying an object with the external appearance characteristic when they left the area. 5. The processing device according to any one of claims 2 to 5, wherein the finder identification means identifies as the candidate finder a person who was not carrying an object with the external appearance characteristic when they entered the area and who was carrying an object with the external appearance characteristic when they left the area. 6. The processing device according to any one of claims 2 to 5, wherein the output means outputs information indicating that the lost item may have been left in the area if no candidate finder is identified. 7. The processing device according to any one of claims 2 to 6, wherein the output means outputs an image including the candidate finder and an object with the external appearance characteristic that is carried by the candidate finder. 8. The processing device according to any one of claims 2 to 7, wherein the output means outputs information indicating the photographing location where the candidate finder carrying the object with the external appearance characteristic was detected.9. A processing method in which one or more computers acquire lost information indicating an area where a person lost an item and the external characteristics of the lost item, identify a photography location on a passageway leading to the area based on map information, detect a person holding an object with the external characteristics from an image taken at the identified photography location, and output information indicating the detected person. 10. The processing method described in 9, in which the computer identifies a candidate finder who may have found the lost item from the detected people, and outputs information indicating the candidate finder. 11. The processing method described in 10, in which the computer identifies a person who is holding an object with the external characteristics when leaving the area as a candidate finder. 12. The lost information further indicates the time when the person lost the item, and the computer identifies a person who left the area after the time when the item was lost and who is holding an object with the external characteristics when leaving the area as a candidate finder. 13. The processing method described in 11, wherein the computer identifies as the candidate finder a person who is not carrying an object having the appearance characteristic when entering the area and who is carrying the object having the appearance characteristic when leaving the area. 14. The processing method described in any of 10 to 13, wherein the computer outputs information indicating that the lost item may have been left in the area if the candidate finder is not identified. 15. The processing method described in any of 10 to 14, wherein the computer outputs an image including the candidate finder and the object having the appearance characteristic that is being carried by the candidate finder. 16. The processing method described in any of 10 to 15, wherein the computer outputs information indicating the photographing location where the candidate finder carrying the object having the appearance characteristic was detected.17. A program that causes a computer to function as: lost item information acquisition means that acquires lost item information indicating the area where a person lost an item and the external characteristics of the lost item; photography location identification means that identifies a photography location on a passageway leading to the area based on map information; finder identification means that detects a person holding an object with the external characteristics from images taken at the identified photography location; and output means that outputs information indicating the detected person. 18. The program according to 17, wherein the finder identification means identifies from the detected people a candidate finder who found the lost item, and the output means outputs information indicating the candidate finder. 19. The program according to 18, wherein the finder identification means identifies a person holding an object with the external characteristics as a candidate finder when leaving the area. 20. 21. The program according to any one of 18 to 21, wherein the output means outputs information indicating that the lost item may have been left in the area if no candidate finder is identified. 22. The program according to any one of 18 to 21, wherein the output means outputs an image including the candidate finder and an object with the external characteristic that is being carried by the candidate finder. 23. The program according to any one of 18 to 22, wherein the output means outputs an image including the candidate finder and an object with the external characteristic that is being carried by the candidate finder. 24. 24. The program according to any one of 18 to 23, wherein the output means outputs information indicating the photographing location where the finder candidate who is carrying the object having the appearance characteristic was detected.

[0100] This application claims priority based on Japanese Patent Application No. 2023-082738, filed May 19, 2023, the disclosure of which is incorporated herein in its entirety.

[0101] 10 Processing device 11 Lost item information acquisition unit 12 Photographing location identification unit 13 Finder identification unit 14 Output unit 1A Processor 2A Memory 3A Input / output I / F 4A Peripheral circuit 5A Bus

Claims

1. a lost item information acquiring means for acquiring lost item information indicating the area where the person lost the item and the external characteristics of the lost item; a photographing location specifying means for specifying a photographing location on a passageway connected to the area based on map information; a finder identification means for detecting a person who is carrying an object having the appearance characteristics from among images taken at the identified photographing location; an output means for outputting information indicating the detected person; A processing device having:

2. the finder identification means identifies a candidate finder who found the lost item from among the detected people, 2. The processing device according to claim 1, wherein said output means outputs information indicating the candidate finders.

3. The finder identification means The processing device according to claim 2 , wherein a person who is carrying an object having the appearance characteristics when leaving the area is identified as a candidate for the finder.

4. The loss information further indicates the time when the person lost the item, and The finder identification means 4. The processing device according to claim 3, wherein a person who leaves the area after the time of loss and who is carrying an object having the appearance characteristic when leaving the area is identified as a candidate for the finder.

5. The finder identification means 4. The processing device according to claim 3, wherein a person who is not carrying an object having said appearance characteristics when entering said area and is carrying an object having said appearance characteristics when leaving said area is identified as a candidate for the finder.

6. The output means 6. The processing device according to claim 2, wherein if no candidate finder is identified, the processing device outputs information indicating that the lost item may have been left in the area.

7. The output means The processing device according to claim 2 , wherein an image including the candidate finder and an object having the appearance feature and held by the candidate finder is output.

8. The output means 6. The processing device according to claim 2, wherein information indicating the photographing location where the finder candidate who possesses the object having the appearance characteristic was detected is output.

9. One or more computers Acquire information about the area where the person lost the item and the external appearance of the item; Based on the map information, a photography point on a passageway leading to the area is identified; Detecting a person holding an object having the appearance characteristic from among images taken at the specified photographing location; A processing method for outputting information indicating the detected person.

10. Computer, a lost item information acquiring means for acquiring lost item information indicating the area where the person lost the item and the external appearance characteristics of the lost item; a photographing location specifying means for specifying a photographing location on a passageway connected to the area based on map information; a finder identification means for detecting a person who is carrying an object having the appearance characteristics from among images taken at the identified photographing location; an output means for outputting information indicating the detected person; A program that functions as a