Image processing device, image processing method, and recording medium

Abstract

An image processing device according to the present disclosure comprises: an acquisition unit that acquires an image which was captured by an imaging device mounted on at least one mobile body and imaging timing information which indicates the timing of imaging of the image; an image analysis unit that analyzes the image and extracts feature information of an object which appears in the image; an input reception unit that acquires feature information of an object to be detected; an identification unit that identifies an image in which the feature information of the object to be detected is extracted; and an output unit that associates and outputs one or more identified images which were captured at the same timing.

Description

Image processing device, image processing method, and recording medium

[0001] The present disclosure relates to an image processing device, an image processing method, and a program.

[0002] A technology related to the present disclosure is disclosed in Patent Document 1. The technology disclosed in Patent Document 1 acquires images taken by each of multiple vehicles, identifies the license plates of the vehicles appearing in the images, and stores the results. The technology then provides the user with an image showing the license plate number of a vehicle specified by the user. The technology collectively presents identification information for multiple images showing the license plate number of a vehicle specified by the user, and displays the specified image from among them.

[0003] JP 2015-014959 A

[0004] In the case of the display method disclosed in the above-mentioned Patent Document 1, if there are a large number of images showing the license plate number of the vehicle specified by the user, it is difficult to find the desired image from among them.

[0005] One example of the objective of the present disclosure is to provide an image processing device, an image processing method, and a program that, in consideration of the above-mentioned problems, make it easier to find a desired image in a technology for identifying and outputting an image containing a detection target.

[0006] According to the present disclosure, there is provided an image processing device having: an acquisition means for acquiring images captured by an imaging device mounted on at least one moving body and imaging timing information indicating the timing at which the images were captured; an image analysis means for analyzing the images and extracting characteristic information of an object appearing in the images; an input acceptance means for acquiring characteristic information of a detected object; an identification means for identifying the image from which the characteristic information of the detected object has been extracted; and an output means for outputting the identified image in association with at least one image captured at the same timing.

[0007] Furthermore, according to the present disclosure, there is provided an image processing method in which one or more computers acquire images captured by an imaging device mounted on at least one moving body and imaging timing information indicating the timing at which the images were captured, analyze the images to extract feature information of objects appearing in the images, acquire feature information of the detected object, identify the images from which the feature information of the detected object has been extracted, and output the identified images in association with at least one image captured at the same timing.

[0008] Furthermore, according to the present disclosure, there is provided a program that causes a computer to function as: an acquisition means that acquires images captured by an imaging device mounted on at least one moving body and imaging timing information indicating the timing at which the images were captured; an image analysis means that analyzes the images and extracts characteristic information of objects appearing in the images; an input acceptance means that acquires characteristic information of the detected object; an identification means that identifies the image from which the characteristic information of the detected object has been extracted; and an output means that outputs the identified image in association with at least one image captured at the same timing.

[0009] According to one aspect of the present disclosure, an image processing device, an image processing method, and a program are realized that make it easier to find a desired image in a technology for identifying and outputting an image that includes a detection target object.

[0010] FIG. 1 is a diagram showing an example of a functional block diagram of an image processing device according to the present disclosure. FIG. 2 is a flowchart showing an example of a processing flow of an image processing device according to the present disclosure. FIG. 3 is a flowchart showing another example of a processing flow of an image processing device according to the present disclosure. FIG. 4 is a diagram showing an example of a functional block diagram of a system including an image processing device according to the present disclosure. FIG. 5 is a diagram showing an example of a hardware configuration of an image processing device according to the present disclosure. FIG. 6 is a diagram showing a schematic diagram of an example of information processed by an image processing device according to the present disclosure. FIG. 7 is a diagram showing another example of a screen output by an image processing device according to the present disclosure. FIG. 8 is a diagram showing another example of a screen output by an image processing device according to the present disclosure. FIG. 9 is a diagram showing another example of a screen output by an image processing device according to the present disclosure.

[0011] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In this disclosure, the drawings relate to one or more embodiments. In all drawings, similar components are designated by similar reference numerals, and descriptions thereof will be omitted as appropriate.

[0012] First Embodiment Fig. 1 is a functional block diagram showing an overview of an image processing apparatus 10. Fig. 2 and Fig. 3 are flowcharts showing an example of the flow of processing executed by the image processing apparatus 10.

[0013] As shown in FIG. 1 , the image processing device 10 includes an acquisition unit 11 , an image analysis unit 12 , an input reception unit 13 , an identification unit 14 , and an output unit 15 .

[0014] The processing of the flowchart in Fig. 2 is executed by the acquisition unit 11 and the image analysis unit 12. The flowchart in Fig. 2 shows the processing of accumulating data.

[0015] In S10, the acquisition unit 11 acquires images captured by an imaging device mounted on at least one (e.g., multiple) moving objects, and imaging timing information indicating the timing at which the images were captured. In S11, the image analysis unit 12 analyzes the images and extracts feature information of objects appearing in the images. In S12, the image analysis unit 12 stores the extraction results in a storage device. That is, the image analysis unit 12 associates the feature information of the objects extracted from each image with each image and stores it in the storage device.

[0016] The processing of the flowchart in Fig. 3 is executed by the input receiving unit 13, the specifying unit 14, and the output unit 15. The flowchart in Fig. 3 shows processing for providing data to a user.

[0017] In S20, the input receiving unit 13 acquires feature information of the detection target object. In S21, the identifying unit 14 refers to the extraction results stored in the storage device and identifies an image from which the feature information of the detection target object has been extracted. In S22, the output unit 15 outputs the image identified in S21. Specifically, the output unit 15 associates and outputs at least one (e.g., multiple) images identified in S21 that were taken at the same time.

[0018] In this way, the image processing device 10 has the feature of "outputting an image from which feature information of a detection object has been extracted, in association with at least one image captured at the same time." With this image processing device 10, even if there are many images from which feature information of a detection object has been extracted, the user can classify and understand the many images based on the capture timing. As a result, the user can easily find a desired image from among the images from which feature information of a detection object has been extracted.

[0019] Second Embodiment "Overview" The image processing device 10 of the second embodiment is a specific implementation of the configuration of the image processing device 10 of the first embodiment. An overview of the processing executed by the image processing device 10 will be shown using FIG. 4. Note that the configuration shown in FIG. 4 is merely an example and is not limiting. Modifications of the configuration shown in FIG. 4 will become clear from the detailed description in the "Functional Configuration" section below.

[0020] As shown in the figure, a plurality of moving objects 30 are each equipped with an image capturing device 20. An image processing device 10 acquires images captured by the image capturing device 20 via a communication network 50 such as the Internet. The image processing device 10 then analyzes the acquired images and extracts feature information of objects captured in the images. The image processing device 10 then stores the extraction results in a storage device.

[0021] The image processing device 10 also acquires feature information of the detection object from the user terminal 40. The image processing device 10 refers to the extraction results stored in the storage device and identifies an image from which the feature information of the detection object has been extracted. The image processing device 10 then associates the image from which the feature information of the detection object has been extracted with at least one image taken at the same time, and outputs the image to the user terminal 40. The user terminal 40 displays the image from which the feature information of the detection object has been extracted with at least one image taken at the same time, on a display, in association with the image.

[0022] The configuration of the image processing device 10 that executes such processing will be described in detail below.

[0023] "Hardware Configuration" First, an example of the hardware configuration of the image processing device 10 will be described. Each functional unit of the image 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.

[0024] FIG. 5 is a block diagram illustrating an example of the hardware configuration of an image processing device 10. As shown in FIG. 5, the image 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 image processing device 10 does not necessarily have to have the peripheral circuit 4A. Note that the image processing device 10 may be composed of multiple devices that are physically and / or logically separated. In this case, each of the multiple devices can have the above hardware configuration.

[0025] 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.

[0026] "Functional Configuration" Next, the functional configuration of the image processing device 10 will be described in detail. Fig. 1 shows an example of a functional block diagram of the image processing device 10. As shown in the figure, the image processing device 10 has an acquisition unit 11, an image analysis unit 12, an input acceptance unit 13, an identification unit 14, and an output unit 15.

[0027] As described in the first embodiment, the acquisition unit 11 and image analysis unit 12 execute the processing of the flowchart in Fig. 2. The flowchart in Fig. 2 shows the processing of accumulating data. The input reception unit 13, the identification unit 14, and the output unit 15 execute the processing of the flowchart in Fig. 3. The flowchart in Fig. 3 shows the processing of providing data to a user. Each functional unit will be described in detail below, divided into "processing of accumulating data" and "processing of providing data to a user."

[0028] "Data Accumulation Process" The acquisition unit 11 acquires images captured by the image capturing device 20 mounted on at least one moving object 30, and image capturing timing information indicating the timing at which the images were captured.

[0029] The "mobile body 30" may be an object that moves on land, an object that moves on water, or an object that moves in the air. Examples of objects that move on land include, but are not limited to, four-wheeled automobiles, two-wheeled automobiles, bicycles, large automobiles such as buses and trucks, and trains that move on rails. Examples of objects that move on water include, but are not limited to, ships, boats, and yachts. Examples of objects that move in the air include, but are not limited to, airplanes, helicopters, unmanned flying objects, and the like.

[0030] The "image capturing device 20" is a so-called camera. Preferably, the image capturing device 20 is a camera that detects visible light to generate an image, but it may also be a camera that detects other types of light to generate an image. The image capturing device 20 can capture images, for example, while the moving object 30 is moving. The image capturing device 20 may generate moving images or may generate still images at predetermined timings. The image capturing device 20 has a date and time measurement function. The image capturing device 20 uses this date and time measurement function to generate image capturing timing information that indicates the capture timing (date and time) of each image. The image capturing timing information is information that can identify the timing (date and time) when each of the multiple frame images included in the moving image was generated. Furthermore, the image capturing timing information is information that can identify the timing (date and time) when a still image was generated. The date and time measurement function and the image capturing timing information can be realized using any widely known technology.

[0031] The term "image" is a concept that includes at least one of a moving image and a still image.

[0032] In addition to the images captured by the imaging device 20 mounted on the moving body 30, the acquisition unit 11 may also acquire images captured by an imaging device 20 not mounted on the moving body 30.

[0033] The image capturing device 20 not mounted on the moving body 30 is, for example, a surveillance camera installed on the road. Other examples of the image capturing device 20 not mounted on the moving body 30 are cameras carried by people and mobile terminals with camera functions. Examples of mobile terminals with camera functions include, but are not limited to, smartphones, mobile phones, tablet terminals, personal computers, game consoles, and smart watches. The acquisition unit 11 may further acquire, for example, images captured by such image capturing devices 20 and image capturing timing information.

[0034] The acquisition unit 11 can acquire data including images generated by the image capture device 20 and image capture timing information by various means.

[0035] For example, the photographing device 20 and the image processing device 10 may be communicably connected to each other via a communication network 50. The photographing device 20 may transmit the data to the image processing device 10 in real time. Alternatively, the photographing device 20 may store the data internally and transmit the data collectively to the image processing device 10 at a predetermined timing.

[0036] The predetermined timing may include any one of the following. Note that the predetermined timings exemplified here are merely examples and are not limited to these. - The timing when there is a user input to turn off the power of the mobile body 30 - The timing when there is a user input to turn off the engine of the mobile body 30 - The timing when another predetermined operation is performed on the mobile body 30 - The timing when the mobile body 30 stops - The timing when there is a user input to turn off the power of the image capture device 20 - The timing when another predetermined operation is performed on the image capture device 20 - A predetermined time in one day - The timing when a predetermined time has elapsed since the previous transmission timing - The timing when there is a transmission instruction input from the user

[0037] Alternatively, the photographing device 20 may transmit to the image processing device 10 only images that satisfy a predetermined transmission condition.

[0038] For example, when a predetermined event occurs, the image capturing device 20 may transmit images captured for a predetermined time before and after the event to the image processing device 10. The predetermined event may be, but is not limited to, a collision with the moving object 30. The occurrence of the event can be detected by various sensors mounted on the moving object 30 or the image capturing device 20.

[0039] As another example, the photographing device 20 may transmit only images with predetermined content to the image processing device 10. For example, the photographing device 20 may analyze the images and transmit only images in which other moving objects 30 appear to the image processing device 10.

[0040] In this example, the data is stored in the image capture device 20, and the image capture device 20 detects whether a predetermined timing or transmission conditions are met, and transmits the data to the image processing device 10 accordingly. As a variation, the data generated by the image capture device 20 may be stored in a device other than the image capture device 20. Then, this device other than the image capture device 20 may detect whether a predetermined timing or transmission conditions are met, and transmit the data to the image processing device 10 accordingly.

[0041] Alternatively, the data stored in the photographing device 20 may be transmitted to the image processing device 10 through manual operation by the user. If the photographing device 20 has a communication function, the user may transmit data directly from the photographing device 20 to the image processing device 10. Alternatively, the user may move the data stored in the photographing device 20 to another communication terminal of the user, and then transmit the data from that communication terminal to the image processing device 10.

[0042] The data acquisition means by the acquisition unit 11 exemplified here are merely examples, and the invention is not limited to these.

[0043] Images captured by the image capture devices 20 may be linked to the owners (users) of the respective image capture devices 20 and transmitted to and stored in the image processing device 10. This process can be realized using any technology. For example, the identification information of the image capture device 20 and the user identification information may be linked to each other and registered in advance in the image processing device 10. Then, based on this information, images captured by each image capture device 20 may be linked to each user.

[0044] The image analysis unit 12 analyzes the image acquired by the acquisition unit 11 and extracts feature information of the object appearing in the image.

[0045] The "object" may include, for example, at least one of an object moving on land, an object moving on water, and an object moving in the air. Details of the object moving on land, the object moving on water, and the object moving in the air are as described above. Alternatively, the object may be a person. The object may also be other man-made objects such as signs and buildings. The object may also be natural objects such as trees and mountains. The object from which feature information is to be extracted is determined in advance. The image analysis unit 12 extracts feature information of the predetermined object from the image.

[0046] "Feature information" is information for distinguishing each object from other objects. Feature information may be, for example, information indicated by a vehicle license plate. Alternatively, feature information may be the feature amount of the object's appearance (such as a person's face information or an object's feature amount). The image analysis unit 12 can extract feature information from an image using any well-known image analysis technology (such as character recognition technology, face recognition technology, or object recognition technology).

[0047] When the image is a still image, the image analysis unit 12 extracts feature information of an object appearing in the still image. On the other hand, when the image is a moving image, the image analysis unit 12 can extract feature information of an object appearing in each frame image. Note that the image analysis unit 12 may subject all frame images to the extraction process, or may subject only some frame images to the extraction process. For example, the image analysis unit 12 may subject frame images every predetermined number of frames to the extraction process.

[0048] The image analysis unit 12 stores the extraction result in a storage device. The storage device may be provided within the image processing device 10. Alternatively, the storage device may be provided in an external device configured to be able to communicate with the image processing device 10.

[0049] An example of information stored in the storage device is shown in Fig. 6. The information shown in the figure includes image identification information, image capture timing information, and extracted feature information.

[0050] The "image identification information" is information for identifying a plurality of images acquired by the acquisition unit 11. For example, the acquisition unit 11 may assign image identification information to each image every time the acquisition unit 11 acquires an image.

[0051] The "shooting timing information" is as described above. The illustrated shooting timing information indicates the start date and time of shooting a moving image and the end date and time of shooting. According to this information, the timing at which each frame image was generated can be identified using, for example, the frame rate. A general value may be applied as the frame rate. Alternatively, the shooting timing information for each image may further include the frame rate.

[0052] "Extracted feature information" indicates feature information extracted from each image. The illustrated feature information is information indicated by the vehicle's license plate. Although not illustrated, if the image is a moving image, the extracted feature information can indicate from which frame image the extracted feature information was extracted.

[0053] "Process for Providing Data to User" Returning to FIG. 1, the input receiving unit 13 acquires feature information of the detection target object.

[0054] The "detection target" is an object that is the detection target. The user determines the detection target. Then, the user inputs feature information of the detection target to the image processing device 10.

[0055] In one example, a user can input feature information of the detection target object to the image processing device 10 via an input device included in the image processing device 10. In another example, the image processing device 10 is a server in a client-server system. The user can operate their own user terminal 40 to send the feature information of the detection target object to the image processing device 10. Examples of the user terminal 40 include, but are not limited to, a smartphone, a mobile phone, a tablet terminal, a personal computer, a smartwatch, etc.

[0056] The user can input text information as feature information of the detection target. For example, the user can input information indicated by the license plate of the vehicle that is the detection target. Alternatively, the user can input an image of the detection target as feature information of the detection target. In this case, the input accepting unit 13 analyzes the input image and extracts feature information of the detection target contained in the image. The input accepting unit 13 can extract feature information from the input image using any widely known image analysis technology (character recognition technology, face recognition technology, object recognition technology, etc.).

[0057] The identification unit 14 identifies the image from which the feature information of the detection object has been extracted. The identification unit 14 identifies the image from which the feature information of the detection object has been extracted, by referring to the result of extraction of the feature information of the object by the image analysis unit 12 as shown in FIG.

[0058] The output unit 15 outputs the image identified by the identification unit 14 .

[0059] "Outputting an image identified by the identification unit 14" means outputting the identified image to a display device and displaying the image on the display device. The display device may be a display, a projection device, a user terminal 40 that has transmitted feature information of the detected object to the image processing device 10, or the like. For example, the output unit 15 may cause the display device to display a still image. Alternatively, the output unit 15 may cause the display device to play and display a moving image. Alternatively, the output unit 15 may cause the display device to display information identifying each of the still images identified by the identification unit 14 and display one or more specified still images from among the still images. Alternatively, the output unit 15 may cause the display device to display information identifying each of the moving images identified by the identification unit 14 and display one or more specified moving images from among the moving images.

[0060] The output unit 15 can output the image identified by the identification unit 14 in association with at least one image that was taken at the same timing.

[0061] "At least one image identified by the identification unit 14 and taken at the same timing" is at least one image taken at the same timing and from which characteristic information of the object to be detected has been extracted.

[0062] The "same timing" may be a timing when the time is completely the same. Alternatively, the "same timing" may be a concept that allows a certain time difference. For example, if "date and time T １ ~Date and time T ２ ”, “Date and time T ２ ~Date and time T ３ The dates and times may be classified into multiple groups for each predetermined time period, such as "." Dates and times that belong to the same group may be defined as the same timing. Note that a moving image may have any time duration. Such a moving image may belong to multiple groups.

[0063] "Associating and outputting at least one image" means clearly indicating that the at least one image belongs to a group, and displaying the at least one image and the other images in a distinguishable manner. There are various means for realizing such display.

[0064] For example, the output unit 15 may simultaneously display at least one image associated with another in a multi-display mode. At this time, other images are not displayed on the screen. As a modified example, the output unit 15 may simultaneously display all images identified by the identification unit 14 in a multi-display mode. Then, information (such as a frame, a mark, or text information) indicating at least one image associated with another may be displayed on the multi-screen.

[0065] Furthermore, the output unit 15 may display information identifying each of the images identified by the identification unit 14, and when displaying one or more images specified from among the images, the output unit 15 may display the identification information of the images associated with each other in association with each other. For example, the output unit 15 may display the identification information of the images associated with each other using the same display method (such as character color, character type, character size, and frame color), and display the identification information of the images that are not associated with each other using a different display method.

[0066] FIG. 7 shows an example in which an image identified by the identification unit 14 is output in association with at least one image captured at the same timing.

[0067] 7, the output unit 15 displays multiple images captured at the same time and from which feature information of the detection object has been extracted, thereby associating the images with each other. In the example of Fig. 7, the captured images were captured between 6:00 and 6:05 on August 1, 2023.

[0068] The timing of capturing images can be changed by operating the "Back" button and "Next" button shown in the figure. For example, by operating the "Next" button, the specified capturing timing changes from 6:05 to 6:10 on August 1, 2023. In response, the output unit 15 switches the display on the screen to a multi-display of multiple images captured between 6:05 and 6:10 on August 1, 2023, from which feature information of the detected object has been extracted. Note that the capturing timing may be specified by other methods. For example, the user may be able to directly specify the date and time.

[0069] If the images displayed in multiple views are moving images, each moving image may be individually played back and displayed. Furthermore, the multiple displayed moving images may be synchronized and played back simultaneously. Furthermore, the moving images may be rewound, fast-forwarded, played in slow motion, and the like. The user can perform these display operations via operation buttons (not shown).

[0070] In addition, there are cases where the imaging device 20 owned by the user who inputs the feature information of the detected object captures an image at a specified capture timing, and the image (hereinafter, the user-captured image) is stored in the image processing device 10. In this case, the output unit 15 may further display the user-captured image on a multi-screen as shown in FIG. 7 . Note that the user-captured image may or may not include the feature information of the detected object specified by the user. In either case, the user-captured image can be displayed on the multi-screen. The output unit 15 can display the user-captured image and other images on the multi-screen in a distinguishable manner. For example, the output unit 15 may display the user-captured image at a predetermined position (e.g., upper left) on the multi-screen. In addition, the output unit 15 may display information indicating the user-captured image (such as a frame, mark, text information, etc.) on the multi-screen.

[0071] As described above, the images captured by the image capture devices 20 may be transmitted to and stored in the image processing device 10 while being linked to the owner (user) of each image capture device 20. In this case, the output unit 15 can identify, based on the information, from among the images acquired by the acquisition unit 11, images captured by the image capture device 20 owned by the user who input the feature information of the detection target object.

[0072] An example of the processing flow of the image processing device 10 of this embodiment is shown in the flowcharts of Figures 2 and 3. The processing flow shown in the flowcharts of Figures 2 and 3 has been explained in the first embodiment, so an explanation thereof will be omitted here.

[0073] "Effects" The image processing device 10 of this embodiment can achieve the same effects as those of the first embodiment.

[0074] Furthermore, the image processing device 10 of this embodiment can be used for a variety of purposes.

[0075] For example, the user is a driver of a mobile object 30 (four-wheeled vehicle, two-wheeled vehicle, etc.) that moves on land. When the user encounters a problem such as an accident, the user inputs characteristic information of the mobile object 30 that the user was driving into the image processing device 10 as characteristic information of the detected object. In response, the image processing device 10 provides the user with an image that shows the characteristic information of the specified detected object. As a result, the user can view an image that shows the mobile object 30 that the user was driving.

[0076] The image processing device 10 outputs at least one image captured at the same time in association with the other images. Therefore, for example, a user can easily identify at least one group of images captured at the time when the user encountered a problem such as an accident and can view them together. The group of images captured at the same time by the image capturing device 20 mounted on at least one moving body 30 may capture the user's moving body 30 from various angles. By reviewing such a group of at least one image captured at the same time, the user can view the user's moving body 30 from various angles at the time when the user encountered a problem such as an accident.

[0077] Furthermore, when an image is captured by the image capturing device 20 mounted on the vehicle 30 that the user is driving, the image processing device 10 can multi-display the image captured by the user and an image showing the user's vehicle 30. The user can view the image captured by the user to recall the situation at the time, and view other images to check the surrounding situation that is not captured in the image captured by the user.

[0078] In another application, the user may be an investigative agency investigating an accident or incident. For example, when handling an accident or the like, the investigative agency inputs characteristic information of the mobile object 30 involved in the accident into the image processing device 10 as characteristic information of the detected object. In response, the image processing device 10 provides the user with an image showing the characteristic information of the specified detected object. As a result, the investigative agency can view an image showing the mobile object 30 involved in the accident. In this case, the same effects as those described above can be obtained.

[0079] In addition, the investigative agency may input characteristic information of a criminal, a missing person, a person to be tracked, etc. as characteristic information of the detected object into the image processing device 10. This allows the investigative agency to view images in which the detected object appears.

[0080] In another application, the user may be any ordinary person. For example, when the user encounters a problem such as an accident or an incident, the user inputs his / her own characteristic information into the image processing device 10 as characteristic information of the detection target. As a result, the user can view an image of himself / herself when he / she encounters the problem.

[0081] It should be noted that the uses of the image processing device 10 are not limited to those exemplified here, and the image processing device 10 can be used for a variety of purposes.

[0082] Third Embodiment In the second embodiment, the image processing device 10 identifies an image from which feature information of a detection object has been extracted and outputs the identified image. In the third embodiment, the image processing device 10 identifies an image that has been captured under specified shooting conditions and from which feature information of a detection object has been extracted and outputs the identified image. This will be described in detail below.

[0083] The input receiving unit 13 acquires photographing conditions that specify at least one of a photographing timing and a photographing position. A user who inputs feature information of a detection object to the image processing device 10 also inputs photographing conditions to the image processing device 10.

[0084] There are various means for accepting input of shooting conditions. For example, a user may input specifying a date, time, and location using a well-known input device. Examples of input devices include, but are not limited to, a touch panel, physical buttons, a microphone, a keyboard, and a mouse. The input accepting unit 13 may accept a pinpoint specification of the shooting timing, or may accept a range of time, such as from 1:00 PM to 2:00 PM on June 1, 2023. The time range may be set by the user. The input accepting unit 13 may also accept a location specification using an area, such as "XX City" or "XX Town." Alternatively, the input accepting unit 13 may accept a partial area on a map that includes a point specified by the user (a circular area with a predetermined radius centered on the specified point) as the specified location. Alternatively, the input accepting unit 13 may accept a partial area on a map that the user specifies as the specified location.

[0085] The identification unit 14 identifies an image that has been captured under a shooting condition designated by the user and from which feature information of the detection object has been extracted.

[0086] For example, the identification unit 14 can identify an image that was captured at a capture timing designated by the user and from which feature information of the detection target object has been extracted.

[0087] Additionally, the specifying unit 14 can specify an image that was taken at a photographing position designated by the user and from which feature information of the detection target object has been extracted.

[0088] Additionally, the identification unit 14 can identify an image that was captured at a capture position designated by the user at a capture timing designated by the user and from which feature information of the detection target object has been extracted.

[0089] When using the shooting position as described above, shooting position information indicating the shooting position of the image acquired by the acquisition unit 11 is required. The image processing device 10 can acquire the shooting position information by various means.

[0090] For example, the image capturing device 20 may have a function for acquiring location information (such as latitude and longitude information) indicating its current location. This function is, for example, but is not limited to, a GPS (global positioning system) function. The image capturing device 20 uses this function to generate image capturing location information indicating the image capturing location of each captured image. The acquisition unit 11 can then acquire the image capturing location information generated by the image capturing device 20. The image capturing location information generated by the image capturing device 20 can be acquired by the same means as those for acquiring the images and image capturing timing information described in the second embodiment.

[0091] As another example, the image analysis unit 12 may analyze the image acquired by the acquisition unit 11 and detect a predetermined landmark from within the image to identify the shooting location of the image. In this manner, shooting location information may be generated. A landmark is an object (such as a building, an artificial object, or a natural object) that is linked to location information (such as latitude and longitude information) and registered in advance in the image processing device 10.

[0092] Other configurations of the image processing device 10 of this embodiment are similar to those of the image processing device 10 of the first and second embodiments.

[0093] The image processing device 10 of this embodiment can achieve the same effects as those of the first and second embodiments. Furthermore, the image processing device 10 of this embodiment can identify images captured under specified shooting conditions and from which feature information of the detection target has been extracted, and output the identified images. With this image processing device 10, a user can more efficiently search for a desired image that captures the detection target by specifying appropriate shooting conditions. For example, by specifying the time period or location of an accident or other problem as shooting conditions, a user can efficiently search for images that were captured during the problem and that capture the detection target.

[0094] An image processing device 10 according to a fourth embodiment outputs an image from which feature information of a detection object has been extracted using a display method different from the method described in the second embodiment. This will be described in detail below.

[0095] In the fourth embodiment, the image processing device 10 acquires shooting position information indicating the shooting position of the image acquired by the acquisition unit 11. The image processing device 10 can acquire the shooting position information in the same manner as in the third embodiment.

[0096] The output unit 15 outputs the image identified by the identification unit 14, as in the first to third embodiments. Various display methods realized by the output unit 15 will be described below. The output unit 15 can realize the following display methods based on the identification result by the identification unit 14, shooting timing information of each image, shooting position information of each image, shooting timing information of the user-captured image, and shooting position information of the user-captured image. The concept of the user-captured image is as described in the second embodiment.

[0097] 8 shows an example of a screen output by the output unit 15. In this example, the user inputs characteristic information of the user's own moving body 30 as characteristic information of the detection target object. An image captured by the image capturing device 20 mounted on the user's moving body 30 becomes the user-captured image.

[0098] L on the screen in Figure 8 １ In the area, the image is taken at the photographing timing designated by the user and the image from which the feature information of the detection object is extracted is taken at the photographing position C １ ~C ７ In the example shown in the figure, the user-specified photographing timing is 6:08:13 on August 1, 2023. The map also shows the photographing position C of the user-specified photograph taken at the photographing timing. ０ It should be noted that the display indicating the shooting position of the user-captured image does not have to be displayed.

[0099] The timing of shooting can be specified in various ways. For example, the timing of shooting can be changed by operating the "back" button and the "forward" button shown in the figure. By operating the "forward" button, the timing of shooting can be advanced. And by operating the "back" button, the timing of shooting can be reversed.

[0100] It should be noted that the timing of image capture may be specified by other methods, such as by allowing the user to directly specify the date and time.

[0101] Additionally, the output unit 15 may have a mode that automatically changes the shooting timing at a constant speed. When the user selects this mode, the specified shooting timing automatically switches at a constant speed. The speed of change may be a speed that changes the shooting timing by one second every second, or may be other. The direction of change may be selectable between a direction that advances the shooting timing forward and a direction that reverses the shooting timing.

[0102] The output unit 15 outputs the L １ The display on the area is switched to a display showing the photographing position of the image photographed at the newly designated photographing timing and from which the feature information of the detected object has been extracted, or the photographing position of the image photographed by the user.

[0103] L on the screen in Figure 8 ２ In the area, at least one image specified by the user is displayed. For example, the user may select L １ Multiple shooting positions C displayed in the area ０ ~C ７ By operating on the mark corresponding to L ２ It may be possible to select the image to be displayed in the area. ２ In an area, one image may be displayed, or multiple images may be displayed in a multi-display.

[0104] L ２The area displays an image (or a frame image in the case of a video) captured at a specified capture timing. If the image is a video, it may be possible to play back and display it from that position. If multiple videos are displayed, each video may be played back and displayed individually. Furthermore, multiple videos may be played back and displayed simultaneously in time synchronization. Furthermore, the video may be rewound, fast-forwarded, played in slow motion, etc. The user can perform these display operations via operation buttons (not shown).

[0105] 8, the user can easily specify the timing of capturing an image when an accident or other trouble occurred based on the user's own position on the map. Also, the user can easily identify the image to be reviewed based on the relationship between the user's position shown on the map and the positions of surrounding cameras.

[0106] FIG. 9 shows another example of the screen output by the output unit 15. In FIG.

[0107] The example of Fig. 9 is a modified example of the example of Fig. 8. In the example of Fig. 9, the output unit 15 outputs the image data at each photographing position C ０ ~C ７ In the example of FIG. 9, the output unit 15 displays information b indicating the shooting direction and the angle of view of all the shooting positions C ０ ~C ７ However, the information b may be displayed by linking it only to the shooting position where the shooting direction and angle of view can be identified.

[0108] The shooting direction and angle of view can be identified by various means. For example, information indicating the shooting direction and angle of view of each image capture device 20 may be stored in advance in the image processing device 10. Then, based on the information, the output unit 15 may identify the shooting direction and angle of view (an angle indicating the extent of the shooting range centered on the shooting direction) of the image captured by each image capture device 20.

[0109] In the case of the image capturing device 20 mounted on the moving body 30, the image capturing direction may be determined, for example, based on the forward direction of the moving body 30. In one example, the forward direction of the moving body 30 is determined as the image capturing direction. In another example, a direction shifted by a predetermined angle in a predetermined direction (right or left in the forward direction) from the forward direction of the moving body 30 is determined as the image capturing direction. The output unit 15 can then identify the forward direction of the moving body 30 based on the trajectory (time change) of the image capturing positions of the images captured by the image capturing device 20 mounted on the moving body 30, and identify the image capturing direction based on the identified forward direction. For example, the direction in which the image capturing position is moving (e.g., the direction from the previous image capturing position toward the latest image capturing position) is determined as the forward direction of the moving body 30.

[0110] If the imaging device 20 is a surveillance camera, the imaging direction and angle of view may be fixed. The imaging direction and angle of view may be stored in the image processing device 10. Alternatively, the imaging direction and angle of view of the surveillance camera may be changeable. In this case, the imaging direction and angle of view at each timing are recorded as history. The output unit 15 can then identify the imaging direction and angle of view at each timing based on the record.

[0111] According to the display as shown in FIG. 9, the same effect as that of the display as shown in FIG. 8 can be achieved. ０ ~C ７ By displaying information b indicating the shooting direction and angle of view linked to the information a, it is possible to grasp whether the object to be detected is captured in each image, and where it is located within the image. For example, it is possible to grasp whether the object is captured slightly at the edge of the image or near the center of the image. Based on the grasped information, the user can easily find the image they want to check.

[0112] FIG. 10 shows another example of the screen output by the output unit 15. In FIG.

[0113] The example of Fig. 10 is a modified example of the example of Fig. 8. In the example of Fig. 10, the output unit 15 outputs the image captured by the user at the image capturing position C ０ Attached to the shooting position C ０The output unit 15 displays information a indicating the moving direction of the moving object 30, i.e., the moving direction of the moving object 30 on which the imaging device 20 that captured the user-captured image is mounted. The output unit 15 may identify the moving direction of the moving object 30 based on the trajectory (change over time) of the imaging positions of the user-captured images. For example, the direction in which the imaging position is moving (e.g., the direction from the immediately previous imaging position toward the latest imaging position) is identified as the moving direction of the moving object 30.

[0114] Although not shown, in the example of Fig. 10, information b in the example of Fig. 9 may also be displayed.

[0115] 10, the same effects as those of the displays in FIGS. 8 and 9 can be achieved. ０ By displaying the information a indicating the moving direction of the moving object 30, that is, the moving direction of the moving object 30, the user can understand which part of the moving object 30 each image captures. For example, in the example of FIG. 10, the image capture position C １ It can be seen that the image at the photographing position C captures the area behind the vehicle 30. ２ It can be seen that the image in FIG. 10 captures the area in front of the vehicle 30 to the right. Based on the information the user has grasped, the user can easily find the image they want to check. Even when capturing an image of the surroundings with the image capturing device 20 mounted on the vehicle 30, blind spots may exist. A display such as that shown in FIG. 10 allows the user to easily find an image capturing a blind spot.

[0116] FIG. 11 shows another example of the screen output by the output unit 15. In FIG.

[0117] The example of Fig. 11 is a modified example of the example of Fig. 10. In the example of Fig. 10, ０ ~C ７ were mapped on the map, but in the example of FIG. 11, each shooting position C ０ ~C ７ is not mapped on the map. Although not shown, the example of Fig. 11 may further display information b in the example of Fig. 9 .

[0118] 11 achieves the same effects as those of the displays in Fig. 8 and Fig. 9. Also, in the display in Fig. 11, the shooting position C of the user-captured image can be easily determined. ０ Based on the information a indicating the direction of movement of the moving object 30, that is, the direction of movement of the moving object 30, the user can understand which part of the moving object 30 each image captures. For example, in the example of FIG. 11, the image capture position C １ It can be seen that the image at the photographing position C captures the area behind the vehicle 30. ２ It can be seen that the image in FIG. 11 captures the area in front of the vehicle 30 to the right. Based on the information the user has grasped, the user can easily find the image they want to check. Even when capturing an image of the surroundings with the image capturing device 20 mounted on the vehicle 30, blind spots may exist. A display such as that shown in FIG. 11 allows the user to easily find an image capturing a blind spot.

[0119] As described above, the acquisition unit 11 of the present embodiment can further acquire image capture position information indicating the image capture position. Furthermore, the input reception unit 13 can further acquire time-series position information of the detection target object.

[0120] Then, the output unit 15 outputs the position of the detection object at the designated photographing timing (photographing position C ０ ) and the specified image shooting position (shooting position C １ ~C ７ ) at the designated photographing timing. ０ ) and the specified image shooting position (shooting position C １ ~C ７ The output unit 15 can output a screen including a map in which the position information of the detected object is mapped. The output unit 15 can also output a screen that further indicates the orientation (movement direction) of the detected object at the specified image capture timing that is identified based on the time-series position information of the detected object. The output unit 15 can then output at least one image that is specified on such a screen.

[0121] In the above example, the time-series position information of the detected object is acquired as a history of the shooting positions of the user-captured images captured by the image capturing device 20 mounted on the user's mobile object 30. As a modified example, the time-series position information of the detected object may be generated by other means. For example, the detected object may be provided with a device having a function for acquiring position information (such as latitude and longitude information) indicating its current location. The device may then acquire and store the position information. The position information may also be provided with timestamp information.

[0122] FIG. 12 shows another example of the screen output by the output unit 15. In FIG.

[0123] The example of Fig. 12 is a modified example of the example of Fig. 7 described in the second embodiment. In the example of Fig. 12, at least one image identified by the identification unit 14 is outputted, arranged in the direction of the arrow in order of decreasing distance from the specified position. Note that the arrows in Fig. 12 are shown for illustrating the arrangement order, and are not displayed on the screen outputted by the output unit 15.

[0124] The "designated position" is the position of the detection target object at the designated shooting timing. In the example of FIG. 12, the position where the image captured by the user's image capture device 20 mounted on the user's moving body 30 is captured is the designated position. Note that, when the designated shooting timing has an arbitrary time width, as in the example of FIG. 7, the "distance from the designated position" can be calculated based on the position of the detection target object and the shooting position of each image at a specific time within the time width. The specific time within the time width may be the first time, the last time, an intermediate time, or any other time.

[0125] In the example of FIG. 12 , the user can search for an image to be confirmed based on the distance from the detection target. Furthermore, due to issues with the accuracy of image analysis, an image that does not actually contain the detection target but contains an object similar to the detection target may be mistakenly identified as an image from which feature information of the detection target has been extracted. When the images are output in order of distance from the detection target as in FIG. 12 , such images that do not actually contain the detection target can be displayed at the back of the image. As a result, the inconvenience of the user needlessly confirming such images that do not contain the detection target can be reduced.

[0126] Other configurations of the image processing device 10 of this embodiment are similar to those of the image processing device 10 of the first to third embodiments.

[0127] The image processing device 10 of this embodiment achieves the same effects as the image processing devices 10 of the first to third embodiments. Furthermore, the image processing device 10 of this embodiment achieves the excellent effects described above by outputting images using the characteristic techniques described above. The effects obtained by each display technique are as described above.

[0128] Fifth Embodiment The images of this embodiment are moving images. The image processing device 10 outputs only scenes from which feature information of the detection object has been extracted, from the moving images from which feature information of the detection object has been extracted. This will be described in detail below.

[0129] The image analysis unit 12 detects scenes from which feature information of the detection target object is extracted from the moving image. For example, the image analysis unit 12 can perform a process of extracting feature information of the detection target object for each frame image. Then, the image analysis unit 12 can detect a scene that combines frame images from which feature information of the detection target object is extracted as a scene from which feature information of the detection target object is extracted.

[0130] Furthermore, the image analysis unit 12 can detect scenes in which the detection target appears even though feature information of the detection target has not been extracted. For example, the image analysis unit 12 detects the detection target in a video based on the features of the detection target. Then, the image analysis unit 12 tracks the detected detection target in the video using a tracking technique for tracking an object in the video. Based on the tracking results, the image analysis unit 12 can detect scenes in which the detection target appears even though feature information of the detection target has not been extracted.

[0131] In one example, the output unit 15 outputs a scene from which feature information of the detection target object has been extracted from a video image identified by the identification unit 14 (a video image from which feature information of the detection target object has been extracted). That is, the output unit 15 causes such a scene to be displayed on a display device. The output unit 15 does not output a scene from which feature information of the detection target object has not been extracted from a video image identified by the identification unit 14. That is, the output unit 15 does not cause such a scene to be displayed on a display device.

[0132] In another example, the output unit 15 outputs scenes from which feature information of the detection target has been extracted from the video identified by the identification unit 14 (video from which feature information of the detection target has been extracted), and scenes from which feature information of the detection target has not been extracted but in which the detection target appears. That is, the output unit 15 displays such scenes on the display device. The output unit 15 does not output scenes from which feature information of the detection target has not been extracted from the video identified by the identification unit 14 and in which the detection target does not appear. That is, the output unit 15 does not display such scenes on the display device.

[0133] Other configurations of the image processing device 10 of this embodiment are similar to those of the image processing device 10 of the first to fourth embodiments.

[0134] The image processing device 10 of this embodiment achieves the same effects as the image processing devices 10 of the first to fourth embodiments. Furthermore, the image processing device 10 of this embodiment can display only scenes containing the detection target object when the image is a moving image. This allows the user to efficiently check only the necessary scenes.

[0135] Furthermore, allowing any user to freely view the images stored in the image processing device 10 raises privacy issues and processing load issues on the image processing device 10. These inconveniences can be alleviated by limiting the images provided to users to scenes that include the object to be detected.

[0136] <Modifications> Modifications applicable to all the embodiments will be described below.

[0137] "Modification 1" In the above embodiment, an image from which feature information of a detection object has been extracted is identified and output using various display methods. That is, the condition for identification and output is that "feature information of a detection object has been extracted." In Modification 1, "feature information of a detection object has been extracted" does not have to be included in the condition for identification and output.

[0138] In this case, the image processing device 10 identifies an image captured under the specified shooting conditions and outputs the identified image. The designation of the shooting conditions and the content of the shooting conditions are as described in the third embodiment.

[0139] The image processing device 10 can, for example, identify and output an image captured at a capture timing designated by the user.

[0140] Additionally, the image processing device 10 can identify and output images captured at a capture position designated by the user.

[0141] Additionally, the image processing device 10 can identify and output an image captured at a user-specified shooting position at a user-specified shooting timing.

[0142] "Variation 2" In the above embodiment, the image processing device 10 acquires images that have been voluntarily transmitted by the photographing device 20. As a variation, the photographing device 20 may transmit images to the image processing device 10 in response to a request from the image processing device 10. Then, the acquisition unit 11 may acquire the images transmitted in this manner.

[0143] For example, when the input receiving unit 13 acquires feature information of the detection target object, the acquiring unit 11 may transmit a request for an image including the feature information to a plurality of image capturing devices 20. The image capturing device 20 analyzes the image and determines whether the image includes the feature information. Then, the image capturing device 20 transmits the image including the feature information to the image processing device 10.

[0144] In another example, when the input receiving unit 13 acquires the photographing conditions, the acquiring unit 11 may transmit requests for images photographed under the photographing conditions to the plurality of photographing devices 20. The photographing devices 20 transmit the images photographed under the photographing conditions to the image processing device 10.

[0145] Here, an example has been described in which a request is sent to the photographing device 20, and the photographing device 20 sends an image in response to the request. As a variation, the image captured by the photographing device 20 may be stored in another device. Then, the image processing device 10 may send a request to this other device and acquire the image from this other device.

[0146] "Variation 3" The output unit 15 may multi-display all of the at least one image identified by the identification unit 14. Then, the output unit 15 may output the at least one image identified by the identification unit 14 in order of proximity of the photographing timing to the designated photographing timing. In other words, the images are displayed in order of the smallest difference between the photographing timing of each image and the designated photographing timing. The photographing timing is designated by the user.

[0147] In this example, the user can search for images to be checked based on the difference between the capture timing of each image and the specified capture timing. For example, the user can specify the timing when the user encountered a problem such as an accident. In this way, the user can easily search for images captured at the desired timing from among the images identified by the identification unit 14.

[0148] "Variation 4" Only users who have registered feature information of their own moving objects 30 in advance in the image processing device 10 may be able to receive the image providing service from the image processing device 10. In other words, the image processing device 10 may accept input of feature information of the detection target only from such users and provide images accordingly.

[0149] The user may be able to input only the characteristic information of his / her own mobile object 30 that has been registered in advance as the characteristic information of the object to be detected.

[0150] In this way, the images provided to the user can be limited to images and scenes that include the user's mobile object 30. Allowing any user to freely view images stored in the image processing device 10 can cause privacy issues and problems with the processing load on the image processing device 10. By limiting the images provided to the user to images and scenes that include the user's mobile object 30, these inconveniences can be alleviated.

[0151] "Variation 5" Only users who have registered their own feature information (e.g., facial information, etc.) in advance in the image processing device 10 may be able to receive the image providing service from the image processing device 10. In other words, the image processing device 10 may accept input of feature information of the detection target only from such users and provide images accordingly.

[0152] The user may be allowed to input only his / her own characteristic information, which has been registered in advance, as the characteristic information of the detection target object.

[0153] In this way, the images provided to the user can be limited to images and scenes in which the user himself / herself appears. If any user is allowed to freely view the images stored in the image processing device 10, privacy issues and problems such as the processing load on the image processing device 10 may arise. By limiting the images provided to the user to images and scenes in which the user himself / herself appears, these inconveniences can be alleviated.

[0154] Modification 6 The output unit 15 may perform mask processing on an image and then output the image that has undergone the mask processing.

[0155] The masking process may be a process of detecting a person in an image and making the detected person unrecognizable, or a process of blurring or masking the face or other parts of the image.

[0156] Alternatively, the masking process may be a process of detecting a vehicle license plate from an image and making the information indicated by the vehicle license plate unrecognizable. The process of making the information indicated by the vehicle license plate unrecognizable may be a process of blurring or otherwise masking the vehicle license plate.

[0157] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0158] In addition, in the flowcharts used in the above description, multiple steps (processes) are described in order. However, the order 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 drawings can be changed as long as it does not cause any problems in terms of the content.

[0159] Some or all of the above embodiments can be described as, but are not limited to, the following notes: 1. An image processing device having: an acquisition means for acquiring images captured by an imaging device mounted on at least one moving body and imaging timing information indicating the timing at which the images were captured; an image analysis means for analyzing the images and extracting feature information of an object appearing in the images; an input acceptance means for acquiring feature information of a detected object; an identification means for identifying the image from which the feature information of the detected object has been extracted; and an output means for outputting the identified image in association with at least one image captured at the same timing. 2. The image processing device described in 1, wherein the acquisition means further acquires imaging position information indicating the imaging position of the image; the input acceptance means further acquires chronological position information of the detected object; and the output means outputs a screen indicating the relative positional relationship between the position of the detected object at a specified timing and the imaging position of the identified image, and outputs at least one of the images specified on the screen. 3. 1. The image processing device according to claim 2, wherein the output means outputs the screen including a map mapping the position of the detected object at the specified timing and the shooting position of the identified image. 4. The image processing device according to claim 2 or 3, wherein the output means outputs the screen further indicating the orientation of the detected object at the specified timing identified based on chronological position information of the detected object. 5. The image processing device according to claim 1, wherein the output means outputs the identified at least one image in order of proximity to the specified timing, and the image processing device according to claim 3, wherein the output means outputs the identified at least one image in order of proximity to the specified timing, and the image processing device according to claim 4, wherein the output means outputs a scene from the identified moving image from which feature information of the detected object has been extracted, and does not output a scene from the identified moving image from which feature information of the detected object has not been extracted.8. The image processing device according to 7, wherein the image analysis means detects scenes from the video in which the detection object is captured but for which feature information of the detection object has not been extracted, and the output means outputs scenes from the identified video in which the feature information of the detection object has been extracted and scenes in which the detection object is captured but for which feature information of the detection object has not been extracted. 9. An image processing method in which one or more computers acquire images captured by an imaging device mounted on at least one moving body and imaging timing information indicating the timing at which the images were captured, analyze the images to extract feature information of objects captured in the images, acquire feature information of the detection object, identify the images from which the feature information of the detection object has been extracted, and output the identified images in association with at least one image captured at the same timing. A program that causes a computer to function as: an acquisition means for acquiring images captured by an imaging device mounted on at least one moving body and imaging timing information indicating the timing at which the images were captured; an image analysis means for analyzing the images and extracting feature information of objects appearing in the images; an input acceptance means for acquiring feature information of the detected object; an identification means for identifying the image from which the feature information of the detected object has been extracted; and an output means for outputting the identified image in association with at least one image captured at the same timing.

[0160] Some or all of Supplements 2 to 8 that are dependent on the image processing device of Supplement 1 described above may also be dependent on the image processing method of Supplement 9 and the program of Supplement 10 in the same dependent relationship as Supplement 1 and Supplements 2 to 8. Furthermore, within the scope of each of the above-mentioned embodiments, some or all of the configurations described as Supplements can be realized in various hardware, software, various recording means for recording software, or systems.

[0161] This application claims priority based on Japanese Patent Application No. 2023-143486, filed September 5, 2023, the disclosure of which is incorporated herein by reference in its entirety.

[0162] REFERENCE SIGNS LIST 10 Image processing device 11 Acquisition unit 12 Image analysis unit 13 Input reception unit 14 Identification unit 15 Output unit 1A Processor 2A Memory 3A Input / output I / F 4A Peripheral circuit 5A Bus

Claims

1. An image processing device having: an acquisition means for acquiring images captured by an imaging device mounted on at least one moving body and imaging timing information indicating the timing at which the images were captured; an image analysis means for analyzing the images and extracting characteristic information of an object appearing in the images; an input acceptance means for acquiring characteristic information of a detected object; an identification means for identifying the image from which the characteristic information of the detected object has been extracted; and an output means for outputting the identified image in association with at least one image captured at the same timing.

2. The image processing device of claim 1, wherein the acquisition means further acquires shooting position information indicating the shooting position of the image, the input receiving means further acquires chronological position information of the detected object, and the output means outputs a screen indicating the relative positional relationship between the position of the detected object at a specified timing and the shooting position of the identified image, and outputs at least one of the images specified on the screen.

3. The image processing device according to claim 2, wherein the output means outputs the screen including a map mapping the position of the detected object at the specified timing and the shooting position of the identified image.

4. An image processing device as described in claim 2 or 3, wherein the output means outputs the screen further indicating the orientation of the detected object at the specified timing determined based on the time-series position information of the detected object.

5. The image processing device according to claim 1, wherein said output means outputs at least one of said identified images in order of proximity from the designated position.

6. The image processing device according to claim 1, wherein said output means outputs at least one of said identified images in order of proximity of the time at which they were taken to the specified time.

7. An image processing device as claimed in any one of claims 1 to 6, wherein the image is a moving image, and the output means outputs a scene from the identified moving image from which feature information of the detected object has been extracted, and does not output a scene from the identified moving image from which feature information of the detected object has not been extracted.

8. The image processing device according to claim 7, wherein the image analysis means detects scenes from the video in which the detection object is captured but for which feature information of the detection object has not been extracted, and the output means outputs scenes from the identified video in which the feature information of the detection object has been extracted, and scenes in which the detection object is captured but for which feature information of the detection object has not been extracted.

9. An image processing method in which one or more computers acquire images captured by an imaging device mounted on at least one moving object and imaging timing information indicating the timing at which the images were captured, analyze the images to extract feature information of objects appearing in the images, acquire feature information of the detected object, identify the images from which the feature information of the detected object has been extracted, and output the identified images in association with at least one image captured at the same timing.

10. The image processing method of claim 9, wherein the one or more computers further acquire shooting position information indicating the shooting position of the image, further acquire chronological position information of the detected object, output a screen indicating the relative positional relationship between the position of the detected object at a specified time and the shooting position of the identified image, and output at least one of the images specified on the screen.

11. The image processing method according to claim 10, wherein the one or more computers output the screen including a map mapping the position of the detected object at the specified time and the shooting position of the identified image.

12. The image processing method according to claim 10 or 11, wherein the one or more computers output the screen further indicating the orientation of the detected object at the specified timing, which is determined based on the time-series position information of the detected object.

13. The image processing method according to claim 9, wherein the one or more computers output the identified at least one image in order of proximity from the specified position.

14. The image processing method according to claim 9, wherein the one or more computers output the identified at least one of the images in order of proximity of the capture time to the specified time.

15. A recording medium having recorded thereon a program that causes a computer to function as: an acquisition means for acquiring images captured by an imaging device mounted on at least one moving body and imaging timing information indicating the timing at which the images were captured; an image analysis means for analyzing the images and extracting characteristic information of objects appearing in the images; an input acceptance means for acquiring characteristic information of the detected object; an identification means for identifying the image from which the characteristic information of the detected object has been extracted; and an output means for outputting the identified image in association with at least one of the images captured at the same timing.

16. The recording medium according to claim 15, wherein the acquisition means further acquires shooting position information indicating the shooting position of the image, the input receiving means further acquires chronological position information of the detected object, and the output means outputs a screen indicating the relative positional relationship between the position of the detected object at a specified timing and the shooting position of the identified image, and outputs at least one of the images specified on the screen.

17. The recording medium according to claim 16, wherein the output means outputs the screen including a map mapping the position of the detected object at the specified timing and the shooting position of the identified image.

18. A recording medium as described in claim 16 or 17, wherein the output means outputs the screen further indicating the orientation of the detection object at the specified timing determined based on the time-series position information of the detection object.

19. The recording medium according to claim 15, wherein said output means outputs at least one of said identified images in order of proximity from the designated position.

20. The recording medium according to claim 15, wherein said output means outputs at least one of said identified images in order of proximity of the photographing time to the specified time.

Images