Search support system, search support method, and search support program

Abstract

To more appropriately search for a search subject desired by a user from photographed images photographed by a camera, and to more efficiently support monitoring work by users.SOLUTION: A search support system comprises at least one camera and a server communicable with the camera. The camera transmits a photographed image obtained from photographing an object and image color information of the photographed image to the server. The server determines whether or not a search condition that is set for the photographed image includes a color condition of at least any one color from white, black, or gray, wherein if the color condition is determined being included in the search condition, photographed images associated with the image color information indicating a black and white image from all the photographed images stored in a database are excluded from a search subject, and a search result is generated and outputted, which includes photographed images satisfying the search condition, and if the color condition is determined not being included in the search condition, the search result is generated and outputted, which includes the photographed images satisfying the search condition out of all the photographed images stored in the database.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to a search support system, a search support method, and a search support program. [Background technology]

[0002] Patent Document 1 discloses a person search system that analyzes position information and characteristic information of a person captured in an image captured at an intersection where k (k: an integer of 2 or more satisfying k≦n) cameras are installed, extracts a search target person in the images captured by (k-1) cameras and the movement direction of the search target person at the intersection using the analysis results, and displays the movement direction of the search target person at the intersection where (k-1) cameras are installed superimposed on map data showing the intersection where k cameras are installed. When the person search system receives different images transmitted from n (n: an integer of 3 or more) cameras, it analyzes the position information and characteristic information of the person captured in each image and accumulates it as the analysis result. The person search system displays on a screen each of the images captured by k cameras selected by user operation from among the n cameras, and based on a search request generated in response to a selection of a person to be searched for who appears in one of the images captured by the k cameras, extracts the movement direction of the person to be searched for at an intersection from the images captured by the (k-1) cameras other than the camera that captured the image showing the person to be searched for that corresponds to the search request, and displays it superimposed on map data showing the intersection where the k cameras are installed. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2020-047259 A Summary of the Invention [Problem to be solved by the invention]

[0004] In the configuration of Patent Document 1 described above, when setting a search request for a search target, a user can set conditions related to the colors of the clothes, belongings, and accessories of the person to be searched. However, since a camera captures color images during the daytime and black and white images during the nighttime, it is difficult to detect the colors of the clothes, belongings, accessories, and accessories of the person to be searched from images captured at night. For this reason, when a search request includes color conditions such as white, black, and gray as conditions related to the colors of the clothes, belongings, accessories, and accessories of the person to be searched, the person search system may present to the user search results including images of people captured at night and with low color detection accuracy (i.e., images that are false positives) as people who satisfy such a search request. Therefore, the person search system may not be able to present the search results desired by the user depending on the search request set by the user.

[0005] The present disclosure has been devised in consideration of the above-described conventional circumstances, and aims to provide a search support system, a search support method, and a search support program that more appropriately searches for search targets desired by a user from images captured by a camera, and more efficiently supports the user's surveillance work. [Means for solving the problem]

[0006] The present disclosure provides a search support system including at least one camera that captures an image of an object and a server capable of communicating with the camera, the camera transmitting an image of the object captured by the camera and image color information indicating whether the captured image is a black-and-white image or a color image to the server, the server storing the captured image and the image color information in a database in association with each other, determining whether a search condition for the captured image set based on a user operation includes a color condition of at least one of white, black, and gray, and, if it is determined that the search condition includes the color condition, excluding from search targets captured images associated with the image color information indicating the black-and-white image from all the captured images stored in the database, generating and outputting search results including captured images that satisfy the search condition, and, if it is determined that the search condition does not include the color condition, generating and outputting search results including the captured images that satisfy the search condition from all the captured images stored in the database.

[0007] The present disclosure also provides a search support method performed by a computer communicatively connected to at least one camera that captures an object, the search support method comprising: storing a captured image of the object in a database in association with image color information indicating whether the captured image is a black-and-white image or a color image; determining whether a search condition for the captured image set based on a user operation includes a color condition of at least one of white, black, and gray; and, if it is determined that the color condition is included, excluding from the search targets all the captured images stored in the database captured images associated with the image color information indicating the black-and-white image; generating and outputting search results including captured images that satisfy the search condition; and, if it is determined that the color condition is not included, generating and outputting search results including captured images that satisfy the search condition among all the captured images stored in the database.

[0008] The present disclosure also provides a search support program for implementing the steps of: storing, in a database, a captured image of an object in a server, which is a computer communicatively connected to at least one camera that captures an object, in association with image color information indicating whether the captured image is a black-and-white image or a color image; determining whether a search condition for the captured image set based on a user operation includes a color condition of at least one of white, black, and gray; excluding, from all the captured images stored in the database, captured images associated with the image color information indicating the black-and-white image from search targets when it is determined that the color condition is included, and generating and outputting search results including captured images that satisfy the search condition; and generating and outputting search results including captured images that satisfy the search condition from all the captured images stored in the database when it is determined that the color condition is not included. Effect of the Invention

[0009] According to the present disclosure, it is possible to more appropriately search for a search target desired by a user from images captured by a camera, and to more efficiently support surveillance operations performed by the user. [Brief description of the drawings]

[0010] [Figure 1] FIG. 1 is a block diagram showing an example of an internal configuration of a search support system according to a first embodiment. [Diagram 2] FIG. 10 is a diagram for explaining an example of a person search condition setting screen in the first embodiment. [Diagram 3] FIG. 10 is a diagram for explaining an example of a vehicle search condition setting screen in the first embodiment. [Figure 4A] A sequence diagram showing an example of a person search procedure of the search support system according to the first embodiment. [Figure 4B] FIG. 1 is a diagram for explaining an example of various data registered in a database in an example of a person search procedure of the search support system according to the first embodiment; [Diagram 5] FIG. 13 is a diagram illustrating an example of a search result screen for people that includes black and white images. [Figure 6] FIG. 13 is a diagram illustrating an example of a search result screen for people excluding black and white images. [Figure 7A] FIG. 1 is a sequence diagram showing an example of a vehicle search procedure of the search support system according to the first embodiment. [Figure 7B] FIG. 1 is a diagram for explaining an example of various data registered in a database in an example of a vehicle search procedure of the search support system according to the first embodiment; [Figure 8] FIG. 13 is a diagram illustrating an example of a search result screen for vehicles including black and white images. [Figure 9] FIG. 13 is a diagram illustrating an example of a search result screen for vehicles excluding black and white images. [Figure 10] FIG. 11 is a sequence diagram showing an example of a person search procedure of the search support system according to a modification of the first embodiment. [Figure 11A] A sequence diagram showing an example of a person search procedure of the search support system according to the second embodiment. [Figure 11B] FIG. 11 is a diagram for explaining an example of various data registered in a database in an example of a person search procedure of the search support system according to the second embodiment. [Figure 12] FIG. 13 is a diagram illustrating an example of a search result screen for people that includes black and white images. [Figure 13] FIG. 13 is a diagram illustrating an example of a search result screen for people excluding black and white images. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Hereinafter, with reference to the drawings as appropriate, each embodiment that specifically discloses the configuration and operation of the search support system, search support method, and search support program according to the present disclosure will be described in detail. However, more detailed explanation than necessary may be omitted. For example, detailed explanation of already well-known matters and duplicate explanation of substantially the same configuration may be omitted. This is to avoid the following explanation becoming unnecessarily redundant and to facilitate understanding by those skilled in the art. Note that the attached drawings and the following explanation are provided to enable those skilled in the art to fully understand the present disclosure, and are not intended to limit the subject matter described in the claims.

[0012] (Embodiment 1) FIG. 1 is a block diagram showing an example of the internal configuration of a search support system 100 according to the first embodiment. The search support system 100 searches for captured images of objects that satisfy search conditions set by a user from captured images captured by a camera, and outputs search results. The search support system 100 includes a plurality of cameras CM1, ..., CMN, a server S1, and a terminal device P1. The camera according to the first embodiment is, for example, a surveillance camera, but the purpose and type of the camera are not limited to this. The number of cameras may be at least one or more. There may be a plurality of terminal devices P1.

[0013] Each of the multiple cameras CM1, ..., CMN is installed indoors or outdoors so as to be able to capture an image of a monitoring area, and captures the image of the monitoring area. Each of the multiple cameras CM1, ..., CMN is a camera equipped with artificial intelligence (AI) and analyzes captured images (captured images) using a trained model of AI, and performs detection of an object set by a user, extraction of features of the object, etc. Each of the multiple cameras CM1, ..., CMN has a similar configuration and includes a communication unit CM10, a processor CM11, a memory CM12, and an imaging unit CM13.

[0014] The communication unit CM10 is connected to the server S1 so as to be able to communicate data with the server S1. Each of the cameras CM1, ..., CMN may be connected to the server S1 so as to be able to communicate with the server S1 via a wired network or via a wireless LAN. The wireless communication here refers to short-range wireless communication such as Bluetooth (registered trademark) or NFC (registered trademark), or communication via a wireless LAN (Local Area Network) such as Wi-Fi (registered trademark).

[0015] The processor CM11 is configured using, for example, a CPU (Central Processing Unit) or an FPGA (Field Programmable Gate Array), and performs various processes and controls in cooperation with the memory CM12. Specifically, the processor CM11 refers to the programs and data stored in the memory CM12 and executes the programs to realize the functions of each part. The functions referred to here include a function of detecting an object (e.g., a person, a vehicle, etc.) using a best shot image based on a pre-set application (learning model), a function of extracting the feature amount of the object, a function of determining whether a face that can be used for face recognition (face matching) processing has been detected, and the like.

[0016] The processor CM11 detects objects (e.g., people, vehicles, etc.) within a monitoring area from captured images based on a pre-set application (learning model) and selects the best shot image of the detected objects.

[0017] In addition, from the standpoint of visibility or recognition and authentication processing accuracy, it is desirable to select the best shot image here from the perspective of, for example, an image in which the subject (e.g., a person, a vehicle, etc.) faces forward, an image that is not out of focus, an image in which the person's eyes are open, an image in which the license plate (number plate) of a vehicle or motorcycle faces forward, etc.

[0018] The processor CM11 determines whether the face of a person, which is an object, is captured in the selected best shot image, and when it is determined that the face of a person is captured, generates information (hereinafter, referred to as "face detection information") indicating whether the face of a person is captured in the best shot image and whether the face is detected as usable for face recognition (face matching) processing. The processor CM11 extracts feature amounts of the object (e.g., attribute information of the person, attribute information of the vehicle, etc.) from the selected best shot image. The processor CM11 also determines whether the selected best shot image is a black and white image captured during a time period such as nighttime or in a dark place, or a color image captured during a time period such as daytime or in a bright place. When it is determined that the image is a black and white image, the processor CM11 generates image color information indicating that the best shot image is a black and white image, and when it is determined that the image is a color image, the processor CM11 generates image color information indicating that the best shot image is a color image.

[0019] The processor CM11 generates metadata that associates the face detection information, information on the feature quantities of the object (i.e., person attribute information, vehicle attribute information, etc.), the face detection information, and image color information, and transmits the detection data that further associates the generated metadata with a best shot image and information on the camera that can identify the own camera to the server S1.

[0020] The attribute information of a person here includes, for example, the person's age (generation), sex, whether or not they are wearing a mask, hairstyle, hair color, upper body clothing, color of upper body clothing, lower body clothing, color of lower body clothing, whether or not they have glasses, whether or not they have a beard, etc. The attribute information of a vehicle includes, for example, the vehicle model, vehicle color, license plate number, etc.

[0021] The memory CM12 has, for example, a RAM (Random Access Memory) as a work memory used when executing each process of the processor CM11, and a ROM (Read Only Memory) that stores programs and data that define the operation of the processor CM11. The RAM temporarily stores data or information generated or acquired by the processor CM11. The ROM stores programs that define the operation of the processor CM11.

[0022] The imaging unit CM13 is configured to have at least a lens (not shown) and an image sensor (not shown). The image sensor is a solid-state imaging element such as a CCD (Charged-Coupled Device) or a CMOS (Complementary Metal-Oxide-Semiconductor), and converts an optical image formed on an imaging surface into an electrical signal. The imaging unit CM13 outputs the captured image to the processor CM11.

[0023] The server S1 is connected to each of the multiple cameras CM1, ..., CMN and the terminal device P1 so that data can be communicated between them. The server S1 may be connected to each of the multiple cameras CM1, ..., CMN and the terminal device P1 so that wired communication can be performed between them, or may be connected via a wireless network such as a wireless LAN. The server S1 registers (stores) the detection data transmitted from each of the multiple cameras CM1, ..., CMN in a database DB1. The server S1 searches for best shot images or metadata registered in the database DB1 based on search conditions transmitted from the terminal device P1, and transmits the search results in which best shot images satisfying the search conditions are extracted to the terminal device P1. The server S1 includes a communication unit 10, a processor 11, a memory 12, and a database DB1. The database DB1 may be configured separately from the server S1. Furthermore, there may be multiple databases DB1.

[0024] The communication unit 10 is configured using a communication interface circuit capable of data communication between each of the multiple cameras CM1, ..., CMN and the terminal device P1. The communication unit 10 outputs search conditions transmitted from the terminal device P1, detection data transmitted from each of the multiple cameras CM1, ..., CMN, etc. to the processor 11. The communication unit 10 also transmits search results output from the processor 11 to the terminal device P1.

[0025] The processor 11 is configured using, for example, a CPU or FPGA, and performs various processes and controls in cooperation with the memory 12. Specifically, the processor 11 refers to the programs and data stored in the memory 12 and executes the programs to realize the functions of each unit. The functions of each unit here include, for example, a function to register (store) the detection data transmitted from each of the multiple cameras CM1, ..., CMN in a database DB1, a function to search for best shot images that satisfy the search conditions based on the search conditions transmitted from the terminal device P1, and the like.

[0026] The memory 12 has, for example, a RAM as a work memory used when the processor 11 executes each process, and a ROM for storing programs and data that define the operation of the processor 11. The RAM temporarily stores data or information generated or acquired by the processor 11. The ROM has written therein the programs that define the operation of the processor 11.

[0027] The database DB1 is configured using, for example, a hard disk drive (HDD) or a solid state drive (SSD). The database DB1 registers (stores) detection data transmitted from each of the multiple cameras CM1, ..., CMN. Note that the server S1 may include multiple databases DB1, or the database DB1 may be configured separately from the server S1.

[0028] The terminal device P1 is realized by, for example, a PC (Personal Computer), a notebook PC, a smartphone, a tablet terminal, etc., and has an interface (for example, a keyboard, a mouse, a touch panel display, etc.) capable of receiving an input operation from a user. The terminal device P1 is connected to the server S1 so as to be able to perform data communication. The terminal device P1 may be connected to the server S1 so as to be able to perform wired communication, or may be connected via a wireless network such as a wireless LAN. The terminal device P1 transmits search conditions generated based on an input operation by the user to the server S1, and displays search results corresponding to the search conditions transmitted from the server S1 on the monitor 23. The terminal device P1 is configured to include a communication unit 20, a processor 21, a memory 22, a monitor 23, and an input unit 24.

[0029] The communication unit 20 is configured using a communication interface circuit capable of transmitting and receiving data to and from the server S1. The communication unit 20 transmits search conditions for searching (detecting) a predetermined object, which are generated by the processor 21, to the server S1 via a wireless communication network or a wired communication network, and outputs search results transmitted from the server S1 to the processor 11.

[0030] The processor 21 is configured using, for example, a CPU or FPGA, and performs various processes and controls in cooperation with the memory 22. Specifically, the processor 21 refers to the programs and data stored in the memory 22 and executes the programs to realize the functions of each unit. The functions of each unit here include, for example, a function of generating search conditions based on the user's input operation input to the input unit 24, a function of displaying the search results transmitted from the server S1 on the monitor 23, etc.

[0031] The memory 22 has, for example, a RAM as a work memory used when executing each process of the processor 21, and a ROM for storing programs and data that define the operation of the processor 21. The RAM temporarily stores data or information generated or acquired by the processor 21. The ROM has written therein programs that define the operation of the processor 21.

[0032] The monitor 23 is configured using a display such as an LCD (Liquid Crystal Display) or an organic EL (Electroluminescence) display, etc. The monitor 23 displays a search condition setting screen (see FIGS. 2 and 3) for setting search conditions, a search result screen (see FIGS. 5, 6, 8, 9, 12, and 13) for displaying search results transmitted from the server S1, etc.

[0033] The input unit 24 is, for example, a user interface that detects an input operation by a user, and is configured using a mouse, a keyboard, a touch panel, etc. The input unit 24 converts the received user operation into an electrical signal (control command) and outputs it to the processor 21.

[0034] Here, a setting screen for search conditions relating to a person, which is an object, will be described with reference to Fig. 2. Fig. 2 is a diagram illustrating an example of a search condition setting screen SC1 for a person in the first embodiment.

[0035] The search condition setting screen SC1 is a screen for setting search conditions related to attribute information of a person as a feature amount of an object based on a user operation. The search condition setting screen SC1 is generated by the processor 21 based on a user operation requesting the setting of a search condition, and is displayed on the monitor 23.

[0036] The search condition setting screen SC1 includes a plurality of setting items related to the attribute information of a person. In the example shown in Fig. 2, the search condition setting screen SC1 includes a plurality of setting items HA1, HA2, HA3, HA4, HA5, HA6, HA7, HA8, HA9, and HA10 related to the attribute information of a person, and setting items HA11 and HA12 related to best shot images. It goes without saying that the various setting items shown in Fig. 2 are merely examples and are not limited thereto.

[0037] The setting item HA1 accepts the designation of a search criterion "Gender" related to a person's gender. The terminal device P1 sets the gender pressed (selected) by a user's operation on the setting item HA1 as a search criterion. In the example shown in FIG. 2, the setting item HA1 includes two options, "Male" and "Female."

[0038] The setting item HA2 accepts the designation of a search criterion "Age" related to a person's age. The terminal device P1 sets the age pressed (selected) by a user operation on the setting item HA2 as a search criterion. In the example shown in FIG. 2, the setting item HA2 includes four options related to a person's age, "0-10," "11-20," "21-60," and "61+," and "21-60" is selected as the search criterion related to a person's age.

[0039] The setting item HA3 accepts the designation of a search condition "Hair Type" related to a person's hairstyle. The terminal device P1 sets the hairstyle pressed (selected) by a user operation on the setting item HA3 as a search condition. In the example shown in FIG. 2, the setting item HA3 includes three types of options related to a person's hairstyle (specifically, long hair, short hair, skinhead, etc.).

[0040] The setting item HA4 accepts the designation of a search criterion "Hair color" related to a person's hair color. The terminal device P1 sets the hair color pressed (selected) by a user operation on the setting item HA4 as a search criterion. In the example shown in FIG. 2, the setting item HA4 includes five options related to a person's hair color, "black," "gray," "white," "brown," and "yellow."

[0041] The setting item HA5 accepts the designation of a search criterion "Tops type" related to clothing for the upper body of a person. The terminal device P1 sets the clothing for the upper body pressed (selected) by a user operation on the setting item HA5 as a search criterion. In the example shown in FIG. 2, the setting item HA5 includes two options related to clothing for the upper body of a person, "short sleeve" and "long sleeve".

[0042] The setting item HA6 accepts the specification of a search criterion "Tops color" related to the color of clothing on the upper half of a person's body. The terminal device P1 sets the color of clothing on the upper half of the body that is pressed (selected) by a user operation on the setting item HA6 as a search criterion. In the example shown in FIG. 2, the setting item HA6 includes eleven options related to the color of clothing on the upper half of a person's body, namely "black," "gray," "white," "brown," "orange," "yellow," "green," "blue," "purple," "pink," and "red."

[0043] The setting item HA7 accepts the designation of a search criterion "Bottoms type" regarding clothing for the lower half of a person's body. The terminal device P1 sets the clothing for the lower half of the body that is pressed (selected) by a user operation on the setting item HA7 as a search criterion. In the example shown in FIG. 2, the setting item HA7 includes two options regarding clothing for the lower half of the person's body, "long pants" and "short pants."

[0044] The setting item HA8 accepts the designation of a search criterion "Bottoms color" relating to the color of clothing on the lower half of a person's body. The terminal device P1 sets the color of clothing on the lower half of the body that is pressed (selected) by a user operation on the setting item HA8 as a search criterion. In the example shown in FIG. 2, the setting item HA8 includes eleven options relating to the color of clothing on the lower half of a person's body, namely "black," "gray," "white," "brown," "orange," "yellow," "green," "blue," "purple," "pink," and "red."

[0045] The setting item HA9 accepts the designation of a search criterion "Glasses" related to glasses, which are an accessory of a person. The terminal device P1 sets the presence or absence of glasses, which is an accessory, pressed (selected) by a user operation on the setting item HA9, as a search criterion. In the example shown in FIG. 2, the setting item HA9 includes two options, "Sunglasses" and "No Glasses," related to glasses, which are an accessory of a person.

[0046] The setting item HA10 accepts the designation of a search condition "Beard" related to a person's beard. The terminal device P1 sets the presence or absence of a beard, which is pressed (selected) by a user operation on the setting item HA10, as a search condition. In the example shown in FIG. 2, the setting item HA10 includes two options related to a person's beard, "Beard" and "No Beard."

[0047] The setting item HA11 accepts the designation of a search criterion "Recognizable face only" for designating whether or not to search for best shot images that satisfy the search criterion set in each of the multiple setting items HA1 to HA10 described above from best shot images associated with face detection information. When the search criterion "Recognizable face only" is pressed (selected) by a user operation in the setting item HA11, the terminal device P1 sets a search criterion for searching for best shot images that satisfy the search criterion set in each of the multiple setting items HA1 to HA10 described above from among the best shot images associated with face detection information. This allows the search support system 100 to more easily search for images in which the face of a person reflected in a best shot image is identifiable in a search for a person using black and white images captured at night, even if it is difficult to search for a person using a search criterion related to color.

[0048] The setting item HA12 accepts the designation of a search condition "Color image only" for designating whether or not to search for best shot images that satisfy the search conditions set in each of the above-mentioned multiple setting items HA1 to HA10 from best shot images associated with image color information indicating that they are color images. When the search condition "Color image only" is pressed (selected) by a user operation in the setting item HA12, the terminal device P1 sets a search condition for searching for best shot images that satisfy the search conditions set in each of the above-mentioned multiple setting items HA1 to HA10 from best shot images associated with image color information indicating that they are color images.

[0049] Here, a setting screen for search conditions relating to a vehicle, which is an object, will be described with reference to Fig. 3. Fig. 3 is a diagram illustrating an example of a search condition setting screen SC2 for a vehicle in the first embodiment.

[0050] The search condition setting screen SC2 is a screen for setting search conditions related to attribute information of a vehicle as a feature amount of an object based on a user operation. The search condition setting screen SC2 is generated by the processor 21 based on a user operation requesting the setting of a search condition, and is displayed on the monitor 23.

[0051] The search condition setting screen SC2 includes a plurality of setting items related to the attribute information of the vehicle. In the example shown in Fig. 3, the search condition setting screen SC2 is displayed including a plurality of setting items CA1 and CA2 related to the attribute information of the vehicle and a setting item CA3 related to the best shot image. It is needless to say that the various setting items shown in Fig. 3 are merely examples and are not limited thereto.

[0052] The setting item CA1 accepts the designation of a search condition "Type" related to the vehicle model. The terminal device P1 sets the vehicle model pressed (selected) by a user operation on the setting item CA1 as a search condition. In the example shown in FIG. 3, the setting item CA1 includes seven options related to the vehicle model, "Sedan," "Van," "SUV," "Truck," "Bus," "PickUp Truck," and "Two wheels."

[0053] The setting item CA2 accepts the designation of a search criterion "Color" related to the color of the vehicle. The terminal device P1 sets the vehicle color pressed (selected) by a user's operation on the setting item CA2 as a search criterion. In the example shown in FIG. 3, the setting item CA2 has 10 options related to the color of the vehicle. There are 11 options, including "black," "gray," "white," "brown," "yellow," "green," "blue," "purple," "pink," and "red."

[0054] The setting item CA3 accepts the designation of a search condition "Color image only" for designating whether or not to search for best shot images that satisfy the search conditions set in each of the above-mentioned multiple setting items CA1 and CA2 from best shot images associated with image color information indicating that they are color images. When the search condition "Color image only" is pressed (selected) by a user operation in the setting item CA3, the terminal device P1 sets a search condition for searching for best shot images that satisfy the search conditions set in each of the above-mentioned multiple setting items CA1 and CA2 from best shot images associated with image color information indicating that they are color images.

[0055] Next, referring to FIG. 4A and FIG. 4B, a person search procedure executed by the search support system 100 will be described. FIG. 4A is a sequence diagram showing an example of a person search procedure of the search support system 100 according to the first embodiment. FIG. 4B is a diagram explaining an example of various data registered in the database DB1 in the example of a person search procedure of the search support system 100 according to the first embodiment. Note that the sequence diagram shown in FIG. 4A is a diagram specifically explaining a search procedure based on each of two search condition examples input in the processing of step St18 and step St23 in order to make the search procedure executed by the server S1 in the first embodiment easy to understand. Note that it goes without saying that each of the two search condition examples is merely an example and is not limited thereto.

[0056] Each of the cameras CM1, ..., CMN detects a person as a target based on a captured image of the monitoring area (St11). Each of the cameras CM1, ..., CMN selects a best shot image for each person as a detected target, and performs a process of determining whether or not the face of the person as a target is captured in the best shot image based on the selected best shot image, such as a process of determining whether or not the face of the person as a target is captured in the best shot image, a process of extracting the feature amount of the target (person), and a process of generating image color information of the best shot image. Each of the cameras CM1, ..., CMN generates metadata that associates the face detection information, the information on the feature amount of the target, the face detection information, and the image color information.

[0057] Each of the cameras CM1, ..., CMN generates detection data that associates the generated metadata, a best shot image of the person, and camera information that can identify the camera, and transmits the data to the server S1 (St12). Note that the best shot image of the person "Person Image No. 1" transmitted to the server S1 in step St12 is a color image captured during the daytime, and shows an example in which the person's attribute information, gender "male" and upper body clothing color "white", are associated with image color information "TRUE" as information on the feature amount of the object. Also, the image color information "TRUE" here indicates that the best shot image "Person Image No. 1" is a color image.

[0058] The server S1 stores (registers) the best shot image "Portrait Image No. 1" transmitted from each of the multiple cameras CM1, . . . , CMN in the database DB1 (St13).

[0059] Each of the cameras CM1, ..., CMN detects a person as an object based on the captured image of the monitoring area (see the process of step St11 within the dashed line shown in FIG. 4A). Each of the cameras CM1, ..., CMN generates detection data in which the generated metadata, the best shot image of the person, and camera information that can identify the camera are associated with each other, and transmits the detection data to the server S1 (St14). Note that the best shot image of the person "person image No. 2" transmitted to the server S1 in step St14 is a black and white image captured during the nighttime, and shows an example in which the person's attribute information of gender "male" and upper body clothing color "gray" are associated with image color information "FALSE" as information on the feature amount of the object. Also, the image color information "FALSE" here indicates that the best shot image "person image No. 2" is a black and white image.

[0060] The server S1 stores (registers) the best shot image "Portrait Image No. 2" transmitted from each of the multiple cameras CM1, . . . , CMN in the database DB1 (St15).

[0061] Similarly, each of the cameras CM1, ..., CMN detects a person as an object based on the captured image of the monitoring area (see the process of step St11 within the dashed line shown in FIG. 4A). Each of the cameras CM1, ..., CMN generates detection data in which the generated metadata, the best shot image of the person, and camera information that can identify the camera are associated with each other, and transmits the detection data to the server S1 (St16). Note that the best shot image of the person "person image No. 1000" transmitted to the server S1 in step St16 is a black and white image captured during the nighttime, and shows an example in which the person's attribute information of gender "male" and upper body clothing color "white" are associated with image color information "FALSE" as information on the feature amount of the object. Note that the image color information "FALSE" here indicates that the best shot image "person image No. 1000" is a black and white image.

[0062] The server S1 stores (registers) the best shot image "Portrait Image No. 1000" transmitted from each of the multiple cameras CM1, . . . , CMN in the database DB1 (St17).

[0063] Through the above-mentioned processes of steps St11 to St17, the database DB1 shown in FIG. 4B stores (registers) the best shot image number ("No." shown in FIG. 4B), the person's gender information "male", the color of the person's upper body clothes "white" or "gray", the image color information "TRUE" or "FALSE" of the best shot image, and 1000 best shot images in association with each other. It goes without saying that each of the best shot images shown in FIG. 4A and FIG. 4B and the metadata associated with each best shot image (e.g., face detection information, person's feature amount, image color information, etc.) are merely examples and are not limited thereto. In the following description of the processes of steps St18 to St27, in order to make the description easier to understand, a procedure for searching for best shot images that satisfy a search condition using each of the 1000 best shot images registered in the database DB1 shown in FIG. 4A will be specifically described. In addition, in Figures 4A and 4B, the best shot images corresponding to numbers "No. 3" to "No. 999" respectively have person attribute information of gender "male", upper body clothing color of the person is "white" or "gray", and image color information of "FALSE", but explanation and illustration are omitted.

[0064] The terminal device P1 accepts an input (setting) operation of search conditions by the user through the input unit 24 (St18). Here, as an example, the search conditions set in step St18 shown in FIG. 4A are described as follows: the search condition "Color image only" is not set (disabled), and the condition related to the feature amount of the object is that the person's gender is "male" and the color of the clothes is "white" or "gray". The terminal device P1 transmits the set search conditions (the person's gender is "male" and the color of the clothes is "white" or "gray") to the server S1 (St19).

[0065] Based on the search conditions transmitted from the terminal device P1, the server S1 refers to the feature amount (here, person attribute information) of the object corresponding to each of the multiple best shot images stored (registered) in the database DB1, and searches for a person image (i.e., best shot image) that satisfies the search conditions (St20). Here, the server S1 in the example shown in FIG. 4A compares the metadata associated with each of the 1000 best shot images registered in the database DB1 with the search conditions (specifically, the gender of the person is "male" and the color of the clothes is "white" or "gray"), and searches for a person image (best shot image) that is determined to satisfy the search conditions. The server S1 generates search result data based on the person image (best shot image) that is determined to satisfy the search conditions, and transmits the generated search result data (here, each of the 1000 best shot images corresponding to the numbers "No. 1" to "No. 1000") to the terminal device P1 (St21).

[0066] The terminal device P1 displays the search result data (that is, each of the 1000 best shot images corresponding to each of the numbers "No. 1" to "No. 1000") transmitted from the server S1 on the monitor 23 (St22).

[0067] The terminal device P1 also accepts an input (setting) operation of search conditions by the user through the input unit 24 (St23). As an example of the search conditions set in step St23 shown in FIG. 4A, a search condition "Color image only" is set (enabled), and the condition regarding the feature amount of the object is that the person's gender is "male" and the color of the clothes is "white" or "gray". The terminal device P1 transmits the set search conditions (the best shot image is a color image, the person's gender is "male", and the color of the clothes is "white" or "gray") to the server S1 (St24).

[0068] Based on the search conditions transmitted from the terminal device P1, the server S1 refers to the feature amount (here, person attribute information) of the object corresponding to each of the multiple best shot images stored (registered) in the database DB1, and searches for a person image (i.e., best shot image) that satisfies the search conditions (St25). Here, the server S1 in the example shown in FIG. 4A compares the metadata associated with each of the 1000 best shot images registered in the database DB1 with the search conditions (specifically, the best shot image is a color image, the gender of the person is "male", and the color of the clothes is "white" or "gray"), and searches for a person image (best shot image) that is determined to satisfy the search conditions. The server S1 generates search result data based on the person image (best shot image) that is determined to satisfy the search conditions, and transmits the generated search result data (here, one best shot image corresponding to the number "No. 1") to the terminal device P1 (St26).

[0069] The terminal device P1 displays the search result data (that is, the best shot image corresponding to the number "No. 1") transmitted from the server S1 on the monitor 23 (St27).

[0070] As described above, the search support system 100 according to the first embodiment determines whether or not to exclude best shot images that are not color images (i.e., best shot images whose image color information is black and white) from search targets by disabling or enabling the search condition "Color image only." In this way, when the search support system 100 enables the search condition "Color image only," it can output search results that exclude best shot images that are not color images (i.e., best shot images whose image color information is black and white). In this way, the search support system 100 can distinguish between information on color features extracted from color images (e.g., white, black, gray, etc.) and information on color features extracted from black and white images (e.g., white, black, gray, etc.), and can output search results that are more suitable for the search conditions.

[0071] Next, the search result screens SC3 and SC4 displayed on the terminal device P1 will be described with reference to Fig. 5 and Fig. 6. Fig. 5 is a diagram illustrating an example of a search result screen SC3 for people including black and white images. Fig. 6 is a diagram illustrating an example of a search result screen SC4 for people excluding black and white images. It goes without saying that the search result screens SC3 and SC4 shown in Fig. 5 and Fig. 6 are merely examples and are not limited to these.

[0072] In addition, each of the search result screens SC3 and SC4 shown in Fig. 5 and Fig. 6 shows an example including input fields for search conditions related to the image capture date and time, face detection information, and image color information, but these search conditions may be set on the search condition setting screen SC1 (see Fig. 2). Furthermore, each of the search result screens SC3 and SC4 shown in Fig. 5 and Fig. 6 may be capable of setting search conditions corresponding to various setting items shown on the search condition setting screen SC1 (see Fig. 2) in "Search Filter". Specifically, when "Search Filter" is selected (pressed) by a user operation on each of the search result screens SC3 and SC4, the terminal device P1 may display a setting field (not shown) in which search conditions corresponding to various setting items shown on the search condition setting screen SC1 (see Fig. 2) can be set and accept the input of search conditions based on the user operation, or may transition to the search condition setting screen SC1 (see Fig. 2) and accept the input of search conditions based on the user operation.

[0073] 5 is generated based on the search result data transmitted from the server S1 by the terminal device P1, and is displayed on the monitor 23. Specifically, the search result screen SC3 is generated to include an imaging date and time setting field DT31, a person search condition field PT31, a search button BT31, and a search result display area AR31.

[0074] The imaging date and time setting field DT31 accepts input operations by the user regarding search conditions related to the imaging date and time or the period of imaging dates and times when the best shot images were captured as search conditions. The terminal device P1 sets the search conditions based on the imaging date and time information input in the imaging start date and time DT32 and the imaging end date and time DT33. In the example shown in FIG. 5, the terminal device P1 sets search conditions to search for best shot images from "3 / 16 / 2020 7:40:47 AM" input in the imaging start date and time DT32 to "3 / 21 / 2020 7:40:47 AM" input in the imaging end date and time DT33.

[0075] The person search condition field PT31 accepts an input operation by the user to set the search condition "Recognizable face only" and the search condition "Color image only" related to the target person. The terminal device P1 sets the search condition selected (pressed) by the user operation. In the example shown in FIG. 5, the terminal device P1 sets a search condition that disables the search condition "Recognizable face only" and the search condition "Color image only".

[0076] The search button BT31 is a button for requesting the server S1 to perform a search process based on the search conditions set in the image capture date and time setting field DT31 and the person search condition field PT31. When the search button BT31 is pressed (selected) by the user, the terminal device P1 generates the search conditions set in the image capture date and time setting field DT31 and the person search condition field PT31, respectively, and a control command for requesting a search based on the search conditions, and transmits the control command to the server S1.

[0077] The search result display area AR31 displays a list of best shot images included in the search result data searched and transmitted by the server S1 based on the search conditions set in the shooting date and time setting field DT31 and the person search condition field PT31, respectively.

[0078] The search result display area AR31 shown in Fig. 5 displays 18 best shot images as search results based on the search conditions set in the shooting date and time setting field DT31 and the person search condition field PT31. Note that in the search result display area AR31 shown in Fig. 5, each of the 12 best shot images surrounded by a solid line frame is a color image. Similarly, each of the 6 best shot images surrounded by a dashed line frame is a black and white image.

[0079] 6 is generated based on the search result data transmitted by the terminal device P1 from the server S1, and is displayed on the monitor 23. Specifically, the search result screen SC4 is generated to include an imaging date and time setting field DT41, a person search condition field PT41, a search button BT41, and a search result display area AR41.

[0080] The imaging date and time setting field DT41 accepts input operations by the user regarding search conditions related to the imaging date and time or the period of imaging dates and times when the best shot images were captured as search conditions. The terminal device P1 sets the search conditions based on the imaging date and time information input in the imaging start date and time DT42 and the imaging end date and time DT43. In the example shown in FIG. 6, the terminal device P1 sets the search conditions to search for best shot images from "3 / 16 / 2020 7:40:47 AM" input in the imaging start date and time DT42 to "3 / 21 / 2020 7:40:47 AM" input in the imaging end date and time DT43.

[0081] The person search condition field PT41 accepts an input operation by the user to set the search condition "Recognizable face only" and the search condition "Color image only" related to the target person. The terminal device P1 sets the search condition selected (pressed) by the user operation. In the example shown in FIG. 6, the terminal device P1 sets the search condition that disables the search condition "Recognizable face only" and enables the search condition "Color image only."

[0082] The search button BT41 is a button for requesting the server S1 to perform a search process based on the search conditions set in the image capture date and time setting field DT41 and the person search condition field PT41. When the search button BT41 is pressed (selected) by the user, the terminal device P1 generates the search conditions set in the image capture date and time setting field DT41 and the person search condition field PT41, respectively, and a control command for requesting a search based on the search conditions, and transmits the control command to the server S1.

[0083] The search result display area AR41 displays a list of best shot images included in the search result data searched and transmitted by the server S1 based on the search conditions set in the shooting date and time setting field DT41 and the person search condition field PT41, respectively.

[0084] The search result display area AR41 shown in Fig. 6 displays each of the 12 best shot images as a search result based on the search conditions set in the shooting date and time setting field DT41 and the person search condition field PT41. Note that in the search result display area AR41 shown in Fig. 6, each of the 12 best shot images surrounded by a solid line frame is a color image.

[0085] As described above, the search support system 100 according to the first embodiment determines whether or not to exclude best shot images that are not color images (i.e., best shot images whose image color information is black and white) from search targets by disabling or enabling the search condition "Color image only." In this way, when the search support system 100 enables the search condition "Color image only," it can output search results that exclude best shot images that are not color images (i.e., best shot images whose image color information is black and white). In this way, the search support system 100 can distinguish between information on color features extracted from color images (e.g., white, black, gray, etc.) and information on color features extracted from black and white images (e.g., white, black, gray, etc.), and can output search results that are more suitable for the search conditions.

[0086] Next, a vehicle search procedure executed by the search support system 100 will be described with reference to FIG. 7A and FIG. 7B. FIG. 7A is a sequence diagram showing an example of a vehicle search procedure of the search support system 100 according to the first embodiment. FIG. 7B is a diagram explaining an example of various data registered in the database DB1 in an example of a person search procedure of the search support system 100 according to the first embodiment. Note that the sequence diagram shown in FIG. 7A is a diagram specifically explaining a search procedure based on each of two search condition examples input in the processing of step St38 and step St43 in order to make the search procedure executed by the server S1 in the first embodiment easier to understand. Note that each of the two search condition examples is merely an example and needless to say is not limited thereto.

[0087] Each of the cameras CM1, ..., CMN detects a vehicle as an object based on a captured image of the monitoring area (St31). Each of the cameras CM1, ..., CMN selects a best shot image for each vehicle as an object detected, and performs processing such as extracting the feature amount of the object (vehicle) and generating image color information of the best shot image based on the selected best shot image. Each of the cameras CM1, ..., CMN generates metadata that associates face detection information, information on the feature amount of the object, and image color information.

[0088] Each of the cameras CM1, ..., CMN generates detection data that associates the generated metadata, a best shot image of the vehicle, and camera information that can identify the camera, and transmits the data to the server S1 (St32). Note that the best shot image of the vehicle "Vehicle Image No. 1" transmitted to the server S1 in step St32 is a color image captured during the daytime, and shows an example in which the vehicle attribute information of the vehicle model "sedan" and vehicle color "white" are associated with image color information "TRUE" as information on the feature amount of the object. Also, the image color information "TRUE" here indicates that the best shot image "Vehicle Image No. 1" is a color image.

[0089] The server S1 stores (registers) the best shot image "vehicle image No. 1" transmitted from each of the cameras CM1, . . . , CMN in the database DB1 (St33).

[0090] Each of the cameras CM1, ..., CMN detects a vehicle, which is an object, based on a captured image of the monitoring area (see the process of step St31 within the dashed line shown in FIG. 7A). Each of the cameras CM1, ..., CMN generates detection data in which the generated metadata, a best shot image of the vehicle, and camera information that can identify the camera are associated with each other, and transmits the detection data to the server S1 (St34). Note that the best shot image of the vehicle "Vehicle Image No. 2" transmitted to the server S1 in step St34 is a black and white image captured during the nighttime, and shows an example in which the vehicle attribute information of the vehicle model "Sedan" and the vehicle color "Gray" are associated with the image color information "FALSE" as information on the feature amount of the object. Also, the image color information "FALSE" here indicates that the best shot image "Vehicle Image No. 2" is a black and white image.

[0091] The server S1 stores (registers) the best shot image "vehicle image No. 2" transmitted from each of the cameras CM1, . . . , CMN in the database DB1 (St35).

[0092] Similarly, each of the cameras CM1, ..., CMN detects a vehicle, which is an object, based on the captured image of the monitoring area (see the process of step St31 within the dashed line shown in FIG. 7A). Each of the cameras CM1, ..., CMN generates detection data in which the generated metadata, the best shot image of the vehicle, and camera information that can identify the camera are associated with each other, and transmits the detection data to the server S1 (St36). Note that the best shot image of the vehicle "Vehicle Image No. 1000" transmitted to the server S1 in step St36 is a black and white image captured during the nighttime, and shows an example in which the vehicle attribute information of the vehicle model "Sedan" and the vehicle color "White" are associated with the image color information "FALSE" as information on the feature amount of the object. Note that the image color information "FALSE" here indicates that the best shot image "Vehicle Image No. 1000" is a black and white image.

[0093] The server S1 stores (registers) the best shot image "vehicle image No. 1000" transmitted from each of the cameras CM1, . . . , CMN in the database DB1 (St37).

[0094] Through the processes of steps St31 to St37 described above, the database DB1 shown in FIG. 7B stores (registers) the best shot image number ("No." shown in FIG. 7B), the vehicle model information "sedan", the vehicle color "white" or "gray", the image color information "TRUE" or "FALSE" of the best shot image, and the 1000 best shot images in association with each other. It goes without saying that each of the best shot images shown in FIG. 7A and FIG. 7B and the metadata associated with each best shot image (e.g., vehicle feature amount, image color information, etc.) are merely examples and are not limited thereto. In the following description of the processes of steps St38 to St47, in order to make the description easier to understand, a specific description will be given of a procedure for searching for a best shot image that satisfies a search condition using each of the 1000 best shot images registered in the database DB1 shown in FIG. 7B. In addition, in Figures 7A and 7B, for the best shot images corresponding to numbers "No. 3" to "No. 999," the vehicle model information is "sedan," the vehicle color is "white" or "gray," and the image color information of the best shot image is "FALSE," but explanation and illustration are omitted.

[0095] The terminal device P1 accepts an input (setting) operation of search conditions by the user through the input unit 24 (St38). Here, as an example, the search conditions set in step St38 shown in FIG. 7A are described as follows: the search condition "Color image only" is not set (disabled), and the condition related to the feature amount of the object is that the vehicle model is "sedan" and the vehicle color is "white" or "gray". The terminal device P1 transmits the set search conditions (the vehicle model is "sedan" and the vehicle color is "white" or "gray") to the server S1 (St39).

[0096] Based on the search conditions transmitted from the terminal device P1, the server S1 refers to the feature amount (here, vehicle attribute information) of the object corresponding to each of the multiple best shot images stored (registered) in the database DB1, and searches for vehicle images (i.e., best shot images) that satisfy the search conditions (St40). Here, the server S1 in the example shown in FIG. 7A compares the metadata associated with each of the 1000 best shot images registered in the database DB1 with the search conditions (specifically, the vehicle model is "sedan" and the vehicle color is "white" or "gray"), and searches for vehicle images (best shot images) that are determined to satisfy the search conditions. The server S1 generates search result data based on the vehicle images (best shot images) that are determined to satisfy the search conditions, and transmits the generated search result data (here, each of the 1000 best shot images corresponding to the numbers "No. 1" to "No. 1000") to the terminal device P1 (St41).

[0097] The terminal device P1 displays the search result data (that is, each of the 1000 best shot images corresponding to each of the numbers "No. 1" to "No. 1000") transmitted from the server S1 on the monitor 23 (St42).

[0098] The terminal device P1 also accepts an input (setting) operation of search conditions by the user through the input unit 24 (St43). As an example of the search conditions set in step St43 shown in FIG. 7A, a search condition "Color image only" is set (enabled), and the vehicle model is "sedan" and the vehicle color is "white" or "gray" as conditions related to the feature amount of the object. The terminal device P1 transmits the set search conditions (the best shot image is a color image, the vehicle model is "sedan", and the vehicle color is "white" or "gray") to the server S1 (St44).

[0099] Based on the search conditions transmitted from the terminal device P1, the server S1 refers to the feature amount (here, vehicle attribute information) of the object corresponding to each of the multiple best shot images stored (registered) in the database DB1, and searches for a vehicle image (i.e., best shot image) that satisfies the search conditions (St45). Here, the server S1 in the example shown in FIG. 7A compares the metadata associated with each of the 1000 best shot images registered in the database DB1 with the search conditions (specifically, the best shot image is a color image, the vehicle model is a "sedan", and the vehicle color is "white" or "gray"), and searches for a vehicle image (best shot image) that is determined to satisfy the search conditions. The server S1 generates search result data based on the vehicle image (best shot image) that is determined to satisfy the search conditions, and transmits the generated search result data (here, one best shot image corresponding to the number "No. 1") to the terminal device P1 (St46).

[0100] The terminal device P1 displays the search result data transmitted from the server S1 (that is, the best shot image corresponding to the number "No. 1") on the monitor 23 (St47).

[0101] As described above, the search support system 100 according to the first embodiment determines whether or not to exclude best shot images that are not color images (i.e., best shot images whose image color information is black and white) from search targets by disabling or enabling the search condition "Color image only." In this way, when the search support system 100 enables the search condition "Color image only," it can output search results that exclude best shot images that are not color images (i.e., best shot images whose image color information is black and white). In this way, the search support system 100 can distinguish between information on color features extracted from color images (e.g., white, black, gray, etc.) and information on color features extracted from black and white images (e.g., white, black, gray, etc.), and can output search results that are more suitable for the search conditions.

[0102] Next, the search result screens SC5 and SC6 displayed on the terminal device P1 will be described with reference to Fig. 8 and Fig. 9. Fig. 8 is a diagram illustrating an example of the search result screen SC5 for vehicles including black and white images. Fig. 9 is a diagram illustrating an example of the search result screen SC6 for vehicles excluding black and white images. It goes without saying that the search result screens SC5 and SC6 shown in Fig. 8 and Fig. 9 are merely examples and are not limited thereto.

[0103] In addition, each of the search result screens SC5 and SC6 shown in Figs. 8 and 9 shows an example including input fields for search conditions related to the image capture date and time, face detection information, and image color information, but these search conditions may be set on the search condition setting screen SC2 (see Fig. 3). Furthermore, each of the search result screens SC5 and SC6 shown in Figs. 8 and 9 may be capable of setting search conditions corresponding to various setting items shown on the search condition setting screen SC2 (see Fig. 3) in "Search Filter". Specifically, when "Search Filter" is selected (pressed) by a user operation on each of the search result screens SC5 and SC6, the terminal device P1 may display a setting field (not shown) in which search conditions corresponding to various setting items shown on the search condition setting screen SC2 (see Fig. 3) can be set and accept input of search conditions based on the user operation, or may transition to the search condition setting screen SC2 (see Fig. 3) and accept input of search conditions based on the user operation.

[0104] 8 is generated by the terminal device P1 based on the search result data transmitted from the server S1, and is displayed on the monitor 23. Specifically, the search result screen SC5 is generated to include an image capture date and time setting field DT51, a vehicle search condition field PT51, a search button BT51, and a search result display area AR51.

[0105] The imaging date and time setting field DT51 accepts input operations by the user regarding search conditions related to the imaging date and time or the period of imaging dates and times when the best shot images were captured as search conditions. The terminal device P1 sets the search conditions based on the imaging date and time information input in the imaging start date and time DT52 and the imaging end date and time DT53. In the example shown in FIG. 8, the terminal device P1 sets search conditions to search for best shot images from "3 / 16 / 2020 7:40:47 AM" input in the imaging start date and time DT52 to "3 / 21 / 2020 7:40:47 AM" input in the imaging end date and time DT53.

[0106] The vehicle search condition field PT51 accepts an input operation by the user for setting the search condition "Color image only" related to the target vehicle. The terminal device P1 sets the search condition selected (pressed) by the user operation. In the example shown in FIG. 8, the terminal device P1 sets a search condition that disables the search condition "Color image only."

[0107] The search button BT51 is a button for requesting the server S1 to perform a search process based on the search conditions set in the image capture date and time setting field DT51 and the vehicle search condition field PT51. When the search button BT51 is pressed (selected) by the user, the terminal device P1 generates the search conditions set in the image capture date and time setting field DT51 and the vehicle search condition field PT51, respectively, and a control command for requesting a search based on the search conditions, and transmits the control command to the server S1.

[0108] The search result display area AR51 displays a list of each of the best shot images included in the search result data searched and transmitted by the server S1 based on the search conditions set in the shooting date and time setting field DT51 and the vehicle search condition field PT51, respectively.

[0109] The search result display area AR51 shown in Fig. 8 displays 12 best shot images as search results based on the search conditions set in the image capture date and time setting field DT51 and the vehicle search condition field PT51. In the search result display area AR51 shown in Fig. 8, each of the seven best shot images surrounded by a solid line frame is a color image. Similarly, each of the five best shot images surrounded by a dashed line frame is a black and white image.

[0110] 9 is generated based on the search result data transmitted by the terminal device P1 from the server S1, and is displayed on the monitor 23. Specifically, the search result screen SC6 is generated to include an image capture date and time setting field DT61, a vehicle search condition field PT61, a search button BT61, and a search result display area AR61.

[0111] The imaging date and time setting field DT61 accepts input operations by the user regarding search conditions related to the imaging date and time or the period of imaging dates and times when the best shot images were captured as search conditions. The terminal device P1 sets the search conditions based on the imaging date and time information input in the imaging start date and time DT62 and the imaging end date and time DT63. In the example shown in FIG. 9, the terminal device P1 sets the search conditions to search for best shot images from "3 / 16 / 2020 7:40:47 AM" input in the imaging start date and time DT62 to "3 / 21 / 2020 7:40:47 AM" input in the imaging end date and time DT63.

[0112] The vehicle search condition field PT61 accepts an input operation by the user for setting the search condition "Color image only" related to the target vehicle. The terminal device P1 sets the search condition selected (pressed) by the user operation. In the example shown in FIG. 9, the terminal device P1 sets a search condition that enables the search condition "Color image only".

[0113] The search button BT61 is a button for requesting the server S1 to perform a search process based on the search conditions set in the image capture date and time setting field DT61 and the vehicle search condition field PT61. When the search button BT61 is pressed (selected) by the user, the terminal device P1 generates the search conditions set in the image capture date and time setting field DT61 and the vehicle search condition field PT61, respectively, and a control command requesting a search based on the search conditions, and transmits the control command to the server S1.

[0114] The search result display area AR61 displays a list of each of the best shot images included in the search result data searched and transmitted by the server S1 based on the search conditions set in the shooting date and time setting field DT61 and the vehicle search condition field PT61, respectively.

[0115] The search result display area AR61 shown in Fig. 9 displays seven best shot images as search results based on the search conditions set in the image capture date and time setting field DT61 and the vehicle search condition field PT61. Note that in the search result display area AR61 shown in Fig. 9, each of the seven best shot images surrounded by a solid line frame is a color image.

[0116] (Modification of the first embodiment) The search support system 100 according to the first embodiment determines whether or not to exclude best shot images that are not color images (i.e., best shot images whose image color information is black and white) from search targets by disabling or enabling the search condition "Color image only", and when the search condition "Color image only" is enabled, an example is shown in which search results excluding best shot images that are not color images (i.e., best shot images whose image color information is black and white) are output. The search support system 100 according to a modification of the first embodiment will be described below as an example in which the search condition "Color image only" is always enabled and search results excluding best shot images that are not color images (i.e., best shot images whose image color information is black and white) are output.

[0117] Note that the internal configuration example of the search support system 100 according to the variation of the first embodiment has almost the same configuration as the internal configuration example of the search support system 100 according to the first embodiment, and therefore a description thereof will be omitted.

[0118] Furthermore, the search condition setting screen in the modification of the first embodiment does not include the search condition item "Color image only." Similarly, the search result screen in the modification of the first embodiment does not include the search condition item "Color image only" in the person search condition field.

[0119] A person search procedure executed by the search support system 100 will be described with reference to FIG. 10. FIG. 10 is a sequence diagram showing an example of a person search procedure of the search support system 100 according to the first embodiment. The sequence diagram shown in FIG. 10 is a diagram specifically explaining a search procedure based on an example of a search condition input in the process of step St51 in order to make the search procedure executed by the server S1 in the first embodiment easier to understand. The search procedure example explained in FIG. 10 is similar to the processes of steps St11 to St17 shown in the search procedure example in FIG. 4, and therefore the explanation will be omitted. An example of various data registered in the database DB1 explained with reference to FIG. 10 is similar to that in FIG. 4B, and therefore the illustration and explanation will be omitted.

[0120] The terminal device P1 accepts an input (setting) operation of search conditions by the user through the input unit 24 (St51). Here, as an example of the search conditions set in step St51 shown in Fig. 10, a case will be described in which the person's gender is "male" and the color of the clothes is "white" or "gray" as conditions related to the feature amount of the object. The terminal device P1 transmits the set search conditions (the person's gender is "male" and the color of the clothes is "white" or "gray") to the server S1 (St52).

[0121] The server S1 determines whether or not the search conditions transmitted from the terminal device P1 include a search condition related to a predetermined color (a color detected from a black and white image, such as white, black, gray, etc.) (St53).

[0122] When the server S1 determines that the search conditions transmitted from the terminal device P1 include a search condition related to a predetermined color (in the example shown in FIG. 10, the color of the clothes is "white" or "gray"), it excludes from the search targets all best shot images stored (registered) in the database DB1 (see the database DB1 shown in FIG. 4B) whose image color information indicates that the image is a black and white image (i.e., best shot images associated with color information "FALSE"), and compares the metadata associated with each of the 1000 best shot images registered in the database DB1 with the search conditions (specifically, the person's gender is "male" and the color of the clothes is "white" or "gray"). The server S1 searches for person images (best shot images) determined to satisfy the search conditions (St54).

[0123] On the other hand, if the server S1 determines that the search conditions transmitted from the terminal device P1 do not include a search condition related to a specific color, it checks the metadata associated with each of the 1000 best shot images registered in the database DB1 against the search conditions (specifically, the person's gender is "male" and the color of the clothes is "white" or "gray"). The server S1 searches for person images (best shot images) determined to satisfy the search conditions (St54).

[0124] The server S1 generates search result data (here, one best shot image corresponding to the number "No. 1") based on the portrait images (best shot images) determined to satisfy the search conditions, and transmits the data to the terminal device P1 (St55).

[0125] The terminal device P1 displays the search result data (that is, the best shot image corresponding to the number "No. 1") transmitted from the server S1 on the monitor 23 (St56).

[0126] As described above, when the search conditions include a specific color such as white, black, or gray that is detectable from a black-and-white image, the search support system 100 according to the modified example of the first embodiment can perform search processing by excluding best shot images whose image color information is black-and-white images from the search targets, regardless of whether the search condition "Color image only" is set.

[0127] (Embodiment 2) The search support system 100 according to the first embodiment has shown an example of a search method when the search condition "Color image only" is enabled. The search support system 100 according to the second embodiment will explain an example of a search method that enables a search for best shot images in which faces that can be used for face recognition (face matching) processing are detected among black-and-white images captured at night by enabling the search condition "Recognizable face only."

[0128] Note that the internal configuration example of the search support system 100 according to the second embodiment has almost the same configuration as the internal configuration example of the search support system 100 according to the first embodiment, and therefore a description thereof will be omitted.

[0129] Next, referring to FIG. 11A and FIG. 11B, a person search procedure executed by the search support system 100 will be described. FIG. 11A is a sequence diagram showing an example of a person search procedure of the search support system 100 according to the first embodiment. FIG. 11B is a diagram explaining an example of various data registered in the database DB1 in the example of a person search procedure of the search support system 100 according to the second embodiment. Note that the sequence diagram shown in FIG. 11A is a diagram specifically explaining a search procedure based on each of two search condition examples input in the processing of step St68 and step St73 in order to make the search procedure executed by the server S1 in the first embodiment easier to understand. Note that each of the two search condition examples is merely an example and needless to say is not limited thereto.

[0130] In addition, in order to make it easier to understand the search procedure executed by the server S1 in this embodiment 1, the sequence diagram shown in FIG. 11A shows an example in which all of the best shot images are black and white images captured during the nighttime hours, but each of the best shot images may also be a color image captured during the daytime hours.

[0131] Each of the multiple cameras CM1, ..., CMN detects a person as a target based on a captured image of the monitoring area (St61). Each of the multiple cameras CM1, ..., CMN selects a best shot image for each person as a detected target, and performs a process of determining whether or not the face of the person as a target is captured in the best shot image based on the selected best shot image, such as a process of determining whether or not the face of the person as a target is captured in the best shot image, a process of extracting the feature amount of the target (person), and a process of generating image color information of the best shot image. Each of the multiple cameras CM1, ..., CMN generates metadata that associates the face detection information, the information on the feature amount of the target, the face detection information, and the image color information.

[0132] Each of the cameras CM1, ..., CMN generates detection data in which the generated metadata, the best shot image of the person, and camera information that can identify the camera are associated with each other, and transmits the detection data to the server S1 (St62). Note that the best shot image of the person "person image No. 1" transmitted to the server S1 in step St62 is a black and white image captured during the nighttime, and an example is shown in which the gender "male", which is attribute information of the person, and the image color information "FALSE" are associated as information on the feature amount of the object. Also, the image color information "FALSE" here indicates that the best shot image "person image No. 1" is a black and white image. Similarly, "no face" indicates that the face of the person was not detected from the best shot image. Note that "no face" may indicate that face detection information, which is information indicating that the face of the person was detected from the best shot image, is not included.

[0133] The server S1 stores (registers) the best shot image "Portrait Image No. 1" transmitted from each of the multiple cameras CM1, . . . , CMN in the database DB1 (St63).

[0134] Each of the cameras CM1, ..., CMN detects a person as an object based on the captured image of the monitoring area (see the process of step St61 within the dashed line shown in FIG. 11A). Each of the cameras CM1, ..., CMN generates detection data in which the generated metadata, the best shot image of the person, and camera information that can identify the camera are associated with each other, and transmits the detection data to the server S1 (St64). Note that the best shot image of the person "person image No. 35" transmitted to the server S1 in step St64 is a black and white image captured during the nighttime, and shows an example in which the person's attribute information, gender "male", image color information "FALSE", and face detection information are associated as information on the feature amount of the object. Also, the image color information "FALSE" here indicates that the best shot image "person image No. 35" is a black and white image. Similarly, face "present" indicates that face detection information, which is information indicating that a person's face has been detected from the best shot image, is included.

[0135] The server S1 stores (registers) the best shot image "Portrait Image No. 35" transmitted from each of the multiple cameras CM1, . . . , CMN in the database DB1 (St65).

[0136] Similarly, each of the cameras CM1, ..., CMN detects a person as an object based on the captured image of the monitoring area (see the process of step St61 within the dashed line shown in FIG. 11A). Each of the cameras CM1, ..., CMN generates detection data in which the generated metadata, the best shot image of the person, and camera information that can identify the camera are associated with each other, and transmits the detection data to the server S1 (St66). Note that the best shot image of the person "person image No. 1000" transmitted to the server S1 in step St66 is a black and white image captured during the nighttime, and shows an example in which the gender "male", which is attribute information of the person, image color information "FALSE", and face detection information are associated as information on the feature amount of the object. Also, the image color information "FALSE" here indicates that the best shot image "person image No. 1000" is a black and white image. Similarly, face "present" indicates that face detection information, which is information indicating that a person's face has been detected from the best shot image, is included.

[0137] The server S1 stores (registers) the best shot image "Portrait Image No. 1000" transmitted from each of the multiple cameras CM1, . . . , CMN in the database DB1 (St67).

[0138] Through the processes of steps St61 to St67 described above, the database DB1 stores (registers) the best shot image number ("No." shown in FIG. 11B), the person's gender information "male", the best shot image image color information "TRUE" or "FALSE", the face detection information "yes" or "no", and the 1000 best shot images in association with each other. It goes without saying that each of the best shot images shown in FIG. 11A and FIG. 11B and the metadata associated with each best shot image (e.g., face detection information, person's feature amount, image color information, etc.) are merely examples and are not limited thereto. In the following explanation of the processes of steps St68 to St77, in order to make the explanation easier to understand, a specific explanation will be given of a procedure for searching for best shot images that satisfy a search condition using each of the 1000 best shot images registered in the database DB1 shown in FIG. 11B. In addition, in Figures 11A and 11B, the best shot images corresponding to numbers "No. 3" to "No. 34" and numbers "No. 36" to "No. 999" respectively have person attribute information with gender "male", image color information "FALSE", and face detection information "none", but explanation and illustration are omitted.

[0139] The terminal device P1 accepts an input (setting) operation of the search conditions by the user through the input unit 24 (St68). Here, as an example of the search conditions set in step St68 shown in Fig. 11A, the search condition "Recognizable face only" is not set (disabled), and the gender of the person is "male" as a condition related to the feature amount of the object. The terminal device P1 transmits the set search conditions (gender of the person is "male") to the server S1 (St69).

[0140] Based on the search conditions transmitted from the terminal device P1, the server S1 refers to the feature amount (here, person attribute information) of the object corresponding to each of the multiple best shot images stored (registered) in the database DB1, and searches for person images (i.e., best shot images) that satisfy the search conditions (St70). Here, the server S1 in the example shown in FIG. 11A compares the metadata associated with each of the 1000 best shot images registered in the database DB1 with the search conditions (specifically, the person's gender is "male"), and searches for person images (best shot images) that are determined to satisfy the search conditions. The server S1 generates search result data based on the person images (best shot images) that are determined to satisfy the search conditions, and transmits the generated search result data (here, each of the 1000 best shot images corresponding to the numbers "No. 1" to "No. 1000") to the terminal device P1 (St71).

[0141] The terminal device P1 displays the search result data (that is, each of the 1000 best shot images corresponding to each of the numbers "No. 1" to "No. 1000") transmitted from the server S1 on the monitor 23 (St72).

[0142] The terminal device P1 also accepts an input (setting) operation of search conditions by the user through the input unit 24 (St73). As an example of the search conditions set in step St73 shown in Fig. 11A, the search condition "Recognizable face only" is set (enabled) and the gender of the person is "male" as a condition related to the feature amount of the object. The terminal device P1 transmits the set search conditions (there is face detection information of the person and the gender of the person is "male") to the server S1 (St74).

[0143] Based on the search conditions transmitted from the terminal device P1, the server S1 refers to the feature amount (here, person attribute information) of the object corresponding to each of the multiple best shot images stored (registered) in the database DB1, and searches for a person image (i.e., best shot image) that satisfies the search conditions (St75). Here, the server S1 in the example shown in FIG. 11A compares the metadata associated with each of the 1000 best shot images registered in the database DB1 with the search conditions (specifically, there is face detection information of the person and the gender of the person is "male"), and searches for a person image (best shot image) that is determined to satisfy the search conditions. The server S1 generates search result data based on the person image (best shot image) that is determined to satisfy the search conditions, and transmits the generated search result data (here, one best shot image corresponding to the number "No. 35") to the terminal device P1 (St76).

[0144] The terminal device P1 displays the search result data (that is, the best shot image corresponding to the number "No. 35") transmitted from the server S1 on the monitor 23 (St77).

[0145] As described above, the search support system 100 according to the first embodiment determines whether or not to exclude best shot images in which a person's face is not usable for face authentication (i.e., best shot images to which face detection information is not associated) from the search target by disabling or enabling the search condition "Recognizable face only" in a search for best shot images of a person using only black and white images captured at night. In this way, when the search condition "Recognizable face only" is enabled, the search support system 100 can output search results excluding best shot images in which a person's face is not usable for face authentication (i.e., best shot images to which face detection information is not associated). In this way, the search support system 100 can search for and output best shot images in which a person satisfying the search condition set by the user is captured among the best shot images in which the face of the person is determined to be identifiable.

[0146] Next, the search result screens SC7 and SC8 displayed on the terminal device P1 will be described with reference to Fig. 12 and Fig. 13. Fig. 12 is a diagram for explaining an example of the search result screen SC7 of people including black and white images. Fig. 13 is a diagram for explaining an example of the search result screen SC8 of people excluding black and white images. It goes without saying that the search result screens SC7 and SC8 shown in Fig. 12 and Fig. 13 are merely examples and are not limited thereto.

[0147] 12 and 13 show an example including input fields for search conditions related to the image capture date and time, face detection information, and image color information, but these search conditions may be set on the search condition setting screen SC1 (see FIG. 2). Furthermore, on the search result screens SC7 and SC8 shown in FIG. 12 and 13, search conditions corresponding to various setting items shown on the search condition setting screen SC1 (see FIG. 2) may be set on "Search Filter". Specifically, when "Search Filter" is selected (pressed) by a user operation on each of the search result screens SC7 and SC8, the terminal device P1 may display a setting field (not shown) in which search conditions corresponding to various setting items shown on the search condition setting screen SC1 (see FIG. 2) can be set and accept the input of search conditions based on the user operation, or may transition to the search condition setting screen SC1 (see FIG. 2) and accept the input of search conditions based on the user operation.

[0148] 12 is generated by the terminal device P1 based on the search result data transmitted from the server S1, and is displayed on the monitor 23. Specifically, the search result screen SC7 is generated to include an imaging date and time setting field DT71, a person search condition field PT71, a search button BT71, and a search result display area AR71.

[0149] The imaging date and time setting field DT71 accepts input operations by the user regarding search conditions related to the imaging date and time or the period of imaging dates and times when the best shot images were captured as search conditions. The terminal device P1 sets the search conditions based on the imaging date and time information input in the imaging start date and time DT72 and the imaging end date and time DT73. In the example shown in FIG. 12, the terminal device P1 sets search conditions to search for best shot images from "3 / 16 / 2020 7:40:47 AM" input in the imaging start date and time DT72 to "3 / 21 / 2020 7:40:47 AM" input in the imaging end date and time DT73.

[0150] The person search condition field PT71 accepts an input operation by the user to set the search condition "Recognizable face only" and the search condition "Color image only" related to the target person. The terminal device P1 sets the search condition selected (pressed) by the user operation. In the example shown in FIG. 12, the terminal device P1 sets a search condition that disables the search condition "Recognizable face only" and the search condition "Color image only".

[0151] The search button BT71 is a button for requesting the server S1 to perform a search process based on the search conditions set in the image capture date and time setting field DT71 and the person search condition field PT71. When the search button BT71 is pressed (selected) by the user, the terminal device P1 generates the search conditions set in the image capture date and time setting field DT71 and the person search condition field PT71, respectively, and a control command for requesting a search based on the search conditions, and transmits the control command to the server S1.

[0152] The search result display area AR71 displays a list of best shot images included in the search result data searched and transmitted by the server S1 based on the search conditions set in the shooting date and time setting field DT71 and the person search condition field PT71, respectively.

[0153] The search result display area AR71 shown in Fig. 12 displays 18 best shot images as search results based on the search conditions set in the shooting date and time setting field DT71 and the person search condition field PT71. Note that in the search result display area AR71 shown in Fig. 12, each of the 12 best shot images surrounded by a solid line frame is a best shot image associated with face detection information (i.e., a best shot image in which a person's face is captured so that it can be used for face recognition). Similarly, each of the six best shot images surrounded by a dashed line frame is a best shot image not associated with face detection information (i.e., a best shot image in which a person's face is captured so that it can be used for face recognition).

[0154] 13 is generated by the terminal device P1 based on the search result data transmitted from the server S1, and is displayed on the monitor 23. Specifically, the search result screen SC8 is generated to include an imaging date and time setting field DT81, a person search condition field PT81, a search button BT81, and a search result display area AR81.

[0155] The imaging date and time setting field DT81 accepts input operations by the user regarding search conditions related to the imaging date and time or the period of imaging dates and times when the best shot images were captured as search conditions. The terminal device P1 sets the search conditions based on the imaging date and time information input in the imaging start date and time DT82 and the imaging end date and time DT83. In the example shown in FIG. 13, the terminal device P1 sets the search conditions to search for best shot images from "3 / 16 / 2020 7:40:47 AM" input in the imaging start date and time DT82 to "3 / 21 / 2020 7:40:47 AM" input in the imaging end date and time DT83.

[0156] The person search condition field PT81 accepts an input operation by the user to set the search condition "Recognizable face only" and the search condition "Color image only" related to the target person. The terminal device P1 sets the search condition selected (pressed) by the user operation. In the example shown in FIG. 13, the terminal device P1 sets the search condition that enables the search condition "Recognizable face only" and disables the search condition "Color image only."

[0157] The search button BT81 is a button for requesting the server S1 to perform search processing based on the search conditions set in the image capture date and time setting field DT81 and the person search condition field PT81. When the search button BT81 is pressed (selected) by the user, the terminal device P1 generates the search conditions set in the image capture date and time setting field DT81 and the person search condition field PT81, respectively, and a control command for requesting a search based on the search conditions, and transmits the control command to the server S1.

[0158] The search result display area AR81 displays a list of best shot images included in the search result data searched and transmitted by the server S1 based on the search conditions set in the shooting date and time setting field DT81 and the person search condition field PT81, respectively.

[0159] The search result display area AR81 shown in Fig. 13 displays each of the 12 best shot images as a search result based on the search conditions set in the shooting date and time setting field DT81 and the person search condition field PT81. Note that in the search result display area AR81 shown in Fig. 13, each of the 12 best shot images surrounded by a solid line frame is a best shot image associated with face detection information (i.e., a best shot image in which a person's face is captured in a manner that can be used for face recognition).

[0160] As described above, the search support system 100 according to the first embodiment determines whether or not to exclude best shot images in which a person's face is not visible in a manner usable by face authentication (i.e., best shot images in which face detection information is not associated) from search targets by disabling or enabling the search condition "Recognizable face only". In this way, when the search condition "Recognizable face only" is enabled, the search support system 100 can output search results excluding best shot images in which a person's face is not visible in a manner usable by face authentication (i.e., best shot images in which face detection information is not associated). In this way, the search support system 100 can search for and output best shot images in which a person satisfying the search condition set by the user is captured among the best shot images in which the person's face is determined to be identifiable.

[0161] As described above, the search support system 100 according to the modification of the first embodiment includes at least one camera CM1, ..., CMN for capturing an image of an object, and a server S1 capable of communicating with the cameras CM1, ..., CMN. The cameras CM1, ..., CMN transmit captured images (i.e., best shot images) of the object and image color information indicating whether the captured image is a black-and-white image or a color image to the server S1. The server S1 associates the captured images with the image color information and stores them in a database DB1, determines whether a search condition for captured images set based on a user operation includes at least one color condition of white, black, or gray, and, if it determines that the search condition includes a color condition, removes captured images associated with image color information indicating a black-and-white image from all captured images stored in the database DB1 from the search target, generates and outputs search results including captured images that satisfy the search condition, and, if it determines that the search condition does not include a color condition, generates and outputs search results including captured images that satisfy the search condition from all captured images stored in the database DB1.

[0162] As a result, when the search conditions include a specific color such as white, black, or gray that is detectable from a black-and-white image, the search support system 100 according to the variation of the first embodiment can perform search processing by excluding best shot images whose image color information is black-and-white images from the search targets, regardless of whether the search condition "Color image only" is set.

[0163] As described above, in the search support system 100 according to the first and second embodiments, the server S1 further judges whether the color condition and the search condition "Color image only" (one example of a first search condition) for searching captured images of color images among all captured images stored in the database DB1 are included in the search condition (i.e., whether the search condition "Color image only" or "Color image only" is valid), and if it is judged that the color condition and the search condition "Color image only" are included in the search condition, the server S1 executes a search for captured images that satisfy the search condition by excluding captured images associated with image color information indicating black and white images among all captured images stored in the database. As a result, when the search condition "Color image only" is validated, the search support system 100 according to the first and second embodiments can output a search result excluding best shot images that are not color images (i.e., best shot images whose image color information is black and white images). Therefore, the search support system 100 can distinguish between information on color features extracted from color images (e.g., white, black, gray, etc.) and information on color features extracted from monochrome images (e.g., white, black, gray, etc.), and can output search results that are more suitable for the search conditions.

[0164] As described above, in the search support system 100 according to the first and second embodiments, the server S1 further determines whether or not the search condition includes the color condition and the search condition "Recognizable face only" (an example of a second search condition) for searching captured images in which the face of a person, which is a target, is captured to a degree suitable for face recognition among the captured images stored in the database and associated with image color information indicating a black-and-white image, and if it determines that the color condition and the search condition "Recognizable face only" are included in the search condition (i.e., the search condition "Recognizable face only" is valid), it executes a search for captured images that satisfy the search condition among the captured images associated with image color information indicating a black-and-white image among all the captured images stored in the database. As a result, when the search condition "Recognizable face only" is enabled, the search support system 100 according to the second embodiment can output a search result excluding best shot images in which a person's face is not shown in a manner that can be used for face recognition (i.e., best shot images to which face detection information is not associated).

[0165] As described above, the black-and-white images in the search support system 100 according to the first embodiment, the modified example of the first embodiment, and the second embodiment are images captured at night. As a result, when a search condition includes a predetermined color such as white, black, or gray that is detectable from a black-and-white image, the search support system 100 according to the first embodiment, the modified example of the first embodiment, and the second embodiment can perform search processing by excluding best shot images that are black-and-white images captured at night from search targets.

[0166] As described above, the color images in the search support system 100 according to the first embodiment, the modified example of the first embodiment, and the second embodiment are images captured during the day. As a result, when a search condition includes a predetermined color such as white, black, or gray that is detectable from a black-and-white image, the search support system 100 according to the first embodiment, the modified example of the first embodiment, and the second embodiment can execute a search process so as not to exclude best shot images, which are color images captured during the day, from the search target.

[0167] As described above, the server S1 in the search support system 100 according to the first embodiment, the modified example of the first embodiment, and the second embodiment displays a screen on the terminal that allows the user to specify the search criterion "Color image only" (an example of a first search criterion), and accepts the search criterion "Color image only" based on a user operation on the search criterion setting screens SC1 and SC2 (examples of screens). This allows the search support system 100 according to the first embodiment, the modified example of the first embodiment, and the second embodiment to accept a user operation for enabling or disabling the search criterion "Color image only".

[0168] As described above, the server S1 in the search support system 100 according to the first embodiment, the modified example of the first embodiment, and the second embodiment displays a screen on the terminal that allows the user to specify the search criterion "Recognizable face only" (an example of a second search criterion), and accepts the search criterion "Recognizable face only" based on a user operation on the search criterion setting screen SC1 (an example of a screen). This allows the search support system 100 according to the first embodiment, the modified example of the first embodiment, and the second embodiment to accept a user operation for enabling or disabling the search criterion "Recognizable face only".

[0169] Although various embodiments have been described above with reference to the drawings, it goes without saying that the present disclosure is not limited to such examples. It is clear that a person skilled in the art can conceive of various modifications, corrections, substitutions, additions, deletions, and equivalents within the scope of the claims, and it is understood that these also naturally belong to the technical scope of the present disclosure. In addition, the components in the various embodiments described above may be arbitrarily combined within the scope of the invention. [Industrial Applicability]

[0170] The present disclosure is useful as a search support system, a search support method, and a search support program that more appropriately searches for a search target desired by a user from images captured by a camera and more efficiently supports surveillance work by the user. [Explanation of symbols]

[0171] 10,20 Communications Department 11,21 Processor 12,22 Memory 23 Monitor 24 Input section DB1 database CM1,CMN camera P1 Terminal Equipment S1 Server SC1, SC2 search condition setting screen SC3, SC4, SC5, SC6, SC7, SC8 Search results screen

Claims

1. At least one camera for capturing an image of an object; a server capable of communicating with the camera; The camera includes: Transmitting a captured image of the object and image color information indicating whether the captured image is a black-and-white image or a color image to the server; The server, storing the captured image and the image color information in a database in association with each other; determining whether or not a search condition for the captured image set based on a user operation includes at least one color condition of white, black, or gray; when it is determined that the color condition is included in the search conditions, a captured image to which the image color information indicating the black-and-white image is associated is excluded from all the captured images stored in the database from the search target, and a search result including captured images that satisfy the search conditions is generated and output; if it is determined that the color condition is not included in the search conditions, a search result including the captured images that satisfy the search conditions among all the captured images stored in the database is generated and output. Search support system.

2. The black-and-white image is an image captured at night. The search support system according to claim 1.

3. The color image is an image captured during the daytime. The search support system according to claim 1.

4. A search support method performed by a computer that is communicably connected to at least one camera that captures an object, comprising: a captured image of the object and image color information indicating whether the captured image is a black-and-white image or a color image are stored in a database in association with each other; determining whether or not a search condition for the captured image set based on a user operation includes at least one color condition of white, black, or gray; if it is determined that the color condition is included, then excluding captured images associated with the image color information indicating the black-and-white image from all the captured images stored in the database from the search target, and generating and outputting search results including captured images that satisfy the search condition; if it is determined that the color condition is not included, a search result including a captured image that satisfies the search condition among all the captured images stored in the database is generated and output. Search aid methods.

5. A server, which is a computer connected to at least one camera that captures an image of an object so as to be capable of communicating with the server, storing the captured image of the object in a database in association with image color information indicating whether the captured image is a black-and-white image or a color image; determining whether or not at least one color condition of white, black, or gray is included in the search conditions for the captured image set based on a user operation; a step of excluding captured images associated with the image color information indicating the black-and-white image from all the captured images stored in the database when it is determined that the color condition is included, and generating and outputting a search result including captured images that satisfy the search condition; generating and outputting a search result including captured images that satisfy the search condition among all the captured images stored in the database when it is determined that the color condition is not included; Search aid program.

Images