Landscape analysis support device and landscape analysis support program

Abstract

To provide a landscape analysis support device and a landscape analysis support program which allow a user to grasp a basis of a subjective evaluation result about a landscape to a region being an analysis object.SOLUTION: A landscape analysis support device 10 using a landscape analysis support model 13D with image information indicating a photographed image obtained by imaging a region being an analysis object as input information and subjective evaluation information indicating a subjective evaluation about a landscape to the photographed image and objective evaluation information indicating an objective evaluation about the landscape as output information, comprises: an acquisition unit 11B which acquires the image information; a derivation unit 11C which derives the subjective evaluation information and the objective evaluation information by inputting the image information acquired by the acquisition unit 11B to the landscape analysis support model 13D; and a presentation unit 11D which presents total evaluation information being information indicating both of the subjective evaluation information and the objective evaluation information derived by the derivation unit 11C.SELECTED DRAWING: Figure 4

Description

[Technical field]

[0001] The present invention relates to a landscape analysis support device and a landscape analysis support program. [Background technology]

[0002] Conventionally, there have been the following techniques for evaluating images.

[0003] Patent Document 1 discloses an evaluation system including a terminal having a first display means and a receiving means, and a control device. In this evaluation system, the display means of the terminal displays a first image including an evaluation target based on first image data, and the receiving means of the terminal receives an evaluator's designation of an attention part in the first image displayed on the first display means and an input of evaluation information for the attention part. In addition, in this evaluation system, the control device generates attention distribution data representing an attention degree for each position in the first image based on a plurality of reception information in which information related to the designation of the attention part and the evaluation information are associated, generates second image data based on the first image and the attention distribution data, and displays the second image on the second display means as a second image. In addition, this evaluation system determines an attention degree for each position in the first image based on information related to a plurality of the attention parts included in the plurality of reception information, and generates the attention distribution data according to the attention degree for each position.

[0004] Patent Document 2 discloses a design production support device for evaluating the impression of a document design. This design production support device includes a storage means for storing a plurality of impression expression databases including different groups of options expressing the impression of the document, and an impression evaluation database in which impression information expressing the impression felt by a person who sees the document is associated with the options included in the plurality of impression expression databases. This design production support device also includes an impression information acquisition means for having a user select at least one option from each of the plurality of impression expression databases that matches the target impression of the document design production. This design production support device also includes a target impression information setting means for referring to the impression evaluation database, extracting impression information associated with the options selected from the plurality of impression expression databases, and setting at least one of the extracted impression information as target impression information expressing the target impression of the document design production. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2018-136604 A [Patent Document 2] JP 2007-279923 A Summary of the Invention [Problem to be solved by the invention]

[0006] Incidentally, in the past, it was possible to use machine learning models to obtain subjective evaluation results, such as "reassuring" or "lively," as an evaluation of the landscape shown in a captured image, but it was not possible to understand the basis for this subjective evaluation.

[0007] The techniques disclosed in the above Patent Documents 1 and 2 do not take the above-mentioned basis into consideration, and therefore cannot solve this problem.

[0008] The present disclosure has been made in consideration of the above circumstances, and aims to provide a landscape analysis support device and a landscape analysis support program that can grasp the basis of subjective evaluation results regarding the landscape for the area being analyzed. [Means for solving the problem]

[0009] The landscape analysis support device according to the present invention described in claim 1 is a landscape analysis support device using a landscape analysis support model in which image information indicating a captured image obtained by capturing an area to be analyzed is used as input information, and subjective evaluation information indicating a subjective evaluation of the landscape for the captured image and objective evaluation information indicating an objective evaluation of the landscape are used as output information, the landscape analysis support device comprising: an acquisition unit that acquires the image information; a derivation unit that inputs the image information acquired by the acquisition unit to the landscape analysis support model to derive the subjective evaluation information and the objective evaluation information; and a presentation unit that presents comprehensive evaluation information which is information indicating both the subjective evaluation information and the objective evaluation information derived by the derivation unit. The acquisition unit acquires a plurality of pieces of image information each indicating a photographed image obtained by photographing the area to be analyzed, the derivation unit derives the subjective evaluation information and the objective evaluation information for each of the acquired plurality of pieces of image information, and the presentation unit presents the overall evaluation information by displaying the evaluation frequency of each of the derived plurality of pieces of subjective evaluation information and objective evaluation information as a graph. .

[0010] According to the landscape analysis support device of the present invention described in claim 1, image information indicating a captured image is used as input information, and subjective evaluation information indicating a subjective evaluation of the landscape for the captured image and objective evaluation information indicating an objective evaluation of the landscape are used as output information.By inputting the acquired image information into a landscape analysis support model, subjective evaluation information and objective evaluation information are derived, and comprehensive evaluation information, which is information indicating both the derived subjective evaluation information and objective evaluation information, is presented.Since the above-mentioned objective evaluation has a large influence on the subjective evaluation and is often the basis for the subjective evaluation, it is possible to grasp the basis for the subjective evaluation result regarding the landscape for the area to be analyzed.

[0011] The landscape analysis support device of the present invention as described in claim 2 is a landscape analysis support device as described in claim 1, wherein the subjective evaluation information includes at least one of information regarding a sense of security, information regarding a sense of liveliness, and information regarding a sense of attractiveness.

[0012] According to the landscape analysis support device of the present invention as described in claim 2, by making the subjective evaluation information include at least one of information relating to a sense of security, information relating to a sense of liveliness, and information relating to a sense of attractiveness, it is possible to grasp the basis for the evaluation result indicated by the information contained in the subjective evaluation information.

[0013] The landscape analysis support device of the present invention as described in claim 3 is a landscape analysis support device as described in claim 1 or claim 2, wherein the objective evaluation information includes at least one of elements and features related to the corresponding subjective evaluation information.

[0014] According to the landscape analysis support device of the present invention as described in claim 3, by making the objective evaluation information include at least one of the elements and features related to the corresponding subjective evaluation information, it is possible to more specifically grasp the basis for the evaluation results indicated by the subjective evaluation information.

[0015] The landscape analysis support device of the present invention as described in claim 4 is a landscape analysis support device as described in any one of claims 1 to 3, further comprising a learning image acquisition unit that acquires learning image information to be used for learning, and the landscape analysis support model is machine-learned using the learning image information acquired by the learning image acquisition unit as input information and the subjective evaluation information and the objective evaluation information corresponding to the learning image information as output information.

[0016] According to the landscape analysis support device of the present invention as described in claim 4, while acquiring learning image information to be used for learning, the landscape analysis support model can be constructed more easily by machine learning the landscape analysis support model using the acquired learning image information as input information and the subjective evaluation information and objective evaluation information corresponding to the learning image information as output information. The landscape analysis support device of the present invention as described in claim 5 is the landscape analysis support device as described in claim 4, wherein the input information used when performing the machine learning is image information obtained by cutting out from the learning image information an area input by a user as an area that serves as the basis for feeling the subjective evaluation indicated by the subjective evaluation information used in the machine learning. The landscape analysis support device of the present invention as described in claim 6 is a landscape analysis support device as described in claim 4, wherein the objective evaluation information used in the machine learning is objectively evaluated by a user. The landscape analysis support device of the present invention as described in claim 7 is the landscape analysis support device as described in claim 4, wherein the subjective evaluation information and the objective evaluation information used in the machine learning are information input by the user while displaying multiple pieces of pre-registered learning image information and allowing the user to specify a base area. The landscape analysis support device of the present invention as described in claim 8 is the landscape analysis support device as described in claim 4, wherein at least one of the subjective evaluation information and the objective evaluation information used in the machine learning is information input by automatically identifying an element that a user is paying attention to in a captured image represented by the learning image information by eye gaze measurement. The landscape analysis support device of the present invention as described in claim 9 is the landscape analysis support device as described in claim 1, wherein the image information is image information indicating captured images cut out at predetermined angles from images obtained by photographing the area with a 360-degree camera, or image information obtained by photographing the area in one direction at different points.

[0017] Claim 10 The landscape analysis support program according to the present invention described above is a landscape analysis support program using a landscape analysis support model in which image information showing a captured image obtained by capturing an image of an area to be analyzed is used as input information, and subjective evaluation information showing a subjective evaluation of the landscape for the captured image and objective evaluation information showing an objective evaluation of the landscape are used as output information, and the program obtains the image information, inputs the obtained image information into the landscape analysis support model to derive the subjective evaluation information and the objective evaluation information, and presents comprehensive evaluation information which is information showing both the derived subjective evaluation information and the derived objective evaluation information. a process for obtaining a plurality of pieces of image information each indicating an image obtained by photographing the area to be analyzed, deriving the subjective evaluation information and the objective evaluation information for each of the obtained plurality of pieces of image information, and presenting the overall evaluation information by displaying the evaluation frequency of each of the derived plurality of pieces of subjective evaluation information and objective evaluation information as a graph, , causing the computer to execute the processing.

[0018] Claim 10 According to the landscape analysis support program of the present invention described above, image information indicating a captured image is used as input information, and subjective evaluation information indicating a subjective evaluation of the landscape for the captured image and objective evaluation information indicating an objective evaluation of the landscape are used as output information. By inputting the acquired image information into a landscape analysis support model, subjective evaluation information and objective evaluation information are derived, and comprehensive evaluation information, which is information indicating both the derived subjective evaluation information and objective evaluation information, is presented. Since the above objective evaluation has a large influence on the subjective evaluation and is often the basis for the subjective evaluation, it is possible to grasp the basis for the subjective evaluation result regarding the landscape for the area to be analyzed. Effect of the Invention

[0019] As described above, according to the present invention, it is possible to grasp the basis for subjective evaluation results regarding the scenery of an area to be analyzed. [Brief description of the drawings]

[0020] [Figure 1] 1 is a block diagram showing an example of a configuration of a landscape analysis support system according to an embodiment. [Diagram 2] 1 is a block diagram showing an example of a hardware configuration of a landscape analysis support device according to an embodiment; [Diagram 3] 1 is a block diagram showing an example of a functional configuration of a landscape analysis support device according to an embodiment when learning a landscape analysis support model. FIG. [Figure 4] 1 is a block diagram showing an example of a functional configuration of a landscape analysis support model in operation of a landscape analysis support device according to an embodiment. FIG. [Diagram 5] FIG. 2 is a schematic diagram showing an example of a configuration of a learning information database according to the embodiment. [Figure 6] FIG. 2 is a schematic diagram showing an example of a configuration of an image information database according to the embodiment. [Figure 7] FIG. 2 is a schematic diagram showing an example of a configuration of an evaluation result information database according to the embodiment. [Figure 8] 11 is a flowchart illustrating an example of an evaluation input process according to the embodiment. [Figure 9] FIG. 13 is a front view showing an example of a configuration of an evaluation input screen according to the embodiment. [Figure 10] 10 is a flowchart illustrating an example of a learning process according to the embodiment. [Figure 11] 1 is a flowchart showing an example of a landscape analysis support process according to the embodiment. [Figure 12] FIG. 13 is a front view showing an example of a configuration of an initial information input screen according to the embodiment. [Figure 13] FIG. 13 is a front view showing an example of a configuration of an evaluation result screen according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0021] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

[0022] First, the configuration of a landscape analysis support system 1 according to this embodiment will be described with reference to Fig. 1. Fig. 1 is a block diagram showing an example of the configuration of the landscape analysis support system 1 according to this embodiment.

[0023] As shown in Fig. 1, the landscape analysis support system 1 according to this embodiment includes a landscape analysis support device 10 that plays a central role in this system, and an information storage device 90. The landscape analysis support device 10 according to this embodiment inputs image information indicating a captured image obtained by capturing an area to be analyzed into a pre-constructed landscape analysis support model, and derives subjective evaluation information indicating a subjective evaluation of the landscape for the captured image, and objective evaluation information indicating an objective evaluation of the landscape. The information storage device 90 according to this embodiment stores various information handled by the landscape analysis support device 10.

[0024] The information storage device 90 according to this embodiment includes a non-volatile memory unit 92. The memory unit 92 is realized by a hard disk drive (HDD), a solid state drive (SSD), a flash memory, or the like. A learning information database 92A, an image information database 92B, and an evaluation result information database 92C are stored in the memory unit 92 as a storage medium. The learning information database 92A, the image information database 92B, and the evaluation result information database 92C will be described in detail later.

[0025] The landscape analysis support device 10 and the information storage device 90 are connected via a network N, and the landscape analysis support device 10 can communicate with the information storage device 90 via the network N. In this embodiment, an in-company communication line such as a LAN (Local Area Network) or a WAN (Wide Area Network) is applied as the network N, but the present invention is not limited to this form. For example, a public communication line such as the Internet or a telephone line may be applied as the network N, or a combination of these in-company communication lines and public communication lines may be applied. In this embodiment, a wired communication line is applied as the network N, but the present invention is not limited to this form, and a wireless communication line may be applied, or a combination of wired and wireless communication lines may be applied.

[0026] Next, the hardware configuration of the landscape analysis support device 10 according to this embodiment will be described with reference to Fig. 2. Fig. 2 is a block diagram showing an example of the hardware configuration of the landscape analysis support device 10 according to this embodiment. Examples of the landscape analysis support device 10 include various computers such as a personal computer and a server computer.

[0027] The landscape analysis support device 10 according to this embodiment includes a CPU (Central Processing Unit) 11, a memory 12 as a temporary storage area, a non-volatile storage unit 13, an input unit 14 such as a keyboard and mouse, a display unit 15 such as a liquid crystal display, a medium reading and writing device (R / W) 16, and a communication interface (I / F) unit 18. The CPU 11, memory 12, storage unit 13, input unit 14, display unit 15, medium reading and writing device 16, and communication interface (I / F) unit 18 are connected to each other via a bus B. The medium reading and writing device 16 reads information written in a recording medium 17 and writes information to the recording medium 17.

[0028] The storage unit 13 is realized by an HDD, an SSD, a flash memory, or the like. The storage unit 13 as a storage medium stores an evaluation input program 13A, a learning program 13B, and a landscape analysis support program 13C. Each of the evaluation input program 13A, the learning program 13B, and the landscape analysis support program 13C is stored (installed) in the storage unit 13 by setting a recording medium 17 on which each of the programs is written in the medium reading and writing device 16, and the medium reading and writing device 16 reading each of the programs from the recording medium 17. The CPU 11 sequentially reads each of the evaluation input program 13A, the learning program 13B, and the landscape analysis support program 13C from the storage unit 13, expands them in the memory 12, and sequentially executes the processes of each of the programs.

[0029] The storage unit 13 also stores a landscape analysis support model 13D. As described above, the landscape analysis support model 13D according to this embodiment receives as input information image information (hereinafter simply referred to as "image information") showing a captured image obtained by capturing an image of an area to be analyzed. As described above, the landscape analysis support model 13D according to this embodiment receives as output information subjective evaluation information (hereinafter simply referred to as "subjective evaluation information") showing a subjective evaluation of the landscape in the captured image, and objective evaluation information (hereinafter simply referred to as "objective evaluation information") showing an objective evaluation of the landscape.

[0030] The landscape analysis support model 13D according to this embodiment is an AI (Artificial Intelligence) model using a CNN (Convolutional Neural Network), but is not limited thereto. Other machine learning models such as AI other than CNN may be applied as the landscape analysis support model 13D.

[0031] In this embodiment, the subjective evaluation information includes information on a sense of security, information on a sense of activity, and information on a sense of attractiveness, but is not limited thereto. For example, in addition to these pieces of information, information including other subjective information such as information on beauty, information on a sense of cleanliness, information on a sense of color, and information on a historical perspective may be used as the subjective evaluation information, and may include one or a combination of multiple pieces of information.

[0032] In addition, in the present embodiment, information including elements and features related to the corresponding subjective evaluation information is applied as the objective evaluation information, but the present invention is not limited to this. For example, information including only either the elements or the features may be used as the objective evaluation information.

[0033] Next, the functional configuration of the landscape analysis support device 10 according to this embodiment when learning the landscape analysis support model 13D will be described with reference to Fig. 3. Fig. 3 is a block diagram showing an example of the functional configuration of the landscape analysis support device 10 according to this embodiment when learning the landscape analysis support model 13D.

[0034] 3, the landscape analysis support device 10 during learning of the landscape analysis support model 13D includes a learning image acquisition unit 11A. The CPU 11 of the landscape analysis support device 10 executes the learning program 13B to function as the learning image acquisition unit 11A.

[0035] The learning image acquisition unit 11A according to this embodiment acquires learning image information used for learning (hereinafter simply referred to as "learning image information").

[0036] In this embodiment, the learning image information is acquired by reading it from a learning information database 92A (see also FIG. 5), which will be described later. However, the present invention is not limited to this embodiment, and image information on an unspecified number of landscapes posted on a social networking service (SNS) or the like may be acquired directly as learning image information via the communication I / F unit 18 or the like.

[0037] The landscape analysis support model 13D in this embodiment is machine-learned using the learning image information acquired by the learning image acquisition unit 11A as input information and the above-mentioned subjective evaluation information and objective evaluation information corresponding to the learning image information as output information.

[0038] Next, the functional configuration of the landscape analysis support device 10 according to this embodiment when the landscape analysis support model 13D is in operation will be described with reference to Fig. 4. Fig. 4 is a block diagram showing an example of the functional configuration of the landscape analysis support device 10 according to this embodiment when the landscape analysis support model 13D is in operation.

[0039] 4, the landscape analysis support device 10 during operation of the landscape analysis support model 13D includes an acquisition unit 11B, a derivation unit 11C, and a presentation unit 11D. The CPU 11 of the landscape analysis support device 10 executes the landscape analysis support program 13C to function as the acquisition unit 11B, the derivation unit 11C, and the presentation unit 11D.

[0040] The acquiring unit 11B according to this embodiment acquires image information (hereinafter simply referred to as "image information") indicating a captured image obtained by capturing an image of a region to be analyzed.

[0041] In this embodiment, the image information is acquired by reading it from an image information database 92B (see also FIG. 6), which will be described later. However, the present invention is not limited to this embodiment, and the image information may be one of a large number of image information related to unspecified landscapes posted on SNS or the like, and may be acquired directly via the communication I / F unit 18 or the like.

[0042] The derivation unit 11C according to this embodiment derives the subjective evaluation information and the objective evaluation information by inputting the image information acquired by the acquisition unit 11B into the landscape analysis support model 13D. The presentation unit 11D according to this embodiment presents comprehensive evaluation information (hereinafter simply referred to as "comprehensive evaluation information") which is information indicating both the subjective evaluation information and the objective evaluation information derived by the derivation unit 11C.

[0043] In this embodiment, the presenting unit 11D presents the overall evaluation information by displaying it on the display unit, but is not limited to this. For example, the overall evaluation information may be presented by sound generated by a sound generating device such as a speaker, or may be presented by printing it on an image forming device such as a printer.

[0044] Next, the learning information database 92A according to this embodiment will be described with reference to Fig. 5. Fig. 5 is a schematic diagram showing an example of the configuration of the learning information database 92A according to this embodiment. The learning information database 92A according to this embodiment is for storing information used in learning the landscape analysis support model 13D.

[0045] As shown in FIG. 5, a learning information database 92A according to this embodiment stores learning image ID (Identification), learning image information, subjective evaluation, objective evaluation, and designated area information in an associated manner.

[0046] The learning image ID is information that is assigned in advance as different information for each piece of learning image information in order to individually identify the learning image information, and the learning image information is information that indicates the learning image information itself.

[0047] In addition, the subjective evaluation is information indicating the result of a user's subjective evaluation of the image indicated by the corresponding learning image information, and the objective evaluation is information indicating the result of a user's objective evaluation of the image indicated by the corresponding learning image information.

[0048] In the example shown in Fig. 5, the subjective evaluation of the image indicated by the learning image information assigned with the learning image ID "L001" is "confident," and the objective evaluation is "the road is wide." Here, the "road width" in the objective evaluation corresponds to the above-mentioned "element," and "wide" corresponds to the above-mentioned "characteristic."

[0049] Furthermore, the specified area is information indicating an area specified by a user when performing an objective evaluation on an image indicated by the corresponding learning image information.

[0050] Next, the image information database 92B according to this embodiment will be described with reference to Fig. 6. Fig. 6 is a schematic diagram showing an example of the configuration of the image information database 92B according to this embodiment. The image information database 92B according to this embodiment is for storing image information to be analyzed.

[0051] As shown in FIG. 6, the image information database 92B according to this embodiment stores information such as district names, analytical image IDs, and analytical image information in association with each other.

[0052] The district name is information indicating the name of the district where photography was performed to obtain the corresponding analytical image information, the analytical image ID is information that is assigned in advance as different information for each piece of analytical image information in order to individually identify the corresponding analytical image information, and the analytical image information is information indicating the analytical image information itself.

[0053] Next, the evaluation result information database 92C according to this embodiment will be described with reference to Fig. 7. Fig. 7 is a schematic diagram showing an example of the configuration of the evaluation result information database 92C according to this embodiment. The evaluation result information database 92C according to this embodiment is for storing information indicating the results of each of the subjective evaluation and objective evaluation for the image to be analyzed.

[0054] As shown in FIG. 7, the evaluation result information database 92C according to this embodiment stores information on the analytical image ID, the subjective evaluation, and the objective evaluation in association with each other.

[0055] The analysis image ID is the same information as the analysis image ID in the image information database 92B, and the subjective evaluation and objective evaluation are information indicating the results of the subjective evaluation and the objective evaluation, respectively, for the image indicated by the corresponding analysis image information.

[0056] Next, the operation of the landscape analysis support device 10 according to this embodiment will be described with reference to FIGS.

[0057] First, the operation of the landscape analysis support device 10 when executing the evaluation input process according to this embodiment will be described with reference to Figures 8 and 9. Figure 8 is a flow chart showing an example of the evaluation input process according to this embodiment.

[0058] The CPU 11 of the landscape analysis support device 10 executes the evaluation input program 13A to execute the evaluation input process shown in Fig. 8. The evaluation input process shown in Fig. 8 is executed when a user inputs an instruction to start execution of the evaluation input program 13A via the input unit 14. Note that, in order to avoid confusion, a case will be described here in which the learning image ID and learning image information have already been registered in the learning information database 92A. Also, a case will be described here in which type information indicating the type, such as "comfortable" or "lively," to be the subject of the subjective evaluation is registered in advance in the storage unit 13.

[0059] In step 100 of FIG. 8, the CPU 11 reads the type information from the storage unit 13, and in step 102, the CPU 11 reads two pieces of learning image information (hereinafter, referred to as "a group of learning images to be processed") from the learning information database 92A.

[0060] In the present embodiment, as the group of learning images to be processed, any two pieces of image information are used that are not registered in the learning information database 92A for the information on subjective evaluation and objective evaluation, but the present invention is not limited to this. For example, two pieces of image information that are not registered in the learning information database 92A for the information on subjective evaluation and objective evaluation, and that were registered in the learning information database 92A in descending order of time, may be used as the group of learning images to be processed.

[0061] In step 104, CPU 11 controls display unit 15 to display an evaluation input screen of a predetermined configuration using the read type information and the group of learning images to be processed, and in step 106, CPU 11 waits until the specified information is input.

[0062] FIG. 9 shows an example of the configuration of the evaluation input screen according to the present embodiment. As shown in FIG. 9, the evaluation input screen according to the present embodiment displays a message urging the user to specify an image that gives one type of subjective evaluation in the read type information (in the example shown in FIG. 9, the evaluation is "feeling of security", hereinafter referred to as "processing target subjective evaluation"). Also, the evaluation input screen according to the present embodiment displays a message to enclose an element that is the basis for the processing target subjective evaluation with a square, and to input the name and characteristics of the element. Then, the evaluation input screen according to the present embodiment displays the image 15A1 and the image 15A2 indicated by the read processing target learning image group side by side, and displays an input area 15B for inputting the name and characteristics of the element.

[0063] 9 is displayed on the display unit 15, the user uses the input unit 14 to surround with a rectangle 15F an area that is the basis for the stronger subjective evaluation of the processing target, for the image in which the processing target subjective evaluation is felt to be stronger, between the displayed images 15A1 and 15A2. Then, the user uses the input unit 14 to input the names and characteristics of the above-mentioned elements into the corresponding input areas 15B, and then selects the end button 15G.

[0064] When the end button 15G is selected by the user, the determination in step is affirmative, and the process proceeds to step .

[0065] In step 108, CPU 11 stores the subjective evaluation of the object to be processed, the objective evaluation consisting of the name and characteristics of the element input by the user on the evaluation input screen, and each piece of information of the designated area indicating the area of ​​square 15F in the corresponding storage area of ​​learning information database 92A. Note that in this embodiment, the storage of the designated area is performed by storing two-dimensional coordinate values ​​indicating the positions of a pair of diagonal corners of the corresponding square 15F, but it goes without saying that this is not limited to this.

[0066] In step 110, CPU 11 determines whether the processing of steps 102 to 108 has been completed for all learning image information for which the subjective evaluation and objective evaluation information is not registered in the learning information database 92A, and if the determination is negative, the process returns to step 102, whereas if the determination is positive, the process ends the evaluation input process. When repeatedly executing steps 102 to 110, CPU 11 applies two combinations of learning image information for which the subjective evaluation and objective evaluation information is not registered in the learning information database 92A as a group of learning images to be processed. When repeatedly executing this process, CPU 11 applies the subjective evaluation that was not applied last time as the subjective evaluation to be processed.

[0067] By the above evaluation input process, a learning information database 92A as shown in FIG. 5 is constructed as an example.

[0068] Next, the operation of the landscape analysis support device 10 in training the landscape analysis support model 13D will be described with reference to Fig. 10. Fig. 10 is a flow chart showing an example of the training process according to this embodiment.

[0069] The CPU 11 of the landscape analysis support device 10 executes the learning program 13B, thereby executing the learning process shown in Fig. 10. The learning process shown in Fig. 10 is executed when a command to start the execution of the learning program 13B is input by the user via the input unit 14. In order to avoid confusion, the following description will be given for the case where the learning information database 92A has already been constructed.

[0070] 10, the CPU 11 reads out a set of learning image information, a subjective evaluation, an objective evaluation, and information on a designated area from the learning information database 92A. In step 202, the CPU 11 extracts image information of an area indicated by the read-out designated area from the read-out learning image information.

[0071] In step 204, the CPU 11 performs machine learning of the landscape analysis support model 13D using the cut-out image information as input information and the read-out information of the subjective evaluation and objective evaluation as output information (correct answer information). In step 206, the CPU 11 judges whether or not the machine learning in step 204 has been completed for all information stored in the learning information database 92A, and if the judgment is negative, the process returns to step 200, whereas if the judgment is positive, the learning process ends. When repeatedly executing the processes of steps 200 to 206, the CPU 11 makes information that has not been the learning target the learning target.

[0072] Through the above learning process, the scene analysis support model 13D is learned.

[0073] Next, the operation of the landscape analysis support device 10 when the landscape analysis support model 13D is operated will be described with reference to Fig. 11 to Fig. 13. Fig. 11 is a flowchart showing an example of the landscape analysis support process according to this embodiment.

[0074] The CPU 11 of the landscape analysis support device 10 executes the landscape analysis support program 13C to execute the landscape analysis support process shown in Fig. 11. The landscape analysis support process shown in Fig. 11 is executed when a command input for starting execution of the landscape analysis support program 13C is made by a user via the input unit 14. In order to avoid confusion, the following description will be given for the case where the learning of the landscape analysis support model 13D has been completed and the image information database 92B has already been constructed.

[0075] In step 300 of FIG. 11, the CPU 11 controls the display unit 15 to display an initial information input screen having a predetermined configuration, and in step 302, the CPU 11 waits until predetermined information is input.

[0076] An example of the configuration of an initial information input screen according to this embodiment is shown in Fig. 12. As shown in Fig. 12, the initial information input screen according to this embodiment displays a message prompting the user to input the name of a target district to be analyzed for landscape (hereinafter, referred to as "target district name"). Furthermore, the initial information input screen according to this embodiment displays an input area 15C for inputting the target district name.

[0077] When an initial information input screen shown in FIG. 12 is displayed on the display unit 15 as an example, the user uses the input unit 14 to input the name of the target area to be analyzed for landscape in the input area 15C, and then presses the finish button 15G.

[0078] When the end button 15G is selected by the user, the determination in step 302 is affirmative, and the process proceeds to step 304.

[0079] In step 304, the CPU 11 reads out from the image information database 92B any one pair of analytical image ID and analytical image information among the information corresponding to the target district indicated by the target district name. In step 306, the CPU 11 inputs the read analytical image information to the landscape analysis support model 13D.

[0080] In step 308, the CPU 11 acquires each piece of information on the subjective evaluation and the objective evaluation output from the landscape analysis support model 13D in response to the input of the analytical image information. In step 310, the CPU 11 stores each piece of information on the subjective evaluation and the objective evaluation in the evaluation result information database 92C in association with the corresponding analytical image ID.

[0081] In step 312, CPU 11 determines whether or not the above processing of steps 304 to 310 has been completed for all analytical image information of the target district indicated by the target district name registered in image information database 92B, and if the determination is negative, the process returns to step 304, whereas if the determination is positive, the process proceeds to step 314. When repeatedly executing the processing of steps 304 to 312, CPU 11 applies, as the processing target, any analytical image information that has not been the processing target up to that point.

[0082] By the above processing, an evaluation result information database 92C shown in FIG. 7 as an example is constructed for the target district corresponding to the target district name (hereinafter referred to as the "processing target district").

[0083] In step 314, CPU 11 reads out all of the subjective evaluation and objective evaluation information corresponding to the area to be processed from evaluation result information database 92C. In step 316, CPU 11 controls display unit 15 to display an evaluation result screen of a predetermined configuration using the read out subjective evaluation and objective evaluation information, and in step 318, CPU 11 waits until the predetermined information is input.

[0084] Fig. 13 shows an example of the configuration of the evaluation result screen according to this embodiment. As shown in Fig. 13, on the evaluation result screen according to this embodiment, for each piece of subjective evaluation and objective evaluation information that has been read out, the frequency of each evaluation is displayed as a radar chart 15D1 according to the content of the corresponding evaluation. This radar chart 15D1 is an example of the comprehensive evaluation information of the present invention. Also, on the evaluation result screen according to this embodiment, an image 15D2 indicated by the analytical image information corresponding to the processing target district is displayed.

[0085] As an example, in this embodiment, as shown in Fig. 13, captured images obtained by shooting with a 360-degree camera (hereinafter referred to as "360-degree images") are applied as the analytical image information. Therefore, as an example, the images indicated by the analytical image information registered in the image information database 92B shown in Fig. 6 are multiple captured images cut out from the 360-degree image at predetermined angles (for example, 5 degrees). However, this is not the only possible form, and the analytical image information registered in the image information database 92B may be in a form that applies image information obtained by shooting in one direction at different points in the corresponding target area.

[0086] Moreover, the evaluation result screen according to this embodiment displays a map image 15E including the area to be processed designated by the user. For this reason, the memory unit 13 of the landscape analysis support device 10 or the memory unit 92 of the information storage device 90 stores map information of the area that the landscape analysis support system 1 covers in advance.

[0087] In the evaluation result screen according to this embodiment, the above-mentioned radar chart 15D1 and image 15D2 are displayed in a balloon 15D indicating the processing target district on a map image 15E. Therefore, by referring to the evaluation result screen, the user can intuitively grasp the overall subjective evaluation of the processing target district and the overall objective evaluation that is the basis for the subjective evaluation, together with the location and the corresponding photographed image.

[0088] 13 is displayed on the display unit 15, the user understands the evaluation contents and then selects the end button 15G using the input unit 14. When the end button 15G is selected by the user, the landscape analysis support process ends.

[0089] As described above, the landscape analysis support device 10 according to the present embodiment is a landscape analysis support device 10 using a landscape analysis support model 13D in which image information showing a photographed image obtained by photographing an area to be analyzed is used as input information, and subjective evaluation information showing a subjective evaluation of the landscape for the photographed image and objective evaluation information showing an objective evaluation of the landscape are used as output information, and the device is equipped with an acquisition unit 11B for acquiring the image information, a derivation unit 11C for deriving the subjective evaluation information and the objective evaluation information by inputting the image information acquired by the acquisition unit 11B to the landscape analysis support model 13D, and a presentation unit 11D for presenting comprehensive evaluation information which is information showing both the subjective evaluation information and the objective evaluation information derived by the derivation unit 11C. Therefore, the objective evaluation has a large influence on the subjective evaluation and is often the basis for the subjective evaluation, so that the basis for the subjective evaluation result for the area to be analyzed can be grasped.

[0090] According to the present embodiment, the subjective evaluation information includes at least one of information related to a sense of security, information related to a sense of activity, and information related to a sense of attractiveness. Therefore, the basis of the evaluation result indicated by the information included in the subjective evaluation information can be understood.

[0091] Furthermore, according to the present embodiment, the objective evaluation information includes at least one of the elements and features related to the corresponding subjective evaluation information, so that the basis of the evaluation result indicated by the subjective evaluation information can be more specifically understood.

[0092] Furthermore, according to this embodiment, while acquiring learning image information to be used for learning, the landscape analysis support model 13D is machine-learned using the acquired learning image information as input information and using subjective evaluation information and objective evaluation information corresponding to the learning image information as output information, so that the landscape analysis support model 13D can be constructed more easily.

[0093] It goes without saying that the configurations of the various screens exemplified in the above embodiment are merely examples and may be modified. For example, the radar chart 15D1 shown in Fig. 13 may be in a form that displays the target information (information on each of the subjective evaluation and objective evaluation in the above embodiment) using other graphs such as a pie chart or a bar graph.

[0094] In the above embodiment, the objective evaluation is performed by a user, but the present invention is not limited to this. For example, if the elements and characteristics of the objective evaluation can be mechanically obtained from a captured image, such as "high green view rate" or "high sky view rate," the objective evaluation may be automatically derived by machine learning AI or the like.

[0095] In the above embodiment, the case where two learning images are displayed on the evaluation input screen has been described, but the present invention is not limited to this. For example, only one learning image may be displayed on the evaluation input screen, or three or more learning images may be displayed on the evaluation input screen.

[0096] In the above embodiment, the input of the evaluation result by the evaluation input process is performed by manual input via the input unit 14 using the evaluation input screen shown in Fig. 9 as an example, but the present invention is not limited to this. For example, software capable of line-of-sight measurement (so-called eye tracking) may be used to automatically identify an element that the user is paying attention to in the captured image to be evaluated, thereby reducing the labor required for inputting at least one of the subjective evaluation and objective evaluation results.

[0097] Furthermore, although not specifically mentioned in the above embodiment, the overall evaluation information obtained by the landscape analysis support processing may be stored, for example, in a database, so that it can be reused for other evaluations rather than simply being displayed.

[0098] In the above embodiment, the landscape analysis support device of the present invention is applied as the landscape analysis support system 1 using the landscape analysis support device 10 and the information storage device 90, but the present invention is not limited to this. For example, the landscape analysis support device of the present invention may be configured as a single device in which the landscape analysis support device 10 and the information storage device 90 are integrated.

[0099] In the above embodiment, for example, the following various processors can be used as the hardware structure of the processing unit that executes each process of the learning image acquisition unit 11A, the acquisition unit 11B, the derivation unit 11C, and the presentation unit 11D. As described above, the above various processors include a CPU, which is a general-purpose processor that executes software (programs) and functions as a processing unit, as well as a programmable logic device (PLD), which is a processor whose circuit configuration can be changed after manufacture such as an FPGA (Field-Programmable Gate Array), a dedicated electric circuit, which is a processor having a circuit configuration designed specifically for executing specific processes such as an ASIC (Application Specific Integrated Circuit), etc.

[0100] The processing unit may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA).The processing unit may also be configured with a single processor.

[0101] As an example of configuring the processing unit with one processor, first, there is a form in which one processor is configured with a combination of one or more CPUs and software, as represented by computers such as client and server, and this processor functions as the processing unit. Second, there is a form in which a processor is used that realizes the functions of the entire system including the processing unit with one IC (Integrated Circuit) chip, as represented by System On Chip (SoC), etc. In this way, the processing unit is configured using one or more of the above various processors as a hardware structure.

[0102] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. [Explanation of symbols]

[0103] 1. Landscape analysis support system 10. Landscape analysis support device 11 CPU 11A Learning image acquisition unit 11B Acquisition Department 11C Derivation part 11D Presentation section 12. Memory 13 Storage section 13A Evaluation Input Program 13B Study Program 13C Landscape Analysis Support Program 13D Landscape Analysis Support Model 14 Input section 15 Display section 15A1, 15A2 Images 15B Input area 15C Input Area 15D Speech bubble 15D1 Radar Chart 15D2 Images 15E Map Image 15F square 15G Exit button 16 Media Read / Write Device 17 Recording media 18 Communication I / F section 90 Information storage device 92 Memory section 92A Educational Information Database 92B Image information database 92C Evaluation Result Information Database

Claims

1. A landscape analysis support device using a landscape analysis support model in which image information indicating a captured image obtained by capturing an image of an area to be analyzed is used as input information, and subjective evaluation information indicating a subjective evaluation of a landscape in the captured image and objective evaluation information indicating an objective evaluation of the landscape are used as output information, An acquisition unit that acquires the image information; a derivation unit that derives the subjective evaluation information and the objective evaluation information by inputting the image information acquired by the acquisition unit into the landscape analysis support model; a presentation unit that presents comprehensive evaluation information that is information indicating both the subjective evaluation information and the objective evaluation information derived by the derivation unit; Equipped with The acquisition unit acquires a plurality of pieces of image information each indicating a captured image obtained by capturing an image of the area to be analyzed, the derivation unit derives the subjective evaluation information and the objective evaluation information for each of the acquired pieces of image information; the presentation unit presents the comprehensive evaluation information by displaying, as a graph, the evaluation frequencies of the derived plurality of pieces of subjective evaluation information and the derived plurality of pieces of objective evaluation information. Landscape analysis support device.

2. The subjective evaluation information includes at least one of information regarding a sense of security, information regarding a sense of vitality, and information regarding a sense of attractiveness. The landscape analysis support device according to claim 1.

3. The objective evaluation information includes at least one of elements and features related to the corresponding subjective evaluation information.

3. The landscape analysis support device according to claim 1 or 2.

4. A learning image acquisition unit that acquires learning image information used for learning, the landscape analysis support model is machine-learned using the learning image information acquired by the learning image acquisition unit as input information and the subjective evaluation information and the objective evaluation information corresponding to the learning image information as output information. The landscape analysis support device according to any one of claims 1 to 3.

5. The input information used in performing the machine learning is image information obtained by cutting out an area input by a user from the learning image information as an area that is the basis for the subjective evaluation indicated by the subjective evaluation information used in the machine learning. The landscape analysis support device according to claim 4.

6. The objective evaluation information used in the machine learning is objective evaluation performed by a user. The landscape analysis support device according to claim 4.

7. The subjective evaluation information and the objective evaluation information used in the machine learning are information input by a user while displaying multiple pieces of pre-registered learning image information and prompting the user to specify a region that serves as a basis for the information. The landscape analysis support device according to claim 4.

8. At least one of the subjective evaluation information and the objective evaluation information used in the machine learning is information input by automatically identifying an element that a user is paying attention to in a captured image indicated by the learning image information by eye gaze measurement. The landscape analysis support device according to claim 4.

9. The image information is image information showing images cut out at a predetermined angle from images taken by a 360-degree camera in the area, or image information obtained by taking images in one direction at different points in the area. The landscape analysis support device according to claim 1.

10. A landscape analysis support program using a landscape analysis support model in which image information indicating a captured image obtained by capturing an image of an area to be analyzed is used as input information, and subjective evaluation information indicating a subjective evaluation of a landscape in the captured image and objective evaluation information indicating an objective evaluation of the landscape are used as output information, Obtaining the image information; The acquired image information is input into the landscape analysis support model to derive the subjective evaluation information and the objective evaluation information; a process of presenting comprehensive evaluation information which is information indicating both the derived subjective evaluation information and the derived objective evaluation information, acquiring a plurality of pieces of image information each indicating a photographed image obtained by photographing the area to be analyzed; deriving the subjective evaluation information and the objective evaluation information for each of the acquired plurality of pieces of image information; presenting the comprehensive evaluation information by displaying the evaluation frequencies of the derived plurality of pieces of subjective evaluation information and the derived plurality of pieces of objective evaluation information as graphs; A landscape analysis support program that allows a computer to carry out processing.

Images