Spatial evaluation support device, spatial evaluation support system, and spatial evaluation support program

Abstract

To provide a space evaluation support apparatus which allows a user to quantitatively determine the attractiveness of an existing infrastructure, a space evaluation support system, and a space evaluation support program.SOLUTION: A space evaluation support apparatus 10 includes: an acquisition unit 11A which acquires captured images obtained by imaging a space to be evaluated; an extraction unit 11B which extracts store name information which indicates a store name existing in the space, from the captured images acquired by the acquisition unit 11A; a specifying unit 11C which specifies a store other than stores opened in multiple locations, as a high originality candidate store, out of stores indicated by the store name information extracted by the extraction unit 11B; and a derivation unit 11D which derives evaluation information on the high originality candidate store specified by the specifying unit 11C.SELECTED DRAWING: Figure 3

Description

Technical Field

[0001] The present invention relates to a space evaluation support device, a space evaluation support system, and a space evaluation support program.

Background Art

[0002] Conventionally, the following technologies have existed as technologies that can contribute to making users feel the charm of wanting to use infrastructure such as cities, streetscapes, and tourist attractions.

[0003] Patent Document 1 discloses a street structure in which a main street area that runs longitudinally and / or transversely through a street area is provided, and an energy plant facility for supplying at least electricity and gas and lifeline backbone facilities are provided on the ground and / or underground of the main street area. In this street structure, an infrastructure network is constructed between the main street area and the urban area outside the main street area.

[0004] Further, Patent Document 2 discloses a street structure in which a pedestrian waiting space is provided along a pedestrian-vehicle boundary that divides a roadway and a sidewalk on at least one side of the roadway, where the sidewalk is provided side by side with a width of 4 m or more. In this street structure, the pedestrian waiting space is provided in a substantially rectangular area in plan view with the extension direction of the street as the long side, and the width intersecting the extension direction of the street is set to 2 m or more and half or less of the width of the sidewalk. Also, in this street structure, a walking floor having a material different from that of the paving surface of the sidewalk is provided on the area, and seating parts such as benches, chairs, and steps are provided. And, in this street structure, all of the long side on the roadway side of the area and a portion of 1.5 m or more on the roadway side of one or both of the short sides connected to the long side are continuously surrounded by a vehicle protection body that rises to a height of 1 m or more from the surface of the walking floor.

[0005] Furthermore, Patent Document 3 discloses an outer structure of a house characterized in that a main part and a corner part where buildings, gardens, etc. are constructed on a site are separated by a passage, and the corner part is used as an open space.

Prior Art Documents

Patent Documents

[0006]

Patent Document 1

Patent Document 2

Patent Document 3

Summary of the Invention

Problems to be Solved by the Invention

[0007] However, the technologies disclosed in Patent Documents 1 to 3 were for contributing to constructing an attractive infrastructure in the future. Therefore, these technologies could not contribute to making the existing infrastructure such as cities, streetscapes, and tourist attractions feel attractive to those who want to visit the infrastructure.

[0008] The present invention has been made in view of the above circumstances, and an object thereof is to provide a space evaluation support device, a space evaluation support system, and a space evaluation support program capable of quantitatively determining the attractiveness of existing infrastructure to users.

Means for Solving the Problems

[0009] The space evaluation support device according to the present invention described in claim 1 includes an acquisition unit that acquires a captured image of a space to be evaluated, an extraction unit that extracts store name information indicating store names existing in the space from the captured image acquired by the acquisition unit, a specification unit that specifies stores other than stores with multiple store expansions as highly innovative candidate stores from the stores indicated by the store name information extracted by the extraction unit, and a derivation unit that derives evaluation information regarding the highly innovative candidate stores specified by the specification unit. A presentation unit that synthesizes and presents the evaluation information derived by the derivation unit on a map image and includes, wherein the evaluation information is the space in a certain areaThe number of stores that do not belong to the multi-store chain that exists in area The originality indicates the ratio of the number of shops to the total number of shops in the area, and the space is an area including the location of the user terminal, which is a terminal owned by the target user. and is an area to which it is automatically applied. The presentation unit synthesizes and presents the store name of the highly original candidate store and the originality as character information at corresponding positions with respect to the map image It is something.

[0010] According to the spatial evaluation support device of the present invention as described in claim 1, an image of the space to be evaluated is obtained, store name information indicating the names of stores existing in the space is extracted from the obtained image, stores other than stores with multiple stores are identified as highly original candidate stores from the stores indicated by the extracted store name information, and evaluation information is derived regarding the identified highly original candidate stores, so that by referring to the evaluation information, users can quantitatively judge the attractiveness of existing infrastructure structures.

[0012] Claim 1 According to the spatial evaluation support device of the present invention described above, the derived evaluation information is synthesized and presented on a map image, thereby enabling users to more effectively quantitatively judge the attractiveness of existing infrastructure structures.

[0013] Claim 2 The spatial evaluation support device according to the present invention described in claim 1 In the spatial evaluation support device according to the present invention, the map image is a social heat map image.

[0014] Claim 2 According to the spatial evaluation support device of the present invention described above, by making the map image into a social heat map image, it is possible to more effectively allow users to quantitatively judge the attractiveness of existing infrastructure structures.

[0015] Claim 3 The spatial evaluation support device according to the present invention described in claim 1 or Claim 2The space evaluation support device according to [reference], wherein the extraction unit extracts the store name information by using a segmentation model learned using the captured image acquired by the acquisition unit.

[0016] Claim 3 According to the space evaluation support device according to the present invention described in claim [claim number], by extracting the store name information by using a segmentation model learned using the acquired captured image, the store name information can be extracted with higher accuracy.

[0017] Claim 4 The space evaluation support device according to the present invention described in claim [claim number] is the space evaluation support device according to any one of claims 1 to claim 3 wherein the captured image is an omnidirectional image.

[0018] Claim 4 According to the space evaluation support device according to the present invention described in claim [claim number], by using the captured image as an omnidirectional image, it is possible to extract not only the store name information in the front but also the store name information around. 。

[0019] Claim 5 The space evaluation support system according to the present invention described in claim [claim number] includes the space evaluation support device according to any one of claims 1 to claim 4 a receiving unit that receives the evaluation information derived by the derivation unit of the space evaluation support device from the space evaluation support device, and a display control unit that performs control to display the evaluation information received by the receiving unit on a display unit, and a terminal including the same.

[0020] Claim 5 According to the space evaluation support system according to the present invention described in claim [claim number], by displaying the evaluation information derived by the space evaluation support device of the present invention, by referring to the evaluation information, it is possible to quantitatively determine the attractiveness of the existing infrastructure for the user.

[0021] Claim 6The space evaluation support program according to the present invention described in the above acquires an image of a space to be evaluated, extracts store name information indicating the names of stores existing in the space from the acquired image, identifies stores other than stores with multiple stores as highly original candidate stores from the stores indicated by the extracted store name information, and derives evaluation information regarding the identified highly original candidate stores. and synthesizes and presents the derived evaluation information on the map image The evaluation information is in a certain area The number of stores that do not belong to the multi-store chain that exists in area The originality indicates the ratio of the number of shops to the total number of shops in the area, and the space is an area including the location of the user terminal, which is a terminal owned by the target user. and is an area to which it is automatically applied synthesizes and presents the store name of the highly original candidate store and the originality as character information at corresponding positions with respect to the map image The processing is executed by a computer.

[0022] Claim 6 According to the spatial evaluation support program of the present invention described above, a photographed image of the space to be evaluated is obtained, store name information indicating the names of stores existing in the space is extracted from the obtained photographed image, stores other than stores with multiple stores are identified as highly original candidate stores from the stores indicated by the extracted store name information, and evaluation information is derived regarding the identified highly original candidate stores, allowing users to quantitatively judge the attractiveness of existing infrastructure structures by referring to the evaluation information. Effect of the Invention

[0023] As described above, according to the present invention, it is possible to allow users to quantitatively judge the attractiveness of existing infrastructure. [Brief description of the drawings]

[0024]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Embodiments for Carrying Out the Invention

[0025] Hereinafter, with reference to the drawings, embodiments for carrying out the present invention will be described in detail. In this embodiment, a case where the present invention is applied to a space evaluation support system including a space evaluation support device configured by a server computer or the like and a plurality of target person terminals which are terminals individually used by each target person will be described.

[0026] First, with reference to FIGS. 1 to 3, the configuration of the spatial evaluation support system 90 according to the present embodiment will be described. FIG. 1 is a block diagram showing an example of the hardware configuration of the spatial evaluation support system 90 according to the present embodiment. Further, FIG. 2 is a diagram for explaining the segmentation model according to the present embodiment. The left diagram is a diagram showing an example of an image obtained by photographing, and the right diagram is a diagram showing an example of a classification result of the image shown in the left diagram. Furthermore, FIG. 3 is a block diagram showing an example of the functional configuration of the spatial evaluation support system 90 according to the present embodiment.

[0027] As shown in FIG. 1, the spatial evaluation support system 90 according to the present embodiment includes a spatial evaluation support device 10 and a plurality of subject terminals 30 that are each accessible to the network 80. Examples of the spatial evaluation support device 10 include information processing devices such as personal computers and server computers. Examples of the subject terminal 30 include portable terminals such as smartphones, tablet terminals, and PDAs (Personal Digital Assistants).

[0028] The subject terminal 30 according to the present embodiment is a terminal held by a plurality of subjects who are the users of the spatial evaluation support system 90. The subject terminal 30 includes a CPU (Central Processing Unit) 31, a memory 32 as a temporary storage area, a non-volatile storage unit 33, an input unit 34 such as a touch panel, a display unit 35 such as a liquid crystal display, and a medium reading / writing device (R / W) 36. The subject terminal 30 also includes a camera 38, a microphone 39, a GPS (Global Positioning Systems) 40, and a wireless communication unit 42. The CPU 31, the memory 32, the storage unit 33, the input unit 34, the display unit 35, the medium reading / writing device 36, the camera 38, the microphone 39, the GPS 40, and the wireless communication unit 42 are connected to each other via a bus B1. The medium reading / writing device 36 reads information written on the recording medium 37 and writes information to the recording medium 37.

[0029] The storage unit 33 is implemented by a HDD (Hard Disk Drive), SSD (Solid State Drive), flash memory, or the like. The storage unit 33 as a storage medium stores an evaluation result display program 33A. The evaluation result display program 33A is stored in the storage unit 33 when the recording medium 37 on which the evaluation result display program 33A is written is set in the medium reading / writing device 36 and the medium reading / writing device 36 reads the evaluation result display program 33A from the recording medium 37. The CPU 31 reads the evaluation result display program 33A from the storage unit 33, expands it in the memory 32, and sequentially executes the processes included in the evaluation result display program 33A.

[0030] On the other hand, the space evaluation support device 10 is a device that comprehensively stores and manages various types of information handled in the space evaluation support system 90. The space evaluation support device 10 includes a CPU 11, a memory 12 as a temporary storage area, a non-volatile storage unit 13, an input unit 14 such as a keyboard and a mouse, a display unit 15 such as a liquid crystal display, a medium reading / writing device 16, and a communication interface (I / F) unit 18. The CPU 11, the memory 12, the storage unit 13, the input unit 14, the display unit 15, the medium reading / writing device 16, and the communication I / F unit 18 are connected to each other via a bus B2. The medium reading / writing device 16 reads information written in the recording medium 17 and writes information to the recording medium 17.

[0031] The storage unit 13 is realized by an HDD, an SSD, a flash memory, or the like. In the storage unit 13 as a storage medium, a space evaluation support program 13A and an evaluation result presentation program 13B are stored. The space evaluation support program 13A is stored in the storage unit 13 when a recording medium 17 on which the space evaluation support program 13A is written is set in the medium reading / writing device 16, and the medium reading / writing device 16 reads the space evaluation support program 13A from the recording medium 17. Also, the evaluation result presentation program 13B is stored in the storage unit 13 when a recording medium 17 on which the evaluation result presentation program 13B is written is set in the medium reading / writing device 16, and the medium reading / writing device 16 reads the evaluation result presentation program 13B from the recording medium 17. The CPU 11 reads the space evaluation support program 13A and the evaluation result presentation program 13B from the storage unit 13 and expands them in the memory 12, and sequentially executes the processes that the space evaluation support program 13A and the evaluation result presentation program 13B each have.

[0032] Also, in the storage unit 13, a segmentation model 13C is stored. The segmentation model 13C according to the present embodiment is a segmentation model that uses, as input information, image information indicating a captured image of a space to be evaluated by the space evaluation support system 90, and outputs, as output information, a segmentation image in which regions of predetermined types of components are classified by type from the captured image. In the present embodiment, as the types of the above components, objects on which store names such as signboards, curtains, lanterns, building shutters, and electric bulletin boards are described or displayed (hereinafter referred to as "store name-attached objects") are applied. Also, the types of "signboards" here include all types such as parapet signboards, wall signboards, protruding signboards, standing signboards, banner stands, and the like.

[0033] In the spatial evaluation support system 90 according to this embodiment, as the segmentation model 13C, a model using a semantic segmentation method using deep learning technology is applied. FIG. 2 shows examples of images before and after classification for each element by the image segmentation technology. Note that the left diagram in FIG. 2 is an example of an image before classification (denoted as "original image" in FIG. 2), and the right diagram in FIG. 2 is an example of an image after classification for the corresponding image (denoted as "segmentation image" in FIG. 2). Also, in the example shown in FIG. 2, vegetation, sidewalk, roadway, building, and sky are applied as components, and each component is represented by a different density.

[0034] In this embodiment, teacher data using omnidirectional images collected by Google for Google Street View is created by Google, and the segmentation model 13C is trained. However, the present invention is not limited to this form, and as the omnidirectional image, an image obtained by shooting using the camera 38 by the subject terminal 30 may be applied. Further, the captured image is not limited to the omnidirectional image, and a captured image obtained by shooting only the normal front may be applied.

[0035] Note that the technology of semantic segmentation using deep learning technology is also described in "ICUC10_Fang-Ying GONG_GSV-ViewFactorMaps_6-10 August 2018, "Quantification of Street Elements in Ultra-Dense Urban Environments in Climate Research Using Google Street View"", "Badrinarayanan, V., Kendall, A., & Cipolla, R. (2017). Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE transactions on pattern analysis and machine intelligence, 39(12), 2481-2495.", "Chen, L. C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2017). Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE transactions on pattern analysis and machine intelligence, 40(4), 834-848.", etc. Since it is a well-known technology, further explanation here is omitted.

[0036] Thus, in the spatial evaluation support system 90 according to this embodiment, as the segmentation model 13C, a model using a semantic segmentation method using deep learning technology is applied, but it is not limited to this form. For example, a model applying other image segmentation technologies such as instance-aware segmentation may be applied as the segmentation model 13C.

[0037] In addition, the storage unit 13 stores an image information database 13D, a store information database 13E, and an original store information database 13F. Details of the image information database 13D, the store information database 13E, and the original store information database 13F will be described later.

[0038] Next, with reference to FIG. 3, the functional configurations of the space evaluation support device 10 and the subject terminal 30 according to the present embodiment will be described.

[0039] As shown in FIG. 3, the space evaluation support device 10 includes an acquisition unit 11A, an extraction unit 11B, a specification unit 11C, a derivation unit 11D, and a presentation unit 11E. When the CPU 11 of the space evaluation support device 10 executes the space evaluation support program 13A and the evaluation result presentation program 13B, it functions as the acquisition unit 11A, the extraction unit 11B, the specification unit 11C, the derivation unit 11D, and the presentation unit 11E.

[0040] The acquisition unit 11A according to the present embodiment acquires a captured image of a space to be evaluated (hereinafter referred to as "evaluation target space"). In the present embodiment, as the captured image, the same captured image used when training the segmentation model 13C, that is, an omnidirectional image collected by Google for Google Street View is applied. However, the present invention is not limited to this form, and as the omnidirectional image, an image obtained by photographing using the camera 38 of the subject terminal 30 may be applied. Instead of the omnidirectional image, a captured image obtained by photographing only the normal front may be applied, which is the same as the captured image applied in the training of the segmentation model 13C.

[0041] Further, the extraction unit 11B according to the present embodiment extracts store name information (in the present embodiment, the above-described "store name attachment") indicating the store name existing in the evaluation target image from the captured image acquired by the acquisition unit 11A. Here, the extraction unit 11B according to the present embodiment performs the extraction of the store name information existing in the evaluation target space using the segmentation model 13C learned using the captured image acquired by the acquisition unit 11A. Thereby, compared with the case of using a segmentation model learned using a captured image other than the captured image acquired by the acquisition unit 11A, the above store name information can be extracted with higher accuracy. However, the present invention is not limited to this form, and the above store name information may be extracted from the captured image of the evaluation target space using a segmentation model learned using a captured image other than the captured image acquired by the acquisition unit 11A. Further, the above store name information may be extracted from the captured image of the evaluation target space using a conventionally known image recognition technique without using a segmentation model.

[0042] Further, the identification unit 11C according to the present embodiment identifies a store other than a store with multi-store expansion as a highly innovative candidate store from the store indicated by the store name information extracted by the extraction unit 11B. Then, the derivation unit 11D according to the present embodiment derives evaluation information regarding the highly innovative candidate store identified by the identification unit 11C.

[0043] Further, the presentation unit 11E according to the present embodiment synthesizes the evaluation information derived by the derivation unit 11D with the map image and presents it. The presentation unit 11E according to the present embodiment performs the presentation of the above evaluation information by transmitting information indicating the evaluation information to the requested target terminal 30 and causing the display unit 35 of the target terminal 30 to display it, but the present invention is not limited to this. For example, the above evaluation information may be presented by causing the display unit 15 of the spatial evaluation support device 10 to display it. Further, the presentation of the evaluation information by the presentation unit 11E is not limited to the presentation by the display by the display unit, and a form in which presentation by voice or presentation by printing by an image forming device (so-called printer) is applied may be used.

[0044] In addition, in the present embodiment, a social heat map image is applied as the map image. The social heat map image is an image that shows a map emphasizing places with a lot of information suitable for the category of the target person by displaying areas with different densities and colors overlaid on the normally displayed map image of the corresponding area. That is, in the present embodiment, a plurality of questions are answered in advance by each target person, and the category of each target person is determined in advance by analyzing and classifying the answer results. Then, the social heat map image according to the present embodiment is overlaid and displayed on the map image so that the higher the density of the place where there is more information (in this embodiment, information posted on SNS (Social Networking Service)) suitable for the category of the target person to be used. However, it is not limited to this form of changing the density, and it may be a form of changing the color such as red → yellow → green in order from high density to low density.

[0045] In the present embodiment, the space evaluation support device 10 is connected via a network 80 or the like to a server that provides the latest version of each social heat map image of the area (hereinafter referred to as the "target area") that the space evaluation support system 90 deals with. Then, the space evaluation support device 10 acquires the latest version of the social heat map image from this server and sequentially updates the social heat map image stored in the image information database 13D (see also FIG. 4) described later. However, it is not limited to this form, and the space evaluation support device 10 itself may sequentially update the social heat map image corresponding to each target person.

[0046] On the other hand, the target person terminal 30 according to the present embodiment includes a reception unit 31A and a display control unit 31B. When the CPU 31 of the target person terminal 30 executes the evaluation result display program 33A, it functions as the reception unit 31A and the display control unit 31B.

[0047] The receiving unit 31A according to this embodiment receives the above evaluation information derived by the derivation unit 11D of the spatial evaluation support device 10 from the spatial evaluation support device 10. Further, the display control unit 31B performs control to display the evaluation information received by the receiving unit 31A on the display unit 35.

[0048] Next, with reference to FIG. 4, the image information database 13D according to this embodiment will be described. FIG. 4 is a schematic diagram showing an example of the configuration of the image information database 13D according to this embodiment.

[0049] The image information database 13D according to this embodiment is a database in which learning of the segmentation model 13C and omnidirectional images used as captured images of the evaluation target space are registered. As shown in FIG. 4, the image information database 13D according to this embodiment stores information on the target area name, social heat map image, omnidirectional image, target area location, and target area ID (Identification).

[0050] The above target area name is information indicating the name of each of the above target areas, and the above social heat map image is information indicating the above-described social heat map image for each target person in the target area indicated by the corresponding target area name. Further, the above omnidirectional image is information indicating the above-described omnidirectional image captured inside the corresponding target area, and the above target area location is information indicating the location where the area (hereinafter referred to as the "target area") where the corresponding omnidirectional image was captured exists.

[0051] In this embodiment, the above target area is divided into areas each surrounded by a rectangle of a predetermined size in plan view, and each of the divided areas is applied as the above target area. Further, in this embodiment, the above target area location is defined as the coordinate position in a two-dimensional coordinate system of a pair of diagonals of the rectangle indicating the corresponding target area. However, the present invention is not limited to this form. For example, instead of the above rectangle, other shapes such as a circle or an ellipse may be applied, or instead of the coordinate position in the above two-dimensional coordinate system, latitude and longitude may be applied.

[0052] Furthermore, the target area ID is information that is pre-assigned to be different for each target area in order to individually identify the corresponding target area.

[0053] Next, with reference to FIG. 5, the store information database 13E according to the present embodiment will be described. FIG. 5 is a schematic diagram showing an example of the configuration of the store information database 13E according to the present embodiment.

[0054] The store information database 13E according to the present embodiment stores information on stores with multi-store deployment described above, which is used when deriving the above-described evaluation information. As shown in FIG. 5, the store information database 13E according to the present embodiment stores information on the chain store name, store name, and address.

[0055] The above chain store name is information indicating the general name of a group of stores deployed as chain stores within a predetermined area (in this embodiment, within Japan). Also, the above store name is information indicating the name of each store belonging to the corresponding chain store, and the above address is information indicating the location of the corresponding store.

[0056] Next, with reference to FIG. 6, the original store information database 13F according to the present embodiment will be described. FIG. 6 is a schematic diagram showing an example of the configuration of the original store information database 13F according to the present embodiment.

[0057] The original store information database 13F according to the present embodiment stores evaluation information and the like obtained by executing the spatial evaluation support program 13A. As shown in FIG. 6, the original store information database 13F according to the present embodiment stores information on the target area name, target area ID, store name, store location, and originality.

[0058] The above target area name and the above target area ID are the same information as the target area name and the target area ID in the image information database 13D, respectively. Also, the above store name is information indicating the name of the highly original candidate store described above, and the above store location is information indicating the location when the address of the corresponding highly original candidate store is converted into the same two-dimensional coordinate system as the above target area location. Furthermore, the above originality is information indicating the level of originality of the stores existing in the corresponding target area and is information corresponding to the above evaluation information.

[0059] In the spatial evaluation support system 90 according to the present embodiment, the above originality is derived by calculating it according to the following formula (1). In formula (1), OD represents the originality, ON represents the number of stores that do not belong to chain stores existing in the corresponding target area, and TN represents the total number of stores existing in the corresponding target area.

[0060] OD = 100×(ON / TN) (1)

[0061] That is, in the spatial evaluation support system 90 according to the present embodiment, as the originality OD, the ratio (percentage) of the number of stores that do not belong to chain stores existing in the target area to the total number of stores existing in the target area is applied.

[0062] Thus, in the spatial evaluation support system 90 according to the present embodiment, as the above evaluation information, the originality OD for all types of stores that do not belong to chain stores for each target area is applied, but it is not limited to this form. For example, stores may be classified by type such as restaurants, clothing stores, coffee shops, etc., and the originality OD for each type may be applied as the above evaluation information. Also, in this form, the weighted average value of the originality OD for each type may be applied as the comprehensive evaluation information for the target area.

[0063] Next, with reference to FIGS. 7 to 11, the operation of the space evaluation support system 90 according to the present embodiment will be described. FIG. 7 is a flowchart showing an example of the space evaluation support process according to the present embodiment. FIG. 8 is a flowchart showing an example of the evaluation result presentation process according to the present embodiment. FIG. 9 is a flowchart showing an example of the evaluation result display process according to the present embodiment. FIG. 10 is a front view showing an example of the configuration of the initial screen according to the present embodiment. Further, FIG. 11 is a front view showing an example of the configuration of the evaluation result screen according to the present embodiment.

[0064] First, with reference to FIG. 7, the operation of the space evaluation support device 10 according to the present embodiment when executing the space evaluation support process will be described. When an instruction input to start the execution of the space evaluation support process is performed by the user of the space evaluation support device 10 (for example, the administrator of the space evaluation support system 90) via the input unit 14, the CPU 11 of the space evaluation support device 10 executes the space evaluation support program 13A, whereby the space evaluation support process shown in FIG. 7 is executed. Here, in order to avoid complication, the case where the image information database 13D and the store information database 13E have already been constructed will be described. Further, here, in order to avoid complication, the case where the segmentation model 13C has been learned using some omnidirectional images registered in the image information database 13D will be described. Furthermore, here, in order to avoid complication, the case where the omnidirectional image to be evaluated (hereinafter referred to as the "evaluation target image") in the image information database 13D has been specified in advance will be described.

[0065] In step 100 of FIG. 7, the CPU 11 reads all the information (hereinafter referred to as "store information") from the store information database 13E.

[0066] In step 102, the CPU 11 reads out any one image (hereinafter referred to as the "processing target image") of the evaluation target images from the image information database 13D together with the corresponding target region name and target area ID. In step 104, the CPU 11 reads out the learned segmentation model 13C from the storage unit 13.

[0067] In step 106, the CPU 11 inputs the image to be processed into the segmentation model 13C. In response to the input of this image to be processed, a corresponding segmentation image is output from the segmentation model 13C. Therefore, in step 108, the CPU 11 acquires the segmentation image output from the segmentation model 13C.

[0068] In step 110, the CPU 11 extracts the above-mentioned store name information from the acquired segmentation image. In step 112, the CPU 11 determines whether the store name (hereinafter referred to as the "extracted store name") included in the extracted store name information is included in the store name in the read store information, thereby determining whether the store corresponding to the extracted store name belongs to any chain store. Here, if the determination is affirmative, the process proceeds to step 116 described later; if the determination is negative, the process proceeds to step 114. Note that the store name included in the above-mentioned store name information can be obtained by a conventionally known character recognition technology such as OCR (Optical Character Recognition) technology.

[0069] In step 114, the CPU 11 stores the extracted store name and the store location in the original store information database 13F as information corresponding to the read target area name and target area ID. Here, as described above, the store location is information indicating the position when the address of the corresponding store is converted into the same two-dimensional coordinate system as the above-mentioned target area location. In this embodiment, as the store location, the address of the corresponding store retrieved from another device via the network 80 is converted into the position in the two-dimensional coordinate system and applied. The store indicated by the extracted store name stored in the original store information database 13F by the process of this step 114 is estimated to be a store with high originality that does not belong to any chain store, and corresponds to the above-mentioned high originality candidate store.

[0070] In step 116, the CPU 11 determines whether the above processing has been completed for all the images to be evaluated. If the determination is negative, it returns to step 102, while if the determination is positive, it proceeds to step 118. When repeatedly executing the processing from step 102 to step 116, in step 102, the images to be evaluated that have not been the processing targets so far are set as the processing target images.

[0071] In step 118, the CPU 11 sets the number of store names for each target area stored in the original store information database 13F as the number ON of the above-mentioned stores, and specifies the total number of stores existing in the corresponding target area from the read store information, and sets the total number as the total number TN of the above-mentioned stores. Then, the CPU 11 substitutes the number ON of the stores and the total number TN of the stores into equation (1) to derive the originality degree OD for each target area.

[0072] In step 120, the CPU 11 stores the derived originality degree OD in the original store information database 13F for each target area, and then ends this spatial evaluation support processing.

[0073] Through the above spatial evaluation support processing, the original store information database 13F shown in FIG. 6 as an example is constructed.

[0074] Next, with reference to FIG. 8, the operation of the spatial evaluation support apparatus 10 according to the present embodiment when executing the evaluation result presentation processing will be described.

[0075] In the spatial evaluation support system 90 according to this embodiment, when a certain subject wants to refer to the above-described evaluation information of each place in a certain target area, the subject terminal 30 held by the subject is used to execute the evaluation result display process described later. In this evaluation result display process, reference request information including information indicating the target area that the subject wants to refer to the evaluation information (hereinafter referred to as "designated target area information") is transmitted to the spatial evaluation support device 10. When this reference request information is received, the CPU 11 of the spatial evaluation support device 10 executes the evaluation result presentation program 13B, and the evaluation result presentation process shown in FIG. 8 is executed. Here, in order to avoid complication, the case where the original store information database 13F has already been constructed will be described.

[0076] In step 150 of FIG. 8, the CPU 11 extracts the designated target area information from the received reference request information. In step 152, the CPU 11 reads out the target area ID, store name, and evaluation information (originality degree OD) of all target areas included in the target area indicated by the designated target area information (hereinafter referred to as "processing target area") from the original store information database 13F. The stores with the store names read here are the above-described highly original candidate stores that are presumed to have high originality.

[0077] In step 154, the CPU 11 reads out the target area position corresponding to the read target area ID, and the social heat map image corresponding to the processing target area and the subject who is the access source from the image information database 13D.

[0078] In step 156, the CPU 11 uses the read social heat map image, the store name and evaluation information of each target area, and each information of the target area position to create information indicating an evaluation result screen having a predetermined configuration (hereinafter referred to as "evaluation result screen information"). In step 158, the CPU 11 transmits the created evaluation result screen information to the subject terminal 30 of the access source, and then ends this evaluation result presentation process.

[0079] Next, with reference to FIG. 9, the operation of the target terminal 30 according to the present embodiment when executing the above-described evaluation result display process will be described. When the CPU 31 of any one of the target terminals 30 executes the evaluation result display program 33A, the evaluation result display process shown in FIG. 9 is executed. The evaluation result display process shown in FIG. 9 is executed, for example, when an execution instruction for the evaluation result display process is input from any one of the target persons (hereinafter referred to as the "target person to be executed") via the input unit 34 of his or her own target terminal 30.

[0080] In step 200 of FIG. 9, the CPU 31 controls the display unit 35 to display an initial screen having a predetermined configuration, and in step 202, the CPU 31 waits until predetermined information is input.

[0081] As shown in FIG. 10 as an example, in the initial screen according to the present embodiment, a message prompting the input of the target area name is displayed, and an input area 35A for inputting the target area name of the target area for which evaluation information is to be referred is displayed. When the initial screen shown in FIG. 10 is displayed by the display unit 35, the target person to be executed uses the input unit 34 to input the name of the target area for which evaluation information is to be referred into the input area 35A, and then designates the end button 35B. In response to this, step 202 becomes an affirmative determination and the process proceeds to step 204. In the present embodiment, the input of the target area name on the initial screen is in the form of directly inputting the target area name, but the present invention is not limited to this, and while all the target area names that can refer to the evaluation information are displayed in a pull-down format, it may also be in the form of designating a desired target area name from the displayed target area names.

[0082] In step 204, the CPU 31 transmits the above-described reference request information to the spatial evaluation support device 10. In response to this, the spatial evaluation support device 10 executes the evaluation result presentation process as described above, and transmits the evaluation result screen information to the target terminal 30 of the access source.

[0083] Therefore, in step 206, the CPU 31 waits until it receives the evaluation result screen information from the space evaluation support device 10. In step 208, the CPU 31 controls the display unit 35 to display the evaluation result screen indicated by the received evaluation result screen information. In step 210, after waiting until predetermined information is input, the CPU 31 ends the present evaluation result display process.

[0084] As an example, as shown in FIG. 11, in the evaluation result screen according to the present embodiment, for the social heat map image of the processing target area, at the positions corresponding to the store names and the originality degree OD of the above-described highly original candidate stores in the target area included in the processing target area, they are displayed. Note that the corresponding positions are the positions indicated by the above-described target area positions.

[0085] Therefore, the person to be implemented can grasp the evaluation information of each place in the processing target area together with the social heat map image and the store names of the highly original candidate stores by referring to the evaluation result screen.

[0086] As described above, according to the present embodiment, an acquisition unit 11A that acquires a captured image of a space to be evaluated, an extraction unit 11B that extracts store name information indicating store names existing in the space from the captured image acquired by the acquisition unit 11A, a specific unit 11C that specifies stores other than stores with multi-store expansions as highly original candidate stores from the stores indicated by the store name information extracted by the extraction unit 11B, and a derivation unit 11D that derives evaluation information regarding the highly original candidate stores specified by the specific unit 11C are provided. Therefore, it is possible to quantitatively determine the attractiveness of the existing infrastructure for the user.

[0087] Also, according to the present embodiment, the derived evaluation information is synthesized with a map image and presented. Therefore, it is possible to more effectively quantitatively determine the attractiveness of the existing infrastructure for the user.

[0088] Also, according to the present embodiment, the above map image is used as a social heat map image. Therefore, it is possible to more effectively enable the user to quantitatively determine the attractiveness of the existing infrastructure.

[0089] Also, according to the present embodiment, the above store name information is extracted using a segmentation model learned using the captured image acquired by the acquisition unit 11A. Therefore, the above store name information can be extracted with higher accuracy.

[0090] Furthermore, according to the present embodiment, the captured image is used as an omnidirectional image. Therefore, not only the information of the store names in the front but also the information of the store names around can be extracted.

[0091] In the above embodiment, the case where only the evaluation information (originality OD) of the target area in the processing target area and the store names of the highly original candidate stores are superimposed and displayed on the social heat map image for the evaluation result screen has been described, but the present invention is not limited to this. For example, in addition to these pieces of information, the corresponding omnidirectional image may be displayed in the vicinity of these pieces of information.

[0092] Also, in the above embodiment, the case where the target person himself / herself designates the processing target area has been described, but the present invention is not limited to this. For example, using the GPS 40 built in the target person terminal 30 possessed by the target person, a region including the position where the target person terminal 30 exists may be automatically applied as the processing target area. Also, information indicating the tendency of the target person's preference may be acquired in advance by the spatial evaluation support device 10, and the information of the target area corresponding to the target person's preference may be provided to the target person at any time.

[0093] Also, in the above embodiment, the case where the spatial evaluation support processing is executed in the spatial evaluation support device 10 has been described, but the present invention is not limited to this. For example, the spatial evaluation support processing may be executed by each target person terminal 30. In this case, the spatial evaluation support device 10 of the present invention is included in the target person terminal 30.

[0094] In the above embodiment, the case where an image showing a map emphasizing locations with a large amount of information suitable for the category of the target person is applied as the social heat map image has been described, but the present invention is not limited to this. For example, an image with a stronger red tone in areas with a higher originality degree OD may be applied as the social heat map image.

[0095] In the above embodiment, the case where a chain store is applied as a store with multiple store expansions has been described, but the present invention is not limited to this. For example, a franchise store may be applied as a store with multiple store expansions.

[0096] In the above embodiment, the case where the name of the highly original candidate store is displayed in association with the position indicated by the target area position of the corresponding target area has been described, but the present invention is not limited to this. For example, the name of the highly original candidate store may be displayed in association with the position indicated by the corresponding store position using the store position stored in the original store information database 13F.

[0097] In the above embodiment, the case where the input of the processing target area is performed on the initial screen using the input unit 34 has been described, but the present invention is not limited to this. For example, the processing target area may be input as voice information using the microphone 39.

[0098] In the above embodiment, although not particularly mentioned about what happens after the target person refers to the evaluation result screen, if the originality degree displayed on the evaluation result screen is different from the target person's own subjective view, the originality degree based on the target person's own subjective view may be reflected in the original store information database 13F using the target person terminal 30.

[0099] In the above embodiment, the case where the store name information in the captured image is extracted using the segmentation model has been described, but the present invention is not limited to this. For example, a form in which other object detection models except the segmentation model are applied to extract the store name information in the captured image may be used.

[0100] In addition, it goes without saying that formula (1) is merely an example and can be appropriately modified and applied without departing from the gist of the present invention.

[0101] In the above-described embodiment, for example, as the hardware structure of a processing unit that executes each process of the acquisition unit 11A, the extraction unit 11B, the specification unit 11C, the derivation unit 11D, and the presentation unit 11E, various types of processors shown below can be used. Among the various types of processors described above, in addition to the CPU, which is a general-purpose processor that executes software (program) and functions as a processing unit as described above, there are a programmable logic device (PLD), such as an FPGA (Field-Programmable Gate Array), which is a processor whose circuit configuration can be changed after manufacturing, and an application-specific integrated circuit (ASIC), which is a processor having a circuit configuration specifically designed to execute specific processing, such as a dedicated electric circuit.

[0102] The processing unit may be composed of one of these various types of processors, or may be composed of a combination of two or more processors of the same type or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Further, the processing unit may be composed of one processor.

[0103] As an example of configuring the processing unit with one processor, firstly, as represented by a computer such as a client and a server, there is a form in which one processor is configured by a combination of one or more CPUs and software, and this processor functions as the processing unit. Secondly, as represented by a system on chip (SoC), etc., there is a form in which a processor that realizes the functions of the entire system including the processing unit with one integrated circuit (IC) chip is used. Thus, the processing unit is configured using one or more of the various types of processors as its hardware structure.

[0104] Furthermore, as the hardware structure of these various processors, more specifically, circuitry combining circuit elements such as semiconductor elements can be used.

Explanation of Signs

[0105] 10 Spatial evaluation support device 11 CPU 11A Acquisition unit 11B Extraction unit 11C Identification unit 11D Derivation unit 11E Presentation unit 12 Memory 13 Storage unit 13A Spatial evaluation support program 13B Evaluation result presentation program 13C Segmentation model 13D Image information database 13E Store information database 13F Original store information database 14 Input unit 15 Display unit 16 Media reading / writing device 17 Recording medium 18 Communication I / F unit 30 Subject terminal 31 CPU 31A Receiving unit 31B Display control unit 32 Memory 33 Storage unit 33A Evaluation result display program 34 Input unit 35 Display unit 36 Media reading / writing device 37 Recording medium 38 Camera 39 Microphone 40 GPS 42 Wireless communication unit 80 Network 90 Spatial evaluation support system

Claims

1. An acquisition unit that acquires a captured image obtained by capturing a space to be evaluated; An extraction unit that extracts store name information indicating the store name existing in the space from the captured image acquired by the acquisition unit; A specifying unit that specifies, as highly original candidate stores, stores other than stores with multi-store deployments from the stores indicated by the store name information extracted by the extraction unit; A derivation unit that derives evaluation information regarding the highly original candidate stores specified by the specifying unit; A presentation unit that synthesizes and presents the evaluation information derived by the derivation unit on a map image; Comprising: The evaluation information is an originality degree indicating the ratio of the number of stores that do not belong to the stores with multi-store deployments existing in the area in the space to the total number of stores existing in the area; The space is an area including the position where the user terminal, which is a terminal possessed by the target person to be used, exists, and is an area to be automatically applied; The presentation unit synthesizes and presents the store name of the highly original candidate store and the originality degree as character information at corresponding positions with respect to the map image; A space evaluation support device.

2. The map image is a social heat map image. The space evaluation support device according to claim 1.

3. The extraction unit extracts the store name information using a segmentation model learned using the captured image acquired by the acquisition unit. The space evaluation support device according to claim 1 or claim 2.

4. The captured image is an omnidirectional image. The space evaluation support device according to any one of claims 1 to 3.

5. The space evaluation support device according to any one of claims 1 to 4, A receiving unit that receives the evaluation information derived by the derivation unit of the space evaluation support device from the space evaluation support device, and a display control unit that performs control to display the evaluation information received by the receiving unit on a display unit; and a terminal comprising: A space evaluation support system including.

6. Acquiring a captured image obtained by capturing a space to be evaluated; Extracting store name information indicating the store name existing in the space from the acquired captured image; Specifying, as highly original candidate stores, stores other than stores with multi-store deployments from the stores indicated by the extracted store name information; Deriving evaluation information regarding the specified highly original candidate stores; Synthesizing and presenting the derived evaluation information on a map image; A process. The evaluation information is an originality degree indicating the ratio of the number of stores that do not belong to the stores with the multi-store deployment existing in the area in the space to the total number of stores existing in the area. The space is an area that includes the position where a user terminal, which is a terminal possessed by a target person to be used, exists, and is an area to which it is automatically applied. For the map image, the store name of the highly original candidate store and the originality degree are synthesized and presented as character information at corresponding positions. A space evaluation support program for causing a computer to execute processing.

Images