Real estate evaluation device, real estate evaluation method, and real estate evaluation program

Abstract

To achieve the omission of on-site surveys and improve the efficiency of period and cost associated with work.SOLUTION: An image retrieval unit 121 acquires a remote sensing image 521 that includes an observation range containing a target range including a position of the target real estate. A target feature detection unit 122 detects the target real estate from the remote sensing image 521 on the basis of the position of the target real estate. A surrounding feature detection unit 123 detects surrounding features of the target real estate from the remote sensing image 521 on the basis of the position of the target real estate and geographical space information 211. A feature analysis unit 124 analyzes the condition of the target real estate and the conditions of the surrounding features of the target real estate and outputs them as real estate evaluation information 53. A positional relationship analysis unit 125 analyzes the positional relationship between the target real estate and the surrounding features of the target real estate and outputs it as the real estate evaluation information 53.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present disclosure relates to a real estate appraisal device, a real estate appraisal method, and a real estate appraisal program.

Background Art

[0002] There is an operation of evaluating the state or value of a collateral property in real estate from viewpoints such as its physical state, legal issues, and appraised value. Conventionally, this has been achieved by an appraiser visually conducting an on-site inspection of the collateral property. However, visual inspection by an appraiser has limitations in terms of working time and working range.

[0003] Patent Document 1 discloses a method of estimating house changes such as new construction, disappearance, or rebuilding based on the output when a pair of images of land taken at different times is input into a machine learning model.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] In the technology of Patent Document 1, the situation of real estate is analyzed from the feature amounts of the building itself. The feature amounts are area or shape. However, in actual real estate appraisal work, not only the target building but also the situation of surrounding ground features or the positional relationship between the building and the ground features are appraisal items. The technology of Patent Document 1 has a problem that the situation of surrounding ground features of the building or the positional relationship between the building and the ground features must be analyzed manually.

[0006] An object of the present disclosure is to realize the omission of on-site inspections and to improve the efficiency of the period and cost related to the work by extracting information necessary for the appraisal of the target real estate.

Means for Solving the Problem

[0007] The real estate evaluation device according to the present disclosure is configured to: Based on the location of the target real estate, which is the real estate to be evaluated, and the geospatial information, perform image analysis on the location of the target real estate and the surroundings of the location of the target real estate in a remote sensing image with the target range including the location of the target real estate as the observation range, and output the state of the target real estate and the state of the surroundings of the target real estate as real estate evaluation information, which is information used for evaluating the target real estate. The device is provided with an image processing unit. The image processing unit includes: A target feature detection unit that detects the target real estate from the remote sensing image based on the location of the target real estate; A surrounding feature detection unit that detects features in the surroundings of the target real estate from the remote sensing image based on the location of the target real estate and the geospatial information; A feature analysis unit that analyzes the state of the target real estate and the state of the features in the surroundings of the target real estate, and outputs the analysis result as the real estate evaluation information; A positional relationship analysis unit that analyzes the positional relationship between the target real estate and the features in the surroundings of the target real estate, and outputs the analysis result as the real estate evaluation information.

Advantages of the Invention

[0008] In the real estate evaluation device according to the present disclosure, based on the location of the target real estate and the geospatial information, it is possible to analyze the state of the target real estate and the features in the surroundings of the target real estate, and the positional relationship between the target real estate and the features in the surroundings of the target real estate from the remote sensing image. Therefore, according to the real estate evaluation device according to the present disclosure, by realizing the omission of on-site inspections, it is possible to improve the efficiency of the period and cost related to the work, and at the same time, improve the accuracy of the real estate evaluation information used for evaluation.

Brief Description of the Drawings

[0009]

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

[0010] Hereinafter, this embodiment will be described with reference to the drawings. In each figure, the same or corresponding parts are denoted by the same reference numerals. In the description of the embodiment, the description of the same or corresponding parts will be omitted or simplified as appropriate. The arrows in the figures mainly indicate the flow of data or the flow of processing.

[0011] Embodiment 1. ***Description of Configuration*** FIG. 1 is a diagram showing a configuration example of the real estate evaluation apparatus 100 according to this embodiment. FIG. 2 is a diagram showing a configuration example of the image processing unit 120 according to this embodiment. The real estate evaluation device 100 is a computer. The real estate evaluation device 100 includes a processor 910 and other hardware such as a memory 921, an auxiliary storage device 922, an input interface 930, an output interface 940, and a communication device 950. The processor 910 is connected to other hardware via signal lines and controls these other hardware.

[0012] As functional elements, the real estate evaluation device 100 includes a range acquisition unit 110, an image processing unit 120, an evaluation unit 130, an update unit 140, and a storage unit 150. The image processing unit 120 includes an image search unit 121, a target feature detection unit 122, a surrounding feature detection unit 123, a feature analysis unit 124, and a positional relationship analysis unit 125. The storage unit 150 stores evaluation target information 50, a target range 51, a remote sensing image database 52, real estate evaluation information 53, an evaluation report 54, update information 55, and support information 56. A remote sensing image 521 is registered in the remote sensing image database 52.

[0013] The functions of the range acquisition unit 110, the image processing unit 120, the evaluation unit 130, and the update unit 140 are realized by software. The storage unit 150 is provided in the memory 921. Note that the storage unit 150 may be provided in the auxiliary storage device 922, or may be distributed and provided in the memory 921 and the auxiliary storage device 922.

[0014] The processor 910 is a device that executes a real estate evaluation program. The real estate evaluation program is a program that realizes the functions of the range acquisition unit 110, the image processing unit 120, the evaluation unit 130, and the update unit 140. The processor 910 is an IC that performs arithmetic processing. Specific examples of the processor 910 are a CPU, a DSP, and a GPU. IC is an abbreviation for Integrated Circuit. CPU is an abbreviation for Central Processing Unit. DSP is an abbreviation for Digital Signal Processor. GPU is an abbreviation for Graphics Processing Unit.

[0015] The memory 921 is a storage device that temporarily stores data. Specific examples of the memory 921 are SRAM or DRAM. SRAM is an abbreviation for Static Random Access Memory. DRAM is an abbreviation for Dynamic Random Access Memory. The auxiliary storage device 922 is a storage device that stores data. A specific example of the auxiliary storage device 922 is an HDD. Also, the auxiliary storage device 922 may be a portable storage medium such as an SD (registered trademark) memory card, CF, NAND flash, flexible disk, optical disk, compact disk, Blu-ray (registered trademark) disk, or DVD. Note that HDD is an abbreviation for Hard Disk Drive. SD (registered trademark) is an abbreviation for Secure Digital. CF is an abbreviation for CompactFlash (registered trademark). DVD is an abbreviation for Digital Versatile Disk.

[0016] The input interface 930 is a port connected to an input device such as a mouse, keyboard, or touch panel. Specifically, the input interface 930 is a USB terminal. Note that the input interface 930 may be a port connected to a LAN. USB is an abbreviation for Universal Serial Bus. LAN is an abbreviation for Local Area Network. Also, the input interface 930 may be connected to the real estate database 200. In FIG. 1, one input interface 930 is shown, but a plurality of input interfaces 930 may exist.

[0017] The output interface 940 is a port to which a cable of an output device such as a display is connected. Specifically, the output interface 940 is a USB terminal or an HDMI (registered trademark) terminal. Specifically, the display is an LCD. The output interface 940 is also referred to as a display interface. HDMI (registered trademark) is an abbreviation for High Definition Multimedia Interface. LCD is an abbreviation for Liquid Crystal Display. Also, the output interface 940 may be connected to the real estate database 200. In FIG. 1, one output interface 940 is described, but a plurality of output interfaces 940 may exist.

[0018] The communication device 950 has a receiver and a transmitter. The communication device 950 is connected to a communication network such as a LAN, the Internet, a telephone line, or Wi-Fi (registered trademark). Specifically, the communication device 950 is a communication chip or a NIC. Note that the communication device 950 may also serve as a communication interface for obtaining information from the real estate database 200 either wired or wirelessly. NIC is an abbreviation for Network Interface Card. The real estate evaluation device 100 communicates with each of the real estate database 200 and the geospatial information database 210 via the communication device 950.

[0019] The real estate appraisal program is executed in the real estate appraisal device 100. The real estate appraisal program is loaded into the processor 910 and executed by the processor 910. In the memory 921, not only the real estate appraisal program but also the OS is stored. The OS is an abbreviation for Operating System. The processor 910 executes the real estate appraisal program while executing the OS. The real estate appraisal program and the OS may be stored in the auxiliary storage device 922. The real estate appraisal program and the OS stored in the auxiliary storage device 922 are loaded into the memory 921 and executed by the processor 910. Note that part or all of the real estate appraisal program may be incorporated into the OS.

[0020] The real estate appraisal device 100 may include a plurality of processors that replace the processor 910. These multiple processors share the execution of the real estate appraisal program. Each processor is a device that executes the real estate appraisal program in the same way as the processor 910.

[0021] Data, information, signal values, and variable values used, processed, or output by the real estate appraisal program are stored in the memory 921, the auxiliary storage device 922, or registers or cache memories within the processor 910.

[0022] The "section" of each of the range acquisition section 110, the image processing section 120, the evaluation section 130, and the update section 140 may be read as "circuit", "process", "procedure", "processing", or "circuitry". When the "section" in the image processing section 120 is read as "processing", it shall be referred to as image analysis processing. The real estate evaluation program causes a computer to execute range acquisition processing, image analysis processing, evaluation processing, and update processing. The "processing" in the range acquisition processing, the image analysis processing, the evaluation processing, and the update processing may be read as "program", "program product", "computer-readable storage medium storing the program", or "computer-readable recording medium recording the program". Further, the real estate evaluation method is a method performed by the real estate evaluation apparatus 100 executing the real estate evaluation program. The real estate evaluation program may be stored in a computer-readable recording medium and provided. Further, the real estate evaluation program may be provided as a program product.

[0023] ***Description of Operations*** FIG. 3 is a flowchart showing an example of real estate evaluation processing which is the operation of the real estate evaluation apparatus 100 according to the present embodiment. Using FIG. 3, the operation of the real estate evaluation apparatus 100 according to the present embodiment will be described. The operation procedure of the real estate evaluation apparatus 100 corresponds to the real estate evaluation method. Further, the program for realizing the operation of the real estate evaluation apparatus 100 corresponds to the real estate evaluation program.

[0024] <Range Acquisition Processing: Step S101> In the range acquisition processing, the range acquisition section 110 acquires evaluation target information 50 in which information regarding the target real estate 31 which is the real estate to be evaluated is stored. The range acquisition section 110 acquires a target range 51 including the position of the target real estate 31 based on the evaluation target information 50.

[0025] For example, the range acquisition section 110 acquires the evaluation target information 50 in which information regarding the target real estate 31 is stored from the user via the input interface 930. Alternatively, the range acquisition unit 110 may acquire the location information of the target real estate 31 from the user via the input interface 930, and generate the evaluation target information 50 in which information regarding the target real estate 31 is stored with reference to the real estate database 200.

[0026] It is possible to acquire the pre-generated evaluation target information 50, or to acquire it by generating the evaluation target information 50 with reference to the real estate database 200.

[0027] The real estate database 200 is a database in which information regarding real estate is registered. The real estate database 200 may be composed of one database. Alternatively, the real estate database 200 may be composed of databases regarding a plurality of real estates registered at various locations. The evaluation target information 50 is a database in which information regarding the target real estate 31 is registered. The real estate database 200 and the evaluation target information 50 shall have items common to real estate. In the evaluation target information 50, as information regarding real estate, information such as location, land, building / house number, condominium building, owner's name, presence or absence of registration of disposition restrictions, relationship between land and building, ranking of mortgage rights, presence or absence of mortgage rights, and information among the canceled registrations is registered. Further, the evaluation target information 50 may include information such as the area, shape, and roof condition of the building, the condition of whether it is in contact with a road, the condition of the boundary with the neighboring real estate, the width of the part in contact with the road, the shape of the land, the slope of the land, the presence or absence of surrounding roads, and the width of the surrounding roads. In addition, information such as the condition of the surface (appearance) of the building and the concentration of surrounding features may be included.

[0028] The range acquisition process will be specifically described. In step S101, the range acquisition unit 110 receives the evaluation target information 50 input from the user via the input interface 930 and stores it in the storage unit 150. Based on the evaluation target information 50, the range acquisition unit 110 acquires the target range 51 including the location of the target real estate 31 and stores it in the storage unit 150. Alternatively, the range acquisition unit 110 acquires the position information of the target real estate 31 to be evaluated via the input interface 930. The range acquisition unit 110 acquires the position information of one or more target real estates 31. The range acquisition unit 110 refers to the real estate database 200 via the communication device 950. Further, the range acquisition unit 110 refers to the real estate database 200 and acquires a target range 51 including the position of the target real estate 31 based on the position information of the target real estate 31.

[0029] <Image analysis process: Step S102, Step S103> FIG. 4 is a flowchart showing an example of an image analysis process that is the operation of the image processing unit 120 according to the present embodiment. The image analysis process (Steps S102 and S103) will be described with reference to FIGS. 3 and 4. The outline of the image analysis process is as follows. In the image analysis process, the image processing unit 120 analyzes the position of the target real estate 31 and the periphery of the position of the target real estate 31 in the remote sensing image 521 based on the position of the target real estate 31, which is the real estate to be evaluated, and the geospatial information 211. Then, the image processing unit 120 outputs the state of the target real estate 31 and the periphery of the target real estate 31 as real estate evaluation information 53. At this time, the remote sensing image 521 is a remote sensing image having the target range 51 including the position of the target real estate 31 as the observation range. Also, the real estate evaluation information 53 is information used for evaluating the target real estate 31. The real estate evaluation information 53 includes road-related information 221 indicating the positional relationship between the target real estate 31 and the roads around the target real estate 31. Further, the real estate evaluation information 53 includes real estate state information 21 indicating the state of the target real estate 31 itself and real estate peripheral information 22 indicating the situation around the target real estate 31. The above-described road-related information 221 is an example of the real estate peripheral information 22 indicating the situation around the target real estate 31. Details of the real estate evaluation information 53 will be described later.

[0030] Further, the image processing unit 120 acquires the geospatial information 211 from the geospatial information database 210. Geospatial information is information composed of spatial location information and various types of information associated with that location information. For example, information such as land use maps, geological maps, thematic maps such as hazard maps, urban planning maps, topographic maps, place name information, ledger information, statistical information, aerial photographs, or satellite images that include information on various themes in a region can be cited.

[0031] The image analysis process will be specifically described. As shown in FIG. 4, the image analysis process (steps S102 and S103) includes an image search process (step S121), a target object detection process (step S122), a surrounding object detection process (step S123), an object analysis process (step S124), and a positional relationship analysis process (step S125).

[0032] <<Image Search Process in Step S121>> The image search unit 121 of the image processing unit 120 acquires a remote sensing image having an observation range including the target range 51. Specifically, it is as follows.

[0033] The image search unit 121 searches the remote sensing image database 52 and acquires a remote sensing image having an observation range including the target range 51. The remote sensing image database 52 stores remote sensing images such as SAR satellite data obtained by observing and photographing the earth's surface by an SAR satellite. Remote sensing images are also referred to as satellite images.

[0034] The remote sensing image database 52 may be an external database of the real estate appraisal apparatus 100. When the remote sensing image database 52 is an external database, the image processing unit 120 refers to the remote sensing image database 52 via the communication device 950.

[0035] In this embodiment, the remote sensing image 521 is registered in the remote sensing image database 52. As another aspect, the image processing unit 120 may transmit an observation request to the SAR satellite to observe an observation range including the target range 51. Then, the image processing unit 120 may acquire a remote sensing image newly captured by the SAR satellite.

[0036] <<Target Feature Detection Process in Step S122>> In step S122, the target feature detection unit 122 detects the target real estate 31 from the remote sensing image acquired in step S121 based on the position of the target real estate 31. The target real estate 31 is a building or land. The target feature detection unit 122 detects the target real estate 31 from the remote sensing image acquired in step S121 using a detector.

[0037] Specifically, it is as follows. For example, an example of the detection processing operation of the detector in the target feature detection unit 122 is as follows. The target feature detection unit 122 uses the remote sensing image 521 including buildings and the label data with the positions of the buildings labeled as learning data for learning. This learning model is a model for labeling or segmenting the positions of buildings from remote sensing images. By preparing such a learning model, the target feature detection unit 122 detects the building, which is the target real estate 31, from the remote sensing image 521. The above method is an example of realizing the target feature detection process by AI processing based on supervised learning. AI is an abbreviation for Artificial Intelligence.

[0038] FIG. 5 is a diagram showing another example of the detection processing operation of the detector in the target feature detection unit 122 according to this embodiment. In addition, the target feature detection unit 122 may detect a building corresponding to the shape of the building that is the target real estate 31 from the remote sensing image 521 using a matching process. Thus, the target feature detection unit 122 may detect the target real estate 31 from the remote sensing image 521 using a matching process. The above method is an example when realized by rule-based processing. For example, the target feature detection unit 122 detects a building with a shape corresponding to pre-prepared building shape information (for example, information that the building is a specific rectangle) from the image by pattern matching or feature point matching. The building shape information is an example of the detected building information that is information regarding the building to be detected.

[0039] <<Surrounding Feature Detection Process of Step S123>> In step S123, the surrounding feature detection unit 123 detects features around the target real estate 31 from the remote sensing image 521 based on the position of the target real estate 31 and the geospatial information 211. For example, the surrounding feature detection unit 123 detects roads around the target real estate 31 from the remote sensing image. The surrounding feature detection unit 123 detects features around the target real estate 31 from the remote sensing image using a detector. For example, the surrounding feature detection unit 123 detects roads around the target real estate 31 from the remote sensing image using a detector. In addition, the surrounding features may be, for example, features existing within a predetermined range from the position of the target real estate 31. Alternatively, features existing in a specific area where the target real estate 31 exists may be used as the surrounding features.

[0040] Specifically, it is as follows. For example, an example of the detection processing operation of the detector in the surrounding feature detection unit 123 is as follows. The surrounding feature detection unit 123 uses a remote sensing image 521 including surrounding features and label data with the positions of the surrounding features labeled as learning data for learning. As a result, the surrounding feature detection unit 123 prepares a learning model for labeling or segmenting the positions of the surrounding features from the remote sensing image. The surrounding feature detection unit 123 uses this learning model to detect the surrounding features from the remote sensing image 521. Similar to the target feature detection unit 122, the above method is a method for realizing the surrounding feature detection process by AI processing based on supervised learning.

[0041] Examples of the features around the detection target include features such as roads, slopes, walls, living fences, fences, trees, gateposts, parking lots, ponds, streets, vegetation, farmland, or soil. Also, railways, water areas (ponds, rivers, lakes, seas, and wetlands) can be considered. The surrounding feature detection unit 123 prepares a learned model including the surrounding features as described above by AI processing and extracts the positions of the surrounding features.

[0042] <<Feature analysis process in step S124>> In step S124, the feature analysis unit 124 analyzes the state of the target real estate 31 and the state of the features around the target real estate 31, and outputs the analysis result as real estate evaluation information 53. That is, the feature analysis unit 124 outputs the real estate state information 21 as the real estate evaluation information 53. The real estate state information 21 is information such as, for example, the area, shape, roof condition, and surface condition of the building. Also, the feature analysis unit 124 outputs, as the real estate evaluation information 53, the information indicating the state of the real estate or the feature itself among the real estate surrounding information 22. The information indicating the state of the real estate or the feature itself among the real estate surrounding information 22 is information such as, for example, the state of the boundary with the adjacent real estate, the shape of the land, the slope of the land, the presence or absence of a surrounding road, the width and length of the surrounding road, and the degree of concentration of the surrounding features.

[0043] <<Position relationship analysis process in step S125>> In step S125, the positional relationship analysis unit 125 analyzes the positional relationship between the target real estate 31 and the features in the vicinity of the target real estate 31, and outputs the analysis result as real estate evaluation information 53. For example, the positional relationship analysis unit 125 analyzes the positional relationship between the target real estate 31 and the roads in the vicinity of the target real estate 31, and outputs the analysis result as real estate evaluation information 53. That is, the positional relationship analysis unit 125 outputs, as real estate evaluation information 53, the real estate surrounding information 22 indicating the positional relationship between the target real estate 31 and the features in the vicinity of the target real estate 31 among the real estate surrounding information 22. For example, the positional relationship analysis unit 125 outputs, as real estate evaluation information 53, the road-related information 221 among the real estate surrounding information 22.

[0044] Hereinafter, the feature analysis process and the positional relationship analysis process will be described in detail. The image processing unit 120 may extract, as the real estate evaluation information 53 of the target real estate 31, information including at least one of various data of the real estate state information 21 and the real estate surrounding information 22 by performing image analysis on the remote sensing image. Alternatively, the image processing unit 120 may extract, as the real estate evaluation information 53 of the target real estate 31, information of a combination of at least two of various data of the real estate state information 21 and the real estate surrounding information 22 by performing image analysis on the remote sensing image.

[0045] More specifically, the feature analysis process is as follows. The feature analysis unit 124 outputs real estate evaluation information 53 including information on at least one of the roof condition of the building, the surface / appearance condition of the building, the shape of the land, and the slope of the land in the target real estate 31. In addition, the feature analysis unit 124 may output information such as the state of the surrounding high-voltage lines, the state of the surrounding electric wires, the presence or absence of surrounding roads, the width (road width) of the surrounding roads, the length of the surrounding roads, and the concentration degree of the surrounding features in the target real estate 31.

[0046] For example, the feature analysis unit 124 calculates information such as the length, width, and area of the features extracted by the surrounding feature detection unit 123. For example, in the case of roads and streets, the feature analysis unit 124 calculates the length and width. Also, in the case of a wall, a hedge, a fence, a tree, or a gatepost, the feature analysis unit 124 calculates the length or the area of the region surrounded by the feature. Further, for a slope, a parking lot, a pond, vegetation, farmland, soil, or a water area, the feature analysis unit 124 calculates the area.

[0047] Also, the feature analysis unit 124 may analyze the boundary state between the target real estate 31 and other real estates, and output information indicating the boundary state of the target real estate 31 as real estate evaluation information 53. For example, the feature analysis unit 124 extracts a polygon indicating the boundary of the target real estate 31 from a public drawing showing the position and shape of the land, and performs a process of superimposing it on the target real estate 31 detected in the remote sensing image. Then, the feature analysis unit 124 analyzes the superimposed result and acquires information indicating the boundary state of the target real estate 31.

[0048] FIG. 6 is a diagram showing an example of the positional relationship analysis process in the positional relationship analysis unit 125 according to the present embodiment. The positional relationship analysis process is more specifically as follows. For example, the positional relationship analysis unit 125 analyzes whether there is a road adjacent to the target real estate 31. The positional relationship analysis unit 125 outputs information indicating whether there is a road adjacent to the target real estate 31 as real estate evaluation information 53. Note that the information indicating whether there is a road adjacent to the target real estate 31 is an example of the road-related information 221.

[0049] Also, when there is a road adjacent to the target real estate 31, the positional relationship analysis unit 125 outputs information indicating the width at which the target real estate 31 is adjacent to the road as real estate evaluation information 53. For example, the positional relationship analysis unit 125 extracts a polygon indicating the boundary of the target real estate 31 from a public drawing showing the position and shape of the land, and performs a process of superimposing the target real estate 31 on the remote sensing image. Then, the positional relationship analysis unit 125 analyzes the superimposed result and acquires information indicating the width by which the target real estate 31 is in contact with the road. Note that the information indicating the width by which the target real estate 31 is in contact with the road is an example of the road-related information 221. Also, the positional relationship analysis unit 125 may calculate, for example, the length of the portion where the ground feature and the building are in contact or the degree of concentration of the ground feature.

[0050] The image processing unit 120 may extract, as real estate evaluation information 53, information on at least two combinations of various data such as the building area, shape, roof condition, and surface (appearance) condition in the real estate status information 21, and the condition of whether or not it is in contact with the road, the condition of the boundary of the real estate, the width by which the real estate is in contact with the road, the shape of the land, the slope of the land, the presence or absence of surrounding roads, the width of the surrounding roads, and the degree of concentration of surrounding ground features in the real estate surrounding information 22. Alternatively, the image processing unit 120 may extract, as real estate evaluation information 53, at least one piece of information from among the various data of the real estate status information 21 and the real estate surrounding information 22. Also, the image processing unit 120 may comprehensively extract, as real estate evaluation information 53, all the information of the various data of the real estate status information 21 and the real estate surrounding information 22.

[0051] Below, various data of the real estate evaluation information 53 will be described. The various data of the real estate evaluation information 53 are data that serve as evaluation items when evaluating the target real estate 31. The real estate status information 21 includes various data such as, for example, the building area, shape, roof condition, and surface (appearance) condition. Also, the real estate surrounding information 22 includes various data such as the condition of whether or not it is in contact with the road, the condition of the boundary of the real estate, the width by which the real estate is in contact with the road, the shape of the land, the slope of the land, the presence or absence of surrounding roads, the width of the surrounding roads, and the degree of concentration of surrounding ground features. In addition, the various data of the real estate evaluation information 53 described above are just examples, and information regarding other real estate may also be included.

[0052] As described above, the image processing unit 120 extracts the roads and ground features around the target real estate 311 from the remote sensing image 521. The image processing unit 120 analyzes the positional relationship between the extracted ground features or the positional relationship between the road and the ground features to extract the various data of the real estate evaluation information 53 shown below. In particular, the image processing unit 120 extracts the road-related information 221 by analyzing the positional relationship between the road and the ground features around the target real estate 31.

[0053] The definitions of the various data of the real estate evaluation information 53 are as follows. (1) Area: Information obtained by checking the area of the building. (2) Shape: Information obtained by checking the shape of the building. (3) Roof condition: Information obtained by checking the roof of the building from above. (4) Surface (appearance) condition: Information obtained by checking the surface (appearance) of the building. (5) Condition of whether it is in contact with a road: Information obtained by checking whether the road and the real estate are in contact. The image processing unit 120 extracts the road and the target real estate 31 in the target range 51 from the remote sensing image. The image processing unit 120 analyzes the positional relationship between the target real estate 31 such as land or building and the road in contact with the target real estate 31. The image processing unit 120 extracts the condition of whether the target real estate 31 is in contact with the road, that is, whether it is in contact with the road, based on the analysis result. (6) Real estate boundary situation: Information obtained by checking the boundary with adjacent real estate. For example, information indicating whether there are any structures such as buildings or plants protruding from the boundary with adjacent real estate. In addition, the information indicating the real estate boundary situation includes information on whether the real estate boundary is as per the official map. The image processing unit 120 extracts the polygon of the real estate boundary from the official map and performs a process of superimposing it on the remote sensing image to determine whether there are any structures such as buildings or plants protruding from the boundary with adjacent real estate and whether the real estate boundary is as per the official map. (7) Width of the real estate adjacent to the road: Information obtained by checking the length of the part where the real estate is adjacent to the road. The image processing unit 120 extracts the road in the target range 51 and the target real estate 31 such as land or building from the remote sensing image. The image processing unit 120 analyzes the positional relationship between the target real estate 31 and the road adjacent to the target real estate 31. The image processing unit 120 extracts the width of the part where the real estate is adjacent to the road based on the analysis result. (8) Shape of the land: Information obtained by checking the degree of obstruction to effective use in the actual shape of the real estate. (9) Slope of the land: Information obtained by checking the slope of the land. (10) Presence or absence of surrounding roads: Information obtained by checking whether there are roads in the vicinity. (11) Width of the surrounding roads: Information obtained by checking the width of the surrounding roads. (12) Concentration degree of surrounding features: For example, information obtained by checking the concentration degree of surrounding houses.

[0054] In addition, information such as information on cliff land and legal land, or the situation of surrounding high-voltage lines or electric wires can be various data of the real estate evaluation information 53. Cliff land and legal land are information obtained by checking the presence or absence of cliff land and legal land within the real estate. Regarding buildings, in addition to the information from (1) to (4) above, information such as whether there is an extension, renovation, loss, or repair can be obtained through image analysis processing.

[0055] <Evaluation process: Step S104> In step S104, the evaluation unit 130 evaluates the target real estate 31 using the real estate evaluation information 53. The evaluation by the evaluation unit 130 is performed based on a predetermined evaluation index 41. Then, the evaluation unit 130 creates an evaluation report 54 indicating the evaluation result. The evaluation items in the evaluation report 54 are various data of the real estate status information 21 and the real estate surrounding information 22. The evaluation report 54 only needs to include at least one piece of data among the various data of the real estate status information 21 and the real estate surrounding information 22. Alternatively, the evaluation report 54 may include a plurality of data among the various data of the real estate status information 21 and the real estate surrounding information 22. Alternatively, the evaluation report 54 may comprehensively include all the data of the various data of the real estate status information 21 and the real estate surrounding information 22.

[0056] In the present embodiment, the evaluation report 54 includes road-related information 221 among the various data of the real estate evaluation information 53. Specifically, the real estate evaluation information 53 such as whether the target real estate 31 is in contact with a road and the width of the part where the target real estate 31 is in contact with the road is included. Further, the evaluation report 54 may include information indicating the situation of the boundary of the target real estate 31 among the various data of the real estate evaluation information 53.

[0057] The evaluation index 41 based on the change of the real estate will be described. Depending on the change of the high-voltage line or electric wire, there may be building restrictions or the like on the collateral property. When building restrictions or the like occur, the evaluation amount of the collateral property may change. Regarding the various data of the real estate status information 21 and the real estate surrounding information 22, the evaluation index 41 is created from the perspective of whether it affects the evaluation amount of the collateral property. For example, if it is confirmed that the adjacent road becomes narrow and it becomes difficult for vehicles to enter and exit, or the sunlight condition deteriorates due to the construction of a building next to it, the evaluation amount of the collateral property will decrease.

[0058] <Update Process: Step S105> FIG. 7 is a flowchart showing an example of the update process by the update unit 140 according to the present embodiment. In the update process, the update unit 140 compares the information on the target real estate 31 registered in the evaluation target information 50 with the real estate evaluation information 53 to determine whether there is a change. If the update unit 140 determines that there is a change, it updates the evaluation target information 50. Alternatively, if the update unit 140 determines that there is a change, it may generate update information 55 for updating the real estate database 200 and update the real estate database 200. Specifically, it is as follows.

[0059] In step S201, the update unit 140 compares the information on the target real estate 31 registered in the evaluation target information 50 with the real estate evaluation information 53. If there is a change, the process proceeds to step S202. If there is no change, the process proceeds to step S203.

[0060] In step S201, the update unit 140 updates the evaluation target information 50 to the latest information using the real estate evaluation information 53. Also, the update unit 140 generates update information 55 for updating the real estate database 200 using the real estate evaluation information 53. The update unit 140 transmits the update information 55 to the real estate database 200 via the communication device 950. The information in the real estate database 200 is updated to the latest information by the update information 55.

[0061] In step S203, the update unit 140 determines whether there is an item in the information on the target real estate 31 registered in the evaluation target information 50 for which the information is not set. If there is an item for which the information is not set, the process proceeds to step S204. If there is no item for which the information is not set, the process ends.

[0062] In step S204, the update unit 140 generates support information 56 used to confirm items for which information is not set through on-site surveys. The support information 56 is output to an output device such as a display or a printer, for example. The support information 56 is information that users use for on-site surveys. The support information 56 includes, for example, the location information of the target real estate 31 and information such as survey items to be surveyed on-site. Note that the update unit 140 may similarly create the support information 56 for items for which information is not set among the information regarding the target real estate 31 registered in the real estate database 200.

[0063] As described above, the evaluation unit 130 creates an evaluation report 54 for the evaluation target information 50 or the target real estate 31 registered in the real estate database 200. Also, the update unit 140 creates update information 55 for updating the evaluation target information 50 or the real estate database 200 to the latest information as necessary. Further, for information that is not set in the evaluation target information 50 or the real estate database 200 and that could not be acquired by the image processing unit 120, the update unit 140 creates support information 56 used to confirm it through on-site surveys.

[0064] ***Other configurations*** <Modification Example 1> The image processing unit 120 may acquire a plurality of remote sensing images as remote sensing images. The plurality of remote sensing images are remote sensing images at different times, for example, remote sensing images at two times. The image processing unit 120 extracts the image changes between the remote sensing images in the plurality of remote sensing images and extracts the real estate evaluation information 53 based on the image changes. Alternatively, the image processing unit 120 may reflect the image changes in the extracted plurality of remote sensing images in the evaluation report. Alternatively, the image processing unit 120 may use the image changes in the extracted plurality of remote sensing images to provide feedback to the real estate evaluation process.

[0065] As methods of applying feedback using changes in an image, there are methods of outputting only the presence or absence of a change (such as an alert), and methods of measuring and outputting numerical or non-numerical information after the change through analysis. The image processing unit 120 extracts changes in the images between the plurality of remote sensing images in the remote sensing images, and outputs an alert based on the change in the image.

[0066] An example of outputting an alert when there is a change in the image will be described. For example, by specifying a specific lot number, it is possible to extract temporal changes in the image at the specific lot number by means of an alert. An alert may be issued when there is a change in the boundary situation or the situation of being in contact with a road in the land corresponding to the specific lot number. With this alert, only when there is some change in the boundary situation or the situation of being in contact with a road, it is possible to conduct an on-site investigation with human intervention, or to check the registered copy of the register and the survey drawing at the government office. Alternatively, by conducting a detailed analysis of the satellite image by a person, the target of the on-site investigation with human intervention or the satellite image analysis can be narrowed down, the change can be grasped efficiently and quickly, and the on-site investigation can be conducted efficiently.

[0067] Another example of outputting an alert when there is a change in the image will be described. For example, by specifying a specific lot number, it is possible to extract temporal changes in the image at the specific lot number by means of an alert. Not only changes such as those in the above example, but also an alert may be issued when there is a deviation between the legal width and the current width in the land's contact with a road and the surrounding roads, or when the road on the map and the current road are displaced. With this alert, when there is any change in the situation of whether the real estate abuts on the road, it can be considered that there is an error in the official map or the survey map itself, or that the situation of whether it abuts on the road, the adjacent real estate, or the land corresponding to a specific lot number may have changed. Similar to the above example, the object of the on-site survey can be efficiently and quickly confirmed.

[0068] The image processing unit 120 acquires, for example, remote sensing images at two times on the same orbit by the same satellite as a plurality of remote sensing images. Alternatively, the image processing unit 120 may acquire each remote sensing image on a different orbit by the same satellite as a plurality of remote sensing images. Alternatively, the image processing unit 120 may acquire remote sensing images at two times by different satellites as a plurality of remote sensing images. Also, the plurality of remote sensing images for observing the change of the image may be three or more.

[0069] <Modification Example 2> The image processing unit 120 may compare the remote sensing image with the official map information which is the boundary information of the real estate, and extract the real estate evaluation information 53 based on the comparison result. The image processing unit 120 extracts the change of the image in the remote sensing image by comparing the official map information with the remote sensing image, and extracts the real estate evaluation information 53 based on the change of the image.

[0070] <Modification Example 3> The image processing unit 120 may acquire the geospatial information 211 including the target range 51, and extract the real estate evaluation information 53 using the remote sensing image and the geospatial information. The geospatial information is, for example, GIS information. GIS is an abbreviation for Geographic Information System. Also, the geospatial information may be three-dimensional point cloud data which is the information of ground objects obtained by a method such as MMS. MMS is an abbreviation for Mobile Mapping System. By using geospatial information, more accurate real estate appraisal information can be obtained.

[0071] Regarding image analysis using GIS information in Modification Example 3, it will be described in detail below. When collating GIS information and satellite images, link the satellite images with the extract of the register, public survey map, building drawings, or public survey standard maps, etc. Regarding the extract of the register corresponding to the lot number, obtain the position coordinate information corresponding to the lot number from the GIS database storing the GIS information.

[0072] For GIS information, the following position coordinates are preset and linked. · The position coordinates of the address corresponding to the lot number, the representative point or reference point (such as a public reference point) of the extract of the register and building drawings corresponding to the lot number · The position coordinates of the representative point or reference point corresponding to the lot number in the survey drawing (single-parcel survey drawing or public survey, etc.) or the land area survey drawing (Article 77 of the Real Estate Registration Regulations) · The position coordinates of the representative point or reference point corresponding to the lot number in the public survey map or the 14-section map

[0073] These position coordinates are preferably expressed in a world geodetic system such as WGS84, but may also be information on latitude / longitude / height expressed in the Japanese geodetic system or the plane rectangular coordinate system. As the representative point or reference point, a certified reference point may be used as the coordinate value of the boundary point based on the results of surveys based on basic triangulation points, etc. Also, as the representative point or reference point, the origin of the map frame, the coordinates of the four corners of the land, the centroid position of the land, the boundary point coordinates, the coordinates of the buried (installed) boundary markers or boundary points, the intersection of the boundary line with the adjacent real estate or road, or the representative point of the land use within a single parcel may be used.

[0074] Also, as GIS information, the map data used in a navigation device may be simply used. In this case, the approximate position of the reference point or representative point corresponding to the lot number may be obtained using the position coordinates of the representative point or reference point corresponding to the address corresponding to the lot number.

[0075] When matching satellite images with GIS information, the reference position in the satellite image data is matched, associated, or linked with the position in the registered transcript, official map, or survey drawing. The reference position in the satellite image data refers to the reference position in the satellite image such as the position coordinates of the GCP obtained from the satellite image, the imaging designated point imaged or obtained by the satellite-mounted camera or radar, or the intersection point where the line of sight axis intersects the ground surface including the target range 51. GCP is the abbreviation of Ground Control Points. By matching the reference position in the satellite image data with the position of the representative point or reference point corresponding to the lot number obtained from the GIS information, the reference position in the satellite image data is matched, associated, or linked with the position in the registered transcript, official map, or survey drawing.

[0076] Also, in the case of a new evaluation, the position coordinate information corresponding to the lot number in the GIS information may be newly stored using the coordinates obtained by a new survey. In this case, the coordinates may be obtained by a public survey. The survey may be performed by positioning using a GNSS receiver. GNSS is the abbreviation of Global Navigation Satellite System. For example, use the equipment specified in Article 93 of the Survey Work Regulations for the Land Readjustment Projects of the Ministry of Land, Infrastructure, Transport and Tourism (see 「https: / / www.mlit.go.jp / crd / city / sigaiti / materials / sokuryou / sagyoukitei.pdf」). Also, 「Vehicle-mounted Photo Laser Survey」 (e.g., MMS) specified in the 「Guidelines for Work Regulations」 may be used (see 「https: / / psgsv2.gsi.go.jp / koukyou / jyunsoku / pdf / R5 / R5_junsoku.pdf」). Also, the 「Manual for Public Survey Using LidarSLAM Technology」 may be used (「https: / / psgsv2.gsi.go.jp / koukyou / public / lidarslam / doc / lidarslam_manual.pdf」).

[0077] In addition, when there are no coordinate values corresponding to the lot number in the GIS information, in addition to obtaining them by new surveying, an approximate position corresponding to the lot number may be obtained using the map data used in the navigation device. In this case, a "reference position in the satellite image" including the target range corresponding to the approximate position may be referred to, and a satellite image corresponding to the reference position may be referred to. A relative comparison may be made between the referred satellite image and the outer shape or surrounding environment of the official drawing, survey map, or building drawing. Based on this comparison, the coordinate positions of the boundary situation of the land corresponding to the lot number or the situation of whether it is in contact with a road may be measured.

[0078] Note that satellites can achieve work efficiency improvement and comprehensive surveys. Therefore, for example, an imaging plan may be made to control the orbit and attitude of the satellite by using a satellite image observation service in cooperation with satellite control. For example, an imaging plan may be made to include the target range 51 including a specific lot number in one imaging or multiple imagings. Also, the satellite may pass directly above a specific lot number to obtain a directly below image. Also, the line of sight of the imaging device mounted on the satellite may pass through a predetermined position of a specific lot number. Also, the imaging device mounted on the satellite may image directly above a predetermined ground object such as a steel tower or a utility pole. Also, the shadow of a predetermined ground object such as a steel tower or a utility pole may be imaged. Also, imaging may be performed from an oblique direction of a predetermined ground object such as a steel tower or a utility pole. Also, the distance, height, or existence position to a predetermined ground object such as an electric wire suspended from a steel tower or a utility pole may be measured using LiDAR or SAR (synthetic aperture radar). Also, during one imaging opportunity when the satellite passes through a predetermined orbit, imaging may be performed so as to trace the target ranges 51 corresponding to a plurality of specific lot numbers.

[0079] <Modification Example 4> FIG. 8 is a diagram showing a configuration example of the real estate evaluation device 100 according to Modification Example 4 of the present embodiment. In the real estate evaluation device 100 according to Modification Example 4 of the present embodiment, in addition to the configuration of FIG. 1, a list of evaluation item information 57 is provided in the storage unit 150. The evaluation item list information 57 is a list of evaluation items for evaluating the target real estate 31. In the evaluation item list information 57, for example, various data of the real estate evaluation information 53 are set as a list of evaluation items for evaluating the target real estate 31.

[0080] The update unit 140 compares the information on the target real estate 31 registered in the real estate database 200 with the evaluation item list information 57. The update unit 140 extracts, as information that cannot be updated with the real estate evaluation information 53, items for which information is not set among the information on the target real estate 31 registered in the real estate database 200. Then, the update unit 140 generates support information 56 for on-site investigation of the information that cannot be updated with the real estate evaluation information 53.

[0081] <Modification Example 5> FIG. 9 is a diagram showing a configuration example of the real estate evaluation apparatus 100 according to Modification Example 5 of the present embodiment. In the real estate evaluation apparatus 100 according to Modification Example 5 of the present embodiment, in addition to the configuration of FIG. 1, a real estate polygon database 58 is provided in the storage unit 150. Note that the real estate polygon database 58 may be included in the real estate evaluation information 53. Alternatively, the real estate polygon database 58 may be provided in a device external to the real estate evaluation apparatus 100.

[0082] FIG. 10 is a diagram showing a configuration example of the image processing unit 120 according to Modification Example 5 of the present embodiment. In the image processing unit 120 according to Modification Example 5 of the present embodiment, a form of reusing the information in the real estate polygon database 58 is shown.

[0083] The real estate evaluation apparatus 100 includes a real estate polygon database 58 in which information on real estate associated with a map is set. The ground feature analysis unit 124 polygonizes the state of the target real estate 31 and the state of the ground features around the target real estate 31, and outputs the polygonized information to the real estate polygon database 58. In addition, the positional relationship analysis unit 125 polygonizes the positional relationship between the target real estate 31 and the features around the target real estate 31, and outputs the polygonized information to the real estate polygon database 58.

[0084] In FIG. 10, the feature analysis unit 124 and the positional relationship analysis unit 125 show the process of temporarily storing the polygonized information in the real estate evaluation information 53 and then storing the polygonized information from there in the real estate polygon database 58. In addition, the feature analysis unit 124 and the positional relationship analysis unit 125 may directly store the polygonized information in the real estate polygon database 58. Alternatively, the feature analysis unit 124 and the positional relationship analysis unit 125 may transmit the polygonized information to an external real estate polygon database 58 via the communication device 950.

[0085] In addition, when the polygonized information is stored in the real estate evaluation information 53, the update unit 140 may determine whether information regarding the target real estate 31 is already registered in the real estate polygon database 58. Then, when information regarding the target real estate 31 is already registered in the real estate polygon database 58, the update unit 140 may execute a process of updating the real estate polygon database 58 to the latest version.

[0086] In addition, the image processing unit 120 may reuse the information regarding the real estate registered in the real estate polygon database 58 as the geospatial information 211.

[0087] Stating the configuration of Modification Example 5 in other words, it is as follows. In addition to being numerical information such as real estate status information 21 and real estate surrounding information 22, the real estate evaluation information 53 has information obtained by polygonizing the target real estate and the features around the target real estate. The polygonized information is stored in the real estate polygon database 58. The real estate polygon database 58 is also referred to as a real estate GIS database. When there is registered data in the real estate polygon database 58 during the analysis of the target real estate, the image processing unit 120 compares the registered data in the real estate polygon database 58 with the latest real estate evaluation information and updates the real estate polygon database 58 to the latest. Also, the image processing unit 120 reuses the information regarding the real estate registered in the real estate polygon database 58 as geospatial information 211. As described above, according to the real estate evaluation apparatus according to Modification 5, the accuracy of evaluation can be further improved.

[0088] <Modification 6> In the present embodiment, the functions of the range acquisition unit 110, the image processing unit 120, the evaluation unit 130, and the update unit 140 are realized by software. As a modification, the functions of the range acquisition unit 110, the image processing unit 120, the evaluation unit 130, and the update unit 140 may be realized by hardware. Specifically, the real estate evaluation apparatus 100 includes an electronic circuit 909 instead of the processor 910.

[0089] FIG. 11 is a diagram showing a configuration example of the real estate evaluation apparatus 100 according to Modification 6 of the present embodiment. The electronic circuit 909 is a dedicated electronic circuit that realizes the functions of the range acquisition unit 110, the image processing unit 120, the evaluation unit 130, and the update unit 140. Specifically, the electronic circuit 909 is a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, a logic IC, a GA, an ASIC, or an FPGA. GA is an abbreviation for Gate Array. ASIC is an abbreviation for Application Specific Integrated Circuit. FPGA is an abbreviation for Field-Programmable Gate Array.

[0090] The functions of the range acquisition unit 110, the image processing unit 120, the evaluation unit 130, and the update unit 140 may be realized by one electronic circuit or may be distributed and realized by a plurality of electronic circuits.

[0091] As another modification, some functions of the range acquisition unit 110, the image processing unit 120, the evaluation unit 130, and the update unit 140 may be realized by an electronic circuit, and the remaining functions may be realized by software. Further, some or all of the functions of the range acquisition unit 110, the image processing unit 120, the evaluation unit 130, and the update unit 140 may be realized by firmware.

[0092] Each of the processor and the electronic circuit is also called a processing circuit. That is, the functions of the range acquisition unit 110, the image processing unit 120, the evaluation unit 130, and the update unit 140 are realized by the processing circuit.

[0093] ***Explanation of the effects of the present embodiment*** In the real estate evaluation apparatus 100 according to the present embodiment, it is possible to analyze the state of the target real estate, the state of the roads around the target real estate, and the positional relationship between the target real estate and the surrounding features of the target real estate. Thus, in the real estate evaluation apparatus 100 according to the present embodiment, by providing a method for extracting information necessary for evaluating the property value, it is possible to comprehensively substitute the evaluation items of the target real estate. Therefore, in the real estate evaluation apparatus 100 according to the present embodiment, it is possible to realize the efficiency improvement of the period and cost related to the real estate evaluation work. In addition, it is possible to omit the on-site survey, realize the efficiency improvement of the period and cost related to the work, and suppress the restrictions in the work time and work range.

[0094] Further, in the real estate evaluation apparatus 100 according to the present embodiment, it is possible to comprehensively substitute the evaluation items in the target real estate by using the remote sensing image. Thereby, it is possible to omit the on-site survey. In addition, in the real estate evaluation apparatus according to the present embodiment, it is possible to automate the work of evaluating the target real estate and creating an evaluation report. Thus, according to the real estate evaluation device 100 according to this embodiment, the work of evaluating the property value can be automated and made one-stop, and the efficiency of the period and cost related to the work can be realized. Further, in the real estate evaluation device 100 according to this embodiment, by analyzing the remote sensing image, various data of the real estate status information and the real estate surrounding information can be extracted. By using a remote sensing image such as a satellite image, it is also possible to check locations such as roofs and rooftops that cannot be seen visually.

[0095] Further, in the real estate evaluation device 100 according to this embodiment, an evaluation report is created for the real estate registered in the real estate database by using the real estate evaluation information obtained by analyzing the remote sensing image. Therefore, according to the real estate evaluation device 100 according to this embodiment, labor saving of the work for creating the evaluation report can be realized.

[0096] Further, in the real estate evaluation device 100 according to this embodiment, update information for updating the information in the real estate database can be generated by using the latest real estate evaluation information. Therefore, according to the real estate evaluation device 100 according to this embodiment, one-stop updating of the real estate database can be realized, and further labor saving can be achieved.

[0097] Further, in the real estate evaluation device 100 according to this embodiment, by using the latest real estate evaluation information, the information in the real estate database is updated, and support information for on-site investigation can be created for information that could not be automatically acquired. Therefore, according to the real estate evaluation device 100 according to this embodiment, the user can know the evaluation items that require on-site investigation and comprehensively acquire the evaluation items necessary for the minimum on-site investigation. In addition, by creating support information, checkpoints can be identified based on individual factors and on-site investigations can be conducted. Examples of checkpoints include the situation of being in contact with a road (direction, road width, and if there is a river between the road, the situation of the bridge spanning it (including the permission status)), changes in the boundaries of real estate, the presence or absence of unregistered buildings, the disappearance of registered properties, slopes / gradients within the site, and the situation of cliff areas. Usually, it is not possible to enter the site of the target property, so it can only be viewed from the outside. Since there may be trouble in some cases, for factories, etc., it is only possible to view the exterior from a distance. According to the real estate evaluation apparatus according to the present embodiment, changes such as unregistered properties in parts that cannot be seen from outside the site can be detected using satellite data.

[0098] In the above-described Embodiment 1, each part of the real estate evaluation apparatus has been described as an independent functional block. However, the configuration of the real estate evaluation apparatus does not have to be the configuration as in the above-described embodiment. The functional blocks of the real estate evaluation apparatus may have any configuration as long as they can realize the functions described in the above-described embodiment. Further, the real estate evaluation apparatus may be not a single apparatus but a system composed of a plurality of apparatuses. Also, in Embodiment 1, a plurality of parts may be combined and implemented. Alternatively, in Embodiment 1, one part may be implemented. In addition, Embodiment 1 may be implemented in any combination, either as a whole or partially. That is, in Embodiment 1, free combinations of each embodiment, or modifications of any constituent elements of each embodiment, or omissions of any constituent elements in each embodiment are possible.

[0099] Note that the above-described embodiments are essentially preferred examples and are not intended to limit the scope of the present disclosure, the scope of the application of the present disclosure, and the scope of the use of the present disclosure. The above-described embodiments can be variously changed as necessary. For example, the procedures described using a flowchart or a sequence diagram may be changed as appropriate.

[0100] Hereinafter, aspects of the present disclosure will be summarized and described as appendices.

[0101] (Appendix 1) Based on the location of the target real estate, which is the real estate to be evaluated, and the geospatial information, image analysis is performed on the location of the target real estate and the periphery of the location of the target real estate in a remote sensing image with the target range including the location of the target real estate as the observation range, and the state of the target real estate and the state of the periphery of the target real estate are output as real estate evaluation information, which is information used for the evaluation of the target real estate, and an image processing unit is provided. The image processing unit A target feature detection unit that detects the target real estate from the remote sensing image based on the location of the target real estate, A peripheral feature detection unit that detects features around the target real estate from the remote sensing image based on the location of the target real estate and the geospatial information, A feature analysis unit that analyzes the state of the target real estate and the state of the features around the target real estate and outputs the analysis result as the real estate evaluation information, A positional relationship analysis unit that analyzes the positional relationship between the target real estate and the features around the target real estate and outputs the analysis result as the real estate evaluation information A real estate evaluation device comprising (Appendix 2) The real estate evaluation device Comprises a real estate polygon database in which information regarding real estate associated with a map is set, The feature analysis unit Polygonalizes the state of the target real estate and the state of the features around the target real estate, and outputs the polygonalized information to the real estate polygon database, which is the information regarding the real estate, The positional relationship analysis unit Polygonalizes the positional relationship between the target real estate and the features around the target real estate, and outputs the polygonalized information to the real estate polygon database. The real estate evaluation device according to Appendix 1. (Appendix 3) The real estate evaluation device An update unit that determines whether information regarding the target real estate is already registered in the real estate polygon database, and updates the real estate polygon database to the latest version if the information regarding the target real estate is already registered in the real estate polygon database. The real estate evaluation apparatus according to appended note 2. (Appended note 4) The image processing unit The real estate evaluation apparatus according to appended note 2 or appended note 3, which reuses the information regarding the real estate registered in the real estate polygon database as the geospatial information. (Appended note 5) The target feature detection unit The real estate evaluation apparatus according to any one of appended notes 1 to 4, which trains a model that labels or segments the position of a building from a remote sensing image by using, as learning data, a remote sensing image including the building and label data in which the position of the building is labeled, and thereby detects the building that is the target real estate from the remote sensing image. (Appended note 6) The target feature detection unit The real estate evaluation apparatus according to any one of appended notes 1 to 4, which detects the target real estate from the remote sensing image by detecting, from the remote sensing image, a building that corresponds to the shape of the building that is the target real estate by using a matching process. (Appended note 7) The surrounding feature detection unit The real estate evaluation apparatus according to any one of appended notes 1 to 6, which trains a model that labels or segments the position of surrounding features from a remote sensing image by using, as learning data, a remote sensing image including the surrounding features and label data in which the position of the surrounding features is labeled, and thereby detects the surrounding features from the remote sensing image. (Appended note 8) The positional relationship analysis unit Analyze whether there is a road adjacent to the target real estate, and output information indicating whether there is a road adjacent to the target real estate as the real estate evaluation information. The real estate evaluation apparatus according to any one of Appendices 1 to 7. (Appendix 9) The positional relationship analysis unit When there is a road adjacent to the target real estate, output information indicating the width by which the target real estate is adjacent to the road as the real estate evaluation information. The real estate evaluation apparatus according to Appendix 8. (Appendix 10) The positional relationship analysis unit Extract a polygon indicating the boundary of the target real estate from a public drawing showing the position and shape of the land, perform a process of superimposing on the target real estate detected in the remote sensing image, and obtain information indicating the width by which the target real estate is adjacent to the road. The real estate evaluation apparatus according to Appendix 9. (Appendix 11) The ground feature analysis unit Analyze the state of the boundary between the target real estate and other real estates, and output information indicating the state of the boundary of the target real estate as the real estate evaluation information. The real estate evaluation apparatus according to any one of Appendices 1 to 10. (Appendix 12) The ground feature analysis unit Extract a polygon indicating the boundary of the target real estate from a public drawing showing the position and shape of the land, perform a process of superimposing on the target real estate detected in the remote sensing image, and obtain information indicating the state of the boundary of the target real estate. The real estate evaluation apparatus according to Appendix 11. (Appendix 13) A real estate evaluation method in which a computer analyzes the position of a target real estate, which is a real estate to be evaluated, and its vicinity in a remote sensing image with a target range including the position of the target real estate as an observation range based on the position and geospatial information of the target real estate, and outputs the state of the target real estate and the state of the vicinity of the target real estate as real estate evaluation information, which is information used for evaluating the target real estate, The computer Based on the location of the target real estate, detect the target real estate from the remote sensing image, Based on the location of the target real estate and the geospatial information, detect the features around the target real estate from the remote sensing image, Analyze the state of the target real estate and the state of the features around the target real estate, and output the analysis result as the real estate evaluation information, A real estate evaluation method for analyzing the positional relationship between the target real estate and the features around the target real estate, and outputting the analysis result as the real estate evaluation information. (Appendix 14) Based on the location of the target real estate, which is the real estate to be evaluated, and the geospatial information, perform image analysis on the location of the target real estate and the periphery of the location of the target real estate in the remote sensing image with the target range including the location of the target real estate as the observation range, and output the state of the target real estate and the state of the periphery of the target real estate as real estate evaluation information, which is information used for the evaluation of the target real estate, and A real estate evaluation program for causing a computer to execute The image analysis process includes A target feature detection process for detecting the target real estate from the remote sensing image based on the location of the target real estate, A peripheral feature detection process for detecting the features around the target real estate from the remote sensing image based on the location of the target real estate and the geospatial information, A feature analysis process for analyzing the state of the target real estate and the state of the features around the target real estate, and outputting the analysis result as the real estate evaluation information, A positional relationship analysis process for analyzing the positional relationship between the target real estate and the features around the target real estate, and outputting the analysis result as the real estate evaluation information A real estate evaluation program for causing a computer to execute.

Description of Reference Signs

[0102] 21 Real estate status information, 22 Real estate surrounding information, 31 Target real estate, 41 Evaluation indicators, 50 Evaluation target information, 51 Target range, 52 Remote sensing image database, 521 Remote sensing image, 53 Real estate evaluation information, 54 Evaluation report, 55 Update information, 56 Support information, 57 List of evaluation items information, 58 Real estate polygon database, 100 Real estate evaluation device, 110 Range acquisition unit, 120 Image processing unit, 121 Image search unit, 122 Target feature detection unit, 123 Surrounding feature detection unit, 124 Feature analysis unit, 125 Position relationship analysis unit, 130 Evaluation unit, 140 Update unit, 150 Memory unit, 200 Real estate database, 210 Geospatial information database, 211 Geospatial information, 909 Electronic circuit, 910 Processor, 921 Memory, 922 Auxiliary storage device, 930 Input interface, 940 Output interface, 950 Communication device.

Claims

1. Based on the location of the target real estate, which is the real estate to be evaluated, and the geospatial information, image analysis is performed on the location of the target real estate and the vicinity of the location of the target real estate in a remote sensing image with the target range including the location of the target real estate as the observation range, and the state of the target real estate and the state of the vicinity of the target real estate are output as real estate evaluation information, which is information used for the evaluation of the target real estate, and includes an image processing unit, The image processing unit is, A target feature detection unit that detects the target real estate from the remote sensing image based on the location of the target real estate, A surrounding feature detection unit that detects features in the vicinity of the target real estate from the remote sensing image based on the location of the target real estate and the geospatial information, A feature analysis unit that analyzes the state of the target real estate and the state of the features in the vicinity of the target real estate and outputs the analysis result as the real estate evaluation information, A positional relationship analysis unit that analyzes the positional relationship between the target real estate and the features in the vicinity of the target real estate and outputs the analysis result as the real estate evaluation information A real estate evaluation device comprising.

2. The real estate evaluation device, Comprises a real estate polygon database in which information regarding real estate associated with a map is set, The feature analysis unit, Polygonalizes the state of the target real estate and the state of the features in the vicinity of the target real estate, and outputs the polygonalized information to the real estate polygon database, which is the information regarding the real estate, The positional relationship analysis unit, The real estate evaluation device according to claim 1, which polygonalizes the positional relationship between the target real estate and the features in the vicinity of the target real estate and outputs the polygonalized information to the real estate polygon database.

3. The real estate evaluation device, Determines whether information regarding the target real estate is already registered in the real estate polygon database, and if the information regarding the target real estate is already registered in the real estate polygon database, comprises an update unit that updates the real estate polygon database to the latest version. The real estate evaluation device according to claim 2.

4. The image processing unit, The real estate evaluation device according to claim 2 or claim 3, which reuses the information regarding the real estate registered in the real estate polygon database as the geospatial information.

5. The target feature detection unit is, Using a remote sensing image including a building and label data with the position of the building labeled as learning data for learning, and preparing a model for labeling or segmenting the position of the building from the remote sensing image, the real estate evaluation device according to any one of claims 1 to 3 for detecting the building which is the target real estate from the remote sensing image.

6. The target feature detection unit The real estate evaluation device according to any one of claims 1 to 3, which detects the building corresponding to the shape of the building which is the target real estate from the remote sensing image by using a matching process, and thereby detects the target real estate from the remote sensing image.

7. The surrounding feature detection unit Using a remote sensing image including surrounding features and label data with the positions of the surrounding features labeled as learning data for learning, and preparing a model for labeling or segmenting the positions of the surrounding features from the remote sensing image, the real estate evaluation device according to any one of claims 1 to 3 for detecting the surrounding features from the remote sensing image.

8. The positional relationship analysis unit The real estate evaluation device according to any one of claims 1 to 3, which analyzes whether there is a road adjacent to the target real estate, and outputs information indicating whether there is a road adjacent to the target real estate as the real estate evaluation information.

9. The positional relationship analysis unit The real estate evaluation device according to claim 8, which, when there is a road adjacent to the target real estate, outputs information indicating the width by which the target real estate is in contact with the road as the real estate evaluation information.

10. The positional relationship analysis unit The real estate evaluation device according to claim 9, which extracts a polygon indicating the boundary of the target real estate from a public drawing showing the position and shape of the land, performs a process of superimposing on the target real estate detected in the remote sensing image, and obtains information indicating the width by which the target real estate is in contact with the road.

11. The feature analysis unit The real estate evaluation device according to any one of claims 1 to 3, which analyzes the state of the boundary between the target real estate and other real estates, and outputs information indicating the state of the boundary of the target real estate as the real estate evaluation information.

12. The feature analysis unit Extract a polygon indicating the boundary of the target real estate from a public map showing the location and shape of the land, perform a process of superimposing on the target real estate detected in the remote sensing image, and acquire information indicating the state of the boundary of the target real estate. The real estate evaluation device according to claim 11.

13. A real estate evaluation method in which a computer analyzes an image of a target real estate including the location of the target real estate and the periphery of the location of the target real estate in a remote sensing image having an observation range as a target range including the location of the target real estate based on the location of the target real estate which is the real estate to be evaluated and geospatial information, and outputs the state of the target real estate and the state of the periphery of the target real estate as real estate evaluation information which is information used for the evaluation of the target real estate, wherein the computer detects the target real estate from the remote sensing image based on the location of the target real estate, detects features around the target real estate from the remote sensing image based on the location of the target real estate and the geospatial information, analyzes the state of the target real estate and the state of the features around the target real estate, and outputs the analysis result as the real estate evaluation information, A real estate evaluation method for analyzing the positional relationship between the target real estate and the features around the target real estate and outputting the analysis result as the real estate evaluation information.

14. A real estate evaluation program for causing a computer to execute an image analysis process of analyzing an image of a target real estate including the location of the target real estate and the periphery of the location of the target real estate in a remote sensing image having an observation range as a target range including the location of the target real estate based on the location of the target real estate which is the real estate to be evaluated and geospatial information, and outputting the state of the target real estate and the state of the periphery of the target real estate as real estate evaluation information which is information used for the evaluation of the target real estate, wherein the image analysis process is a target feature detection process for detecting the target real estate from the remote sensing image based on the location of the target real estate, is a peripheral feature detection process for detecting features around the target real estate from the remote sensing image based on the location of the target real estate and the geospatial information, is a feature analysis process for analyzing the state of the target real estate and the state of the features around the target real estate and outputting the analysis result as the real estate evaluation information, A positional relationship analysis process that analyzes the positional relationship between the target real estate and the features around the target real estate and outputs the analysis result as the real estate evaluation information, and A real estate evaluation program that causes a computer to execute.

Images