Land status assessment device, land status assessment method, and land status assessment program

Abstract

The land status grasping device (100) includes a land use classification unit (110) that analyzes a remote sensing image (52) and sets label information (511) of a survey area. In addition, a local information estimation unit (120) estimates the state and condition of the land at a survey point where an IoT device (61) is present as local condition information (53) based on log information (31) transmitted from the IoT device (61). A high accuracy improvement unit (140) estimates the state and condition of the land at points other than the survey point in the survey area based on the remote sensing image (52) and the local condition information (53), and generates area status information (55) that represents the state and condition of the land in the survey area with higher accuracy than the label information (511).

Description

[Technical field]

[0001] The present disclosure relates to a land status assessment device, a land status assessment method, and a land status assessment program. [Background technology]

[0002] There are methods for collecting information from multiple devices and estimating the extent of a natural disaster based on the collected information. Patent Document 1 discloses a technique for extracting candidate areas to be surveyed from sensor information for surface information acquired from remote sensing images at the time of a disaster, and determining the survey area. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] International Publication No. 2023 / 017612 Summary of the Invention [Problem to be solved by the invention]

[0004] The technology of Patent Document 1 only determines the survey area, and is not capable of grasping the land condition and situation of the survey area with high accuracy.

[0005] The present disclosure aims to grasp the land state and conditions of a survey area with greater accuracy. [Means for solving the problem]

[0006] The land status grasping device according to the present disclosure comprises: a land use classification unit that analyzes remote sensing images and sets label information that represents the land cover status of the survey area; a local information estimation unit that receives log information transmitted from an IoT device (Internet of Things device) installed in the survey area and estimates the state and situation of the land at the survey point where the IoT device is located as local situation information based on the log information; The system further includes a precision improvement unit that estimates the state and condition of the land at points other than the survey point in the survey area based on the remote sensing image and the local condition information, and generates area condition information that represents the state and condition of the land in the survey area with higher accuracy than the label information. Effect of the Invention

[0007] In the land status grasping device according to the present disclosure, the local information estimation unit receives log information transmitted from an IoT device installed in a survey area. The local information estimation unit estimates the state and condition of the land at the survey point where the IoT device is located as local situation information based on the log information. The high accuracy unit estimates the state and condition of the land at points other than the points in the survey area based on the remote sensing image and the local situation information, and generates area status information that represents the state and condition of the land in the survey area with higher accuracy than the label information. Therefore, the land status grasping device according to the present disclosure has an effect of being able to grasp the state and condition of the land in the survey area with higher accuracy. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram showing an example of the configuration of a land status grasping device according to a first embodiment. [Diagram 2] 4 is a flow diagram showing an example of the operation of the land status grasping device according to the first embodiment. [Diagram 3] FIG. 2 is a diagram showing an example of data acquired by the land status grasping device according to the first embodiment. [Figure 4] FIG. 4 is a schematic diagram showing an example of a flow of a land status grasping process according to the first embodiment. [Diagram 5] FIG. 2 is a schematic diagram showing Example 1 of a land situation grasping process in a survey area according to the first embodiment. [Figure 6]FIG. 13 is a diagram showing an example in which interpolation is performed using sensor data F in Example 1 of the land status grasping process according to the first embodiment. [Figure 7] FIG. 4 is a schematic diagram showing Example 2 of a land situation grasping process in a survey area according to the first embodiment. [Figure 8] FIG. 13 is a schematic diagram showing Example 3 of a land situation grasping process in a survey area according to the first embodiment. [Figure 9] FIG. 13 is a diagram showing a configuration example of a land status grasping device according to a modified example of the first embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, the present embodiment will be described with reference to the drawings. In each drawing, the same or corresponding parts are given 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 drawing mainly indicate the flow of data or the flow of processing. In addition, the relationship of the size of each component in the following drawings may differ from the actual one. In addition, in the description of the embodiment, directions or positions such as up, down, left, right, front, back, front, and back may be indicated. These notations are for convenience of explanation and do not limit the arrangement, direction, or orientation of devices, instruments, parts, etc.

[0010] Embodiment 1 ***Configuration Description*** FIG. 1 is a diagram showing an example of the configuration of a land status grasping device 100 according to the present embodiment. The land status grasping device 100 is a device that grasps the state and situation of land in a survey area by using a remote sensing image 52 and log information 31 and sensor data 32 from an IoT device 61. In this embodiment, the land status grasping device 100 is also called a wide-area behavior grasping device that grasps the state and situation of land including the behavior of things in the survey area.

[0011] The land status assessment device 100 is a computer. The land status assessment 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 the other hardware via signal lines and controls the other hardware.

[0012] The land status grasping device 100 comprises, as functional elements, a land use classification unit 110, a local information estimation unit 120, a behavior analysis unit 130, a precision improvement unit 140, and a memory unit 150. The memory unit 150 stores a land use map 51, a remote sensing image 52, local situation information 53, local behavior information 54, and area state information 55. The land use map 51 includes label information 511 that indicates the land coverage status.

[0013] The functions of the land use classification unit 110, the local information estimation unit 120, the dynamics analysis unit 130, and the accuracy improvement unit 140 are realized by software. The storage unit 150 is provided in the memory 921. The storage unit 150 may be provided in the auxiliary storage device 922, or may be provided in a distributed manner in the memory 921 and the auxiliary storage device 922.

[0014] The processor 910 is a device that executes a land status assessment program. The land status assessment program is a program that realizes the functions of the land use classification unit 110, the local information estimation unit 120, the dynamics analysis unit 130, and the accuracy improvement 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 and 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 a HDD. The auxiliary storage device 922 may also be a portable storage medium such as an SD (registered trademark) memory card, CF, NAND flash, a flexible disk, an optical disk, a compact disk, a Blu-ray (registered trademark) disk, or a 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, a keyboard, or a touch panel. Specifically, the input interface 930 is a USB terminal. 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.

[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 called a display interface. HDMI (registered trademark) is an abbreviation for High Definition Multimedia Interface. LCD is an abbreviation for Liquid Crystal Display.

[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. NIC is an abbreviation for Network Interface Card.

[0019] The land situation grasping program is executed in the land situation grasping device 100. The land situation grasping program is read into the processor 910 and executed by the processor 910. In addition to the land situation grasping program, the OS is also stored in the memory 921. The OS is an abbreviation for Operating System. The processor 910 executes the land situation grasping program while executing the OS. The land situation grasping program and the OS may be stored in the auxiliary storage device 922. The land situation grasping 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 a part or all of the land situation grasping program may be incorporated into the OS.

[0020] The land status determination device 100 may include a plurality of processors that replace the processor 910. These plurality of processors share the task of executing the land status determination program. Each of the processors is a device that executes the land status determination program in the same manner as the processor 910.

[0021] Data, information, signal values ​​and variable values ​​used, processed or output by the land condition determination program are stored in memory 921, secondary storage device 922, or in registers or cache memory within processor 910.

[0022] The "parts" of the land use classification unit 110, the local information estimation unit 120, the dynamic analysis unit 130, and the high accuracy improvement unit 140 may be read as "circuits," "steps," "procedures," "processing," or "circuitry." The land situation assessment program causes a computer to execute a land use classification process, a local information estimation process, a dynamic analysis process, and a high accuracy improvement process. The "processing" of the land use classification process, the local information estimation process, the dynamic analysis process, and the high accuracy improvement process may be read as a "program" or a "program product." Alternatively, the "processing" of the land use classification process, the local information estimation process, the dynamic analysis process, and the high accuracy improvement process may be read as a "computer-readable storage medium storing a program." Alternatively, the "processing" of the land use classification process, the local information estimation process, the dynamic analysis process, and the high accuracy improvement process may be read as a "computer-readable storage medium storing a program." The land situation assessment method is a method performed by the land situation assessment device 100 executing the land situation assessment program. The land status assessment program may be provided by being stored in a computer-readable recording medium, or may be provided as a program product.

[0023] ***Explanation of Operation*** FIG. 2 is a flow diagram showing an example of the operation of the land status grasping device 100 according to the present embodiment. The operation of the land status grasping device 100 according to the present embodiment will be described. The operation procedure of the land status grasping device 100 corresponds to a land status grasping method. Also, a program for realizing the operation of the land status grasping device 100 corresponds to a land status grasping program.

[0024] <Land use classification process: Step S101> The land use classification unit 110 analyzes the remote sensing image 52 and sets label information 511 that represents the land coverage status of the survey area. The survey area is an area to be surveyed by the land status grasping device 100, that is, an area to be classified and identified for land use. The land use status includes the classification indicated by the land label information, and the state and status of the land including the dynamics of things. The land label information indicates the cover status of the land. Specifically, the following applies:

[0025] FIG. 3 shows an example of data acquired by the land status grasping device 100 according to the present embodiment. The data acquired by the land condition grasping device 100 includes a remote sensing image 52 and data acquired by an IoT device 61. The land use classifier 110 acquires remote sensing imagery 52 .

[0026] The land use classification unit 110 acquires a plurality of remote sensing images 52 with different granularities. Specifically, as shown in Fig. 3, the remote sensing images 52 are images such as (1) satellite multi-sensing data, (2) aircraft photography data, or (3) drone photography data. For example, the remote sensing images 52 have increasingly finer image granularities in the order of (1) satellite multi-sensing data, (2) aircraft photography data, and (3) drone photography data.

[0027] The land use classification unit 110 performs image analysis on the remote sensing image 52 and outputs a land use map 51. The land use classification unit 110 also performs image analysis on the remote sensing image 52 and sets label information 511 that indicates the land coverage status of the survey area. The label information 511 may be associated with the land use map 51. The label information 511 representing the land coverage status includes at least classifications such as buildings, water bodies, bare land, and soil and sand. Land cover status includes what the land is used for, what condition the land is in, and how the land is changing.

[0028] <Local information estimation process: step S102> The local information estimation unit 120 receives log information 31 transmitted from an IoT device 61 installed in a survey area. Then, the local information estimation unit 120 estimates the state and situation of the land at the survey point where the IoT device 61 exists as local situation information 53 based on the log information 31. The state and situation of the land includes not only land use information classified by label information, but also surrounding conditions or surrounding circumstances such as whether the surroundings of the survey point are in a normal state or an abnormal state. The local information estimation unit 120 receives log information 31 corresponding to each IoT device of a device group consisting of one or more IoT devices 61 present on the ground. The log information 31 indicates, for example, whether the IoT device 61 is normal or abnormal. Based on the log information 31, the local information estimation unit 120 estimates whether each IoT device of the device group is normal or abnormal at the investigation point where the device is present.

[0029] For example, the IoT device 61 is at least one of an IoT home appliance and an elevator. The IoT home appliances include, for example, an air conditioner, a refrigerator, a television, or other home appliances connected to the Internet. The IoT device 61 may be any device that is connected to the Internet and can transmit information to the land condition grasping device 100.

[0030] The following devices may be used as the IoT device 61. The IoT device 61 may be a device such as a fixed surveillance camera, a mobile surveillance camera (lidar / radar), a camera mounted on a moving object, or a PMV periphery monitoring sensor. The IoT device 61 may be a high-precision locator other than a camera. The IoT device 61 may be a sensor installed in a facility, a drive recorder, a publicly installed sensor, a sensor on a mobile terminal, or a sensor used for entrance / exit management. In this way, the IoT device 61 may be one mounted on a device such as a home appliance, one mounted on a moving object, one mounted on a facility, or one existing in the air. The IoT device 61 may be a sensor that can estimate the presence or absence of a building or house based on its log information.

[0031] When the IoT device 61 is an IoT home appliance, the log information 31 is, for example, information such as an on / off signal for an air conditioner, an open / close signal for a refrigerator, or an on / off signal for a television. The local information estimation unit 120 estimates the state and condition of the land at the survey point where the IoT device 61 is located from such log information 31 as local situation information 53. Specifically, the local situation information 53 includes information such as whether or not a building exists at the survey point where the IoT device 61 is located and whether the survey point is normal or abnormal.

[0032] If the IoT device 61 is an elevator, the log information 31 may be, for example, information on whether the elevator is ascending or descending, whether or not the elevator is submerged as detected by a submersion sensor, or whether or not water is detected on the floor as detected by a thermal camera. The local information estimation unit 120 estimates the state and condition of the land at the survey point where the IoT device 61 is located as local situation information 53 from such log information 31. Specifically, the local situation information 53 includes information such as whether the survey point where the IoT device 61 is located is flooded or has a fire, and whether the elevator is operating normally. The local situation information 53 includes information such as whether the survey point is normal or abnormal.

[0033] The log information 31 is "operation and running information of a device that has a built-in wireless LAN module and can connect to a network, and external information collected by a sensor mounted on the device." For example, the log information 31 is information transmitted from the IoT device 61, and is source or origin information for estimating the state and condition of the land at the survey point where the IoT device 61 is located as local situation information. For example, the log information 31 is information indicating the normal or abnormal state of the IoT device 61. Also, the log information 31 is information indicating the operation state of the IoT device 61 (on / off signal, signal indicating normal operation, etc.) or the state and mode of the component parts (open / close signal, signal indicating rise or fall, etc.). Also, the log information 31 is information indicating the physical state or the detection state of a substance detected by a sensor of the IoT device 61 (information indicating the presence or absence of flooding by a flood sensor, information indicating the detection of water on the floor by a thermo camera, etc.).

[0034] <Dynamic analysis process: Step S103> The behavior analysis unit 130 analyzes the log information 31 and generates the behavior of things at the investigation point where the IoT device 61 is located as local behavior information 54. The behavior analysis unit 130 may acquire sensor data 32 from the IoT device 61, analyze the log information 31 and the sensor data 32, and generate the local behavior information 54. When the IoT device 61 is an elevator, surveillance video transmitted from a surveillance camera installed in the elevator becomes the sensor data 32. When the IoT device 61 is an elevator, a door opening / closing signal or the like becomes the log information 31, and the surveillance video becomes the sensor data 32. Furthermore, when the IoT device 61 is an air conditioner, an infrared image transmitted from an infrared camera provided in the air conditioner becomes the sensor data 32. When the IoT device 61 is an air conditioner, an on / off signal or the like becomes the log information 31, and the infrared image becomes the sensor data 32.

[0035] The behavior analysis unit 130 analyzes the presence or absence of a person at the survey point where the IoT device 61 is located from log information 31 such as an on / off signal of an air conditioner, an open / close signal of a refrigerator, or an on / off signal of a television. The behavior analysis unit 130 also analyzes the behavior of a person, such as what the person is doing, from images of a surveillance camera. Alternatively, the behavior analysis unit 130 may analyze the temperature around a person from an infrared image. The behavior analysis unit 130 generates local behavior information 54 indicating the situation or behavior of people in the vicinity of the survey point where the IoT device 61 is located, by combining and analyzing the log information 31 and the sensor data 32.

[0036] In this embodiment, a person is used as an example of an object to be analyzed, but the movement of an object other than a person may be analyzed. For example, the movement of an animal such as a pet may be analyzed. Alternatively, the movement of a machine in operation may be analyzed. In addition, the movement of any object may be analyzed as long as the movement can be analyzed.

[0037] In addition, the behavior analysis unit 130 may transmit the behavior of the person included in the local behavior information 54 as monitoring information 541 to the user. Here, the user who receives the monitoring information 541 is a user who is registered in advance as a user who receives the monitoring information 541. Specifically, the monitoring information 541 including the local behavior information 54 of a family living in a building at the survey point is transmitted to a member of the family who is registered in advance. More specifically, the monitoring information 541 including the local behavior information 54 of a child, an elderly person, a pet, or the like is transmitted to a guardian, manager, or the like. Alternatively, the monitoring information 541 including the local behavior information 54 of a user who uses a facility is transmitted to a manager, or the like of the facility who is registered in advance.

[0038] The local information estimation unit 120 acquires a plurality of pieces of log information 31 from a plurality of IoT devices 61 provided at a plurality of investigation points. Moreover, the local information estimation unit 120 acquires a plurality of types of log information 31 from a plurality of types of IoT devices 61. Moreover, the activity analysis unit 130 acquires a plurality of pieces of sensor data 32 from a plurality of IoT devices 61 provided at a plurality of investigation points. Moreover, the activity analysis unit 130 acquires a plurality of types of sensor data 32 from a plurality of types of IoT devices 61. In this embodiment, the local information estimation unit 120 and the behavior analysis unit 130 are described as separate components. However, the functions of the local information estimation unit 120 and the behavior analysis unit 130 may be realized by a single component.

[0039] 3, specific examples of the log information 31 and the sensor data 32 include (4) video data, (5) building sensing data, (6) home appliance sensing data, (7) vehicle flow data, and (8) SNS data. SNS is an abbreviation for Social Networking Service. (4) Video data is, for example, images or videos captured by security cameras installed in a city or local area. (5) The building sensing data is data acquired by a building condition sensor installed in a building. For example, the building sensing data is data of a vibration waveform that indicates the state of the building's vibration. Alternatively, the building sensing data may include images or videos of the state inside the building. (6) Home appliance sensing data is acquired by sensors installed in home appliances that have a communication function called IoT. Home appliance sensing data is data that indicates the state of the home appliance or the state of the surroundings of the home appliance. IoT is an abbreviation for Internet of Things. (7) Vehicle flow data is data acquired by ETC, a drive recorder, or a GPS receiver. Vehicle flow data is data that indicates the distribution and flow of vehicles. ETC is an abbreviation for Electronic Toll Collection System. GPS is an abbreviation for Global Positioning System. (8) SNS data is data that people post via SNS, and includes information such as text, images, or videos.

[0040] <High-precision processing: steps S104 to S108> In step S104, the accuracy improving unit 140 determines whether or not a disaster has been detected in the survey area. If no disaster is detected, the process proceeds to step S105. If a disaster is detected, the process proceeds to step S106.

[0041] The occurrence of a disaster may be detected by the land use classification unit 110 from the remote sensing image 52. Alternatively, the remote sensing image 52 may be assigned with information on whether it is an image at the time of a disaster or an image at peacetime. Alternatively, the land use classification unit 110 may determine whether a disaster has occurred based on whether the source of the remote sensing image 52 is a cloud at the time of a disaster or a cloud at peacetime. Any other method may be used to detect the occurrence of a disaster in the survey area.

[0042] <<High-precision processing during normal times>> Step S105 is a process carried out when no disaster has been detected in the survey area, that is, during normal times. In step S105, the accuracy improving unit 140 estimates the state and situation of land at points other than the survey point in the survey area based on the remote sensing image 52 and the local situation information 53, and generates area state information 55. The area state information 55 is information that represents the state and situation of land in the survey area with higher accuracy than the label information 511. In addition, the accuracy improving unit 140 may generate area state information 55 including the movement of people at the survey point based on the remote sensing image 52, the local situation information 53, and the local movement information 54. The accuracy improving unit 140 may transmit the area state information 55 to a user who is registered in advance as a user who will receive the area state information 55. When no disaster is detected, the accuracy improving unit 140 may not transmit the area state information 55.

[0043] The accuracy improving unit 140 re-estimates the state and situation of the land at points other than the survey points where each of the IoT devices 61 is located, based on the remote sensing image 52, the local situation information 53, and the local activity information 54. In this way, the accuracy improving unit 140 can interpolate the state and situation of the land at points other than the survey points where each of the IoT devices 61 is located, based on the remote sensing image 52, the local situation information 53, and the local activity information 54, and generate highly accurate area state information 55.

[0044] <<High-precision processing during disasters>> Steps S106 to S108 are processes carried out when it is detected that a disaster has occurred in the survey area, that is, when a disaster occurs. In step S106, the accuracy improving unit 140 generates area state information 55 based on the remote sensing image 52, the local situation information 53, and the local behavior information 54. The generation of the area state information 55 is similar to that in step S104. Here, the accuracy improving unit 140 generates area state information 55 including the behavior of people at the investigation point based on the remote sensing image 52, the local situation information 53, and the local behavior information 54. At this time, the accuracy improving unit 140 generates area state information 55 including delayed escape information 551 indicating whether or not there is anyone who was unable to escape at the investigation point.

[0045] The high accuracy unit 140 transmits the area state information 55 to a user who is registered in advance as a user who will receive the area state information 55. Here, the user who is registered in advance as a user who will receive the area state information 55 is, for example, a government, a local government, a fire department, or a rescue team such as the police.

[0046] In step S107, the accuracy improving unit 140 notifies the movement analysis unit 130 that the delayed escape information 551 has been generated. In step S108, the movement analysis unit 130 receives a notification from the accuracy improvement unit 140 that the late escape information 551 has been generated. The movement analysis unit 130 acquires the late escape information 551 and adds the late escape information 551 to the watching information 541. The movement analysis unit 130 transmits the watching information 541 with the late escape information 551 added thereto to the user. Here, the user to whom the watching information 541 with the late escape information 551 added thereto is transmitted is a user who is registered in advance as a user who will receive the watching information 541. That is, the user is a family member, a guardian, or a manager of the person being watched.

[0047] When some event occurs in the survey area, the accuracy improving unit 140 may generate the area state information 55. Specifically, the accuracy improving unit 140 may generate the area state information 55 when a disaster occurs in the survey area, that is, when the occurrence of a disaster is detected. Alternatively, the accuracy improving section 140 may periodically or irregularly generate the area state information 55. The accuracy improving section 140 may also generate the area state information 55 in response to a request from a user.

[0048] The high accuracy unit 140 generates area status information 55 that represents the state and condition of the land with high accuracy by combining the land coverage state obtained from the remote sensing image 52 with the log information 31 and sensor data 32 transmitted from the IoT device 61. The area status information 55 includes information indicating the land coverage state and the state and condition of buildings or houses in the survey area. The area status information 55 also includes information indicating the movement of the monitored objects such as people, animals, or operating machines in the survey area. The area status information 55 also includes information indicating changes in the land status or people's movement by combining the classification result of the land status and situation with the log information 31 and sensor data 32 of the data acquisition timing different from the time of the classification in a chronological order.

[0049] The land use classification unit 110 may obtain the area condition information 55 and reset the label information 511 based on the remote sensing image 52 and the area condition information 55 . Here, the reset label information 511 is information that further subdivides and details classifications such as buildings, water bodies, bare land, and soil and sand with a high degree of accuracy. The land status grasping device 100 grasps the land cover status by observing remote sensing images. Regarding land cover information, classification such as buildings, water bodies, bare land, and soil and sand, which are determined from image characteristics of optical images and SAR images, can be considered. Another example may be classification such as water bodies, vegetation, clouds, snow cover, soil grain size, urban areas, and shadows, determined from statistics of wavelength information of optical images. As yet another example, possible areas include water areas, fields, forests, urban areas, farmland, snow cover, etc., which are determined based on polarization information and coherence information of SAR images.

[0050] <Example of land status assessment processing> Next, an example of land condition grasping processing according to the present embodiment will be described with reference to Fig. 4 to Fig. 8. In Fig. 4 to Fig. 8, a remote sensing image may be abbreviated to remote sensing or remote sensing.

[0051] FIG. 4 is a schematic diagram showing an example of the flow of the land status grasping process according to the present embodiment. FIG. 4 shows processes 1 to 6 in the land status understanding process.

[0052] In FIG. 4, a remote sensing image 52 is shown in the upper part, and log information 31 and sensor data 32 are shown in the lower part. 4, a remote sensing image A obtained by an optical satellite or SAR, a remote sensing image B obtained by an aircraft, and a remote sensing image C obtained by a drone are shown as remote sensing images 52. SAR is an abbreviation for synthetic aperture radar. In addition, a sensor D which is a drive recorder, a sensor E which is a security camera, and a sensor F which is an IoT home appliance are described as sensor devices provided in the IoT device 61. In other words, the sensors D, E, and F are examples of the IoT device 61.

[0053] <<Spatially interpolate observations of the target area using sensor data>> 4, the land status assessment device 100 observes the survey area 62, in which label information is set, by remote sensing images during a disaster. The land status assessment device 100 grasps the land coverage situation by observing the remote sensing images. Regarding land cover information, classification such as buildings, water bodies, bare land, and soil and sand, which are determined from image characteristics of optical images or SAR images, can be considered. Another example may be classification such as water bodies, vegetation, clouds, snow cover, soil grain size, urban areas, and shadows, determined from statistics of wavelength information of optical images. As yet another example, possible areas include water areas, fields, forests, urban areas, farmland, snow cover, etc., which are determined based on polarization information and coherence information of SAR images. At that time, the land status grasping device 100 acquires log information and sensor data from the IoT device in the observation range of the remote sensing image. The log information and sensor data from the IoT device are information with high accuracy locally, although the range is narrow in the vicinity of the survey point 63. The land status grasping device 100 uses the log information and sensor data to interpolate the observation information of the remote sensing image. Specifically, the land status grasping device 100 estimates the state and situation of the land other than the survey point 63 in the survey area 62 using the log information and sensor data. As a result, the land status grasping device 100 can generate area status information 55 reflecting the highly accurate log information and sensor data, and can expand the observation range with high accuracy.

[0054] <<Spatial and temporal interpolation of target area observations using sensor data>> In each of processes 1 to 6 in Fig. 4, the land status grasping device 100 combines the damage situation or damage state with log information and sensor data in a chronological order. Specifically, the land status grasping device 100 combines the damage situation or damage state of a specific area, building, and house with log information and sensor data of a data acquisition timing different from the land status and classification result in a chronological order. In this way, the land status grasping device 100 obtains changes in the damage situation or damage state. In this case, the land status grasping device 100 uses log information and sensor data from IoT devices in the observation range of the remote sensing image. The log information and sensor data from the IoT devices are narrow in range but have high local accuracy and can acquire information more frequently than the remote sensing image. The land status grasping device 100 uses such log information and sensor data to spatially and temporally interpolate the observation information of the remote sensing image. This allows the land status grasping device 100 to generate area state information 55 that reflects the log information and sensor data with high accuracy and frequency, and expand the observation range with high accuracy.

[0055] 5, process 1 to process 6 described as "label update" are executed by, for example, a high accuracy unit of the land status grasping device. In each of process 1 to process 6, the high accuracy unit of the land status grasping device may proactively select remote sensors B and C, or sensors D, E, and F. Alternatively, in each of process 1 to process 6, the high accuracy unit of the land status grasping device may passively select remote sensors B and C, or sensors D, E, and F. Specifically, the following applies:

[0056] An example of a proactive approach is an automated case that is completed within the land status assessment device. The land status assessment device designates a specific location or state in advance and monitors the situation or state. If there is a change in the monitoring, the land status assessment device obtains the situation, state, or information of the location using a more granular remote sensor or sensor.

[0057] In a passive example, a specific location or state is specified from outside the land status assessment device via an input interface. The specific location or state is monitored externally via an output interface. If a change is detected by the monitor, a finer-grained remote sensor or sensor is specified to obtain the situation, state, or information of the location. In this case, the process of detecting changes by monitoring may be performed automatically within the land status assessment device. If necessary, the granularity may be increased step by step, the location may be adaptively switched, or monitoring may be continued repeatedly.

[0058] For example, remote sensors B and C or sensors D, E, and F may be selected depending on the purpose of use of the area state information 55. Specific examples of the purpose of use include planning evacuation routes from disaster areas, predicting changes in disaster conditions, and notifying disaster victims of these. In addition, there are also cases where users such as the government, local governments, fire departments, or police plan rescue team dispatch routes or determine rescue urgency.

[0059] An example of the land status grasping process will be described in more detail below. 5 to 8, which will be described later, an IoT home appliance, sensor F, is shown as an example of a sensor that acquires log information and sensor data. This is just one example, and the present embodiment can be applied even if sensor F is replaced with sensor D or sensor E.

[0060] <Example 1 of land status understanding processing> FIG. 5 is a schematic diagram showing Example 1 of the land situation grasping process in the survey area according to the present embodiment. In example 1 of the land condition grasping process, the land use classification unit 110 acquires a remote sensing image A and sets label information. Here, the label information is set as buildings, water areas, bare land, and earth and sand. The local information estimation unit 120 acquires log information from the sensor F and generates local situation information. The behavior analysis unit 130 acquires log information and sensor data from the sensor F, and generates local behavior information. The accuracy improving unit 140 uses the remote sensing image A, the local situation information, and the local activity information to generate the area state information 55. The land use classification unit 110 may use the area state information 55 to update the label information.

[0061] FIG. 6 is a diagram showing a process in which interpolation is performed using log information and sensor data from sensor F in example 1 of the land status grasping process according to the present embodiment. The accuracy improving unit 140 estimates the state and condition of land at points other than the survey point from the log information from the sensor F, the local situation information based on the sensor data, and the local activity information, and generates area state information 55. Alternatively, the accuracy improving unit 140 may estimate land coverage and environmental conditions in an area between multiple ground sensors based on multiple sensor data, and generate area state information 55.

[0062] The land status assessment device 100 uses log information and sensor data from the sensor F in the observation range of the remote sensing A to interpolate the observation information of the remote sensing A. This enables the land status assessment device 100 to expand the observation range based on the highly accurate information from the sensor F.

[0063] Furthermore, the land status assessment device 100 continuously interpolates the observation information of remote sensing A spatially and temporally using log information and sensor data from sensor F in the observation range of remote sensing A. This enables the land status assessment device 100 to expand the observation range based on the highly accurate information from sensor F while updating the log information and sensor data from sensor F.

[0064] <<Spatial Edition (Remote Sensing A + Sensor F)>> (Disaster Response) An example will be described in which, in the event of a disaster, the land status grasping device 100 uses log information and sensor data from the sensor F to spatially interpolate the area status information 55 with high accuracy. The land status assessment device 100 combines log information and sensor data from sensor F with low-precision information from remote sensing A, based on information that has been previously analyzed and classified into a land use map on the state and condition of the land, and on observation information from remote sensing A. This allows the observation information from remote sensing A to be interpolated. This allows the land status assessment device 100 to comprehensively assess a wide range of disaster situations, such as damage to buildings, fires, flooding, and landslides, at an early stage of a disaster. The land status assessment device 100 can also generate information on people who are late in escaping, contributing to rescue efforts and the like.

[0065] <<Space & Time (Remote Sensing A + Sensor F) & Time>> (Disaster Response) An example will be described in which, in the event of a disaster, the land status grasping device 100 uses log information and sensor data from the sensor F to spatially and temporally interpolate the area status information 55 with high accuracy. The land status grasping device 100 constantly acquires log information and sensor data from the sensor F in relation to information on the state and condition of the land that has been analyzed in advance and classified into a land use map, and observation information from the remote sensing A. The land status grasping device 100 then combines the log information and sensor data constantly acquired from the sensor F with the low-precision information from the remote sensing A. In this way, the land status grasping device 100 continuously interpolates and updates the observation information from the remote sensing A spatially and temporally using the sensor F. As a result, the land status grasping device 100 is configured to comprehensively and continuously grasp various disaster situations such as building damage, fires, flooding, and landslides and their changes over a wide range at an early stage of the disaster. The land status grasping device 100 can also generate information on people who are late in escaping, contributing to rescue activities and the like.

[0066] <Land status understanding processing example 2> FIG. 7 is a schematic diagram showing Example 2 of the land situation grasping process in the survey area according to the present embodiment. Here, an example will be described in which remote sensing images A and B and a sensor F are used to highly accurately interpolate the area state information 55.

[0067] The land condition grasping device 100 performs observation by remote sensing B based on the observation information of remote sensing A interpolated with log information and sensor data from sensor F. Remote sensing B has a narrower observation range than remote sensing A, but is capable of acquiring highly accurate information. In this way, the log information and sensor data from sensor F and remote sensing B can improve the accuracy of the observation range.

[0068] <<Spatial Edition (Remote Sensing A + Remote Sensing B + Sensor F)>> (Disaster Response) An example will be described in which, in the event of a disaster, the land status grasping device 100 uses log information and sensor data from the sensor F to spatially interpolate the area status information 55 with high accuracy. In order to grasp areas and damage types with high priority for evacuation and rescue of victims from the damage situation grasped comprehensively at an early stage of the disaster, the land situation grasping device 100 performs observation as follows. The land situation grasping device 100 performs observation by remote sensing B based on the information classified in the land use map and the observation information of remote sensing A interpolated with log information and sensor data from sensor F. Remote sensing B has a narrower observation range than remote sensing A but can acquire highly accurate information, for example, aircraft imaging. By such observation, the land situation grasping device 100 performs interpolation of observation information by a combination of sensor F, remote sensing A, and remote sensing B. The land situation grasping device 100 is configured to grasp areas and damage types with high priority for evacuation and rescue of victims, and damage situations in various damage situations such as building damage, fire, flooding, and landslides, by using highly accurate sensor F and remote sensing B. In addition, the land situation grasping device 100 can generate information on people who are late to escape and contribute to rescue activities.

[0069] <<Space & Time (Remote Sensing A + Remote Sensing B + Sensor F) & Time>> (Disaster Response) An example will be described in which, in the event of a disaster, the land status grasping device 100 uses log information and sensor data from the sensor F to spatially and temporally interpolate the area status information 55 with high accuracy. In order to constantly grasp areas and damage types with high priority for evacuation and rescue of victims from the damage situation comprehensively grasped at an early stage of the disaster, the land situation grasping device 100 performs observation as follows. The land situation grasping device 100 performs observation by remote sensing B based on the information classified in the land use map and the observation information of remote sensing A interpolated with log information and sensor data from sensor F. Remote sensing B has a narrower observation range than remote sensing A but can acquire information with high accuracy and high acquisition frequency, for example, aircraft imaging. By such observation, the land situation grasping device 100 performs spatial and temporal interpolation of the observation information by the combination of sensor F, remote sensing A, and remote sensing B. The land situation grasping device 100 is configured to adaptively grasp areas and damage types with high priority for evacuation and rescue of victims, damage situations, and changes thereof in various damage situations such as building damage, fire, flooding, and landslides, by using the highly accurate sensor F and remote sensing B. The land situation grasping device 100 can also generate information on people who are late to escape, thereby contributing to rescue activities, etc.

[0070] <Land status understanding processing example 3> FIG. 8 is a schematic diagram showing Example 3 of the land situation grasping process in the survey area according to the present embodiment. Here, an example will be described in which remote sensing images A, B, and C and a sensor F are used to highly accurately interpolate the area state information 55.

[0071] When more accurate observation information is required, the land status assessment device 100 performs observation as follows. Based on the observation information of remote sensing A and remote sensing B interpolated by sensor F, the land status assessment device 100 performs observation by remote sensing C, which has a narrower observation range than remote sensing B but can acquire highly accurate information. This observation is an interpolation of observation information by a combination of sensor F, remote sensing A, remote sensing B, and remote sensing C. The highly accurate sensor F and remote sensing C can increase the accuracy of the observation range.

[0072] When more accurate and frequent observation information is required, the land status assessment device 100 performs observation as follows. Based on the observation information of remote sensing A and remote sensing B interpolated by sensor F, the land status assessment device 100 performs observation by remote sensing C, which has a narrower observation range than remote sensing B but can acquire information with higher accuracy and frequency. This observation is an interpolation of observation information by a combination of sensor F, remote sensing A, remote sensing B, and remote sensing C. The observation range can be expanded by using sensor F and remote sensing C, which have higher accuracy and frequency.

[0073] <<Spatial Edition (Remote Sensing A + Remote Sensing B + Remote Sensing C + Sensor F)>> (Disaster Response) An example will be described in which, in the event of a disaster, the land status grasping device 100 uses log information and sensor data from the sensor F to spatially interpolate the area status information 55 with high accuracy. In the event of a disaster, in order to obtain highly accurate observation information for grasping specific information necessary for the movement and rescue work of rescue teams such as police and fire departments heading to the disaster site from the disaster situation that grasps the areas with high priority for victim evacuation and rescue and the type of damage, observation is performed as follows. The land situation grasping device 100 performs observation by remote sensing C based on information that has been previously analyzed and classified into a land use map in which the state and situation of the land is analyzed and the observation information of remote sensing A and remote sensing B that is interpolated by sensor F. Remote sensing C has a narrower observation range than remote sensing B but can obtain highly accurate information, for example, drone imaging. By such observation, the land situation grasping device 100 performs interpolation of observation information by a combination of sensor F, remote sensing A, remote sensing B, and remote sensing C. The land situation grasping device 100 is configured to grasp areas with high priority for victim evacuation and rescue, the type of damage, and the damage situation by the highly accurate sensor F and remote sensing C.

[0074] <<Space & Time (Remote Sensing A + Remote Sensing B + Remote Sensing C + Sensor F) & Time>> (Disaster Response) The observations are as follows: An example will be described in which, in the event of a disaster, the land status grasping device 100 uses log information and sensor data from the sensor F to spatially and temporally interpolate the area status information 55 with high accuracy. In the event of a disaster, when highly accurate observation information is continuously required to grasp specific information necessary for rescue teams such as police and fire departments heading to the disaster site and rescue operations based on the disaster situation that grasps areas with high priority for victim evacuation and rescue and the type of damage, observation is performed as follows. The land situation grasping device 100 performs observation by remote sensing C based on information that has been previously analyzed and classified into a land use map in which the state and situation of the land have been analyzed and the observation information of remote sensing A and remote sensing B that has been interpolated by sensor F. Remote sensing C has a narrower observation range than remote sensing B, but is highly accurate and can obtain information frequently, such as drone imaging. Through such observation, the land situation grasping device 100 performs interpolation of observation information by a combination of sensor F, remote sensing A, remote sensing B, and remote sensing C. The land situation grasping device 100 is configured to grasp movement to specific disaster areas and disaster points, detailed conditions of disaster areas and disaster points, and changes therein, using highly accurate sensor F and remote sensing C.

[0075] <Example 4 of land status understanding processing> <Updating land use labels to reflect disaster information> (Disaster response) <<Space Edition>> The land condition grasping device 100 updates the labels based on the remote sensing image and the log information and sensor data from the sensor F. The land condition grasping device 100 improves the observation accuracy and expands the observation range by combining remote sensing images and log information and sensor data from the sensor F according to the use, purpose, situation, etc. It enables highly accurate and reliable updating of land use labels based on a land use map that can be used for adaptively grasping the disaster situation and for disaster response.

[0076] <Space & Time> The land condition grasping device 100 updates the labels based on time-series remote sensing images and time-series log information and sensor data from the sensor F. The land status assessment device 100 combines remote sensing images and log information and sensor data from the sensor F in a time series with observation information and data acquired at different times according to the use, purpose, situation, etc. The land status assessment device 100 continuously improves the observation accuracy and expands the observation range through such combinations. This enables the land status assessment device 100 to adaptively assess the disaster situation and update land use labels based on a land use map that can be used for disaster response with high accuracy and reliability.

[0077] ***Other configurations*** <Variation 1> As described above in step S101, the land use classification unit 110 performs image analysis on the remote sensing image 52 and outputs the land use map 51. The land use classification unit 110 also performs image analysis on the remote sensing image 52 and sets label information 511 that indicates the land coverage status of the survey area. The label information 511 may be associated with the land use map 51.

[0078] In a first modification of this embodiment, the land use classification unit 110 may update the land use map 511 based on the remote sensing image 52 and the area status information 55. In a first modification of this embodiment, the land use classification unit 110 may execute a map update process to update the land use map 511 based on the remote sensing image 52 and the area status information 55. The other processing is the same as that in FIG.

[0079] The map update process may be executed after the land use classification process 2 in step S101 described in the first embodiment. That is, the land use classification unit 110 may acquire the area state information 55, and reset the label information 511 based on the remote sensing image 52 and the area state information 55, and update the land use map 511.

[0080] <Variation 2> In this embodiment, an example of a land situation grasping process for grasping the land situation when a disaster occurs has been mainly described, but this embodiment can be applied not only when a disaster occurs but also in peacetime. Basically, land status understanding processing in peacetime is similar to disaster response. Land status understanding processing in peacetime may differ from disaster response in that the time axis is long, the focus is on operational aspects such as maintenance, and the main function is updating by resetting.

[0081] The land status grasping process corresponding to FIG. 5 and FIG. 6 can also be applied in peacetime. In the observation range of remote sensing A, sensor F, which has a narrow range but can acquire the state of land and buildings with high accuracy locally, is used to increase the accuracy of the observation information of remote sensing A, and the observation range is expanded by using sensor F, which has a wide range. At this time, the precision improvement unit 140 generates area state information 55 including the movement of people at the survey point based on the log information and sensor data from remote sensing A and sensor F. In addition, the movement analysis unit 130 transmits the movement of people included in the local movement information obtained from the log information and sensor data from sensor F as monitoring information to a user such as the guardian of the person being monitored.

[0082] <Spatial Edition (Remote Sensing A + Sensor F)> (Peacetime Response) The observations are as follows: The land status grasping device 100 combines log information and sensor data from sensor F with low-precision information from remote sensing A for the information classified in the land use map and the observation information from remote sensing A to interpolate the observation information from remote sensing A. Sensor F is, for example, an IoT home appliance. As a result, the land status grasping device 100 has a configuration for comprehensively grasping the status and condition of changes, weathering, deterioration, damage, etc. of land / rivers / harbors / facilities / buildings over a wide range. In addition, the land status grasping device 100 has a configuration for transmitting the behavior of people included in the local behavior information as monitoring information to a user such as the guardian of the person being monitored.

[0083] <Space & Time (Remote Sensing A + Sensor F) & Time> (Peacetime) The land status grasping device 100 constantly acquires log information and sensor data from the sensor F for the information classified in the land use map and the observation information of the remote sensing A. The land status grasping device 100 then combines the low-precision information of the remote sensing A and continuously interpolates and updates the observation information of the remote sensing A in terms of space and time. In this way, the land status grasping device 100 is configured to comprehensively grasp the situation and state of changes, weathering, deterioration, damage, etc. of land / rivers / harbors / facilities / buildings and their changes in a wide range. The land status grasping device 100 is also configured to continuously transmit the movement of people included in the local movement information as monitoring information to a user such as a guardian of the person being monitored.

[0084] The land status grasping process corresponding to FIG. 7 can also be applied in peacetime.

[0085] <Spatial Edition (Remote Sensing A + Remote Sensing B + Sensor F)> (Peacetime Response) The land status grasping device 100 performs observation by remote sensing B based on the information classified in the land use map and the observation information of remote sensing A interpolated with the log information and sensor data from sensor F. Through such observation, the land status grasping device 100 interpolates the observation information by a combination of sensor F, remote sensing A, and remote sensing B. In this way, the land status grasping device 100 is configured to grasp the situation and condition of changes, weathering, deterioration, damage, etc. of land / rivers / harbors / facilities / buildings by using highly accurate sensor F and remote sensing B. In addition, the land status grasping device 100 is configured to transmit the movement of a person included in the local movement information as monitoring information to a user such as a guardian of the person being monitored.

[0086] <Space & Time (Remote Sensing A + Remote Sensing B + Sensor F) & Time> (Normal Response) The land status grasping device 100 performs observation by remote sensing B based on the information classified in the land use map and the observation information of remote sensing A interpolated with the log information and sensor data from sensor F. Through such observation, the land status grasping device 100 performs spatial and temporal interpolation of the observation information obtained by combining sensor F, remote sensing A, and remote sensing B. The land status grasping device 100 is configured to adaptively grasp the situation and state, such as changes, weathering, deterioration, and damage, of land / rivers / harbors / facilities / buildings, and their changes, using highly accurate sensor F and remote sensing B. In addition, the land status grasping device 100 is configured to continuously transmit the movements of people included in the local movement information to a user such as a guardian of the person being watched as watching information.

[0087] The land status grasping process corresponding to FIG. 8 can also be applied in peacetime.

[0088] <Spatial Edition (Remote Sensing A + Remote Sensing B + Remote Sensing C + Sensor F)> (Peacetime Response) The observations are as follows: The land status grasping device 100 performs observation by remote sensing C based on the information classified in the land use map, and the observation information of remote sensing A and remote sensing B interpolated with the log information and sensor data from sensor F. Through such observation, the land status grasping device 100 interpolates the observation information by a combination of sensor F, remote sensing A, remote sensing B, and remote sensing C. In this way, the land status grasping device 100 is configured to comprehensively grasp the situation and condition of changes, weathering, deterioration, damage, etc. of land / rivers / harbors / facilities / buildings from the entire object to localized parts by using highly accurate sensor F and remote sensing C. In addition, the land status grasping device 100 is configured to transmit the movement of a person included in the local movement information as monitoring information to a user such as a guardian of the person being watched.

[0089] <Space & Time (Remote Sensing A + Remote Sensing B + Remote Sensing C + Sensor F) & Time> (Normal Response) The observations are as follows: The land status grasping device 100 performs observation by remote sensing C based on the information classified in the land use map, the log information from sensor F, and the observation information of remote sensing A and remote sensing B interpolated with the sensor data. By such observation, the land status grasping device 100 interpolates the observation information by the combination of sensor F, remote sensing A, remote sensing B, and remote sensing C. In this way, the land status grasping device 100 is configured to comprehensively grasp the situation and condition of changes, weathering, deterioration, damage, etc. of land / rivers / harbors / facilities / buildings from the entire object to localized parts, including changes over time, by using highly accurate sensor F and remote sensing C. In addition, the land status grasping device 100 is configured to continuously transmit the movement of people included in the local movement information to a user such as a guardian of the person being watched as watching information.

[0090] <Variation 3> In this embodiment, the functions of the land use classification unit 110, the local information estimation unit 120, the behavior analysis unit 130, and the accuracy improvement unit 140 are realized by software. As a modification, the functions of the land use classification unit 110, the local information estimation unit 120, the behavior analysis unit 130, and the accuracy improvement unit 140 may be realized by hardware. Specifically, the land condition grasping device 100 includes an electronic circuit 909 instead of a processor 910 .

[0091] FIG. 9 is a diagram showing an example of the configuration of a land status grasping device 100 according to a modified example of the present embodiment. The electronic circuit 909 is a dedicated electronic circuit that realizes the functions of the land use classification unit 110, the local information estimation unit 120, the dynamic analysis unit 130, and the accuracy improvement 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.

[0092] The functions of the land use classification unit 110, the local information estimation unit 120, the dynamics analysis unit 130, and the accuracy improvement unit 140 may be realized by a single electronic circuit, or may be realized by distributing them among multiple electronic circuits.

[0093] As another modification, some of the functions of the land use classification unit 110, the local information estimation unit 120, the behavior analysis unit 130, and the accuracy improvement unit 140 may be realized by electronic circuits, and the remaining functions may be realized by software. Also, some or all of the functions of the land use classification unit 110, the local information estimation unit 120, the behavior analysis unit 130, and the accuracy improvement unit 140 may be realized by firmware.

[0094] Each of the processor and the electronic circuit is also called a processing circuitry. That is, the functions of the land use classification unit 110, the local information estimation unit 120, the dynamics analysis unit 130, and the accuracy improvement unit 140 are realized by the processing circuitry.

[0095] <Modification 4> Here, the land cover information that the land status assessment device 100 assesses through observation using remote sensing images will be described. Regarding land cover information, classification such as buildings, water bodies, bare land, and soil and sand, which are determined from image characteristics of optical images and SAR images, can be considered. Another example may be classification such as water bodies, vegetation, clouds, snow cover, soil grain size, urban areas, and shadows, determined from statistics of wavelength information of optical images. As yet another example, possible areas include water areas, fields, forests, urban areas, farmland, snow cover, etc., which are determined based on polarization information and coherence information of SAR images.

[0096] ***Explanation of the Effects of the Present Embodiment*** The effects of this embodiment will be described. The land status assessment device 100 of this embodiment combines a land use map obtained from the analysis results of remote sensing images with log information and sensor data from multiple IoT devices to assess the status and changes of land cover over a wide area and in detail. The local information estimation unit estimates whether each device in a device group consisting of one or more IoT devices present at a survey location is normal or abnormal at the location where each device in the device group is located, based on a log signal indicating normality or abnormality corresponding to each device in the device group. The high accuracy improvement unit estimates information indicating land use information of points other than the survey point using local land use information at the survey point and land use information corresponding to the survey area acquired by remote sensing. Then, the high accuracy improvement unit re-estimates the land use information in the survey area with high accuracy based on the local land use information at the survey point, the land use information corresponding to the survey area acquired by remote sensing, and information indicating land use information of points other than the survey point. As described above, the land status grasping device 100 according to the present embodiment can estimate information other than the survey point and improve the accuracy of the survey area by linking the log information and sensor data of the survey point with the remote sensing data. The land status grasping device 100 according to the present embodiment can obtain highly accurate land use information by linking and aggregating the log information and sensor data of the survey point with the remote sensing data.

[0097] In the above-mentioned first embodiment, each part of the land status grasping device has been described as an independent functional block. However, the configuration of the land status grasping device does not have to be as in the above-mentioned embodiment. The functional blocks of the land status grasping device may have any configuration as long as they can realize the functions described in the above-mentioned embodiment. Furthermore, the land status grasping device may not be a single device, but may be a system composed of multiple devices. Also, it is possible to combine a plurality of parts of the first embodiment and to implement the present invention. Alternatively, it is possible to implement only one part of the first embodiment. In addition, it is possible to implement the present embodiment in any combination as a whole or in part. That is, in the first embodiment, the embodiments can be freely combined, or any of the components in each embodiment can be modified, or any of the components in each embodiment can be omitted.

[0098] The above-described embodiment is essentially a preferred example, and is not intended to limit the scope of the present disclosure, the scope of application of the present disclosure, and the scope of use of the present disclosure. The above-described embodiment can be modified in various ways as necessary. For example, the procedure described using a flow chart or sequence chart may be modified as appropriate. [Explanation of symbols]

[0099] 31 log information, 32 sensor data, 51 land use map, 52 remote sensing image, 53 local situation information, 54 local activity information, 55 area status information, 61 IoT device, 62 survey area, 63 survey point, 100 land situation grasping device, 110 land use classification unit, 120 local information estimation unit, 130 activity analysis unit, 140 high accuracy improvement unit, 150 memory unit, 511 label information, 541 monitoring information, 551 late escape information, 909 electronic circuit, 910 processor, 921 memory, 922 auxiliary storage device, 930 input interface, 940 output interface, 950 communication device.

Claims

1. A land use classification unit analyzes remote sensing images and sets label information representing the land cover status of the survey area, A local information estimation unit receives log information transmitted from IoT devices (Internet of Things devices) installed in the survey area, and estimates the land condition and situation at the survey point where the IoT device is located as local condition information based on the log information. A high-precision unit that estimates the state and condition of the land at locations other than the survey points in the survey area based on the remote sensing image and the local condition information, and generates area condition information that represents the state and condition of the land in the survey area with higher accuracy than the label information. A land condition assessment device equipped with the following features.

2. The aforementioned land condition assessment device, The system includes a dynamic analysis unit that analyzes the log information and generates local dynamic information of human movement at the survey site, The aforementioned high-precision unit is The land condition assessment device according to claim 1, which generates area condition information including the movement of people at the survey site based on the remote sensing image, the local condition information and the local movement information.

3. The aforementioned high-precision unit is The land condition assessment device according to claim 2, which, upon detecting the occurrence of a disaster in the survey area, generates area state information including information indicating whether or not there are any people who have been left behind at the survey point, based on the remote sensing image, the local condition information and the local dynamic information.

4. The aforementioned high-precision unit is The land condition assessment device according to claim 3, wherein the area condition information is transmitted to a user who has been pre-registered as a user to receive the area condition information.

5. The aforementioned dynamic analysis unit, The land condition monitoring device according to claim 3 or claim 4, which transmits the movement of people included in the local movement information to a user who has been pre-registered as a user to receive the monitoring information.

6. The aforementioned dynamic analysis unit, The land condition assessment device according to claim 5, which acquires the information on delayed evacuation, adds the information on delayed evacuation to the monitoring information, and transmits it to a user who has been pre-registered as a user to receive the monitoring information.

7. The aforementioned dynamic analysis unit, A land condition assessment device according to any one of claims 2 to 4, which acquires sensor data from a sensor device provided in the IoT device, analyzes the log information and the sensor data, and generates local dynamic information.

8. The land condition assessment device according to any one of claims 1 to 4, wherein the IoT device is at least one of an IoT home appliance and an elevator.

9. The computer analyzes the remote sensing images and sets label information that represents the land cover of the survey area. The computer receives log information transmitted from IoT devices (Internet of Things devices) installed in the survey area, and estimates the land condition and situation at the survey point where the IoT device is located as local condition information based on the log information. A method for understanding land conditions, wherein a computer estimates the state and condition of the land at locations other than the survey points in the survey area based on the remote sensing image and the local condition information, and generates area condition information that represents the state and condition of the land in the survey area with higher accuracy than the label information.

10. Land use classification processing involves analyzing remote sensing images to set label information representing the land cover status of the survey area, and Local information estimation processing that receives log information transmitted from IoT devices (Internet of Things devices) installed in the survey area, and estimates the state and condition of the land at the survey point where the IoT device is located as local condition information based on the log information, Based on the remote sensing image and the local condition information, a high-precision processing is performed to estimate the state and condition of the land at locations other than the survey points in the survey area, and to generate area condition information that represents the state and condition of the land in the survey area with higher accuracy than the label information. A land condition assessment program that is executed by a computer.

Images