Feature region determination system and feature region determination method

Abstract

To enable the correspondence between feature areas appearing in a plurality of division areas to be easily identified.SOLUTION: A feature area determination system includes a state information receiving unit, a positional information receiving unit, an identification unit, and a determination unit. The state information receiving unit receives, from a flying object, state information indicating states of division areas obtained by dividing an entire observation target into a plurality of areas. The positional information receiving unit receives positional information and information acquisition direction information at the time of information acquisition in the state information. The identification unit identifies a feature area based on the state information. The determination unit determines identity of each feature area identified in the plurality of division areas, based on the positional information and the information acquisition direction information.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a characteristic region determining system and a characteristic region determining method. [Background technology]

[0002] Conventionally, aerial photography using aircraft (unmanned aerial vehicles (drones, etc.) has been widely practiced. Such aerial images are not only used by individuals to appreciate the scenery, but are also used for business purposes such as disaster relief, agriculture, ecological surveys, news reports, infrastructure inspections, and inspections of abnormalities.

[0003] For example, as an example of infrastructure inspection, aerial images can be used to inspect solar power generation equipment (solar panels, etc.) at solar power plants. Solar power generation equipment generates electricity mainly through the photovoltaic effect, so power generation is hindered by dirt, damage, etc. on the surface that receives sunlight. Aerial images make it possible to grasp the dirt, damage, etc. of the solar power generation equipment. Therefore, photographing and inspecting solar power generation equipment with aerial images is effective in improving the power generation efficiency at solar power plants.

[0004] As another example, conventionally, soil components are analyzed by measuring and analyzing the light spectrum of the soil. That is, since the wavelength and intensity of light absorbed differ depending on the type and amount of soil components, measurements are made of the specific light spectrum (absorption spectrum) of the reflected wave according to the soil components. This allows the soil condition in the field to be understood, and reduces the use of fertilizer and other feed. (For example, Patent Document 1) [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Patent No. 3906326 Summary of the Invention [Problem to be solved by the invention]

[0006] When the total area of ​​the observation target is large, such as a mega solar power plant or a farm field, the entire area must be divided into multiple parts in order to inspect and measure the object from the sky. This is because there is a limit to the distance (altitude) at which the condition of the object can be grasped when inspecting and measuring the object from the sky. One example is the resolution of an aerial photograph. Depending on the object being observed, when photographed from the sky at the required resolution, the entire object may not fit within the image.

[0007] When dividing the entire area of ​​an observation target for inspection, measurement, etc., each divided area needs to overlap partially with adjacent areas. This is because if there is no overlap, there is a possibility that some parts of the target for inspection, etc. will be missed. However, when divided areas are overlapped, if there is a feature area in the overlapping area, one feature area will appear in a separate divided area. A feature area is, for example, an abnormality in a solar panel, or an area that shows the value of the absorption spectrum in a farm field.

[0008] When taking any action on a feature area (such as identifying the condition or calculating the amount of fertilizer), it requires a great deal of effort and processing cost to determine whether feature areas appearing in two or more adjacent separate divided areas are actually a single feature area or different feature areas.

[0009] The present invention has been made to solve the above-mentioned problems, and has an object to make it possible to easily specify the correspondence between feature regions appearing in a plurality of divided regions. [Means for solving the problem]

[0010] According to one embodiment, the characteristic region determination system includes a status information receiving unit, a position information receiving unit, an identification unit, and a determination unit. The status information receiving unit receives, from the flying object, status information indicating the status of divided regions obtained by dividing the entire observation target into a plurality of regions. The position information receiving unit receives, from the status information, position information at the time of information acquisition and information acquisition direction information. The identification unit identifies the characteristic region based on the status information. The determination unit determines the identity of each of the characteristic regions identified in each of the plurality of divided regions based on the position information and the information acquisition direction information. In the above-mentioned characteristic region determination system, the location information may include a navigation signal from a global positioning satellite system that the aircraft received in response to the photographing, and the photographing direction information may include the orientation of the aircraft's body and the orientation of the photographing unit installed on the aircraft. In the above-mentioned characteristic region determination system, the location information may include a navigation signal received by the aircraft from a global positioning satellite system in response to photographing, and the photographing direction information may include the orientation of the aircraft's body and the orientation of the photographing unit installed on the aircraft. In the above-described characteristic region determination system, the determination unit may calculate the position within the entire object of observation for each of the characteristic regions identified in each of the multiple divided regions, and determine that the calculated positions of the characteristic regions are identical if they are within a set range. In the above-described characteristic region determination system, a plurality of observation objects which may include the characteristic region are arranged in a predetermined shape in the divided region, and the determination unit may determine identity based on position information, information acquisition direction information, and an arrangement rule for the plurality of observation objects. In the above-described characteristic region determination system, a plurality of observation objects which may include the characteristic region are arranged in a predetermined shape in the divided region, and the determination unit may determine identity based on position information, information acquisition direction information, and an arrangement rule for the plurality of observation objects. In the above-described characteristic region determination system, the state information may be infrared images, and the identifying section may identify the characteristic region based on temperature information of each of the infrared images. In the above characteristic region determination system, the state information may be images showing a vegetation state of plants, and the identifying unit may identify the characteristic region based on the vegetation state information of each image showing the vegetation state. Effect of the Invention

[0011] According to the embodiment, it is possible to easily identify the correspondence between feature regions appearing in a plurality of divided regions. [Brief description of the drawings]

[0012] [Figure 1] FIG. 1 is a schematic block diagram showing a feature region determination system according to a first embodiment. [Diagram 2] FIG. 1 is a conceptual diagram showing an overview of a wide area including a plurality of divided areas. [Diagram 3] FIG. 1 is a schematic diagram showing an overview of a wide area including multiple divided areas. [Figure 4] Schematic diagram of an infrared image. [Diagram 5] FIG. 2 is a conceptual diagram showing the positional relationship between a shooting position and an image center. [Figure 6] 1 is a schematic diagram showing a set region including a feature region in an infrared image. [Figure 7] Schematic diagram showing the positional relationship between the image center and feature regions. [Figure 8] 5 is a schematic flowchart showing the flow of feature region determination processing according to the first embodiment. [Figure 9] FIG. 11 is a schematic block diagram showing a feature region determination system according to a second embodiment. [Figure 10] FIG. 11 is a conceptual diagram showing an outline of a determination process according to a second embodiment. [Figure 11] 10 is a schematic flowchart showing the flow of feature region determination processing according to the second embodiment. [Figure 12] FIG. 13 is a schematic block diagram showing a feature region determination system according to a third embodiment. [Figure 13] 13 is a schematic flowchart showing the flow of feature region determination processing according to the third embodiment. [Figure 14] FIG. 13 is a schematic block diagram showing a feature region determination system according to a fourth embodiment. [Figure 15] 13 is a schematic flowchart showing the flow of feature region determination processing according to the fourth embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] The characteristic region determining systems according to the first to fourth embodiments will be described with reference to FIGS.

[0014] [First embodiment] The overall configuration of a characteristic region determination system 100 according to a first embodiment will be described with reference to Fig. 1 to Fig. 6. Note that the characteristic region determination system in Fig. 1 is just one example, and does not exclude the inclusion of other configurations, and can be embodied in various forms. In the first embodiment, an example of inspecting photovoltaic power generation panels in a solar power plant will be described.

[0015] (Overview of the Flying Vehicle D) As shown in FIG. 1, the flying object D includes a status information acquisition unit D1, a position receiving unit D2, a gyroscope D3, and a gimbal D4. The status information acquisition unit D1 includes an infrared camera. The status information acquisition unit D1 captures an infrared image (e.g., FIG. 4) of a divided area (see conceptual diagrams 2 and 3) obtained by dividing a wide area including a plurality of imaging targets. The position receiving unit D2 receives navigation signals from positioning satellites such as GNSS (Global Navigation Satellite System), e.g., GPS, GLONASS, Galileo, and Quasi-Zenith Satellite System (QZSS), and measures the three-dimensional position of the flying object D and adds it to the infrared image (e.g., EXIF ​​information). The position receiving unit D2 may also be equipped with, for example, a water pressure gauge and a barometer, and convert the results into depth and altitude. As another example, an ultrasonic sensor may be equipped to measure the distance from the surface of the earth, the bottom of the sea, etc. to the flying object D. The received one-dimensional position information is added to the infrared image. In this way, the three-dimensional position of the infrared image can be specified. These are transmitted as additional information together with the infrared image to the characteristic region determination system 100. Note that the observed objects in Figures 2 and 3 are merely examples, and the objects depicted in each image may be other types of observed objects.

[0016] The gyroscope D3 of the flying object D detects the inclination of the flying object D. The flying object D uses the gyroscope D3 to determine the direction the aircraft is facing and the attitude deviation from that direction based on the orientation information. The orientation information and inclination information of the flying object D are transmitted to the characteristic region determination system 100. It may be an acceleration sensor in three axial directions. The gimbal D4 supports the status information acquisition unit D1 on the flying object D so that it can tilt, making it possible to control the attitude of the status information acquisition unit D1. This makes it possible to control the optical axis of the status information acquisition unit D1. Information on the direction of the optical axis based on the inclination of the status information acquisition unit D1 is transmitted to the characteristic region determination system 100. The flying object D also receives orientation information using a geomagnetic sensor D5. This makes it possible to grasp the orientation (course) of the flying object D. Transmission of various data from the flying object D to the characteristic region determination system 100 is performed by the transmission unit T.

[0017] The characteristic region determination system 100 includes a position information receiving unit 110, an image receiving unit 120, an identifying unit 130, a determining unit 140, a control unit C, and a storage unit S. The position information receiving unit 110 receives from the flying object D positioning information (three-dimensional position, etc.) of the flying object D based on a navigation signal, one-dimensional position such as altitude and depth, tilt information, and optical axis direction information of the flying object D. For example, these may be received as information added to an image as EXIF ​​information.

[0018] The image receiving unit 120 receives an infrared image from the status information acquiring unit D1 of the flying object D. The identifying unit 130 identifies a characteristic region based on the status information. This identification includes identifying a specific imaging target or a group of imaging targets in the image, acquiring temperature information of the imaging targets, determining the status of each part of the imaging target based on the temperature information and a threshold value, and identifying the coordinates in the image of a region exhibiting a characteristic state (hereinafter referred to as a "characteristic region"). Each of the regions indicating each imaging target in the infrared image identified by the identifying unit 130 will be referred to as a "set region" below.

[0019] In the following, a photovoltaic power generation panel will be described as an example of the imaging target and the set area. Furthermore, for the sake of convenience, the "photovoltaic power generation panel or a group of a predetermined number of photovoltaic power generation panels" as the "set area" will be described simply as the "photovoltaic power generation panel" in principle. However, in this embodiment and other embodiments and their modified examples described below, even if the "set area" is described, the above is an example and is not limited to the photovoltaic power generation panel. Other examples of the set area or imaging target include a large number of automobiles, structures of buildings (glass, etc.), various sensors arranged in large numbers, mass-produced products that are inspected, etc.

[0020] (Specific Section 130) The identification unit 130 will be further described. The identification unit 130 identifies a set area in an infrared image. As an example, the identification unit 130 identifies the area based on the shape of the outer edge of the image capture target. When the image capture target is a solar power generation panel or a group of solar power generation panels, the set area may be identified based on the shape of the panel. As an example, "identifying an area" includes identifying the coordinates of the outer edge of the set area, or the coordinates belonging to the area.

[0021] For example, the photovoltaic power generation panel group as the specified target may be a photovoltaic power generation panel group with two vertical columns and two horizontal rows, or a photovoltaic power generation panel group with two vertical columns and one horizontal row. This detection unit may be determined for each characteristic region determination system and may not be changed, or may be a setting changeable by a user's operation via an input unit (not shown). Below, a configuration for specifying "each photovoltaic power generation panel" is described, but since this embodiment includes a modified example in which the specifying unit 130 detects "two or more photovoltaic power generation panels as one unit," the following description also takes into account such a modified example in which multiple imaging targets are detected as a group.

[0022] The determination unit 130 acquires temperature information for each set region in the infrared image by any known technique. For example, the temperature information is obtained from the color temperature of each minimum unit constituting the image in the infrared image. The minimum unit may be a pixel or a block of predefined pixel units. Coordinate information in the image may be associated with each minimum unit of temperature information.

[0023] The identification unit 130 also obtains the temperature distribution for each set region from the temperature information. The identification unit 130 further identifies the high temperature range, the medium temperature range, and the low temperature range in the temperature distribution. The high temperature range is, for example, the top 20% of temperature information in the distribution. The low temperature range is, for example, the bottom 20% of temperature information in the distribution. The medium temperature range is temperature information between the high temperature range and the low temperature range. The identification unit 130 also compares (for example, the difference) the temperature information of the high temperature range and the medium temperature range to identify a region showing a characteristic numerical value in the set region as a characteristic region. For example, the difference in the average value between the high temperature range and the medium temperature range in each set region, or the variation (standard deviation, etc.) of the difference between the set regions is used to compare the temperature information.

[0024] For example, for a set region with large variation, the identification unit 130 identifies a characteristic region by identifying the coordinates in the image of a set of high temperature regions in the temperature distribution of the set region. That is, in the above example, the identification unit 130 identifies the characteristic region in the following manner.

[0025] The identification unit 130 first separates the image target from other parts, and acquires temperature information for each minimum unit used to determine the peculiar part of the image target. Next, the identification unit 130 compares the temperature information of the high temperature range and the medium temperature range in the temperature distribution of the minimum unit. Next, the identification unit 130 groups several groups of minimum units, obtains the variation of the comparison results within the group, and extracts those with large variations. Next, the identification unit 130 identifies parts (pixels, etc.) that are in the high temperature range from those with large variations (e.g., suspected panel), and identifies the coordinates of the collection of those parts in the image. An example of a characteristic region is outlined in FIG. 4. The part surrounded by a thick black rectangle in FIG. 4 is an example of a set region. Within this rectangle, there is a part shown in white, which indicates the high temperature range in the above example, and the collection of pixels shown in white is the "characteristic region."

[0026] (Judgment unit 140) The determination unit 140 determines the identity of each feature region identified in each of the set regions in the plurality of divided regions, based on the position information and the state information acquisition direction. As an example, the determination unit 140 determines the position of the infrared image, for example, the position information of the center of the image. The determination unit 140 also calculates the estimated actual position of the feature region in the infrared image. Next, the determination unit 140 determines the identity of each feature region in the different infrared images based on a comparison of the estimated actual positions. Specific examples of these processes are given below.

[0027] <Infrared image location> The determination unit 140 identifies the position of the infrared image, for example, the position information of the center of the image. The determination unit 140 receives a navigation signal from the global positioning satellite system, i.e., information including the signal transmission time transmitted by the satellite and information related to the satellite orbit, via the position information receiving unit 110. Based on this information, the determination unit 140 identifies the two-dimensional position (e.g., latitude and longitude) and altitude or depth of the flying object D at the time of acquisition of the infrared image received from the status information receiving unit 120. Furthermore, the determination unit 140 associates information that associates the three-dimensional position of the flying object D and the time based on these with the infrared image. The determination unit 140 may perform this association at a predetermined time interval. In addition, the configuration is not limited to receiving information from the position information receiving unit 110 in this way, and if position information is added to the infrared image, the position information may be used.

[0028] The positional relationship between the status information acquisition unit D1 and the infrared image is determined based on the direction and inclination of the flying object D and the optical axis direction of the camera in the status information acquisition unit D1. In other words, the infrared image is not necessarily an image vertically below the two-dimensional position (Lat·Lng, etc.) of the flying object D specified above. Therefore, the determination unit 140 corrects the position information of the infrared image based on the direction and inclination information and the optical axis direction based on the orientation of the status information acquisition unit D1. An example of the details will be described next. Note that FIG. 5 is a conceptual diagram showing an overview of the correction process.

[0029] The determination unit 140 corrects the above various position information of the infrared image by the Vincenty forward solution based on the above azimuth information, tilt information, and optical axis direction information. For example, as shown in Fig. 5, the determination unit 140 determines a horizontal distance S that is calculated from the latitude, longitude, and altitude h of the shooting position of the flying object D and the composite pitch angle θ. The determination unit 140 also determines an azimuth angle α from the composite yaw angle and azimuth information. Based on this horizontal distance S and azimuth angle α, the determination unit 140 determines corrected position information. A specific example is as follows.

[0030] If the altitude of the flying object D obtained from the above various position information is h, the composite pitch angle obtained from the above tilt information and the optical axis direction is θ, and the mount length of the solar power panel is L, the "horizontal distance S" to the solar power panel can be calculated by the following formula 1. In addition, the "starting point" (longitude, latitude) used in the Vincenty forward solution is the above various position information, and the "azimuth angle" is obtained based on the composite yaw angle obtained from the above tilt information and the optical axis direction, and the orientation information obtained by the geomagnetic sensor.

[0031] (supplement) Altitude h: The height from the ground surface (ground surface) included in the GNSS information to the aircraft D (or the GNSS information receiver (not shown)). Alternatively, the height measured by an ultrasonic sensor, etc. Frame length L: The height from the ground surface (ground surface, etc.) to the center of the solar panel. starting point: Photographing position of aircraft D (Figure 5: latitude φ1, longitude λ1 / vertical downward position (ground surface)) Horizontal distance S: The distance from the above shooting position to the correction position (center position CP of the infrared image / latitude φ2, longitude λ2).

[0032]

number

[0033] Furthermore, the sensor size information and lens focal length of the status information acquisition unit D1 of the flying object D can be known in advance. In other words, it is possible to calculate the actual measurement ratio of the dimensions and sizes in the infrared image based on the horizontal distance S, the composite pitch angle θ, the sensor size, and the lens focal length.

[0034] That is, the determination unit 140 calculates the distance Sm from the position of the image center CP of the infrared image (e.g., Lat1, Lng1 in Fig. 7) to the position of the feature region appearing in the infrared image (Lat2, Lng2), and the azimuth angle of the feature region position relative to the center position (Fig. 7) based on the horizontal distance S and azimuth angle α (both in Fig. 5). This is done using Vincenty's forward method, similar to the method used to obtain the correction information for the infrared image position described above. The estimated actual position of the feature region (Lat2, Lng2) is stored in association with the infrared image.

[0035] <Determining the Identity of the Estimated Actual Location> Next, the determination unit 140 compares the estimated actual positions of the characteristic regions in the different infrared images (FIGS. 4 and 6). This comparison is performed as follows: The identification unit 130 identifies all infrared images that contain characteristic regions. Furthermore, the estimated actual position is calculated for each characteristic region. The determination unit 140 uses the Vincenty inverse method to find the distance between the longitude and latitude coordinates of the estimated actual positions of the characteristic regions in the different infrared images.

[0036] Once the distance between the longitude and latitude coordinates is calculated, the determination unit 140 then compares the calculated distance with a set value (such as a threshold value). If the calculated distance is less than the threshold value, the determination unit 140 estimates that the compared estimated actual positions are the same position. For example, in determining whether a solar panel is suspected of being faulty, feature areas (suspected fault areas) that appear in different infrared images are estimated to be the same. For example, the feature areas within the bold rectangular frames in Figures 4 and 6 are estimated to be the same.

[0037] (Control section C configuration) For convenience of explanation, the processing of each unit in the above description has been described as being executed under the control of the control unit C shown in Fig. 1. For example, the control unit C comprehensively controls the position information receiving unit 110, the image receiving unit 120, the identification unit 130, and the determination unit 140. The control unit C also performs control to store the positioning information (three-dimensional position information, time information, etc.) received by the position information receiving unit 110, the infrared image received by the image receiving unit 120, the presence or absence of a characteristic region, the estimated actual position of the characteristic region, etc.

[0038] The control unit C may be configured to include a single or multiple circuits, such as a central processing unit (CPU), a graphics processing unit (GPU), or an application specific integrated circuit (ASIC). The control unit C realizes its function by reading and executing, for example, an image position identification program stored in a memory. Instead of storing a program in a memory, the program may be directly built into the circuit. In this case, the control unit C realizes its function by reading and executing a program built into the circuit. The control unit C is not limited to being configured as a single circuit, and may be configured as a single processor by combining multiple independent circuits to realize its function. Furthermore, multiple components in the embodiment (for example, at least two or more of the position information receiving unit 110, the image receiving unit 120, the identifying unit 130, and the determining unit 140) may be integrated into a single processor to realize its function.

[0039] [Operation] Fig. 8 is a diagram showing the flow of processing in this embodiment. The flow of processing in the characteristic region determining system 100 will be described below along with step numbers (S001 to S007) with reference to Fig. 8.

[0040] (S001) The position information receiving section 110 in the characteristic region determining system 100 receives position information from the flying object D. Furthermore, the image receiving section 120 receives an infrared image.

[0041] (S002) The identification unit 130 identifies the photovoltaic power generation panel in the infrared image.

[0042] (S003) The identification unit 130 identifies a characteristic region based on the state information. For example, temperature information within each solar power generation panel in the infrared image identified by the identification unit 130 is acquired. The identification unit 130 also identifies a region showing a characteristic numerical value in the set region by comparing (e.g., the difference) temperature information between a high temperature region and a medium temperature region in the temperature distribution as the characteristic region. The characteristic region is stored in association with coordinates within the image in the infrared image.

[0043] (S004) The determination unit 140 identifies the position of the infrared image, for example, the position information of the center of the image, based on the shooting position information and the state information acquisition direction, etc.

[0044] (S005) The determining unit 140 also calculates an estimated actual position of the feature region within the infrared image.

[0045] (S006) The determination unit 140 then determines the identity of each of the feature regions in the different infrared images based on a comparison of the estimated actual positions.

[0046] (S007) The determination unit 140 performs display control so as not to present to the user any of the infrared images including the feature regions determined to be identical, or notifies the user that any of the infrared images including the feature regions determined to be identical are being presented in an overlapping manner.

[0047] [effect] According to this embodiment, when an entire area including a plurality of imaging targets is divided into an imaging range, the identity of each feature area identified in each divided area is determined based on the position information and the information acquisition direction information (imaging direction information, etc.). When feature areas appearing in different images are determined to be identical, display control is performed so that any of the infrared images including the feature areas determined to be identical are not presented to the user. Alternatively, the user is notified that any of the infrared images including the feature areas determined to be identical are presented in duplicate.

[0048] This configuration can prevent a user from inspecting the same feature area that appears in different images multiple times, thereby reducing the amount of work and processing costs required of the user.

[0049] Furthermore, the imaging target in the infrared image is identified from other objects, and temperature information of objects other than the imaging target is excluded from the information used for abnormality determination. For example, in a solar power generation facility, between one solar power generation panel group and another solar power generation panel group, there are power generation equipment (power controllers and cables), asphalt pavement, water, plants, etc., which present temperature information completely different from that of the solar power generation panels. If temperature abnormality is detected in the entire infrared image, there is a possibility that such noise will be included, which may hinder abnormality determination. According to this embodiment, the solar power generation panel is first identified, and abnormality determination is performed for each solar power generation panel or each solar power generation panel group. As a result, it is possible to reduce the possibility of noise being included. Furthermore, depending on the arrangement position of the solar power generation panel, for example, the average value of temperature information may differ between the upper right corner and the lower left corner of the solar power generation panel array due to shadows, and in this respect, it is also possible to reduce errors in abnormality determination.

[0050] According to the above embodiment, since the occurrence of misjudgment is reduced, panels that are unlikely to be faulty are more likely to be excluded from suspected faults, which makes it possible to reduce the considerable effort and processing costs imposed on the user.

[0051] [Second embodiment] A state determination system 200 according to the second embodiment will be described with reference to Figures 9 to 11. In the following description, descriptions that overlap with those of the first embodiment will be omitted.

[0052] As in the first embodiment, in the second embodiment, the object to be imaged in the infrared image is identified (set area), and the characteristic area is identified by identifying the coordinates in the image of a group of parts that are high temperature areas in the set area based on the difference in the average values ​​of the high temperature area and the medium temperature area in each set area and the variation in this difference between the set areas.

[0053] (Condition Determination System 200) 9, the state determination system 200 of the second embodiment includes a position information receiving unit 210, an image receiving unit 220, an identifying unit 230, a determining unit 240, a control unit C, and a storage unit S. The position information receiving unit 210, the image receiving unit 220, and the identifying unit 230 are similar to those of the first embodiment, and therefore will not be described.

[0054] (Judgment unit 240) The determination unit 240 determines the identity of each feature region specified in each of the set regions in the plurality of divided regions based on the position information and the state information acquisition direction. As an example, the process of the determination unit 240 will be described with reference to FIG.

[0055] The determination unit 240 compares the estimated actual positions of the characteristic regions in the same manner as in the first embodiment. That is, the determination unit 240 uses Vincenty's inverse solution to obtain the distance between the longitude and latitude coordinates of the estimated actual positions of the characteristic regions in the different infrared images.

[0056] In the determination unit 240, a condition for determining that two feature regions are the same has been added from the first embodiment. That is, when feature regions determined to be the same in the above-mentioned distance-based determination are further in a predetermined relationship based on the arrangement shape or arrangement rule of the image pickup target in the infrared image, they are ultimately determined to be the same feature region. Alternatively, before the determination of identity, the above-mentioned distance-based determination is made when the feature regions to be compared are in a predetermined relationship based on the arrangement rule or the like.

[0057] For example, in the case of solar panels, each panel is arranged in a matrix. Also, the shape of a solar panel tends to have its long side in the horizontal direction and its short side in the vertical direction. Therefore, even if feature regions appearing in different images are separated in the horizontal direction, they may be determined to be the same because they are close in the vertical direction. In other words, even if different feature regions exist on adjacent panels in the vertical direction, they may be determined to be the same feature region because they are adjacent in the vertical direction.

[0058] As a countermeasure to this, the determination unit 240 determines whether the solar panels arranged in a matrix have the same horizontal position, in other words, whether the panels belong to the same row, as an additional condition. That is, the determination unit 240 executes both a determination based on distance similar to the first embodiment and a determination of whether they belong to the same row, and is configured to finally determine that they are the same feature area when both conditions are satisfied.

[0059] Note that since the identification unit 230 identifies the photovoltaic power generation panels in the infrared image, the determination unit 240 identifies the above-mentioned rows based on the positions of each panel identified in the image. For example, the determination unit 240 identifies a group of panels in the image, and identifies the row and column of the photovoltaic power generation panels in the group.

[0060] In addition, if there is a regularity in the arrangement of the observation targets such as photovoltaic power generation panels, the determination unit 240 may supplementarily use information on the arrangement rule when identifying the rows. In the case of a matrix arrangement, since each panel is arranged in a roughly linear manner, the determination unit 240 performs a determination based on the above distance for panels adjacent to each other in a linear manner along the lateral direction of one panel. As another example, consider an arrangement rule in which a plurality of observation targets are arranged in a circle, and the arrangement becomes concentric. The determination unit 240 regards a set of observation targets appearing in the image as one group, and identifies the outer edge of the group. The determination unit 240 assumes the center position of the circular arrangement for each observation target group (each set) based on the identified outer edge. Since the entire group of circular observation targets may not appear in the image, this center position may be assumed to be a position outside the image. If the arrangement rule is a perfect circle, the determination unit 240 regards each observation target at an equal distance from the assumed center position as the above determination target.

[0061] The arrangement rule does not have to be a perfect circle. For example, if the arrangement rule is an ellipse, and the shape of the ellipse is set in advance, it is possible to specify other observation targets to be judged for one observation target based on the curvature of each part of the outer edge of the observation target that appears in the image. It is also possible to exclude other observation targets for one observation target from the judgment targets.

[0062] As shown in Fig. 10, the first feature region (Lat2, Lng2) in the image on the left side and the second feature region (Lat3, Lng3) in the image on the right side are arranged in a matrix pattern, and are adjacent to each other in the longitudinal direction (horizontal direction in Fig. 10) of the rectangular observation target. The determination unit 240 determines the identity of the feature regions based on the distance between the feature regions included in the set region (observation target) in the same row (predetermined positional relationship set in advance).

[0063] [Operation] Fig. 11 is a diagram showing the flow of processing in this embodiment. Below, with reference to Fig. 11, the flow of processing in the characteristic region determining system 200 will be explained along with step numbers (S011 to S017).

[0064] (S011) A position information receiving section 210 in the characteristic region determining system 200 receives position information from the flying object D. Furthermore, an image receiving section 220 receives an infrared image.

[0065] (S012) The identification unit 230 identifies the photovoltaic power generation panel in the infrared image.

[0066] (S013) The identification unit 230 identifies a characteristic region based on the state information. For example, temperature information within each solar power generation panel in the infrared image identified by the identification unit 230 is acquired. The identification unit 230 also identifies a region showing a characteristic value in the set region by comparing (e.g., the difference) temperature information between a high temperature region and a medium temperature region in the temperature distribution as the characteristic region. The characteristic region is stored in association with coordinates within the image in the infrared image.

[0067] (S014) The determination unit 240 identifies the position of the infrared image, for example, the position information of the center of the image, based on the shooting position information and the state information acquisition direction, etc.

[0068] (S015) The determining unit 240 also calculates an estimated actual position of the feature region within the infrared image.

[0069] (S016) Next, the determination unit 240 determines which subset the characteristic region belongs to among the subsets set based on the shape features of the photovoltaic power generation panels and the arrangement rules of the photovoltaic power generation panels. As a specific example, in the case of a general photovoltaic power generation facility in which the photovoltaic power generation panels are short in the vertical direction and long in the horizontal direction and arranged in a matrix, the process is executed as follows. If a group of photovoltaic power generation panels is set as a universal set, and a set of photovoltaic power generation panels arranged in the row direction of the matrix arrangement in the universal set is set as a subset, the determination unit 240 identifies the universal set in the infrared image including the characteristic region. Next, the determination unit 240 identifies a subset in the row direction of the universal set (a set of set regions). Next, the determination unit 240 determines which subset the characteristic region belongs to (which row of the matrix arrangement it belongs to).

[0070] (S017) Next, the determination unit 240 compares the estimated actual positions of the feature regions in the different infrared images that are determined to belong to the same subset based on the subset determination result in S016. In this way, the determination unit 240 determines the identity of each of the feature regions in the different infrared images.

[0071] (S018) The determination unit 240 performs display control so as not to present to the user any of the infrared images including the feature regions determined to be identical, or notifies the user that any of the infrared images including the feature regions determined to be identical are being presented in an overlapping manner.

[0072] [effect] According to this embodiment, when an entire area including a plurality of imaging targets is divided into an imaging range, the identity of each feature area identified in each divided area is determined based on the position information and the information acquisition direction information (imaging direction information, etc.). When feature areas appearing in different images are determined to be identical, display control is performed so that any of the infrared images including the feature areas determined to be identical are not presented to the user. Alternatively, the user is notified that any of the infrared images including the feature areas determined to be identical are presented in duplicate.

[0073] Furthermore, in the second embodiment, a condition for determining that two feature regions are the same is added to that in the first embodiment. That is, when feature regions determined to be the same based on the distance described above have a predetermined relationship based on the arrangement shape or arrangement rule of the imaged object in the infrared image, they are ultimately determined to be the same feature region.

[0074] This configuration can prevent a user from inspecting the same feature area that appears in different images multiple times, thereby reducing the amount of work and processing costs required of the user.

[0075] Furthermore, the imaging target in the infrared image is identified from other objects, and temperature information of objects other than the imaging target is excluded from the information used for abnormality determination. For example, in a solar power generation facility, between one solar power generation panel group and another solar power generation panel group, there are power generation equipment (power controllers and cables), asphalt pavement, water, plants, etc., which present temperature information completely different from that of the solar power generation panels. If temperature abnormality is detected in the entire infrared image, there is a possibility that such noise will be included, which may hinder abnormality determination. According to this embodiment, the solar power generation panel is first identified, and abnormality determination is performed for each solar power generation panel or each solar power generation panel group. As a result, it is possible to reduce the possibility of noise being included. Furthermore, depending on the arrangement position of the solar power generation panel, for example, the average value of temperature information may differ between the upper right corner and the lower left corner of the solar power generation panel array due to shadows, and in this respect, it is also possible to reduce errors in abnormality determination.

[0076] According to the above embodiment, since the occurrence of misjudgment is reduced, panels that are unlikely to be faulty are more likely to be excluded from suspected faults, which makes it possible to reduce the considerable effort and processing costs imposed on the user.

[0077] [Third embodiment] The overall configuration of a characteristic region determination system 300 according to the third embodiment will be described with reference to Fig. 12 and Fig. 13. Note that the characteristic region determination system in Fig. 12 is just one example, and does not exclude the inclusion of other configurations, and can be embodied in various forms. In the third embodiment, an example of inspecting the fertility state of soil in a farm will be described.

[0078] (Overview of the Flying Vehicle D) 12, the flying object D includes a status information acquisition unit D1, a position receiving unit D2, a gyroscope D3, and a gimbal D4. As in the first and second embodiments, the status information acquisition unit D1 includes an infrared camera, and the position receiving unit D2 measures the three-dimensional position of the flying object D and adds it to the infrared image. Also, this is similar to the first and second embodiments in that this is transmitted as additional information to the characteristic region determination system 300 together with the infrared image.

[0079] The gyroscope D3 and gimbal D4 of the flying object D are similar to those in the first and second embodiments. A transmitting unit T transmits various data from the flying object D to the characteristic region determination system 300.

[0080] The characteristic region determination system 300 includes a position information receiving section 310, an image receiving section 320, a specifying section 330, a determination section 340, a control section C, and a storage section S. The position information receiving section 310 and the image receiving section 320 are similar to those in the first and second embodiments.

[0081] In the following description, the soil portion of a farm is taken as an example of an imaging target, and the "set region" is described below.

[0082] (Specific Section 330) The identification unit 330 identifies a set area in the infrared image. As an example, the area is identified based on the overall shape of the outer edge of the soil part as the imaging target, and the partial shapes of a predetermined size that are divided into partial areas arranged in a matrix. "Identifying an area" includes, as an example, identifying the coordinates of the outer edge of the set area, or the coordinates that belong to the area.

[0083] For example, the method of dividing the soil portion may be determined for each characteristic area determination system and may not be changed, or the settings may be changeable by user operation via an input unit (not shown).

[0084] The determination unit 330 acquires temperature information for each set region in the infrared image by any known technique. For example, the temperature information is obtained from the color temperature of each minimum unit constituting the image in the infrared image. The minimum unit may be a pixel or a block of predefined pixel units. Coordinate information in the image may be associated with each of the minimum unit temperature information.

[0085] The identification unit 330 also obtains the temperature distribution for each set region from the temperature information, and identifies the high temperature region, the medium temperature region, and the low temperature region, in the same manner as in the first embodiment, etc. The identification unit 330 also identifies the characteristic region, in the same manner as in the first embodiment, etc.

[0086] (Judgment unit 340) The determination unit 340 determines the identity of each of the characteristic regions in the different infrared images, as in the first or second embodiment.

[0087] [Operation] Fig. 13 is a diagram showing the flow of processing in this embodiment. Below, with reference to Fig. 13, the flow of processing in the characteristic region determining system 300 will be explained along with step numbers (S021 to S029).

[0088] (S021) A position information receiving section 310 in the characteristic region determination system 300 receives position information from the flying object D. Furthermore, an image receiving section 320 receives an infrared image.

[0089] (S022) The identification unit 330 identifies the regions based on the overall shape of the outer edge of the soil portion in which the plant to be imaged is planted, and the partial shapes of a predetermined size that are determined by dividing the overall shape into partial regions arranged in a matrix.

[0090] (S023) The identification unit 330 identifies a characteristic region based on the state information. For example, the identification unit 330 acquires temperature information within each set region (partial region) obtained by dividing the entire soil in the infrared image identified by the identification unit 330. The identification unit 330 also identifies a region in the set region that shows a characteristic numerical value as a characteristic region by comparing (for example, the difference) temperature information between a high temperature region and a medium temperature region in the temperature distribution. The characteristic region is stored in association with coordinates within the image in the infrared image.

[0091] (S024) The determination unit 340 identifies the position of the infrared image, for example, the position information of the center of the image, based on the shooting position information and the state information acquisition direction, etc.

[0092] (S025) The determining unit 340 also calculates an estimated actual location of the feature region within the infrared image.

[0093] (S026) Next, the determination unit 340 determines which subset the characteristic region belongs to among the subsets set based on the shape features of the set region and the arrangement rules of the set regions set by dividing the whole. As a specific example, when the set regions are short vertically and long horizontally, and are arranged in a matrix, the process is executed as follows. If the soil portion before division is set as the universal set, and the set of set regions arranged in the row direction of the matrix arrangement in the universal set is set as a subset, the determination unit 340 identifies the universal set in the infrared image including the characteristic region. Next, the determination unit 340 identifies the subset in the row direction of the universal set. Next, the determination unit 340 determines which row the characteristic region belongs to (which row in the matrix arrangement it belongs to).

[0094] (S027) Next, the determination unit 340 compares the estimated actual positions of the feature regions in the different infrared images that are determined to belong to the same subset based on the subset determination result in S026. In this way, the determination unit 340 determines the identity of each of the feature regions in the different infrared images.

[0095] (S028) The determination unit 340 performs display control so as not to present to the user any of the infrared images including the feature regions determined to be identical, or notifies the user that any of the infrared images including the feature regions determined to be identical are being presented in an overlapping manner.

[0096] [effect] According to this embodiment, when an entire area including a plurality of imaging targets is divided into an imaging range, the identity of each feature area identified in each divided area is determined based on the position information and the information acquisition direction information (imaging direction information, etc.). When feature areas appearing in different images are determined to be identical, display control is performed so that any of the infrared images including the feature areas determined to be identical are not presented to the user. Alternatively, the user is notified that any of the infrared images including the feature areas determined to be identical are presented in duplicate.

[0097] In addition, if feature areas that are determined to be identical based on the above distance-based determination are further in a predetermined relationship based on the arrangement shape or arrangement rules of the imaged object in the infrared image, they may be concluded to be the same feature area.

[0098] This configuration can prevent a user from inspecting the same feature area that appears in different images multiple times, thereby reducing the amount of work and processing costs required of the user.

[0099] Furthermore, the imaging target in the infrared image is identified from other objects, and temperature information of other objects than the imaging target is excluded from the information used for abnormality judgment. For example, in a farm, there are farm roads, paved roads, waterways, fences, pest control tools, pest control equipment, farm tools, storage sheds, etc., which exhibit temperature information completely different from the soil part where crops are grown. If temperature abnormality is detected in the entire infrared image, there is a possibility that such noise will be included, which may hinder abnormality judgment. According to this embodiment, the soil part to be judged is first identified, and abnormality judgment is performed for each set area divided from the soil part. As a result, it is possible to reduce the possibility of noise being included. Furthermore, depending on the position of the soil part in the entire farm, for example, the average value of temperature information may differ due to shadows, and in this respect, it is also possible to reduce errors in abnormality judgment.

[0100] According to the above embodiment, since the occurrence of misjudgment is reduced, panels that are unlikely to be faulty are more likely to be excluded from suspected faults, which makes it possible to reduce the considerable effort and processing costs imposed on the user.

[0101] [Fourth embodiment] The overall configuration of a characteristic region determination system 400 according to the fourth embodiment will be described with reference to Fig. 14 to Fig. 15. Note that the characteristic region determination system in Fig. 14 is just one example, and does not exclude the inclusion of other configurations, and can be embodied in various forms. In the fourth embodiment, an example of inspecting the fertility state of soil in a farm will be described.

[0102] (Overview of Aircraft D) 14, the flying object D includes a status information acquisition unit D1, a position receiving unit D2, a gyroscope D3, and a gimbal D4. The status information acquisition unit D1 is an optical device, such as a multispectral camera, an RGB camera, or a hyperspectral camera. The position receiving unit D2 measures the three-dimensional position of the flying object D and adds the position information to the captured image, as in the first to third embodiments. Also, the information is transmitted as additional information to the characteristic region determination system 400 together with the captured image.

[0103] The gyroscope D3 and gimbal D4 of the flying object D are similar to those of the first to third embodiments. A transmitting unit T transmits various data from the flying object D to the characteristic region determination system 400.

[0104] The characteristic region determination system 400 includes a position information receiving unit 410, an image receiving unit 420, an identifying unit 430, a determining unit 440, a control unit C, and a storage unit S. The position information receiving unit 410 is the same as in the first and second embodiments. The image receiving unit 420 receives a captured image from a status information acquiring unit D1 (such as a spectrum camera) of the flying object D. The identifying unit 430 identifies the characteristic region based on the status information. This identification includes identifying a predetermined imaging target or a group of imaging targets in the image, acquiring a vegetation index of the imaging target, determining the status of each part of the imaging target based on the vegetation index and a threshold value, and identifying the coordinates in the image in the characteristic region. In addition, each of the regions indicating the imaging targets in the captured image identified by the identifying unit 430 will be referred to as a "set region" hereinafter, as in the above embodiment.

[0105] In the following, plants are used as an example of the imaging subject. Plants include grains (corn, rice (paddy rice), wheat, etc.) and other crops, fresh flowers, cotton, etc. The "set area" is also explained below. Vegetation indices are invented for the purpose of grasping the state of vegetation with a simple formula using data photographed from the air, taking advantage of the characteristics of light reflection by plants, and represent the amount and vitality of plants. A typical vegetation index is the Normalized Difference Vegetation Index (NDVI).

[0106] (Specific section 430) The identification unit 430 identifies a set area in the captured image. As an example, the area is identified based on the overall shape of the outer edge of a group of plants that are aligned and grown as the image capture subject, and a partial area in which one plant or a predetermined number of plants is one unit. "Identifying the area" includes, as an example, identifying the coordinates of the outer edge of a set area in which one or more plants are one unit, or the coordinates belonging to the area. Alternatively, the area belonging to one constituent unit may be identified as any set shape, such as a square, rectangle, circle, or polygon, in the captured image without strictly identifying one plant or the unit.

[0107] For example, the above-mentioned identification method may be determined for each characteristic region determination system and may not be changed, or the settings may be changeable by user operation via an input unit (not shown).

[0108] The identifying unit 430 acquires a vegetation index for each set region in the captured image by any known technique. For example, the vegetation index is obtained from the reflected light of red light (e.g., wavelength of about 620 nm to 680 nm) and near-infrared light (e.g., wavelength of about 760 nm to 780 nm) for each minimum unit constituting the image in the captured image. The minimum unit may be a pixel or a block of predefined pixel units. Coordinate information in the image may be associated with each of the minimum unit vegetation indices. NDVI=(IR-R) / (IR+R) IR: Near infrared reflectance R: Red light reflection

[0109] The identifying unit 430 obtains the vegetation condition for each set region from the vegetation index in the same manner as in the first embodiment and identifies the high activity region, the medium activity region, and the low activity region. The activity level here may be the vegetation index itself, a corrected value of the vegetation index, or an evaluation value or evaluation rank calculated based on these. The high activity region is, for example, the top 20% of activity information in the distribution. The low activity region is, for example, the bottom 20% of activity information in the distribution. The medium activity region is activity information between the high activity region and the low activity region.

[0110] The identification unit 430 also identifies an area showing a characteristic value in the set area as a characteristic area by comparing (e.g., the difference) between the activity information of the medium activity area and the low activity area. For example, the difference between the average values ​​of the medium activity area and the low activity area in each set area, or the variation (standard deviation, etc.) of the difference between the set areas is used to compare the activity information.

[0111] For example, for a set region with large variation, the identification unit 430 identifies a feature region by identifying the coordinates in the image of a set of low activity regions in the activity distribution of the set region. That is, in the above example, the identification unit 430 identifies the feature region in the following manner.

[0112] The identification unit 430 first separates the measurement target from non-measurement target portions, and acquires activity information for each minimum constituent unit used to determine peculiar portions of the measurement target. The identification unit 430 then compares the activity information of the medium activity area and the low activity area in the activity distribution of the minimum constituent units. The identification unit 430 then groups a number of groups of minimum constituent units, finds the variance of the comparison results within the group, and extracts those with large variance. The identification unit 130 then identifies portions (pixels, etc.) that are low activity areas from those with large variances (e.g., suspected panels), and identifies the coordinates of the collection of those portions within the image.

[0113] (Judgment unit 440) The determination section 440 determines the identity of each of the feature regions in different captured images, as in the first or second embodiment.

[0114] [Operation] Fig. 15 is a diagram showing the flow of processing in this embodiment. Below, with reference to Fig. 15, the flow of processing in the characteristic region determining system 400 will be explained along with step numbers (S031 to S039).

[0115] (S031) A position information receiving section 410 in the characteristic region determination system 400 receives position information from the flying object D. An image receiving section 420 receives a captured image.

[0116] (S032) The identification unit 430 identifies the region based on a partial region in which one plant or a predetermined number of plants of the plant to be imaged is one unit. Alternatively, the identification unit 430 may identify a region belonging to one constituent unit as an arbitrary set shape such as a square, rectangle, circle, or polygon in the captured image without strictly identifying one plant or the unit.

[0117] (S033) The identification unit 430 identifies a characteristic region based on the state information. For example, the identification unit 430 acquires a vegetation index within each set region (partial region) in the captured image identified by the identification unit 430 in S032. The identification unit 430 also identifies a region in the set region that shows a characteristic numerical value by comparing (for example, the difference) the vegetation index of a low activity region and a medium activity region in the activity distribution as a characteristic region. The characteristic region is stored in association with the coordinates within the image in the captured image.

[0118] (S034) The determination unit 440 specifies the position of the captured image, for example, the position information of the center of the image, based on the capturing position information and the state information acquisition direction, etc.

[0119] (S035) The determination unit 440 also calculates the estimated actual position of the characteristic region within the captured image.

[0120] (S036) Next, the determination unit 440 determines which subset the characteristic region belongs to among the subsets set based on the shape features of the set regions and the arrangement rules of the set regions. As a specific example, when the set regions are arranged in a matrix, the process is executed as follows. If all the plants to be measured are set as the universal set, and a set of set regions arranged in the row direction of the matrix arrangement in the universal set is set as a subset, the determination unit 440 identifies the universal set in the captured image including the characteristic region. Next, the determination unit 440 identifies a subset in the row or column direction of the universal set. Next, the determination unit 440 determines which row or column the characteristic region belongs to (which row in the matrix arrangement it belongs to). Whether the direction is the row or column direction is set based on the outer edge shape of the set area, as in the above embodiment.

[0121] (S037) Next, the determination unit 440 compares the estimated actual positions of the feature regions in the different captured images that are determined to belong to the same subset based on the subset determination result in S036. In this way, the determination unit 440 determines the identity of each of the feature regions in the different captured images.

[0122] (S038) The determination unit 440 performs display control so as not to present to the user any of the captured images including the feature regions determined to be identical, or notifies the user that any of the captured images including the feature regions determined to be identical are being presented in an overlapping manner.

[0123] In addition, as in the present embodiment, the data indicating the vegetation state of plants is not limited to NDVI and numerical information using or correcting it (such as nitrogen absorption amount). For example, it may be numerical information or indexes indicating any vegetation state, such as vegetation coverage information or photosynthetic efficiency, or evaluation information obtained by analyzing them.

[0124] As described in the second embodiment, when the arrangement of the plants is not in a matrix form, the determination can be processed in the same manner as in the second embodiment. Also, it is possible for the determination unit 440 to perform the determination simply based on the distance and a threshold value, without using the arrangement rules as in the first embodiment.

[0125] [effect] According to this embodiment, the identity of each feature area specified in the set area is determined based on the position information and information acquisition direction information (photographing direction information, etc.). When feature areas appearing in different images are determined to be identical, display control is performed so that any of the captured images including the feature areas determined to be identical are not presented to the user. Alternatively, the user is notified that any of the captured images including the feature areas determined to be identical are presented in an overlapping manner.

[0126] In addition, if feature areas that are determined to be identical based on the above distance-based determination are further in a predetermined relationship based on the arrangement shape or arrangement rules of the object to be imaged in the captured image, they may be concluded to be the same feature area.

[0127] This configuration can prevent a user from inspecting the same feature area that appears in different images multiple times, thereby reducing the amount of work and processing costs required of the user.

[0128] Furthermore, the imaging target in the captured image is identified from other objects, and pixels and the like that are not the imaging target are excluded from the information used for abnormality determination. For example, in a farm, there are farm roads, paved roads, waterways, fences, pest control tools, pest control equipment, farm implements, storage sheds, and other objects that exhibit vegetation indices that are completely different from plants. If activity abnormalities are detected in the entire captured image, there is a possibility that such noise will be included in large quantities, which may hinder abnormality determination. According to this embodiment, the soil portion to be determined is first identified, and abnormality determination is performed for each set area divided from the soil portion. As a result, it is possible to reduce the possibility of noise being included. Furthermore, depending on the position of the soil portion in the entire farm, for example, the average value of the vegetation index may differ due to shadows, and in this respect, it is also possible to reduce errors in abnormality determination.

[0129] According to the above embodiment, since the occurrence of misjudgment is reduced, panels that are unlikely to be faulty are more likely to be excluded from suspected faults, which makes it possible to reduce the considerable effort and processing costs imposed on the user.

[0130] Although the embodiments of the present invention have been described, the above embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included in the scope and spirit of the invention, and are included in the invention and its equivalents described in the claims. [Explanation of symbols]

[0131] 100, 200, 300, 400 Feature Region Judgment System 110, 210, 310, 410 Location information receiving unit 120, 220, 320, 420 Image receiving unit 130, 230, 330, 430 Specific part 140, 240, 340, 440 Judgment section D. Flying object D1 Status information acquisition unit D2 Position acquisition part D3 Gyroscope D4 Gimbal D5 Geomagnetic Sensor

Claims

1. a status information receiving unit that receives, from the aircraft, status information indicating a status of a divided region obtained by dividing the entire observation target into a plurality of regions; a position information receiving unit for receiving position information and shooting direction information at the time of information acquisition in the state information; an identification unit that identifies a feature region based on the state information; a determination unit that calculates a position in the entire observation target for each of the feature regions identified in the plurality of divided regions, and determines identity based on whether the calculated positions of the feature regions are within a set range; The location information includes a navigation signal received by the aircraft from a global positioning satellite system corresponding to the photographing, The shooting direction information includes a direction of the aircraft and a direction of a shooting unit provided on the aircraft, The determination unit (A) calculates the position information using a first calculation method based on orientation information of the flying object, inclination information of the flying object, and an optical axis direction based on the orientation of the image capture unit, (B) calculates an azimuth angle from the orientation information and a composite yaw angle obtained from the inclination information and the optical axis direction, and the azimuth angle, and (C) calculates a distance between longitude and latitude coordinates of the positions of characteristic regions in separate infrared images using a second calculation method. A feature region determination system comprising:

2. In the divided region, a plurality of observation objects that may include the feature region are arranged in a predetermined shape, The determination unit determines the identity based on the position information, the shooting direction information, and a matrix-like arrangement rule of the plurality of observation objects.

2. The system according to claim 1, wherein the characteristic region is a region that is a feature of the image.

3. In the divided region, a plurality of observation objects that may include the feature region are arranged in a predetermined shape, The determination unit determines the identity based on the position information, the shooting direction information, and a circular arrangement rule of the plurality of observation objects.

2. The system according to claim 1, wherein the characteristic region is a region that is a feature of the image.

4. the status information is an infrared image; The identification unit identifies a characteristic region based on temperature information of each of the infrared images.

4. The system according to claim 1, wherein the characteristic region is a region that is a feature of the image.

5. the state information is an image showing a vegetation state of a plant, The identification unit identifies a characteristic region based on vegetation condition information of each of the images showing the vegetation condition.

5. The system according to claim 1, wherein the characteristic region is a region that is a feature of the image.

Images