Remote sensing product authenticity inspection method, device, electronic equipment and storage medium

Abstract

The present invention provides a remote sensing product authenticity verification method, device, electronic device and storage medium, which relates to the field of remote sensing technology. The method includes: based on the distribution of vegetation in the original remote sensing image, determining multiple original detection sample points, collecting target data corresponding to each original detection sample point, the target data including the angle less than 90° between the ground where the original detection sample point is located and the horizontal plane, obtaining the position of each target detection sample point based on the target data corresponding to each original detection sample point, performing data collection at each target detection sample point, obtaining the ground measurement value corresponding to the remote sensing product to be tested, and performing authenticity verification based on the ground measurement value. The remote sensing product authenticity verification method, device, electronic device and storage medium provided by the present invention can more accurately determine the target detection sample points on the basis of comprehensively considering the natural growth state of vegetation and the actual terrain and geomorphic characteristics, and can provide a more accurate data basis for the authenticity verification of remote sensing products.

Description

Technical Field

[0001] The present invention relates to the field of remote sensing technology, and in particular to a remote sensing product authenticity inspection method, device, electronic equipment and storage medium. Background Art

[0002] With the development of remote sensing technology, remote sensing images collected by remote sensing sensors are widely used in environmental monitoring and protection, natural resource investigation and management, agricultural production monitoring, disaster warning and assessment, etc.

[0003] Normally, in order to ensure the image quality of remote sensing images, remote sensing sensors usually collect remote sensing images during the day when the weather is fine. However, the canopy structure of vegetation will form shadow areas on the ground under the illumination of light. The information of vegetation shadow areas in remote sensing images is often blocked or distorted, which reduces the information content and analysis accuracy of remote sensing images. Therefore, removing shadows in remote sensing images is a key step to improve the image quality and analysis effect of remote sensing images.

[0004] However, due to the differences in lighting conditions, climate, vegetation types, and topography in different regions, the actual growth state of vegetation is usually more complicated. When performing remote sensing image shadow removal in related technologies, the actual growth state of vegetation is not considered, making it difficult to accurately remove shadows from remote sensing images. Therefore, how to more accurately remove shadows from remote sensing images is a technical problem that needs to be solved in this field. Summary of the invention

[0005] The present invention provides a remote sensing image shadow removal method, device, electronic device and storage medium, which are used to solve the defect that it is difficult to accurately remove the shadow of the remote sensing image in the prior art, and to achieve more accurate shadow removal of the remote sensing image, which is a technical problem to be solved urgently in the field.

[0006] The invention provides a remote sensing image shadow removal method, comprising the following steps.

[0007] Based on the distribution of vegetation in the original remote sensing image, a plurality of original detection sample points are determined, and the remote sensing product to be tested is obtained based on the original remote sensing image;

[0008] Collect target data corresponding to each original detection sample point, the target data corresponding to any original detection sample point includes the vertical distance between the highest point of the canopy of the sample vegetation corresponding to any original detection sample point and the ground, the canopy width of the sample vegetation corresponding to any original detection sample point, the angle less than 90° between the ground where any original detection sample point is located and the horizontal plane, and the bending angle of the sample vegetation corresponding to any original detection sample point, the bending angle of the sample vegetation is the angle between the central axis of the sample vegetation and the vertical plane that is not greater than 90°, and the angle between the ground where any original detection sample point is located and the horizontal plane is not 0°;

[0009] Based on the target data corresponding to each original detection sample point, the position of each original detection sample point is corrected to obtain the position of each target detection sample point;

[0010] Based on the position of each target detection sample point, data is collected at each target detection sample point, and based on the collected data, a ground measurement value corresponding to the remote sensing product to be inspected is obtained;

[0011] An authenticity check is performed on the remote sensing product to be checked based on the ground measurement value to obtain an authenticity check result of the remote sensing product to be checked.

[0012] According to a remote sensing image shadow removal method provided by the present invention, based on the target data corresponding to each original detection sample point, the position of each original detection sample point is corrected to obtain the position of each target detection sample point, including:

[0013] Based on the target data corresponding to each original detection sample point, obtaining the offset corresponding to each original detection sample point;

[0014] Move any of the original detection sample points along the offset direction corresponding to the any of the original detection sample points by the offset amount corresponding to the any of the original detection sample points, and determine the position of the any of the original detection sample points after the move as the position of the target detection sample point corresponding to the any of the original detection sample points, and the offset direction corresponding to the any of the original detection sample points is determined based on the position of the vertical projection point of the highest point of the canopy of the sample vegetation corresponding to the any of the original detection sample points on the ground.

[0015] According to a remote sensing image shadow removal method provided by the present invention, the step of obtaining the offset corresponding to each original detection sample point based on the target data corresponding to each original detection sample point includes:

[0016] Based on the target data corresponding to any one of the original detection sample points, obtaining the offset corresponding to any one of the original detection sample points includes:

[0017] In the case that the number of sample vegetation corresponding to any original detection sample point is one, a first intermediate result corresponding to any original detection sample point is calculated based on the vertical distance between the highest point of the canopy of the sample vegetation corresponding to any original detection sample point and the ground, the bending angle of the sample vegetation corresponding to any original detection sample point, and the angle less than 90° between the ground where the any original detection sample point is located and the horizontal plane, and a second intermediate result corresponding to any original detection sample point is calculated based on the canopy width of the sample vegetation corresponding to any original detection sample point, the bending angle of the sample vegetation corresponding to any original detection sample point, and the angle less than 90° between the ground where the any original detection sample point is located and the horizontal plane, and then the difference between the first intermediate result and the second intermediate result corresponding to any original detection sample point is determined as the offset corresponding to the any original detection sample point;

[0018] In the case that there are multiple sample vegetations corresponding to any of the original detection sample points, for each sample vegetation corresponding to any of the original detection sample points, based on the vertical distance between the highest point of the canopy of each sample vegetation and the ground, the bending angle of the sample vegetation corresponding to each sample vegetation, and the angle less than 90° between the ground where the any of the original detection sample points is located and the horizontal plane, a first intermediate result corresponding to each sample vegetation is calculated; based on the canopy width of each sample vegetation, the bending angle of each sample vegetation, and the angle less than 90° between the ground where the any of the original detection sample points is located and the horizontal plane, a second intermediate result corresponding to each sample vegetation is calculated; the difference between the first intermediate result and the second intermediate result corresponding to each sample vegetation is calculated as the offset corresponding to each sample vegetation; and the average value of the offsets corresponding to the sample vegetations corresponding to any of the original detection sample points is determined as the offset corresponding to the any of the original detection sample points.

[0019] According to a remote sensing image shadow removal method provided by the present invention, before moving any of the original detection sample points along the offset direction corresponding to the any of the original detection sample points by the offset amount corresponding to the any of the original detection sample points, the method further includes:

[0020] In the case that the number of sample vegetation corresponding to any one of the original detection sample points is one, the direction of the vertical projection point of the highest point of the canopy of the sample vegetation corresponding to the any one of the original detection sample points on the ground is determined as the offset direction corresponding to the any one of the original detection sample points;

[0021] In the case that there are multiple sample vegetations corresponding to any of the original detection sample points, for each sample vegetation corresponding to any of the original detection sample points, obtain the angle between the horizontal line and the line connecting the ground growth point of each sample vegetation and the vertical projection point of the highest point of the canopy of each sample vegetation on the ground in the clockwise direction as the offset angle corresponding to each sample vegetation, and determine the offset angle corresponding to each sample vegetation corresponding to any of the original detection sample points as the offset angle corresponding to any of the original detection sample points, and then determine the offset direction corresponding to any of the original detection sample points based on the offset angle corresponding to any of the original detection sample points and the horizontal line, and the ground growth point of the sample vegetation is the intersection of the sample vegetation and the ground.

[0022] According to a remote sensing image shadow removal method provided by the present invention, after collecting the target data corresponding to each original detection sample point, the method further includes:

[0023] Based on the target data corresponding to each original detection sample point and the solar incidence angle at the target time, shadow removal is performed on the original remote sensing image;

[0024] The target time is determined based on the time when the original remote sensing image is collected; and the solar incident angle refers to the angle between the incident direction of sunlight and the vertical plane that is less than 90°.

[0025] According to a remote sensing image shadow removal method provided by the present invention, the shadow removal of the original remote sensing image is performed based on the target data corresponding to each original detection sample point and the solar incidence angle at the target time, including:

[0026] Determine, in the original remote sensing image, a vegetation shadow area corresponding to each original detection sample point based on the target data corresponding to each original detection sample point and the solar incidence angle at the target time;

[0027] Based on the vegetation shadow area corresponding to each original detection sample point, determine the vegetation shadow area in each detection sample area in the original remote sensing image, each detection sample area is determined based on each original detection sample point, and each detection sample area constitutes the original remote sensing image;

[0028] Shadow removal is performed on the vegetation shadow area in each detection sample area in the original remote sensing image.

[0029] The present invention also provides a remote sensing image shadow removal device, comprising the following modules:

[0030] A test sample point determination module is used to determine a plurality of original test sample points based on the distribution of vegetation in the original remote sensing image, and the remote sensing product to be tested is obtained based on the original remote sensing image;

[0031] The first data acquisition module is used to collect target data corresponding to each original detection sample point, and the target data corresponding to any original detection sample point includes the vertical distance between the highest point of the canopy of the sample vegetation corresponding to any original detection sample point and the ground, the canopy width of the sample vegetation corresponding to any original detection sample point, the angle less than 90° between the ground where any original detection sample point is located and the horizontal plane, and the bending angle of the sample vegetation corresponding to any original detection sample point, the bending angle of the sample vegetation is the angle between the central axis of the sample vegetation and the vertical plane that is not greater than 90°, and the angle between the ground where any original detection sample point is located and the horizontal plane is not 0°;

[0032] A test sample point correction module, used to correct the position of each original detection sample point based on the target data corresponding to each original detection sample point, so as to obtain the position of each target detection sample point;

[0033] A second data acquisition module is used to collect data at each target detection sample point based on the position of each target detection sample point, and obtain a ground measurement value corresponding to the remote sensing product to be inspected based on the collected data;

[0034] The authenticity verification module is used to perform an authenticity verification on the remote sensing product to be verified based on the ground measurement value, and obtain an authenticity verification result of the remote sensing product to be verified.

[0035] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, any of the remote sensing image shadow removal methods described above is implemented.

[0036] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the remote sensing image shadow removal method described in any one of the above methods is implemented.

[0037] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the remote sensing image shadow removal method described above is implemented.

[0038] The remote sensing image shadow removal method, device, electronic device and storage medium provided by the present invention determine multiple original detection sample points based on the distribution of vegetation in the original remote sensing image, collect target data corresponding to each original detection sample point, and then correct the position of each original detection sample point based on the target data corresponding to each original detection sample point. After obtaining the position of each target detection sample point, data is collected at each target detection sample point based on the position of each target detection sample point, and ground measurement values ​​corresponding to the remote sensing product to be tested are obtained based on the collected data. The authenticity of the remote sensing product to be tested is tested based on the ground measurement values ​​to obtain the authenticity test results of the remote sensing product to be tested. The target detection sample points can be determined more accurately on the basis of comprehensively considering the natural growth state of vegetation and the actual terrain and geomorphic characteristics, and the ground measurement values ​​corresponding to the remote sensing product to be tested can be obtained more accurately and objectively, which can provide more accurate data basis for the authenticity test of the remote sensing product to be tested, improve the accuracy of the authenticity test results of the remote sensing product to be tested, and provide more accurate data basis for the quality evaluation, analysis and control of remote sensing data. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 It is one of the comparison pictures between vegetation in an ideal growth state and vegetation in a natural growth state.

[0041] Figure 2 It is a flow chart of the remote sensing image shadow removal method provided by the present invention.

[0042] Figure 3 It is one of the schematic diagrams of sample vegetation in the remote sensing product authenticity verification method provided by the present invention.

[0043] Figure 4 It is one of the top view schematic diagrams of original detection sample points and target detection sample points in the remote sensing product authenticity inspection method provided by the present invention.

[0044] Figure 5 This is the second top view schematic diagram of the original detection sample points and the target detection sample points in the remote sensing product authenticity inspection method provided by the present invention.

[0045] Figure 6 This is the second comparison picture between vegetation in an ideal growth state and vegetation in a natural growth state.

[0046] Figure 7 This is the second schematic diagram of sample vegetation in the remote sensing product authenticity verification method provided by the present invention.

[0047] Figure 8 This is the third schematic diagram of sample vegetation in the remote sensing product authenticity verification method provided by the present invention.

[0048] Fig. 9 It is a structural schematic diagram of the vegetation remote sensing product authenticity inspection device provided by the present invention.

[0049] Fig.10 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] In the description of the invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0052] In the description of the present application, the terms "first", "second", etc. are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are usually a class, and the number of objects is not limited. For example, the first object can be one or more. In addition, in the description of the present application, "and / or" represents at least one of the connected objects, and the character " / " generally represents that the front and back associated objects are in an "or" relationship.

[0053] It should be noted that remote sensing images with different spatial resolutions, such as sub-meter, meter, decimeter, hundred-meter, kilometer, etc., are obtained using remote sensing sensors such as satellite remote sensing sensors and drone remote sensing sensors. Remote sensing products obtained based on remote sensing images with different spatial resolutions can provide effective methods and basic data support for resource and environmental monitoring and sustainable development.

[0054] The authenticity test of remote sensing products is an important way to evaluate the quality of remote sensing products. It can not only provide support for the preliminary principle research and design of satellite payloads, but also provide a basis for the quality evaluation, analysis and control of remote sensing data.

[0055] In the authenticity test of remote sensing products, the ground measurement value that can represent the characteristics of surface vegetation can be used as the relative truth value. The consistency between the remote sensing product to be tested and the relative truth value can be evaluated by an independent method and its uncertainty can be analyzed to obtain the authenticity test result of the remote sensing product to be tested. Therefore, as a key parameter for the authenticity test of remote sensing products, the accuracy of ground measurement values ​​is of great significance to improving the accuracy of the authenticity test of remote sensing products.

[0056] In the related technology, after determining the spatial structure of the vegetation community in the target area based on the remote sensing image of the target area corresponding to the remote sensing product to be tested, multiple sampling points can be determined in the remote sensing image of the target area based on the spatial structure of the vegetation community in the target area. For example, in areas with homogeneous and dense vegetation distribution, square sampling mode, cross sampling mode and diamond sampling mode should be adopted to determine multiple sampling points in the remote sensing image of the target area; in areas with sparse and discontinuous vegetation distribution, diagonal sampling mode should be adopted to determine multiple sampling points in the remote sensing image of the target area.

[0057] After determining multiple sampling points in the remote sensing image of the target area, the ground projection points corresponding to the above sampling points in the real world can be determined as inspection sample points in the target area, and then ground measurement values ​​can be obtained based on the image data collected at the above inspection sample points.

[0058] Normally, vegetation in an ideal growth state grows upright. However, in actual scenarios, vegetation in a natural growth state is subject to the effects of limited growth space, external forces, growth environment, light conditions, pests and diseases, cultivation management, and climate factors, either alone or in combination, which can easily lead to twisted and skewed growth states, making it difficult for most vegetation to maintain an ideal growth state. The bending of tree trunks will change the geometry of trees, causing the trunk parts that were originally perpendicular to the ground to become tilted or twisted. Therefore, for vegetation in a natural growth state, the roots and canopy of the above vegetation are usually not in the same vertical plane.

[0059] It should be noted that in the description of the present invention, vegetation refers to tree vegetation.

[0060] Figure 1 This is one of the comparison pictures between vegetation in an ideal growth state and vegetation in a natural growth state. Figure 1 As shown, for any point on a non-horizontal ground C , if the above ground point C Growing at a height of and vegetation in an ideal growth state AC , then vegetation AC The canopy apex A The vertical projection point on the horizontal ground is C point.

[0061] like Figure 1 As shown, if the above ground points C Growing at a height of , Vegetation in its natural state BC , then vegetation BC The canopy apex B The vertical projection point on the horizontal ground , and the above ground points C There is also a certain offset between them.

[0062] It should be noted that if Figure 1 As shown, vegetation BC The canopy apex B With perpendicular projection point The line between the ground points C The ground is vertical, the vegetation AC The canopy apex A With ground point C The line between the ground points C The ground is vertical.

[0063] Since the sampling perspective of remote sensing images is a bird's-eye view, the vegetation images in remote sensing images are usually images of vegetation canopies. The sampling points in the remote sensing images of the target area can be determined as the canopy vertices of a certain vegetation in the target area.

[0064] When the above-mentioned vegetation is in an ideal growth state, the vertical projection point corresponding to the canopy apex of the above-mentioned vegetation in the real world is indeed the ground point where the above-mentioned vegetation is located, and then the vertical projection point corresponding to the canopy apex of the above-mentioned vegetation in the real world can be determined as the inspection sample point in the target area.

[0065] However, when the above-mentioned vegetation is in a state of natural growth, there is a certain deviation between the vertical projection point corresponding to the canopy apex of the above-mentioned vegetation in the real world and the ground point where the above-mentioned vegetation is actually located. If the vertical projection point corresponding to the canopy apex of the above-mentioned vegetation in the real world is determined as the inspection sample point in the target area, the ground measurement value obtained based on the image data collected at the above-mentioned detection sample point is inaccurate, and it is difficult to accurately perform authenticity inspection on the remote sensing product to be inspected.

[0066] Therefore, the ground measurement values ​​obtained without considering the real growth state of vegetation, as well as conditions such as lighting conditions, climate environment, vegetation type, and topography, are often difficult to accurately and objectively reflect the vegetation characteristics of the inspection sample points, which leads to low accuracy of remote sensing product authenticity inspection. How to obtain more accurate and objective ground measurement values ​​based on comprehensive consideration of the natural growth state of vegetation, as well as lighting conditions, climate environment, vegetation type, and topography, and thus improve the accuracy of remote sensing product authenticity inspection, is a technical problem that needs to be solved in this field.

[0067] In this regard, the present invention provides a remote sensing product authenticity verification method. The remote sensing product authenticity verification method provided by the present invention mainly determines the sampling method according to the spatial structure of the vegetation community in the remote sensing image when performing spatial sampling of remote sensing products in the related technology. The vegetation inside the sample area has a natural growth state, which is somewhat different from the vertical growth state of theoretically simulated vegetation, resulting in a technical defect that the spatial observation point sampling of remote sensing products has a certain error. Spatial sampling is performed on the basis of considering the natural growth state of vegetation, and spatial observation point sampling for satellite sensor remote sensing products with different spatial resolutions is realized, thereby realizing a high-precision and representative spatial sampling method.

[0068] Combine the following Figure 2-Figure 7 The remote sensing product authenticity verification method of the present invention is described.

[0069] Figure 2 FIG. 1 is a flow chart of the remote sensing image shadow removal method provided by the present invention. Figure 2 As shown, the method includes the following steps: Step 201, based on the distribution of vegetation in the original remote sensing image, a plurality of original detection sample points are determined, and the remote sensing product to be tested is obtained based on the original remote sensing image.

[0070] It should be noted that the execution subject of the embodiment of the present invention is a remote sensing product authenticity verification device. The remote sensing product authenticity verification device can be configured in electronic devices such as smart phones, personal computers (PCs) or servers.

[0071] Specifically, the remote sensing product to be inspected is the inspection object of the remote sensing product authenticity inspection provided by the present invention. Based on the remote sensing product authenticity inspection method provided by the present invention, the remote sensing product to be inspected can be authenticity inspected to obtain the authenticity inspection result of the remote sensing product to be inspected.

[0072] It is understandable that the remote sensing product to be inspected in the embodiment of the present invention may be determined based on actual needs. The remote sensing product to be inspected in the embodiment of the present invention is not specifically limited.

[0073] It should be noted that the remote sensing product to be inspected in the embodiment of the present invention is obtained based on the original remote sensing image. The original remote sensing image in the embodiment of the present invention is a remote sensing image of the target area.

[0074] It is understandable that the remote sensing image of the target area is collected by a remote sensing sensor. The remote sensing sensor in the embodiment of the present invention may include but is not limited to a satellite remote sensing sensor and an unmanned aerial vehicle remote sensing sensor.

[0075] Based on the distribution of vegetation in the original remote sensing images, in areas where the vegetation distribution is homogeneous and dense in the original remote sensing images, square sampling mode, cross sampling mode and diamond sampling mode can be used to determine multiple sampling points in the original remote sensing images. In areas where the vegetation distribution is sparse and discontinuous in the original remote sensing images, diagonal sampling mode can be used to determine multiple sampling points in the original remote sensing images.

[0076] Specifically, after determining multiple sampling points in the original remote sensing image, the vertical projection point of each sampling point in the original remote sensing image in the real world can be determined as an original detection sample point in the target area based on the mapping relationship between the original remote sensing image and the real world.

[0077] Step 202: collect target data corresponding to each original detection sample point. The target data corresponding to any original detection sample point includes the vertical distance between the highest point of the canopy of the sample vegetation corresponding to any original detection sample point and the ground, the canopy width of the sample vegetation corresponding to any original detection sample point, the angle less than 90° between the ground where any original detection sample point is located and the horizontal plane, and the bending angle of the sample vegetation corresponding to any original detection sample point. The bending angle of the sample vegetation is the angle between the central axis of the sample vegetation and the vertical plane that is not greater than 90°, and the angle between the ground where any original detection sample point is located and the horizontal plane is not 0°.

[0078] like Figure 1 As shown, at the ground growth point C Vegetation in a natural growth state when the angle between the ground and the horizontal plane is not 0° BC Vertical height , refers to vegetation BC The canopy apex Vertical distance from the ground; vegetation BC Bending angle , refers to vegetation BC The angle between the central axis and the vertical plane is not greater than 90°; vegetation BC Ground growth point C , for vegetation BC The point of intersection with the ground.

[0079] At ground growth point C When the angle between the ground and the horizontal plane is not 0°, for vegetation in its natural growth state BC , the above vegetation BC The canopy apex B The vertical projection point on the ground Ground growth points with vegetation above C The distance between , and the above vegetation BC Vertical height And the above vegetation BC Bending angle With ground growth point C The angle between the ground and the horizontal plane is no greater than 90° The relationship between the difference is shown in Table 1.

[0080]

[0081] As can be seen from Table 1, the vertical height of vegetation BC under natural growth conditions The higher the distance The bigger, The larger the distance The bigger.

[0082] At ground growth point C When the angle between the ground and the horizontal plane is not 0°, for vegetation in its natural growth state BC , in the above vegetation BC Vertical height When the above vegetation is a fixed value BC The canopy apex B The vertical projection point on the ground Ground growth points with vegetation above C The distance between , and the above vegetation BC Crown Width And the above vegetation BC Bending angle With ground growth point C The angle between the ground and the horizontal plane is no greater than 90° The relationship between the difference is shown in Table 2.

[0083]

[0084] From Table 2, we can see that the vertical height of vegetation BC under natural growth state is Under certain circumstances, the crown width of the above vegetation BC The smaller the distance The bigger, the higher The larger the distance The bigger.

[0085] At ground growth point C When the angle between the ground and the horizontal plane is not 0°, the distance With vertical height and bending angle The relationship between can be expressed by the following formula:

[0086]

[0087] Therefore, at the ground growth point C When the angle between the ground and the horizontal plane is not 0°, in the embodiment of the present invention, the crown width, bending angle, vertical height of the vegetation and the angle between the ground and the horizontal plane not greater than 90° of the vegetation are determined as target data.

[0088] In the embodiment of the present invention, Identify the original detection points in the target area, , Indicates the total number of original detection points in the target area.

[0089] It should be noted that since the growth state of vegetation is regional, the growth space, external forces, growth environment, lighting conditions, pests and diseases, cultivation management and climatic factors of vegetation in the same area are similar.

[0090] Therefore, for the original detection points in the target area In the embodiment of the present invention, the distance from the original detection sample point can be The nearest one or more vegetation points are determined as the original detection points Corresponding sample vegetation .

[0091] Figure 3 This is one of the schematic diagrams of sample vegetation in the remote sensing product authenticity verification method provided by the present invention. Figure 3 As shown, at the original detection point When the angle between the ground and the horizontal plane is not 0°, various sensors can be used in the embodiment of the present invention to collect sample vegetation. The highest point of the canopy Vertical distance from the ground , sample vegetation Crown Width , sample vegetation Bending angle And the original test sample The angle between the ground and the horizontal plane , as the original detection sample point The corresponding target data.

[0092] For example, in the embodiment of the present invention, a ranging sensor can be used to collect sample vegetation. The vertical distance between the highest point of the canopy and the ground , using radar sensors to collect sample vegetation Crown Width , using angle sensors to collect sample vegetation Bending angle And the original test sample The angle between the ground and the horizontal plane .

[0093] Step 203: Based on the target data corresponding to each original detection sample point, the position of each original detection sample point is corrected to obtain the position of each target detection sample point.

[0094] Specifically, obtain the original detection sample points After the corresponding target data is obtained, the original detection sample points can be The corresponding target data is analyzed by numerical calculation, mathematical statistics and deep learning technology to obtain the original detection points. The position is corrected to obtain the target detection sample point location.

[0095] As an optional embodiment, based on the target data corresponding to each original detection sample point, the position of each original detection sample point is corrected to obtain the position of each target detection sample point, including: based on the target data corresponding to each original detection sample point, obtaining the offset corresponding to each original detection sample point.

[0096] Specifically, obtain the original detection sample points After the corresponding target data is obtained, the original detection sample points can be The corresponding target data is obtained through numerical calculation, mathematical statistics and deep learning technology to obtain the original detection sample points The corresponding offset .

[0097] As an optional embodiment, based on the target data corresponding to each original detection sample point, the offset corresponding to each original detection sample point is obtained, including: when the number of sample vegetation corresponding to any original detection sample point is one, based on the vertical distance between the highest point of the canopy of the sample vegetation corresponding to any original detection sample point and the ground, the bending angle of the sample vegetation corresponding to any original detection sample point, and the angle less than 90° between the ground where any original detection sample point is located and the horizontal plane, a first intermediate result corresponding to any original detection sample point is calculated; based on the canopy width of the sample vegetation corresponding to any original detection sample point, the bending angle of the sample vegetation corresponding to any original detection sample point, and the angle less than 90° between the ground where any original detection sample point is located and the horizontal plane, a second intermediate result corresponding to any original detection sample point is calculated; and then the difference between the first intermediate result and the second intermediate result corresponding to any original detection sample point is determined as the offset corresponding to any original detection sample point.

[0098] Specifically, at the original detection point The angle between the ground and the horizontal plane is not 0° and the original detection sample point Corresponding sample vegetation When the number is 1, the original detection sample point The corresponding first intermediate result It can be calculated by the following formula:

[0099]

[0100] Original test sample The corresponding second intermediate result It can be calculated by the following formula:

[0101]

[0102] Original test sample The corresponding offset It can be calculated by the following formula:

[0103]

[0104] When there are multiple sample vegetations corresponding to any original detection sample point, for each sample vegetation corresponding to any original detection sample point, based on the vertical distance between the highest point of the canopy of each sample vegetation and the ground, the bending angle of the sample vegetation corresponding to each sample vegetation, and the angle less than 90° between the ground where any original detection sample point is located and the horizontal plane, a first intermediate result corresponding to each sample vegetation is calculated; based on the canopy width of each sample vegetation, the bending angle of each sample vegetation, and the angle less than 90° between the ground where any original detection sample point is located and the horizontal plane, a second intermediate result corresponding to each sample vegetation is calculated; the difference between the first intermediate result and the second intermediate result corresponding to each sample vegetation is calculated as the offset corresponding to each sample vegetation; and the average value of the offsets corresponding to the sample vegetations corresponding to any original detection sample point is determined as the offset corresponding to any original detection sample point.

[0105] Specifically, at the original detection point The angle between the ground and the horizontal plane is not 0° and the original detection sample point Corresponding sample vegetation When the number is multiple, the embodiment of the present invention can be used Identify the original detection sample point Corresponding sample vegetation , , Indicates the total number of sample vegetation corresponding to the original detection sample points.

[0106] Accordingly, the sample vegetation .

[0107] For the original detection sample Corresponding sample vegetation , sample vegetation The corresponding first intermediate result It can be calculated by the following formula:

[0108]

[0109] in, Indicates sample vegetation The highest point of the canopy The vertical distance from the ground; Indicates sample vegetation The bending angle.

[0110] Sample vegetation The corresponding second intermediate result It can be calculated by the following formula:

[0111]

[0112] in, Indicates sample vegetation The crown width.

[0113] Sample vegetation The corresponding offset It can be calculated by the following formula:

[0114]

[0115] Calculate the original detection sample points The offset corresponding to each sample vegetation Afterwards, the original detection points can be calculated The average value of the offset corresponding to each sample vegetation is used as the original detection sample point The corresponding offset , the specific calculation formula is as follows:

[0116]

[0117] Any original detection sample point is moved along the offset direction corresponding to any original detection sample point by the offset amount corresponding to any original detection sample point, and the position of any original detection sample point after the move is determined as the position of the target detection sample point corresponding to any original detection sample point. The offset direction corresponding to any original detection sample point is determined based on the position of the vertical projection point of the highest point of the canopy of the sample vegetation corresponding to any original detection sample point on the ground.

[0118] Specifically, based on the original detection sample points Corresponding sample vegetation The highest point of the canopy Vertical projection point on the ground The location of the original detection sample point can be determined by numerical calculation The corresponding offset direction.

[0119] Determine the original detection sample point After the corresponding offset direction, the original detection sample point can be Along the original detection points Move the original detection sample point in the corresponding offset direction The corresponding offset , and then the original detection sample points after movement can be The location is determined as the original detection sample point Corresponding target original detection sample points The location.

[0120] As an optional embodiment, before moving any original detection sample point along the offset direction corresponding to any original detection sample point and by the offset amount corresponding to any original detection sample point, the method also includes: when the number of sample vegetation corresponding to any original detection sample point is one, pointing any original detection sample point to the direction of the vertical projection point of the highest point of the canopy of the sample vegetation corresponding to any original detection sample point on the ground, and determining it as the offset direction corresponding to any original detection sample point.

[0121] Figure 4 This is one of the top view schematic diagrams of the original detection sample points and the target detection sample points in the remote sensing product authenticity inspection method provided by the present invention. Corresponding sample vegetation When the number is 1, the original detection sample point The corresponding offset direction is Figure 4 shown.

[0122] When there are multiple sample vegetations corresponding to any original detection sample point, for each sample vegetation corresponding to any original detection sample point, obtain the angle between the line connecting the ground growth point of each sample vegetation and the vertical projection point of the highest point of the canopy of each sample vegetation on the ground and the horizontal line in the clockwise direction as the offset angle corresponding to each sample vegetation, and determine the offset angle corresponding to each sample vegetation corresponding to any original detection sample point as the offset angle corresponding to any original detection sample point, and then determine the offset direction corresponding to any original detection sample point based on the offset angle corresponding to any original detection sample point and the horizontal line, and the ground growth point of the sample vegetation is the intersection of the sample vegetation and the ground.

[0123] Specifically, at the original detection point Corresponding sample vegetation If there are multiple , you can use Indicates sample vegetation The highest point of the canopy, Indicates sample vegetation The highest point of the canopy At the vertical projection point on the ground, use Indicates sample vegetation Ground growth point, with Indicates sample vegetation The corresponding offset angle is Represents the original detection sample point The corresponding offset angle.

[0124] Original test sample The corresponding offset angle It can be calculated by the following formula:

[0125]

[0126] Get the original detection sample point The corresponding offset angle After that, the angle between the horizontal line and the clockwise direction can be direction, determined as the original detection sample point The corresponding offset direction.

[0127] Figure 5 This is the second top view schematic diagram of the original detection sample point and the target detection sample point in the remote sensing product authenticity inspection method provided by the present invention. Corresponding sample vegetation When the number is multiple, the original detection sample points The corresponding offset direction is Figure 5 shown.

[0128] The embodiment of the present invention determines multiple original detection sample points based on the distribution of vegetation in the original remote sensing image, and then corrects the position of any original detection sample point based on the target data corresponding to any original detection sample point to obtain the position of each target detection sample point. The target detection sample points can be determined more accurately based on the actual growth status of the vegetation and the terrain and geomorphic characteristics, and the ground measurement values ​​corresponding to the remote sensing product to be tested can be more accurately obtained, which can provide more accurate data basis for the authenticity inspection of the remote sensing product to be tested.

[0129] Step 204: Based on the position of each target detection sample point, data is collected at each target detection sample point, and based on the collected data, a ground measurement value corresponding to the remote sensing product to be tested is obtained.

[0130] Specifically, after the position of each target detection sample point is determined, the image sensor may be sequentially disposed at each target detection sample point, and then the image data of each target detection sample point may be acquired by using the image sensor.

[0131] After obtaining the image data of each target detection sample point, the ground measurement value corresponding to the remote sensing product to be tested can be obtained through numerical calculation, model processing, etc. based on the image data of each target detection sample point.

[0132] It can be understood that, in the remote sensing product to be verified, the data types included in the ground measurement values ​​corresponding to the remote sensing product to be verified are the same.

[0133] Step 205: Perform an authenticity check on the remote sensing product to be checked based on the ground measurement value to obtain an authenticity check result of the remote sensing product to be checked.

[0134] Specifically, after obtaining the ground measurement values ​​corresponding to the remote sensing product to be tested, the authenticity of the remote sensing product to be tested can be tested based on the above ground measurement values, and the degree of consistency between the remote sensing product to be tested and the above ground measurement values ​​can be evaluated through independent methods. The uncertainty between the remote sensing product to be tested and the above ground measurement values ​​can also be analyzed, thereby obtaining the authenticity test result of the remote sensing product to be tested.

[0135] The embodiment of the present invention determines multiple original detection sample points based on the distribution of vegetation in the original remote sensing image, collects target data corresponding to each original detection sample point, and then corrects the position of each original detection sample point based on the target data corresponding to each original detection sample point. After obtaining the position of each target detection sample point, data is collected at each target detection sample point based on the position of each target detection sample point, and ground measurement values ​​corresponding to the remote sensing product to be tested are obtained based on the collected data. The authenticity of the remote sensing product to be tested is tested based on the ground measurement values ​​to obtain the authenticity test results of the remote sensing product to be tested. The target detection sample points can be determined more accurately on the basis of comprehensively considering the natural growth state of vegetation and the actual terrain and geomorphic characteristics, and the ground measurement values ​​corresponding to the remote sensing product to be tested can be obtained more accurately and objectively, which can provide more accurate data basis for the authenticity test of the remote sensing product to be tested, improve the accuracy of the authenticity test results of the remote sensing product to be tested, and provide more accurate data basis for quality evaluation, analysis and control of remote sensing data.

[0136] As an optional embodiment, after collecting the target data corresponding to each original detection sample point, the method further includes: removing shadows from the original remote sensing image based on the target data corresponding to each original detection sample point and the sun incidence angle at the target time.

[0137] Among them, the target time is determined based on the time when the original remote sensing image is collected; the solar incidence angle refers to the angle between the incident direction of sunlight and the vertical plane that is less than 90°.

[0138] Remote sensing sensors usually collect remote sensing images during the day and on sunny days, but vegetation will produce a shadow effect on sunny days, that is, the curved trunks of the vegetation may block the leaves or the ground below, causing these areas to appear as vegetation shadow areas on the remote sensing images.

[0139] It should be noted that, since the shadow of the trunk of the vegetation is relatively small and can be ignored for remote sensing images, the shadow of the vegetation in the embodiment of the present invention refers to the shadow of the vegetation canopy.

[0140] For remote sensing images, vegetation shadow areas may cause distortion of remote sensing images due to factors such as projection angle, which in turn may cause errors and affect the accuracy of remote sensing image interpretation. Vegetation shadow areas will also reduce the contrast and clarity of remote sensing images, making it difficult to accurately identify ground object information and may even lead to misjudgment. In the fields of environmental monitoring, urban planning, disaster warning, etc., the presence of vegetation shadow areas will interfere with the effective extraction and analysis of image information of remote sensing images, thereby reducing the accuracy of remote sensing image analysis.

[0141] Therefore, the spectral reflectance characteristics of vegetation shadow areas are significantly different from those of normal lighting areas, which will increase the complexity and uncertainty of remote sensing image post-processing.

[0142] When removing vegetation shadow areas from remote sensing images in related technologies, the natural growth state of vegetation is usually not taken into consideration. Instead, the position of the shadow area in the remote sensing image is determined based on the ideal growth state of vegetation.

[0143] Figure 6 This is the second comparison between vegetation in an ideal growth state and vegetation in a natural growth state. Figure 6 As shown, at the above ground point C When the angle between the ground and the horizontal plane is 0°, for any point on the horizontal ground C , if the above ground point C Growing at a height of h and vegetation in an ideal growth state AC , then the solar altitude angle is m In the case of vegetation AC The vegetation shadow area formed on the horizontal ground is Figure 1 The light gray area in the C Growing at a height of h and vegetation in an ideal growth state BC , then the solar altitude angle is m In the case of vegetation BC The vegetation shadow area formed on the horizontal ground is Figure 6 The dark grey area in the .

[0144] like Figure 6 As shown, at the above ground point C When the angle between the ground and the horizontal plane is not 0°, the sun altitude angle and the vegetation height are the same, the vegetation AC and vegetation BC The locations of vegetation shadow areas formed on horizontal ground are not uniform.

[0145] Therefore, without considering the natural growth state of vegetation, it is difficult to accurately determine the vegetation shadow area in the remote sensing image, and further difficult to accurately remove the shadow of the remote sensing image.

[0146] like Figure 6 As shown, vegetation BC Ground growth point C Vegetation in its natural growth state when the angle between the ground and the horizontal plane is 0° BC Vertical height , refers to vegetation BC The canopy apex Vertical distance from the ground; vegetation BC Bending angle , refers to vegetation BC The angle between the central axis and the vertical plane is not greater than 90°; vegetation BC Ground growth point C , for vegetation BC Intersection point with the ground; sun incidence angle at target time It is the angle between the incident direction of sunlight and the vertical plane.

[0147] It should be noted that in the embodiment of the present invention, the target time and the time of collecting the target remote sensing image are in the same time period in the same period. For example, if the time of collecting the target remote sensing image is 10:30 am on March 1, the target time can be any time between 10 am and 11 am on any day from March 2 to April 1. The duration of the above period and the duration of the above time period can be determined based on prior knowledge and / or actual conditions. In the embodiment of the present invention, the duration of the above period and the duration of the above time period are not specifically limited.

[0148] In vegetation BC Ground growth point C When the angle between the ground and the horizontal plane is not 0°, for vegetation in its natural growth state BC , in the above vegetation BC Vertical height and the above vegetation BC Crown Width Fixed case, the above vegetation BC The length of the vegetation shadow area , and the above vegetation BC Bending angle and the solar incidence angle With ground growth point C The angle between the ground and the horizontal plane is no greater than 90° The relationship between the difference values ​​is shown in Table 3.

[0149]

[0150] From Table 3, we can see that in vegetation BC Ground growth point C When the angle between the ground and the horizontal plane is not 0°, for vegetation in its natural growth state BC , the above vegetation BC Bending angle and the solar incidence angle With ground growth point C The angle between the ground and the horizontal plane is no greater than 90° The greater the difference, the BC The length of the vegetation shadow area The larger the vegetation BC Bending angle Within a certain angle range, the larger the vegetation BC The length of the vegetation shadow area The larger the vegetation, the BC Bending angle Beyond the above angle range, the above vegetation BC Bending angle The larger the vegetation BC The length of the vegetation shadow area The smaller.

[0151] In vegetation BC Ground growth point C When the angle between the ground and the horizontal plane is not 0°, for vegetation in its natural growth state BC and vegetation in ideal growth conditions AC If the above vegetation BC Height and the above vegetation AC Height The same, then the above vegetation BC Vegetation shadow area and the above vegetation AC The vegetation shadow deviation distance between the vegetation shadow areas , and the above vegetation BC Bending angle and the solar incidence angle With ground growth point C The angle between the ground and the horizontal plane is no greater than 90° The relationship between the difference is shown in Table 4.

[0152]

[0153] From Table 4, we can see that in vegetation BC Ground growth pointC When the angle between the ground and the horizontal plane is 0°, for vegetation in its natural growth state BC and vegetation in ideal growth conditions AC , solar incident angle With ground growth point C The angle between the ground and the horizontal plane is no greater than 90° The greater the difference, the BC Vegetation shadow area and the above vegetation AC The vegetation shadow deviation distance between the vegetation shadow areas The larger the vegetation BC Bending angle The larger the vegetation BC Vegetation shadow area and the above vegetation AC The vegetation shadow deviation distance between the vegetation shadow areas The bigger.

[0154] Therefore, at the ground growth point C When the angle between the ground and the horizontal plane is not 0°, in the embodiment of the present invention, the crown width, bending angle, vertical height and ground growth point of the vegetation are adjusted. C The angle between the ground and the horizontal plane is no greater than 90° The solar incidence angle at the target time is determined as the target data.

[0155] Figure 7 This is the second schematic diagram of the sample vegetation in the remote sensing product authenticity inspection method provided by the present invention, such as Figure 7 As shown, for the original detection sample point , at the original detection point When the angle between the ground and the horizontal plane is not 0°, various sensors can be used in the embodiment of the present invention to collect sample vegetation. The highest point of the canopy Vertical distance from the ground , sample vegetation Crown Width , sample vegetation Bending angle , the solar incident angle at the target time And the original test sample The angle between the ground and the horizontal is no more than 90° .

[0156] In the embodiment of the present invention, the sample vegetation can be used to The highest point of the canopy Vertical distance from the ground , sample vegetation Crown Width , sample vegetation Bending angle and the solar incidence angle at the target time , through numerical calculation, mathematical statistics, conditional judgment and deep learning technology, the sampling points are determined in the original remote sensing image The corresponding vegetation shadow area. Among them, the original detection sample point It is based on the sampling points in the original remote sensing image. Sure.

[0157] As an optional embodiment, shadow removal is performed on the original remote sensing image based on the target data corresponding to each original detection sample point and the solar incidence angle at the target time, including: determining the vegetation shadow area corresponding to each original detection sample point in the original remote sensing image based on the target data corresponding to each original detection sample point and the solar incidence angle at the target time.

[0158] Specifically, the sample vegetation The length of the vegetation shadow area It can be calculated by the following formula:

[0159]

[0160] Sample vegetation The width of the vegetation shadow area = .

[0161] Based on the time when the original remote sensing image was collected, the solar altitude angle at the time of collecting the original remote sensing image can be determined. Based on the solar altitude angle at the time of collecting the original remote sensing image, the sampling point can be determined. The corresponding vegetation shadow extension direction.

[0162] Calculate the sample vegetation The length of the vegetation shadow area and width Afterwards, the original remote sensing image resolution and sample vegetation The length of the vegetation shadow area and width , get the sampling point The length of the corresponding vegetation shadow area and width , and then the long axis can be used as the sampling point The length of the corresponding vegetation shadow area , the minor axis is the sampling point The width of the corresponding vegetation shadow area , the major axis is located at the sampling point The elliptical area corresponding to the extension direction of the vegetation shadow is determined as the sampling point The corresponding vegetation shadow area.

[0163] It should be noted that the sampling point The corresponding vegetation shadow area is closer to the sampling point The major axis vertex and sampling point The distance between them is based on the sample vegetation The highest point of the canopy Vertical distance from the ground Determined. Sample vegetation The highest point of the canopy Vertical distance from the ground The larger the value, the larger the sampling point. The corresponding vegetation shadow area is closer to the sampling point The major axis vertex and sampling point The greater the distance between them.

[0164] Based on the vegetation shadow area corresponding to each original detection sample point, the vegetation shadow area in each detection sample area in the original remote sensing image is determined. Each detection sample area is determined based on each original detection sample point, and each detection sample area constitutes the original remote sensing image.

[0165] It should be noted that since the original detection sample points in the embodiment of the present invention are determined based on the distribution of vegetation in the original remote sensing image, the embodiment of the present invention can divide the original remote sensing image based on the distribution of each sampling point in the original remote sensing image, and obtain the detection sample area corresponding to each sampling point, and then obtain the detection sample area corresponding to each original detection sample point.

[0166] For the original detection sample Corresponding detection sample area, in the embodiment of the present invention, an edge detection algorithm (such as Canny edge detector) can be used to obtain the original detection sample point The corresponding vegetation area in the detection sample area.

[0167] Get the original detection sample point After the vegetation area in the corresponding detection sample area, a plurality of grid points may be evenly set in the vegetation area, and the density of the grid points is determined based on the resolution of the original remote sensing image.

[0168] For the original detection sample Each grid point in the vegetation area of ​​the corresponding detection sample area can be represented by the long axis as the sampling point The length of the corresponding vegetation shadow area , the minor axis is the sampling point The width of the corresponding vegetation shadow area , the elliptical area whose major axis is located in the extension direction of the vegetation shadow corresponding to the above grid point is determined as the vegetation shadow area corresponding to the above grid point.

[0169] It should be noted that in the vegetation shadow area corresponding to the above grid point, the distance between the long axis vertex closer to the above grid point and the above grid point is The corresponding vegetation shadow area is closer to the sampling point The major axis vertex and sampling point The distance between them is the same.

[0170] Determine the original detection sample point After the vegetation shadow area corresponding to each grid point in the vegetation area in the corresponding detection sample area is determined, the vegetation shadow area corresponding to each grid point can be determined as the original detection sample point The corresponding vegetation shadow area within the detection sample area.

[0171] The shadow of vegetation shadow area in each detection sample area in the original remote sensing image is removed.

[0172] Specifically, after determining the vegetation shadow area in each detection sample area in the original remote sensing image, the shadow of the vegetation shadow area in each detection sample area in the original remote sensing image can be removed by image processing.

[0173] The embodiment of the present invention determines the vegetation shadow area corresponding to each original detection sample point in the original remote sensing image based on the target data corresponding to each original detection sample point and the solar incidence angle at the target time, and then determines the vegetation shadow area in each detection sample area in the original remote sensing image based on the vegetation shadow area corresponding to each original detection sample point, and then removes the shadow of the vegetation shadow area in each detection sample area in the original remote sensing image. The vegetation shadow area in the remote sensing image can be determined more accurately, and the shadow of the remote sensing image can be removed more accurately, which can better improve the image quality and analysis effect of the remote sensing image.

[0174] Figure 8 This is the third schematic diagram of the sample vegetation in the remote sensing product authenticity inspection method provided by the present invention, such as Figure 8As shown, when the angle between the ground where any original detection sample point is located and the horizontal plane is 0°, based on the target data corresponding to each original detection sample point, the offset corresponding to each original detection sample point is obtained, including: when the number of sample vegetation corresponding to any original detection sample point is one, based on the vertical distance between the highest point of the canopy of the sample vegetation corresponding to any original detection sample point and the ground and the bending angle of the sample vegetation corresponding to any original detection sample point, a first intermediate result corresponding to any original detection sample point is calculated, based on the canopy width of the sample vegetation corresponding to any original detection sample point and the bending angle of the sample vegetation corresponding to any original detection sample point, a second intermediate result corresponding to any original detection sample point is calculated, and then the difference between the first intermediate result and the second intermediate result corresponding to any original detection sample point is determined as the offset corresponding to any original detection sample point.

[0175] Specifically, at the original detection point The angle between the ground and the horizontal plane is 0° and the original detection sample point Corresponding sample vegetation When the number is 1, the original detection sample point The corresponding first intermediate result It can be calculated by the following formula:

[0176]

[0177] Original test sample The corresponding second intermediate result It can be calculated by the following formula:

[0178]

[0179] Original test sample The corresponding offset It can be calculated by the following formula:

[0180]

[0181] When the angle between the ground where any original detection sample point is located and the horizontal plane is 0° and the number of sample vegetation corresponding to any original detection sample point is multiple, for each sample vegetation corresponding to any original detection sample point, based on the vertical distance between the highest point of the canopy of each sample vegetation and the ground and the bending angle of the sample vegetation corresponding to each sample vegetation, the first intermediate result corresponding to each sample vegetation is calculated, based on the canopy width of each sample vegetation and the bending angle of each sample vegetation, the second intermediate result corresponding to each sample vegetation is calculated, and the difference between the first intermediate result and the second intermediate result corresponding to each sample vegetation is calculated as the offset corresponding to each sample vegetation, and the average value of the offsets corresponding to the sample vegetation corresponding to any original detection sample point is determined as the offset corresponding to any original detection sample point.

[0182] Specifically, at the original detection point The angle between the ground and the horizontal plane is 0° and the original detection sample point Corresponding sample vegetation When the number is multiple, the embodiment of the present invention can be used Identify the original detection sample point Corresponding sample vegetation , , Indicates the total number of sample vegetation corresponding to the original detection sample points.

[0183] Accordingly, the sample vegetation .

[0184] For the original detection sample Corresponding sample vegetation , sample vegetation The corresponding first intermediate result It can be calculated by the following formula:

[0185]

[0186] in, Indicates sample vegetation The highest point of the canopy The vertical distance from the ground; Indicates sample vegetation The bending angle.

[0187] Sample vegetation The corresponding second intermediate result It can be calculated by the following formula:

[0188]

[0189] in, Indicates sample vegetation The crown width.

[0190] Sample vegetation The corresponding offset It can be calculated by the following formula:

[0191]

[0192] Calculate the original detection sample points The offset corresponding to each sample vegetation Afterwards, the original detection points can be calculated The average value of the offset corresponding to each sample vegetation is used as the original detection sample point The corresponding offset , the specific calculation formula is as follows:

[0193]

[0194] Fig. 9 This is a schematic diagram of the structure of the vegetation remote sensing product authenticity inspection device provided by the present invention. Fig. 9 The authenticity verification device for vegetation remote sensing products provided by the present invention is described. The authenticity verification device for vegetation remote sensing products described below and the authenticity verification method for vegetation remote sensing products provided by the present invention described above can be referred to each other. Fig. 9 As shown, the device includes: a test sample point determination module 901, a first data acquisition module 902, a test sample point correction module 903, a second data acquisition module 904 and an authenticity verification module 905.

[0195] The inspection sample point determination module 901 is used to determine a plurality of original inspection sample points based on the distribution of vegetation in the original remote sensing image, and the remote sensing product to be inspected is obtained based on the original remote sensing image.

[0196] The first data acquisition module 902 is used to collect target data corresponding to each original detection sample point. The target data corresponding to any original detection sample point includes the vertical distance between the highest point of the canopy of the sample vegetation corresponding to any original detection sample point and the ground, the canopy width of the sample vegetation corresponding to any original detection sample point, the angle less than 90° between the ground where any original detection sample point is located and the horizontal plane, and the bending angle of the sample vegetation corresponding to any original detection sample point. The bending angle of the sample vegetation is the angle between the central axis of the sample vegetation and the vertical plane that is not greater than 90°, and the angle between the ground where any original detection sample point is located and the horizontal plane is not 0°.

[0197] The inspection sample point correction module 903 is used to correct the position of each original detection sample point based on the target data corresponding to each original detection sample point to obtain the position of each target detection sample point.

[0198] The second data acquisition module 904 is used to collect data at each target detection sample point based on the position of each target detection sample point, and obtain the ground measurement value corresponding to the remote sensing product to be tested based on the collected data.

[0199] The authenticity verification module 905 is used to perform authenticity verification on the remote sensing product to be verified based on the ground measurement value, and obtain the authenticity verification result of the remote sensing product to be verified.

[0200] Specifically, the inspection sample point determination module 901, the first data acquisition module 902, the inspection sample point correction module 903, the second data acquisition module 904 and the authenticity inspection module 905 are electrically connected.

[0201] The remote sensing product authenticity verification device in the embodiment of the present invention determines multiple original detection sample points based on the distribution of vegetation in the original remote sensing image, collects target data corresponding to each original detection sample point, and then corrects the position of each original detection sample point based on the target data corresponding to each original detection sample point. After obtaining the position of each target detection sample point, data is collected at each target detection sample point based on the position of each target detection sample point, and the ground measurement value corresponding to the remote sensing product to be tested is obtained based on the collected data. The authenticity of the remote sensing product to be tested is verified based on the ground measurement value to obtain the authenticity verification result of the remote sensing product to be tested. The target detection sample points can be determined more accurately on the basis of comprehensively considering the natural growth state of vegetation and the actual terrain and geomorphic characteristics, and the ground measurement value corresponding to the remote sensing product to be tested can be obtained more accurately and objectively, which can provide a more accurate data basis for the authenticity verification of the remote sensing product to be tested, improve the accuracy of the authenticity verification result of the remote sensing product to be tested, and provide a more accurate data basis for the quality evaluation, analysis and control of remote sensing data.

[0202] Fig.10 An example of a physical structure diagram of an electronic device is shown in FIG. Fig.10As shown, the electronic device may include: a processor 1010, a communication interface 1020, a memory 1030 and a communication bus 1040, wherein the processor 1010, the communication interface 1020 and the memory 1030 communicate with each other through the communication bus 1040. The processor 1010 may call the logic instructions in the memory 1030 to execute the remote sensing product authenticity verification method, the method comprising: determining a plurality of original detection sample points based on the distribution of vegetation in the original remote sensing image, the remote sensing product to be verified is obtained based on the original remote sensing image; collecting the target data corresponding to each original detection sample point, the target data corresponding to any original detection sample point includes the vertical distance between the highest point of the canopy of the sample vegetation corresponding to any original detection sample point and the ground, the canopy width of the sample vegetation corresponding to any original detection sample point, the angle between the ground where any original detection sample point is located and the horizontal plane less than 100°, and the target data corresponding to any original detection sample point. The bending angle of the sample vegetation is the angle between the central axis of the sample vegetation and the vertical plane that is no more than 100°, and the angle between the ground where any original detection sample point is located and the horizontal plane is not 0°; based on the target data corresponding to each original detection sample point, the position of each original detection sample point is corrected to obtain the position of each target detection sample point; based on the position of each target detection sample point, data is collected at each target detection sample point, and based on the collected data, the ground measurement value corresponding to the remote sensing product to be tested is obtained; based on the ground measurement value, the authenticity of the remote sensing product to be tested is tested, and the authenticity test result of the remote sensing product to be tested is obtained.

[0203] In addition, the logic instructions in the above-mentioned memory 1030 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0204] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the remote sensing product authenticity verification method provided by the above methods. The method includes: based on the distribution of vegetation in the original remote sensing image, determining multiple original detection sample points, and the remote sensing product to be tested is obtained based on the original remote sensing image; collecting target data corresponding to each original detection sample point, and the target data corresponding to any original detection sample point includes the vertical distance between the highest point of the canopy of the sample vegetation corresponding to any original detection sample point and the ground, the canopy width of the sample vegetation corresponding to any original detection sample point, and any original detection sample point. The angle between the ground where the point is located and the horizontal plane is less than 90°, and the bending angle of the sample vegetation corresponding to any original detection sample point, the bending angle of the sample vegetation is the angle between the central axis of the sample vegetation and the vertical plane that is not greater than 90°, and the angle between the ground where any original detection sample point is located and the horizontal plane is not 0°; based on the target data corresponding to each original detection sample point, the position of each original detection sample point is corrected to obtain the position of each target detection sample point; based on the position of each target detection sample point, data is collected at each target detection sample point, and based on the collected data, the ground measurement value corresponding to the remote sensing product to be tested is obtained; based on the ground measurement value, the authenticity of the remote sensing product to be tested is tested, and the authenticity test result of the remote sensing product to be tested is obtained.

[0205] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the remote sensing product authenticity inspection method provided by the above methods, the method comprising: determining a plurality of original detection sample points based on the distribution of vegetation in the original remote sensing image, and obtaining the remote sensing product to be inspected based on the original remote sensing image; collecting target data corresponding to each original detection sample point, the target data corresponding to any original detection sample point including the vertical distance between the highest point of the canopy of the sample vegetation corresponding to any original detection sample point and the ground, the canopy width of the sample vegetation corresponding to any original detection sample point, and the distance between the ground where any original detection sample point is located and the horizontal plane less than 90 degrees. ° and the bending angle of the sample vegetation corresponding to any original detection sample point, the bending angle of the sample vegetation is the angle between the central axis of the sample vegetation and the vertical plane that is not greater than 90°, and the angle between the ground where any original detection sample point is located and the horizontal plane is not 0°; based on the target data corresponding to each original detection sample point, the position of each original detection sample point is corrected to obtain the position of each target detection sample point; based on the position of each target detection sample point, data is collected at each target detection sample point, and based on the collected data, the ground measurement value corresponding to the remote sensing product to be tested is obtained; based on the ground measurement value, the authenticity of the remote sensing product to be tested is tested, and the authenticity test result of the remote sensing product to be tested is obtained.

[0206] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0207] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0208] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A remote sensing product authenticity verification method, characterized in that: include: Based on the distribution of vegetation in the original remote sensing image, a plurality of original detection sample points are determined, and the remote sensing product to be tested is obtained based on the original remote sensing image; Collect target data corresponding to each original detection sample point, the target data corresponding to any original detection sample point includes the vertical distance between the highest point of the canopy of the sample vegetation corresponding to any original detection sample point and the ground, the canopy width of the sample vegetation corresponding to any original detection sample point, the angle less than 90° between the ground where any original detection sample point is located and the horizontal plane, and the bending angle of the sample vegetation corresponding to any original detection sample point, the bending angle of the sample vegetation is the angle between the central axis of the sample vegetation and the vertical plane that is not greater than 90°, and the angle between the ground where any original detection sample point is located and the horizontal plane is not 0°; Based on the target data corresponding to each original detection sample point, the position of each original detection sample point is corrected to obtain the position of each target detection sample point; Based on the position of each target detection sample point, data is collected at each target detection sample point, and based on the collected data, a ground measurement value corresponding to the remote sensing product to be inspected is obtained; An authenticity check is performed on the remote sensing product to be checked based on the ground measurement value to obtain an authenticity check result of the remote sensing product to be checked.

2. The remote sensing product authenticity verification method according to claim 1, characterized in that: The step of correcting the position of each original detection sample point based on the target data corresponding to each original detection sample point to obtain the position of each target detection sample point includes: Based on the target data corresponding to each original detection sample point, obtaining the offset corresponding to each original detection sample point; Move any of the original detection sample points along the offset direction corresponding to the any of the original detection sample points by the offset amount corresponding to the any of the original detection sample points, and determine the position of the any of the original detection sample points after the move as the position of the target detection sample point corresponding to the any of the original detection sample points, and the offset direction corresponding to the any of the original detection sample points is determined based on the position of the vertical projection point of the highest point of the canopy of the sample vegetation corresponding to the any of the original detection sample points on the ground.

3. The remote sensing product authenticity verification method according to claim 2, characterized in that: The acquiring, based on the target data corresponding to each original detection sample point, an offset corresponding to each original detection sample point, comprises: Based on the target data corresponding to any one of the original detection sample points, obtaining the offset corresponding to any one of the original detection sample points includes: In the case that the number of sample vegetation corresponding to any original detection sample point is one, a first intermediate result corresponding to any original detection sample point is calculated based on the vertical distance between the highest point of the canopy of the sample vegetation corresponding to any original detection sample point and the ground, the bending angle of the sample vegetation corresponding to any original detection sample point, and the angle less than 90° between the ground where the any original detection sample point is located and the horizontal plane, and a second intermediate result corresponding to any original detection sample point is calculated based on the canopy width of the sample vegetation corresponding to any original detection sample point, the bending angle of the sample vegetation corresponding to any original detection sample point, and the angle less than 90° between the ground where the any original detection sample point is located and the horizontal plane, and then the difference between the first intermediate result and the second intermediate result corresponding to any original detection sample point is determined as the offset corresponding to the any original detection sample point; In the case that there are multiple sample vegetations corresponding to any of the original detection sample points, for each sample vegetation corresponding to any of the original detection sample points, based on the vertical distance between the highest point of the canopy of each sample vegetation and the ground, the bending angle of the sample vegetation corresponding to each sample vegetation, and the angle less than 90° between the ground where the any of the original detection sample points is located and the horizontal plane, a first intermediate result corresponding to each sample vegetation is calculated; based on the canopy width of each sample vegetation, the bending angle of each sample vegetation, and the angle less than 90° between the ground where the any of the original detection sample points is located and the horizontal plane, a second intermediate result corresponding to each sample vegetation is calculated; the difference between the first intermediate result and the second intermediate result corresponding to each sample vegetation is calculated as the offset corresponding to each sample vegetation; and the average value of the offsets corresponding to the sample vegetations corresponding to any of the original detection sample points is determined as the offset corresponding to the any of the original detection sample points.

4. The remote sensing product authenticity verification method according to claim 2, characterized in that: Before moving any of the original detection sample points along the offset direction corresponding to the any of the original detection sample points by the offset amount corresponding to the any of the original detection sample points, the method further includes: In the case that the number of sample vegetation corresponding to any one of the original detection sample points is one, the direction of the vertical projection point of the highest point of the canopy of the sample vegetation corresponding to the any one of the original detection sample points on the ground is determined as the offset direction corresponding to the any one of the original detection sample points; In the case that there are multiple sample vegetations corresponding to any of the original detection sample points, for each sample vegetation corresponding to any of the original detection sample points, obtain the angle between the horizontal line and the line connecting the ground growth point of each sample vegetation and the vertical projection point of the highest point of the canopy of each sample vegetation on the ground in the clockwise direction as the offset angle corresponding to each sample vegetation, and determine the offset angle corresponding to each sample vegetation corresponding to any of the original detection sample points as the offset angle corresponding to any of the original detection sample points, and then determine the offset direction corresponding to any of the original detection sample points based on the offset angle corresponding to any of the original detection sample points and the horizontal line, and the ground growth point of the sample vegetation is the intersection of the sample vegetation and the ground.

5. The remote sensing product authenticity verification method according to claim 1, characterized in that: After collecting the target data corresponding to each original detection sample point, the method further includes: Based on the target data corresponding to each original detection sample point and the solar incidence angle at the target time, shadow removal is performed on the original remote sensing image; The target time is determined based on the time when the original remote sensing image is collected; and the solar incident angle refers to the angle between the incident direction of sunlight and the vertical plane that is less than 90°.

6. The remote sensing product authenticity verification method according to claim 5, characterized in that: The shadow removal of the original remote sensing image based on the target data corresponding to each original detection sample point and the solar incidence angle at the target time includes: Determine, in the original remote sensing image, a vegetation shadow area corresponding to each original detection sample point based on the target data corresponding to each original detection sample point and the solar incidence angle at the target time; Based on the vegetation shadow area corresponding to each original detection sample point, determine the vegetation shadow area in each detection sample area in the original remote sensing image, each detection sample area is determined based on each original detection sample point, and each detection sample area constitutes the original remote sensing image; Shadow removal is performed on the vegetation shadow area in each detection sample area in the original remote sensing image.

7. A remote sensing product authenticity inspection device, characterized in that: include: A test sample point determination module is used to determine a plurality of original test sample points based on the distribution of vegetation in the original remote sensing image, and the remote sensing product to be tested is obtained based on the original remote sensing image; The first data acquisition module is used to collect target data corresponding to each original detection sample point, and the target data corresponding to any original detection sample point includes the vertical distance between the highest point of the canopy of the sample vegetation corresponding to any original detection sample point and the ground, the canopy width of the sample vegetation corresponding to any original detection sample point, the angle less than 90° between the ground where any original detection sample point is located and the horizontal plane, and the bending angle of the sample vegetation corresponding to any original detection sample point, the bending angle of the sample vegetation is the angle between the central axis of the sample vegetation and the vertical plane that is not greater than 90°, and the angle between the ground where any original detection sample point is located and the horizontal plane is not 0°; A test sample point correction module, used to correct the position of each original detection sample point based on the target data corresponding to each original detection sample point, so as to obtain the position of each target detection sample point; A second data acquisition module is used to collect data at each target detection sample point based on the position of each target detection sample point, and obtain a ground measurement value corresponding to the remote sensing product to be inspected based on the collected data; The authenticity verification module is used to perform an authenticity verification on the remote sensing product to be verified based on the ground measurement value, and obtain an authenticity verification result of the remote sensing product to be verified.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the remote sensing product authenticity verification method as described in any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the remote sensing product authenticity verification method as claimed in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the remote sensing product authenticity verification method as claimed in any one of claims 1 to 6 is implemented.

Images