Image matching result determination method and device, equipment and storage medium

Abstract

The application provides an image matching result determination method and device, computer equipment and a readable storage medium. The method comprises: obtaining a matching result of a remote sensing image and an orthographic image corresponding to the remote sensing image, the matching result comprising: a matching geographical range, a matching pixel range and a matching confidence; determining a matching relative error of the remote sensing image and the orthographic image according to the matching geographical range; extracting image features of the remote sensing image and image features of the orthographic image according to the matching pixel range, the matching confidence, the remote sensing image and the orthographic image; determining a matching pixel error of the remote sensing image and the orthographic image according to the remote sensing image features and the orthographic image features; determining a matching absolute error of the remote sensing image and the orthographic image according to the matching pixel error; and determining a matching result evaluation result of the remote sensing image and the orthographic image according to the matching relative error and the matching absolute error. The evaluation capability of the image matching result can be improved.

Description

Technical Field

[0001] The present application relates to the field of geographic information systems, and specifically to a method, apparatus, device, and storage medium for determining image matching results. Background Art

[0002] Remote sensing images are films or photographs that record the electromagnetic waves of various ground features. In remote sensing images, the main elements of the map are composed of images, supplemented by certain map symbols to represent or illustrate the mapping objects. Compared with ordinary maps, image maps contain rich ground information, clearly structured content, and clear and easy-to-read images, fully demonstrating the dual advantages of images and maps. Orthophotos are remote sensing images with the properties of orthographic projection.

[0003] Remote sensing imagery can be obtained through Earth observation satellites. The resolution of satellite remote sensing images typically ranges from 30 meters to sub-meters, while the resolution of aerial orthophotos derived from satellite remote sensing images typically reaches sub-meter or centimeter levels. This significant difference in image resolution between the two makes matching remote sensing and orthophoto images more difficult. Therefore, a method for evaluating the matching results between remote sensing and orthophoto images is needed to improve their accuracy. Summary of the Invention

[0004] The purpose of this application is to provide a method, device, equipment and storage medium for determining image matching results in response to the technical problems in the above-mentioned prior art, so as to solve the problem that the prior art lacks the actual need for determining image matching results.

[0005] To achieve the above objectives, the technical solutions adopted in the embodiments of the present application are as follows:

[0006] In a first aspect, an embodiment of the present application provides a method for determining an image matching result, the method comprising:

[0007] Obtaining matching results of a remote sensing image and an orthophoto corresponding to the remote sensing image, wherein the matching results include: matching geographic range, matching pixel range, and matching confidence;

[0008] Determining a relative matching error between the remote sensing image and the orthophoto image according to the matching geographic range;

[0009] Extracting remote sensing image features of the remote sensing image and orthophoto image features of the orthophoto image according to the matching pixel range, the matching confidence, the remote sensing image and the orthophoto image;

[0010] Determining a matching pixel error between the remote sensing image and the orthophoto image based on the remote sensing image features and the orthophoto image features;

[0011] Determine the matching absolute error between the remote sensing image and the orthophoto according to the matching pixel error;

[0012] An evaluation result of a matching result between the remote sensing image and the orthophoto image is determined according to the matching relative error and the matching absolute error.

[0013] As an optional implementation manner, determining the relative matching error between the remote sensing image and the orthophoto image according to the matching geographic range includes:

[0014] Reprojecting according to the matching geographic range to obtain a first geographic range;

[0015] Reprojecting the remote sensing image according to its shooting geographical range to obtain a second geographical range;

[0016] Determining an overlapping area and error distances of multiple boundary points based on the first geographic range and the second geographic range;

[0017] Determining a first mean of the error distances of the plurality of boundary points;

[0018] The overlapping area and the first mean are used as the matching relative error.

[0019] As an optional implementation, extracting the remote sensing image features of the remote sensing image and the orthophoto image features of the orthophoto image based on the matching pixel range, the matching confidence, the remote sensing image, and the orthophoto image includes:

[0020] resampling the orthophoto to obtain a sampled orthophoto;

[0021] Adjusting the resolution of the sampled orthophoto according to the resolution of the remote sensing image to obtain an adjusted orthophoto;

[0022] The remote sensing image features and the orthophoto image features are extracted according to the matching pixel range, the matching confidence, the remote sensing image and the adjusted orthophoto image.

[0023] As an optional implementation, determining the matching pixel error between the remote sensing image and the orthophoto image based on the remote sensing image features and the orthophoto image features includes:

[0024] Matching the remote sensing image features and the orthophoto image features to obtain a matching result;

[0025] Determine similar coverage areas according to the matching results;

[0026] Determining the pixel distance between the remote sensing image and the orthophoto image based on the similar coverage area;

[0027] The pixel distance is used as the matching pixel error.

[0028] As an optional implementation manner, determining the absolute matching error between the remote sensing image and the orthophoto image based on the matching pixel error includes:

[0029] Mapping the pixel distance to the coordinate system of the remote sensing image to obtain mapped coordinates;

[0030] Reprojecting the mapped coordinates to obtain absolute values ​​of coordinate distances;

[0031] The same type coverage area and the absolute value of the coordinate distance are used as the matching absolute error.

[0032] As an optional implementation manner, determining the matching result evaluation result between the remote sensing image and the orthophoto image based on the matching relative error and the matching absolute error includes:

[0033] Comparing the overlapping area and the similar coverage area to obtain a first comparison result;

[0034] Comparing the first mean and the absolute value of the coordinate distance to obtain a second comparison result;

[0035] According to the first comparison result and the second comparison result, an evaluation result of the matching result between the remote sensing image and the orthophoto image is obtained.

[0036] As an optional implementation manner, obtaining a matching result evaluation result between the remote sensing image and the orthophoto image based on the first comparison result and the second comparison result includes:

[0037] If the first comparison result is less than or equal to a first preset threshold, and the second comparison result is less than or equal to a second preset threshold, it is determined that the accuracy of the matching result between the remote sensing image and the orthophoto image meets a preset condition.

[0038] In a second aspect, an embodiment of the present application provides an image matching result determination device, the device comprising:

[0039] An acquisition module is used to obtain matching results of a remote sensing image and an orthophoto corresponding to the remote sensing image, wherein the matching results include: matching geographic range, matching pixel range, and matching confidence;

[0040] A determination module, configured to determine a relative matching error between the remote sensing image and the orthophoto image based on the matching geographic range;

[0041] an extraction module, configured to extract remote sensing image features of the remote sensing image and orthophoto image features of the orthophoto image based on the matching pixel range, the matching confidence, the remote sensing image and the orthophoto image;

[0042] The determining module is further configured to:

[0043] Determining a matching pixel error between the remote sensing image and the orthophoto image based on the remote sensing image features and the orthophoto image features;

[0044] The determining module is further configured to:

[0045] Determine the matching absolute error between the remote sensing image and the orthophoto according to the matching pixel error;

[0046] The determining module is further configured to:

[0047] An evaluation result of a matching result between the remote sensing image and the orthophoto image is determined according to the matching relative error and the matching absolute error.

[0048] As a possible implementation manner, the determining module is specifically configured to:

[0049] Reprojecting according to the matching geographic range to obtain a first geographic range;

[0050] Reprojecting the remote sensing image according to its shooting geographical range to obtain a second geographical range;

[0051] Determining an overlapping area and error distances of multiple boundary points based on the first geographic range and the second geographic range;

[0052] Determining a first mean of the error distances of the plurality of boundary points;

[0053] The overlapping area and the first mean are used as the matching relative error.

[0054] As a possible implementation, the extraction module is specifically configured to:

[0055] resampling the orthophoto to obtain a sampled orthophoto;

[0056] Adjusting the resolution of the sampled orthophoto according to the resolution of the remote sensing image to obtain an adjusted orthophoto;

[0057] The remote sensing image features and the orthophoto image features are extracted according to the matching pixel range, the matching confidence, the remote sensing image and the adjusted orthophoto image.

[0058] As a possible implementation manner, the determining module is specifically configured to:

[0059] Matching the remote sensing image features and the orthophoto image features to obtain a matching result;

[0060] Determine similar coverage areas according to the matching results;

[0061] Determining the pixel distance between the remote sensing image and the orthophoto image based on the similar coverage area;

[0062] The pixel distance is used as the matching pixel error.

[0063] As a possible implementation manner, the determining module is specifically configured to:

[0064] Mapping the pixel distance to the coordinate system of the remote sensing image to obtain mapped coordinates;

[0065] Reprojecting the mapped coordinates to obtain absolute values ​​of coordinate distances;

[0066] The same type coverage area and the absolute value of the coordinate distance are used as the matching absolute error.

[0067] As a possible implementation manner, the determining module is specifically configured to:

[0068] Comparing the overlapping area and the similar coverage area to obtain a first comparison result;

[0069] Comparing the first mean and the absolute value of the coordinate distance to obtain a second comparison result;

[0070] According to the first comparison result and the second comparison result, an evaluation result of the matching result between the remote sensing image and the orthophoto image is obtained.

[0071] As a possible implementation manner, the determining module is specifically configured to:

[0072] If the first comparison result is less than or equal to a first preset threshold, and the second comparison result is less than or equal to a second preset threshold, it is determined that the accuracy of the matching result between the remote sensing image and the orthophoto image meets a preset condition.

[0073] In a third aspect, an embodiment of the present application provides a computer device comprising: a processor, a storage medium, and a bus, wherein the storage medium stores machine-readable instructions executable by the processor. When the device is running, the processor communicates with the storage medium through the bus, and the processor executes the machine-readable instructions to perform the steps of the image matching result determination method as described in the first aspect above.

[0074] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the image matching result determination method as described in the first aspect above are executed.

[0075] The beneficial effects of this application are:

[0076] The present application provides a method, apparatus, device and storage medium for determining image matching results. First, the matching results of a remote sensing image and an orthophoto are obtained. The matching results include a matching geographic range, a matching pixel range and a matching confidence. Secondly, based on the matching geographic range, the matching relative error between the remote sensing image and the orthophoto is determined. Then, based on the matching pixel range, the matching confidence, the remote sensing image and the orthophoto, the remote sensing image features of the remote sensing image and the orthophoto features of the orthophoto are extracted. Based on the remote sensing image features and the orthophoto features, the matching pixel error between the remote sensing image and the orthophoto is determined. Then, based on the matching pixel error, the matching absolute error between the remote sensing image and the orthophoto is determined. Finally, based on the matching relative error and the matching absolute error, the matching result evaluation result between the remote sensing image and the orthophoto is determined. Since the matching relative error and the matching absolute error are combined to evaluate the matching results, the accuracy of the evaluation of the image matching results can be guaranteed. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0078] Figure 1 A schematic diagram showing a flow chart of a method for determining image matching results provided in an embodiment of the present application is shown;

[0079] Figure 2 A schematic diagram illustrating a flow chart of determining the relative matching error between a remote sensing image and an orthophoto image according to a matching geographic range in an image matching result determination method provided in an embodiment of the present application is shown;

[0080] Figure 3 A schematic diagram of a process for extracting remote sensing image features and orthophoto image features of a remote sensing image based on a matching pixel range, a matching confidence level, a remote sensing image, and an orthophoto image in a method for determining an image matching result provided by an embodiment of the present application is shown;

[0081] Figure 4A schematic diagram of a process for determining the matching pixel error between a remote sensing image and an orthophoto image based on remote sensing image features and orthophoto image features in an image matching result determination method provided in an embodiment of the present application is shown;

[0082] Figure 5 A schematic diagram of a process for determining the absolute matching error between a remote sensing image and an orthophoto image based on the matching pixel error in the image matching result determination method provided in an embodiment of the present application is shown;

[0083] Figure 6 A schematic diagram illustrating a flow chart of determining a matching result evaluation result between a remote sensing image and an orthophoto image based on a matching relative error and a matching absolute error in an image matching result determination method provided in an embodiment of the present application is shown;

[0084] Figure 7 A module structure diagram of an image matching result determination device provided in an embodiment of the present application is shown;

[0085] Figure 8 A schematic diagram of the computer device structure provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0086] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of illustration and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowcharts can be implemented out of sequence, and steps without logical context can be reversed or implemented simultaneously. In addition, those skilled in the art, under the guidance of the contents of this application, can add one or more other operations to the flowchart, or remove one or more operations from the flowchart.

[0087] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present application.

[0088] To enable those skilled in the art to utilize the present disclosure, the following embodiments are provided in conjunction with the specific application scenario of "image matching." Those skilled in the art will appreciate that the general principles defined herein can be applied to other embodiments and application scenarios without departing from the spirit and scope of this disclosure. While this disclosure primarily focuses on image matching, it should be understood that this is merely an exemplary embodiment.

[0089] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0090] Since the resolution of aerial photography orthophotos often reaches sub-meter or centimeter levels, while the resolution of satellite remote sensing images is often between 30 meters and sub-meter levels, the huge gap in image resolution makes it more difficult to match images with each other. However, the existing technology lacks a method to accurately evaluate the matching results.

[0091] Based on the above problems, the embodiment of the present application proposes a method for determining image matching results, which combines the matching relative error and absolute error of the remote sensing image and the orthophoto image to accurately determine the evaluation result of the matching result of the remote sensing image and the orthophoto image.

[0092] Figure 1 This is a flow chart of the method for determining image matching results provided in the embodiment of the present application. The execution subject of this method can be any computer device with computing processing capabilities. Figure 1 As shown, the method includes:

[0093] S101: Obtain matching results of a remote sensing image and an orthophoto image corresponding to the remote sensing image, where the matching results include: matching geographic range, matching pixel range, and matching confidence.

[0094] Optionally, after acquiring a remote sensing image and generating its corresponding orthophoto, a specific algorithm can be used to generate matching results between the remote sensing image and the orthophoto, and a corresponding query matching result interface can be provided for user access. Furthermore, in this step, the matching results between the remote sensing image and its corresponding orthophoto can be obtained by calling the query matching result interface.

[0095] Optionally, the obtained matching results may include: matching geographic range, matching pixel range, and matching confidence. The matching geographic range refers to the geographic range of the orthophoto image that matches the remote sensing image, the matching pixel range refers to the pixel range of the orthophoto image within the remote sensing image, and the matching confidence indicates the credibility of the matching result.

[0096] S102: Determine the relative matching error between the remote sensing image and the orthophoto image based on the matching geographic range.

[0097] Optionally, based on the matching geographic range, the relative overlapping area of ​​the remote sensing image and the orthophoto image can be obtained, and then the relative matching error between the remote sensing image and the orthophoto image can be obtained.

[0098] S103 , extracting remote sensing image features of the remote sensing image and orthophoto image features of the orthophoto image according to the matching pixel range, the matching confidence, the remote sensing image and the orthophoto image.

[0099] Optionally, remote sensing image features and orthophoto image features are extracted based on the matching pixel range, matching confidence, remote sensing image and orthophoto image. The specific image feature extraction method will be explained in detail in the following embodiments.

[0100] S104: Determine the matching pixel error between the remote sensing image and the orthophoto image based on the remote sensing image features and the orthophoto image features.

[0101] Optionally, based on the remote sensing image features and orthophoto image features extracted in step S103, a matching pixel error between the remote sensing image and the orthophoto image is obtained. The matching pixel error can represent the error between the remote sensing image and the orthophoto image in terms of pixels. The method for determining the matching pixel error will be explained in detail in the following embodiments.

[0102] S105. Determine the absolute matching error between the remote sensing image and the orthophoto image based on the matching pixel error.

[0103] Optionally, based on the matching pixel error determined in step S104, the same coverage area between the remote sensing image and the orthophoto image can be obtained, and further, the absolute matching error between the remote sensing image and the orthophoto image can be obtained. The method for determining the absolute matching error will be explained in detail in the following embodiments.

[0104] S106: Determine an evaluation result of the matching result between the remote sensing image and the orthophoto image based on the matching relative error and the matching absolute error.

[0105] Optionally, a method for determining an evaluation result of a matching result between a remote sensing image and an orthophoto image based on a matching relative error and a matching absolute error will be explained in detail in the following embodiments.

[0106] In this embodiment, first, the matching results of the remote sensing image and the orthophoto image are obtained. The matching results include the matching geographic range, the matching pixel range, and the matching confidence. Secondly, based on the matching geographic range, the relative matching error between the remote sensing image and the orthophoto image is determined. Then, based on the matching pixel range, the matching confidence, the remote sensing image, and the orthophoto image, the remote sensing image features and the orthophoto image features are extracted. Based on the remote sensing image features and the orthophoto image features, the matching pixel error between the remote sensing image and the orthophoto image is determined. Then, based on the matching pixel error, the absolute matching error between the remote sensing image and the orthophoto image is determined. Finally, based on the matching relative error and the matching absolute error, an evaluation result of the matching result between the remote sensing image and the orthophoto image is determined. Since the matching results are evaluated by combining the matching relative error and the matching absolute error, the accuracy of the evaluation of the image matching results can be guaranteed.

[0107] The following describes the process of determining the relative matching error between the remote sensing image and the orthophoto image based on the matching geographic range.

[0108] Figure 2 The image matching result determination method provided in the embodiment of the present application is a flowchart of determining the relative error of matching between the remote sensing image and the orthophoto image according to the matching geographical range, as shown in FIG. Figure 2 As shown, the above step S102 includes:

[0109] S201 : Reproject according to the matching geographic range to obtain a first geographic range.

[0110] Optionally, the coordinates of the points of the geographical range of the orthophoto image indicated by the matching geographical range are projected a second time to obtain a new geographical range, and the new geographical range is used as the first geographical range.

[0111] S202: Reproject the remote sensing image according to its shooting geographical range to obtain a second geographical range.

[0112] Optionally, the shooting geographical range refers to the geographical range covered by the remote sensing image. A new geographical range is obtained by performing a second projection on the coordinates of the points in the shooting geographical range of the remote sensing image, and the new geographical range is used as the second geographical range.

[0113] S203: Determine an overlapping area and error distances of multiple boundary points according to the first geographical range and the second geographical range.

[0114] Optionally, the overlapping area is the area of ​​the overlapping region between the first and second geographic ranges, and the multiple boundary point error distances are the fitted boundary of the matching result, which may be the corresponding distances between multiple vertices of the rectangular boundary and the fitted boundary of the true value. The first and second geographic ranges saved in the above steps are read to determine the overlapping area of ​​the first and second geographic ranges, and the corresponding distances between the multiple vertices of the fitted boundary.

[0115] S204: Determine a first mean value of the error distances of multiple boundary points.

[0116] Optionally, based on the above-mentioned multiple boundary point error distances, the corresponding distances between multiple vertices of the rectangular boundary and the fitting boundary of the true value are averaged to obtain a first mean value of the multiple boundary point error distances.

[0117] S205: Use the overlapping area and the first mean as the matching relative error.

[0118] Optionally, the overlapping area and the first mean are used as the relative matching error between the remote sensing image and the orthophoto image.

[0119] In this embodiment, by reprojecting the matching geographic range with the captured geographic range of the remote sensing image, a first geographic range and a second geographic range are obtained. The overlapping area and a first average of the error distances of multiple boundary points are then determined, and the overlapping area and the first average are used as the relative matching error. In this embodiment, using the overlapping area and the first average as the relative matching error ensures the accuracy of the relative matching error.

[0120] The following describes a process of extracting remote sensing image features of a remote sensing image and orthophoto image features of an orthophoto image based on a matching pixel range, a matching confidence, a remote sensing image, and an orthophoto image.

[0121] Figure 3 A flow chart of extracting remote sensing image features of a remote sensing image and orthophoto image features of an orthophoto image according to the matching pixel range, matching confidence, remote sensing image and orthophoto image provided in the image matching result determination method of the embodiment of the present application is as follows: Figure 3 As shown, the above step S103 includes:

[0122] S301: resample the orthophoto to obtain a sampled orthophoto.

[0123] Optionally, the grayscale of the orthophoto is resampled according to a preset geometric relationship to obtain a new orthophoto after sampling.

[0124] S302: Adjust the resolution of the sampled orthophoto according to the resolution of the remote sensing image to obtain an adjusted orthophoto.

[0125] Optionally, the resolution of the orthophoto and remote sensing images can be unified. The resolution of the sampled orthophoto can be adjusted based on the resolution of the remote sensing image to obtain a new adjusted orthophoto. The remote sensing image and the adjusted orthophoto can then be saved, allowing the remote sensing image and the adjusted orthophoto to be read in this step. Unifying the resolution of the orthophoto and remote sensing images can improve the accuracy of subsequent image feature extraction based on the remote sensing image and the adjusted orthophoto.

[0126] S303 , extracting remote sensing image features and orthophoto image features according to the matching pixel range, matching confidence, remote sensing image, and adjusted orthophoto image.

[0127] Optionally, the pixel range of the orthophoto in the remote sensing image, the credibility of the matching result determined by the matching process, the remote sensing image and the adjusted orthophoto are read, and remote sensing image features and orthophoto features are extracted according to a threshold classification method.

[0128] In this embodiment, the image grayscale of the orthophoto is resampled according to a preset geometric relationship to obtain a new orthophoto after sampling, and the resolution of the orthophoto and remote sensing images are unified. According to the resolution of the remote sensing image, the resolution of the sampled orthophoto is adjusted to obtain an adjusted orthophoto. According to the matching pixel range, matching confidence, the remote sensing image and the adjusted orthophoto, the remote sensing image features and the orthophoto features are extracted to ensure that the remote sensing image features and the orthophoto features are easy to process.

[0129] The following describes a process of determining the matching pixel error between a remote sensing image and an orthophoto image based on the remote sensing image features and the orthophoto image features.

[0130] Figure 4 The image matching result determination method provided in the embodiment of the present application is a flowchart of determining the matching pixel error between the remote sensing image and the orthophoto image based on the remote sensing image features and the orthophoto image features, as shown in FIG. Figure 4 As shown, the above step S104 includes:

[0131] S401: Match the remote sensing image features and the orthophoto image features to obtain a matching result.

[0132] Optionally, the remote sensing image features and the orthophoto image features are segmented and matched separately, and image feature matching results of the remote sensing image and the orthophoto image are obtained based on the matching results of the segmented features.

[0133] S402: Determine the coverage area of ​​the same type according to the matching results.

[0134] Optionally, the same type coverage area is the coverage ratio of boundary data with identical classifications in the remote sensing image and the orthophoto in the matching results. Based on the image feature matching results of the remote sensing image and the orthophoto, the boundary is extracted by type to obtain the coverage ratio of boundary data with identical classifications in the remote sensing image and the orthophoto.

[0135] S403: Determine the pixel distance between the remote sensing image and the orthophoto image based on the same type of coverage area.

[0136] Optionally, the pixel distance between the remote sensing image and the orthophoto image may be a Euclidean distance. The Euclidean distance formula is used to calculate the Euclidean distance between the remote sensing image and the orthophoto image based on the coverage of boundary data with identical classifications in the remote sensing image and the orthophoto image in the matching results.

[0137] S404: Use the pixel distance as the matching pixel error.

[0138] Optionally, the pixel distance between the remote sensing image and the orthophoto image is used as the relative error of the matching between the remote sensing image and the orthophoto image.

[0139] In this embodiment, by matching the remote sensing image features and the orthophoto image features, a matching result is obtained. Based on the matching result, the coverage rate of the boundary data with exactly the same classification as the remote sensing image and the orthophoto image is obtained, and the pixel distance between the remote sensing image and the orthophoto image is obtained. The pixel distance is used as the matching pixel error between the remote sensing image and the orthophoto image, thereby ensuring the determination of the absolute error of the subsequent matching of the remote sensing image and the orthophoto image.

[0140] The following describes the process of determining the absolute matching error between the remote sensing image and the orthophoto image based on the matching pixel error.

[0141] Figure 5 The flowchart of the method for determining the image matching result provided in the embodiment of the present application is to determine the absolute matching error between the remote sensing image and the orthophoto image based on the matching pixel error, as shown in FIG. Figure 5 As shown, the above step S105 includes:

[0142] S501 : Map pixel distances to a coordinate system of a remote sensing image to obtain mapped coordinates.

[0143] Optionally, the pixel distance between the remote sensing image and the orthophoto image is mapped into the coordinate system of the remote sensing image to obtain mapped coordinates.

[0144] S502: Reproject the mapped coordinates to obtain the absolute value of the coordinate distance.

[0145] Optionally, the pixel distance is reprojected to obtain the absolute value of the coordinate distance. The mapped geographic coordinates are reprojected to the target projection range, and the matching pixel error is converted to the distance under the target projection to obtain the absolute value of the coordinate distance.

[0146] S503: Use the same type of coverage area and the absolute value of the coordinate distance as the matching absolute error.

[0147] Optionally, the above-mentioned similar coverage area and absolute value of coordinate distance are used as the absolute matching error between the remote sensing image and the orthophoto image.

[0148] In this embodiment, the pixel distance is mapped to the coordinate system of the remote sensing image to obtain the mapped coordinates, and the mapped coordinates are reprojected to obtain the absolute value of the coordinate distance. The same coverage area and the absolute value of the coordinate distance are used as the matching absolute error, thereby ensuring that the matching absolute error is subsequently used to determine the image matching result.

[0149] The following describes a process for determining the evaluation result of the matching result between the remote sensing image and the orthophoto image based on the matching relative error and the matching absolute error.

[0150] Figure 6 The image matching result determination method provided in the embodiment of the present application is a flowchart of determining the matching result evaluation result of the remote sensing image and the orthophoto image based on the matching relative error and the matching absolute error, as shown in FIG. Figure 6 As shown, the above step S106 includes:

[0151] S601: Compare the overlapping area and the similar coverage area to obtain a first comparison result.

[0152] Optionally, in step S203, an overlapping area is determined based on the first and second geographic ranges. In steps S401 and S402, the remote sensing image features and the orthophoto image features are matched to obtain a matching result. Based on the matching result, a similar coverage area is determined. The overlapping area and the similar coverage area are compared to obtain a first comparison result. For example, a difference between the overlapping area and the similar coverage area can be calculated and used as the first comparison result.

[0153] S602: Compare the first mean and the absolute value of the coordinate distance to obtain a second comparison result.

[0154] Optionally, in step S204, a first mean of the error distances of the plurality of boundary points is determined, and in steps S501 and S502, the pixel distances are mapped to the coordinate system of the remote sensing image to obtain mapped coordinates, the mapped coordinates are reprojected to obtain absolute values ​​of the coordinate distances, and the first mean and the absolute values ​​of the coordinate distances are compared to obtain a second comparison result. For example, the difference between the first mean and the absolute values ​​of the coordinate distances can be calculated, and the difference can be used as the second comparison result.

[0155] S603: Obtain a matching result evaluation result between the remote sensing image and the orthophoto image according to the first comparison result and the second comparison result.

[0156] Optionally, if the first comparison result is less than or equal to a first preset threshold, and the second comparison result is less than or equal to a second preset threshold, then it is determined that the accuracy of the matching result between the remote sensing image and the orthophoto image meets the preset conditions. Based on the above steps S601-S602, it can be seen that the first comparison result is the difference between the overlapping area and the similar coverage area, and the second comparison result is the difference between the first mean and the absolute value of the coordinate distance. If the first comparison result is less than or equal to the first preset threshold, it indicates that the accuracy of the matching result of the remote sensing image and the orthophoto image in the overlapping area is high. At the same time, if the second comparison result is less than or equal to the second preset threshold, it indicates that the accuracy of the matching result of the remote sensing image and the orthophoto image in the pixel distance is high. Therefore, if the above two conditions are met at the same time, it can be determined that the accuracy of the matching result of the remote sensing image and the orthophoto image is high.

[0157] It is worth noting that the first preset threshold and the second preset threshold can be obtained based on actual verification.

[0158] In this embodiment, a first comparison result is obtained by comparing the overlapping area and the similar coverage area, and a second comparison result is obtained by comparing the first mean and the absolute value of the coordinate distance. Based on the first comparison result and the second comparison result, an evaluation result of the matching result of the remote sensing image and the orthophoto image is obtained, thereby achieving an evaluation result of the matching result of the remote sensing image and the orthophoto image based on the matching relative error and the matching absolute error.

[0159] Based on the same inventive concept, an image matching result determination device corresponding to the image matching result determination method is also provided in the embodiment of the present application. Since the principle of solving the problem by the device in the embodiment of the present application is similar to the above-mentioned image matching result determination method in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0160] Figure 7 This is a module structure diagram of an image matching result determination device provided in an embodiment of the present application, such as Figure 7 As shown, the device includes:

[0161] The acquisition module 701 is used to obtain the matching results of the remote sensing image and the orthophoto image corresponding to the remote sensing image, and the matching results include: matching geographic range, matching pixel range, and matching confidence.

[0162] The determination module 702 is configured to determine a relative matching error between the remote sensing image and the orthophoto image according to the matching geographic range.

[0163] The extraction module 703 is configured to extract remote sensing image features of the remote sensing image and orthophoto image features of the orthophoto image according to the matching pixel range, the matching confidence, the remote sensing image and the orthophoto image.

[0164] The determination module 702 is further configured to:

[0165] According to the remote sensing image features and the orthophoto image features, a matching pixel error between the remote sensing image and the orthophoto image is determined.

[0166] The determination module 702 is further configured to:

[0167] The absolute matching error between the remote sensing image and the orthophoto image is determined according to the matching pixel error.

[0168] The determination module 702 is further configured to:

[0169] An evaluation result of a matching result between the remote sensing image and the orthophoto image is determined according to the matching relative error and the matching absolute error.

[0170] As a possible implementation, the determining module 702 is specifically configured to:

[0171] Reprojection is performed according to the matching geographic range to obtain a first geographic range.

[0172] Reprojection is performed according to the shooting geographical range of the remote sensing image to obtain a second geographical range.

[0173] An overlapping area and error distances of multiple boundary points are determined based on the first geographic range and the second geographic range.

[0174] A first mean value of the error distances of the plurality of boundary points is determined.

[0175] The overlapping area and the first mean are used as the matching relative error.

[0176] As a possible implementation, the extraction module 703 is specifically configured to:

[0177] The orthophoto is resampled to obtain a sampled orthophoto.

[0178] The resolution of the sampled orthophoto is adjusted according to the resolution of the remote sensing image to obtain an adjusted orthophoto.

[0179] The remote sensing image features and the orthophoto image features are extracted according to the matching pixel range, the matching confidence, the remote sensing image and the adjusted orthophoto image.

[0180] As a possible implementation, the determining module 702 is specifically configured to:

[0181] Matching the remote sensing image features and the orthophoto image features to obtain a matching result.

[0182] The same type of coverage area is determined according to the matching result.

[0183] The pixel distance between the remote sensing image and the orthophoto image is determined according to the similar coverage area.

[0184] The pixel distance is used as the matching pixel error.

[0185] As a possible implementation, the determining module 702 is specifically configured to:

[0186] The pixel distance is mapped to the coordinate system of the remote sensing image to obtain mapped coordinates.

[0187] The mapped coordinates are reprojected to obtain absolute values ​​of coordinate distances.

[0188] The same type coverage area and the absolute value of the coordinate distance are used as the matching absolute error.

[0189] As a possible implementation, the determining module 702 is specifically configured to:

[0190] The overlapping area and the similar coverage area are compared to obtain a first comparison result.

[0191] The first mean and the absolute value of the coordinate distance are compared to obtain a second comparison result.

[0192] According to the first comparison result and the second comparison result, an evaluation result of the matching result between the remote sensing image and the orthophoto image is obtained.

[0193] As a possible implementation, the determining module 702 is specifically configured to:

[0194] If the first comparison result is less than or equal to a first preset threshold, and the second comparison result is less than or equal to a second preset threshold, it is determined that the accuracy of the matching result between the remote sensing image and the orthophoto image meets a preset condition.

[0195] The embodiment of the present application also provides a computer device 80, such as Figure 8 FIG. 8 is a schematic diagram of the structure of a computer device 80 provided in an embodiment of the present application, comprising: a processor 81, a memory 82, and a bus 83. The memory 82 stores machine-readable instructions executable by the processor 81 (e.g., Figure 7 The acquisition module 701, the determination module 702 and the execution instructions corresponding to the extraction module 703 in the device, etc.), when the computer device 80 is running, the processor 81 communicates with the memory 82 through the bus 83, and when the machine-readable instructions are executed by the processor 81, the method steps in the above method embodiment are executed.

[0196] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method for determining the image matching result in the above embodiment are executed.

[0197] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and device described above can refer to the corresponding process in the method embodiment, and will not be repeated in this application. In the several embodiments provided in this application, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0198] In addition, the functional units in the various embodiments of the present application can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially 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, which is stored in a storage medium and includes several instructions for enabling 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 various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0199] The above is only a specific implementation method of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the protection scope of the present application.

Claims

1. A method for determining an image matching result, characterized in that: include: Obtaining matching results of a remote sensing image and an orthophoto corresponding to the remote sensing image, wherein the matching results include: matching geographic range, matching pixel range, and matching confidence; Determining a relative matching error between the remote sensing image and the orthophoto image according to the matching geographic range; Extracting remote sensing image features of the remote sensing image and orthophoto image features of the orthophoto image according to the matching pixel range, the matching confidence, the remote sensing image and the orthophoto image; Determining a matching pixel error between the remote sensing image and the orthophoto image based on the remote sensing image features and the orthophoto image features; Determine the matching absolute error between the remote sensing image and the orthophoto according to the matching pixel error; An evaluation result of a matching result between the remote sensing image and the orthophoto image is determined according to the matching relative error and the matching absolute error.

2. The method according to claim 1, characterized in that Determining the relative matching error between the remote sensing image and the orthophoto image according to the matching geographic range includes: Reprojecting according to the matching geographic range to obtain a first geographic range; Reprojecting the remote sensing image according to its shooting geographical range to obtain a second geographical range; Determining an overlapping area and error distances of multiple boundary points based on the first geographic range and the second geographic range; Determining a first mean of the error distances of the plurality of boundary points; The overlapping area and the first mean are used as the matching relative error.

3. The method according to claim 1, characterized in that Extracting the remote sensing image features of the remote sensing image and the orthophoto image features of the orthophoto image according to the matching pixel range, the matching confidence, the remote sensing image, and the orthophoto image includes: resampling the orthophoto to obtain a sampled orthophoto; Adjusting the resolution of the sampled orthophoto according to the resolution of the remote sensing image to obtain an adjusted orthophoto; The remote sensing image features and the orthophoto image features are extracted according to the matching pixel range, the matching confidence, the remote sensing image and the adjusted orthophoto image.

4. The method according to claim 2, characterized in that Determining the matching pixel error between the remote sensing image and the orthophoto image based on the remote sensing image features and the orthophoto image features includes: Matching the remote sensing image features and the orthophoto image features to obtain a matching result; Determine similar coverage areas according to the matching results; Determining the pixel distance between the remote sensing image and the orthophoto image based on the similar coverage area; The pixel distance is used as the matching pixel error.

5. The method according to claim 4, characterized in that The determining of the matching absolute error between the remote sensing image and the orthophoto image according to the matching pixel error comprises: Mapping the pixel distance to the coordinate system of the remote sensing image to obtain mapped coordinates; Reprojecting the mapped coordinates to obtain absolute values ​​of coordinate distances; The same type coverage area and the absolute value of the coordinate distance are used as the matching absolute error.

6. The method according to claim 5, characterized in that Determining the matching result evaluation result between the remote sensing image and the orthophoto image based on the matching relative error and the matching absolute error includes: Comparing the overlapping area and the similar coverage area to obtain a first comparison result; Comparing the first mean and the absolute value of the coordinate distance to obtain a second comparison result; According to the first comparison result and the second comparison result, an evaluation result of the matching result between the remote sensing image and the orthophoto image is obtained.

7. The method according to claim 6, characterized in that Obtaining a matching result evaluation result between the remote sensing image and the orthophoto image based on the first comparison result and the second comparison result includes: If the first comparison result is less than or equal to a first preset threshold, and the second comparison result is less than or equal to a second preset threshold, it is determined that the accuracy of the matching result between the remote sensing image and the orthophoto image meets a preset condition.

8. An image matching result determination device, characterized in that: The device comprises: An acquisition module is used to obtain matching results of a remote sensing image and an orthophoto corresponding to the remote sensing image, wherein the matching results include: matching geographic range, matching pixel range, and matching confidence; A determination module, configured to determine a relative matching error between the remote sensing image and the orthophoto image based on the matching geographic range; an extraction module, configured to extract remote sensing image features of the remote sensing image and orthophoto image features of the orthophoto image based on the matching pixel range, the matching confidence, the remote sensing image and the orthophoto image; The determination module is further configured to determine a matching pixel error between the remote sensing image and the orthophoto image based on the remote sensing image features and the orthophoto image features; The determining module is further configured to determine an absolute matching error between the remote sensing image and the orthophoto image based on the matching pixel error; The determination module is further configured to determine an evaluation result of a matching result between the remote sensing image and the orthophoto image based on the matching relative error and the matching absolute error.

9. A computer device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor executes the machine-readable instructions to perform the steps of the image matching result determination method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for determining an image matching result according to any one of claims 1 to 7 are executed.

Images