Orthographic image positioning method, device and storage medium

Abstract

The application provides an orthographic image positioning method, device and storage medium, wherein the method comprises the following steps: first, obtaining an orthographic image; performing first resolution matching on the orthographic image and historical remote sensing images to obtain a first remote sensing image matched with the orthographic image; performing second resolution matching on the basis of the orthographic image and the first remote sensing image to obtain a matching result of the orthographic image in the first remote sensing image, wherein the second resolution is greater than the first resolution; and finally, determining position information corresponding to the orthographic image according to the matching result of the orthographic image. The application can realize calibration and positioning based on background data when signal loss or positioning failure of a third-party device occurs, thereby improving the overall analysis capability of a GIS system.

Description

Technical Field

[0001] This application relates to the field of geographic information technology, and more specifically, to an orthophoto positioning method, device, and storage medium. Background Technology

[0002] Earth observation refers to observing the Earth from outside its surface, utilizing spatial location advantages to obtain geographic information data. Earth observation can be conducted using Earth observation satellites or drones. Currently, both Earth observation satellites and drones establish their own position within the overall spatial information system through positioning systems, and simultaneously determine the position of targets within their respective spatial information systems.

[0003] The positioning technologies in existing positioning systems mainly include satellite positioning technology, mobile communication-based positioning technology, mobile communication-assisted satellite positioning technology, IP positioning technology, and WiFi positioning technology.

[0004] However, existing positioning technologies all heavily rely on signal transmission or third-party equipment. When the signal is lost or the third-party equipment fails, it becomes difficult to locate the observation equipment. Summary of the Invention

[0005] The purpose of this application is to address the shortcomings of the prior art by providing an orthophoto positioning method, device, and storage medium to solve the problem that it is difficult to locate the observation device when the signal is lost or the third-party device fails.

[0006] To achieve the above objectives, the technical solution adopted in this application is as follows:

[0007] In a first aspect, this application provides an orthophoto positioning method, the method comprising:

[0008] Obtain orthophotos;

[0009] A first resolution match is performed between the orthophoto and historical remote sensing images to obtain a first remote sensing image that matches the orthophoto.

[0010] Based on the orthophoto and the first remote sensing image, a second resolution matching is performed to obtain the matching result of the orthophoto in the first remote sensing image, wherein the second resolution is greater than the first resolution.

[0011] The location information corresponding to the orthophoto is determined based on the matching result of the orthophoto.

[0012] Optionally, the step of performing a first resolution match between the orthophoto and historical remote sensing images to obtain a first remote sensing image matching the orthophoto includes:

[0013] The height of the orthophoto is obtained by estimating its height.

[0014] The resolution of the orthophoto is determined based on the height of the orthophoto.

[0015] Based on the resolution of the orthophoto and the first resolution, the orthophoto is scaled to obtain a scaled orthophoto.

[0016] Feature extraction is performed on the scaled orthophoto, and feature matching is performed between the extracted features and the features of the historical remote sensing image to obtain the first remote sensing image.

[0017] Optionally, estimating the height of the orthophoto to obtain the height of the orthophoto includes:

[0018] Based on the current altitude, the resolution of the orthophoto is estimated to obtain the predicted resolution.

[0019] The orthophoto is scaled based on the estimated resolution and the first resolution to obtain a scaled orthophoto.

[0020] Determine the matching degree between the scaled orthophoto and the historical remote sensing image, adjust the current height to obtain a new current height, and re-execute the step of estimating the resolution of the orthophoto based on the current height to obtain the estimated resolution. Obtain multiple matching degrees between the scaled image and the historical remote sensing image, and take the height of the historical remote sensing image with the highest matching degree as the height of the orthophoto.

[0021] Optionally, determining the resolution of the orthophoto based on its height includes:

[0022] The position of the virtual camera is determined based on the height of the orthophoto;

[0023] At the location of the virtual camera, the coverage area of ​​the camera is determined based on the parameter information of the camera model, including: camera parameters, camera focal length, and wide-angle information;

[0024] The resolution of the orthophoto is obtained by matching pixels according to the coverage area of ​​the camera.

[0025] Optionally, the step of extracting features from the scaled orthophoto and matching the extracted features with features from the historical remote sensing image to obtain the first remote sensing image includes:

[0026] Feature extraction is performed on the scaled orthophoto to obtain multiple features;

[0027] The multiple features are matched with the multiple features of the historical remote sensing image to obtain a sparse matching rate matrix between the scaled orthophoto and the historical remote sensing image. The sparse matching rate matrix is ​​used to characterize the matching degree of each region in the orthophoto and the historical remote sensing image.

[0028] The region with the highest matching degree in the matching rate sparse matrix is ​​determined, and the region with the highest matching degree is cropped based on the matching range to obtain the first remote sensing image.

[0029] Optionally, the step of performing a second resolution matching based on the orthophoto and the first remote sensing image to obtain the matching result of the orthophoto in the first remote sensing image includes:

[0030] Based on the orthophoto and the first remote sensing image, a first-level resolution matching is performed to obtain a second remote sensing image of the orthophoto within the first remote sensing image.

[0031] Optionally, the step of performing a second resolution matching based on the orthophoto and the first remote sensing image to obtain the matching result of the orthophoto in the first remote sensing image includes:

[0032] Based on the orthophoto and the first remote sensing image, a second-level resolution matching is performed to obtain the matching result of the orthophoto in the first remote sensing image, wherein the second-level resolution is greater than the first-level resolution.

[0033] Optionally, the step of performing a second-level resolution matching based on the orthophoto and the first remote sensing image to obtain the matching result of the orthophoto in the first remote sensing image includes:

[0034] Based on the resolution of the orthophoto and the second-level resolution, the orthophoto is scaled to obtain a scaled orthophoto.

[0035] The first remote sensing image and the scaled orthophoto image are subjected to grayscale processing to obtain a grayscale image of the first remote sensing image and a grayscale image of the scaled orthophoto image.

[0036] Feature extraction is performed on the grayscale image of the first remote sensing image and the grayscale image of the scaled orthophoto image to obtain the grayscale image features of the first remote sensing image and the grayscale image features of the scaled orthophoto image.

[0037] Feature matching is performed on the grayscale features of the first remote sensing image and the grayscale features of the scaled orthophoto image to obtain a first matching region between the grayscale features of the first remote sensing image and the grayscale features of the scaled orthophoto image.

[0038] Feature extraction is performed on the first remote sensing image and the scaled orthophoto to obtain the features of the first remote sensing image and the features of the orthophoto image.

[0039] The first remote sensing image features and the scaled orthophoto image features are matched to obtain the second matching region.

[0040] The first matching region and the second matching region are merged to obtain the matching result of the orthophoto in the first remote sensing image.

[0041] Secondly, this application provides an electronic device, including: a processor, a storage medium, and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of the orthophoto positioning method described above.

[0042] Thirdly, this application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the orthophoto positioning method described above.

[0043] The beneficial effects of this application are: by performing multiple resolution matching, the accuracy of the matching results can be improved; by performing multi-resolution matching between orthophotos and historical remote sensing images in Earth observation equipment, calibration and positioning based on baseline data can be achieved when signals are lost or third-party equipment positioning fails, thereby improving the overall analytical capabilities of the GIS system. Attached Figure Description

[0044] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 This illustration shows an application scenario provided by an embodiment of this application.

[0046] Figure 2 A flowchart of an orthophoto localization method provided in an embodiment of this application is shown;

[0047] Figure 3 This application provides a flowchart of an embodiment for obtaining a first remote sensing image.

[0048] Figure 4A flowchart illustrating an orthophoto imaging height estimation method provided in an embodiment of this application is shown;

[0049] Figure 5 This document illustrates a flowchart of another method for estimating the imaging height of orthophotos provided in an embodiment of this application.

[0050] Figure 6 A flowchart illustrating an orthophoto resolution calculation method provided in an embodiment of this application is shown.

[0051] Figure 7 This document illustrates a flowchart of another method for obtaining a first remote sensing image, as provided in an embodiment of this application.

[0052] Figure 8 This document illustrates a flowchart of a second resolution matching process provided in an embodiment of this application.

[0053] Figure 9 This paper shows a schematic diagram of the structure of an orthophoto positioning device provided in an embodiment of this application;

[0054] Figure 10 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the accompanying drawings in this application are for illustrative and descriptive purposes only and are not intended to limit the scope of protection of this application. Furthermore, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of this application. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical contextual relationships may be reversed or implemented simultaneously. In addition, those skilled in the art, guided by the content of this application, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0056] Furthermore, the described embodiments are merely some, not all, of the embodiments of this application. The components of the embodiments of this application described and illustrated herein can typically be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0057] It should be noted that the term "comprising" will be used in the embodiments of this application to indicate the presence of the features declared thereafter, but does not exclude the addition of other features.

[0058] The positioning technologies in existing positioning systems mainly include satellite positioning technology, mobile communication-based positioning technology, mobile communication-assisted satellite positioning technology, IP positioning technology, and WiFi positioning technology.

[0059] The current main positioning methods of Geographic Information Systems (GIS) are based on a combination of satellite positioning technology and mobile communication-assisted satellite positioning technology. Both of these methods heavily rely on signal transmission or third-party equipment and lack the ability to perform calibration and positioning based on baseline data.

[0060] When signals are lost or third-party equipment fails, how to perform calibration and positioning based on baseline data from satellites or drones becomes an urgent problem to be solved.

[0061] To address the aforementioned issues, this application proposes an orthophoto positioning method. By matching orthophotos acquired in real time by satellites or UAVs with historical remote sensing images, the location of the satellite or UAV that captured the orthophotos can be determined. This method enables calibration and positioning based on baseline data from satellites or UAVs, thereby enhancing the overall analytical capabilities of the GIS system.

[0062] like Figure 1 The diagram shown is a schematic of an application scenario provided in this application. When the drone loses its signal and fails to locate, it can acquire the current image and process the image to obtain an orthophoto. Based on the current orthophoto, it can perform multi-resolution calibration matching with the historical remote sensing images of the current plot stored in the drone to determine the location of the drone that captured the current orthophoto in the current plot.

[0063] Next, combine Figure 2 The orthophoto positioning method of this application will be further described below. The subject executing this method can be an Earth observation device with data processing capabilities, such as... Figure 1 The drones or Earth observation satellites mentioned can also be electronic devices that communicate with Earth observation equipment, such as... Figure 2 As shown, the method includes:

[0064] S201: Acquire orthophoto.

[0065] Orthophotos are remote sensing images that exhibit orthogonal projection properties. Raw remote sensing images suffer from varying degrees of distortion and falsification due to changes in the sensor's internal state, external conditions, and surface features during imaging. Geometric processing of remote sensing images not only extracts spatial information, such as drawing contour lines, but also resamples the image's grayscale according to correct geometric relationships to form new orthophotos.

[0066] Optionally, the Earth observation equipment can acquire remote sensing images and perform orthophoto processing on the remote sensing images to obtain orthophotos.

[0067] S202: Perform a first resolution match between the orthophoto and historical remote sensing images to obtain a first remote sensing image that matches the orthophoto.

[0068] Optionally, historical remote sensing images can be remote sensing images of the current area acquired by Earth observation equipment during past acquisition cycles, and the resolution of historical remote sensing images can be the first resolution.

[0069] Before performing initial resolution matching between orthophotos and historical remote sensing images, remote sensing images from the database storing remote sensing images at the target time can be selected as historical remote sensing images based on the imaging time of the orthophotos. The number of historical remote sensing images can be one or more.

[0070] For example, the remote sensing image for the target time can be a remote sensing image from the same month, day, and time of the previous year. If there is no remote sensing image for the target time, the remote sensing image of the nearest time to the target time can be used as the aforementioned historical remote sensing image.

[0071] Optionally, the first resolution can be 30 meters or higher. For example, remote sensing images at the first resolution can be acquired first, and orthophotos and these remote sensing images can be matched to obtain a first remote sensing image that matches the orthophotos.

[0072] After obtaining the first resolution matching result between the orthophoto and the historical remote sensing image, the area indicated by the matching result can be cropped in the original remote sensing image to obtain the first remote sensing image.

[0073] Optionally, the first remote sensing image may characterize the matching area of ​​the orthophoto in the historical remote sensing image, and the range indicated by the matching area may be equal to or greater than the range indicated by the orthophoto.

[0074] S203: Based on the orthophoto and the first remote sensing image, perform second resolution matching to obtain the matching result of the orthophoto in the first remote sensing image, wherein the second resolution is greater than the first resolution.

[0075] After obtaining the first remote sensing image, in order to further determine the position of the orthophoto image in the remote sensing image, a second matching can be performed based on the orthophoto image and the first remote sensing image. The second resolution can be greater than the first resolution.

[0076] For example, assuming the first resolution is a remote sensing image with a resolution of 30 meters or higher, the second resolution can be a remote sensing image with a resolution of 10 meters or a remote sensing image with a sub-meter resolution. After obtaining the first remote sensing image, the orthophoto can be scaled down to the second resolution, and the scaled orthophoto can be matched with the first remote sensing image to obtain the matching result of the orthophoto in the first remote sensing image.

[0077] Optionally, the matching result of the orthophoto in the first remote sensing image can indicate the matching area of ​​the orthophoto in the first remote sensing image, and the range indicated by the matching result can be greater than or equal to the range indicated by the orthophoto.

[0078] S204: Determine the location information corresponding to the orthophoto based on the matching results of the orthophoto.

[0079] Since orthophotos are acquired and processed by Earth observation equipment, after determining the matching results of the orthophotos, the shooting range of the Earth observation equipment can be determined based on the area of ​​the matching results in the remote sensing image, thereby obtaining the location information of the Earth observation equipment.

[0080] For example, after determining the matching result of the orthophoto, the region of the matching result can be determined in the remote sensing image, and the position of the center point of the region can be used as the position information of the Earth observation device.

[0081] In this embodiment, an orthophoto is first acquired. A first resolution match is performed between the orthophoto and historical remote sensing images to obtain a first remote sensing image that matches the orthophoto. A second resolution match is performed between the orthophoto and the first remote sensing image to obtain the matching result of the orthophoto in the first remote sensing image. The second resolution is greater than the first resolution. Finally, the location information corresponding to the orthophoto is determined based on the matching result of the orthophoto.

[0082] By performing multiple resolution matching operations, the accuracy of the matching results can be improved. By performing multi-resolution matching between orthophotos and historical remote sensing images from Earth observation equipment, calibration and positioning based on baseline data can be achieved when signals are lost or third-party equipment positioning fails, thereby improving the overall analytical capabilities of the GIS system.

[0083] Furthermore, the step in S202 above, which involves performing a first resolution match between the orthophoto and historical remote sensing images to obtain a first remote sensing image that matches the orthophoto, is as follows: Figure 3As shown, it includes:

[0084] S301: Estimate the height of the orthophoto to obtain the height of the orthophoto.

[0085] Optionally, the height of the orthophoto can be the height of the Earth observation equipment when acquiring the orthophoto.

[0086] S302: Determine the resolution of the orthophoto based on its height.

[0087] Once the height of the orthophoto is estimated, its resolution can be estimated based on that height.

[0088] For example, digital modeling can be performed based on orthophotos to obtain a virtual camera, which is then applied to the geographic ellipsoid to obtain the coverage area of ​​the virtual camera. Finally, the coverage area and pixels of the camera are matched to calculate the resolution of the orthophoto.

[0089] S303: Based on the resolution of the orthophoto and the first resolution, scale the orthophoto to obtain a scaled orthophoto.

[0090] Optionally, after determining the resolution of the orthophoto in this application, the orthophoto can be scaled down to the first resolution to obtain a scaled orthophoto.

[0091] S304: Extract features from the scaled orthophoto and match the extracted features with features from historical remote sensing images to obtain the first remote sensing image.

[0092] As one possible implementation, the features of historical remote sensing images can be extracted simultaneously with the feature extraction of scaled orthophotos.

[0093] As another possible implementation, in order to improve the efficiency of feature matching, features can be extracted from historical remote sensing images in advance to obtain multiple features of historical remote sensing images. Feature matching is then performed based on the features extracted from historical remote sensing images and the features of scaled orthophotos. The region in the historical remote sensing image with the highest matching degree with the scaled orthophoto is taken as the first remote sensing image.

[0094] It is worth noting that the method for feature extraction from historical remote sensing images can be the same as the method for feature extraction from scaled orthophotos. For example, deep learning methods or scale-invariant feature transform (SIFT) methods can be used for feature extraction.

[0095] The following is a further explanation of the height estimation of the orthophoto in S301 above, to obtain the height of the orthophoto. Figure 4 As shown, the above step S301 includes:

[0096] S401: Based on the current altitude, the resolution of the orthophoto is estimated to obtain the predicted resolution.

[0097] In this application, an initial estimated height can be preset, and the resolution of the orthophoto can be estimated at the initial estimated height to obtain the estimated resolution.

[0098] For example, the initial estimated height can be set to 500 meters. At a height of 500 meters, the resolution of the virtual camera at that height can be estimated using a digitally modeled virtual camera, and this resolution can be used as the estimated resolution.

[0099] S402: Scale the orthophoto based on the estimated resolution to obtain a scaled orthophoto.

[0100] Optionally, after obtaining the estimated resolution, the orthophoto can be scaled based on the estimated resolution to obtain a scaled orthophoto.

[0101] S403: Determine the matching degree between the scaled orthophoto and the historical remote sensing image, adjust the current height to obtain a new current height, and re-execute the step of estimating the resolution of the orthophoto based on the current height to obtain the estimated resolution. Obtain multiple matching degrees between the scaled image and the historical remote sensing image, and take the height of the historical remote sensing image with the highest matching degree as the height of the orthophoto.

[0102] In this application, a coefficient can be calculated based on the RGB values ​​of the scaled orthophoto, and a coefficient can also be calculated based on the RGB values ​​of the historical remote sensing image. Then, the scaled orthophoto and the historical remote sensing image are matched based on the calculated coefficient to obtain the matching degree between the scaled orthophoto and the historical remote sensing image. For example, the calculation method can be to calculate a coefficient based on the RGB values ​​using the normalized interpolation sum of squares method.

[0103] It should be noted that, in this application, after performing the above steps S401-S402 on the orthophoto at the initial estimated height to obtain the matching degree A at the initial estimated height, the initial estimated height can be adjusted, for example, by increasing or decreasing the initial estimated height to obtain a new height. Then, based on the new height, the above steps S401-S402 are performed again to obtain the matching degree B between the scaled orthophoto and the historical remote sensing image at the new height.

[0104] like Figure 5 The diagram shown is a flowchart of the orthophoto imaging height estimation method provided in this application. (Refer to...) Figure 5 After obtaining the matching degree A and matching degree B, the size of matching degree A and matching degree B can be compared. If matching degree A is greater than matching degree B, the estimated height can be increased. For example, the current estimated height can be increased by 100 meters each time, and the current height can be updated to 600 meters. Then, the above steps S401-S402 are executed again to obtain the matching degree C at 600 meters. The size of matching degree C and matching degree B is compared again. If matching degree C is still greater than matching degree B, the current height is increased again until the new matching degree is less than the matching degree obtained in the previous calculation.

[0105] When the matching score first decreases, the estimated height can be reduced. The decrease in the estimated height each time can be less than the increase in the estimated height each time. For example, assuming the estimated height is increased by 100 meters each time, the estimated height can be reduced by 50 meters each time. Then, the above steps S401-S402 are re-executed to obtain a new matching score. The new matching score is compared with the matching score obtained in the previous calculation until the new matching score is less than or equal to the matching score obtained in the previous calculation.

[0106] After the matching degree first decreases, the estimated height can be further reduced to obtain a new matching degree. When the new matching degree shows a continuous downward trend, the height with the highest matching degree can be taken as the height of the orthophoto.

[0107] After determining the height, this application can determine the resolution of the orthophoto based on the height of the orthophoto, such as... Figure 6 As shown, step S302 above includes:

[0108] S601: Determine the position of the virtual camera based on the height of the orthophoto.

[0109] In this application, a virtual camera can be modeled in advance. The orthophoto can include camera parameters, camera focal length, and wide-angle information. Based on this information, a digital model can be created to obtain a virtual camera.

[0110] Optionally, the position of the virtual camera can be the height of the orthophoto obtained in S301 above.

[0111] S602: At the location of the virtual camera, determine the coverage area of ​​the camera based on the parameter information of the camera model. The parameter information includes: camera parameters, camera focal length, and wide-angle information.

[0112] In this application, the height of the virtual camera can be set to the height of the orthophoto, and the virtual camera can be applied to the geographic ellipsoid at this height to obtain the camera's coverage area.

[0113] S603: Matches pixels based on the camera's coverage area to obtain the resolution of the orthophoto.

[0114] Optionally, after determining the camera's coverage area, pixels can be matched to the camera's coverage area to obtain the resolution of the camera's coverage area, and this resolution can be used as the resolution of the orthophoto.

[0115] The following describes the steps for extracting features from the scaled orthophoto and matching the extracted features with features from historical remote sensing images to obtain the first remote sensing image. Figure 7 As shown, step S304 above includes:

[0116] S701: Extract features from the scaled orthophoto to obtain multiple features.

[0117] Optionally, the feature extraction method can be deep learning or SIFT.

[0118] S702: Perform feature matching between multiple features and multiple features of historical remote sensing images to obtain a sparse matrix of matching rate between the scaled orthophoto and historical remote sensing images. The sparse matrix of matching rate is used to characterize the matching degree of each region in the orthophoto and historical remote sensing images.

[0119] Optionally, the matching rate sparse matrix can characterize the matching degree between each region in the orthophoto and the historical remote sensing image. For example, assuming the orthophoto is 2×2 in size and the historical remote sensing image is 10×10 in size, the matching rate sparse matrix can be 5×5 in size, with each value representing the matching degree between the 2×2 region of the orthophoto and the historical remote sensing image.

[0120] S703: Determine the region with the highest matching degree in the sparse matching rate matrix, and crop the region with the highest matching degree based on the matching range to obtain the first remote sensing image.

[0121] Optionally, the region with the highest matching degree in the matching rate sparse matrix can be the region with the highest density in the matrix, and this region can be used as the region with the highest matching degree.

[0122] Optionally, the matching range can be a preset size range. After determining the area with the highest matching degree, the area with the highest matching degree can be cropped from the historical remote sensing image based on the matching range to obtain the first remote sensing image.

[0123] The following is a further explanation of the above-mentioned second-resolution matching based on orthophotos and the first remote sensing image, to obtain the matching results of the orthophotos in the first remote sensing image, including:

[0124] Based on the orthophoto and the first remote sensing image, a first-level resolution matching is performed to obtain the second remote sensing image of the orthophoto within the first remote sensing image.

[0125] Optionally, the first-level resolution can be 10-meter resolution.

[0126] In this application, after performing a first resolution matching on the integrated impact, the original remote sensing image can be cropped according to the matching result to obtain a first remote sensing image, the resolution of which can be the size of a second-level resolution.

[0127] After obtaining the first remote sensing image, the orthophoto image can be scaled up to the first level resolution, and features can be extracted from the scaled orthophoto image and the first remote sensing image. The specific steps can be referred to in S701-S703 above, which will not be repeated here. The matching rate sparse matrix of the scaled orthophoto image and the first remote sensing image is obtained, and the region with the highest matching degree is cropped based on the preset matching range to obtain the second remote sensing image.

[0128] As another possible implementation, the second resolution matching can also be sub-meter resolution matching. In step S203 above, the second resolution matching is performed based on the orthophoto and the first remote sensing image to obtain the matching result of the orthophoto in the first remote sensing image, including:

[0129] Based on the orthophoto and the first remote sensing image, a second-level resolution matching is performed to obtain the matching result of the orthophoto in the first remote sensing image, wherein the second-level resolution is greater than the first-level resolution.

[0130] Optionally, the second level of resolution can be sub-meter resolution. In this case, when cropping the first remote sensing image, the first remote sensing image can be cropped to a sub-meter resolution remote sensing image.

[0131] In this application, the first remote sensing image and the orthophoto image can be further matched, and two matching methods are provided: 10-meter resolution and sub-meter resolution. It should be understood that other resolution levels can also be matched between the first remote sensing image and the orthophoto image according to actual needs, and this application does not impose any restrictions on this.

[0132] The following is a further explanation of the matching results of the orthophoto image in the first remote sensing image, based on the second-level resolution matching of the orthophoto image and the first remote sensing image. Figure 8 As shown, this step includes:

[0133] S801: Based on the resolution and second-level resolution of the orthophoto, scale the orthophoto to obtain a scaled orthophoto.

[0134] Optionally, the second level of resolution can be sub-meter resolution, which can scale the orthophoto to sub-meter resolution to obtain a scaled orthophoto.

[0135] S802: Perform grayscale processing on the first remote sensing image and the scaled orthophoto to obtain a grayscale image of the first remote sensing image and a grayscale image of the scaled orthophoto.

[0136] S803: Extract features from the grayscale image of the first remote sensing image and the grayscale image of the scaled orthophoto image to obtain the grayscale features of the first remote sensing image and the grayscale features of the scaled orthophoto image.

[0137] In this application, grayscale processing can be performed on the first remote sensing image and the scaled orthophoto image respectively, and feature extraction can be performed on the grayscale images after grayscale processing. For example, the feature extraction method can be deep learning or SIFT method.

[0138] S804: Perform feature matching on the grayscale features of the first remote sensing image and the grayscale features of the scaled orthophoto image to obtain the first matching region between the grayscale features of the first remote sensing image and the grayscale features of the scaled orthophoto image.

[0139] Optionally, after obtaining the grayscale features of the first remote sensing image and the grayscale features of the scaled orthophoto, feature matching can be performed on the features of the two grayscale images to output a sparse matching rate matrix of the grayscale images of the first remote sensing image and the scaled orthophoto. Based on the sparse matching rate matrix, the first matching region is determined in the grayscale image of the first remote sensing image, that is, the region with the highest matching degree indicated by the sparse matching rate matrix.

[0140] S805: Extract features from the first remote sensing image and the scaled orthophoto to obtain the features of the first remote sensing image and the orthophoto image.

[0141] S806: Perform feature matching between the features of the first remote sensing image and the scaled orthophoto image to obtain the second matching region.

[0142] Grayscale images and color images can exhibit different features. Therefore, in this application, feature extraction and feature matching can also be performed on the color image to obtain a second matching region. The methods of feature extraction and feature matching can be referred to in S701-S703 above, and will not be elaborated here.

[0143] S807: Merge the first matching region and the second matching region to obtain the matching result of the orthophoto in the first remote sensing image.

[0144] Optionally, the first matching region and the second matching region can be merged. This can be done by finding the union of the first matching region and the second matching region, and using the region indicated by the union of the two as the matching result of the orthophoto in the first remote sensing image.

[0145] Based on the same inventive concept, this application also provides an orthophoto positioning device corresponding to the orthophoto positioning method. Since the principle of the device in this application is similar to that of the orthophoto positioning method described above, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0146] Reference Figure 9 The diagram shown is a schematic of an orthophoto positioning device provided in an embodiment of this application. The device includes: an acquisition module 901, a first matching module 902, a second matching module 903, and a determination module 904.

[0147] Acquisition module 901 is used to acquire orthophotos;

[0148] The first matching module 902 is used to perform a first resolution matching between the orthophoto and the historical remote sensing image to obtain a first remote sensing image that matches the orthophoto.

[0149] The second matching module 903 is used to perform second resolution matching based on the orthophoto and the first remote sensing image to obtain the matching result of the orthophoto in the first remote sensing image, wherein the second resolution is greater than the first resolution.

[0150] The determination module 904 is used to determine the location information corresponding to the orthophoto based on the matching result of the orthophoto.

[0151] Optionally, the first matching module 902 is specifically used for:

[0152] The height of the orthophoto is obtained by estimating its height.

[0153] The resolution of an orthophoto is determined based on its height.

[0154] Based on the resolution of the orthophoto and the first resolution, the orthophoto is scaled to obtain the scaled orthophoto.

[0155] Feature extraction is performed on the scaled orthophoto, and feature matching is performed between the extracted features and features from historical remote sensing images to obtain the first remote sensing image.

[0156] Optionally, the first matching module 902 is also specifically used for:

[0157] Based on the current altitude, the resolution of the orthophoto is estimated to obtain the predicted resolution.

[0158] The orthophoto is scaled based on the estimated resolution and the first resolution to obtain the scaled orthophoto.

[0159] Determine the matching degree between the scaled orthophoto and the historical remote sensing image, adjust the current height to obtain a new current height, and re-perform the step of estimating the resolution of the orthophoto based on the current height to obtain the estimated resolution. Obtain multiple matching degrees between the scaled image and the historical remote sensing image, and take the height of the historical remote sensing image with the highest matching degree as the height of the orthophoto.

[0160] Optionally, the first matching module 902 is also specifically used for:

[0161] The position of the virtual camera is determined based on the height of the orthophoto;

[0162] With the virtual camera in position, the camera's coverage area is determined based on the camera model's parameter information, which includes: camera parameters, camera focal length, and wide-angle information.

[0163] The resolution of the orthophoto is obtained by matching pixels according to the camera's coverage area.

[0164] Optionally, the first matching module 902 is also specifically used for:

[0165] Feature extraction is performed on the scaled orthophoto to obtain multiple features;

[0166] By performing feature matching between multiple features and multiple features of historical remote sensing images, a sparse matching rate matrix between the scaled orthophoto and historical remote sensing images is obtained. The sparse matching rate matrix is ​​used to characterize the matching degree of each region in the orthophoto and historical remote sensing images.

[0167] The region with the highest matching degree in the sparse matching rate matrix is ​​identified, and the region with the highest matching degree is cropped based on the matching range to obtain the first remote sensing image.

[0168] Optionally, the second matching module 903 is specifically used for:

[0169] Based on the orthophoto and the first remote sensing image, a first-level resolution matching is performed to obtain the second remote sensing image of the orthophoto within the first remote sensing image.

[0170] Optionally, the second matching module 903 is specifically used for:

[0171] Based on the orthophoto and the first remote sensing image, a second-level resolution matching is performed to obtain the matching result of the orthophoto in the first remote sensing image, wherein the second-level resolution is greater than the first-level resolution.

[0172] Optionally, the second matching module 903 is specifically used for:

[0173] Based on the resolution and second-level resolution of the orthophoto, the orthophoto is scaled to obtain a scaled orthophoto.

[0174] The first remote sensing image and the scaled orthophoto image are processed to obtain a grayscale image of the first remote sensing image and a grayscale image of the scaled orthophoto image.

[0175] Feature extraction is performed on the grayscale image of the first remote sensing image and the grayscale image of the scaled orthophoto image to obtain the grayscale image features of the first remote sensing image and the grayscale image features of the scaled orthophoto image.

[0176] Feature matching is performed on the grayscale features of the first remote sensing image and the grayscale features of the scaled orthophoto image to obtain the first matching region between the grayscale features of the first remote sensing image and the grayscale features of the scaled orthophoto image.

[0177] Feature extraction is performed on the first remote sensing image and the scaled orthophoto to obtain the features of the first remote sensing image and the features of the orthophoto image.

[0178] The second matching region is obtained by performing feature matching between the features of the first remote sensing image and the features of the scaled orthophoto image.

[0179] The first and second matching regions are merged to obtain the matching result of the orthophoto in the first remote sensing image.

[0180] The processing flow of each module in the device and the interaction flow between each module can be referred to the relevant descriptions in the above method embodiments, and will not be detailed here.

[0181] The embodiments of this application can improve the accuracy of the matching results by performing first resolution matching and second resolution matching. By performing multi-resolution matching on orthophotos and historical remote sensing images in Earth observation equipment, calibration and positioning based on baseline data can be achieved when signals are lost or third-party equipment positioning fails, thereby improving the overall analysis capability of the GIS system.

[0182] This application also provides an electronic device, such as... Figure 10 The diagram shown is a schematic representation of an electronic device structure provided in an embodiment of this application, including: a processor 1001, a memory 1002, and a bus. The memory 1002 stores machine-readable instructions executable by the processor 1001 (e.g., ...). Figure 9 The device includes the acquisition module 901, the first matching module 902, the second matching module 903, and the determination module 904 (and the corresponding execution instructions, etc.). When the computer device is running, the processor 1001 and the memory 1002 communicate via a bus. When the machine-readable instructions are executed by the processor 1001, the above-mentioned orthophoto positioning method is processed.

[0183] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the above-described orthophoto positioning method.

[0184] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and devices described above can be referred to the corresponding processes in the method embodiments, and will not be repeated here. In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, 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 displayed or discussed mutual coupling or direct coupling or communication connection can be through some communication interfaces; the indirect coupling or communication connection of devices or modules can be electrical, mechanical, or other forms.

[0185] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. If the functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0186] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A method for orthophoto localization, characterized in that, include: Obtain orthophotos; A first resolution match is performed between the orthophoto and historical remote sensing images to obtain a first remote sensing image that matches the orthophoto. Based on the orthophoto and the first remote sensing image, a second resolution matching is performed to obtain the matching result of the orthophoto in the first remote sensing image, wherein the second resolution is greater than the first resolution. The location information corresponding to the orthophoto is determined based on the matching result of the orthophoto; The step of performing a first resolution matching between the orthophoto and historical remote sensing images to obtain a first remote sensing image that matches the orthophoto includes: The height of the orthophoto is obtained by estimating its height. The resolution of the orthophoto is determined based on the height of the orthophoto. Based on the resolution of the orthophoto and the first resolution, the orthophoto is scaled to obtain a scaled orthophoto. Feature extraction is performed on the scaled orthophoto, and feature matching is performed between the extracted features and the features of the historical remote sensing image to obtain the first remote sensing image. The step of estimating the height of the orthophoto to obtain the height of the orthophoto includes: Based on the current altitude, the resolution of the orthophoto is estimated to obtain the predicted resolution. The orthophoto is scaled based on the estimated resolution and the first resolution to obtain a scaled orthophoto. Determine the matching degree between the scaled orthophoto and the historical remote sensing image, adjust the current height to obtain a new current height, and re-execute the step of estimating the resolution of the orthophoto based on the current height to obtain the estimated resolution. Obtain multiple matching degrees between the scaled orthophoto and the historical remote sensing image, and take the height of the historical remote sensing image with the highest matching degree as the height of the orthophoto.

2. The method according to claim 1, characterized in that, Determining the resolution of the orthophoto image based on its height includes: The position of the virtual camera is determined based on the height of the orthophoto; At the location of the virtual camera, the coverage area of ​​the camera is determined based on the parameter information of the virtual camera, which includes: camera parameters, camera focal length, and wide-angle information; The resolution of the orthophoto is obtained by matching pixels according to the coverage area of ​​the camera.

3. The method according to claim 1, characterized in that, The step of extracting features from the scaled orthophoto and matching the extracted features with features from the historical remote sensing image to obtain the first remote sensing image includes: Feature extraction is performed on the scaled orthophoto to obtain multiple features; The multiple features are matched with the multiple features of the historical remote sensing image to obtain a sparse matching rate matrix between the scaled orthophoto and the historical remote sensing image. The sparse matching rate matrix is ​​used to characterize the matching degree of each region in the orthophoto and the historical remote sensing image. The region with the highest matching degree in the sparse matching rate matrix is ​​determined, and the region with the highest matching degree is cropped based on the matching range to obtain the first remote sensing image.

4. The method according to claim 1, characterized in that, The step of performing a second resolution matching based on the orthophoto and the first remote sensing image to obtain the matching result of the orthophoto in the first remote sensing image includes: Based on the orthophoto and the first remote sensing image, a first-level resolution matching is performed to obtain a second remote sensing image of the orthophoto within the first remote sensing image.

5. The method according to claim 1, characterized in that, The step of performing a second resolution matching based on the orthophoto and the first remote sensing image to obtain the matching result of the orthophoto in the first remote sensing image includes: Based on the orthophoto and the first remote sensing image, a second-level resolution matching is performed to obtain the matching result of the orthophoto in the first remote sensing image, wherein the second-level resolution is greater than the first-level resolution.

6. The method according to claim 5, characterized in that, The step of performing a second-level resolution matching based on the orthophoto and the first remote sensing image to obtain the matching result of the orthophoto in the first remote sensing image includes: Based on the resolution of the orthophoto and the second-level resolution, the orthophoto is scaled to obtain a scaled orthophoto. The first remote sensing image and the scaled orthophoto image are subjected to grayscale processing to obtain a grayscale image of the first remote sensing image and a grayscale image of the scaled orthophoto image. Feature extraction is performed on the grayscale image of the first remote sensing image and the grayscale image of the scaled orthophoto image to obtain the grayscale image features of the first remote sensing image and the grayscale image features of the scaled orthophoto image. Feature matching is performed on the grayscale features of the first remote sensing image and the grayscale features of the scaled orthophoto image to obtain a first matching region between the grayscale features of the first remote sensing image and the grayscale features of the scaled orthophoto image. Feature extraction is performed on the first remote sensing image and the scaled orthophoto to obtain the features of the first remote sensing image and the features of the orthophoto image. The first remote sensing image features and the scaled orthophoto image features are matched to obtain the second matching region. The first matching region and the second matching region are merged to obtain the matching result of the orthophoto in the first remote sensing image.

7. An electronic device, characterized in that, include: The device includes a processor, a storage medium, and a bus. The storage medium stores program instructions executable by the processor. When the electronic device is running, the processor communicates with the storage medium via the bus. The processor executes the program instructions to perform the steps of the orthophoto positioning method as described in any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the orthophoto positioning method as described in any one of claims 1 to 6.

Images