Oblique image rectification method and device, electronic equipment and storage medium
By performing calculations on the equivalent downward-looking image to determine its attitude data and calculate the initial attitude of other tilted images, the problem of large computational load and high complexity in the existing technology is solved, and more efficient image data processing is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- AERIAL PHOTOGRAMMETRY & REMOTE SENSING CO LTD
- Filing Date
- 2023-07-14
- Publication Date
- 2026-06-19
AI Technical Summary
Existing methods for adjusting oblique images involve large computational demands, resulting in high requirements for computer processing hardware and high data processing complexity.
By first processing the equivalent downward-looking image to determine its target attitude data, then calculating the initial attitude data of other tilted images based on this attitude data, and finally combining the corresponding point data to obtain the target's geographical location, the grouping calculation of image data is realized.
It reduces computational complexity, improves computational efficiency, and reduces the time required to acquire the initial pose of other tilted images.
Smart Images
Figure CN116907448B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of remote sensing image technology, and more specifically, to an oblique image adjustment method, apparatus, electronic device, and storage medium. Background Technology
[0002] Oblique photogrammetry is an important technique in the field of surveying and mapping. It overcomes the limitation that orthophotos can only be taken from a vertical angle. By mounting multiple sensors (each with a different angle between its principal optical axis and the ground) on the same flight platform, it acquires multi-view images from multiple different angles, both vertical and oblique, while in flight. Since each sensor takes images from a different angle, oblique image adjustment is required to obtain the actual geographic coordinates of the objects captured by each sensor and the attitude data of each sensor at the time of capture.
[0003] The existing methods for adjusting oblique images mainly involve first performing image matching on the acquired oblique images to obtain corresponding point data, and then simultaneously performing adjustment processing on all the acquired corresponding point data to finally obtain the adjustment result of the oblique image.
[0004] However, existing tilt image adjustment methods involve large short-term computations, thus requiring advanced computer processing hardware and resulting in high data processing complexity. Summary of the Invention
[0005] The purpose of this application is to address the shortcomings of the prior art by providing a method, apparatus, electronic device, and storage medium for tilt image adjustment, thereby reducing computational complexity.
[0006] To achieve the above objectives, the technical solutions adopted in the embodiments of this application are as follows:
[0007] In a first aspect, embodiments of this application provide a method for adjusting oblique images, the method comprising:
[0008] Based on the multiple tilted images obtained at the target time, corresponding point data is extracted. The multiple tilted images include equivalent downward view image, forward view image, backward view image, left view image, and right view image. The corresponding point data is used to indicate the position coordinates of the same geographical location in each tilted image.
[0009] Based on the first initial attitude data corresponding to the equivalent downward view image and the data of each corresponding point, the first target attitude data corresponding to the equivalent downward view image is determined. The first initial attitude data is used to indicate the attitude of the camera corresponding to the equivalent downward view image at the target time.
[0010] Based on the first target attitude data and the installation position relationship between each camera, each second initial attitude data is determined. Each second initial attitude data is used to indicate the attitude of the camera corresponding to the front view image at the target time, the attitude of the camera corresponding to the rear view image at the target time, the attitude of the camera corresponding to the left view image at the target time, and the attitude of the camera corresponding to the right view image at the target time.
[0011] Based on each of the second initial attitude data and each corresponding point data, determine the target geographical location corresponding to each corresponding point data;
[0012] Based on the first target attitude data, each of the second initial attitude data, and each corresponding point data, the second target attitude data corresponding to each of the second initial attitude data is determined.
[0013] Optionally, the first initial attitude data includes the camera position coordinates and camera rotation angle of the camera corresponding to the equivalent downward view image at the target time;
[0014] The step of determining the first target pose data corresponding to the equivalent downward view image based on the first initial pose data corresponding to the equivalent downward view image and the data of each corresponding point includes:
[0015] The first attitude error corresponding to the equivalent downward view image is determined based on the camera position coordinates, camera rotation angle, and corresponding point data of the camera at the target time.
[0016] The first initial attitude data is corrected based on the first attitude error to obtain the first target attitude data.
[0017] Optionally, determining each second initial attitude data based on the first target attitude data and the installation position relationship between each camera includes:
[0018] Based on the installation position relationship between each camera, construct the rotation angle parameters and translation parameters corresponding to each second initial attitude data;
[0019] Based on the first target attitude data and the rotation angle parameters and translation parameters corresponding to each second initial attitude data, each second initial attitude data is determined.
[0020] Optionally, determining the target geographical location corresponding to each corresponding point based on each of the second initial attitude data and each corresponding point data includes:
[0021] Pair the data of each point with the same name into multiple pairs of points with the same name;
[0022] Based on each pair of points with the same name and each second initial attitude data, determine the intermediate geographic coordinates corresponding to each pair of points with the same name.
[0023] Based on the intermediate geographic coordinates corresponding to each pair of points with the same name, determine the target geographic coordinates corresponding to each data point with the same name.
[0024] Optionally, determining the intermediate geographic coordinates corresponding to each pair of corresponding points based on each pair of corresponding points and each second initial attitude data includes:
[0025] Based on each second initial pose data, construct the rotation matrix corresponding to each second initial pose data;
[0026] Based on the rotation matrix corresponding to each of the second initial attitude data and each pair of corresponding points, determine the intermediate geographic coordinates corresponding to each pair of corresponding points.
[0027] Optionally, determining the target geographic coordinates corresponding to each corresponding point data based on the intermediate geographic coordinates of each corresponding point pair includes:
[0028] The average of the intermediate geographic coordinates of each corresponding point is used to obtain the uncorrected geographic coordinates of each corresponding point data.
[0029] Using a preset error equation, calculate the position coordinate correction value corresponding to each corresponding point data;
[0030] The original geographic coordinates of each corresponding point are corrected based on the correction value corresponding to each corresponding point, so as to obtain the target geographic coordinates corresponding to each corresponding point data.
[0031] Optionally, based on each of the second initial attitude data and each corresponding point data, the second target attitude data corresponding to each of the second initial attitude data is determined, including:
[0032] Using a preset error equation, calculate the attitude correction value corresponding to each corresponding point data under each second initial attitude data.
[0033] Based on the attitude correction values corresponding to each corresponding point data under each second initial attitude data, the second initial attitude data are corrected to obtain the second target attitude data corresponding to each second initial attitude data.
[0034] Secondly, embodiments of this application also provide an oblique image adjustment device, the device comprising:
[0035] The extraction module is used to extract corresponding point data from multiple oblique images acquired at the target time. The multiple oblique images include equivalent downward view image, forward view image, backward view image, left view image, and right view image. The corresponding point data is used to indicate the position coordinates of the same geographical location in each oblique image.
[0036] The determining module is used to determine the first target attitude data corresponding to the equivalent downward view image based on the first initial attitude data corresponding to the equivalent downward view image and the corresponding point data. The first initial attitude data is used to indicate the attitude of the camera corresponding to the equivalent downward view image at the target time.
[0037] The determination module is used to determine each second initial attitude data according to the first target attitude data and the installation position relationship between each camera. Each second initial attitude data is used to indicate the attitude of the camera corresponding to the front view image at the target time, the attitude of the camera corresponding to the rear view image at the target time, the attitude of the camera corresponding to the left view image at the target time, and the attitude of the camera corresponding to the right view image at the target time.
[0038] The determination module is used to determine the target geographical location corresponding to each corresponding point data based on the first target attitude data, each second initial attitude data, and each corresponding point data.
[0039] The determination module is used to determine the second target attitude data corresponding to each second initial attitude data based on each second initial attitude data and each corresponding point data.
[0040] Optionally, the first initial attitude data includes the camera position coordinates and camera rotation angle of the camera corresponding to the equivalent downward view image at the target time;
[0041] The determining module is specifically used for:
[0042] The first attitude error corresponding to the equivalent downward view image is determined based on the camera position coordinates, camera rotation angle, and corresponding point data of the camera at the target time.
[0043] The first initial attitude data is corrected based on the first attitude error to obtain the first target attitude data.
[0044] Optionally, the determining module is specifically used for:
[0045] Based on the installation position relationship between each camera, construct the rotation angle parameters and translation parameters corresponding to each second initial attitude data;
[0046] Based on the first target attitude data and the rotation angle parameters and translation parameters corresponding to each second initial attitude data, each second initial attitude data is determined.
[0047] Optionally, the determining module is specifically used for:
[0048] Pair the data of each point with the same name into multiple pairs of points with the same name;
[0049] Based on each pair of points with the same name and each second initial attitude data, determine the intermediate geographic coordinates corresponding to each pair of points with the same name.
[0050] Based on the intermediate geographic coordinates corresponding to each pair of points with the same name, determine the target geographic coordinates corresponding to each data point with the same name.
[0051] Optionally, the determining module is specifically used for:
[0052] Based on each second initial pose data, construct the rotation matrix corresponding to each second initial pose data;
[0053] Based on the rotation matrix corresponding to each of the second initial attitude data and each pair of corresponding points, determine the intermediate geographic coordinates corresponding to each pair of corresponding points.
[0054] Optionally, the determining module is specifically used for:
[0055] The average of the intermediate geographic coordinates of each corresponding point is used to obtain the uncorrected geographic coordinates of each corresponding point data.
[0056] Using a preset error equation, calculate the position coordinate correction value corresponding to each corresponding point data;
[0057] The original geographic coordinates of each corresponding point are corrected based on the correction value corresponding to each corresponding point, so as to obtain the target geographic coordinates corresponding to each corresponding point data.
[0058] Optionally, the determining module is specifically used for:
[0059] Using a preset error equation, calculate the attitude correction value corresponding to each corresponding point data under each second initial attitude data.
[0060] Based on the attitude correction values corresponding to each corresponding point data under each second initial attitude data, the second initial attitude data are corrected to obtain the second target attitude data corresponding to each second initial attitude data.
[0061] Thirdly, embodiments of this application also provide an electronic device, including: a processor, a storage medium, and a bus, wherein the storage medium stores program instructions executable by the processor, and when the application runs, the processor communicates with the storage medium via the bus, and the processor executes the program instructions to perform the steps of the tilt image adjustment method described in the first aspect above.
[0062] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which is read and executes the steps of the tilt image adjustment method described in the first aspect.
[0063] The beneficial effects of this application are:
[0064] This application provides a method, apparatus, electronic device, and storage medium for adjusting oblique images. It first processes the data corresponding to the equivalent downward-looking image, then calculates the initial attitude data of other oblique images at the target time based on the calculated target attitude data under the equivalent downward-looking image. Finally, it obtains the target geographical location of each corresponding point based on the initial attitude data of each oblique image and the corresponding point data. This allows for grouped calculation of image data, avoiding the inefficiency caused by simultaneously calculating large amounts of data. Furthermore, calculating the initial attitude data of other oblique images using the target attitude data of the equivalent downward-looking image significantly reduces the time required to obtain the initial attitude data of other oblique images, thereby effectively improving computational efficiency. Attached Figure Description
[0065] 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.
[0066] Figure 1 A schematic flowchart of an oblique image adjustment method provided in an embodiment of this application;
[0067] Figure 2 A flowchart illustrating another oblique image adjustment method provided in this application embodiment;
[0068] Figure 3 A flowchart illustrating another oblique image adjustment method provided in this application embodiment;
[0069] Figure 4 A schematic diagram of an apparatus for a tilted image adjustment method provided in an embodiment of this application;
[0070] Figure 5 This is a structural block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation
[0071] 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.
[0072] 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.
[0073] 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.
[0074] Image maps are maps created using aerial photographs or satellite remote sensing imagery. Through geometric correction, projection transformation, and scale normalization, and employing specific map symbols and annotations, they directly reflect the geographical features and spatial distribution of the mapped object. Image maps combine the advantages of both remote sensing imagery and line maps, containing the rich content information of remote sensing imagery while ensuring the accuracy and geometric precision of topographic maps. However, remote sensing imagery is often affected by various error sources during the imaging process, such as errors in the trajectory and attitude measurements during photography, and distortions in the image's internal orientation elements. These positioning errors result in lower positioning accuracy in image maps during production, affecting the accuracy of large-area mapping.
[0075] This application provides an adjustment method for oblique images, which realizes the correction of images and ensures the geometric accuracy of the map.
[0076] Figure 1 This is a flowchart illustrating a method for adjusting oblique images provided in an embodiment of this application, as shown below. Figure 1 As shown, the method includes:
[0077] S101. Extract corresponding point data from multiple oblique images obtained at the target time.
[0078] Optionally, the oblique imagery can be images acquired simultaneously from different angles, such as a vertical view and four side views, by multiple sensors mounted on a flight platform. This provides four additional oblique shooting angles compared to traditional photogrammetry, thus allowing for the acquisition of richer information such as side textures. For example, an oblique aerial camera is a five-lens camera integrating a downward-looking camera and multiple oblique cameras. These oblique cameras can include a forward-looking camera, a rear-looking camera, a left-looking camera, and a right-looking camera. Images captured at the target time using the downward-looking, forward-looking, rear-looking, left-looking, and right-looking cameras can be considered as multiple oblique images. These multiple oblique images can then include equivalent downward-looking images, forward-looking images, rear-looking images, left-looking images, and right-looking images.
[0079] Optionally, when photographing a certain feature, the corresponding image points of the same feature can be captured in different oblique images. Therefore, when multiple oblique images are acquired, feature matching can be performed to obtain the corresponding point data of the multiple oblique images. The corresponding point data is used to indicate the position coordinates of the same geographical location in each oblique image. These position coordinates are also the position coordinates of the image points corresponding to the same geographical location in each oblique image.
[0080] S102. Determine the first target attitude data corresponding to the equivalent downward view image based on the first initial attitude data and the data of each corresponding point.
[0081] The first initial attitude data is used to indicate the attitude of the camera corresponding to the equivalent downward view image at the target time, that is, the camera attitude of the equivalent downward view camera when it captures the equivalent downward view image at the target time.
[0082] Optionally, the first initial attitude data of the equivalent downward view image can be corrected using a preset method based on the first initial attitude data corresponding to the equivalent downward view image and the data of each corresponding point, so as to obtain the first target attitude data corresponding to the equivalent downward view image.
[0083] S103. Based on the first target attitude data and the installation position relationship between each camera, determine the second initial attitude data respectively.
[0084] Optionally, once the first target attitude data corresponding to the equivalent downward-looking image at the target time is determined, the second initial attitude data corresponding to each of the other tilting cameras at the target time can be determined based on the installation position relationship between the equivalent downward-looking camera and each of the other tilting cameras at the target time.
[0085] The second initial attitude data are used to indicate the attitude of the camera corresponding to the forward-looking image at the target time, the attitude of the camera corresponding to the rear-looking image at the target time, the attitude of the camera corresponding to the left-looking image at the target time, and the attitude of the camera corresponding to the right-looking image at the target time.
[0086] S104. Based on the second initial attitude data and the corresponding point data, determine the target geographical location corresponding to each corresponding point data.
[0087] Optionally, a preset method can be used to determine the target geographical location corresponding to each corresponding point based on each second initial attitude data and each corresponding point data, wherein the target geographical location is the actual geographical location coordinates of each corresponding point on the actual geographical map.
[0088] S105. Based on the first target attitude data, each second initial attitude data, and each corresponding point data, determine the second target attitude data corresponding to each second initial attitude data.
[0089] Optionally, the corresponding point data are the corresponding point data that match the images captured by the camera under the first target pose data and the images captured by the camera under each second initial pose data. For example, the corresponding point data that matches the images captured by the equivalent downward-looking camera and the images captured by the left-looking camera; the corresponding point data that matches the images captured by the equivalent downward-looking camera and the images captured by the right-looking camera; the corresponding point data that matches the images captured by the equivalent downward-looking camera and the images captured by the front-looking camera; the corresponding point data that matches the images captured by the equivalent downward-looking camera and the images captured by the rear-looking camera.
[0090] Optionally, the first target attitude data can be used as control data. Based on each second initial attitude data and each corresponding point data, an adjustment calculation is performed on each second initial attitude data using a preset method to obtain the adjustment calculation result, wherein the adjustment calculation result is the second target attitude data corresponding to each second initial attitude data.
[0091] In the above steps S102-S105, the second target attitude data and the target geographical location corresponding to each corresponding point data can be calculated based on the calculation method of regional network adjustment. The obtained second target attitude data and the target geographical location corresponding to each corresponding point data are the calculation results obtained by the oblique image adjustment method of this application.
[0092] In this embodiment, the data corresponding to the equivalent downward-looking image is first processed and calculated. Then, based on the target attitude data obtained from the equivalent downward-looking image, the initial attitude data of each other oblique image at the target time is calculated. Finally, the target geographical location of each corresponding point is obtained based on the initial attitude data of each oblique image and the corresponding point data. This allows for grouped calculation of image data, avoiding the need to calculate a large amount of data simultaneously, which would lead to low computational efficiency. Furthermore, calculating the initial attitude data of each other oblique image using the target attitude data from the equivalent downward-looking image can significantly reduce the time required to obtain the initial attitude of other oblique images, thereby effectively improving computational efficiency.
[0093] Figure 2 A schematic flowchart of another oblique image adjustment method provided in this application embodiment is shown below. Figure 2 As shown, in step S102 above, determining the first target attitude data corresponding to the equivalent downward-looking image based on the first initial attitude data corresponding to the equivalent downward-looking image and the corresponding point data may include:
[0094] Optionally, the first initial attitude data may include the camera position coordinates of the camera corresponding to the equivalent downward-looking image at the target time and the camera's rotation angle. The camera position coordinates of the camera corresponding to the equivalent downward-looking image at the target time are the spatial position coordinates of the camera at that moment when it was taking the picture; for example, (X...) can be used. x Y s Z s The rotation angle of a camera can be represented by (φ, ω, k), which indicates the rotation angle of the camera in the x, y, and z directions, respectively.
[0095] S201. Determine the first attitude error corresponding to the equivalent downward view based on the camera position, camera rotation angle, and corresponding point data of the camera at the target time corresponding to the equivalent downward view image.
[0096] The first attitude error is the error value of the calculated camera position coordinates and rotation angle. Specifically, it can be calculated according to formula (I), which is as follows:
[0097] V x =At+BX-L x Formula (1)
[0098] Among them, V x Let t be the correction for the coordinates of each corresponding point, where t = [Δφ Δω Δk ΔX]. x ΔY s ΔZ sLet t be the error value of each element of the camera's position coordinates and rotation angle, which is also the first attitude error. X = [ΔX ΔY ΔZ], where X is the error value of the geographic coordinates corresponding to the same point, A is the coefficient matrix corresponding to the correction values of each element in the camera position and camera rotation angle corresponding to the equivalent downward-looking image, and B is the coefficient matrix corresponding to the correction values of the geographic coordinates corresponding to the same point data. The first attitude error t can be calculated from the coefficient matrices A and B.
[0099] Optionally, the geographic coordinates corresponding to the same point data can be calculated using formula (II), as follows:
[0100] x i =-f[a1(XX s )+b1(YY s )+c1(ZZ s )] / [a3(XX s )+b3(YY s )+c3(ZZ s )]
[0101] y i =-f[a2(XX s )+b2(YY s )+c2(ZZ s )] / [a3(XX s )+b3(YY s )+c3(ZZ s )]
[0102] Formula (II)
[0103] Where, x i y i For the coordinates of the corresponding points, X x Y s Z s Let X, Y, and Z be the equivalent position coordinates of the downward-looking camera during shooting, and a1, a2, and a3 be the geographic coordinates corresponding to the corresponding point data. The geographic coordinates X, Y, and Z of the corresponding points are calculated using formula (II).
[0104] S202. Correct the first initial attitude data according to the first attitude error to obtain the first target attitude data.
[0105] Optionally, after calculating the error values of each element of the camera's position coordinates and rotation angle in S201, which is the first attitude error, each coordinate element can be corrected according to the error values of each coordinate element in the camera's position coordinates, and each angle element of the camera can be corrected according to the error values of each angle element in the camera's rotation angle, so as to obtain the first target attitude data corresponding to the equivalent downward view image.
[0106] For example, for the position coordinate X in the camera's first initial pose data x Y s Z s The calculated ΔX can be used x ΔY s ΔZ s For X respectively x Y s Z s The corrected position coordinates are then used as the position coordinate data in the first target attitude data; the rotation angle in the first initial attitude data... ω and k can be obtained through calculation. Δω and Δk are used to correct each angle, and the corrected rotation angles are used as the rotation angle data in the first target attitude data.
[0107] In this embodiment, by first performing calculations on the image data under the equivalent downward view image, the amount of data that needs to be calculated simultaneously can be reduced.
[0108] Optionally, determining the second initial attitude data in S103 based on the first target attitude data and the installation position relationship between the cameras may include:
[0109] Optionally, rotation angle parameters and translation parameters corresponding to each second initial attitude data are constructed based on the installation position relationship between each camera. Each second initial attitude data represents the attitude of the camera corresponding to each other tilted image at the target time. At the target time, the cameras corresponding to each other tilted image and the camera corresponding to the equivalent downward-looking image have an installation position relationship within a defined plane. Based on this installation position relationship, the rotation angle parameters and translation parameters of each other tilted image relative to the camera corresponding to the equivalent downward-looking image can be determined.
[0110] Optionally, if the installation position relationship between the camera corresponding to each other tilted image and the camera corresponding to the equivalent downward view image is known, the rotation angle parameters and translation parameters of each other tilted image relative to the camera corresponding to the equivalent downward view image can be directly obtained based on the installation data.
[0111] Optionally, if the installation position relationship between the camera corresponding to each other tilted image and the camera corresponding to the equivalent downward view image is unknown, the rotation angle parameter and translation parameter of each other tilted image relative to the camera corresponding to the equivalent downward view image can be automatically calculated using the matching information between each other tilted image and the equivalent downward view image.
[0112] Optionally, each second initial attitude data is determined based on the first target attitude data, the rotation angle parameters corresponding to each second initial attitude data, and the translation parameters.
[0113] Among them, the rotation angle parameter is the change parameter of the camera rotation angle corresponding to each other tilted image relative to the camera rotation angle corresponding to the equivalent downward view image; the translation parameter is the translation parameter of the change of the position of the camera corresponding to each other tilted image relative to the camera corresponding to the equivalent downward view image in different directions, for example, represented by dx, dy, dz.
[0114] Specifically, the translation parameters can be added to or subtracted from the camera position coordinates in the first target attitude data to obtain the camera position coordinates in the second initial attitude data; the rotation angle parameters can be added to or subtracted from the camera rotation angle in the first target attitude data to obtain the camera rotation angle in the second initial attitude data.
[0115] In this embodiment, the initial attitude data of other tilted images are calculated by using the camera attitude data of the equivalent downward view image, which can realize the group calculation of data and reduce the time used to obtain the initial value of the tilted image.
[0116] Figure 3 This is a flowchart illustrating another oblique image adjustment method provided in an embodiment of this application, as shown below. Figure 3 As shown, in step S104 above, determining the target geographical location corresponding to each corresponding point data based on each second initial attitude data and each corresponding point data may include:
[0117] S301. Pair the data of each point with the same name to form multiple pairs of points with the same name.
[0118] The corresponding point data indicates the image point coordinates of the same object captured by the camera corresponding to each tilted image at the target time. These corresponding point data captured by the camera corresponding to each tilted image at the target time can be considered as a set of corresponding point data. If the camera captures an image only once at the target time, five corresponding point data points can be obtained at that target time.
[0119] Optionally, the target geographic location corresponding to corresponding points can be calculated using the forward intersection of multiple imagery. Specifically, each corresponding point in each group can be paired up. If the data of each corresponding point in each group is {(x1, y1), ..., (x...i y i )}, i = 1…n, where n is the number of corresponding data points in each group, which can be used By pairing elements in various permutations and combinations, each pair of elements with the same name can be used to represent the elements in {(x)}. j y j ), (x k y k )} is used to represent.
[0120] S302. Based on each pair of points with the same name and each second initial attitude data, determine the intermediate geographic coordinates corresponding to each pair of points with the same name.
[0121] Each of the second initial attitude data is used to indicate the attitude of the camera corresponding to each tilted image at the target time. The intermediate geographic coordinates corresponding to each pair of corresponding points under each second initial attitude data can be determined using a preset method based on each pair of corresponding points and each of the second initial attitude data.
[0122] S303. Based on the intermediate geographic coordinates corresponding to the same point pairs, determine the target geographic coordinates corresponding to each same point data.
[0123] Optionally, based on the intermediate geographic coordinates corresponding to the multiple pairs of corresponding points calculated in S302 above, a preset method is used to calculate the target geographic coordinates corresponding to each pair of corresponding points under each second initial attitude data at the target time.
[0124] In this embodiment, by matching the corresponding points at the target time, the intermediate geographic coordinates of each pair of corresponding points are calculated, and finally the target geographic coordinates corresponding to each pair of corresponding points are obtained. The method of forward intersection of multiple images can make the calculated geographic coordinates corresponding to each pair of corresponding points more accurate. Furthermore, the corresponding point data of each second initial attitude data can be grouped and calculated simultaneously, which greatly reduces the time for calculating the geographic coordinates corresponding to each pair of corresponding points and effectively improves the calculation efficiency.
[0125] Optionally, determining the intermediate geographic coordinates corresponding to each pair of points based on each pair of corresponding points and each second initial attitude data in S302 above may include:
[0126] Optionally, a rotation matrix corresponding to each second initial pose data is constructed based on each second initial pose data.
[0127] Optionally, each second initial attitude data includes the camera rotation angle data corresponding to each tilted image at the target time, for example, using... ω and k represent the rotation angles of the camera in different directions corresponding to each tilted image.
[0128] Specifically, the rotation matrix corresponding to each second initial pose data can be: The parameters in the rotation matrix R are calculated from the rotation angles in each of the second initial attitude data.
[0129] Optionally, the intermediate geographic coordinates corresponding to each pair of corresponding points can be determined based on the rotation matrix corresponding to each second initial attitude data and each pair of corresponding points.
[0130] Optionally, the intermediate geographic coordinates corresponding to each pair of corresponding points can be calculated using formula (ii) above. Specifically, the coordinates of each corresponding point in each pair, the parameters in the rotation matrix of each second initial attitude data, and the camera position coordinates in each second initial attitude data can be substituted into formula (ii) above to obtain the intermediate geographic coordinates corresponding to each pair of corresponding points. For example, (X... jk Y jk Z jk ), where j and k represent the sequence numbers corresponding to the corresponding points in each pair of points.
[0131] Optionally, in S303 above, determining the target geographic coordinates corresponding to each corresponding point data based on the intermediate geographic coordinates of the corresponding point pairs includes:
[0132] Optionally, the intermediate geographic coordinates of each corresponding point can be averaged to obtain the original geographic coordinates of each corresponding point.
[0133] Specifically, it can be used This indicates that m is the number of pairs of corresponding points in each group, and the geographic coordinates obtained by averaging the intermediate geographic coordinates corresponding to each pair of corresponding points are used as the pre-correction geographic coordinates of each corresponding point data.
[0134] Optionally, an error equation can be used to calculate the location coordinate correction value corresponding to each corresponding point data. The location coordinate correction value is the correction value applied to each coordinate in different directions within the location coordinates. Specifically, the location coordinate correction value corresponding to each corresponding point data can be obtained using the above formula (i), and the original geographic coordinates of each corresponding point can be corrected based on the calculated location coordinate correction value to obtain the target geographic coordinates corresponding to each corresponding point data.
[0135] When calculating the position coordinate correction value corresponding to each corresponding point according to formula (I), V in formula (I) x L is the correction value for the coordinates of each corresponding point. xLet X = [ΔX ΔY ΔZ], where X represents the corrected geographic coordinates of each corresponding point. Let A be the coefficient matrix corresponding to the corrections for each element in the camera position and camera rotation angle for each oblique image, and B be the coefficient matrix corresponding to the corrections for the geographic coordinates of each corresponding point. The corrected position coordinates of each corresponding point can be calculated from the coefficient matrices A and B.
[0136] Optionally, the aforementioned first target attitude data, based on each second initial attitude data and each corresponding point data, respectively determine the second target attitude data corresponding to each second initial attitude data, including:
[0137] Optionally, a preset error equation can be used to calculate the attitude correction value corresponding to each corresponding point data under each initial attitude data. Specifically, it can be calculated using the above formula (I), such as t=[ΔφΔωΔkΔX x ΔY s ΔZ s The correction value t can be calculated based on the coefficient matrix A and the coefficient matrix B, where A is the coefficient matrix corresponding to the correction values of each element in the camera position and camera rotation angle corresponding to each tilted image, and B is the coefficient matrix corresponding to the correction values of the geographic coordinates corresponding to each corresponding point data.
[0138] Optionally, each second initial attitude data is corrected based on the attitude correction value corresponding to each corresponding point data under each second initial attitude data to obtain the second target attitude data corresponding to each second initial attitude data.
[0139] Figure 4 A schematic diagram of an apparatus for a tilted image adjustment method provided in an embodiment of this application is shown below. Figure 4 As shown, the device includes:
[0140] The extraction module 401 is used to extract corresponding point data based on multiple tilted images acquired at the target time. The multiple tilted images include equivalent downward view image, forward view image, backward view image, left view image, and right view image. The corresponding point data is used to indicate the position coordinates of the same geographical location in each tilted image.
[0141] The determining module 402 is used to determine the first target attitude data corresponding to the equivalent downward view image based on the first initial attitude data corresponding to the equivalent downward view image and the corresponding point data. The first initial attitude data is used to indicate the attitude of the camera corresponding to the equivalent downward view image at the target time.
[0142] The determining module 402 is used to determine each second initial attitude data according to the first target attitude data and the installation position relationship between each camera. Each second initial attitude data is used to indicate the attitude of the camera corresponding to the front view image at the target time, the attitude of the camera corresponding to the rear view image at the target time, the attitude of the camera corresponding to the left view image at the target time, and the attitude of the camera corresponding to the right view image at the target time.
[0143] The determination module 402 is used to determine the target geographical location corresponding to each corresponding point data based on each of the second initial attitude data and each corresponding point data.
[0144] The determination module 402 is used to determine the second target attitude data corresponding to each second initial attitude data based on each second initial attitude data and each corresponding point data.
[0145] Optionally, the first initial attitude data includes the camera position coordinates and camera rotation angle of the camera corresponding to the equivalent downward view image at the target time;
[0146] Module 402 is specifically used for:
[0147] The first attitude error corresponding to the equivalent downward view image is determined based on the camera position coordinates, camera rotation angle, and corresponding point data of the camera at the target time.
[0148] The first initial attitude data is corrected based on the first attitude error to obtain the first target attitude data.
[0149] Optionally, module 402 is specifically used for:
[0150] Based on the installation position relationship between each camera, construct the rotation angle parameters and translation parameters corresponding to each second initial attitude data;
[0151] Based on the first target attitude data and the rotation angle parameters and translation parameters corresponding to each second initial attitude data, each second initial attitude data is determined.
[0152] Optionally, module 402 is specifically used for:
[0153] Pair the data of each point with the same name into multiple pairs of points with the same name;
[0154] Based on each pair of points with the same name and each second initial attitude data, determine the intermediate geographic coordinates corresponding to each pair of points with the same name.
[0155] Based on the intermediate geographic coordinates corresponding to each pair of points with the same name, determine the target geographic coordinates corresponding to each data point with the same name.
[0156] Optionally, the determined module 402 is specifically used for:
[0157] Based on each second initial pose data, construct the rotation matrix corresponding to each second initial pose data;
[0158] Based on the rotation matrix corresponding to each of the second initial attitude data and each pair of corresponding points, determine the intermediate geographic coordinates corresponding to each pair of corresponding points.
[0159] Optionally, module 402 is specifically used for:
[0160] The average of the intermediate geographic coordinates of each corresponding point is used to obtain the uncorrected geographic coordinates of each corresponding point data.
[0161] Using a preset error equation, calculate the position coordinate correction value corresponding to each corresponding point data;
[0162] The original geographic coordinates of each corresponding point are corrected based on the correction value corresponding to each corresponding point, so as to obtain the target geographic coordinates corresponding to each corresponding point data.
[0163] Optionally, module 402 is specifically used for:
[0164] Using a preset error equation, calculate the attitude correction value corresponding to each corresponding point data under each second initial attitude data.
[0165] Based on the attitude correction values corresponding to each corresponding point data under each second initial attitude data, the second initial attitude data are corrected to obtain the second target attitude data corresponding to each second initial attitude data.
[0166] Figure 5 A structural block diagram of an electronic device 500 provided in this application embodiment is shown below. Figure 5 As shown, the electronic device may include: processor 501 and memory 502.
[0167] Optionally, a bus 503 may also be included, wherein the memory 502 is used to store machine-readable instructions executable by the processor 501. When the electronic device 500 is running, the processor 501 and the memory 502 communicate via the bus 503. When the machine-readable instructions are executed by the processor 501, the method steps in the above method embodiments are performed.
[0168] This application also provides a computer-readable storage medium storing a computer program, which, when run by a processor, executes the method steps described in the above-described tilted image adjustment method embodiment.
[0169] 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.
[0170] 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 application, in essence, or the part that contributes to the prior art, or 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 application. The aforementioned storage medium includes: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.
[0171] 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 adjusting an oblique image, characterized by, The method includes: Based on the multiple tilted images obtained at the target time, corresponding point data is extracted. The multiple tilted images include equivalent downward view image, forward view image, backward view image, left view image, and right view image. The corresponding point data is used to indicate the position coordinates of the same geographical location in each tilted image. Based on the first initial attitude data corresponding to the equivalent downward view image and the data of each corresponding point, the first target attitude data corresponding to the equivalent downward view image is determined. The first initial attitude data is used to indicate the attitude of the camera corresponding to the equivalent downward view image at the target time. The first initial attitude data includes the camera position coordinates and the camera rotation angle of the camera corresponding to the equivalent downward view image at the target time. Based on the first target attitude data and the installation position relationship between each camera, each second initial attitude data is determined. Each second initial attitude data is used to indicate the attitude of the camera corresponding to the front view image at the target time, the attitude of the camera corresponding to the rear view image at the target time, the attitude of the camera corresponding to the left view image at the target time, and the attitude of the camera corresponding to the right view image at the target time. Based on each of the second initial attitude data and each corresponding point data, determine the target geographical location corresponding to each corresponding point data; Based on the first target attitude data, each of the second initial attitude data and each corresponding point data, the second target attitude data corresponding to each second initial attitude data is determined respectively. The step of determining each second initial attitude data based on the first target attitude data and the installation position relationship between each camera includes: Based on the installation position relationship between each camera, construct the rotation angle parameters and translation parameters corresponding to each second initial attitude data; Based on the first target attitude data and the rotation angle parameters and translation parameters corresponding to each second initial attitude data, determine each second initial attitude data; The step of determining the target geographical location corresponding to each corresponding point based on each of the second initial attitude data and each corresponding point data includes: Pair the data of each point with the same name into multiple pairs of points with the same name; Based on each pair of points with the same name and each second initial attitude data, determine the intermediate geographic coordinates corresponding to each pair of points with the same name. Based on the intermediate geographic coordinates corresponding to each pair of points with the same name, determine the target geographic coordinates corresponding to each data point with the same name.
2. The tilt image adjustment method according to claim 1, characterized in that, The step of determining the first target pose data corresponding to the equivalent downward view image based on the first initial pose data corresponding to the equivalent downward view image and the data of each corresponding point includes: The first attitude error corresponding to the equivalent downward view image is determined based on the camera position coordinates, camera rotation angle, and corresponding point data of the camera at the target time. The first initial attitude data is corrected based on the first attitude error to obtain the first target attitude data.
3. The method of claim 1, wherein, The step of determining the intermediate geographic coordinates corresponding to each pair of points based on the corresponding point pairs and the second initial pose data includes: Based on each second initial pose data, construct the rotation matrix corresponding to each second initial pose data; Based on the rotation matrix corresponding to each of the second initial attitude data and each pair of corresponding points, determine the intermediate geographic coordinates corresponding to each pair of corresponding points.
4. The method of claim 1, wherein, The step of determining the target geographic coordinates corresponding to each corresponding point data based on the intermediate geographic coordinates of each corresponding point pair includes: The average of the intermediate geographic coordinates of each corresponding point is used to obtain the uncorrected geographic coordinates of each corresponding point data. Using a preset error equation, calculate the position coordinate correction value corresponding to each corresponding point data; The original geographic coordinates of each corresponding point are corrected based on the correction value corresponding to each corresponding point, so as to obtain the target geographic coordinates corresponding to each corresponding point data.
5. The method of claim 1, wherein, Based on each of the second initial attitude data and each corresponding point data, the second target attitude data corresponding to each of the second initial attitude data is determined, including: Using a preset error equation, calculate the attitude correction value corresponding to each corresponding point data under each second initial attitude data. Based on the attitude correction values corresponding to each corresponding point data under each second initial attitude data, the second initial attitude data are corrected to obtain the second target attitude data corresponding to each second initial attitude data.
6. A device for rectifying oblique images, characterized in that include: The extraction module is used to extract corresponding point data from multiple oblique images acquired at the target time. The multiple oblique images include equivalent downward view image, forward view image, backward view image, left view image, and right view image. The corresponding point data is used to indicate the position coordinates of the same geographical location in each oblique image. The determining module is used to determine the first target attitude data corresponding to the equivalent downward view image based on the first initial attitude data corresponding to the equivalent downward view image and the corresponding point data. The first initial attitude data is used to indicate the attitude of the camera corresponding to the equivalent downward view image at the target time. The first initial attitude data includes the camera position coordinates and the camera rotation angle of the camera corresponding to the equivalent downward view image at the target time. The determination module is used to determine each second initial attitude data according to the first target attitude data and the installation position relationship between each camera. Each second initial attitude data is used to indicate the attitude of the camera corresponding to the front view image at the target time, the attitude of the camera corresponding to the rear view image at the target time, the attitude of the camera corresponding to the left view image at the target time, and the attitude of the camera corresponding to the right view image at the target time. The determination module is used to determine the target geographical location corresponding to each corresponding point data based on each of the second initial attitude data and each corresponding point data. The determination module is used to determine the second target attitude data corresponding to each second initial attitude data based on the first target attitude data, each second initial attitude data and each corresponding point data. The determining module is specifically used for: Based on the installation position relationship between each camera, construct the rotation angle parameters and translation parameters corresponding to each second initial attitude data; Based on the first target attitude data and the rotation angle parameters and translation parameters corresponding to each second initial attitude data, determine each second initial attitude data; The determining module is specifically used for: Pair the data of each point with the same name into multiple pairs of points with the same name; Based on each pair of points with the same name and each second initial attitude data, determine the intermediate geographic coordinates corresponding to each pair of points with the same name. Based on the intermediate geographic coordinates corresponding to each pair of points with the same name, determine the target geographic coordinates corresponding to each data point with the same name.
7. An electronic device, comprising: It includes a memory and a processor, the memory storing a computer program executable by the processor, the processor executing the computer program to implement the steps of the tilt image adjustment method according to any one of claims 1-5.
8. A computer-readable storage medium, characterized in that, The computer-readable storage medium contains a computer program that, when executed by a processor, performs the steps of the tilt image adjustment method as described in any one of claims 1-5.