Unmanned aerial vehicle image real-time correction method, system and device and storage medium

Abstract

The invention provides an unmanned aerial vehicle image real-time correction method, system and device and a storage medium, and relates to the technical field of image correction, and the method comprises the steps: obtaining the camera pose information, image information and shooting space information of an unmanned aerial vehicle image; performing image distortion correction on the unmanned aerial vehicle image based on the camera pose information and the image information of the unmanned aerial vehicle image to obtain a distortion-corrected unmanned aerial vehicle image; and performing geometric correction on the unmanned aerial vehicle image subjected to distortion correction based on the camera pose information, the image information and the camera shooting space information of the unmanned aerial vehicle image so as to obtain an unmanned aerial vehicle image subjected to geometric correction. According to the invention, image distortion correction and geometric correction are carried out on the unmanned aerial vehicle image according to the camera pose information, the image information and the photography space information of the unmanned aerial vehicle image, so that the problem of large image correction error caused by a non-system due to uncontrollable non-system factors in real-time image correction of an existing unmanned aerial vehicle is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of image correction, and in particular to a method, system, device and storage medium for real-time correction of unmanned aerial vehicle images. Background Art

[0002] Correcting an image is the process of calculating the new coordinates of each pixel in the corrected image. This can be achieved through a transformation matrix to reduce the vertical disparity of corresponding matching points between images and make the horizontal disparity between images uniformly distributed. It is mainly used in computer vision, satellite data, automatic recognition of military targets and other fields.

[0003] Drones have the advantages of flexibility, low energy consumption, and rapid response, and are being used in more and more fields. However, the real-time correction of drone images is uncontrollable due to non-system factors, so there is a problem of large image correction errors caused by non-system factors. Summary of the invention

[0004] The present invention provides a method, system, device and storage medium for real-time correction of unmanned aerial vehicle images, which solves the problem that the real-time correction of images of existing unmanned aerial vehicles is uncontrollable due to non-system factors, and thus there is a large image correction error caused by non-system factors.

[0005] In a first aspect, an embodiment of the present invention provides a method for real-time correction of drone images, the method comprising the following process:

[0006] Obtain the camera pose information, image information and camera space information of the drone image;

[0007] Performing image distortion correction on the UAV image based on the camera pose information and image information of the UAV image to obtain a distortion-corrected UAV image;

[0008] Based on the camera pose information, image information and camera space information of the UAV image, geometric correction is performed on the distortion-corrected UAV image to obtain a geometrically corrected UAV image;

[0009] The process of geometric correction is as follows:

[0010] Calculate the spatial coordinates of the world coordinate system corresponding to the four corner points of the distortion-corrected drone image according to the collinear equation;

[0011] Back-project the spatial coordinates of the four corner points corresponding to the world coordinate system to the distortion-corrected UAV image to obtain the homography transformation matrix;

[0012] The distortion-corrected UAV image is linearly transformed according to the homography transformation matrix, and the geographic coordinate range of the distortion-corrected UAV image is calculated to obtain a geometrically corrected UAV image.

[0013] In the above embodiment, the present invention performs image distortion correction and geometric correction on the drone image according to the camera posture information, image information and photographic space information of the drone image, so as to solve the problem that the existing drone image real-time correction is uncontrollable due to non-system factors, and thus there is a large image correction error caused by non-system.

[0014] As some optional embodiments of the present application, the camera pose information of the drone image includes the radial distortion coefficient, eccentric distortion coefficient, movement distance of the center of the optical axis along the radial direction, extrinsic parameter matrix, and extrinsic parameter matrix of the camera; the image information of the drone image includes four corner point coordinates, principal point coordinates, principal distance, and rotation angle; the camera space information includes the object space coordinates of the camera station, the object space coordinates of the object point, and the direction cosines composed of the three external azimuth elements of the image.

[0015] In the above-mentioned embodiment, the present invention comprehensively obtains the camera posture information, image information and camera space information of the drone image, so as to achieve a better correction effect of the drone image in the later stage.

[0016] As some optional implementations of the present application, the image distortion correction includes radial distortion correction and tangential distortion correction.

[0017] In the above embodiments, the radial distortion involved in the present invention is the distortion distributed along the radius of the camera lens, which is caused by the light being more bent at the center of the lens than near the center, and this distortion is more obvious in short-focus lenses. Tangential distortion is caused by the fact that the camera lens itself is not parallel to the camera sensor plane (imaging plane) or the image plane, which is mostly caused by the installation deviation of the camera lens being pasted to the lens module.

[0018] As some optional implementations of the present application, the calculation formula for radial distortion correction is as follows:

[0019] x0=x(1+k1r 2 +k2r 4 +k3r 6 )

[0020] y0=y(1+k1r 2 +k2r 4 +k3r 6 )

[0021] Among them, (x0, y0) represents the coordinates of the principal point of the distortion-corrected drone image, (x, y) represents the coordinates of the pixel point of the original drone image, k1, k2, k3 represent the radial distortion coefficients of the camera, and r represents the moving distance of the center of the camera's optical axis along the radial direction.

[0022] In the above embodiment, the present invention considers the cause of radial distortion and constructs a mathematical model of distortion. The radial distortion of the drone image is corrected by the mathematical model of distortion, and the correction effect is better.

[0023] As some optional implementations of the present application, the calculation formula for tangential distortion correction is as follows:

[0024] x0=x+(2p1y+p2(r 2 +2x 2 )

[0025] y0=y+(2p2x+p1(r 2 +2y 2 )

[0026] Among them, (x0, y0) represents the coordinates of the principal point of the distortion-corrected drone image, (x, y) represents the pixel coordinates of the original drone image, p1, p2 represent the eccentricity distortion coefficients of the camera, and r represents the movement distance of the center of the camera's optical axis along the radial direction.

[0027] In the above embodiment, the present invention considers the cause of tangential distortion and constructs a mathematical model of distortion. The tangential distortion of the drone image is corrected by the mathematical model of distortion, and the correction effect is better.

[0028] As some optional implementations of the present application, the collinear equation calculation formula is as follows:

[0029]

[0030] Among them, (x1, y1) represents the pixel coordinates of the distortion-corrected drone image, (X, Y, Z) represents the spatial coordinates of the world coordinate system, K represents the intrinsic parameter matrix of the camera, and M represents the extrinsic parameter matrix of the camera.

[0031] In the above embodiment, the present invention combines the intrinsic parameter matrix and the extrinsic parameter matrix of the camera to calculate the collinear equation, and corresponds the four corner points of the drone image to the spatial coordinates of the world coordinate system.

[0032] As some optional implementations of the present application, the external parameter matrix M includes a rotation matrix and a translation vector.

[0033] As some optional implementations of the present application, the rotation matrix is ​​expressed as follows:

[0034]

[0035] Where R represents the rotation matrix, ω, k represent the rotation angles around the x-axis, y-axis, and z-axis respectively. Represents the multiplication of three rotation matrices around the x-axis, y-axis, and z-axis respectively.

[0036] In the above embodiment, during the flight of the drone, the change of posture may cause the direction of the captured image to be inconsistent, so the drone image needs to be processed through a rotation matrix to facilitate subsequent image stitching and fusion.

[0037] As some optional implementations of the present application, the calculation formula for the geographic coordinate range of the distortion-corrected drone image is as follows:

[0038]

[0039] Among them, (x0, y0) represents the coordinates of the principal point of the distortion-corrected UAV image, f represents the principal distance, (x2, y2) represents the geographic coordinate range of the pixel points of the UAV image, and X S ,Y S ,Z S Indicates the object space coordinates of the camera station, X A ,Y A ,Z A Represents the object space coordinates of the object point, a i ,b i ,c i (i=1,2,3) represents the direction cosines composed of the three exterior azimuth elements of the image.

[0040] In the above embodiment, the present invention calculates the geographic coordinate range of the drone image, which can be easily stored or calculated in the database later.

[0041] The geographic coordinate range (polygon) of the image taken by the drone is convenient for subsequent programs to store it in the database and for subsequent neighboring image searches.

[0042] In a second aspect, the present invention provides a real-time correction system for unmanned aerial vehicle images, the system comprising:

[0043] An image information acquisition unit, the image information acquisition unit is used to acquire camera pose information, image information and camera space information of the drone image;

[0044] An image distortion correction unit, wherein the image distortion correction unit performs image distortion correction on the drone image based on the camera posture information and image information of the drone image to obtain a distortion-corrected drone image;

[0045] An image geometry correction unit, wherein the image geometry correction unit performs geometry correction on the distortion-corrected UAV image based on camera pose information, image information, and camera space information of the UAV image to obtain a geometry-corrected UAV image;

[0046] The process of geometric correction is as follows:

[0047] Calculate the spatial coordinates of the world coordinate system corresponding to the four corner points of the distortion-corrected drone image according to the collinear equation;

[0048] Back-project the spatial coordinates of the four corner points corresponding to the world coordinate system to the distortion-corrected UAV image to obtain the homography transformation matrix;

[0049] The distortion-corrected UAV image is linearly transformed according to the homography transformation matrix, and the geographic coordinate range of the distortion-corrected UAV image is calculated to obtain a geometrically corrected UAV image.

[0050] In a third aspect, the present invention provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method for real-time correction of drone images when executing the computer program.

[0051] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for real-time correction of drone images is implemented.

[0052] The beneficial effects of the present invention are as follows: the present invention performs image distortion correction and geometric correction on drone images according to the camera posture information, image information and photographic space information of the drone images. When the camera spacing is large, the correction effect is still good, and the accuracy of the correction is less affected by the calibration parameters; and when there is a vertical mismatch in the positions of corresponding points between multi-viewpoint images and uneven horizontal parallax, the synthesized three-dimensional image will not have blurred object edges when displayed, and the stereoscopic effect is good. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0054] Figure 1 is a schematic diagram of the computer device structure of the hardware operating environment described in the embodiment of the present invention;

[0055] Figure 2 is a flow chart of the real-time correction method for drone images according to an embodiment of the present invention;

[0056] Figure 3is a schematic diagram comparing pincushion and barrel distortion according to an embodiment of the present invention;

[0057] Figure 4 is a schematic diagram of image comparison before and after geometric correction according to an embodiment of the present invention;

[0058] Figure 5 It is a block diagram of the real-time correction system for drone images described in an embodiment of the present invention. DETAILED DESCRIPTION

[0059] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0060] In order to solve the problem that the existing real-time image correction of drones is uncontrollable due to non-system factors, there is a large image correction error caused by non-system factors. The embodiment of the present invention provides a real-time image correction method, system, device and storage medium for drones. Before introducing the specific technical solution of the present application, the hardware operating environment involved in the embodiment of the present application is first introduced.

[0061] See also Figure 1 , Figure 1 The figure is a schematic diagram of the computer device structure of the hardware operating environment involved in the embodiment of the present invention.

[0062] like Figure 1 As shown, the computer device may include: a processor, such as a central processing unit (CPU), a communication bus, a user interface, a network interface, and a memory. Among them, the communication bus is used to realize the connection and communication between these components. The user interface may include a display screen (Display), an input unit such as a keyboard (Keyboard), and optionally, the user interface may also include a standard wired interface and a wireless interface. The network interface may be a wired interface or a wireless interface (such as a wireless fidelity interface). The memory may be a high-speed random access memory (Random Access Memory, RAM) or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk storage. The memory may optionally be a storage device independent of the aforementioned processor.

[0063] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the computer device, and may include more or less components than shown in the figure, or combine some components, or arrange the components differently.

[0064] like Figure 1 As shown, the memory as a storage medium may include an operating system module, a network communication module, a user interface module and a data storage module.

[0065] exist Figure 1 In the computer device shown, the network interface is mainly used for data communication with the network server; the user interface is mainly used for data interaction with the user; the processor and memory in the computer device of the present application can be set in the computer device, and the computer device calls a real-time correction system for drone images stored in the data storage module through the processor, and executes a real-time correction method for drone images provided in an embodiment of the present application.

[0066] Based on the hardware environment of the aforementioned embodiment, the embodiment of the present application provides a method for real-time correction of drone images, please refer to Figure 2 , Figure 2 The flowchart of the real-time correction method of the UAV image is as follows:

[0067] (1) Obtain the camera pose information, image information, and camera space information of the drone image.

[0068] In the embodiment of the present invention, the camera pose information of the drone image includes but is not limited to the radial distortion coefficient of the camera, the eccentric distortion coefficient, the moving distance of the optical axis center along the radial direction, the external parameter matrix, the external parameter matrix, etc. The image information of the drone image includes but is not limited to the coordinates of the four corner points, the coordinates of the principal point, the principal distance, the rotation angle, etc. The camera space information includes but is not limited to the object space coordinates of the camera station, the object space coordinates of the object point, and the direction cosines composed of the three external azimuth elements of the image.

[0069] (2) Based on the camera posture information and image information of the UAV image, image distortion correction is performed on the UAV image to obtain a distortion-corrected UAV image.

[0070] In the embodiment of the present invention, the image distortion correction includes radial distortion correction and tangential distortion correction.

[0071] In the embodiments of the present invention, the camera lens will introduce distortion due to the manufacturing accuracy and assembly process deviation, resulting in distortion of the original image. Lens distortion is divided into radial distortion and tangential distortion. Radial distortion is the distortion distributed along the radius of the lens. The reason for this is that the light is more bent at the center of the lens than near the center. This distortion is more obvious in short-focus lenses. Radial distortion mainly includes barrel distortion and pincushion distortion. Please refer to Figure 3 , Figure 3 Schematic diagram comparing pincushion and barrel distortion.

[0072] In the embodiment of the present invention, the distortion at the center of the optical axis of the imager is 0, and the distortion becomes more and more serious as it moves toward the edge along the radius of the lens. The mathematical model of radial distortion correction can be described by the first few terms of the Taylor series expansion around the principle point. Specifically, the calculation formula of the radial distortion correction is as follows:

[0073] x0=x(1+k1r 2 +k2r 4 +k3r 6 )

[0074] y0=y(1+k1r 2 +k2r 4 +k3r 6 )

[0075] Among them, (x0, y0) represents the coordinates of the principal point of the distortion-corrected drone image, (x, y) represents the coordinates of the pixel point of the original drone image, k1, k2, k3 represent the radial distortion coefficients of the camera, and r represents the moving distance of the center of the camera's optical axis along the radial direction.

[0076] In the embodiment of the present invention, the tangential distortion is caused by the non-parallelism of the lens itself and the camera sensor plane (imaging plane) or the image plane, which is mostly caused by the installation deviation of the lens being attached to the lens module. Specifically, the calculation formula for the tangential distortion correction is as follows:

[0077] x0=x+(2p1y+p2(r 2 +2x 2 )

[0078] y0=y+(2p2x+p1(r 2 +2y 2 )

[0079] Among them, (x0, y0) represents the coordinates of the principal point of the distortion-corrected drone image, (x, y) represents the pixel coordinates of the original drone image, p1, p2 represent the eccentricity distortion coefficients of the camera, and r represents the movement distance of the center of the camera's optical axis along the radial direction.

[0080] (3) Based on the camera pose information, image information and camera space information of the UAV image, geometric correction is performed on the distortion-corrected UAV image to obtain a geometrically corrected UAV image. Figure 4 , Figure 4 It is a schematic diagram of image comparison before and after the geometric correction.

[0081] The process of geometric correction is as follows:

[0082] (3.1) The spatial coordinates of the world coordinate system corresponding to the four corner points of the distortion-corrected drone image are calculated according to the collinearity equation.

[0083] In the embodiment of the present invention, the collinear equation calculation formula is as follows:

[0084]

[0085] Among them, (x1, y1) represents the pixel coordinates of the distortion-corrected drone image, (X, Y, Z) represents the spatial coordinates of the world coordinate system, K represents the intrinsic parameter matrix of the camera, and M represents the extrinsic parameter matrix of the camera.

[0086] Specifically, the extrinsic parameter matrix M includes a rotation matrix and a translation vector, wherein the translation vector in the extrinsic parameter matrix directly represents the position offset of the origin of one coordinate system relative to the origin of another coordinate system.

[0087] Specifically, the rotation matrix is ​​expressed as follows:

[0088]

[0089] Where R represents the rotation matrix, ω, k represent the rotation angles around the x-axis, y-axis, and z-axis respectively. Represents the multiplication of three rotation matrices around the x-axis, y-axis, and z-axis respectively.

[0090] (3.2) The spatial coordinates of the four corner points corresponding to the world coordinate system are back-projected to the distortion-corrected UAV image to obtain the homography transformation matrix.

[0091] (3.3) The distortion-corrected UAV image is linearly transformed according to the homography transformation matrix, and the geographic coordinate range of the distortion-corrected UAV image is calculated to obtain a geometrically corrected UAV image.

[0092] In an embodiment of the present invention, the calculation formula for the geographic coordinate range of the distortion-corrected drone image is as follows:

[0093]

[0094] Among them, (x0, y0) represents the coordinates of the principal point of the distortion-corrected UAV image, f represents the principal distance, (x2, y2) represents the geographic coordinate range of the pixel points of the UAV image, and X S ,Y S ,Z S Indicates the object space coordinates of the camera station, X A ,Y A ,Z A Represents the object space coordinates of the object point, a i ,bi ,c i (i=1,2,3) represents the direction cosines composed of the three exterior azimuth elements of the image.

[0095] In summary, the present invention performs image distortion correction and geometric correction on drone images according to the camera posture information, image information and photographic space information of the drone images. When the camera spacing is large, the correction effect is still good, and the accuracy of the correction is less affected by the calibration parameters; and when there is a vertical mismatch in the positions of corresponding points between multi-viewpoint images and uneven horizontal parallax, the synthesized three-dimensional image will not have blurred object edges when displayed, and the stereoscopic effect is better.

[0096] In addition, in one embodiment, based on the same inventive concept as the above embodiment, the embodiment of the present invention provides a real-time correction system for drone images, see Figure 5 , Figure 5 The structure block diagram of the UAV image real-time correction system is shown in FIG. The system corresponds to the method of Example 1 one by one, and the system includes:

[0097] An image information acquisition unit, the image information acquisition unit is used to acquire camera pose information, image information and camera space information of the drone image;

[0098] An image distortion correction unit, wherein the image distortion correction unit performs image distortion correction on the drone image based on the camera posture information and image information of the drone image to obtain a distortion-corrected drone image;

[0099] An image geometry correction unit, wherein the image geometry correction unit performs geometry correction on the distortion-corrected UAV image based on camera pose information, image information, and camera space information of the UAV image to obtain a geometry-corrected UAV image;

[0100] The process of geometric correction is as follows:

[0101] Calculate the spatial coordinates of the world coordinate system corresponding to the four corner points of the distortion-corrected drone image according to the collinear equation;

[0102] Back-project the spatial coordinates of the four corner points corresponding to the world coordinate system to the distortion-corrected UAV image to obtain the homography transformation matrix;

[0103] The distortion-corrected UAV image is linearly transformed according to the homography transformation matrix, and the geographic coordinate range of the distortion-corrected UAV image is calculated to obtain a geometrically corrected UAV image.

[0104] It should be noted that each unit in the real-time correction system for drone images in this embodiment corresponds one-to-one to each step in the real-time correction method for drone images in the aforementioned embodiment. Therefore, the specific implementation manner and technical effects achieved by this embodiment can refer to the implementation manner of the aforementioned real-time correction method for drone images, and will not be repeated here.

[0105] In addition, in one embodiment, the present application also provides a computer device, which includes a processor, a memory, and a computer program stored in the memory, and the computer program implements the method in the aforementioned embodiment when executed by the processor.

[0106] In addition, in one embodiment, the present application further provides a computer storage medium, on which a computer program is stored, and the computer program implements the method in the aforementioned embodiment when executed by a processor.

[0107] In some embodiments, the computer readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or various devices including one or any combination of the above memories. The computer may be various computing devices including intelligent terminals and servers.

[0108] In some embodiments, executable instructions may be in the form of a program, software, software module, script or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine or other unit suitable for use in a computing environment.

[0109] As an example, executable instructions may, but need not, correspond to a file in a file system, may be stored as part of a file that stores other programs or data, such as in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files storing one or more modules, subroutines, or code portions).

[0110] By way of example, executable instructions may be deployed to be executed on one computing device, or on multiple computing devices located at one site, or on multiple computing devices distributed across multiple sites and interconnected by a communication network.

[0111] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0112] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0113] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a multimedia terminal device (which can be a mobile phone, a computer, a television receiver, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0114] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A real-time correction method for drone images, characterized in that: The method The process includes: Obtain the camera pose information, image information and camera space information of the drone image; Performing image distortion correction on the UAV image based on the camera pose information and image information of the UAV image to obtain a distortion-corrected UAV image; Based on the camera pose information, image information and camera space information of the UAV image, geometric correction is performed on the distortion-corrected UAV image to obtain a geometrically corrected UAV image; The process of geometric correction is as follows: Calculate the spatial coordinates of the world coordinate system corresponding to the four corner points of the distortion-corrected drone image according to the collinear equation; Back-project the spatial coordinates of the four corner points corresponding to the world coordinate system to the distortion-corrected UAV image to obtain the homography transformation matrix; The distortion-corrected UAV image is linearly transformed according to the homography transformation matrix, and the geographic coordinate range of the distortion-corrected UAV image is calculated to obtain a geometrically corrected UAV image.

2. The real-time correction method for drone images according to claim 1 is characterized in that: The camera pose information of the drone image includes the radial distortion coefficient, eccentric distortion coefficient, movement distance of the optical axis center along the radial direction, extrinsic parameter matrix, and extrinsic parameter matrix of the camera; the image information of the drone image includes the coordinates of four corner points, the coordinates of the principal point, the principal distance, and the rotation angle; the camera space information includes the object space coordinates of the camera station, the object space coordinates of the object point, and the direction cosines composed of the three external azimuth elements of the image.

3. The real-time correction method for drone images according to claim 2 is characterized in that: The image distortion correction includes radial distortion correction and tangential distortion correction.

4. The real-time correction method for drone images according to claim 3 is characterized in that: The calculation formula for the radial distortion correction is as follows: x0=x(1+k1r 2 +k2r 4 +k3r 6 ) y0=y(1+k1r 2 +k2r 4 +k3r 6 ) Among them, (x0, y0) represents the coordinates of the principal point of the distortion-corrected drone image, (x, y) represents the coordinates of the pixel point of the original drone image, k1, k2, k3 represent the radial distortion coefficients of the camera, and r represents the moving distance of the center of the camera's optical axis along the radial direction.

5. The real-time correction method for drone images according to claim 3 is characterized in that: The calculation formula for the tangential distortion correction is as follows: <h2 style=";text-align:left;direction:ltr">x0 = x + (2p1y + p2(r<h2 style=";text-align:left;direction:ltr"> 2 <h2 style=";text-align:left;direction:ltr"> +2x<h2 style=";text-align:left;direction:ltr"> 2 <h2 style=";text-align:left;direction:ltr"> ) <h2 style=";text-align:left;direction:ltr">y0 = y+(2p2x+p1(r<h2 style=";text-align:left;direction:ltr"> 2 <h2 style=";text-align:left;direction:ltr"> +2y<h2 style=";text-align:left;direction:ltr"> 2 <h2 style=";text-align:left;direction:ltr"> ) Among them, (x0, y0) represents the coordinates of the principal point of the distortion-corrected drone image, (x, y) represents the pixel coordinates of the original drone image, p1, p2 represent the eccentricity distortion coefficients of the camera, and r represents the movement distance of the center of the camera's optical axis along the radial direction.

6. The real-time correction method for drone images according to claim 2 is characterized in that: The collinear equation calculation formula is as follows: Among them, (x1, y1) represents the pixel coordinates of the distortion-corrected drone image, (X, Y, Z) represents the spatial coordinates of the world coordinate system, K represents the intrinsic parameter matrix of the camera, and M represents the extrinsic parameter matrix of the camera.

7. The real-time correction method for drone images according to claim 6 is characterized in that: The external parameter matrix M includes a rotation matrix and a translation vector.

8. The real-time correction method for drone images according to claim 7 is characterized in that: The rotation matrix is ​​expressed as follows: Where R represents the rotation matrix, ω, k represent the rotation angles around the x-axis, y-axis, and z-axis respectively. R ω R k Represents the multiplication of three rotation matrices around the x-axis, y-axis, and z-axis respectively.

9. The real-time correction method for drone images according to claim 2 is characterized in that: The calculation formula for the geographic coordinate range of the distortion-corrected drone image is as follows: Among them, (x0, y0) represents the coordinates of the principal point of the distortion-corrected UAV image, f represents the principal distance, (x2, y2) represents the geographic coordinate range of the pixel points of the UAV image, and X S ,Y S ,Z S Indicates the object space coordinates of the camera station, X A ,Y A ,Z A Represents the object space coordinates of the object point, a i ,b i ,c i (i=1,2,3) represents the direction cosines composed of the three exterior azimuth elements of the image.

10. A real-time correction system for drone images, characterized in that: The system comprises: An image information acquisition unit, the image information acquisition unit is used to acquire camera pose information, image information and camera space information of the drone image; An image distortion correction unit, wherein the image distortion correction unit performs image distortion correction on the drone image based on the camera posture information and image information of the drone image to obtain a distortion-corrected drone image; An image geometry correction unit, wherein the image geometry correction unit performs geometry correction on the distortion-corrected UAV image based on camera pose information, image information, and camera space information of the UAV image to obtain a geometry-corrected UAV image; The process of geometric correction is as follows: Calculate the spatial coordinates of the world coordinate system corresponding to the four corner points of the distortion-corrected drone image according to the collinear equation; Back-project the spatial coordinates of the four corner points corresponding to the world coordinate system to the distortion-corrected UAV image to obtain the homography transformation matrix; The distortion-corrected UAV image is linearly transformed according to the homography transformation matrix, and the geographic coordinate range of the distortion-corrected UAV image is calculated to obtain a geometrically corrected UAV image.

11. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the real-time correction method for drone images described in any one of claims 1 to 9 is implemented.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the method for real-time correction of drone images as described in any one of claims 1 to 9 is implemented.

Images