Unmanned aerial vehicle image calibration method and device, electronic equipment and storage medium

Abstract

The invention discloses an unmanned aerial vehicle image calibration method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining the image data of an unmanned aerial vehicle image, and carrying out the analysis of the image data, and obtaining the parameter information of the unmanned aerial vehicle image and the flight attitude information of an unmanned aerial vehicle; wherein the flight attitude information comprises a pitching angle, a rolling angle and a flight height; calculating the initial resolution of the image center point of the unmanned aerial vehicle image according to the parameter information and the flight height, and calculating the initial resolution of the image center point of the unmanned aerial vehicle image according to the initial resolution, the pitching angle, the rolling angle and the offset distance of each pixel point in the unmanned aerial vehicle image relative to the image center point. Calculating the actual resolution of each pixel point in the unmanned aerial vehicle image; and according to the actual resolution, calibrating the resolution of each pixel point in the unmanned aerial vehicle image to obtain a calibrated unmanned aerial vehicle image. According to the invention, the calibration precision of the unmanned aerial vehicle image can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle image processing, and in particular to a method, device, electronic equipment and storage medium for unmanned aerial vehicle image calibration. Background Art

[0002] UAV aerial photography technology is widely used in the fields of geographic information, agriculture, construction, environmental monitoring, etc. UAV images have high flexibility and can collect detailed information that traditional satellite images cannot cover, so they play an important role in applications that require high-precision data. However, due to factors such as flight attitude (such as yaw, pitch and roll angles) and camera parameters (such as focal length, sensor size, etc.), images taken by drones have accuracy problems in spatial resolution, especially when mapping geographic coordinates, uncorrected images will lead to measurement and data analysis errors.

[0003] Most existing image correction technologies estimate the ground sampling distance (GSD) through a fixed resolution, that is, a uniform spatial resolution is used for the entire image. However, this method ignores the resolution differences of pixels at different locations in the image, especially the distance of the pixel relative to the center point of the image and the impact of the flight attitude on the resolution of each pixel. It fails to correct each pixel in the image, resulting in deviations in the geographic reference accuracy of the image. Summary of the invention

[0004] The present invention provides a UAV image calibration method, device, electronic device and storage medium to solve the technical problem that the existing UAV image calibration technology ignores the resolution difference of pixels at different positions in the image, especially ignores the distance of the pixel relative to the center point of the image and the influence of the flight posture on the resolution of each pixel, and fails to correct each pixel in the image.

[0005] In order to solve the above technical problems, an embodiment of the present invention provides a method for calibrating a drone image, comprising:

[0006] Acquire image data of the drone image, and parse the image data to obtain parameter information of the drone image and flight attitude information of the drone; wherein the parameter information includes: GPS information, camera focal length and sensor size; the flight attitude information includes: pitch angle, roll angle and flight altitude;

[0007] Calculate the initial resolution of the image center point of the drone image according to the parameter information and the flight altitude, and calculate the actual resolution of each pixel in the drone image according to the initial resolution, the pitch angle, the roll angle, and the offset distance of each pixel in the drone image from the image center point;

[0008] According to the actual resolution, the resolution of each pixel in the drone image is calibrated to obtain a calibrated drone image.

[0009] As a preferred solution, the flight attitude information further includes: yaw angle;

[0010] Before calculating the initial resolution of the image center point of the drone image according to the sensor size and the flight altitude, the method further includes:

[0011] The attitude correction of the drone image is performed according to the yaw angle, pitch angle and roll angle.

[0012] As a preferred solution, the posture correction of the drone image according to the yaw angle, pitch angle and roll angle includes:

[0013] Rotating the drone image according to the yaw angle to adjust the drone image from the drone perspective to a horizontal perspective;

[0014] According to the pitch angle and the roll angle, geometric shape compensation adjustment is performed on the drone image to eliminate the influence of the attitude angle on the image structure of the drone image.

[0015] As a preferred solution, the initial resolution of the center point of the image of the drone image is calculated according to the following formula:

[0016]

[0017] Among them, GSD x,y is the initial resolution of the image center point of the drone image, indicating the ground sampling distance of the image center point; the image width is the image width of the drone image.

[0018] As a preferred solution, the actual resolution of each pixel in the drone image is calculated according to the following formula:

[0019]

[0020] Among them, the x resolution is the resolution of the pixel point in the drone image in the x direction, which indicates the ground sampling distance of the pixel point in the x direction; the y resolution is the resolution of each pixel point in the drone image in the y direction, which indicates the ground sampling distance of the pixel point in the y direction; the x distance from the center is the offset distance of the pixel point relative to the center point of the image in the x direction; and the y distance from the center is the offset distance of the pixel point relative to the center point of the image in the y direction.

[0021] As a preferred solution, after calibrating the resolution of each pixel in the drone image according to the actual resolution to obtain the calibrated drone image, the method further includes:

[0022] According to the actual resolution of each pixel in the drone image and the center point geographic coordinates corresponding to the center point of the image, the pixel point geographic coordinates of all pixels in the drone image are obtained, and the geographic coordinate information of the drone image is generated according to the pixel point geographic coordinates.

[0023] On the basis of the above-mentioned embodiment, another embodiment of the present invention provides a UAV image calibration device, comprising: an image data parsing module, an actual resolution calculation module and a UAV image calibration module;

[0024] The image data parsing module is used to obtain image data of the drone image, and parse the image data to obtain parameter information of the drone image and flight attitude information of the drone; wherein the parameter information includes: GPS information, camera focal length and sensor size; the flight attitude information includes: pitch angle, roll angle and flight altitude;

[0025] The actual resolution calculation module is used to calculate the initial resolution of the image center point of the drone image according to the parameter information and the flight altitude, and calculate the actual resolution of each pixel in the drone image according to the initial resolution, the pitch angle, the roll angle and the offset distance of each pixel in the drone image from the image center point;

[0026] The drone image calibration module is used to calibrate the resolution of each pixel in the drone image according to the actual resolution to obtain a calibrated drone image.

[0027] As a preferred solution, the drone image calibration device further includes: a geographic information generation module;

[0028] The geographic information generation module is used to obtain the pixel point geographic coordinates of all pixels in the drone image based on the actual resolution of each pixel point in the drone image and the center point geographic coordinates corresponding to the center point of the image, and generate the geographic coordinate information of the drone image based on the pixel point geographic coordinates.

[0029] Based on the above embodiments, another embodiment of the present invention provides an electronic device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, the drone image calibration method described in the above invention embodiment is implemented.

[0030] Based on the above embodiments, another embodiment of the present invention provides a storage medium, wherein the storage medium includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the drone image calibration method described in the above invention embodiment.

[0031] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0032] The present invention provides a method for calibrating unmanned aerial vehicle images, which acquires image data of unmanned aerial vehicle images, and parses the image data to obtain parameter information of the unmanned aerial vehicle images and flight attitude information of the unmanned aerial vehicle; wherein the parameter information includes: GPS information, camera focal length and sensor size; the flight attitude information includes: pitch angle, roll angle and flight altitude; according to the parameter information and the flight altitude, the initial resolution of the image center point of the unmanned aerial vehicle image is calculated, and according to the initial resolution, pitch angle, roll angle and the offset distance of each pixel point in the unmanned aerial vehicle image from the image center point, the actual resolution of each pixel point in the unmanned aerial vehicle image is calculated; according to the actual resolution, the resolution of each pixel point in the unmanned aerial vehicle image is calibrated to obtain a calibrated unmanned aerial vehicle image.

[0033] The present invention calculates the actual resolution of each pixel in the drone image based on the initial resolution of the image center point of the drone image, the flight attitude information of the drone, and the offset distance of each pixel in the drone image from the image center point, and then calibrates the resolution of each pixel in the drone image based on the actual resolution. Through the present invention, the resolution of each pixel in the drone image can be dynamically adjusted, and the actual geographic mapping accuracy of the image can be ensured based on the distance between the pixel and the image center point and the flight attitude parameters, overcoming the error problem caused by the overall fixed resolution in the prior art, and can greatly improve the calibration accuracy of the drone image. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a flowchart of a method for calibrating a drone image provided by an embodiment of the present invention;

[0035] Figure 2 It is a structural schematic diagram of a UAV image calibration device provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0037] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0038] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0039] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0040] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0041] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0042] In the description of the embodiments of the present application, unless otherwise clearly specified and limited, technical terms such as "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal connection of two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0043] Embodiment 1

[0044] Please refer to Figure 1 , is a flow chart of a method for calibrating a drone image provided by an embodiment of the present invention, comprising the following specific steps:

[0045] S1. Acquire image data of a drone image, and parse the image data to obtain parameter information of the drone image and flight attitude information of the drone; wherein the parameter information includes: GPS information, camera focal length, and sensor size; and the flight attitude information includes: pitch angle, roll angle, and flight altitude;

[0046] Specifically, most existing drone image correction technologies estimate the ground sampling distance (GSD) through a fixed resolution, that is, a uniform spatial resolution is used for the entire image. However, this method ignores the resolution differences of pixels at different positions in the image, especially the distance of the pixel relative to the center point of the image and the impact of the flight attitude on the resolution of each pixel. The shortcomings of this method are:

[0047] (1) Resolution error: In the edge area of ​​the image, due to the changes in viewing angle and distance, the spatial resolution cannot accurately reflect the true distance on the ground, and the correction result is prone to errors at the edge of the image;

[0048] (2) Lack of attitude angle compensation: The existing technology fails to dynamically correct each pixel according to the UAV flight attitude parameters (yaw, pitch and roll angles), resulting in deviations in the georeferenced accuracy of the image. In particular, when the UAV is flying at an angle, the image is prone to distortion or distortion.

[0049] (3) Low geographic reference accuracy: In the image stitching or remote sensing data mapping of the geographic information system (GIS), the existing correction methods can hardly meet the high-precision requirements.

[0050] In addition, the traditional overall scene calibration method relies on route planning and multi-image superposition to improve spatial accuracy. The core of this method is to accurately plan the flight path of the drone to ensure the image acquisition range and overlap rate, so as to calibrate through image stitching and alignment algorithms in the later stage. The shortcomings of this method include:

[0051] (1) Time-consuming and labor-intensive: Overall scene calibration requires the superposition and stitching of a large number of images, which requires a large amount of data processing and high computing resources, and cannot meet the needs of rapid feedback;

[0052] (2) Complex operation: Route planning and image stitching require high technical skills of operators and precise flight planning and attitude control;

[0053] (3) Poor adaptability: Existing methods are not suitable for monitoring scenarios that require rapid feedback, such as disaster relief, agricultural pest monitoring, and traffic accident handling.

[0054] In response to the above problems, the present invention proposes a single image high-precision correction method based on drone attitude parameters. The present invention can read drone images to automatically obtain and comprehensively calculate flight attitude (yaw, pitch, roll) and image sensor information, calculate the resolution of each pixel relative to the center point through drone attitude parameters and camera imaging principles, and perform pixel-by-pixel spatial correction according to flight altitude and attitude to ensure high-precision mapping of images in geographic space and achieve high-precision spatial resolution correction in single-frame images. The present invention effectively solves the problems of complex processing and long time consumption in existing calibration methods that rely on multi-image superposition, and can adapt to rapid monitoring tasks, significantly improving the real-time performance and application scope of drone images. The specific implementation steps are as follows:

[0055] 1. Image reading and parameter acquisition:

[0056] The image data of the drone image is read through the OpenCV library, and the image data is parsed to obtain the GPS information, camera focal length, sensor size and other parameters of the drone image. At the same time, the flight attitude information of the drone is extracted from the image data, including yaw, pitch, roll angle and flight altitude for subsequent correction.

[0057] S2. Calculate the initial resolution of the image center point of the drone image according to the parameter information and the flight altitude, and calculate the actual resolution of each pixel in the drone image according to the initial resolution, the pitch angle, the roll angle, and the offset distance of each pixel in the drone image from the image center point;

[0058] Preferably, the flight attitude information also includes: yaw angle; before calculating the initial resolution of the image center point of the drone image according to the sensor size and flight altitude, it also includes: performing attitude correction on the drone image according to the yaw angle, pitch angle and roll angle.

[0059] Preferably, the attitude correction of the drone image is performed according to the yaw angle, pitch angle and roll angle, including: rotating the drone image according to the yaw angle to adjust the drone image from a drone perspective to a horizontal perspective; performing geometric shape compensation adjustment on the drone image according to the pitch angle and roll angle to eliminate the influence of the attitude angle on the image structure of the drone image.

[0060] 2. Image posture correction and rotation:

[0061] Perform attitude correction on the drone image based on the yaw height, pitch height and roll height:

[0062] First, the yaw angle is applied to rotate the drone image from the drone's perspective to the horizontal perspective. Then, the drone image is geometrically compensated and adjusted according to the pitch height and roll angle. The specific method is to use the cv2.warpAffine function to rotate the drone image in turn to eliminate the influence of the attitude angle on the image structure. This step can reduce the distortion of the overall geometric structure of the image caused by the attitude, making the image close to the horizontal perspective, which is convenient for subsequent resolution correction.

[0063] Preferably, the initial resolution of the center point of the image of the drone image is calculated according to the following formula:

[0064]

[0065] Among them, GSD x,y is the initial resolution of the image center point of the drone image, indicating the ground sampling distance of the image center point; the image width is the image width of the drone image.

[0066] Preferably, the actual resolution of each pixel in the drone image is calculated according to the following formula:

[0067]

[0068]

[0069] Among them, the x resolution is the resolution of the pixel point in the drone image in the x direction, which indicates the ground sampling distance of the pixel point in the x direction; the y resolution is the resolution of each pixel point in the drone image in the y direction, which indicates the ground sampling distance of the pixel point in the y direction; the x distance from the center is the offset distance of the pixel point relative to the center point of the image in the x direction; and the y distance from the center is the offset distance of the pixel point relative to the center point of the image in the y direction.

[0070] 3. Dynamic resolution calibration:

[0071] According to the sensor information and flight altitude, the initial resolution (ground sampling distance, GSD) of the image center point of the drone image is first calculated using the following formula:

[0072]

[0073] The actual resolution of each pixel in the drone image is further calculated. Since the distances of the pixels in the drone image from the center point of the image are different, the corresponding ground resolutions are also different. For each pixel, the resolution is dynamically adjusted according to its offset distance relative to the center point of the image and the pitch and roll angles of the drone. The formula is as follows:

[0074]

[0075] Among them: "Adjusted x-resolution" and "Adjusted y-resolution" are the ground sampling distances of the drone image in the x and y directions respectively; "pitch angle" indicates the pitch angle of the drone; "roll angle" indicates the roll angle of the drone; "altitude" is the altitude of the drone; "x distance from center" and "y distance from center" indicate the offset distance of the pixel point relative to the center point of the image in the x and y directions respectively.

[0076] This step can dynamically adjust the resolution of each pixel in the UAV image, comprehensively considering the flight attitude and sensor characteristics to improve the spatial resolution accuracy of the UAV image.

[0077] S3. Calibrate the resolution of each pixel in the drone image according to the actual resolution to obtain a calibrated drone image.

[0078] Preferably, after calibrating the resolution of each pixel in the drone image according to the actual resolution to obtain the calibrated drone image, it also includes: obtaining the pixel point geographic coordinates of all pixel points in the drone image according to the actual resolution of each pixel in the drone image and the center point geographic coordinates corresponding to the center point of the image, and generating the geographic coordinate information of the drone image based on the pixel point geographic coordinates.

[0079] 4. Geographic coordinate conversion and image output:

[0080] According to the actual resolution, the resolution of each pixel in the drone image is calibrated to obtain a calibrated drone image. Use the GDAL library to create a GeoTIFF format image and set the geographic coordinate information for the image. Combine the calibrated x and y direction resolution and the geographic coordinates of the center point of the image to specify an accurate geographic reference for the output image. The final output calibrated image has a high-precision geographic reference, which can accurately correspond to the actual geographic location and meet the needs of high-precision geographic information applications.

[0081] It can be seen that the present invention provides a method for calibrating drone images. Compared with the prior art, the present invention has the following advantages:

[0082] Single-image high-precision correction: Instead of relying on the stitching of multiple frames of images, it is based on the pixel-by-pixel resolution adjustment of a single-frame image, achieving high-precision image correction, which is suitable for data quickly collected by drones;

[0083] Strong real-time performance: Compared with the calibration method that relies on multi-image superposition, the present invention only needs to process a single frame of image, which significantly reduces the amount of data processing and calculation time, and is suitable for rapid monitoring tasks;

[0084] High degree of automation: By automatically extracting flight attitude information from images and automatically completing corrections, it is suitable for batch processing of image data collected by drones to reduce human errors;

[0085] Dynamic resolution adjustment: Pixel-by-pixel dynamic calibration can more accurately reflect ground information, especially the accuracy of the edge area of ​​the image is significantly improved, overcoming the problem of low accuracy in the edge area of ​​the existing technology;

[0086] Multi-field applicability: Applicable to monitoring scenarios that require rapid feedback, such as disaster emergency monitoring, real-time monitoring of agricultural pests and diseases, traffic accident handling, and rapid assessment of construction progress.

[0087] Embodiment 2

[0088] Please refer to Figure 2 , is a schematic diagram of the structure of a UAV image calibration device provided by an embodiment of the present invention, the device comprising: an image data parsing module, an actual resolution calculation module and a UAV image calibration module;

[0089] The image data parsing module is used to obtain image data of the drone image, and parse the image data to obtain parameter information of the drone image and flight attitude information of the drone; wherein the parameter information includes: GPS information, camera focal length and sensor size; the flight attitude information includes: pitch angle, roll angle and flight altitude;

[0090] The actual resolution calculation module is used to calculate the initial resolution of the image center point of the drone image according to the parameter information and the flight altitude, and calculate the actual resolution of each pixel in the drone image according to the initial resolution, the pitch angle, the roll angle and the offset distance of each pixel in the drone image from the image center point;

[0091] The drone image calibration module is used to calibrate the resolution of each pixel in the drone image according to the actual resolution to obtain a calibrated drone image.

[0092] Preferably, the drone image calibration device also includes: a geographic information generation module; the geographic information generation module is used to obtain the pixel point geographic coordinates of all pixel points in the drone image based on the actual resolution of each pixel point in the drone image and the center point geographic coordinates corresponding to the center point of the image, and generate the geographic coordinate information of the drone image based on the pixel point geographic coordinates.

[0093] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0094] Those skilled in the art can clearly understand that for the sake of convenience and brevity, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0095] Embodiment 3

[0096] Accordingly, an embodiment of the present invention provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the drone image calibration method described in the above-mentioned embodiment of the invention when executing the computer program.

[0097] The electronic device may be a computing device such as a desktop computer, a notebook, a palm computer, a cloud server, etc. The device may include, but is not limited to, a processor and a memory.

[0098] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the device, and various interfaces and lines are used to connect various parts of the entire device.

[0099] Embodiment 4

[0100] Accordingly, an embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the drone image calibration method described in the above-mentioned embodiment of the invention.

[0101] The memory can be used to store the computer program, and the processor realizes various functions of the device by running or executing the computer program stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0102] The storage medium is a computer-readable storage medium, and the computer program is stored in the computer-readable storage medium. When the computer program is executed by the processor, the steps of each method embodiment described above can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0103] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for calibrating drone images, characterized in that: include: Acquire image data of the drone image, and parse the image data to obtain parameter information of the drone image and flight attitude information of the drone; wherein the parameter information includes: GPS information, camera focal length and sensor size; the flight attitude information includes: pitch angle, roll angle and flight altitude; Calculate the initial resolution of the image center point of the drone image according to the parameter information and the flight altitude, and calculate the actual resolution of each pixel in the drone image according to the initial resolution, the pitch angle, the roll angle, and the offset distance of each pixel in the drone image from the image center point; According to the actual resolution, the resolution of each pixel in the drone image is calibrated to obtain a calibrated drone image.

2. The drone image calibration method according to claim 1, characterized in that: The flight attitude information also includes: yaw angle; Before calculating the initial resolution of the image center point of the drone image according to the sensor size and the flight altitude, the method further includes: The attitude correction of the drone image is performed according to the yaw angle, pitch angle and roll angle.

3. The UAV image calibration method according to claim 2, characterized in that: The performing attitude correction on the drone image according to the yaw angle, the pitch angle and the roll angle includes: Rotating the drone image according to the yaw angle to adjust the drone image from the drone perspective to a horizontal perspective; According to the pitch angle and the roll angle, geometric shape compensation adjustment is performed on the drone image to eliminate the influence of the attitude angle on the image structure of the drone image.

4. The drone image calibration method according to claim 1, characterized in that: The initial resolution of the center point of the image of the drone image is calculated according to the following formula: Among them, GSD x,y is the initial resolution of the image center point of the drone image, indicating the ground sampling distance of the image center point; the image width is the image width of the drone image.

5. The drone image calibration method according to claim 4, characterized in that: The actual resolution of each pixel in the drone image is calculated according to the following formula: Among them, the x resolution is the resolution of the pixel point in the drone image in the x direction, which indicates the ground sampling distance of the pixel point in the x direction; the y resolution is the resolution of each pixel point in the drone image in the y direction, which indicates the ground sampling distance of the pixel point in the y direction; the x distance from the center is the offset distance of the pixel point relative to the center point of the image in the x direction; and the y distance from the center is the offset distance of the pixel point relative to the center point of the image in the y direction.

6. The drone image calibration method according to claim 1, characterized in that: After calibrating the resolution of each pixel in the drone image according to the actual resolution to obtain the calibrated drone image, the method further includes: According to the actual resolution of each pixel in the drone image and the center point geographic coordinates corresponding to the center point of the image, the pixel point geographic coordinates of all pixels in the drone image are obtained, and the geographic coordinate information of the drone image is generated according to the pixel point geographic coordinates.

7. A drone image calibration device, characterized in that: include: Image data analysis module, actual resolution calculation module and drone image calibration module; The image data parsing module is used to obtain image data of the drone image, and parse the image data to obtain parameter information of the drone image and flight attitude information of the drone; wherein the parameter information includes: GPS information, camera focal length and sensor size; the flight attitude information includes: pitch angle, roll angle and flight altitude; The actual resolution calculation module is used to calculate the initial resolution of the image center point of the drone image according to the parameter information and the flight altitude, and calculate the actual resolution of each pixel in the drone image according to the initial resolution, the pitch angle, the roll angle and the offset distance of each pixel in the drone image from the image center point; The drone image calibration module is used to calibrate the resolution of each pixel in the drone image according to the actual resolution to obtain a calibrated drone image.

8. The drone image calibration device according to claim 7, characterized in that: Also includes: Geographic information generation module; The geographic information generation module is used to obtain the pixel point geographic coordinates of all pixels in the drone image based on the actual resolution of each pixel point in the drone image and the center point geographic coordinates corresponding to the center point of the image, and generate the geographic coordinate information of the drone image based on the pixel point geographic coordinates.

9. An electronic device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the drone image calibration method according to any one of claims 1 to 6 is implemented.

10. A storage medium, characterized in that: The storage medium includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the drone image calibration method according to any one of claims 1 to 6.

Images