Automatic puzzle method and device for remote sensing image of unmanned aerial vehicle

Abstract

The invention discloses an automatic puzzle method and device for an unmanned aerial vehicle remote sensing image, and the method comprises the steps: obtaining the unmanned aerial vehicle remote sensing image, setting an original graphic representation at a preset position in a measurement region, carrying out the image collection of the measurement region through an unmanned aerial vehicle, and obtaining a remote sensing image containing a graphic representation corresponding to the original graphic representation; extracting the graphic representation from any unmanned aerial vehicle remote sensing image, and determining a coordinate transformation matrix based on the graphic representation; converting the pixel coordinates of any unmanned aerial vehicle remote sensing image into geographic coordinates based on the coordinate conversion matrix; and based on the geographic coordinates, matching the any unmanned aerial vehicle remote sensing image with a base map. According to the method, manual point pricking is not needed, and the pose data during camera shooting can be directly analyzed by identifying the graphic representation in the image, so that automatic splicing of multiple unmanned aerial vehicle images is realized. The defects of poor accuracy and efficiency of automatic splicing are overcome.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to an automatic jigsaw puzzle method and device for unmanned aerial vehicle remote sensing images. Background Art

[0002] At present, UAV remote sensing images have been widely used in land and resources surveys, security inspections, disaster assessments, etc. The increase in the application scenarios of UAV images has brought higher requirements for image accuracy, especially in the fields of geographic information systems (GIS) and photogrammetry, where UAV images need to be accurately georeferenced. However, traditional georeferencing and image stitching rely on manual marking of control points, which is inefficient and error-prone in large-scale image data processing. With the expansion of UAV applications, the shortcomings of manual marking have become increasingly prominent, and a more automated solution is urgently needed. Traditional image stitching methods usually rely on ground control points (GCPs) for geometric correction and registration, but it is time-consuming and labor-intensive to find the location of control points in multiple UAV images, and the problem is particularly prominent when the image collection area is large. Summary of the invention

[0003] The main purpose of the present invention is to provide a method and device for automatically assembling remote sensing images from unmanned aerial vehicles to solve the defects existing in the related art.

[0004] In order to achieve the above-mentioned purpose, according to a first aspect of the present invention, there is provided a method for automatically piecing together UAV remote sensing images, comprising acquiring a UAV remote sensing image, wherein an original graphic representation is set at a preset position in a measurement area, and the UAV performs image acquisition on the measurement area to obtain a remote sensing image including a graphic representation corresponding to the original graphic representation; extracting the graphic representation from any UAV remote sensing image, and determining a coordinate transformation matrix based on the graphic representation; converting the pixel coordinates of any UAV remote sensing image into geographic coordinates based on the coordinate transformation matrix; and matching any UAV remote sensing image with a base map based on the geographic coordinates.

[0005] Optionally, before converting the pixel coordinates of any UAV remote sensing image into geographic coordinates, the method further includes: determining a camera pose based on the coordinates of the corner points represented by the graphic; and performing direction correction on any UAV remote sensing image based on the camera pose.

[0006] Optionally, the graphic representation is a QR code, and determining the coordinate transformation matrix based on the graphic representation includes: identifying the content of the graphic representation to obtain its corresponding tag number; determining its corresponding target geographic coordinates based on the tag number; and determining the coordinate transformation matrix based on the pixel coordinates of the corrected graphic representation and the target geographic coordinates.

[0007] Optionally, before determining the coordinate transformation matrix based on the graphic representation, the method further comprises: screening the extracted graphics based on the original graphic representation, wherein a preset quality evaluation rule is used for evaluation, and the quality evaluation rule is: , The x and y represent the pixel row and column numbers in any UAV remote sensing image; x' and y' represent the pixel row and column numbers in the graphical representation; I represents the grayscale value of the UAV remote sensing image; T represents the grayscale value at the template position; R(x, y) represents the normalized cross-correlation of the position x and y, 0 represents the poor quality of the detection result, and 1 represents the good quality of the detection result.

[0008] Optionally, matching any one of the UAV remote sensing images with the base map based on the geographic coordinates includes: matching an initial base map from the base map based on the target geographic coordinates; matching a target base map that matches any one of the UAV remote sensing images from the initial base map based on the geographic coordinates corresponding to feature points in any one of the UAV remote sensing images.

[0009] Optionally, extracting a graphic representation from any UAV remote sensing image includes: performing threshold detection on any UAV remote sensing image to generate a QR code candidate frame; determining a graphic representation frame from the candidate frame, and deduplicating the graphic representation frame to obtain a graphic representation.

[0010] According to a second aspect of the present invention, there is provided an automatic jigsaw puzzle device for unmanned aerial vehicle remote sensing images, comprising an image acquisition unit for acquiring unmanned aerial vehicle remote sensing images, wherein the unmanned aerial vehicle remote sensing images are obtained by a unmanned aerial vehicle performing image acquisition on a designated area, and a graphic representation is set at a preset position in the designated area; an image preprocessing unit for extracting the graphic representation from any unmanned aerial vehicle remote sensing image and determining a coordinate transformation matrix based on the graphic representation; a jigsaw puzzle unit for converting the pixel coordinates of any unmanned aerial vehicle remote sensing image into geographic coordinates based on the coordinate transformation matrix; and matching any unmanned aerial vehicle remote sensing image with a base map based on the geographic coordinates.

[0011] According to a third aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to execute the method according to the first aspect.

[0012] According to a fourth aspect of the present invention, there is provided an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor executes the method described in any one implementation of the first aspect.

[0013] According to a fifth aspect of the present invention, a computer program is provided, which implements the method described in the first aspect when executed by a processor.

[0014] The automatic mosaic method and device for UAV remote sensing images of this embodiment include obtaining UAV remote sensing images, wherein an original graphic representation is set at a preset position in the measurement area, and the UAV performs image acquisition on the measurement area to obtain a remote sensing image containing a graphic representation corresponding to the original graphic representation; extracting the graphic representation from any UAV remote sensing image, and determining a coordinate transformation matrix based on the graphic representation; converting the pixel coordinates of any UAV remote sensing image into geographic coordinates based on the coordinate transformation matrix; and matching any UAV remote sensing image with a base map based on the geographic coordinates. There is no need for manual puncture points, and the automatic mosaic of multiple UAV images can be achieved by directly identifying the graphic representation in the image and parsing the posture data when the camera is shooting. The defects of poor accuracy and efficiency of automatic mosaic are overcome. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 is a flow chart of an automatic jigsaw puzzle method for UAV remote sensing images according to an embodiment of the present invention; Figure 2 is a schematic diagram of collecting remote sensing images of a drone according to an embodiment of the present invention; Figure 3 is a schematic diagram of a graphical representation extraction of an embodiment of the present invention; Figure 4 is a schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0018] It should be noted that the terms "first", "second", etc. in the specification of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so as to describe the embodiments of the present invention described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0019] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0020] According to an embodiment of the present invention, a method for automatically assembling a remote sensing image of an unmanned aerial vehicle is provided. Figure 1 As shown, it includes the following steps 101 to 103: Step 101: Acquire a UAV remote sensing image, wherein the UAV remote sensing image is obtained by collecting images of a designated area by a UAV, and a graphic representation is set at a preset position in the designated area.

[0021] In this step, the graphic representations are arranged in the survey area. The distance and position between the graphic representations are designed to ensure that they can be clearly distinguished in the image at the drone's flight altitude. The flight path and altitude of the drone are planned to ensure that the image captured by the drone covers all the graphic representations and the resolution is sufficient to identify the graphic representations. After obtaining the drone remote sensing image, the image is processed by radiometric correction, color balancing, etc.

[0022] Step 102: extracting a graphic representation from any UAV remote sensing image, and determining a coordinate transformation matrix based on the graphic representation.

[0023] In this step, a graphic representation is extracted from the UAV remote sensing image, and a coordinate transformation matrix is ​​determined based on the content related to the graphic representation. The coordinate transformation matrix is ​​used to transform pixel coordinates into geographic coordinates.

[0024] Step 103: converting the pixel coordinates of any UAV remote sensing image into geographic coordinates based on the coordinate conversion matrix; and matching any UAV remote sensing image with a base map based on the geographic coordinates.

[0025] In this step, the pixel coordinates in the UAV remote sensing image are converted into geographic coordinates, and the geographic coordinates of the feature points in the UAV remote sensing image are matched with the base map based on the graphical representation of the geographic coordinates. After each UAV remote sensing image is matched with the base map, a stitched image that matches the base map can be obtained.

[0026] As an optional implementation method of this embodiment, before converting the pixel coordinates of any UAV remote sensing image into geographic coordinates, the method also includes: determining the camera pose based on the corner point coordinates represented by the graphic; and performing direction correction on any UAV remote sensing image based on the camera pose.

[0027] In this optional implementation, after detecting the coordinates of the four corner points of the graphic representation, the rotation matrix and the position and posture can be calculated by geometric methods and camera calibration parameters. After obtaining the camera position and posture, the direction of the UAV remote sensing image can be corrected.

[0028] As an optional implementation method of this embodiment, the graphic representation is a QR code, and determining the coordinate transformation matrix based on the graphic representation includes: identifying the content of the graphic representation to obtain its corresponding mark number; determining its corresponding target geographic coordinates based on the mark number; and determining the coordinate transformation matrix based on the pixel coordinates of the corrected graphic representation and the target geographic coordinates.

[0029] In this optional implementation, the graphic representation can be a QR code, which is a binary square mark consisting of a wide black border and an internal binary matrix. The internal matrix determines the mark number of the QR code, which is represented by the mark ID. High-contrast colors can also be used to form the QR code. The QR code can be set in advance in the measurement area, refer to Figure 2 ,Collection is carried out by the UAV, and the QR code position set in the ,measurement area is measured and calibrated, which can be represented by the geographical coordinates of the ,center point of the QR code. After obtaining the image, the pixel coordinates of the QR code ,can be determined, and the transformation matrix can be determined based on the pixel coordinates and ,geographical coordinates.

[0030] As an optional implementation of this embodiment, before determining the coordinate transformation matrix based on the graphic representation, the method further includes: screening the extracted graphics based on the original graphic representation, wherein the graphics are evaluated using a preset quality evaluation rule, and the quality evaluation rule is: , The x and y represent the pixel row and column numbers in any UAV remote sensing image; x' and y' represent the pixel row and column numbers in the graphic representation; I represents the grayscale value of the UAV remote sensing image; T represents the grayscale value on the original graphic representation; R(x, y) represents the normalized cross-correlation of the position x and y, 0 represents the poor quality of the detection result, and 1 represents the good quality of the detection result.

[0031] In this optional implementation, the QR code in the drone image is matched with the original QR code to evaluate the effect of QR code recognition. The quality evaluation method of the QR code mark detection result is as follows: , x, y represent the pixel row and column numbers in the drone image, x', y' represent the pixel row and column numbers in the marker, I represents the grayscale value in the drone image, T represents the grayscale value on the original graphic representation, R(x, y), the normalized cross-correlation of position x, y, 0 represents the poor quality of the detection result, and 1 represents the good quality of the detection result.

[0032] As an optional implementation method of this embodiment, the matching of any one of the UAV remote sensing images with the base map based on the geographic coordinates includes: matching the initial base map from the base map based on the target geographic coordinates; matching the target base map that matches any one of the UAV remote sensing images from the initial base map based on the geographic coordinates corresponding to the feature points in any one of the UAV remote sensing images.

[0033] In this optional implementation, a rough match is performed from the base map based on the geographic coordinates represented by the graphic to match the base map module that matches the geographic location coordinates represented by the graphic. After the rough match, a match can be performed based on the geographic location coordinates of the feature points in the image to match the location points in the base map that match the feature points. After the match, the image and the base map can be accurately matched.

[0034] As an optional implementation method of this embodiment, extracting a graphic representation from any UAV remote sensing image includes: performing threshold detection on any UAV remote sensing image to generate a QR code candidate frame; determining a graphic representation frame from the candidate frame, and deduplicating the graphic representation frame to obtain a graphic representation.

[0035] In this optional implementation, reference Figure 3 The process of extracting the QR code before extracting the camera pose is illustrated. For example, a QR code candidate frame is generated by threshold detection, and then the contour perimeter and distance are calculated to determine the marking frame of the calibrated QR code, and then the camera pose data can be determined based on the QR code.

[0036] The control points of this embodiment do not need to be manually punctured. The two-dimensional code mark in the image can be directly identified to parse the posture data of the camera when shooting. At the same time, the geographic coordinates of the control points are assigned to the marking points to realize the automatic stitching of multiple drone images.

[0037] This embodiment adopts automatic control point marking: In the traditional UAV image processing process, the marking of image control points usually needs to be done manually, which is not only time-consuming and labor-intensive, but also prone to errors. After adopting automatic marking, control points can be automatically identified by computer vision technology, reducing manual intervention and improving efficiency and accuracy. Accurate image geo-referenced: In order to generate high-precision geo-referenced images or 3D models, it is necessary to ensure the accurate correspondence between UAV images and ground coordinates. By using automatic marking, the control points in the image are automatically matched with the measured ground coordinates, thereby ensuring the accuracy of geo-referenced. Improve image processing efficiency: In traditional methods, manual marking of control points is not only time-consuming, but also inefficient when processing a large number of images. Through automatic identification and matching, the efficiency of image processing is greatly improved, especially in the processing of large-scale or high-resolution images, the advantages are more obvious. Control point consistency of multi-view images: In multi-view shooting, the identification and matching of the same control point in the image at different perspectives is a challenge. Through a unique QR code tag ID, the same control points in different images can be automatically identified and matched, ensuring the consistency of points between multi-view images.

[0038] This embodiment overcomes the time-consuming and error-prone defects of manual marking: traditional methods usually require operators to manually mark control points in the image, which is very time-consuming and labor-intensive for large-scale image data sets. Manual marking is easily affected by the operator's experience and attention, and may cause marking errors, resulting in a decrease in the accuracy of control point matching, which in turn affects the accuracy of image geo-registration. Insufficient consistency in control point recognition: In scenes shot by drones from multiple perspectives, manually marked control points may have inconsistent positions in different images, making it difficult to ensure point consistency between multi-perspective images. This will affect the accuracy of subsequent image stitching and 3D modeling. Poor flexibility in the layout of marking points: The layout position and number of traditional control points are often limited by terrain conditions and measurement methods, and it is difficult to flexibly adjust according to specific needs, which may affect the accuracy and effect of image processing.

[0039] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0040] According to an embodiment of the present invention, there is also provided an automatic puzzle device based on unmanned aerial vehicle remote sensing images, comprising: an image acquisition unit, used to acquire unmanned aerial vehicle remote sensing images, wherein the unmanned aerial vehicle remote sensing images are obtained by a unmanned aerial vehicle performing image acquisition on a designated area, and a graphic representation is set at a preset position in the designated area; an image preprocessing unit, used to extract a graphic representation from any unmanned aerial vehicle remote sensing image, and determine a coordinate transformation matrix based on the graphic representation; a puzzle unit, used to convert the pixel coordinates of any unmanned aerial vehicle remote sensing image into geographic coordinates based on the coordinate transformation matrix; and based on the geographic coordinates, match any unmanned aerial vehicle remote sensing image with a base map.

[0041] As an optional implementation method of this embodiment, before converting the pixel coordinates of any UAV remote sensing image into geographic coordinates, the method also includes: determining the camera pose based on the corner point coordinates represented by the graphic; and performing direction correction on any UAV remote sensing image based on the camera pose.

[0042] As an optional implementation method of this embodiment, the graphic representation is a QR code, and determining the coordinate transformation matrix based on the graphic representation includes: identifying the content of the graphic representation to obtain its corresponding mark number; determining its corresponding target geographic coordinates based on the mark number; and determining the coordinate transformation matrix based on the pixel coordinates of the corrected graphic representation and the target geographic coordinates.

[0043] As an optional implementation of this embodiment, the device further screens the extracted graphics based on the original graphic representation, wherein a preset quality evaluation is used for evaluation, and the quality evaluation rule is: , The x and y represent the pixel row and column numbers in any UAV remote sensing image; x' and y' represent the pixel row and column numbers in the graphical representation; I represents the grayscale value of the UAV remote sensing image; T represents the grayscale value at the template position; R(x, y) represents the normalized cross-correlation of the position x and y, 0 represents the poor quality of the detection result, and 1 represents the good quality of the detection result.

[0044] As an optional implementation method of this embodiment, the matching of any one of the UAV remote sensing images with the base map based on the geographic coordinates includes: matching the initial base map from the base map based on the target geographic coordinates; matching the target base map that matches any one of the UAV remote sensing images from the initial base map based on the geographic coordinates corresponding to the feature points in any one of the UAV remote sensing images.

[0045] As an optional implementation method of this embodiment, extracting a graphic representation from any UAV remote sensing image includes: performing threshold detection on any UAV remote sensing image to generate a QR code candidate frame; determining a graphic representation frame from the candidate frame, and deduplicating the graphic representation frame to obtain a graphic representation.

[0046] According to an embodiment of the present invention, the present invention also provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can implement the method described in any of the above embodiments when executing.

[0047] According to an embodiment of the present invention, the present invention further provides a readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to implement the method described in any of the above embodiments when executed.

[0048] According to an embodiment of the present invention, the present invention further provides a computer program product, which can implement the method described in any of the above embodiments when executed by a processor.

[0049] Figure 4 A schematic block diagram of an example electronic device 300 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices.

[0050] like Figure 4 As shown, the electronic device 300 includes a computing unit 301, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 302 or a computer program loaded from a storage unit 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 can also be stored. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0051] A number of components in the electronic device 300 are connected to the I / O interface 305, including: an input unit 306, such as a keyboard, a mouse, etc.; an output unit 307, such as various types of displays, speakers, etc.; a storage unit 308, such as a disk, an optical disk, etc.; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the electronic device 300 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0052] The computing unit 301 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 301 performs the various methods and processes described above, such as the object matching method. For example, in some embodiments, the object matching method may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 308. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 300 via the ROM 302 and / or the communication unit 309. When the computer program is loaded into the RAM 303 and executed by the computing unit 301, one or more steps of the method described above may be performed.

[0053] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0054] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0055] In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

Claims

1. An automatic jigsaw puzzle method for drone remote sensing images, characterized in that: include: Acquiring a remote sensing image from a drone, wherein an original graphic representation is set at a preset position in a measurement area, and the drone performs image acquisition on the measurement area to obtain a remote sensing image including a graphic representation corresponding to the original graphic representation; Extracting the graphical representation from any UAV remote sensing image, and determining a coordinate transformation matrix based on the graphical representation; Based on the coordinate conversion matrix, the pixel coordinates of any UAV remote sensing image are converted into geographic coordinates; based on the geographic coordinates, the any UAV remote sensing image is matched with a base map.

2. The automatic mosaic method of UAV remote sensing images according to claim 1, characterized in that: Before converting the pixel coordinates of any one of the UAV remote sensing images into geographic coordinates, the method further includes: Determine the camera pose based on the coordinates of the corner points represented by the graphic; Direction correction is performed on any one of the UAV remote sensing images based on the camera posture.

3. The automatic mosaic method of UAV remote sensing images according to claim 2, characterized in that: The graphical representation is a two-dimensional code, and determining a coordinate transformation matrix based on the graphical representation comprises: Identify the content of the graphic representation to obtain its corresponding mark number; Determine the target geographic coordinates corresponding to the marker number based on the marker number; A coordinate transformation matrix is ​​determined based on the pixel coordinates of the corrected graphical representation and the target geographic coordinates.

4. The automatic mosaic method of UAV remote sensing images according to claim 1, characterized in that: Before determining the coordinate transformation matrix based on the graphical representation, the method further includes: The graphical representation is quality evaluated, and the graphical representation is screened based on the result of the quality evaluation, wherein the quality evaluation rule is: ， The x and y represent the pixel row and column numbers in any UAV remote sensing image; x' and y' represent the pixel row and column numbers represented by the graphic; I represents the grayscale value of the UAV remote sensing image; T represents the grayscale value represented by the original graphic; R(x, y) represents the normalized cross-correlation of the position x and y, 0 represents the poor quality of the detection result, and 1 represents the good quality of the detection result.

5. The automatic mosaic method of UAV remote sensing images according to claim 3, characterized in that: The matching of any one of the UAV remote sensing images with the base map based on the geographic coordinates includes: Matching an initial base map from the base map based on the target geographic coordinates; Based on the geographic coordinates corresponding to the feature points in any one of the UAV remote sensing images, a target base map matching the any one of the UAV remote sensing images is matched from the initial base map.

6. The automatic mosaic method of UAV remote sensing images according to claim 1, characterized in that: Extracting graphical representations from any drone remote sensing imagery includes: Performing threshold detection on any of the UAV remote sensing images to generate a QR code candidate frame; A graphic representation frame is determined from the candidate frames, and duplicate graphic representation frames are removed to obtain a graphic representation.

7. An automatic jigsaw puzzle device for drone remote sensing images, characterized in that: include: An image acquisition unit is used to acquire a remote sensing image of a drone, wherein the remote sensing image of the drone is obtained by collecting images of a designated area by the drone, and a graphic representation is set at a preset position in the designated area; An image preprocessing unit, for extracting a graphic representation from any UAV remote sensing image, and determining a coordinate transformation matrix based on the graphic representation; The jigsaw unit is used to convert the pixel coordinates of any UAV remote sensing image into geographic coordinates based on the coordinate conversion matrix; and match any UAV remote sensing image with a base map based on the geographic coordinates.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method according to any one of claims 1 to 6.

9. An electronic device, characterized in that: include: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor executes the method described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method according to any one of claims 1 to 6.

Images