A Method and Device for Obtaining Nonlinear Image Stitching Sequences Based on Unmanned Aerial Vehicles

Abstract

The present invention provides a method and device for obtaining a non-linear image stitching sequence based on an unmanned aerial vehicle. This method stores a large number of disordered aerial images on each divided area according to coordinate information, calculates the similarity between the image to be stitched and other images to be stitched, as well as the position information of each deviation direction of each image to be stitched within the target area of the image to be stitched, so as to screen out the stitching images in eight directions; continuously perform iterative calculations within the target area of the obtained stitching images until all images are calculated, and obtain the stitching sequence of the images. Compared with the existing ordered stitching method, through the above scheme, the present invention calculates the stitching images within the corresponding range and generates a non-linear image stitching sequence through iterative calculations, ensuring the stitching accuracy between images and greatly improving the efficiency of image stitching.

Description

Technical Field

[0001] The present invention relates to the field of UAV aerial photography, and particularly to a method and device for obtaining a non-linear image stitching sequence based on a UAV. Background Art

[0002] For cameras that need to shoot large scenes, the lens viewfinder of the camera is very limited. Those skilled in the art often take multiple photos, stitch these photos together, and then through a series of adjustments, finally obtain a picture containing the entire large scene. With the continuous development of UAV technology, using UAV aerial photography for scene shooting has become increasingly widespread. Relying on the advantages of strong climbing ability and flexible altitude control of the UAV, UAV aerial photography can achieve multi-angle and all-round shooting. Therefore, UAV aerial photography has obvious advantages in obtaining aerial images of strip areas. Using UAV aerial photography for large scene shooting can greatly improve the shooting efficiency and obtain high-quality photos. However, in the stitching process of the captured photos, the common stitching method usually determines the shooting direction of the UAV and strictly shoots according to the positional relationship of the front and rear images, so as to stitch the captured images. This kind of ordered linear image stitching often adopts single-direction continuous stitching. However, when stitching a large number of messy images, the ordered linear image stitching often has the problem of very low stitching efficiency and is also prone to stitching errors, resulting in misaligned stitched images.

[0003] For the method of obtaining a non-linear image stitching sequence based on a UAV, the prior art includes: "A fast geographical stitching method for UAV orthophotos with low cost" proposed by Ming Yuan, Yang Yonggang, etc. This technology calculates the similarity and adjacent relationship by using the image EXIF information, and at the same time calculates the overlap degree of the images and the ratio of the registration points to the image range, so as to fuse and stitch the images. This prior art can only calculate the positional relationship, overlap degree and the ratio of the registration points to the image range of two images pairwise, and its registration requires calculation of all images, with relatively low efficiency. Summary of the Invention

[0004] Embodiments of the present invention provide a method and device for obtaining a non-linear image stitching sequence based on a UAV, which are used to improve the image stitching efficiency and avoid the problem of errors in stitching a large number of unordered images.

[0005] To solve the above problems, an embodiment of the present invention provides a method for obtaining a non-linear image stitching sequence based on a UAV, including:

[0006] Obtain aerial photos, extract the image information of each image to be stitched in the aerial photos, and store each piece of the image information in a planar area; wherein, the image information includes image content and image coordinates; and the planar area is divided into multiple regions according to the image coordinates;

[0007] According to each piece of the image information, select the target area of each image to be stitched; wherein, the target area includes an attribution area and an adjacent area;

[0008] According to each of the target areas and each piece of the image information, calculate the similarity between each image to be stitched and other images to be stitched, as well as the position information of each image to be stitched in each deviation direction;

[0009] Perform iterative calculations on each image to be stitched in turn, so that after each iterative calculation, the best stitched images of the current iterative image in each deviation direction are screened out from the target area until all images to be stitched are calculated, and the best stitched images of each image to be stitched in each deviation direction are obtained;

[0010] Perform duplicate removal processing on the best stitched images of each image to be stitched in each deviation direction, so that only one image is retained for each image to be stitched, and generate the stitching order of the aerial photos.

[0011] As an improvement of the above solution, the performing iterative calculations on each image to be stitched in turn is specifically:

[0012] Taking one image to be stitched as the center, determine the target area of the current iterative image, and perform eight-direction calculations in a cross structure with other images to be stitched within the target area to screen out the best stitched images in eight directions;

[0013] Taking the best stitched image screened out as the center, determine the target area of the current iterative image, and perform eight-direction calculations in a cross structure with other images to be stitched within the target area to screen out new best stitched images in eight directions, and perform iterative calculations on the best stitched images in this way;

[0014] When all images to be stitched are calculated, the iteration ends.

[0015] As an improvement of the above solution, the calculating the similarity between each image to be stitched and other images to be stitched, as well as the position information of each image to be stitched in each deviation direction according to each of the target areas and each piece of the image information is specifically:

[0016] Obtain the image information of each image to be stitched and other images to be stitched; wherein, the other images to be stitched are within the target area of each image to be stitched;

[0017] According to the image information of each image to be stitched and other images to be stitched, the similarity between each image to be stitched and other images to be stitched is obtained by using the feature matching method for each image to be stitched;

[0018] The position information is obtained by calculating the angles and distances between each image to be stitched and other images to be stitched in each deviation direction.

[0019] As an improvement of the above solution, according to the respective image information, the target area of each image to be stitched is selected; wherein, the target area includes an attribution area and an adjacent area, specifically:

[0020] The attribution area is determined according to the image coordinates of each image to be stitched;

[0021] The azimuth information can be obtained by calculating the angle according to the central coordinates in the image coordinates, and the adjacent area of each image to be stitched is determined according to the azimuth information.

[0022] As an improvement of the above solution, the extraction of the image information of each image to be stitched in the aerial photo is specifically:

[0023] The EXIF information of the aerial photo is extracted, and the information of the time, focal length, coordinates, length and width of the aerial photo is filtered out as the image information.

[0024] An embodiment of the present invention further provides a device for obtaining a non-linear image stitching sequence based on an unmanned aerial vehicle, including: an image extraction module, a region delineation module, a calculation module, an iteration module and a duplicate removal module;

[0025] Among them, the extraction module acquires the aerial photo, extracts the image information of each image to be stitched in the aerial photo, and stores each piece of image information in a planar region; wherein, the image information includes image content and image coordinates; the planar region is divided into multiple regions according to the image coordinates;

[0026] The region delineation module is used to select the target area of each image to be stitched according to the respective image information; wherein, the target area includes an attribution area and an adjacent area;

[0027] The calculation module is used to calculate the similarity between each image to be stitched and other images to be stitched, and the position information of each image to be stitched in each deviation direction according to each target area and each piece of image information;

[0028] The iteration module is used to perform iterative calculations on each image to be stitched in turn, so that after each iterative calculation, the best stitching image of the current iterative image in each deviation direction is screened out from the target area until all the images to be stitched are calculated, and the best stitching images of each image to be stitched in each deviation direction are obtained;

[0029] The duplicate removal module is used to perform duplicate removal processing on the best stitched images of each to-be-stitched image in each deflection direction, so that only one of each to-be-stitched image is retained, and the stitching order of the aerial photos is generated.

[0030] As an improvement of the above solution, the calculation module is used to calculate the similarity between each to-be-stitched image and other to-be-stitched images, and the position information of each to-be-stitched image in each deflection direction according to each of the target regions and each of the image information. Specifically:

[0031] Obtain the image information of each to-be-stitched image and other to-be-stitched images; wherein, the other to-be-stitched images are located within the target region of each to-be-stitched image.

[0032] Use the method of feature matching for each to-be-stitched image to obtain the similarity with other to-be-stitched images;

[0033] Calculate the angle and distance between each to-be-stitched image and other to-be-stitched images in each deflection direction to obtain the position information.

[0034] As an improvement of the above solution, the iteration module is used to perform iterative calculations on each to-be-stitched image in sequence. Specifically:

[0035] Taking one to-be-stitched image as the center, determine the target region of the current iterative image, and perform eight-direction calculations in a cross structure with other to-be-stitched images within the target region to screen out the best stitched images in eight directions;

[0036] Taking the best stitched image screened out as the center, determine the target region of the current iterative image, and perform eight-direction calculations in a cross structure with other to-be-stitched images within the target region to screen out new best stitched images in eight directions, and perform iterative calculations of the best stitched images in this way;

[0037] When all the to-be-stitched images have been calculated, the iteration ends.

[0038] An embodiment of the present invention also provides a computer terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the method for obtaining the non-linear image stitching order based on an unmanned aerial vehicle as described in the present invention is implemented.

[0039] An embodiment of the present invention also provides a computer-readable storage medium. The computer-readable storage medium includes a stored computer program. When the computer program runs, it controls the device where the computer-readable storage medium is located to execute the method for obtaining the non-linear image stitching order based on an unmanned aerial vehicle as described in the present invention.

[0040] The embodiments of the present invention have the following beneficial effects:

[0041] The present invention provides a method and apparatus for non-linear image stitching order based on an unmanned aerial vehicle. The method stores a large number of disordered aerial images on each divided area according to coordinate information, calculates the similarity between the image to be stitched and other images to be stitched, and the position information of each deviation direction of each image to be stitched within the target area of the image to be stitched, so as to screen out the best stitched images in eight directions; continuously perform iterative calculations within the target area of the obtained best stitched images until all images are calculated, and obtain the stitching order of the images. Compared with the existing ordered stitching method, through the above scheme, the present invention calculates the best stitched images within the best range and generates a non-linear image stitching order through iterative calculations, ensuring the stitching accuracy between images and greatly improving the efficiency of image stitching.

[0042] Furthermore, after the iteration is completed, the present invention performs duplicate removal processing on the best stitched images of each image to be stitched in each deviation direction, so that only one image is retained for each image to be stitched, reducing the repetition degree of image stitching and making the output image more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 is a schematic flowchart of an embodiment of a method for obtaining a non-linear image stitching order based on an unmanned aerial vehicle provided by the present invention;

[0044] Figure 2 is a schematic structural diagram of an embodiment of an apparatus for obtaining a non-linear image stitching order based on an unmanned aerial vehicle provided by the present invention;

[0045] Figure 3 is a schematic flowchart of another embodiment of a method for obtaining a non-linear image stitching order based on an unmanned aerial vehicle provided by the present invention;

[0046] Figure 4 is a schematic structural diagram of an embodiment of a terminal device provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0048] See Figure 1 , Figure 1It is a schematic flowchart of an embodiment of the method for obtaining a non-linear image stitching sequence based on an unmanned aerial vehicle provided by the present invention. As Figure 1 shown, the method includes steps 101 to 105, and the specific steps are as follows:

[0049] Step 101: Obtain aerial photos, extract the image information of each image to be stitched in the aerial photos, and store each piece of the image information in a planar region; wherein, the image information includes image content and image coordinates; and the planar region is divided into multiple regions according to the image coordinates.

[0050] In this embodiment, extract the EXIF information of the aerial photos, and screen out the information of the time, focal length, coordinates, length, and width of the aerial photos as the image information.

[0051] Step 102: Select the target regions of each image to be stitched according to each piece of the image information; wherein, the target region includes an attribution region and an adjacent region.

[0052] In this embodiment, determine the attribution region according to the image coordinates of each image to be stitched; calculate the angle according to the central coordinates in the image coordinates to obtain the azimuth information, and determine the adjacent region of each image to be stitched according to the azimuth information.

[0053] Step 103: Calculate the similarity between each image to be stitched and other images to be stitched, and the position information of each image to be stitched in each deviation direction according to each of the target regions and each piece of the image information.

[0054] In this embodiment, obtain the image information of each image to be stitched and other images to be stitched; wherein, the other images to be stitched are within the target region of each image to be stitched; according to the image information of each image to be stitched and other images to be stitched, obtain the similarity between each image to be stitched and other images to be stitched by using the feature matching method; calculate the angle and distance between each image to be stitched and other images to be stitched in each deviation direction to obtain the position information.

[0055] In this embodiment, the Euclidean distance calculation method is used for feature point matching.

[0056] Step 104: Perform iterative calculations on each image to be stitched in sequence, so that after each iterative calculation, the best stitching image of the current iterative image in each deviation direction is screened out from the target region until all the images to be stitched are calculated, and the best stitching images of each image to be stitched in each deviation direction are obtained.

[0057] In this embodiment, with one image to be stitched as the center, the target area of the current iterative image is determined, and an eight-direction calculation of a cross structure is performed within the target area with other images to be stitched, and the best stitched images in eight directions are selected; with the selected best stitched images as the center, the target area of the current iterative image is determined, and an eight-direction calculation of a cross structure is performed within the target area with other images to be stitched, and new best stitched images in eight directions are selected, and the iterative calculation of the best stitched images is performed in this way; when all the images to be stitched are calculated, the iteration ends.

[0058] Step 105: Perform duplicate removal processing on the best stitched images of each image to be stitched in each deviation direction, so that only one image is retained for each image to be stitched, and generate the stitching order of the aerial photos.

[0059] See Figure 2 , Figure 2 is a schematic structural diagram of an embodiment of a device for obtaining a non-linear image stitching order based on an unmanned aerial vehicle provided by the present invention. As Figure 2 shown, the device includes: an image extraction module 201, a region delineation module 202, a calculation module 203, an iteration module 204, and a duplicate removal module 205;

[0060] Among them, the extraction module 201 acquires aerial photos, extracts the image information of each image to be stitched in the aerial photos, and stores each image information in a planar area; among them, the image information includes image content and image coordinates; the planar area is divided into multiple regions according to the image coordinates;

[0061] The region delineation module 202 is used to select the target area of each image to be stitched according to each image information; among them, the target area includes an attribution area and an adjacent area;

[0062] The calculation module 203 is used to calculate the similarity between each image to be stitched and other images to be stitched, and the position information of each image to be stitched in each deviation direction according to each target area and each image information;

[0063] The iteration module 204 is used to perform iterative calculations on each image to be stitched in turn, so that after each iterative calculation, the best stitched images of the current iterative image in each deviation direction are selected from the target area until all the images to be stitched are calculated, and the best stitched images of each image to be stitched in each deviation direction are obtained;

[0064] The duplicate removal module 205 is used to perform duplicate removal processing on the best stitched images of each image to be stitched in each deviation direction, so that only one image is retained for each image to be stitched, and generate the stitching order of the aerial photos.

[0065] In this embodiment, the calculation module 203 is configured to calculate the similarity between each image to be stitched and other images to be stitched, as well as the position information of each image to be stitched in each deviation direction, according to each target area and each image information. Specifically: obtain the image information of each image to be stitched and other images to be stitched; wherein, the other images to be stitched are located within the target area of each image to be stitched; use the feature matching method for each image to be stitched to obtain the similarity with other images to be stitched; calculate the angle and distance between each image to be stitched and other images to be stitched in each deviation direction to obtain the position information.

[0066] In this embodiment, the iteration module 204 is configured to perform iterative calculations on each image to be stitched in sequence. Specifically: taking one image to be stitched as the center, determine the target area of the current iterative image, and perform eight-direction calculations in a cross structure with other images to be stitched within the target area, and screen out the best stitched images in eight directions; taking the best stitched images screened out as the center, determine the target area of the current iterative image, and perform eight-direction calculations in a cross structure with other images to be stitched within the target area, and screen out the new best stitched images in eight directions, and perform iterative calculations on the best stitched images in this way; when all the images to be stitched are calculated, the iteration ends.

[0067] See Figure 3 , Figure 3 is a schematic flowchart of another embodiment of the method for obtaining the non-linear image stitching sequence based on an unmanned aerial vehicle provided by the present invention. As Figure 3 shown, specifically:

[0068] Step 301: In this embodiment, divide multiple equivalent plane areas, obtain the data in the aerial images, obtain the time, focal length, coordinates, length and width information of the images from the EXIF information, and store them into multiple equivalent plane areas according to the obtained image information and coordinates respectively.

[0069] Step 302: In this embodiment, select an initial stitching image, obtain the information of the initial stitching image, and obtain the information of all other stitching images according to the area where the initial stitching image is located and the adjacent areas of the initial stitching image; calculate the similarity and position relationship between the initial stitching image and all other stitching images, and screen out the best stitched sequence images of the initial stitching image in eight deviation directions.

[0070] Step 303: Continuously perform iterative calculations according to the best stitched sequence images screened out to obtain the best stitched sequence images of each image in eight deviation directions, and then exclude the repeated stitched images of all images to ensure that only one image is retained for each image, and finally generate a cross-width stitching sequence.

[0071] See Figure 4 , Figure 4It is a schematic structural diagram of a terminal device provided by an embodiment of the present invention.

[0072] A terminal device in this embodiment includes: a processor 401, a memory 402, and a computer program stored in the memory 402 and executable on the processor 401. When the processor 401 executes the computer program, it implements the steps in the above-mentioned various embodiments of the method for obtaining the non-linear image stitching sequence based on an unmanned aerial vehicle, such as Figure 1 All steps of the image comparison method based on unmanned aerial vehicle aerial photography as shown. Alternatively, when the processor executes the computer program, it implements the functions of each module in the above-mentioned device embodiments, such as: Figure 2 All modules of the device for obtaining the non-linear image stitching sequence based on an unmanned aerial vehicle as shown.

[0073] In addition, an embodiment of the present invention further provides a computer-readable storage medium, which includes a stored computer program. When the computer program runs, it controls the device where the computer-readable storage medium is located to execute the device for obtaining the non-linear image stitching sequence based on an unmanned aerial vehicle as described in any of the above embodiments.

[0074] Those skilled in the art can understand that the schematic diagram is only an example of the terminal device, and does not constitute a limitation on the terminal device. It may include more or fewer components than shown, or combine some components, or different components. For example, the terminal device may further include input / output devices, network access devices, buses, etc.

[0075] The so-called processor 401 may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor 401 is the control center of the terminal device, and connects various parts of the entire terminal device through various interfaces and lines.

[0076] The memory 402 can be used to store the computer programs and / or modules. By running or executing the computer programs and / or modules stored in the memory, and invoking the data stored in the memory 402, the processor 401 realizes various functions of the terminal device. The memory 402 mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the mobile phone (such as audio data, phone book, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0077] Among them, if the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above method embodiments of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above method embodiments can be realized. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, an executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disc, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0078] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the attached 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 can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement it without creative work.

[0079] As can be seen from the above, the present invention provides a method and device for obtaining a non-linear image stitching sequence based on an unmanned aerial vehicle. By calculating the similarity of images and the positional relationship between images, the best stitching images are selected, and the retrieval method of the cross structure is continuously iteratively calculated. Finally, the images with repeated stitching are excluded to obtain the non-linear image stitching sequence. The present invention solves the problems of low efficiency, low accuracy and low integrity in stitching a large number of disordered images, and can be widely applied to the stitching of aerial images, with high economic benefits.

[0080] The above is the preferred embodiment of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements are also regarded as the protection scope of the present invention.

Claims

1. A method for obtaining a non-linear image stitching sequence based on an unmanned aerial vehicle, characterized in that Including: Obtain aerial photos, extract the image information of each image to be stitched in the aerial photos, and store each piece of the image information in a planar region; wherein, the image information includes image content and image coordinates; and the planar region is divided into multiple regions according to the image coordinates; Select the target region of each image to be stitched according to each piece of the image information; wherein, the target region includes an attribution region and an adjacent region; Calculate the similarity between each image to be stitched and other images to be stitched, and the position information of each image to be stitched in each deviation direction according to each of the target regions and each piece of the image information; wherein, the other images to be stitched are located within the target region of each image to be stitched; Perform iterative calculations on each image to be stitched in sequence, so that after each iterative calculation, the best stitched images of the current iterative image in each deviation direction are screened out from the target region until all images to be stitched are calculated, and the best stitched images of each image to be stitched in each deviation direction are obtained; Perform duplicate removal processing on the best stitched images of each image to be stitched in each deviation direction, so that only one image is retained for each image to be stitched, and generate the stitching order of the aerial photos.

2. The method for obtaining the non-linear image stitching sequence based on an unmanned aerial vehicle according to claim 1, wherein The step of performing iterative calculations on each image to be stitched in sequence is specifically: Taking one image to be stitched as the center, determine the target region of the current iterative image, and perform eight-direction calculations in a cross structure with other images to be stitched within the target region to screen out the best stitched images in eight directions; Taking the best stitched image screened out as the center, determine the target region of the current iterative image, and perform eight-direction calculations in a cross structure with other images to be stitched within the target region to screen out new best stitched images in eight directions, and perform iterative calculations of the best stitched images in this way; When all images to be stitched are calculated, the iteration ends.

3. The method for obtaining the non-linear image stitching sequence based on an unmanned aerial vehicle according to claim 1, wherein The step of calculating the similarity between each image to be stitched and other images to be stitched, and the position information of each image to be stitched in each deviation direction according to each of the target regions and each piece of the image information is specifically: Obtain the image information of each image to be stitched and other images to be stitched; According to the image information of each image to be stitched and other images to be stitched, use the method of feature matching for each image to be stitched to obtain the similarity with other images to be stitched; Calculate the angle and distance between each image to be stitched and other images to be stitched in each deviation direction to obtain the position information.

4. The method for obtaining the non-linear image stitching sequence based on an unmanned aerial vehicle according to claim 1, wherein The step of selecting the target region of each image to be stitched according to each piece of the image information; wherein, the target region includes an attribution region and an adjacent region is specifically: Determine the attribution region according to the image coordinates of each image to be stitched; Calculate the angle according to the center coordinates in the image coordinates to obtain the azimuth information, and determine the adjacent region of each image to be stitched according to the azimuth information.

5. The method for obtaining the non-linear image stitching sequence based on an unmanned aerial vehicle according to claim 1, characterized in that The step of extracting the image information of each image to be stitched in the aerial photos is specifically: Extract the EXIF information of the aerial photos, and screen out the information of the time, focal length, coordinates, length and width of the aerial photos as the image information.

6. An apparatus for obtaining a non-linear image stitching sequence based on an unmanned aerial vehicle, characterized in that Including: An image extraction module, a region demarcation module, a calculation module, an iteration module, and a duplicate removal module; Among them, the extraction module acquires aerial photos, extracts the image information of each image to be stitched in the aerial photos, and stores each piece of the image information in a planar region; among them, the image information includes image content and image coordinates; the planar region is divided into multiple regions according to the image coordinates; The region demarcation module is used to select the target regions of each image to be stitched according to each piece of the image information; among them, the target regions include attribution regions and adjacent regions; The calculation module is used to calculate the similarity between each image to be stitched and other images to be stitched, and the position information of each image to be stitched in each deviation direction according to each of the target regions and each piece of the image information; among them, the other images to be stitched are located within the target region of each image to be stitched; The iteration module is used to perform iterative calculations on each image to be stitched in sequence, so that after each iterative calculation, the best stitched images of the current iterative image in each deviation direction are screened out from the target region until all images to be stitched are calculated, and the best stitched images of each image to be stitched in each deviation direction are obtained; The duplicate removal module is used to perform duplicate removal processing on the best stitched images of each image to be stitched in each deviation direction, so that only one image is retained for each image to be stitched, and the stitching sequence of the aerial photos is generated.

7. The device for obtaining the non-linear image stitching sequence based on an unmanned aerial vehicle according to claim 6, wherein The calculation module is used to calculate the similarity between each image to be stitched and other images to be stitched, and the position information of each image to be stitched in each deviation direction according to each of the target regions and each piece of the image information, specifically: Acquire the image information of each image to be stitched and other images to be stitched; Adopt a feature matching method for each image to be stitched to obtain the similarity with other images to be stitched; Calculate the angles and distances between each image to be stitched and other images to be stitched in each deviation direction to obtain the position information.

8. The device for obtaining the non-linear image stitching sequence based on an unmanned aerial vehicle according to claim 6, wherein The iteration module is used to perform iterative calculations on each image to be stitched in sequence, specifically: Taking an image to be stitched as the center, determine the target region of the current iterative image, and perform eight-direction calculations in a cross structure with other images to be stitched within the target region, and screen out the best stitched images in eight directions; Taking the best stitched image screened out as the center, determine the target region of the current iterative image, and perform eight-direction calculations in a cross structure with other images to be stitched within the target region, and screen out new best stitched images in eight directions, and perform iterative calculations of the best stitched images in this way; When all images to be stitched are calculated, the iteration ends.

9. A computer terminal device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the method for obtaining the non-linear image stitching sequence based on an unmanned aerial vehicle as described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the method for obtaining the non-linear image stitching sequence based on an unmanned aerial vehicle according to any one of claims 1 to 6.

Images