Long-flight-strip unmanned aerial vehicle image sub-scene segmentation method, system, medium and equipment

Abstract

The invention discloses a long-strip unmanned aerial vehicle image sub-scene segmentation method and system, a medium and equipment, and relates to the field of digital photogrammetry, and the method mainly comprises the steps: constructing a scene graph through the constraint of connection points between images, and carrying out the simplification and gross error elimination of the scene graph; analyzing a single image camera parameter optimization gradient direction in combination with a neighborhood image having a connection relationship with the current image; and connecting edge weights are set through similarity measurement among image nodes, and robust segmentation of sub-scenes is realized by using a normalized graph segmentation method. By implementing the long-flight-strip unmanned aerial vehicle image sub-scene segmentation method, system, medium and device provided by the invention, the robustness of sub-scene segmentation in the long-flight-strip unmanned aerial vehicle image can be improved, and the improvement of the precision of sub-scene reconstruction is facilitated.

Description

Technical Field

[0001] The present invention relates to the field of digital photogrammetry, and more specifically to a method, system, medium and device for segmenting sub-scenes of long-flight unmanned aerial vehicle images. Background Art

[0002] Unmanned aerial vehicle photogrammetry is an important means to achieve three-dimensional reconstruction of scenes. It is widely used in digital cities, disaster warning, power inspection and other fields. Traditional large-scale regional drone images use a multi-strip structure for data collection. The image strip constraints are strong. Sub-scene segmentation and model merging are effective measures to improve the efficiency of three-dimensional reconstruction through parallel processing. However, in order to pursue data collection efficiency, drone images for strip scenes usually use a rectangular or S-shaped flight method with two strips for data collection, resulting in weak image strip constraints. If sub-scene segmentation and model merging are performed on such scenes, the stability of the internal structure of the segmented sub-scenes needs to be considered. The current sub-scene segmentation method is mainly used for large-scale regional scenes. Scene graphs are usually used to describe images and their connection relationships. The segmentation of sub-scenes can be converted into a scene graph segmentation problem in combination with graph theory. The weight of the connection edge is designed based on the number of matching points between image pairs, visual similarity, and epipolar geometric error. Then, sub-model segmentation is performed based on graph theory, including graph cut method, community detection algorithm, etc. However, the above methods use connection point information or image similarity measurement to design the weight information of the connection edges in the graph. These methods cannot directly reflect the error size of the connection points and cannot guarantee the minimum error during the adjustment optimization between sub-scenes. Summary of the invention

[0003] The object of the present invention is to provide a method, system, medium and device for sub-scene segmentation of long-strip UAV images, which can improve the robustness of sub-scene segmentation in long-strip UAV images and help improve the accuracy of sub-scene reconstruction.

[0004] The present invention provides a long-strip unmanned aerial vehicle image sub-scene segmentation method, comprising the following steps: S1: acquiring an initial scene graph, preprocessing the initial scene graph, and obtaining a preprocessed initial scene graph; S2: obtaining a single image camera parameter optimization gradient direction according to the preprocessed initial scene graph; S3: obtaining an image connection edge weight according to the single image camera parameter optimization gradient direction and the preprocessed initial scene graph; and performing sub-scene segmentation using a normalized graph cut algorithm according to the image connection edge weight.

[0005] Further, step S2 specifically includes: S21: according to the preprocessed initial scene graph, obtaining the optimized gradient direction of the reference image camera parameter in the current image pair, such as the formula: , , in, Indicates the steepest direction of the reference image camera parameter optimization in the current image pair, that is, the optimization gradient direction of the reference image camera parameters in the current image pair; Indicates Image nodes, is the Jacobian matrix of the objective function, is the error vector; To optimize the objective function; For images and images The relative translation vector between Indicated in the image The normalized three-dimensional coordinates of the feature points in , Indicated in the image Normalized three-dimensional coordinates of the feature points in; S22: According to the optimized gradient direction of the reference image camera parameters in the current image pair, the principal component analysis algorithm is used to obtain the optimized gradient direction of the single image camera parameters.

[0006] Furthermore, the above optimization of the gradient direction and the preprocessed initial scene graph based on the camera parameters of a single image can obtain the connection edge weight of the image, as shown in the formula: , in, is the gradient consistency cost function, that is, the image The connection edge weights of For images The camera parameter optimization gradient direction, express The transpose of For images The camera parameter optimization gradient direction, Represents the norm.

[0007] The present invention also provides a long-strip UAV image sub-scene segmentation system, comprising the following modules: a preprocessing module, configured to: obtain an initial scene graph, preprocess the initial scene graph, and obtain a preprocessed initial scene graph; an optimized gradient direction calculation module, configured to: obtain a single image camera parameter optimized gradient direction according to the preprocessed initial scene graph; an image connection edge weight module, configured to: obtain an image connection edge weight according to a single image camera parameter optimized gradient direction and the preprocessed initial scene graph; and perform sub-scene segmentation using a normalized graph cut algorithm based on the image connection edge weight.

[0008] Furthermore, the optimized gradient direction calculation module is specifically configured as follows: according to the preprocessed initial scene graph, the optimized gradient direction of the reference image camera parameters in the current image pair is obtained, such as the formula: , , in, Indicates the steepest direction of the reference image camera parameter optimization in the current image pair, that is, the optimization gradient direction of the reference image camera parameters in the current image pair; Indicates Image nodes, is the Jacobian matrix of the objective function, is the error vector; To optimize the objective function; For images and images The relative translation vector between Indicated in the image The normalized three-dimensional coordinates of the feature points in , Indicated in the image The normalized three-dimensional coordinates of the feature points in the image are obtained; according to the optimized gradient direction of the reference image camera parameters in the current image pair, the principal component analysis algorithm is used to obtain the optimized gradient direction of the single image camera parameters.

[0009] Furthermore, the above optimization of the gradient direction and the preprocessed initial scene graph based on the camera parameters of a single image can obtain the connection edge weight of the image, as shown in the formula: , in, is the gradient consistency cost function, that is, the image The connection edge weights of For images The camera parameter optimization gradient direction, express The transpose of For images The camera parameter optimization gradient direction, Represents the norm.

[0010] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned long-strip drone image sub-scene segmentation method are implemented.

[0011] The present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the above-mentioned long-strip drone image sub-scene segmentation method are implemented.

[0012] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned long-strip UAV image sub-scene segmentation method.

[0013] The method, system, medium and device for segmenting sub-scenes of long-flight drone images provided by the present invention have the following beneficial effects: The present invention utilizes the connection point constraints between images to construct a scene graph, and simplifies and removes gross errors; combines neighborhood images that are connected to the current image to analyze the gradient direction of the camera parameters of a single image; sets the weights of the connection edges in the scene graph by the similarity measure between the image nodes, and uses the normalized graph cut method to achieve robust segmentation of subscenes; effectively ensures that the subscene has a robust connection structure, which can improve the robustness of subscene segmentation in long-flight unmanned aerial vehicle images, ensure that the internal size of the segmented subscene is balanced and the structure is stable, provide a stable internal structure for the parallel reconstruction of the subscenes, and provide important structural support for the subsequent reconstruction and merging of subscene models, which helps to improve the accuracy of subscene reconstruction, and thus achieve high-precision and rapid reconstruction of long-flight unmanned aerial vehicle images. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The present invention will be further described below with reference to the accompanying drawings and embodiments, in which: Figure 1 It is a flow chart of the long-flight-belt UAV image sub-scene segmentation method provided by the present invention; Figure 2 is the initial scene graph provided by the present invention; Figure 3 It is a schematic diagram of a local closed-loop constraint provided by the present invention; Figure 4 It is a schematic diagram of gradient direction analysis of single image camera parameter optimization provided by the present invention; Figure 5 is a schematic diagram of image block segmentation results based on normalized graph cuts provided by the present invention; Figure 6 It is a structural block diagram of the computer device provided by the present invention. DETAILED DESCRIPTION

[0015] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, specific embodiments of the present invention are now described in detail with reference to the accompanying drawings.

[0016] Figure 1 A schematic diagram of a long-strip UAV image sub-scene segmentation method of this embodiment is shown. In this embodiment, the long-strip UAV image sub-scene segmentation method includes the following steps: S1: Obtain an initial scene graph, preprocess the initial scene graph, and obtain a preprocessed initial scene graph; As an exemplary embodiment, in step S1, the initial scene graph is subjected to gross error elimination using a connection point information constraint method and an adaptive local closed-loop constraint method to obtain a preprocessed initial scene graph; S2: According to the preprocessed initial scene graph, the gradient direction of the camera parameter optimization of a single image is obtained; In an exemplary embodiment, step S2 specifically includes: S21: According to the preprocessed initial scene graph, the optimized gradient direction of the reference image camera parameters in the current image pair is obtained, such as the formula: , , in, Indicates the steepest direction of the reference image camera parameter optimization in the current image pair, that is, the optimization gradient direction of the reference image camera parameters in the current image pair; Indicates Image nodes, is the Jacobian matrix of the objective function, is the error vector; To optimize the objective function; For images and images The relative translation vector between , indicating that in the image The feature points in The normalized three-dimensional coordinates of From the global coordinate system to the image The rotation matrix of the camera coordinate system, is the pixel coordinate of the feature point in the two-dimensional image; Indicated in the image The feature points in The normalized three-dimensional coordinates of the feature points and are image points with the same name; S22: according to the optimized gradient direction of the reference image camera parameters in the current image pair, using the principal component analysis algorithm, obtain the optimized gradient direction of the single image camera parameters; S3: Optimize the gradient direction and the preprocessed initial scene graph according to the camera parameters of a single image to obtain the edge weight of the image; and use the normalized graph cut algorithm to perform sub-scene segmentation according to the edge weight of the image. In an exemplary embodiment, the above-mentioned optimization of the gradient direction and the preprocessed initial scene graph based on the camera parameters of a single image obtains the connection edge weight of the image, such as the formula: , in, is the gradient consistency cost function, that is, the image The connection edge weights of For images The camera parameter optimization gradient direction, express The transpose of For images The camera parameter optimization gradient direction, Represents the norm.

[0017] In one embodiment, the above-mentioned long-strip drone image sub-scene segmentation method includes: first, using the connection point constraints between images to construct a scene graph, and simplifying and eliminating gross errors; second, combining the neighboring images that have a connection relationship with the current image, analyzing the single image camera parameters to optimize the gradient direction; finally, setting the connection edge weights through the similarity measurement between the image nodes, and using the normalized graph cut method to achieve robust segmentation of the sub-scene.

[0018] In another embodiment, the above-mentioned long-strip drone image sub-scene segmentation method includes the following steps: 1. Scene graph preprocessing: For a given scene graph with epipolar geometry, there are a large number of redundant connection edges. At the same time, due to the image shooting light, viewing angle, and the appearance of repeated structures in the scene, there are gross errors in the epipolar geometry between the connected images in the scene graph. Therefore, it is necessary to simplify the initial scene graph and perform preprocessing operations to eliminate gross errors. This embodiment first simplifies the subscene graph by constraints such as the number of connection points, the distribution of connection points, and the intersection angle, and then searches for image nodes with large errors in the local closed-loop connection graph through adaptive local closed-loop constraints to eliminate gross errors in the scene graph. 2. Analysis of gradient direction of camera parameter optimization for a single image: For the sub-scene graph preprocessed in the above steps, use the image nodes and the connected domain images to calculate the camera parameter optimization gradient direction of a single image; specifically, first use the image as the reference image, then combine it with the domain images connected to it to build an image pair, and use the kernel constraint as the optimization cost function to find the steepest direction of the reference image parameters in the current image pair as the optimized gradient direction of the reference image camera parameters in the current image pair; after calculating all adjacent image pairs with the reference image, there are differences in the optimized gradient direction of the reference image in each image pair; finally, use the series of optimized gradient directions calculated for each image pair, combined with the principal component analysis method, to obtain the final optimized gradient direction of the current reference image; 3. Sub-scene segmentation based on normalized graph cut: To ensure sufficient balance between each sub-scene obtained by segmentation, facilitating subsequent parallel reconstruction of sub-scene models; in this embodiment, the normalized graph cut method is adopted. Based on the above-mentioned preprocessing of the scene graph, the weights of the connecting edges in the scene graph are set according to the optimized gradient direction angle of the image, and finally, combined with the normalized graph cut algorithm, the robust segmentation of the sub-scene is ultimately achieved.

[0019] In another embodiment, the above-mentioned method for segmenting sub-scenes of long flight strip UAV images includes the following steps: Step 1: Preprocessing of the scene graph: The input of this embodiment is the initial scene graph with epipolar geometry , as Figure 2 shown; the vertices V of the scene graph represent the image sequences, and the edges E of the scene graph represent the relative poses of image pairs with connection relationships ; in this embodiment, connection point information and adaptive local closed-loop constraint conditions are used for scene graph simplification and gross error elimination; Among them, the connection point information constraint is specifically as follows: UAV images have a high overlap degree. Through the number and distribution of connection points, weak connection image pairs can be eliminated, realizing redundancy removal of the connecting edges in the scene graph; first, select all neighboring images with connection relationships with the current image, sort them in descending order according to the number of connection points, and delete the connecting edges less than the threshold in the scene graph; secondly, among the remaining adjacent images, design a weighted function considering the distribution of connection points and the intersection angle and sort the weights, and retain the first adjacent images; Among them, the adaptive local closed-loop constraint is specifically as follows: for the image triple with mutual connection relationships, the relative rotation matrix should satisfy , where is the identity matrix, represents the metric between two matrices, using distance metric, is the threshold; to avoid inefficiency caused by traversing all triples in the flight strip and the instability of local triangular closed-loop constraints, in this embodiment, stable connecting edges in the scene graph are analyzed, and based on this, adaptive local closed-loop verification is carried out, as Figure 3 shown; first, construct a triangular mesh according to the image nodes, and verify whether all triangle vertices satisfy the angle constraint relationship, and retain the connecting edges satisfying the threshold constraint; secondly, iteratively traverse , and sequentially search for image nodes with connection relationships within a fixed distance along the vertices of the edge . If the vertices and If there is a connection relationship between them along the reserved edges, verify whether the closed loop composed of these edges satisfies the constraint relationship (where the vertex and Image Node connection), if it satisfies, the connection edge is retained ; Finally, after several iterations, the rough errors of the scene graph connection edges are eliminated; Step 2: Single image camera parameter optimization gradient direction analysis: In the preprocessed scene graph In the example, we traverse the image nodes one by one. , and find the node All neighboring nodes that are connected , calculate the node Optimize the objective function between neighboring nodes The steepest gradient direction , (1) in is the Jacobian matrix of the objective function, is the error vector; the kernel line constraint is used as the cost function, and the calculation formula is: (2) in, Representing feature points The normalized three-dimensional coordinates of Represents the transition from the global coordinate system to the image The rotation matrix of the camera coordinate system, For images and images The relative translation vector between Calculate the node by formula (1) All optimized gradients between neighboring nodes ,like Figure 4 Finally, the principal component analysis algorithm is used to extract the main direction of the series of gradient vectors as the image The optimized gradient direction ; Step 3: Sub-scene segmentation based on normalized graph cuts: In the preprocessed scene graph In the example, the weight of the connection edge is set by the similarity measure between the image nodes, and the sub-scene segmentation problem can be solved using the minimum cut theory; the image is calculated through the above steps. The optimized gradient direction , using the gradient consistency cost function Computational imaging The connection edge weight is: (3) In order to ensure the balance of the size of the segmented sub-scenes, the normalized graph cut algorithm is used to The segmentation result is as follows Figure 5 As shown, a basic analysis unit can be provided for the subsequent parallel reconstruction of sub-scenes.

[0020] Through the above steps, the robust segmentation of the long-flight drone image sub-scenes is achieved, which can ensure the stability of the internal structure of the sub-scenes, improve the accuracy of sub-scene model reconstruction, and provide important structural support for the subsequent sub-model merging.

[0021] The present embodiment provides a long-strip UAV image sub-scene segmentation system, comprising the following modules: a preprocessing module, configured to: obtain an initial scene graph, preprocess the initial scene graph, and obtain a preprocessed initial scene graph; an optimized gradient direction calculation module, configured to: obtain a single image camera parameter optimized gradient direction according to the preprocessed initial scene graph; an image connection edge weight module, configured to: obtain an image connection edge weight according to a single image camera parameter optimized gradient direction and the preprocessed initial scene graph; and perform sub-scene segmentation using a normalized graph cut algorithm based on the image connection edge weight.

[0022] In an exemplary embodiment, the optimized gradient direction calculation module is specifically configured as follows: according to the preprocessed initial scene graph, the optimized gradient direction of the reference image camera parameter in the current image pair is obtained, such as the formula: , , in, Indicates the steepest direction of the reference image camera parameter optimization in the current image pair, that is, the optimization gradient direction of the reference image camera parameters in the current image pair; Indicates Image nodes, is the Jacobian matrix of the objective function, is the error vector; To optimize the objective function; For images and images The relative translation vector between , indicating that in the image The feature points in The normalized three-dimensional coordinates of From the global coordinate system to the image The rotation matrix of the camera coordinate system, is the pixel coordinate of the feature point in the two-dimensional image; Indicated in the image The feature points in The normalized three-dimensional coordinates of the feature points and are image points with the same name; according to the optimized gradient direction of the reference image camera parameters in the current image pair, the principal component analysis algorithm is used to obtain the optimized gradient direction of the single image camera parameters.

[0023] In an exemplary embodiment, the above-mentioned optimization of the gradient direction and the preprocessed initial scene graph based on the camera parameters of a single image obtains the connection edge weight of the image, such as the formula: , in, is the gradient consistency cost function, that is, the image The connection edge weights of For images The camera parameter optimization gradient direction, express The transpose of For images The camera parameter optimization gradient direction, Represents the norm.

[0024] This embodiment provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned long-range drone image sub-scene segmentation method are implemented. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (Flash Memory), a hard disk (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.

[0025] This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the above-mentioned long-strip drone image sub-scene segmentation method are implemented.

[0026] like Figure 6As shown, the computer device 120 may include: at least one processor 121, such as a central processing unit (CPU), at least one communication interface 123, a memory 124, and at least one communication bus 122. Among them, the communication bus 122 is used to realize the connection and communication between these components. Among them, the communication interface 123 may include a display screen (Display), a keyboard (Keyboard), and the optional communication interface 123 may also include a standard wired interface and a wireless interface. The memory 124 may be a high-speed random access memory (Random Access Memory, RAM), or a non-volatile memory (non-volatile memory), such as at least one disk storage. The memory 124 may also be at least one storage device located away from the aforementioned processor 121. Among them, the memory 124 stores an application program, and the processor 121 calls the program code stored in the memory 124 to perform any of the above method steps. Among them, the communication bus 122 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The communication bus 122 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6Only one line is used to represent it, but it does not mean that there is only one bus or one type of bus. Among them, the memory 124 may include a volatile memory (volatile memory), such as a random-access memory (random-access memory, RAM); the memory may also include a non-volatile memory (non-volatile memory), such as a flash memory (flash memory), a hard disk drive (hard disk drive, HDD) or a solid-state drive (solid-state drive, SSD); the memory 124 may also include a combination of the above-mentioned types of memory. Among them, the processor 121 may be a central processing unit (central processing unit, CPU), a network processor (network processor, NP) or a combination of CPU and NP. Among them, the processor 121 may further include a hardware chip. The above-mentioned hardware chip may be an application-specific integrated circuit (application-specific integrated circuit, ASIC), a programmable logic device (programmable logic device, PLD) or a combination thereof. The above-mentioned PLD may be a complex programmable logic device (complex programmable logic device, CPLD), a field-programmable gate array (field-programmable gate array, FPGA), a generic array logic (generic array logic, GAL) or any combination thereof. Optionally, the memory 124 is also used to store program instructions. The processor 121 can call the program instructions to implement the long-flight strip drone image sub-scene segmentation method as in this embodiment.

[0027] This embodiment provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned long-strip drone image sub-scene segmentation method.

[0028] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are within the protection of the present invention.

Claims

1. A method for segmenting sub-scenes of long-range UAV images, characterized in that: The following steps are involved: S1: Acquire an initial scene graph, and preprocess the initial scene graph to obtain a preprocessed initial scene graph; S2: Obtaining a single image camera parameter optimization gradient direction according to the preprocessed initial scene graph; S3: Optimizing the gradient direction and the preprocessed initial scene graph according to the single image camera parameter to obtain the image connection edge weight; and performing sub-scene segmentation using a normalized graph cut algorithm according to the image connection edge weight.

2. The long-strip UAV image sub-scene segmentation method according to claim 1 is characterized in that: Step S2 specifically includes: S21: According to the preprocessed initial scene graph, the optimized gradient direction of the reference image camera parameters in the current image pair is obtained, such as the formula: ， ， in, Indicates the steepest direction of the reference image camera parameter optimization in the current image pair, that is, the optimization gradient direction of the reference image camera parameters in the current image pair; Indicates Image nodes, is the Jacobian matrix of the objective function, is the error vector; To optimize the objective function; For images and images The relative translation vector between Indicated in the image The normalized three-dimensional coordinates of the feature points in , Indicated in the image The normalized three-dimensional coordinates of the feature points in; S22: Obtaining a single image camera parameter optimization gradient direction using a principal component analysis algorithm according to the optimization gradient direction of the reference image camera parameter in the current image pair.

3. The long-strip UAV image sub-scene segmentation method according to claim 1 is characterized in that: The gradient direction and the preprocessed initial scene graph are optimized according to the single image camera parameters to obtain the image connection edge weight, such as the formula: ， in, is the gradient consistency cost function, that is, the image The connection edge weights of For images The camera parameter optimization gradient direction, express The transpose of For images The camera parameter optimization gradient direction, Represents the norm.

4. A long-range drone image sub-scene segmentation system, characterized in that: Includes the following modules: A preprocessing module is configured to: obtain an initial scene graph, preprocess the initial scene graph, and obtain a preprocessed initial scene graph; The optimized gradient direction calculation module is configured to: obtain the optimized gradient direction of the single image camera parameters according to the preprocessed initial scene graph; The image connection edge weight module is configured as follows: according to the single image camera parameter, the gradient direction and the preprocessed initial scene graph are optimized to obtain the image connection edge weight; according to the image connection edge weight, a normalized graph cut algorithm is used to perform sub-scene segmentation.

5. The long-strip UAV image sub-scene segmentation system according to claim 4 is characterized in that: The specific configuration of the optimized gradient direction calculation module is: According to the preprocessed initial scene graph, the optimized gradient direction of the reference image camera parameters in the current image pair is obtained, such as the formula: ， ， in, Indicates the steepest direction of the reference image camera parameter optimization in the current image pair, that is, the optimization gradient direction of the reference image camera parameters in the current image pair; Indicates Image nodes, is the Jacobian matrix of the objective function, is the error vector; To optimize the objective function; For images and images The relative translation vector between Indicated in the image The normalized three-dimensional coordinates of the feature points in , Indicated in the image The normalized three-dimensional coordinates of the feature points in; According to the optimized gradient direction of the reference image camera parameters in the current image pair, the optimized gradient direction of the single image camera parameters is obtained by using a principal component analysis algorithm.

6. The long-strip UAV image sub-scene segmentation system according to claim 4 is characterized in that: The gradient direction and the preprocessed initial scene graph are optimized according to the single image camera parameters to obtain the image connection edge weight, such as the formula: ， in, is the gradient consistency cost function, that is, the image The connection edge weights of For images The camera parameter optimization gradient direction, express The transpose of For images The camera parameter optimization gradient direction, Represents the norm.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the long-strip UAV image sub-scene segmentation method as described in any one of claims 1 to 3 are implemented.

8. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the long-strip drone image sub-scene segmentation method as described in any one of claims 1-3 are implemented.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the long-strip UAV image sub-scene segmentation method described in any one of claims 1-3 are implemented.

Images