Unmanned aerial vehicle visual guidance obstacle avoidance system and method based on polarization information

Abstract

The invention discloses an unmanned aerial vehicle visual guidance obstacle avoidance system and method based on polarization information, and relates to the technical field of unmanned aerial vehicle navigation and obstacle avoidance. Polarization image information in a flight scene is collected in real time through a polarization sensor, and the perception capability of a complex environment is enhanced. Polarization parameters are extracted through a compression observation method, the efficiency and accuracy of feature extraction are improved, a visual attention mechanism is combined, an obstacle background area is accurately recognized, a self-adaptive decision fusion model is constructed, the feature weight is optimized, and the reliability of target contour features is enhanced. Preliminary path search is carried out based on target contour features, and a centralized optimization sampling method is adopted, so that the probability of generating an optimal flight path in a complex environment is effectively improved. And the obstacle avoidance flight module is used for smoothing the flight path, so that the smoothness and controllability of the flight path are ensured, and the navigation and obstacle avoidance capabilities of the unmanned aerial vehicle in a complex environment are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle navigation and obstacle avoidance, and in particular to a vision-guided obstacle avoidance system and method for unmanned aerial vehicle based on polarization information. Background Art

[0002] Currently, drone technology is widely used in various fields, such as agricultural monitoring, environmental monitoring, express logistics, etc. However, in complex environments, traditional vision-guided obstacle avoidance systems mostly rely on RGB images for target detection and path planning. Although these systems can identify static obstacles, in dynamic environments, especially when the lighting conditions are complex and the background noise is large, it is often difficult to accurately judge the nature and location of obstacles, resulting in obstacle avoidance failure or unreasonable path planning. In addition, the existing technology performs poorly in dealing with obstructions, reflected light sources, etc., affecting the autonomous flight capability and safety of drones.

[0003] Most of the existing technical solutions obtain image information through a single visual sensor and process it using computer vision algorithms. However, traditional RGB images fail to fully utilize the polarization information of light, resulting in low target detection accuracy and slow response speed. At the same time, these solutions are easily affected by reflected light and shadows when processing high dynamic range scenes, resulting in misjudgment or missed detection. Therefore, there is an urgent need for a new type of UAV vision-guided obstacle avoidance system that can effectively integrate polarization information, improve the accuracy and reliability of obstacle detection, and thus achieve more efficient path planning and obstacle avoidance flight. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a UAV vision-guided obstacle avoidance system and method based on polarization information, which solves the problems of the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a UAV visual guidance obstacle avoidance system based on polarization information, comprising the following modules: a polarization information acquisition module, a polarization information extraction module, an obstacle target detection module, a path planning module, and an obstacle avoidance flight module; the polarization information acquisition module is used to collect polarization image information in a flight scene through a polarization sensor to obtain images with different polarization directions; the polarization information extraction module is used to extract feature information of images with different polarization directions through compressed observation, and set an extraction termination condition to obtain polarization parameters; the obstacle target detection module is used to perform multi-level clustering on polarization parameters, and extract the global uniqueness feature of polarization degree layer by layer. The obstacle target background area is judged and marked by the visual attention mechanism, and an adaptive decision fusion model is constructed according to the global feature distribution and the marked obstacle target background area, the feature weight is optimized, and the target contour feature is output; the path planning module is used to perform a preliminary path search through a path planning algorithm based on the target contour feature, and to perform obstacle avoidance judgment according to the global feature distribution and the marked obstacle target background area, to perform centralized optimization sampling on the preliminary path search, and to output the optimal flight path; the obstacle avoidance flight module is used to smooth the optimal flight path, remove redundant inflection points, and parse the smoothed flight path into a waypoint sequence.

[0006] Furthermore, the specific process of extracting feature information from images with different polarization directions through compressed observation is as follows: the flight scene is divided into several scene blocks, and a Gaussian random matrix is ​​applied to each scene block as a compressed observation matrix to perform multiple measurements; the measurement value of each scene block is generated according to the compressed sensing theory, and only the measurement matrix of the calculated scene block is stored.

[0007] Furthermore, the specific process of setting the extraction termination condition is as follows: reconstruct the scene for each transmitted image block measurement value, calculate the inner product between the current reconstruction result and the previous reconstruction result, and when the inner product value gradually approaches 1, judge the accuracy of the reconstruction result; when the inner product reaches the threshold, it indicates that the scene reconstruction information is saturated, and the measurement value transmission is terminated.

[0008] Furthermore, the polarization parameters are clustered at multiple levels, and the specific process of extracting the global uniqueness and spatial distribution characteristics of the polarization degree layer by layer is as follows: the first-layer clustering: the polarization degree is preliminarily clustered through the Gaussian mixture model to obtain the probability value of each pixel under each Gaussian component, the polarization degree of each pixel is calculated, the probability vector is generated, and the two elements with the largest probability are retained; the second-layer clustering: the probability density function of the first layer is used for re-clustering to extract the feature distribution, calculate the similarity between different pixels, and generate a similarity matrix; the global uniqueness characteristics of the target are extracted by calculating the mean polarization degree and spatial distance of each region; the spatial distribution characteristics of the polarization degree are calculated, the spatial variance of each pixel is evaluated, and the target area is identified.

[0009] Furthermore, the specific process of judging the obstacle target background area through the visual attention mechanism and marking it is as follows: Background area judgment: According to the probability vector and feature distribution information generated by the first layer of clustering, the boundary between the obstacle target and the background area in the image is identified; by analyzing the boundary connectivity of each area, the similarity between the target area and the background area is calculated, and the difference in their spatial distribution is judged; Marking process: For the identified background area, the visual attention mechanism is applied to mark the area through the set threshold.

[0010] Furthermore, the specific process of constructing an adaptive decision fusion model, optimizing feature weights, and outputting target contour features is as follows: construct a multi-level decision framework by comprehensively analyzing the extracted polarization parameter features, background area features marked by the visual attention mechanism, and global uniqueness features; through weighted fusion, various features are comprehensively processed through weighted coefficients to construct an adaptive decision fusion model; and the feature weights are dynamically adjusted through an adaptive algorithm to output target contour features.

[0011] Furthermore, based on the target contour features, the logical process of preliminary path search through the path planning algorithm is as follows: construct a tree structure with the starting point as the root node; in the free space, add vertices by random sampling to expand the tree structure; reconnect the tree by minimizing the cost of the newly added vertices and nearby vertices; after finding a preliminary feasible solution, generate a local ellipsoid optimization area of ​​the solution.

[0012] Furthermore, obstacle avoidance judgment is made according to the global feature distribution and the marked obstacle target background area. The specific process of centralized optimization sampling of the preliminary path search is as follows: the cost of the preliminary path is calculated, and when the cost is lower than the set threshold, the centralized optimization stage is entered; the ellipsoid area is sampled in the local space of the solution to further refine the path; the tree structure is updated, new low-cost vertices are connected, the path is optimized, the updated path is compared with the preliminary path, and the one with the lowest cost is selected as the optimal flight path.

[0013] The invention discloses a visual guidance obstacle avoidance method for unmanned aerial vehicles based on polarization information, comprising the following steps: S1. collecting polarization image information in a flight scene through a polarization sensor to obtain images with different polarization directions; S2. extracting feature information of images with different polarization directions through compressed observation, setting extraction termination conditions, and obtaining polarization parameters; S3. multi-level clustering of polarization parameters, extracting global uniqueness features and spatial distribution features of polarization degree layer by layer, judging obstacle target background areas through a visual attention mechanism, and marking them; constructing an adaptive decision fusion model according to the global feature distribution and the marked obstacle target background areas, optimizing feature weights, and outputting target contour features; S4. performing preliminary path search through a path planning algorithm based on target contour features, performing obstacle avoidance judgment according to the global feature distribution and the marked obstacle target background areas, performing centralized optimization sampling on the preliminary path search, and outputting the optimal flight path; S5. smoothing the optimal flight path, removing redundant inflection points, and parsing the smoothed flight path into a waypoint sequence.

[0014] The present invention has the following beneficial effects:

[0015] (1) The UAV visual guidance obstacle avoidance system based on polarization information collects polarization image information in the flight scene through a polarization sensor, obtains images with different polarization directions, provides multi-dimensional information of the environment, extracts feature information of images with different polarization directions through compressed observation, sets extraction termination conditions, obtains polarization parameters, and extracts key polarization features, thereby enhancing target recognition capabilities and processing efficiency. Polarization parameters are analyzed through multi-level clustering, and global unique features and spatial distribution features are extracted layer by layer. The obstacle target background area is judged and marked in combination with the visual attention mechanism. The accuracy and speed of obstacle detection are improved, and potential obstacles in complex environments can be quickly and accurately identified, reducing flight risks.

[0016] (2) The UAV visual guidance obstacle avoidance method based on polarization information performs preliminary path search and obstacle avoidance judgment through the path planning algorithm of the target contour features. And through centralized optimization sampling, the success rate and efficiency of path planning are improved, and the global optimal path can be quickly found. It ensures that the UAV can flexibly respond to complex environments during flight and improves the accuracy and effectiveness of path planning. The optimal flight path is smoothed and redundant inflection points are removed to ensure the stability and safety of the UAV flight. This processing not only improves the comfort of flight, but also reduces the impact on the equipment, reduces the failure rate, and extends the service life of the UAV. At the same time, the smooth flight path improves flight efficiency and ensures that the UAV can fly smoothly in complex environments.

[0017] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a flow chart of the UAV vision-guided obstacle avoidance system based on polarization information of the present invention.

[0019] Figure 2 The present invention is a flow chart of the UAV vision-guided obstacle avoidance method based on polarization information. DETAILED DESCRIPTION

[0020] The embodiment of the present application effectively solves the problem that it is difficult for drones to accurately identify obstacles and plan safe flight paths in complex environments through a UAV visual guidance obstacle avoidance system and method based on polarization information. Through multi-level polarization information collection and processing, the system can analyze the surrounding environment in real time, improve the accuracy of obstacle detection, optimize path planning, and ensure the flight safety and stability of drones under various lighting conditions.

[0021] The overall idea of ​​the problem in the embodiment of this application is as follows:

[0022] The polarization image information in the flight scene is collected through the polarization sensor to obtain images with different polarization directions.

[0023] Feature information of images with different polarization directions is extracted through compressed observation, and the extraction termination condition is set to obtain polarization parameters.

[0024] The polarization parameters are clustered at multiple levels, and the global uniqueness and spatial distribution characteristics of the polarization degree are extracted layer by layer. The obstacle target background area is judged and marked through the visual attention mechanism. According to the global feature distribution and the marked obstacle target background area, an adaptive decision fusion model is constructed to optimize the feature weights and output the target contour features.

[0025] Based on the target contour features, a preliminary path search is performed through the path planning algorithm, and obstacle avoidance judgment is made according to the global feature distribution and the marked obstacle target background area. The preliminary path search is centrally optimized and sampled to output the optimal flight path.

[0026] The optimal flight path is smoothed, redundant inflection points are removed, and the smoothed flight path is parsed into a waypoint sequence.

[0027] See also Figure 1The embodiment of the present invention provides a technical solution: a UAV visual guidance obstacle avoidance system based on polarization information, comprising the following modules: a polarization information acquisition module, a polarization information extraction module, an obstacle target detection module, a path planning module, and an obstacle avoidance flight module; the polarization information acquisition module is used to collect polarization image information in the flight scene through a polarization sensor to obtain images with different polarization directions; the polarization information extraction module is used to extract feature information of images with different polarization directions through compressed observation, and set extraction termination conditions to obtain polarization parameters; the obstacle target detection module is used to perform multi-level clustering on the polarization parameters, and extract the global uniqueness characteristics and spatial distribution of polarization degrees layer by layer. The system uses the global feature distribution to determine the obstacle target background area and marks it. It builds an adaptive decision fusion model based on the global feature distribution and the marked obstacle target background area, optimizes the feature weights, and outputs the target contour features. The path planning module is used to perform a preliminary path search based on the target contour features through the path planning algorithm, and makes obstacle avoidance judgments based on the global feature distribution and the marked obstacle target background area. It performs centralized optimization sampling on the preliminary path search and outputs the optimal flight path. The obstacle avoidance flight module is used to smooth the optimal flight path, remove redundant inflection points, and parse the smoothed flight path into a waypoint sequence.

[0028] In this embodiment, polarization information acquisition module: Polarization information: refers to the characteristics of the vibration direction of light waves, usually obtained by polarization sensors. Different surfaces or objects will have different effects on the polarization state of light waves, so polarization information can provide important clues about the surface characteristics of objects and environmental information. Polarization sensor: A sensor for capturing polarized light information, which can measure the polarization state of light to generate a polarization image. Polarization information extraction module: Compressed observation: A data processing technique used to reduce the amount of data while retaining important features. This method can improve processing efficiency and reduce computational burden. Feature information extraction: refers to extracting useful feature information from the original image for subsequent analysis and processing. Obstacle target detection module: Multi-level clustering: A machine learning technique that identifies patterns by grouping data into different categories. In this case, it is used to analyze polarization parameters to identify obstacles. Global uniqueness feature: refers to a feature that is unique in a data set and can effectively distinguish different objects or areas. Spatial distribution feature: A feature that describes the distribution of data in space, which can reflect the shape, position and relationship of objects. Visual attention mechanism: A technique that mimics the human visual system and focuses on important areas in an image to improve the efficiency and accuracy of target recognition. Adaptive decision fusion model: An intelligent model that integrates information from different sources to make decisions and is able to dynamically adjust to optimize results. Path planning module: Path planning algorithm: An algorithm used to determine the optimal path from the starting point to the end point. In this system, the flight path of the drone is generated by analyzing environmental characteristics and obstacle information. Concentrated optimization sampling: refers to more refined sampling within the local area of ​​the known solution to improve the efficiency and accuracy of path search. Obstacle avoidance flight module: Smoothing: A post-processing technique used to optimize the path, remove redundant inflection points, and make the flight path more natural and efficient. Waypoint sequence: A flight path consisting of a series of predetermined location points for the drone to refer to and navigate during flight.

[0029] Specifically, the specific process of extracting feature information from images with different polarization directions through compressed observation is as follows: the flight scene is divided into several scene blocks, and a Gaussian random matrix is ​​applied to each scene block as a compressed observation matrix to perform multiple measurements; the measurement value of each scene block is generated according to the compressed sensing theory, and only the measurement matrix of the calculated scene block is stored.

[0030] In this embodiment, the scene T is divided into n scene blocks, each of which is denoted as B. i (0≤i<n), each block size is z i (0≤i<n). Design measurement matrix λ={λ i}(0≤i<n,λ∈R j×z ) as the compressed measurement matrix of T, where the sub-measurement matrix λ of λi It is scene block B i The block measurement matrix λ is a Gaussian random matrix, and each matrix element in the matrix obeys an independent normal distribution N(0,1). Let the block measurement matrix λ i =λ[1:k i ,1:z i ],k i For B i Block measurement times, i.e. block B i According to the theory of compressed sensing, the measurement value I of scene T can be expressed as: λ i For scene block B i Block measurement matrix of scene block B i The size of z i The number of block measurements k i It directly determines the size of the intra-block measurement matrix. When calculating the measurement value, it is only necessary to store and calculate the intra-block measurement matrix of each scene block, without storing and calculating the measurement matrix λ of the entire target scene. This greatly reduces the storage and computational complexity of the measurement values ​​during the compressed observation process. At the same time, according to normal observation habits, when the scene block is at the edge of the entire scene, it contains more background information than target information. At this time, the block measurement number of the scene block is small, the block measurement matrix is ​​small, and the measurement value obtained is small, which largely discards the useless background information in the scene block.

[0032] Specifically, the specific process of setting the extraction termination condition is as follows: reconstruct the scene for each transmitted image block measurement value, calculate the inner product between the current reconstruction result and the previous reconstruction result, and when the inner product value gradually approaches 1, judge the accuracy of the reconstruction result; when the inner product reaches the threshold, it indicates that the scene reconstruction information is saturated, and the measurement value transmission is terminated.

[0033] In this embodiment, the compressed measurement value I in the block iImage reconstruction is performed by fusion. If you want to accurately reconstruct an n-dimensional signal with a fixed sparsity S in the transform domain, the total number of measurements k of all scene blocks needs to satisfy the equation k = Ο(S·ln(n)). However, before observing the scene information, the neural network cannot know the definite sparsity value of the scene to be observed in a certain transform domain. At the same time, due to the variability of scene information and the adaptive characteristics of the neural network, the value of the total number of measurements k is also uncertain. Therefore, the photoreceptor cells that observe the information do not need to obtain the transmission times of the optimal measurement value, but only need to reduce the number of compressed observations as much as possible under the premise of maximizing the quality of scene reconstruction. Assuming that the scene reconstruction quality is Q, the objective function that the received signal value needs to satisfy is: {I} = argmax(Q)i∈V(1-3); where V represents the set of all scene blocks. Since the original image cannot be obtained, there is no standard for the size of the scene reconstruction quality Q. Therefore, each time the image block measurement value is transmitted, the scene is reconstructed based on the converged measurement value. The quality of the reconstructed scene is measured by calculating the inner product q between the current reconstruction result and the previous reconstruction result. The inner product calculation formula is as follows: q j = <T j ,T j+1 >(1-4); in formula (1-4), T j and T j+1 They represent the jth and j+1th reconstruction results respectively. As the number of measurements increases, the reconstruction results become more and more accurate. The inner product q j It is also getting closer to 1. When q j When =1, the reconstruction result information is saturated and the transmission of the measured value is terminated.

[0034] Specifically, the specific process of multi-level clustering of polarization parameters and extracting the global uniqueness characteristics and spatial distribution characteristics of polarization degree layer by layer is as follows: the first layer of clustering: the polarization degree is preliminarily clustered through the Gaussian mixture model to obtain the probability value of each pixel under each Gaussian component, the polarization degree of each pixel is calculated, the probability vector is generated, and the two elements with the largest probability are retained; the second layer of clustering: the probability density function of the first layer is used for re-clustering to extract the feature distribution, calculate the similarity between different pixels, and generate a similarity matrix; the global uniqueness characteristics of the target are extracted by calculating the mean polarization degree and spatial distance of each region; the spatial distribution characteristics of the polarization degree are calculated, the spatial variance of each pixel is evaluated, and the target area is identified.

[0035] In this embodiment, in the first layer of feature extraction, the degree of polarization is clustered and calculated using a Gaussian mixture model. The degree of polarization of each pixel is I x It is represented by k Gaussian components linearly weighted, I x Belongs to k i The probability of (i=1,2,...,N) components is calculated using the following formula: In the formula, ω k Indicates the kth i The weighting coefficients of the Gaussian components, and are the mean polarization degree and covariance matrix of the Gaussian component respectively. Get model k i The global feature F(k i ) in, Represents component k i and k j The Euclidean distance of the mean polarization degree, D(k i ,k j ) represents the spatial distance of the component center. According to formula (2-1), the polarization probability vector P = [p1, p2, ..., p k ], each probability vector P is a Gaussian component, retain the two elements with the highest probability in the vector, and set the others to zero. The message passing clustering algorithm is used to cluster the Gaussian components retained for each pixel. The similarity matrix in the message passing clustering algorithm is given by the spatial correlation matrix between the Gaussian components in the upper layer. The Gaussian component k i and k j The spatial correlation matrix of is expressed as: Then after the second layer of clustering calculation, the polarization degree of each pixel I x The total probability attributable to model K can be expressed as: Then the calculation formula for the spatial distribution of polarization degree of model K is: in, Represents pixel I x The distance from the center of all pixels. The spatial distribution characteristic of polarization degree is the sum of weighted spatial variances. The smaller the spatial variance of polarization degree, the more likely the area where the polarization degree is located belongs to the target.

[0036] Specifically, the specific process of judging the obstacle target background area through the visual attention mechanism and marking it is as follows: Background area judgment: According to the probability vector and feature distribution information generated by the first layer of clustering, the boundary between the obstacle target and the background area in the image is identified; by analyzing the boundary connectivity of each area, the similarity between the target area and the background area is calculated, and the difference in their spatial distribution is judged; Marking process: For the identified background area, the visual attention mechanism is applied to mark the area through the set threshold.

[0037] In this embodiment, background area judgment: probability vector generated by the first layer of clustering: in the multi-level clustering process, the first layer of clustering generates a probability vector by analyzing the feature information of the polarization image. The vector represents the possibility that different areas in the image belong to obstacles or backgrounds. Feature distribution information: the feature distribution information includes visual features related to obstacle targets (such as color, shape, texture, etc.) and visual features of the background. By comparing these features, the system can determine which areas belong to obstacle targets and which areas are backgrounds. Identify boundaries: based on the probability vector and feature distribution information, the system identifies the boundaries between obstacle targets and background areas by analyzing the features in the image. This process may involve image processing techniques, such as edge detection, to clarify the boundaries of different areas. Boundary connectivity analysis: analyzing the boundary connectivity of each area is an important step in determining the integrity and coherence of the background area and the target area. Connectivity analysis can help identify whether there is an obstacle. Similarity calculation: calculate the similarity between the target area and the background area to determine the difference in their spatial distribution. This process may use various similarity metrics (such as cosine similarity, Euclidean distance, etc.) to quantify the similarity between areas. Labeling process: Visual attention mechanism: Visual attention mechanism is a technology that mimics human visual processing and can focus on important parts of the image. By analyzing the background area, the system will be able to distinguish which areas need further processing. Setting a threshold: In order to determine whether to mark an area as background, the system needs to set a threshold. This threshold can be determined based on previous training or experience data to determine whether the feature similarity meets the labeling requirements. Region labeling: Once the similarity of a region exceeds the set threshold, the region is marked as background. This labeling process will help the system distinguish between obstacle targets and background in subsequent processing, thereby making more effective obstacle avoidance decisions.

[0038] Specifically, the specific process of constructing an adaptive decision fusion model, optimizing feature weights, and outputting target contour features is as follows: construct a multi-level decision framework by comprehensively analyzing the extracted polarization parameter features, background area features marked by the visual attention mechanism, and global uniqueness features; through weighted fusion, various features are comprehensively processed through weighted coefficients to construct an adaptive decision fusion model; dynamically adjust feature weights through an adaptive algorithm to output target contour features.

[0039] In this embodiment, the extracted polarization parameter features: the features obtained from the polarization information extraction module, usually including information such as polarization degree and polarization direction, these features provide the reflection characteristics of the obstacle surface, which helps to distinguish the obstacle from the background. Background area features marked by the visual attention mechanism: the background area features marked by the visual attention mechanism reflect the recognition of the target under specific background conditions. These marks provide boundary information between obstacles and backgrounds, further helping to distinguish targets from the environment. Global uniqueness features: Global uniqueness features refer to the overall feature extraction of a specific target in the entire image, usually involving information such as the shape, size, and color distribution of the target, to ensure that the target can still be accurately identified in multiple environments. Multi-level decision framework: The features from the above different sources are analyzed at multiple levels to construct a decision framework containing multiple levels. The framework of each level can process information at different levels, such as local features, global features, and contextual information, making the decision more comprehensive. Weighted fusion: Different features are weighted by weighting coefficients to form a comprehensive feature representation. This process may use mathematical methods such as weighted average and weighted sum to ensure that each feature has its corresponding influence in the decision. Adaptive decision fusion model: This model can dynamically adjust the weights of features based on feedback and new data in different environments and conditions. Through training data or real-time feedback, the model can learn which features are more important under specific conditions, thereby optimizing the decision-making process. Adaptive algorithm: The adaptive algorithm dynamically adjusts the feature weights by monitoring environmental changes and system performance in real time. This mechanism allows the model to respond quickly to new information and optimize decision quality. For example, in some cases, the degree of polarization may be more reflective of obstacle characteristics, while in other cases, global uniqueness features may be more important. Target contour features: After the above comprehensive analysis and weighted processing, the target contour features finally output by the model contain the boundary information and shape characteristics of the obstacle. These contour features provide important input for the subsequent path planning module, helping drones make efficient obstacle avoidance decisions in complex environments.

[0040] Specifically, based on the target contour features, the logical process of preliminary path search through the path planning algorithm is as follows: construct a tree structure with the starting point as the root node; in the free space, add vertices by random sampling to expand the tree structure; reconnect the tree by minimizing the cost of the newly added vertices and nearby vertices; after finding a preliminary feasible solution, generate a local ellipsoid optimization area of ​​the solution.

[0041] In this implementation scheme, the RRT algorithm based on concentrated search in the ellipsoid region "flows as follows: gradually build a tree T = (V, E) in the planning space, where V is a set of vertices and E is the edge connecting these vertices. Initialize the tree structure with the starting point as the root node. In the free space, add new vertices to the tree by random sampling. This process expands the tree structure by generating random states and gradually covers the planning space. Reconnection of the tree: For each newly added vertex, the tree is reconnected by minimizing the cost between the newly added vertex and the nearby vertices. This process ensures that the cost of adjacent vertices in the tree is minimized, thereby enhancing the optimization ability of the path. Centralized optimization phase: Once a preliminary feasible solution is found (i.e., path p is not empty), the centralized sampling RRT* algorithm will optimize the sampling of the ellipsoid region in the local space of the solution by calculating the cost value of the solution. Ellipsoid region sampling: In the centralized optimization phase, the ellipsoid region is sampled according to the cost value of the solution to further refine the path. This centralized sampling method in the local space can increase the probability of quickly finding the local optimal solution in a complex environment. Update the tree structure: Connect new low-cost vertices to the tree and update the tree structure to optimize the path. In this process, the cost of the updated path is compared with the cost of the preliminary path, and the one with the lowest cost is selected as the optimal flight path.

[0042] Specifically, obstacle avoidance judgment is made according to the global feature distribution and the marked obstacle target background area, and the specific process of centralized optimization sampling of the preliminary path search is as follows: the cost of the preliminary path is calculated, and when the cost is lower than the set threshold, the centralized optimization stage is entered; the ellipsoid area is sampled in the local space of the solution to further refine the path; the tree structure is updated, new low-cost vertices are connected, the path is optimized, the updated path is compared with the preliminary path, and the one with the lowest cost is selected as the optimal flight path.

[0043] In this implementation scheme, obstacle avoidance judgment: obstacle avoidance judgment is performed based on the global feature distribution and the marked obstacle target background area. On this basis, the cost value of the preliminary path is calculated. Cost judgment and centralized optimization: when the cost is lower than the set threshold, the centralized optimization stage is entered to perform sampling operations on the ellipsoid area. This step further refines the path, improves the planning success rate and convergence speed. Path optimization selection: during the optimization process, the tree structure is updated, the newly generated low-cost vertices are connected to the tree, and compared with the preliminary path. Finally, the path with the lowest cost is selected as the optimal flight path. The improved RRT* algorithm effectively improves the path planning capability of the UAV in complex environments, ensuring that while quickly finding the local optimal solution, the planning success rate and efficiency are significantly improved.

[0044] See also Figure 2The method for obstacle avoidance of unmanned aerial vehicle (UAV) based on polarization information includes the following steps: S1. polarization image information in a flight scene is collected by a polarization sensor to obtain images with different polarization directions; S2. feature information of images with different polarization directions is extracted by compressed observation, and extraction termination conditions are set to obtain polarization parameters; S3. multi-level clustering is performed on the polarization parameters, and the global uniqueness and spatial distribution characteristics of the polarization degree are extracted layer by layer. The obstacle target background area is judged and marked by the visual attention mechanism, and an adaptive decision fusion model is constructed according to the global feature distribution and the marked obstacle target background area, the feature weight is optimized, and the target contour feature is output; S4. preliminary path search is performed by a path planning algorithm based on the target contour feature, and obstacle avoidance judgment is performed according to the global feature distribution and the marked obstacle target background area, and the preliminary path search is sampled centrally and optimized to output the optimal flight path; S5. the optimal flight path is smoothed to remove redundant inflection points, and the smoothed flight path is parsed into a waypoint sequence.

[0045] In this embodiment, in the flight path generated by the path planning algorithm, there are usually many redundant turning points, which may be caused by environmental complexity or the characteristics of the path planning algorithm. In order to improve the smoothness and smoothness of the flight path, the path needs to be smoothed. The smoothing process mainly includes removing unnecessary turning points to reduce sharp turns in the flight route and ensure that the drone can fly in a more natural way. Once the path is smoothed, the smoothed flight path can be parsed into a specific waypoint sequence. Each waypoint will contain corresponding coordinate location information, which is usually expressed in the form of longitude and latitude or three-dimensional space coordinates. The waypoint sequence provides clear flight instructions for the drone to ensure that the drone can accurately navigate along the predetermined route during flight. This analysis not only helps the flight control system understand and execute flight missions, but also improves the safety and efficiency of the entire flight process.

[0046] In summary, this application has at least the following effects:

[0047] The UAV visual guidance obstacle avoidance system and method based on polarization information collects polarization image information in the flight scene through a polarization sensor, obtains images with different polarization directions, provides multi-dimensional information of the environment, extracts feature information of images with different polarization directions through compressed observation, sets extraction termination conditions, obtains polarization parameters, and extracts key polarization features, thereby enhancing target recognition capability and processing efficiency. Polarization parameters are analyzed through multi-level clustering, global uniqueness features and spatial distribution features are extracted layer by layer, and obstacle target background areas are judged and marked in combination with the visual attention mechanism. The accuracy and speed of obstacle detection are improved, potential obstacles in complex environments can be quickly and accurately identified, and flight risks are reduced. Preliminary path search and obstacle avoidance judgment are performed through the path planning algorithm of target contour features. And through centralized optimization sampling, the success rate and efficiency of path planning are improved, and the global optimal path can be quickly found. It ensures that the UAV can flexibly cope with complex environments during flight, and improves the accuracy and effectiveness of path planning. The optimal flight path is smoothed to remove redundant inflection points, thereby ensuring the stability and safety of the UAV flight. This treatment not only improves flight comfort, but also reduces impact on the equipment, reduces failure rate, and extends the service life of the drone. At the same time, the smooth flight path improves flight efficiency and ensures smooth flight of the drone in complex environments.

[0048] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0049] The present invention is described with reference to flowcharts and / or block diagrams of systems, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0050] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0051] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0052] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0053] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. The UAV visual guidance obstacle avoidance system based on polarization information is characterized by: It includes the following modules: polarization information acquisition module, polarization information extraction module, obstacle target detection module, path planning module, obstacle avoidance flight module; The polarization information acquisition module is used to collect polarization image information in the flight scene through a polarization sensor to obtain images with different polarization directions; The polarization information extraction module is used to extract feature information of images with different polarization directions through compressed observation, and set extraction termination conditions to obtain polarization parameters; The obstacle target detection module is used to perform multi-level clustering on polarization parameters, extract the global uniqueness and spatial distribution characteristics of polarization degree layer by layer, determine the obstacle target background area through the visual attention mechanism, and mark it, build an adaptive decision fusion model according to the global feature distribution and the marked obstacle target background area, optimize the feature weight, and output the target contour feature; The path planning module is used to perform a preliminary path search based on the target contour features through a path planning algorithm, and to make obstacle avoidance judgments based on the global feature distribution and the marked obstacle target background area, to perform centralized optimization sampling on the preliminary path search, and to output the optimal flight path; The obstacle avoidance flight module is used to smooth the optimal flight path, remove redundant inflection points, and parse the smoothed flight path into a waypoint sequence.

2. The UAV visual guidance obstacle avoidance system based on polarization information according to claim 1, characterized in that: The specific process of extracting feature information from images with different polarization directions through compressed observation is as follows: The flight scene is divided into several scene blocks, and a Gaussian random matrix is ​​applied to each scene block as a compressed observation matrix to perform multiple measurements; The measurement value of each scene block is generated according to the compressed sensing theory, and only the measurement matrix of the calculated scene block is stored.

3. The UAV visual guidance obstacle avoidance system based on polarization information according to claim 2, characterized in that: The specific process of setting the extraction termination conditions is as follows: The scene is reconstructed for each transmitted image block measurement value, and the inner product between the current reconstruction result and the previous reconstruction result is calculated. When the inner product value gradually approaches 1, the accuracy of the reconstruction result is determined; When the inner product reaches the threshold, it means that the scene reconstruction information is saturated and the measurement value transmission is terminated.

4. The UAV visual guidance obstacle avoidance system based on polarization information according to claim 3 is characterized by: The specific process of multi-level clustering of polarization parameters and extracting the global uniqueness and spatial distribution characteristics of polarization degree layer by layer is as follows: First-level clustering: The degree of polarization is preliminarily clustered using a Gaussian mixture model to obtain the probability value of each pixel under each Gaussian component, calculate the degree of polarization of each pixel, generate a probability vector, and retain the two elements with the largest probability. The second layer of clustering: re-clustering is performed through the probability density function of the first layer, feature distribution is extracted, similarity between different pixels is calculated, and a similarity matrix is ​​generated; By calculating the mean polarization degree and spatial distance of each area, the global uniqueness characteristics of the target are extracted; The spatial distribution characteristics of polarization degree are calculated, the spatial variance of each pixel is evaluated, and the target area is identified.

5. The UAV visual guidance obstacle avoidance system based on polarization information according to claim 4, characterized in that: The specific process of judging the obstacle target background area and marking it through the visual attention mechanism is as follows: Background area judgment: According to the probability vector and feature distribution information generated by the first layer of clustering, the boundary between the obstacle target and the background area in the image is identified; By analyzing the boundary connectivity of each region, the similarity between the target region and the background region is calculated to determine their spatial distribution differences; Marking process: For the identified background area, the visual attention mechanism is applied to mark the area by the set threshold.

6. The UAV visual guidance obstacle avoidance system based on polarization information according to claim 5, characterized in that: The specific process of building an adaptive decision fusion model, optimizing feature weights, and outputting target contour features is as follows: A multi-level decision framework is constructed by comprehensively analyzing the extracted polarization parameter features, the background area features marked by the visual attention mechanism, and the global uniqueness features. Through weighted fusion, various features are comprehensively processed through weighted coefficients to build an adaptive decision fusion model; the feature weights are dynamically adjusted through an adaptive algorithm to output the target contour features.

7. The UAV visual guidance obstacle avoidance system based on polarization information according to claim 6, characterized in that: Based on the target contour features, the logical process of performing preliminary path search through the path planning algorithm is as follows: Build a tree structure with the starting point as the root node; In free space, add vertices by random sampling to expand the tree structure; Reconnect the tree by minimizing the cost of the newly added vertex and nearby vertices; After finding a preliminary feasible solution, a local ellipsoid optimization region of the solution is generated.

8. The UAV visual guidance obstacle avoidance system based on polarization information according to claim 7, characterized in that: The specific process of performing obstacle avoidance judgment and centralized optimization sampling for preliminary path search based on global feature distribution and marked obstacle target background area is as follows: Calculate the cost of the preliminary path. When the cost is lower than the set threshold, enter the centralized optimization stage. The local space of the solution is sampled by the ellipsoid region to further refine the path; Update the tree structure, connect new low-cost vertices, optimize the path, compare the updated path with the preliminary path, and choose the one with the lowest cost as the optimal flight path.

9. A method for obstacle avoidance by visual guidance of a UAV based on polarization information, applied to a system for obstacle avoidance by visual guidance of a UAV based on polarization information according to any one of claims 1 to 8, characterized in that: The following steps are involved: S1. Collect polarization image information in the flight scene through a polarization sensor to obtain images in different polarization directions; S2. extracting feature information of images in different polarization directions through compressed observation, setting extraction termination conditions, and obtaining polarization parameters; S3. Perform multi-level clustering on polarization parameters, extract the global uniqueness and spatial distribution characteristics of polarization degree layer by layer, determine the obstacle target background area through the visual attention mechanism, and mark it. According to the global feature distribution and the marked obstacle target background area, build an adaptive decision fusion model, optimize the feature weights, and output the target contour features; S4. Based on the target contour features, a preliminary path search is performed through a path planning algorithm, and obstacle avoidance judgment is performed based on the global feature distribution and the marked obstacle target background area. The preliminary path search is centrally optimized and sampled to output the optimal flight path; S5. Smooth the optimal flight path, remove redundant turning points, and parse the smoothed flight path into a waypoint sequence.

Images