Power transmission corridor tree obstacle identification method and device based on SIFT feature points, and medium

Abstract

The invention discloses a power transmission corridor tree obstacle identification method and device based on SIFT feature points and a medium, and belongs to the field of image data identification, and the method comprises the steps: shooting image data of different types of trees in a power transmission line corridor area, the image data comprising RGB images and multispectral images; preprocessing the collected image, extracting SIFT feature points from the image, evaluating and screening the contrast and stability of key feature points, generating a feature descriptor according to neighborhood information of each feature point, and performing feature matching; and matching the SIFT feature points in the image with the pre-stored tree feature descriptors in the database based on a nearest neighbor matching method of a Lowe ratio test, carrying out tree classification and identification, judging whether the current tree forms a tree obstacle object, and evaluating whether the tree can influence the power transmission line through a detection rate. The method has the advantages of high-precision tree obstacle identification capability, low misjudgment rate and omission ratio, and high-efficiency tree obstacle identification and processing.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of image data recognition, and particularly relates to a power transmission corridor tree barrier recognition method, device and medium based on SIFT feature points. BACKGROUND

[0002] With the development of the power industry, the safe operation of power transmission lines has attracted more and more attention. The tree barrier problem in the power transmission corridor, especially when the trees grow too high or too dense, can cause the shutdown, damage or even safety accidents of the power transmission line. How to efficiently and accurately identify and monitor tree barriers in a wide power transmission corridor has become an important task in the operation and maintenance of the power system. Traditional tree barrier identification methods rely on manual inspection, although this method has achieved certain results in the early stage, but due to its high labor intensity, limited coverage, low efficiency and easy to be affected by human factors, it gradually exposes many problems.

[0003] Many technologies currently try to use image processing, LiDAR point cloud data and deep learning to improve the automation and accuracy of tree barrier identification. Image-based tree barrier detection methods usually rely on edge detection, image segmentation, color space transformation and other traditional image processing techniques. However, these methods often perform poorly in the face of complex backgrounds and low-quality images, with low recognition accuracy and robustness. With the rise of deep learning, techniques using convolutional neural networks (CNN), object detection algorithms (such as YOLO, Faster R-CNN) for tree barrier identification have gradually emerged. Although deep learning methods perform well in image processing, their shortcomings are also obvious, mainly in the strong dependence on labeled data, high demand for computing resources, long training time and other issues. Especially in practical applications, the labeling work of many data sets is very tedious and expensive, and deep learning methods often require a large number of samples to achieve good recognition results, so in some data-lacking fields, the application of this method is limited.

[0004] LiDAR point cloud technology has also been widely used in recent years, especially in the precise positioning of tree barrier objects in three-dimensional space. LiDAR point cloud can provide detailed spatial data to help the system accurately identify the location and height of trees and obstacles. However, the cost of LiDAR technology is relatively high, and its data processing is complex, especially in the processing of high-density point cloud data, the accuracy of segmentation and classification is often limited. Moreover, the deployment and maintenance cost of LiDAR equipment is large, which is usually suitable for large-scale and long-term projects, but it is not economical for short-term and small-scale inspection tasks.

[0005] In view of the above technical deficiencies, the present technology proposes a tree barrier recognition method based on SIFT (Scale-Invariant Feature Transform) feature points, aiming to improve the accuracy and robustness of tree barrier recognition through classical feature point extraction techniques in image processing. SIFT algorithm has been widely applied in image recognition field, which extracts key feature points in image and realizes target detection and recognition through matching these feature points. Unlike traditional image segmentation methods, SIFT algorithm can effectively handle image rotation, scale change and partial occlusion problems, making it perform well in complex background and environment. At the same time, SIFT feature extraction has lower requirements for image quality, so it can obtain good recognition effect in relatively ordinary images.

[0006] The present technology combines the practical needs of SIFT feature point extraction and tree barrier recognition, and in the detection of tree barriers in power transmission corridors, SIFT algorithm is used to extract representative feature points from images, and matching algorithm is used to identify the position of trees or other obstacles. Compared with traditional image processing methods, SIFT feature extraction method can better cope with rotation, scale change and complex background in image, so as to improve the accuracy and stability of tree barrier detection. SIFT algorithm does not rely on large-scale labeled data set required by deep learning, so it has lower data requirement and is suitable for application in environment with difficult data acquisition.

[0007] This tree barrier recognition method based on SIFT feature points has obvious advantages compared with deep learning and LiDAR methods. It requires lower computing resources and can realize real-time processing on ordinary hardware, suitable for low-cost, fast deployment application scenarios. SIFT feature point method has lower requirements for image quality and can stably extract key features in low-resolution images, so it is particularly suitable for large-scale inspection tasks. SIFT feature point extraction algorithm has strong real-time performance and can realize fast recognition, meeting the demand for real-time and high efficiency in inspection. SUMMARY

[0008] In view of the above existing problems, the present technology aims to fill the gap in the prior art and provide a solution for efficiently and accurately identifying tree barriers in power transmission corridors in low-resource environments. By combining SIFT feature point extraction technology and tree barrier recognition requirements, this method can operate stably in complex background and occlusion conditions, and has strong application prospect.

[0009] To solve the above technical problems, a tree barrier recognition method based on SIFT feature points in power transmission corridors is proposed, which includes,

[0010] The high-definition RGB camera is carried by the unmanned aerial vehicle to take aerial photographs, image data of different types of trees in the power transmission line corridor area is taken, different growth stages and perspectives are covered, and the image data includes RGB images and multispectral images; the collected images are preprocessed, the median filter is used to remove noise generated under low light conditions, and the histogram equalization is used for image enhancement; SIFT feature points are extracted from the images, key feature points are extracted under different scales and rotation angles through the scale invariance characteristic, the contrast and stability of the key feature points are evaluated and screened, the feature descriptors are generated according to the neighborhood information of each feature point, and feature matching is performed; the nearest neighbor matching method based on the Lowe ratio test is used to match the SIFT feature points in the images and the pre-stored tree feature descriptors in the database, the classification and identification of the trees are performed, and it is determined whether each tree is a tree barrier; the spatial distribution of the trees is analyzed through the clustering algorithm, the tree area affecting the power transmission line is extracted, the distance between the spatial coordinates of the trees and the power transmission line is combined, and the geometric constraint model is used to determine whether the current trees constitute a tree barrier object; the performance is evaluated by using the evaluation index, and whether the trees will affect the power transmission line is further evaluated by the detection rate.

[0011] As a preferred scheme of the SIFT feature point-based power transmission corridor tree barrier identification method, the image data includes image data collected in the power transmission corridor area of different types of growing trees by the unmanned aerial vehicle platform with high-resolution shooting capability and the camera equipment carried by the unmanned aerial vehicle platform; the camera equipment adopts a multispectral camera; and the image data is collected simultaneously.

[0012] The constraint conditions for collecting the images are set as follows: condition one, the climate conditions and light changes are considered, the climate conditions include sunny days and cloudy days, and the light changes include morning, noon and evening; condition two, the flight height of the unmanned aerial vehicle is set as 80 meters according to the average height of the trees and the width of the power transmission corridor; condition three, the overlap degree between adjacent flight lines is set as 70% during the flight process; and condition four, one image is shot per second, and the flight line angle is adjusted every 30 meters during the flight process.

[0013] The tree objects in each image are labeled by manual labeling, including the types, positions and sizes of the trees, the image labeling tool LabelImg is used for labeling, each tree object is framed as a rectangular region, and the corresponding tree types are labeled; during the image labeling process, the height of the tree and the crown width of the tree based on the pixel ratio of the measuring tool and the image are recorded for each labeled tree object, wherein the height of the tree is measured by using the RTK positioning system carried by the unmanned aerial vehicle, and the actual height of each tree is calculated by combining the height data during the flight process of the unmanned aerial vehicle.

[0014] The flight route is planned in advance using flight planning software, the flight height, route spacing and image shooting frequency are input in the software, the unmanned aerial vehicle is automatically flown, and the image is automatically shot according to the set parameters, after the flight starts, the camera shoots the image according to the flight planning and the set frequency, after each flight is completed, the image is uploaded to the storage server using the data transmission equipment, and the shooting angle and image brightness of the camera are monitored in real time during the flight process;

[0015] All collected image data is transmitted to a local server and stored in a classified manner, and a RAID storage array is used for data redundancy backup, all image data is classified according to tree species, lighting conditions and shooting time, and an image index is established, and after the experimental data collection is completed, the image data quality is checked by visual inspection.

[0016] As a preferred scheme of the power transmission corridor tree barrier recognition method based on SIFT feature points, the pre-processing of the collected image comprises,

[0017] The collected image data is input, a 3x3 and 5x5 window median filter is selected for image denoising, the median value of all pixels in the neighborhood is calculated for each pixel in the image data, and the original pixel value is replaced with the median value, and the step is repeated until the noise in the image is suppressed;

[0018] The low-contrast image is enhanced by histogram equalization to ensure the distinguishability of the tree profile in a complex background, the gray level histogram of the input image data is calculated, and the cumulative distribution function of the image is calculated , the gray value range of the image is set as , wherein L is the gray level: ;

[0019] , wherein is the number of pixels of the gray value i, is the total number of pixels of the image, i is a variable index, and k is the number of gray values; each pixel value of the image is remapped using the cumulative distribution function to obtain an enhanced image: each pixel value is mapped to a new value:

[0020] ;

[0021] The local contrast limited adaptive histogram equalization method is used for histogram equalization in a local area, the image is divided into a plurality of 8x8 or 16x16 pixel local areas, histogram equalization is performed on each area, and the contrast is limited to grow, all areas are combined to obtain an enhanced overall image, wherein the limited contrast is: ;

[0022] wherein, is an upper limit of the control contrast, is the maximum pixel value of the image in the region;

[0023] Different perspectives and postures of the collected images are standardized by geometric transformation, and for each image, random rotation and scaling operations are performed by an affine transformation matrix.

[0024] As a preferred scheme of the SIFT feature point-based power transmission corridor tree barrier recognition method, the SIFT feature points are extracted from the image after image preprocessing, and a SIFT feature point extraction algorithm is used to extract robust feature points from the image:

[0025] The image is subjected to multi-scale Gaussian blur processing to generate a blurred image and construct a scale space;

[0026] In the scale space, potential feature points are found by calculating the local extreme value of the image;

[0027] The feature points are accurately positioned using Gaussian difference;

[0028] A direction is assigned to each feature point according to the gradient direction of the image, and the feature point direction assignment is performed;

[0029] Based on the neighborhood information of each feature point, a 128-dimensional feature descriptor is generated.

[0030] As a preferred scheme of the SIFT feature point-based power transmission corridor tree barrier recognition method, the feature matching includes comparing the feature points in the newly collected image with the calibrated images in the database, matching the feature descriptors generated by each feature point with the descriptors in the database through the nearest neighbor matching method based on Lowe's ratio test, and judging the reliability of the matching by the ratio of the minimum matching distance to the second smallest matching distance;

[0031] Specifically, for each feature point in the new image, the corresponding generated feature descriptor For all tree images in the database, the descriptors of all feature points are calculated, and the Euclidean distance between the new image and is calculated: ;

[0032] wherein, and are the values of the i-th dimension in the descriptors and ; and

[0033] select the two closest descriptors and wherein, is the minimum matching distance, is the second minimum matching distance;

[0034] According to and perform Lowe ratio test, i.e. filter out false matches by comparing the ratio of and calculate the ratio : ;

[0035] Set the matching threshold τ = 0.7, when (set threshold τ is usually 0.7), it is considered that the current feature point matching is valid; when , it is considered that the current feature point matching is invalid;

[0036] According to the matching result, the tree classification is carried out by a machine learning classification algorithm, the feature points with valid matching are assigned a label, the label is the tree category of the corresponding image, and the trees with assigned labels form a calibration data set.

[0037] As a preferred scheme of the SIFT feature point-based power transmission corridor tree barrier identification method, wherein: the classification and identification comprises, based on the result of feature matching, analysis of the spatial distribution of trees, extraction of the spatial coordinates of each tree , clustering the positions of the trees by a clustering algorithm, the position of each tree will be input data of the K-means algorithm, and the tree area threatening the power transmission line in the target image is identified,

[0038] Set the number of clusters K, i.e. divide the tree area into different groups according to the preset number of clusters, randomly initialize the centroids of the K clusters , each centroid is a two-dimensional coordinate , and is the two-dimensional coordinate of the kth centroid; Calculate the Euclidean distance of the tree points to the centroids of the clusters, for the ith tree point, the distance of the ith tree point to the kth centroid is: ;

[0039] Assign the tree points to the cluster to which the nearest centroid belongs, for the kth cluster, the new centroid of the cluster is determined by the mean value of all the tree points in the cluster: ;

[0040] wherein, and is the spatial coordinate of the i-th tree, is the number of tree points in the cluster, until the center of the cluster does not change or the preset maximum number of iterations is reached, after the clustering is completed, the tree density and distribution in each cluster are analyzed, and the area affecting the power transmission line is identified, when the tree density in each cluster is greater than 110 trees per hectare, the current area is considered to be a tree barrier area;

[0041] For extracting the spatial coordinates of each tree, geometric constraints and classification judgments are performed to determine whether the trees constitute a tree barrier object, the judgment rules including the horizontal distance of the tree from the power transmission line, the tree height, and the tree width

[0042] The horizontal distance of the tree from the power transmission line includes calculating the horizontal distance between the tree and the power transmission line, and according to the spatial position of the tree: ;

[0043] wherein D is the horizontal distance of the tree from the power transmission line, is the spatial coordinate of the power transmission line;

[0044] The tree height, when the height of the tree exceeds a set threshold , and the horizontal distance of the power transmission line is less than a threshold , the current tree is determined to be a tree barrier object;

[0045] The width of the tree in the image is calculated by contour detection of the image , when the width of the tree is greater than a set threshold , and the horizontal distance of the power transmission line is less than a threshold , the current tree is determined to be a tree barrier.

[0046] As a preferred scheme of the SIFT feature point-based power transmission corridor tree barrier identification method, the detection rate includes using the evaluation methods of accuracy, recall, precision, and F1 value as evaluation indicators to evaluate the performance;

[0047] The performance of different tree species is further evaluated by the tree barrier detection rate to determine whether the trees will affect the power transmission line;

[0048] wherein the tree barrier detection rate is calculated by comparing the detection results with the manually labeled tree barrier area: ;

[0049] When the tree barrier detection rate is greater than 90%, it is considered that the current tree species performs well in the current identification, the identification is accurate, and the current identification result can be adopted, wherein, is the number of regions correctly identified as tree barriers, is the total tree barrier region.

[0050] A computer device comprises a memory and a processor, and the memory stores a computer program, characterized in that the processor implements the steps of the SIFT feature point-based power transmission corridor tree barrier identification method when executing the computer program.

[0051] A computer readable storage medium stores a computer program, characterized in that the computer program is executed by a processor to implement the steps of the SIFT feature point-based power transmission corridor tree barrier identification method.

[0052] The present application has the following advantages: (1) The present application uses scale-invariant feature transform (SIFT) technology for feature point extraction, describes the key feature points in the tree image, and ensures that the unique features of the tree can be stably extracted under different viewing angles and different lighting conditions. The scale and rotation invariance of SIFT make the tree recognition more robust, effectively improving the accuracy of tree barrier identification.

[0053] Through the experimental test of various trees by the present application, the recognition accuracy and tree barrier detection rate are excellent. Especially when facing trees in different growth stages and different environments, the present application can effectively reduce misjudgment and omission, and ensure the accuracy of the identified trees as potential tree barriers.

[0054] (2) Through Lowe ratio test and nearest neighbor matching algorithm, the probability of false matching is greatly reduced, thereby effectively reducing the false tree barrier identification result. This optimization strategy compares the matching quality of each feature point, and only when the distance ratio of the two closest matching points meets the set threshold, the matching is considered effective, further ensuring the identification accuracy and reliability. In the method, the geometric constraint relationship between the tree and the power transmission line is combined, and by setting the distance threshold and the tree height and width limit, the problems of omission and misjudgment are effectively avoided. Even for trees in different growth stages, the judgment of whether they are tree barriers can be accurate and accurate, reducing the common omission phenomenon in traditional methods.

[0055] (3) Based on computer vision and image processing algorithms, it can automatically identify whether the trees are tree barriers, reducing the workload and time cost of manual inspection. In large-scale power transmission corridor inspection, it can quickly and accurately process a large amount of image data, greatly improving work efficiency. Through unmanned aerial vehicle or satellite remote sensing technology to obtain image data, the invention can realize real-time image preprocessing, feature extraction and matching, tree classification and tree barrier judgment, greatly improving the real-time monitoring and rapid response ability, especially suitable for rapid inspection and abnormal detection of power transmission lines.

[0056] (4) The invention can effectively identify different tree species, not only suitable for different tree species, but also cope with tree identification under different growth environments and climate conditions. In practical application, different types of trees and tree growth environments may have different effects on tree barrier formation, and the use of the invention can ensure high universality.

[0057] The scale invariance and rotation invariance of SIFT feature points make the invention still able to stably extract effective features under different lighting conditions and different viewing angles. Especially in complex climate conditions or mountainous areas, it can better adapt to different environmental challenges.

[0058] (5) Not only can it process RGB images, but also can analyze combined with depth image data, enhancing the accuracy and stability of tree barrier detection. For occluded or low-contrast tree regions, the additional spatial information provided by the depth image helps improve the accuracy of identification. By integrating SIFT features and machine learning algorithms (such as support vector machine SVM, k- nearest neighbor KNN, etc.), the method can automatically classify and judge trees, and combine the spatial distribution of trees with the geometric relationship of power transmission lines to intelligently determine which trees are tree barrier objects, further improving the intelligent level of tree barrier management.

[0059] (6) The automatic tree barrier identification system greatly reduces the demand and cost of manual inspection, and through unmanned aerial vehicle or other automatic equipment for image acquisition and using the invention for tree barrier identification, not only improves the inspection efficiency, but also saves a lot of labor and time cost. Through efficient and accurate identification of tree barriers, it can effectively prevent trees from affecting the safety of power transmission lines due to excessive height or excessive density, reduce power outages caused by tree barriers, and thus ensure the stable operation of the power system and improve the economic benefits of power companies.

[0060] (7) The application is not only suitable for power transmission corridor tree barrier identification, but also can be applied to other fields such as vegetation monitoring in agriculture and forestry. Due to the generality of the feature extraction and identification method, the tree classification model can be adjusted according to different application scenarios in the future to improve the applicability. The application can also be combined with other technologies such as unmanned aerial vehicle flight control system, three-dimensional modeling, map information system, etc., to further expand its application range. The tree barrier identification result can be combined with the geographic information of the power transmission line by combining GIS (Geographic Information System) technology, to realize more accurate positioning and management. BRIEF DESCRIPTION OF DRAWINGS

[0061] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0062] Figure 1 The overall flowchart of a SIFT feature point-based power transmission corridor tree barrier identification method provided by an embodiment of the present application.

[0063] Figure 2 The SIFT feature point extraction principle diagram of a SIFT feature point-based power transmission corridor tree barrier identification method provided by an embodiment of the present application.

[0064] Figure 3 The image matching algorithm flowchart of a SIFT feature point-based power transmission corridor tree barrier identification method provided by an embodiment of the present application.

[0065] Figure 4 The geometric constraint and classification judgment architecture diagram of a SIFT feature point-based power transmission corridor tree barrier identification method provided by an embodiment of the present application.

[0066] Figure 5 The multi-dimensional feature extraction module structure diagram of a SIFT feature point-based power transmission corridor tree barrier identification method provided by an embodiment of the present application. DETAILED DESCRIPTION

[0067] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings in the specification. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0068] In the following description, a lot of specific details are set forth in order to provide a thorough understanding of the present application. However, the present application can be practiced without the specific details, other than those described herein, and it is understood that the present application is not limited to the embodiments described herein and that the scope of the present application encompasses other variations, alternatives, and modifications than those described herein.

[0069] Embodiment 1, Reference Figures 1-5 As a first embodiment of the present application, the embodiment provides a transmission corridor tree barrier identification method based on SIFT feature points, comprising:

[0070] S1: Through the unmanned aerial vehicle carrying a high-definition RGB camera for aerial photography, image data of different types of trees in the transmission line corridor area are photographed, covering different growth stages and viewing angles, and the image data includes RGB images and multispectral images.

[0071] It should be noted that through the unmanned aerial vehicle platform with high resolution shooting capability and the camera equipment carried:

[0072] The unmanned aerial vehicle platform uses DJI Matrice 300 RTK unmanned aerial vehicle, which has a precise positioning system and can maintain stable flight in complex environments;

[0073] The camera equipment uses DJI Zenmuse H20T multispectral camera, which has 20MP high-definition RGB image shooting capability and supports near-infrared (NIR) image acquisition, which is convenient for subsequent multispectral image processing;

[0074] The device can simultaneously collect RGB images and multispectral images, has high resolution, and is suitable for a wide range of applications, especially for tree barrier monitoring in large areas such as transmission corridors.

[0075] Set the constraint conditions when collecting images:

[0076] Condition one, considering the climate conditions and light changes, the climate conditions include sunny and cloudy days, and the light changes include morning, noon and evening.

[0077] Condition two, according to the average height of the trees and the width of the transmission corridor, the flight height of the unmanned aerial vehicle is set to 80 meters; this flight height can ensure that the image collection covers the range, and at the same time, it will not cause the trees to be blocked due to too low height, and it is sufficient to ensure that the overall form of the trees can be clearly presented in the image.

[0078] Condition three, in order to obtain the complete information of the trees and ensure that the image has good overlap, the overlap between adjacent flight lines is set to 70% during flight.

[0079] Condition four, set every second to take a picture, and in the process of flight every 30 meters to adjust the flight path angle, so as to cover the tree information under different angles and fields of view.

[0080] By artificial labeling, the tree objects in each image are labeled, including the species, position and size of the tree, and the image labeling tool LabelImg is used for labeling. Each tree object is framed as a rectangular region, and the corresponding tree species is labeled. During the image labeling process, for each labeled tree object, the tree height and crown width based on the pixel ratio of the measuring tool and the image are recorded. The RTK positioning system carried by the unmanned aerial vehicle is used to measure the tree height, and the actual height of each tree is calculated by combining the height data during the flight of the unmanned aerial vehicle.

[0081] The flight planning software is used to plan the route in advance. After inputting the flight height, route spacing and image shooting frequency in the software, the unmanned aerial vehicle automatically flies and automatically shoots images according to the set parameters. After the flight starts, the camera shoots images according to the flight planning and the set frequency. Each image is saved as a JPEG format with a resolution of 20MP and an image size of about 5MB.

[0082] After each flight, the image is uploaded to the storage server using the data transmission device. The shooting angle and image brightness of the camera are monitored in real time during the flight.

[0083] All collected image data is transmitted to the local server and stored in categories. RAID storage array is used for data redundancy backup. All image data is classified according to tree species, lighting conditions and shooting time, and an image index is established. After the experimental data collection is completed, the image data quality is checked visually to ensure that the images are clear, without obvious distortion, excessive exposure or shadow problems. For images with poor quality due to weather, flight jitter or other factors, appropriate screening is performed to ensure the high quality of the final data set.

[0084] S2: Preprocess the collected images, remove noise generated under low light conditions using median filtering, and enhance the images through histogram equalization.

[0085] It should be noted that the collected image data is input, and a 3x3 and 5x5 window median filter is selected for image denoising. For each pixel in the image data, the median value of all pixels in the neighborhood is calculated, and the original pixel value is replaced with the median value. Repeat the steps until the noise in the image is suppressed. Let the pixel value of a point in the image be , the neighborhood of which is a k x k window, and the pixel values in the window are , where and , the replaced value For:

[0086] ;

[0087] wherein, represents the median of the pixel values in the neighborhood.

[0088] It should also be noted that the purpose of image enhancement is to improve the contrast and brightness of the image, so that the tree features in the image are more prominent, which helps the subsequent extraction of feature points. For tree images, especially in poor lighting or complex background conditions, enhancement processing is particularly important.

[0089] Specifically, the low-contrast image is enhanced by histogram equalization to ensure the recognizability of the tree contour in the complex background. The gray level histogram of the input image data is calculated, and the cumulative distribution function of the image is calculated , the gray value range of the image is set as , wherein L is the gray level number: ;

[0090] wherein, is the number of pixels with gray value i, is the total number of pixels of the image, i is the variable index, and k is the number of gray values; the cumulative distribution function is used to re-map each pixel value of the image to obtain the enhanced image: each pixel value is mapped to a new value : ;

[0091] Further, using the local contrast limited adaptive histogram equalization method, in some complex background, directly using global histogram equalization may cause over-enhancement or over-exposure, resulting in loss of details. Therefore, the CLAHE method is also used to perform histogram equalization in the local area to control the problem of over-enhancement.

[0092] Specifically, the image is divided into multiple local areas of 8x8 or 16x16 pixels, and histogram equalization is performed on each area respectively, and the growth of contrast is limited, and all areas are combined to obtain the enhanced overall image, wherein the limited contrast is: ;

[0093] wherein, is the upper limit of the control contrast, is the maximum pixel value of the image in the area;

[0094] Further, different perspectives and poses of the collected images are standardized by geometric transformation, and for each image, random rotation and scaling operations are performed by an affine transformation matrix.

[0095] Specifically, the rotation transformation formula is as follows: ;

[0096] where (x, y) is the coordinate in the original image, θ is the rotation angle, (x', y') is the coordinate after rotation.

[0097] Scaling transformation formula: ;

[0098] wherein, and are the scaling factors along the x and y axes; through the above denoising and enhancement processing, the image quality can be significantly improved. For images under different lighting conditions (such as overcast and evening), the brightness and contrast of the preprocessed image are more balanced, and the outline of the tree is clearer, especially in the case of complex background or tree partial occlusion, the detailed information in the image is effectively enhanced. The image processed in this way provides more accurate input for the subsequent SIFT feature point extraction.

[0099] Further, after the image preprocessing is completed, the SIFT feature point extraction algorithm is used to extract robust feature points from the image:

[0100] ① Construct a scale space: To achieve the scale invariance of the feature, first, the original image is subjected to layer-by-layer Gaussian blur processing and forms a multi-scale pyramid structure. Specifically, different standard deviations σ of the Gaussian kernel are applied to the input image to generate a sequence of progressively blurred images from low to high scales; each scale group contains several Gaussian blurred images, and the σ between adjacent scales increases by a fixed multiple. A complete scale space is formed by concatenating multiple scale groups, so that the feature points can be stably detected at different spatial resolutions.

[0101] ②Detect scale space extreme points: In the Gaussian scale space, by comparing each pixel point in its 26-neighborhood at its scale and adjacent upper and lower scales, the local maximum or minimum of the DoG (Difference of Gaussian) response is found as a potential feature point.

[0102] ③Feature point precise positioning: The Taylor expansion is used to optimize the sub-pixel level position and scale of the candidate extreme points, and the points with low contrast or located in unstable edge structure are removed, and only the key feature points with high stability are retained.

[0103] ​IV. Feature point direction assignment: A direction histogram is constructed according to the gradient amplitude and direction information of the feature point neighborhood, and a main direction is selected as the main direction of the feature point, thereby realizing rotation invariance.

[0104] V. Generating feature descriptors: A number of sub-regions are divided with the feature point as the center, and the gradient direction histogram is counted in each region, and finally the 128-dimensional SIFT descriptor is spliced to form a 128-dimensional SIFT descriptor, which is used for subsequent matching and classification recognition.

[0105] The Gaussian blur processing includes Gaussian blur processing of the original image with different standard deviations to generate images of different scales, and applying a Gaussian kernel function to each layer of image: ;

[0106] Wherein, σ is the standard deviation of blur, which controls the degree of blur; for each image of different scales, a group of blurred images is constructed using different scales (such as from σ = 1 to σ = 10), and each group of images is used as a pyramid level, and the scale gradually increases;

[0107] The Gaussian difference includes that SIFT highlights the local features of the image by calculating the difference between adjacent scales according to the generated blurred images, and the difference between two images of adjacent scales is calculated : ;

[0108] Wherein, and are the Gaussian kernel functions of the two images of adjacent scales; a Gaussian difference image is obtained, and extreme point search is performed on the Gaussian difference image, that is, local maximum and minimum values are found in the 26 neighborhood pixels around each pixel, and the current local extreme point is a potential feature point;

[0109] The positioning feature point includes correcting the position of the feature point by Taylor expansion, optimizing the coordinates of each feature point, and deleting the feature points with low contrast and unstable edges;

[0110] The feature point direction assignment includes that SIFT algorithm determines the direction of each feature point based on the gradient amplitude and gradient direction of its neighborhood pixels, first calculates the gradient according to the pixel intensity difference, and the calculation formula of the gradient is as follows: ;

[0111] Wherein, and are the gradients of the image in x and y directions; 、 、 , These represent the intensities of the four most direct neighboring pixels of a given pixel. , The gradient in the x-direction is calculated by comparing the intensity of the left and right neighbors of the pixel. , The gradient in the y-direction is calculated by comparing the intensity of the pixel's upper and lower neighbors. This invention employs a bivariate arctangent function. Calculate the true gradient direction for each pixel ; This invention can return the absolute direction angle within the range of (−π,π], accurately distinguishing the four quadrants, thereby ensuring the uniqueness and accuracy of the direction of the feature point; Then, the gradient directions of all pixels in the neighborhood of the feature point are accumulated into the orientation histogram at set angular intervals, and the direction with the largest amplitude in the histogram is selected as the main direction of the feature point. When there are secondary peaks with similar amplitudes, multiple additional directions can be generated to enhance the rotation invariance of the feature.

[0112] The feature descriptor includes the following steps: After determining the orientation of a feature point, SIFT generates a feature descriptor based on the neighborhood information of each feature point, dividing the neighborhood of each feature point into 16 sub-regions, each sub-region being 16x16 pixels in size; within each sub-region, the magnitude and direction of the gradient are calculated, and a histogram with 8 directions is generated; the 8-direction information of all 16 sub-regions is then sequentially concatenated into a 128-dimensional descriptor. , It is the gradient direction histogram of the i-th sub-region;

[0113] To ensure the robustness of feature descriptors to changes in illumination and noise, each descriptor is L2 normalized to avoid the impact of brightness variations in certain regions on matching accuracy.

[0114] Through the SIFT feature point extraction method described above, stable and reliable feature points can be obtained from each tree image, typically several hundred feature points. For example, 200 feature points may be extracted from a eucalyptus image, while 250 feature points may be extracted from a pine image. The number of feature points is related to the tree's shape, image resolution, and shooting angle.

[0115] Feature points are typically distributed in structurally rich areas such as the tree's outline and the junctions between branches and leaves. For example, feature points of eucalyptus trees are mostly concentrated around the crown, while those of cypress trees are concentrated at the junctions between the trunk and branches. These feature points are of great significance for subsequent tree category identification, location estimation, and modeling of the relative positional relationship between trees and transmission lines, enabling effective identification of tree obstacles in transmission corridors.

[0116] In summary, the application adopts multi-source data fusion, not only processes standard RGB images, but also analyzes multi-dimensional data such as depth images. In the depth image, the depth information of each pixel point can provide additional support for the spatial relationship between the trees and the power transmission line, thereby improving the recognition accuracy of the trees. Through multi-source data fusion, the application can overcome the influence of factors such as light and shielding, and better detect tree barriers.

[0117] The existing tree barrier recognition method generally only relies on a single type of image data (such as an RGB image), and ignores depth information. By combining additional information such as depth images, the application can better handle complex scenes, especially areas with shielding and dense trees.

[0118] S3: Extract SIFT feature points in the image, extract key feature points at different scales and rotation angles through the scale invariance property, evaluate and screen the contrast and stability of the key feature points, generate feature descriptors according to the neighborhood information of each feature point, and perform feature matching.

[0119] The evaluation and screening include: ① Contrast evaluation: calculate the local response value of the candidate feature point in the DoG (Gaussian difference) space, if the response amplitude is lower than the preset threshold, it is considered that the point is in a low-contrast area (such as a weak texture or noise area), such points are easy to fail in matching, and therefore are removed.

[0120] ② Stability screening (edge response suppression): to avoid retaining unstable feature points located on the strip-shaped edge, the principal curvature ratio H of the Hessian matrix is used for judgment: ;

[0121] Wherein, is the second-order partial derivative of the image in the x direction, reflecting the curvature of the feature point in the x direction; is the second-order partial derivative of the image in the y direction, reflecting the curvature of the feature point in the y direction; is the mixed second-order partial derivative of the image in the x and y directions, reflecting the cross curvature or rotation invariance of the feature point.

[0122] Calculate its trace and determinant, when the principal curvature ratio value exceeds the threshold (i.e. presents obvious one-way edge structure) or the determinant is negative, it is determined that the feature point is unstable and is deleted.

[0123] ③ Generate feature descriptors: for the feature points screened, construct local feature descriptors according to the amplitude and direction of the neighborhood gradient, which are used for subsequent feature matching.

[0124] Through the above contrast filtering and edge response suppression, the feature points with significant structure, stable positioning and high distinguishability can be effectively retained, thereby improving the subsequent matching accuracy and the reliability of tree barrier identification.

[0125] Further, in the feature matching, the feature points in the newly collected image are compared with the calibrated images in the database. Through the nearest neighbor matching method based on Lowe ratio test, the feature descriptor generated by each feature point is matched with the descriptor in the database, and the reliability of the matching is judged by the ratio of the minimum matching distance and the second minimum matching distance.

[0126] Specifically, for each feature point in the new image, the corresponding generated feature descriptor is calculated For all tree images in the database, the descriptors of all feature points are calculated, and the Euclidean distance between the new image and the descriptor is calculated ;

[0127] Among them, and are the values of the i-th dimension in the descriptors and ;

[0128] The two descriptors with the closest distance and are selected, where is the minimum matching distance, and is the second minimum matching distance.

[0129] According to and , Lowe ratio test is performed, that is, by comparing the ratio of and , the wrong matching is filtered out, and the ratio is calculated: ;

[0130] According to experience, the matching threshold τ=0.7 is set, when (set threshold τ is usually 0.7), it is considered that the current feature point matching is effective; when , it is considered that the current feature point matching is invalid.

[0131] According to the matching result, the tree is classified by a machine learning classification algorithm, the feature points with effective matching are assigned a label, the label is the tree category of the corresponding image, and the trees with assigned labels form a calibration data set.

[0132] ​In summary, the traditional tree barrier detection method depends on simple image difference analysis or traditional template matching algorithm, which is easily disturbed by light changes, tree shape differences and view angle changes in complex environments, resulting in low recognition accuracy and high misjudgment rate.

[0133] The present application adopts SIFT (Scale Invariant Feature Transform) feature point extraction technology to realize efficient recognition of tree images, so that the shape of the tree can be stably recognized in different environments, greatly improving the reliability of detection. SIFT technology has scale invariance and rotation invariance, and can extract stable and high-discrimination feature points under different viewing angles and different lighting conditions. Compared with traditional image recognition methods, SIFT can avoid the influence of environmental changes and shooting angle changes on the recognition result, thereby improving the robustness of tree barrier recognition.

[0134] S4: nearest neighbor matching method based on Lowe ratio test, matching SIFT feature points in the image and pre-stored tree feature descriptors in the database, classifying and identifying the tree, and determining whether each tree is a tree barrier.

[0135] Specifically, when performing feature matching, the feature points in the newly collected image are compared with the calibrated images in the database. Through the nearest neighbor matching method based on Lowe ratio test, the feature descriptors generated by each feature point are matched with the descriptors in the database, and the reliability of the match is judged by the ratio of the minimum matching distance to the second smallest matching distance.

[0136] Specifically, for each feature point in each new image, the corresponding generated feature descriptor is calculated For all tree image in the database, calculate the descriptor of all feature points, and calculate the Euclidean distance with the feature descriptor in the new image

[0137] Wherein, and are the values of the i-th dimension in the descriptors and

[0138] Select the two closest descriptors and , wherein, is the minimum matching distance, is the second smallest matching distance;

[0139] According to and , Lowe ratio test is performed, that is, by comparing the ratio of and , the wrong match is filtered out, and the ratio is calculated​​​ : ;

[0140] Set the matching threshold τ = 0.7, when (set threshold τ is usually 0.7), it is considered that the current feature point matching is valid; when , it is considered that the current feature point matching is invalid;

[0141] According to the matching result, the tree classification is carried out by the machine learning classification algorithm, the feature points with valid matching are assigned a label, the label is the tree category of the corresponding image, and the trees with assigned labels form a calibration data set;

[0142] In an optional embodiment of the present application, the machine learning classification algorithm can be a support vector machine, and the tree classification is carried out, specifically:

[0143] The 128-dimensional SIFT descriptor of each feature point is input as a feature vector into the SVM model;

[0144] According to the calibration data set, the SVM classifier is trained, and the classification of tree species according to the SIFT feature descriptor is learned;

[0145] After the training is completed, the feature points in the newly collected image are classified by using the SVM model, and the tree category is predicted;

[0146] The optimization objective of the SVM model training is to maximize the interval between two categories, so that the classification boundary has the minimum classification error rate, and the SVM optimization is: ; ;

[0147] Wherein, w is the normal vector of the hyperplane, b is the bias term, is the relaxation variable, is the training sample, is the category label.

[0148] In an optional embodiment of the present application, the machine learning classification algorithm can be a k-neighbor algorithm (KNN) for tree classification, and the k-neighbor algorithm classifies according to the distance between the new sample and all samples in the training set, specifically:

[0149] For each feature point in the newly collected image, the KNN algorithm calculates the Euclidean distance between each feature point and each feature point in the training set, selects the K nearest training samples, counts their category labels, and determines the category of the current feature point according to the label, and the majority category label is taken as the predicted category of the feature point: ;

[0150] wherein, is the predicted class.

[0151] By using the nearest neighbor matching method with Lowe ratio test, the feature points in the new image can be accurately matched with the feature points in the database, and the trees in the new image are classified by support vector machine (SVM) or k-nearest neighbor algorithm (KNN).

[0152] In summary, the prior art often relies on simple image features or color information in the process of tree classification, which lacks sufficient robustness and accuracy. By introducing the combination of SIFT feature matching and machine learning algorithm, the accuracy of tree classification can be significantly improved, and the trees in complex environment can be accurately distinguished.

[0153] In the process of tree recognition, the feature point matching method based on Lowe ratio test and machine learning algorithm (such as SVM or KNN) are used for tree classification. Lowe ratio test effectively filters out false matching points by analyzing the ratio of the minimum matching distance and the second smallest matching distance of each feature point, thereby ensuring the high accuracy of the matching result. For the classification of trees, by training the classification model, the trees can be automatically identified according to the feature descriptors of the trees, so as to intelligently classify the trees into potential tree barriers or non-tree barriers.

[0154] S5: Perform spatial distribution analysis on the positions of the trees by clustering algorithm, extract the tree area affecting the power transmission line, combine the spatial coordinates of the trees with the distance of the power transmission line, and use the geometric constraint model to judge whether the current tree constitutes a tree barrier object.

[0155] Further, based on the results of feature matching, the analysis of the spatial distribution of trees, the spatial coordinates of each tree are extracted, the positions of the trees are clustered by clustering algorithm, and the positions of each tree will be used as input data of K-means clustering algorithm to identify the tree area in the target image that poses a threat to the power transmission line,

[0156] Set the number of clusters K, i.e. divide the tree area into different groups according to the preset number of clusters, randomly initialize the centroids of K clusters Each centroid is a two-dimensional coordinate , , and is the two-dimensional coordinate of the kth centroid; Calculate the Euclidean distance of the tree points to each cluster centroid. For the ith tree point, the distance between it and the kth centroid is: ;

[0157] Cluster assignment: Assign tree points to the nearest cluster to which the centroid belongs; Centroid update: For the kth cluster, its new centroid is determined by the mean of all tree points in the cluster:

[0158] where, and are the spatial coordinates of the ith tree, is the number of tree points in the cluster, until the cluster center no longer changes significantly or reaches a preset maximum number of iterations, after clustering is completed, the density and distribution of trees in each cluster are analyzed, and the area affecting the power transmission line is identified, when the density of trees in each cluster is greater than 110 trees per hectare, the current area is considered to be a tree barrier area;

[0159] For extracting the spatial coordinates of each tree, geometric constraints and classification judgments are performed to determine whether the tree constitutes a tree barrier object, the judgment rules including the horizontal distance of the tree from the power transmission line, the tree height, and the tree width

[0160] The horizontal distance of the tree from the power transmission line includes calculating the horizontal distance between the tree and the power transmission line, according to the spatial position of the tree:

[0161] where D is the horizontal distance of the tree from the power transmission line, is the spatial coordinate of the power transmission line;

[0162] The tree height, when the height of the tree exceeds a set threshold , and the horizontal distance of the power transmission line is less than a threshold , the current tree is determined to be a tree barrier object;

[0163] The width of the tree in the image is calculated by contour detection of the image , when the width of the tree is greater than a set threshold , and the horizontal distance of the power transmission line is less than a threshold , the current tree is determined to be a tree barrier, the threshold is set to 5-12 meters according to experience and is automatically adjusted according to the voltage grade of the project line, the threshold is set to 30-50px (pixels) according to experience, which is used to filter out meaningless small vegetation or noise targets.

[0164] ​​Through the extraction of tree barrier areas and geometric constraint judgment, it can accurately identify which trees may constitute tree barriers, thereby affecting the safety of the power transmission line. Based on the clustering analysis of spatial position and the constraint conditions of geometric model, combined with the height and width of the trees, the potentially dangerous trees can be effectively screened out, and the tree barrier identification is further judged.

[0165] In summary, the traditional tree barrier judgment method depends on the visual features of the image (such as tree size, color, etc.), and these methods are easily affected by external factors (such as tree overlap, image blur, etc.). This method introduces a geometric constraint model, combines the spatial position of the trees and the relative position of the power transmission line, and determines whether the tree is a tree barrier by setting a threshold. In particular, by using the spatial coordinates of the trees and the distance relationship of the power transmission line, the horizontal distance D and the tree height H are calculated If the distance is less than the set threshold and the height is greater than the threshold, the tree is determined to be a tree barrier.

[0166] The introduction of this geometric model enhances the accuracy of tree barrier judgment and avoids the shortcomings of relying solely on image features. The tree barrier judgment combined with geometric constraints not only considers the appearance features of the trees themselves, but also considers the spatial relationship between the trees and the power transmission line, making the tree barrier identification more accurate, especially suitable for complex terrain and multi-tree species environment.

[0167] S6: Evaluate performance using evaluation indicators, and further evaluate whether the trees will affect the power transmission line through detection rate.

[0168] It should be noted that the performance of the evaluation method using the evaluation indicators of accuracy, recall rate, precision, and F1 value: accuracy Acc = (TP + TN) / (TP + TN + FP + FN);

[0169] Recall rate Rec = TP / (TP + FN);

[0170] Precision Pre = TP / (TP + FP);

[0171] F1 value F1-Score = 2 * [(Pre * Rec) / (Pre + Rec)];

[0172] Where: TP is the correctly identified tree barrier, TN is the correctly identified non-tree barrier, FP is the incorrectly identified non-tree barrier, and FN is the incorrectly identified non-tree barrier;

[0173] Further evaluate the performance of different tree species by tree barrier detection rate to determine whether the trees will affect the power transmission line;

[0174] Where, the tree barrier detection rate is calculated by comparing the detection results with the manually labeled tree barrier area: ;

[0175] When the tree barrier detection rate is greater than 90%, it is considered that the current tree species performs well in the current identification, the identification is accurate, and the current identification result can be adopted, wherein, is the number of correctly identified tree barrier regions, the region refers to a continuous tree area (such as a tree crown range or a tree community area) in artificial labeling that is identified as a tree barrier and is also judged as a tree barrier in system output, and each region is usually taken as a statistical unit in the form of a connected domain in an image, a tree clustering cluster or a risk unit based on spatial coordinates; is the total tree barrier region, and an artificial labeling personnel identifies all tree regions that may affect the power transmission line according to indexes such as tree height, distance from the conductor, tree crown coverage range, and the like, each region corresponds to an independent tree barrier judgment unit, and can be obtained based on image connected domains, polygon labeling boxes or geographical space partitioning.

[0176] When the tree barrier detection rate is greater than 90%, it is considered that the current tree species performs well in the current model identification, the system can stably and accurately identify the risk region thereof, and the identification result can be directly used for power transmission line tree barrier risk assessment.

[0177] Embodiment 2 is a second embodiment of the present application, and provides a power transmission corridor tree barrier identification method based on SIFT feature points. In order to verify the beneficial effects of the present application, scientific demonstration is performed through experiments.

[0178] A typical power transmission corridor region is selected in the experiment, which is about 3000 meters long and about 50 meters wide, and different types of trees grow in the corridor, including eucalyptus, camphor tree, broussonetia papyrifera, Chinese oak, tung tree, thuja, pine, cedar and bamboo, etc. The number, distribution and tree species of the trees in the region are relatively complex, which can better simulate the actual power transmission corridor environment.

[0179] In order to ensure the diversity of the data set, the nine typical trees are selected, and the growth characteristics and morphologies of these trees are quite different, including tall eucalyptus, pine and cedar, and relatively short bamboo and thuja. The tree height, crown shape and growth density of each tree are different, which represent the common tree types in the power transmission corridor.

[0180] (1) The identification results of the nine common trees are shown in Table 1, including the accuracy, precision, recall and F1-score of each tree category.

[0181] Table 1 Identification results

[0182] Result analysis:

[0183] From the experimental results, it can be seen that the method performs very well on different tree species, with an accuracy rate generally exceeding 90%, among which the recognition result of bamboo is the best, with an accuracy rate of 96.3% and an F1 value of 95.9%. This shows that the method can well identify whether most tree species are tree barriers, and has good universality.

[0184] ②Accuracy and precision: The accuracy and precision of almost all tree species are relatively high, especially for eucalyptus, tung tree and bamboo, with precision rates of 96.2%, 96.4% and 97.1% respectively. The recognition of these trees can reduce misjudgment and improve the reliability of transmission corridor tree barrier detection.

[0185] ③Recall rate and F1 value: The recall rate and F1 value are also excellent, indicating that the method not only effectively identifies whether a tree constitutes a tree barrier, but also minimizes missed detection. Especially for eucalyptus and tung tree, their recall rates are close to 90% or above, and their F1 values remain above 94%.

[0186] ④Performance of specific tree species: For some trees, such as balsa and pine, although their precision and recall rates are slightly lower, their overall recognition ability is still reliable, which is closely related to the shape characteristics and growth environment of different trees. For some highly similar tree species, the method may need more image data for training and adjustment to improve its classification accuracy.

[0187] (2) Analysis of tree barrier detection rate

[0188] The tree barrier detection rate results for 9 typical tree species are shown in Table 2:

[0189] Table 2 Detection rate results

[0190] Results analysis:

[0191] ①High detection rate: From the experimental results, it can be seen that for tung tree, bamboo, eucalyptus, pine and other tree species, the tree barrier detection rate is above 90%, especially for bamboo, with a tree barrier detection rate of 95%. This shows that the recognition method based on SIFT feature points performs very well on these tree species, and can accurately identify the areas that may constitute tree barriers.

[0192] ②Lower detection rate: For balsa and pine, the tree barrier detection rate is relatively low, at 78% and 85% respectively. This phenomenon may be related to the morphological characteristics and distribution density of these trees. The trunks and crowns of balsa and pine are relatively slender and sparse, which may lead to inaccurate feature matching in the recognition process, thereby affecting the accurate recognition of tree barriers.

[0193] ③Influencing factors: The differences in tree barrier detection rates are related to multiple factors, including the growth morphology of trees, the similarity between trees, the spatial distribution of trees, and image quality. For complex or similar tree shapes, the matching of SIFT features may be affected, resulting in lower tree barrier detection rates.

[0194] This method shows high detection rates in most tree species, especially for tree species with thick trunks and obvious morphological characteristics, such as bamboo and oil camphor trees. The tree barrier detection rate is very high. For images taken under complex backgrounds, partially occluded trees, or different lighting conditions, the system still maintains high recognition accuracy, with a false detection rate of less than 5%, proving the high reliability of this method in handling these trees. This method can achieve efficient tree barrier detection in most trees, especially in power line maintenance, effectively identifying tree areas that may affect line safety, and improving the efficiency and accuracy of tree barrier management.

[0195] In summary, this embodiment shows that the tree barrier recognition method based on SIFT feature points has high accuracy and good robustness in power corridor tree recognition and tree barrier detection. It has shown high accuracy and stability in tree barrier detection of most trees, especially under different tree species, different growth stages, and different viewing angles. It can provide an effective tree barrier recognition solution. Compared with traditional image processing methods and deep learning methods, this method has obvious advantages in data demand, computing efficiency, and real-time performance. By integrating with other sensor data (such as LiDAR point clouds), the system can further improve the accuracy and stability of tree barrier detection, and adapt to changing environments and conditions.

[0196] Embodiment 3, the third embodiment of the present application, which is different from the first two embodiments:

[0197] If the function is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes instructions for making a computer device (which can be a personal computer, server, or network device, etc.) execute all or part of the steps of the methods described in the embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk, and various media that can store program codes.

[0198] The logic and / or steps represented in the flow diagrams and / or otherwise described herein, for example, can be considered as a sequence of executable instructions, and can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. Just by way of example, a "computer-readable medium" can be any means for storing, communicating, propagating, or transporting a program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable medium can have the non-transitory nature of any stored content only exemplarily.

[0199] More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection (electronic) having one or more wires, a portable computer diskette (magnetic), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can also be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, for example, via an optical scanner, then compiled, interpreted, or otherwise processed, and stored in a computer memory in a form that can be later executed by a computer.

[0200] It should be understood that aspects of the application can be implemented in hardware, software, firmware or combinations thereof. In the above embodiments, various steps or methods can be implemented in software or firmware that is stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any of the following technologies and combinations thereof can be used: a discrete logic circuit having logic gates for implementing logic functions upon data signals, an application specific integrated circuit having appropriate combinational logic gates, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

Claims

1. A method for identifying tree obstacles in power transmission corridors based on SIFT feature points, characterized in that: include, A drone equipped with a high-definition RGB camera was used to take aerial photos of different types of trees in the power transmission line corridor area, covering different growth stages and perspectives. The image data included RGB images and multispectral images. The acquired images are preprocessed, with median filtering used to remove noise generated under low lighting conditions, and histogram equalization used for image enhancement. SIFT feature points are extracted from the image. Key feature points are extracted at different scales and rotation angles by leveraging the scale invariance property. The contrast and stability of key feature points are evaluated and filtered. Feature descriptors are generated based on the neighborhood information of each feature point, and feature matching is performed. The nearest neighbor matching method based on Lowe's ratio test matches SIFT feature points in the image with pre-stored tree feature descriptors in the database to classify and identify trees and determine whether each tree is a tree obstacle. By using clustering algorithms to analyze the spatial distribution of trees, the areas of trees that affect power transmission lines are extracted. By combining the spatial coordinates of the trees with the distance to the power transmission lines, a geometric constraint model is used to determine whether the current trees constitute tree obstacles. Performance is evaluated using assessment metrics, and the impact of trees on power transmission lines is further assessed using detection rates.

2. The method for identifying tree obstacles in power transmission corridors based on SIFT feature points as described in claim 1, characterized in that: The image data includes images captured by a drone platform with high-resolution shooting capabilities and its onboard camera equipment: the drone platform; the camera equipment, which uses a multispectral camera; and the simultaneous acquisition of image data in the power transmission corridor area where different tree species grow. The constraints for image acquisition are as follows: Condition 1: Consider weather conditions and light variations, including sunny and cloudy days, and light variations including early morning, noon, and evening; Condition 2: Based on the average height of trees and the width of the power transmission corridor, set the drone's flight altitude to 80 meters; Condition 3: Set the overlap between adjacent flight paths to 70% during flight; Condition 4: Set the drone to capture one image per second and adjust the flight path angle every 30 meters during flight. Each tree in the image is labeled manually, including its species, location, and size. The LabelImg image annotation tool is used for annotation, with each tree object defined as a rectangular area and labeled with its corresponding tree species. During the image annotation process, for each labeled tree object, the tree height and crown width are recorded based on the measurement tool and the pixel ratio of the image. In particular, the tree height is measured using the RTK positioning system on the drone, and the actual height of each tree is calculated by combining the altitude data during the drone's flight. Flight planning software is used to plan routes in advance. After inputting the flight altitude, route spacing, and image capture frequency in the software, the drone flies automatically and captures images according to the set parameters. After the flight starts, the camera captures images according to the flight plan and the set frequency. After each flight, the images are uploaded to the storage server using a data transmission device. During the flight, the camera's shooting angle and image brightness are monitored in real time. All acquired image data was transmitted to a local server and stored in a categorized manner. RAID storage arrays were used for redundant data backup. All image data was categorized according to tree species, lighting conditions, and shooting time, and an image index was established. After the experimental data acquisition was completed, the image data quality was visually inspected.

3. The method for identifying tree obstacles in power transmission corridors based on SIFT feature points as described in claim 2, characterized in that: The preprocessing of the acquired images includes, Input the acquired image data, select the median filter of 3x3 and 5x5 windows for image denoising, calculate the median of all pixels in the neighborhood for each pixel in the image data, and replace the original pixel value with the median. Repeat the steps until the noise in the image is suppressed. Histogram equalization is used to enhance low-contrast images, ensuring the legibility of tree outlines against complex backgrounds. The gray-level histogram of the input image data is calculated, and the cumulative distribution function of the image is also computed. Set the grayscale value range of the image to Where L is the number of gray levels: ； in, Let i be the number of pixels with grayscale value i. Let i be the total number of pixels in the image, i be the variable index, and k be the number of grayscale values. The cumulative distribution function is used to remap each pixel value to obtain the enhanced image: [The text then abruptly shifts to a different topic:] ...the total number of pixels in the image, i is the variable index, and k is the number of grayscale values; ...the cumulative distribution function is used to remap each pixel value... Mapped to new value : ； A local contrast-limited adaptive histogram equalization method is used to perform histogram equalization within local regions. The image is divided into multiple 8x8 or 16x16 pixel local regions, and histogram equalization is performed on each region separately, while limiting the increase in contrast. All regions are then merged to obtain the enhanced overall image. The method limits the contrast increase. for: ； in, To control the upper limit of contrast, The maximum pixel value of the image within the region; Images are standardized by geometric transformation for different viewpoints and poses. For each image, random rotation and scaling operations are performed using an affine transformation matrix.

4. The method for identifying tree obstacles in power transmission corridors based on SIFT feature points as described in claim 3, characterized in that: The step of extracting SIFT feature points from an image includes, after image preprocessing, using the SIFT feature point extraction algorithm to extract feature points from the image: The image is subjected to multi-scale Gaussian blurring to generate a blurred image, and a scale space is constructed. In scale space, potential feature points are found by calculating local extrema of the image; Use the difference of Gaussians to accurately locate feature points; Assign an orientation to each feature point based on the gradient direction of the image, and assign the feature point orientation value. Based on the neighborhood information of each feature point, a 128-dimensional feature descriptor is generated.

5. The method for identifying tree obstacles in power transmission corridors based on SIFT feature points as described in claim 4, characterized in that: The feature matching includes, during feature matching, comparing feature points in the newly acquired image with images calibrated in the database, matching the feature descriptor generated for each feature point with the descriptor in the database using the nearest neighbor matching method based on the Lowe ratio test, and judging the reliability of the matching by the ratio of the minimum matching distance to the second minimum matching distance. Specifically, for each feature point in a new image, the corresponding generated feature descriptor is calculated. For all tree images in the database, calculate the descriptors of all feature points and compare them with those in the new image. Euclidean distance: ； in, and Descriptors and The value of the i-th dimension; Select the two closest descriptors and ,in, To minimize the matching distance, This is the second smallest matching distance; according to and Conduct a Lowe ratio test, that is, by comparing and The ratio is used to filter out incorrect matches; the ratio is calculated. : ； Set the matching threshold τ=0.7, when If the current feature point match is valid, then the current feature point match is considered valid; when The current feature point match is considered invalid. Based on the matching results, the trees are classified using a machine learning classification algorithm. Labels are assigned to the valid matching feature points, with each label representing the tree category in the corresponding image. The labeled trees are then used to form a calibration dataset.

6. The method for identifying tree obstacles in power transmission corridors based on SIFT feature points as described in claim 5, characterized in that: The classification and identification includes analyzing the spatial distribution of trees based on feature matching results and extracting the spatial coordinates of each tree. The location of trees is clustered using a clustering algorithm. The location of each tree is used as input data for the K-means algorithm to identify tree regions in the target image that pose a threat to power transmission lines. Set the number of clusters K, that is, divide the tree region into different groups according to the preset number of clusters, and randomly initialize the centroids of K clusters. Each centroid is a two-dimensional coordinate. , and Let be the two-dimensional coordinates of the k-th centroid; Calculate the Euclidean distance from each tree point to the centroid of each cluster. For the i-th tree point, calculate its distance to the k-th centroid. for: ； Assign tree points to the clusters whose centroids are closest to them. For the k-th cluster, its new centroid is determined by the mean of all tree points within the cluster. ； in, and Let i be the spatial coordinates of the i-th tree. The number of tree points in a cluster is used until the center of the cluster remains unchanged or the preset maximum number of iterations is reached. After clustering is completed, the tree density and distribution in each cluster are analyzed to identify areas that affect the power transmission line. When the tree density in each cluster is greater than 110 trees / hectare, the current area is considered to be a tree barrier area. For each tree, its spatial coordinates are extracted, and geometric constraints and classification judgments are applied to determine whether the tree constitutes a tree obstacle. The judgment rules include the horizontal distance between the tree and the power transmission line, the tree height, and the tree width.

7. The method for identifying tree obstacles in power transmission corridors based on SIFT feature points as described in claim 6, characterized in that: The horizontal distance between the trees and the power transmission line includes calculating the horizontal distance between the trees and the power transmission line based on the spatial location of the trees: ； Where D is the horizontal distance from the tree to the power transmission line. These are the spatial coordinates of the power transmission line; The tree height, when the tree height Exceeding the set threshold And the horizontal distance of the transmission line Less than the threshold If so, the current tree is determined to be a tree obstacle; The width of the trees in the image is calculated through contour detection. When the width of the tree Greater than the set threshold And the horizontal distance of the transmission line Less than the threshold If so, the current tree is determined to be a tree obstacle.

8. The method for identifying tree obstacles in power transmission corridors based on SIFT feature points as described in claim 7, characterized in that: The detection rate includes the performance evaluation of the method using metrics such as accuracy, recall, precision, and F1 score. The tree obstacle detection rate is used to further evaluate the performance of different tree species and determine whether trees will affect power transmission lines. Among them, tree obstacle detection rate It is calculated by comparing the test results with manually marked tree barrier areas: ； When the tree obstacle detection rate is greater than 90%, the current tree species is considered to have performed well in the current identification process, the identification is accurate, and the current identification result is considered usable. To correctly identify the number of areas that are tree barriers, This refers to the total tree-blocked area.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method for identifying tree obstacles in a power transmission corridor based on SIFT feature points, as described in any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for identifying tree obstacles in a power transmission corridor based on SIFT feature points, as described in any one of claims 1 to 8.

Images