基于改进Canny算子的树障与导线边缘检测算法  

Tree barrier and wire edge detection algorithm based on improved canny operator

作　　者：穆晓飞 刘红喜[2] 方俊 MU Xiaofei;LIU Hongxi;FANG Jun(School of Information and Control Engineering,Jilin Institute of Chemical Technology,Jilin Jilin 132022,China;School of Electrical and Information Engineering,Changchun Institute of Technology,Changchun 130012,China)

机构地区：[1]吉林化工学院信息与控制工程学院,吉林吉林132022 [2]长春工程学院电气与信息工程学院,长春130012

出　　处：《智能计算机与应用》2024年第1期200-203,208,共5页Intelligent Computer and Applications

基　　金：吉林省教育厅科学技术研究项目(JJKH20210691KJ)。

摘　　要：针对目前输电线路通道树障检测中,树障与导线的边缘信息难以提取、不清晰以及连续性差等问题,提出一种基于改进Canny算子的树障与导线边缘检测算法。首先使用可以去噪保边的双边滤波取代传统Canny算子中的高斯滤波,使得树障与导线图片的边缘信息得以确保清晰,同时图片边缘更加细腻;然后使用基于Scharr算子3×3的梯度模板代替2×2的模板来改进梯度计算方法,在水平和垂直方向上扩充了45°和135°,两个方向的梯度模板加权求和;其次,对改进后的梯度幅值实施非极大值抑制,减少边缘检测带来的不利影响以使边缘变细;最后使用双阈值算法确定真实与虚假边缘,实现目标图片的边缘检测,减少干扰。实验结果表明,图片的边缘清晰度分别为8.53、0.474、12.93。改进后的算法对树障与导线边缘检测的结果相对于传统算法具有更好的边缘清晰度,可以清晰地观察树障与导线。In view of the marginal information of the tree barrier and the wire is difficult to extract,unclear and with poor continuity in the current transmission line channel tree barrier detection,the tree barrier and wire edge detection algorithm based on the improved Canny operator is proposed.Firstly,the bilateral filter that can remain edge while removing noise is used to replace the Gaussian filter in the traditional Canny operator so that we can ensure the marginal information of the tree barrier and the wire picture is clear,as well as the edge of the picture is more delicate.Then,a gradient template based on Scharr operator 3×3 is used to replace the 2×2 template to improve the gradient calculation method,and the weighted sum of gradient templates in 45°and 135°directions is expanded in the horizontal and vertical directions.Secondly,non-maximum suppression is applied to the improved gradient amplitude to reduce the adverse effects of edge detection to make the edge thinner.Finally,the double threshold algorithm is used to determine the real and false edges to achieve the target image edge detection and reduce interference.The results of the experiment indicate that the marginal sharpness of the pictures is 8.53,0.474 and 12.93 respectively.Compared with the traditional algorithm,the improved algorithm detects the edge of the tree barrier and the wire with better marginal clarity and can clearly observe the tree barrier and the wire.

关 键 词：树障与导线边缘检测 CANNY算子 双边滤波 Scharr算子 边缘清晰度 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]