基于输电线路图像边缘斜率突变的改进型Freeman链码断股缺陷识别研究

Research on Strand Broken Defect Recognition of Improved Freeman Chain Code Based on Image Edge Slope Mutation of Electric Transmission Line

阐述了当前无人机航拍图像缺陷识别的现状和存在的问题,提出了一种基于图像边缘斜率突变检测的改进型Freeman链码断股识别方法,该方法以改进Freeman链码寻址和图像边缘斜率几何特点为基础,以寻址像素点为单位按一定间隔取直线上的2点求直线斜率,观察不同取值斜率是否有突变,用以判定直线是否有突变点,进而判断导线是否有断股缺陷。选取18张各类无人机航拍典型图像作为试验样本,使用MATLAB软件对提出的新方法进行仿真,验证了新方法导线断股缺陷识别的高效性和准确性。

It illustrated the current situation and existing problems of the defect recognition of aerial image of UAV(unmanned aerial vehicle),and proposed a method of strand broken defect recognition of improved freeman chain code based onimage edge slope muta⁃tion detection.The method was based on improved freeman chain code addressing and the geometric characteristics of image edge slope.Taking the addressing pixel points as the unit and selecting 2 points on the straight line to calculate the slope.It observed whether there was a sudden change in the slopes of different values,so as to determine whether there was a sudden change point in the straight line,and then judged the broken strands.It selected 18 typical aerial images of various UAV as experimental samples.It simulated the new method using MATLAB software,and proved the efficiency and accuracy of the new method.