摘要
针对复杂背景输电线路图像识别的难题,结合深度计算和阈值分割技术,开展了基于双目视觉的SGC立体匹配算法的研究及应用。对标准图像库及实际获取图像进行了测试,分析了算法的误匹配率和运行时间,结果表明,基于SGC立体匹配算法得到了效果良好的视差图,通过阈值分割可有效检测出复杂背景输电线路图像中的输电线。
In order to solve the problem of image recognition for transmission lines with a complex background,this paper carries out the research and application of SGC stereo matching algorithm based on binocular vision combined with depth calculation and threshold segmentation technology.Through the experiments on the standard image database and actual image,the false match rate and running time of the algorithm is analyzed.The results show that the SGC algorithm gets a good disparity map,and the transmission line on the transmission line image with a complex background can be effectively detected by the threshold segmentation.
作者
毛天奇
王传策
李云
张敏
陈玉
MAO Tianqi;WANG Chuance;LI Yun;ZHANG Min;CHEN Yu(Guizhou Power Grid Corporation Limited, Zunyi 563000, China;School of Electrical Engineering,Xi’an Jiaotong University, Xi’an 710049, China;Northwest University, Xi’an 710127, China)
出处
《智慧电力》
北大核心
2018年第12期105-111,共7页
Smart Power
基金
国家自然科学基金青年科学基金资助项目(61701404)
中国南方电网有限责任公司科技项目(GZKJXM20170280)~~
关键词
输电线路
复杂背景
双目视觉
SGC算法
立体匹配
transmission line
complex background
binocular vision
SGC algorithm
stereo matching
