摘要
从具有复杂地物背景的无人机拍摄图像中快速准确地检测到电力线,是树障清理机器人在工作中的一个关键问题。通过分析图像中的电力线的特征,提出一种复杂地物背景下电力线检测的方法。首先对原始图像进行图像均衡处理,增强电力线与背景之间的对比度;采用Hessian算法对电力线边缘进行提取与对比;进一步利用Hough变换实现对电力线的提取,并通过聚类方法对直线进行筛选,最终获得完整的电力线。实验结果表明,本方法在复杂背景下,对电力线提取的准确率较高,且提取出的电力线完整程度较好。
Fast and accurate detection of power lines from images taken by UAV with a complex background is a key problem in the work of tree block cleaning robots. In this paper, by analyzing the characteristics of power lines in images, a method for power line detection in a complex background is proposed. First, the equalization processing is performed on original images to increase the contrast between power lines and background. Then the Hessian algorithm is used to detect the edge of power lines, further the Hough transform is used to extract power line and linear screening method based on k-means++ cluster is used to extract the power line. The experimental results show that the method has higher accuracy and completion of power line extraction in a complex background.
作者
张秋雁
杨忠
陈聪
胡国雄
韩家明
许昌亮
赖尚祥
ZHANG Qiuyan;YANG Zhong;CHEN Cong;HU Guoxiong;HAN Jiaming;XU Changliang;LAI Shangxiang(Electric Power Research Institute of Guizhou Power Grid Co., Ltd., Guiyang 550000, China;College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China)
出处
《应用科技》
CAS
2019年第5期51-56,共6页
Applied Science and Technology
基金
国家自然科学基金项目（61473144）
中国南方电网有限责任公司科技项目（066600KK52170074）
