Computer Engineering and Applications ›› 2016, Vol. 52 ›› Issue (22): 198-202.

Previous Articles     Next Articles

Power line extraction method in complex ground object background

LI Cailin, FENG Zhaohui, DENG Xiaojing, HAN Lei   

  1. School of Civil and Architectural Engineering, Shandong University of Technology, Zibo, Shandong 255000, China
  • Online:2016-11-15 Published:2016-12-02

复杂地物背景下的电力线提取方法

李彩林,冯朝晖,邓晓景,韩  磊   

  1. 山东理工大学 建筑工程学院,山东 淄博 255000

Abstract: With the high-speed development of unmanned aerial vehicle in power line detection, acquiring the power line in aerial images has become the foundation of the detection research. And how to catch the completed power line in complex background has been the focus in power line research field, which can’t wait to solve. Thus the thesis puts forward a line-recovering method based on features, which can manage to connect the fragmented power line according to their geometry features after the arithmetic and transform. The experimental result shows it can track the intact power line, which has an accurate position. Except that, the thesis has the advantages of simplicity and stabilization and makes great effect on power line detection.

Key words: unmanned aerial vehicle, power line detection, Canny arithmetic, Hough transform, line-recovering method based on features

摘要: 随着无人机航拍在电力线巡检领域的快速发展,提取航拍影像中的电力线成为巡检工作的前提和基础,如何从背景复杂的航拍影像中提取出完整的电力线,成为电力线巡检中亟待解决的问题。在利用Canny算子提取图像边缘、Hough变换生成破碎直线段的基础上提出一种根据电力线的几何特征恢复完整电力线的算法。利用实际航拍影像进行实验验证,结果表明算法可以在复杂的背景中提取出完整且位置准确的电力线,实验结果稳定,对电力线巡检工作具有重要意义。

关键词: 无人机, 电力线巡检, Canny算子, Hough变换, 线特征恢复