ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume IV-2/W7
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., IV-2/W7, 227–234, 2019
https://doi.org/10.5194/isprs-annals-IV-2-W7-227-2019
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., IV-2/W7, 227–234, 2019
https://doi.org/10.5194/isprs-annals-IV-2-W7-227-2019

  16 Sep 2019

16 Sep 2019

AUTOMATIC EXTRACTION OF POWER LINES FROM UAV LIDAR POINT CLOUDS USING A NOVEL SPATIAL FEATURE

M. Zhou1, K. Y. Li1,2, J. H. Wang1, C. R. Li1, G. E. Teng1, L. Ma1, H. H. Wu1, W. Li1, H. J. Zhang1, J. Y. Chen1, and L. S. Chen1,2 M. Zhou et al.
  • 1Key Laboratory of Quantitative Remote Sensing Information Technology, Academy of Opto-Electronics, Chinese Academy of Sciences, Beijing 100094, China
  • 2University of Chinese Academy of Sciences, Beijing 100049, China

Keywords: Power Line Extraction, UAV LiDAR, 3D Spatial Features, Linear Elements

Abstract. UAV LiDAR systems have unique advantage in acquiring 3D geo-information of the targets and the expenses are very reasonable; therefore, they are capable of security inspection of high-voltage power lines. There are already several methods for power line extraction from LiDAR point cloud data. However, the existing methods either introduce classification errors during point cloud filtering, or occasionally unable to detect multiple power lines in vertical arrangement. This paper proposes and implements an automatic power line extraction method based on 3D spatial features. Different from the existing power line extraction methods, the proposed method processes the LiDAR point cloud data vertically, therefore, the possible location of the power line in point cloud data can be predicted without filtering. Next, segmentation is conducted on candidates of power line using 3D region growing method. Then, linear point sets are extracted by linear discriminant method in this paper. Finally, power lines are extracted from the candidate linear point sets based on extension and direction features. The effectiveness and feasibility of the proposed method were verified by real data of UAV LiDAR point cloud data in Sichuan, China. The average correct extraction rate of power line points is 98.18%.