High Speed Automatic Power Line Detection and Tracking for a UAV-Based Inspection

摘要

Detection and tracking power lines in complex environments is one of the most important and challenging tasks for UAV-based inspection. This paper presents a novel method of power lines detection and tracking. Firstly, the Hough transform is used to extract line segments of power lines. Secondly, according to the characteristics of power lines in the aerial images, we use K-means in the Hough space to cluster and filter the straight lines, and then detect power lines. Finally, a Kalman filter is used to track the power lines in the Hough space, based on the continuity of a video sequence. The experimental results demonstrate that the proposed approach is effective for automatic power line detection and tracking in complex environments.