An Algorithm for Radar Power Line Detection （雷达电源线路检测的算法）.pdf

An Algorithm for Radar Power Line Detection with Tracking Qirong Ma , Darren S. Goshi , Long Bui , and Ming-Ting Sun University of Washington, Seattle, WA 98195, USA E-mail: qm, mts@ee.washington.edu Honeywell Corporation, Torrance, CA 90504, USA Abstract—In this paper we deal with the problem of power line detection from millimeter-wave radar video. We propose an algorithm that is based on Hough Transform, Support Vector Machine, and particle filter tracking. We explore the defining characteristics of the power lines in the radar video, and present an approach to utilize these characteristics together with the temporal correlation property of the power line objects. The particle filter framework naturally captures the temporal correlation of the power line objects, and the power-line-specific feature is embedded into the conditional likelihood measurement process of the particle filter. Experimental result validates the effectiveness of the power line detection approach. I. INTRODUCTION For the flight safety of helicopters, power-line-strike acci- dent has been a substantial threat [5]. Most of these accidents happened at night, thus an automatic power line detection and warning system for helicopters that can work anytime is highly desirable to ensure helicopter flight safety. A few previous works have been developed for power line detection with Fig. 1: B-scope image of a scene that contains power lines radar [1][8][10]. However, these works provide no automatic