An algorithm for radar power line detection with tracking

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.