Overhead Power Line Detection from UAV Video Images

Currently, unmanned aerial vehicles (UAVs) are applied to routine inspection tasks of electric distribution networks. As an important information source, machine vision attracts much attention in the area of the UAV's autonomous control. To this end, real-time algorithms are studied in this paper to detect the power lines in the UAV video images. First, video images are converted into binary images through an adaptive thresholding approach. Then, Hough Transform is used to detect line candidates in the binary images. Finally, a fuzzy C-means (FCM) clustering algorithm is used to discriminate the power lines from the detected line candidates. The properties of power lines are used to remove the spurious lines, and the length and slope of the detected lines are used as features to establish the clustering data set. Experimental results show that the algorithms proposed are effective and able to tolerate noises from complicated terrain background and various illuminations.