Object-aware power line detection using color and near-infrared images

Abstract

Vision-based power line detection (PLD) is an important yet challenging problem in low-altitude flight. Different from the traditional PLD methods, which only aim at line information, we propose a novel object-aware PLD method to obtain better detection performance. A new definition of power line is first proposed to present its object-aware properties; and then a cascaded PLD scheme is devised with line detection, region filtration, and object validation based on corresponding image cues in joint color (RGB) and near-infrared (NIR) images. Considering that the primary goal of PLD is to capture all potential information and decrease the false negatives, we first treat the universal line shape in pixel from joint RGB-NIR images as a basic feature to explore general line candidates. To further pick out the accurate regions occupied by power lines, on the one hand we filter the false candidates based on the region-based intensity of special material characteristics in NIR, and on the other hand we validate the power lines according to the color features in RGB. The experiments demonstrate the advantages of our proposed method in three aspects: good detection accuracy, high true detection rate, and low false detection rate.