Power Line Segmentation by Multilevel Attention From Hough Domain

Ning Wei, Yuyang Jin, Zhiping Dan, Na Liu, Fangzheng Peng, Shuifa Sun

Abstract: Power line segmentation is one of the fundamental and important research topics in unmanned aerial vehicles (UAVs)-based smart grid inspection. However, due to the dilemma that the power line feature is vulnerable in complex backgrounds but its extension is huge in spatial, even when using convolutional neural network (CNN)-based models, the accuracy of its segmentation remains unsatisfactory. To this end, in this article, we propose a novel power line segmentation network PLNet. In this network, after the backbone feature is reinforced by the multichannel feature fusion (MCFF) module, the line feature extraction (LFE) module is proposed to robustly encode the global straight-line features by leveraging the Hough domain. Moreover, the output of LEF guides the encoding of lower-level features through the attention mechanism in the proposed line feature attention (LFA) module. Finally, through the multilevel top-down manner structure, the segmentation detail is progressively refined. Experimental results demonstrate that our proposed method achieves state-of-the-art performance in power line segmentation on the public TTPLA dataset. The testing code is available online at https://github.com/JYYMALL/PLNet.