DRA-Net: A Dual-Branch Residual Attention Network for Pixelwise Power Line Detection

The accurate extraction of transmission lines from unmanned aerial vehicle (UAV) aerial photography is a necessary but challenging task for intelligent power inspection due to some factors, such as complex backgrounds, varying illumination, and class-imbalance issue. Although there have been some research achievements in transmission line extraction, especially U-Net and its variant networks, there are still some shortcomings, such as insufficiency processing of local features, limited noise denoising ability, and poor edge feature representation ability. In this article, we propose a dual-branch residual attention network, called DRA-Net, which introduces a dual-branch encoder composed of a residual convolutional neural network (RCNN) branch and a recurrent RCNN (RRCNN) branch to extract richer semantic information and a context fusion block (CFB) to fuse temporal and spatial information effectively. In addition, a U-shaped noise denoising (UND) block is proposed to reduce interference from complex backgrounds and an edge enhancement block (EEB) is also proposed to strength the capacity of segmentation network to extract useful edge feature information from noise. Experiments demonstrate that the proposed DRA-Net has obtained an excellent segmentation manifestation on remote sensing images, with a 93.26% Dice coefficient and 93.19% mIoU value on the public power line dataset (PLD), and a 96.40% Dice coefficient and 96.04% mIoU value on the self-built overhead power line (OPL) dataset.