Semantic Segmentation Algorithm Fusing Infrared and Natural Light Images for Automatic Navigation in Transmission Line Inspection

Abstract

Unmanned aerial vehicles (UAVs) are widely used in power transmission line inspection nowadays and they need to navigate automatically by recognizing the category and accurate position of transmission pylon equipment in line inspection. Semantic segmentation is an effective method for recognizing transmission pylon equipment. In this paper, a semantic segmentation algorithm that fuses infrared and natural light images is proposed. A cross-modal attention interaction activation mechanism is adopted to fully exploit the complementation between natural light and infrared images. Firstly, a global information block with a feature pyramid structure is used to deeply mine and fuse multi-scale global contextual information of fused features, and then the block is used to conduct feature aggregation in the decoding processing, and enough aggregation with multi-scale features of infrared and natural light images is used to enhance the expression ability of the model and improve the accuracy of semantic segmentation of transmission pylon equipment in complex scenes. Our method guides the process of low-level up-sampling and restoration by denser global and high-level features. Experimental results on a dataset of transmission pylon equipment collected by us show that the proposed method achieved better semantic segmentation results than the state-of-the-art methods.