DBFN: Double Branch Fusion Network for Vital Components and Defect Detection of Transmission Line

Abstract

AbstractA double branch fusion network is proposed based on unmanned aerial vehicle (UAV) inspection images to increase the detection accuracy of vital components and defects in transmission lines. The backbone feature extraction network comprises a combination of a convolutional neural network (CNN) and a Transformer network. To be specific, the CNN should extract local information, and the Transformer network is responsible for the extraction of global information. Besides, global information and local information have semantic differences, while resulting in feature aliasing after fusion. To solve this problem, a multiscale convolution module and a multiscale pooling module are proposed to solve semantic differences and feature aliasing through the interaction between two types of information. In general, the enhanced feature extraction network comprises a residual‐like convolution module, which can reduce the loss of detailed information (e.g., edge contours) and further extract high‐level semantic information from the deep network. Besides, it performs feature fusion in multiple regions in the enhanced feature extraction network, such that the multi‐scale adaptability of the neural network is effectively enhanced. Last, the fused feature information at different scales is decoded, and the final detection results are yielded.