AE-FPN: adaptive enhance feature learning for detecting wire defects

• Published in: Signal, image and video processing image and video processing, 2023-07, Vol.17 (5), p.2145-2155
• Main Authors: Zhang, Hui, Du, Jianming, Xie, Chengjun, Zhang, Jie, Qian, Shaowei, Li, Rui
• Format: Article
• Language: English
• Subjects: Aspect ratio; Computer Imaging; Computer Science; Defects; High altitude; Image Processing and Computer Vision; Multimedia Information Systems; Original Paper; Pattern Recognition and Graphics; Signal,Image and Speech Processing; Transmission lines; Vision; Wire
• ISSN: 1863-1703; 1863-1711
• DOI: 10.1007/s11760-022-02429-3

Wire defects usually occur in high-altitude transmission lines, leading to line transmission failures and even the possibility of large-scale power outages. Therefore, timely and accurate locating wire defects detection is a key technology for power transmission. However, there are still challenges for wire defect objects with large aspect ratios, arbitrary orientations, and complex backgrounds. In this paper, we design a novel Adaptive Enhancement Feature Pyramid Network (AE-FPN) to focus on the wire defect features through an attention mechanism during feature fusion and extraction. AE-FPN is a plug-and-play component that can be used in different networks. Using AE-FPN in a basic Faster R-CNN system, our method achieves a 3.2% AP gain at a very marginal extra cost. In addition, a multi-scenario multi-object dataset of wire defects is established that provides the baseline for detecting wire defects in transmission lines.