CCL-YOLO: Catenary Components Location Based on YOLO and Gather-Distribute Mechanism

Abstract

The catenary is an important part of the railway power supply system, and the good health of its key components is an important condition for the operation of high-speed trains. Due to the complex composition of catenary components and the large size difference between components, it is very difficult to implement the positioning and detection of all components. It severely limits the subsequent failure analysis of catenary components. Aiming at the problem of the difficult positioning of multiple components, this paper proposes a catenary complex component locating method based on the improved YOLO algorithm named CCL-YOLO. Firstly, based on the YOLO baseline method, a framework for locating complex components of railway catenary is proposed, which achieves the accurate locating of 40 catenary components and paves the way for subsequent fault detection. Furthermore, a novel "Gather-and Distribute" mechanism is introduced, which improves the original feature fusion method and its global feature fusion capability and effectively improves the positioning accuracy of complex catenary components. In addition, the Wasserstein distance loss is also applied to improve the detection capability of small objects. Finally, the comprehensive experimental results show that the proposed method for locating complex components of railway catenary can achieve a mean intersection over union of 94.1% for 40 components of different sizes. Meanwhile, it reduces the number of parameters and the complexity of the algorithm to a certain extent, thus paving the way for subsequent fault detection, which is of important application value.