Visual Recognition Method for Lateral Swing of the Tail Rope

Abstract

The large lateral displacement of tail ropes increases the risk of their wear and fracture, posing hidden dangers to the safety of the hoisting system. However, no suitable method is available to recognize the lateral swing of tail ropes online. A target-free visual measurement method, which includes the dual-branch SiamSeg, was proposed in this study. Considering the slender characteristics of tail ropes, the receptive field of the feature extraction network was enhanced via the Receptive Field Module (RFM), thereby strengthening the discriminability and integrity of tail rope features. The consistency loss constraints were added to the segmentation loss function to maximize the time sequence information of the video and further improve the accuracy of pixel-level displacement. Compared with other methods, the proposed approach achieved better segmentation effects. Comparison results synchronously measured by sensors revealed the effectiveness of this method and its potential for practical underground applications.