A high-efficiency method of pantograph collector strip wearing inspection based on stereo vision

Abstract

Pantograph is a power collector to get current from the overhead catenary for electric train engine. When the train moves forward, the high frequency friction between pantograph and catenary gives rise to the wear of the carbon strips. In this paper, we propose an efficient stereo-based method to non-contact monitor the pantograph wearing. Firstly, a modified SGM-based stereo matching algorithm is raised to overcome the complicated illumination in the actual environment. Secondly, the point cloud segmentation using Radius Filter and Density-based Spatial Clustering of Applications with Noise (RF-DBSCAN) is carried out to eliminate noisy points caused by mismatching and extract the carbon strips from background. Finally, for the purpose of wearing detection, the processed point cloud is aligned with stand CAD model by the proposed coarse-to-fine iterative closest point (CF-ICP) method. The experimental data which is obtained from a real train maintenance depot reveals that root mean square (RMS) of the wearing inspection is less than 4 mm, which outperform than other classic methods