A Robust 3-D Abrasion Diagnosis Method of Pantograph Slipper Based on Stereo Vision

Abstract

The pantograph is an essential component in modern electrified trains. Due to the characters of contactless and high precision, the 3-D stereo vision, which can effectively monitor the abrasion, is of great significance for ensuring train safety. However, illumination conditions, such as overbrightness and insufficient light, have a great impact on semiglobal matching (SGM) stereo matching, inevitably affecting the integrity and accuracy of the abrasion measurement of the pantograph slipper. In this regard, a robust SGM stereo matching is proposed in this article for the 3-D abrasion measurement. First, the combination of the neighborhood information-aware census cost and multiscale fusion for cost aggregation is put forward. While insensitive to illumination condition changes, the improved census cost can quantify the texture information of the neighborhood. Moreover, multiscale cost aggregation further fuses the neighborhood information of different scales. As a result, the performance of SGM in weakly textured areas is greatly improved, especially in complex illumination conditions. Eventually, with the help of the subpixel disparity refinement and local points fitting, an accurate 3-D abrasion calculation is achieved. Practical experiments show the robustness of stereo matching. The precision verification and computation time analysis confirm the measurement accuracy and applicability.