Bionic Vision-Based Pantograph–Catenary Contact Point Detection Study in China High-Speed Railway

Abstract

The pantograph–catenary system of high-speed electric multiple units (EMU) is the only way to get electric power for high-speed trains. Over the past several years, video frames taken from traditional cameras have been used to analyze pantograph–catenary arcs. A traditional camera is built on mimicking human vision; thus, the natural phenomenon that an object will appear smaller if it is far from an observer but will become larger as it moves toward the observer will be reflected in the pictures that are taken. This is analogous to an implicit depth. Based on this observation, a bionic vision-based algorithm that utilizes the implicit depth is proposed in the present work to extract the touch point between the contact wire and pantograph slide under interference from the messenger wire. Experiments indicate that the proposed algorithm works quite well, with only marginal errors occurring, thus providing a strong base for future research activities.