Pantograph Pose Measurement Based on Keypoint Location and Edge Shape Optimization Under Complex Conditions

The violent swing of the pantograph deteriorates the contact status of the pantograph and catenary system (PCS) and seriously threatens the operation security of high-speed trains. Currently, video surveillance is commonly used for pantograph pose monitoring. Due to complex weather conditions of illumination change, occlusion, and background interference on the roof, achieving effective real-time high-precision attitude measurement remains challenging. Therefore, this study proposes a deep-learning-based 3-D measurement method. First, an accurate end-to-end pantograph keypoint location network (PKLNet) is proposed to position image coordinates of the keypoints. In PKLNet, local and global contexts are integrated by an improved Transformer encoder to solve the common interference and occlusion. Differentiable numerical regression (DNR) is performed to realize an accurate coordinate regression of the keypoints. Second, the keypoint positioning is used to overcome the interference of the complex background to extract the edge, and an edge shape algorithm is employed to optimize the pose. If the edge extraction fails, the perspective-
${n}$
-point (PnP) of the keypoints is carried out for pose calculation. Evaluation of practical image sequences indicates that the average precision at PCKp@0.03 is 96%. An attitude accuracy experiment further confirms that the optimized attitude root mean squared error (RMSE) is less than 0.35° and the average speed is 36.2 frames/s, fulfilling the strict requirement of pantograph attitude measurement.