Pose estimation and motion analysis of ski jumpers based on ECA-HRNet

Ski jumping is a high-speed sport, which makes it difficult to accurately analyze the technical motion in a subjective way. To solve this problem, we propose an image-based pose estimation method for analyzing the motion of ski jumpers. First, an image keypoint dataset of ski jumpers (KDSJ) was constructed. Next, in order to improve the precision of ski jumper pose estimation, an efficient channel attention (ECA) module was embedded in the residual structures of a high-resolution network (HRNet) to fuse more useful feature information. At the training stage, we used a transfer learning method which involved pre-training on the Common Objection in Context (COCO2017) to obtain feature knowledge from the COCO2017 for using in the task of ski jumper pose estimation. Finally, the detected keypoints of the ski jumpers were used to analyze the motion characteristics, using hip and knee angles over time (frames) as an example. Our experimental results showed that the proposed ECA-HRNet achieved the average precision of 73.4% on the COCO2017 test-dev set and the average precision of 86.4% on the KDSJ test set using the ground truth bounding boxes. These research results can provide guidance for auxiliary training and motion evaluation of ski jumpers.