Decoupling Video and Human Motion: Towards Practical Event Detection in Athlete Recordings
This work addresses practical event detection in sports analytics, offering a flexible pose-based method that is incremental over end-to-end approaches.
The paper tackled motion event detection in athlete recordings by using 2D human pose sequences to decouple motion from raw video, achieving F1 scores of over 91% for swimming starts and 96% for athletics jumps with precise temporal accuracy.
In this paper we address the problem of motion event detection in athlete recordings from individual sports. In contrast to recent end-to-end approaches, we propose to use 2D human pose sequences as an intermediate representation that decouples human motion from the raw video information. Combined with domain-adapted athlete tracking, we describe two approaches to event detection on pose sequences and evaluate them in complementary domains: swimming and athletics. For swimming, we show how robust decision rules on pose statistics can detect different motion events during swim starts, with a F1 score of over 91% despite limited data. For athletics, we use a convolutional sequence model to infer stride-related events in long and triple jump recordings, leading to highly accurate detections with 96% in F1 score at only +/- 5ms temporal deviation. Our approach is not limited to these domains and shows the flexibility of pose-based motion event detection.