Decoupling Video and Human Motion: Towards Practical Event Detection in Athlete Recordings
Abstract
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.
Cite
Text
Einfalt and Lienhart. "Decoupling Video and Human Motion: Towards Practical Event Detection in Athlete Recordings." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020. doi:10.1109/CVPRW50498.2020.00454Markdown
[Einfalt and Lienhart. "Decoupling Video and Human Motion: Towards Practical Event Detection in Athlete Recordings." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020.](https://mlanthology.org/cvprw/2020/einfalt2020cvprw-decoupling/) doi:10.1109/CVPRW50498.2020.00454BibTeX
@inproceedings{einfalt2020cvprw-decoupling,
title = {{Decoupling Video and Human Motion: Towards Practical Event Detection in Athlete Recordings}},
author = {Einfalt, Moritz and Lienhart, Rainer},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2020},
pages = {3901-3910},
doi = {10.1109/CVPRW50498.2020.00454},
url = {https://mlanthology.org/cvprw/2020/einfalt2020cvprw-decoupling/}
}