论文标题
解耦视频和人类运动：迈向运动员录音中的实用事件检测
Decoupling Video and Human Motion: Towards Practical Event Detection in Athlete Recordings
论文作者
论文摘要
在本文中，我们解决了各个运动的运动员录音中运动事件检测的问题。与最近的端到端方法相反，我们建议使用2D人姿势序列作为中间表示，使人类运动与原始视频信息相关。结合了适应领域的运动员跟踪，我们描述了两种在姿势序列上进行事件检测的方法，并在互补的领域中对其进行了评估：游泳和田径运动。对于游泳，我们展示了关于姿势统计数据的强大决策规则如何检测游泳开始时的不同运动事件，尽管数据有限，但F1得分超过91％。对于田径运动，我们使用卷积序列模型在长和三跳记录中推断与步步相关的事件，从而导致高度准确的检测，而F1得分为96％，仅在+/- 5ms时间偏差下。我们的方法不仅限于这些领域，并显示了基于姿势的运动事件检测的灵活性。
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.
