School of Computer Science and Engineering, Beihang University, Beijing 100191, China.
State Key Laboratory of Software Development Environment, Beihang University, Beijing 100191, China.
Sensors (Basel). 2020 Dec 30;21(1):197. doi: 10.3390/s21010197.
This paper addresses the Multi-Athlete Tracking (MAT) problem, which plays a crucial role in sports video analysis. There exist specific challenges in MAT, e.g., athletes share a high similarity in appearance and frequently occlude with each other, making existing approaches not applicable for this task. To address this problem, we propose a novel online multiple athlete tracking approach which make use of long-term temporal pose dynamics for better distinguishing different athletes. Firstly, we design a Pose-based Triple Stream Network (PTSN) based on Long Short-Term Memory (LSTM) networks, capable of modeling long-term temporal pose dynamics of athletes, including pose-based appearance, motion and athletes' interaction clues. Secondly, we propose a multi-state online matching algorithm based on bipartite graph matching and similarity scores produced by PTSN. It is robust to noisy detections and occlusions due to the reliable transitions of multiple detection states. We evaluate our method on the APIDIS, NCAA Basketball and VolleyTrack databases, and the experiment results demonstrate its effectiveness.
本文针对多运动员跟踪 (MAT) 问题进行了研究，该问题在体育视频分析中起着至关重要的作用。MAT 存在一些特定的挑战，例如，运动员在外观上非常相似，并且经常相互遮挡，这使得现有的方法不适用于这项任务。为了解决这个问题，我们提出了一种新颖的在线多运动员跟踪方法，该方法利用长期的时间姿态动力学来更好地区分不同的运动员。首先，我们设计了一个基于姿态的三重流网络 (PTSN)，它基于长短期记忆 (LSTM) 网络，能够对运动员的长期时间姿态动力学进行建模，包括基于姿态的外观、运动和运动员之间的交互线索。其次，我们提出了一种基于二分图匹配和 PTSN 生成的相似性得分的多状态在线匹配算法。由于多个检测状态的可靠转换，它对噪声检测和遮挡具有鲁棒性。我们在 APIDIS、NCAA 篮球和 VolleyTrack 数据库上评估了我们的方法，实验结果表明了其有效性。
