Online Multiple Athlete Tracking with Pose-Based Long-Term Temporal Dependencies.

Autor: Kong L; School of Computer Science and Engineering, Beihang University, Beijing 100191, China., Zhu M; State Key Laboratory of Software Development Environment, Beihang University, Beijing 100191, China., Ran N; School of Computer Science and Engineering, Beihang University, Beijing 100191, China., Liu Q; Hangzhou Innovation Institute, Beihang University, Hangzhou 310000, China., He R; School of Computer Science and Engineering, Beihang University, Beijing 100191, China.
Jazyk: angličtina
Zdroj: Sensors (Basel, Switzerland) [Sensors (Basel)] 2020 Dec 30; Vol. 21 (1). Date of Electronic Publication: 2020 Dec 30.
DOI: 10.3390/s21010197
Abstrakt: 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.
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje