Tracking of Ball and Players in Beach Volleyball Videos

Abstract

This paper presents methods for the determination of players' positions and contact time points by tracking the players and the ball in beach volleyball videos. Two player tracking methods are compared, a classical particle filter and a rigid grid integral histogram tracker. Due to mutual occlusion of the players and the camera perspective, results are best for the front players, with 74,6% and 82,6% of correctly tracked frames for the particle method and the integral histogram method, respectively. Results suggest an improved robustness against player confusion between different particle sets when tracking with a rigid grid approach. Faster processing and less player confusions make this method superior to the classical particle filter. Two different ball tracking methods are used that detect ball candidates from movement difference images using a background subtraction algorithm. Ball trajectories are estimated and interpolated from parabolic flight equations. The tracking accuracy of the ball is 54,2% for the trajectory growth method and 42,1% for the Hough line detection method. Tracking results of over 90% from the literature could not be confirmed. Ball contact frames were estimated from parabolic trajectory intersection, resulting in 48,9% of correctly estimated ball contact points.

What Players do with the Ball: A Physically Constrained Interaction Modeling

“…In this section, we compare our results to those of several state-of-the-art multi-view ball-tracking algorithms [27,28,23], a monocular one [10], as well as two tracking methods that could easily be adapted for this purpose [30,2].…”

“…In short, our contribution is a principled and generic formulation of the ball tracking problem and related physical constraints in terms of a MIP. We will demonstrate that it outperforms state-of-the-art approaches [27,28,23,10] in soccer, volleyball, and basketball.…”

“…There is a substantial body of literature about dealing with these issues, but almost always using heuristics that are specific to a particular sport such as soccer [31], volleyball [10], or basketball [6]. A few more generic approaches explicitly account for the interaction between the players and the ball [28] while others impose physics-based constraints on ball motion [23].…”

A System for Analysing the Basketball Free Throw Trajectory Based on Particle Swarm Optimization

“…One of the basic problems with computer vision is the detection and tracking of objects [21]. The methods used for their tracking are applied in various fields, including the army, industry, medicine, and robotics [22].…”

Untitled

“…Several studies have used tools to evaluate the game, one based on the use of video (Link, 2014;Tilp, Koch, Stifter, & Ruppert, 2006) and another to develop standards-based data mining analysis (Zhang, Zhao, & Wu, 2006). Other research has investigated the development of technology for tracking moving objects such as balls, with the support of photogrammetry 2D (Gomez, Herrera López, Link, & Eskofier, 2014;Jlassi, Douik, & Messaoud, 2012), as well as with 3D photogrammetry (Chen, Tsai, Lee, & Yu, 2012). These studies have provided teams with the strategies and tactics of the game through ball movements analyzed using these systems.…”