Dataset Information

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.

SUBMITTER: Gomez G

PROVIDER: S-EPMC4245102 | biostudies-literature | 2014

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Tracking of ball and players in beach volleyball videos.

Gomez Gabriel G Herrera López Patricia P Link Daniel D Eskofier Bjoern B

PloS one 20141126 11

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, respectiv ...[more]

PMID: 25426936

Similar Datasets

Project description:Volleyball is an exceedingly popular physical activity in the adolescent population, especially with females. The study objective was to assess the effect of volleyball training and natural ontogenetic development on the somatic parameters of adolescent girls. The study was implemented in a group of 130 female volleyball players (aged 12.3 ± 0.5 - 18.1 ± 0.6 years) along with 283 females from the general population (aged 12.3 ± 0.5 - 18.2 ± 0.5 years). The measured parameters included: body height (cm), body mass (kg), body fat (kg, %), visceral fat (cm2), body water (l), fat free mass (kg) and skeletal muscle mass (kg, %). Starting at the age of 13, the volleyball players had significantly lower body fat ratio and visceral fat values than those in the general population (p < 0.001 in body fat % and p < 0.01 in visceral fat). In volleyball players, the mean body fat (%) values were 17.7 ± 6.6 in 12-year-old players, 16.7 ± 4.9 in 13-year-old players, 18.5 ± 3.9 in 16-year-old players, and 19.3 ± 3.1 in 18-year-old players. In the general population, the mean body fat (%) values were 19.6 ± 6.3 in 12-year-old girls, 21.7 ± 6.4 in 13-year-old girls, 23.4 ± 6.1 in 16-year-old girls, and 25.8 ± 7.0 in 18-year-old girls. The visceral fat (cm2) mean values were 36.4 ± 19.3 in 12-year-old players, 39.2 ± 16.3 in 13-year-old players, 45.7 ± 14.7 in 16-year-old players, and 47.2 ± 12.4 in 18-year-old players. In the general population, the mean visceral fat (cm2) values were 41.4 ± 21.1 in 12-year-old girls, 48.4 ± 21.5 in 13-year-old girls, 58.0 ± 24.7 in 16-year-old girls, and 69.1 ± 43.7 in 18-year-old girls. In volleyball players, lower body fat ratio corresponded with a higher skeletal muscle mass ratio. The differences found in skeletal muscle mass ratio were also significant starting at the age of 13 (p < 0.001). The mean skeletal muscle mass (%) values were 44.1 ± 3.4 in 12-year-old volleyball players, 45.4 ± 2.5 in 13-year-old players, 45.0 ± 2.2 in 16-year-old players, and 44.7 ± 1.8 in 18-year-old players. In the general population, the mean skeletal muscle mass (%) values were 42.8 ± 3.2 in 12-year-old girls, 42. ± 4.1 in 13-year-old girls, 41.9 ± 3.3 in 16-year-old girls, and 40.6 ± 3.7 in 18-year-old girls. Differences in body composition between the individual age groups were similar between the volleyball players and girls in the general population. The results indicate that regular volleyball training influences the body composition of young females however the development of body composition parameters is subject to their ontogenetic development.

Dataset Information

Tracking of ball and players in beach volleyball videos.

Publications

Tracking of ball and players in beach volleyball videos.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets