Title :
Pose Estimation for Evaluating Standing Long Jumps via Dynamic Bayesian Networks
Author :
Hsu, Hui-Huang ; Yen, Yao-Bao ; Chen, Chu-Song ; Ho, Chun-Ta
Author_Institution :
Dept. of Comput. Sci. & Inf. Eng., Tamkang Univ., Taipei
Abstract :
A system is developed for analyzing poses in a standing long jump automatically. In the system, silhouette of the jumper is segmented from the background first. A thinning algorithm is then used to find a rough skeleton from the silhouette. Some image processing techniques are applied to make the resulted skeleton smoother and simpler. Key points are extracted from the skeleton. Finally, the dynamic Bayesian network (DBN) is used to determine the corresponding pose from the key points. The experimental result shows that pose estimation accuracy is quite good. According to the standing long jump standards, incorrect movements at different stages of the jump can thus be identified.
Keywords :
Bayes methods; feature extraction; image thinning; pose estimation; smoothing methods; dynamic Bayesian networks; image processing; jumper silhouette; key points extraction; pose estimation; skeleton smoothing; standing long jumps evaluation; thinning algorithm; Art; Bayesian methods; Cameras; Computer science; Data mining; Distributed computing; Genetic algorithms; Humans; Motion analysis; Skeleton; Dynamic Bayesian networks; Motion analysis; Pose estimation; Standing long jumps; Thinning;
Conference_Titel :
Distributed Computing Systems Workshops, 2008. ICDCS '08. 28th International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-0-7695-3173-1
Electronic_ISBN :
1545-0678
DOI :
10.1109/ICDCS.Workshops.2008.72