Title :
Motion Stream Segmentation and Recognition by Classification
Author :
Li, Chuanjun ; Kulkarni, Punit R. ; Prabhakaran, B.
Author_Institution :
Dept. of Comput. Sci., Texas Univ., Dallas, TX
Abstract :
This paper proposes a classification-based approach to segmenting and recognizing patterns in motion signals. Feature vectors are extracted based on singular value decomposition (SVD) for classification. Multi-class support vector machine (SVM) classifiers with class probability estimates are explored for segmenting and recognizing motion streams. Experiments show that the proposed approach can find patterns in the multi-attribute motion streams with high accuracy
Keywords :
image classification; image motion analysis; image segmentation; probability; singular value decomposition; support vector machines; SVD; SVM; classification-based approach; motion signals; motion stream segmentation; pattern recognition; singular value decomposition; support vector machine; Animation; Data gloves; Feature extraction; Matrix decomposition; Motion analysis; Pattern recognition; Singular value decomposition; Streaming media; Support vector machine classification; Support vector machines;
Conference_Titel :
Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference on
Conference_Location :
Toulouse
Print_ISBN :
1-4244-0469-X
DOI :
10.1109/ICASSP.2006.1661331
