TY - GEN
T1 - Recognizing human actions using curvature estimation and NWFE-based histogram vectors
AU - Hsu, Fu Song
AU - Lin, Cheng Hsien
AU - Lin, Wei Yang
PY - 2011
Y1 - 2011
N2 - This paper presents a novel scheme for human action recognition. First of all, we employ the curvature estimation to analyze human posture patterns and to yield the discriminative feature sequences. The feature sequences are further represented into sets of strings. Consequently, we can solve human action recognition problem by the string matching technique. In order to boost the performance of string matching, we apply the NonparametricWeighted Feature Extraction (NWFE) to compact the string representation. Finally, we train a Bayes classifier to perform action recognition. Unlike traditional approaches using the nearest neighbor rule, our proposed scheme can classify the human actions more efficiently while maintaining high accuracy. The experiment results show that the proposed scheme is efficient and accurate in human action recognition.
AB - This paper presents a novel scheme for human action recognition. First of all, we employ the curvature estimation to analyze human posture patterns and to yield the discriminative feature sequences. The feature sequences are further represented into sets of strings. Consequently, we can solve human action recognition problem by the string matching technique. In order to boost the performance of string matching, we apply the NonparametricWeighted Feature Extraction (NWFE) to compact the string representation. Finally, we train a Bayes classifier to perform action recognition. Unlike traditional approaches using the nearest neighbor rule, our proposed scheme can classify the human actions more efficiently while maintaining high accuracy. The experiment results show that the proposed scheme is efficient and accurate in human action recognition.
UR - http://www.scopus.com/inward/record.url?scp=84862938028&partnerID=8YFLogxK
U2 - 10.1109/VCIP.2011.6115911
DO - 10.1109/VCIP.2011.6115911
M3 - Conference contribution
AN - SCOPUS:84862938028
SN - 9781457713200
T3 - 2011 IEEE Visual Communications and Image Processing, VCIP 2011
BT - 2011 IEEE Visual Communications and Image Processing, VCIP 2011
T2 - 2011 IEEE Visual Communications and Image Processing, VCIP 2011
Y2 - 6 November 2011 through 9 November 2011
ER -