TY - GEN
T1 - Action recognition using local joints structure and histograms of 3D joints
AU - Liang, Yan
AU - Lu, Wanxuan
AU - Liang, Wei
AU - Wang, Yucheng
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2015/1/20
Y1 - 2015/1/20
N2 - In this paper, we present a method for human action recognition using local joints structure and histograms of 3D joints. Global features like histograms of 3D joints [12] ignore the local structure information of the human body joints, which is also essential for accurate action recognition. To address this problem, we propose a local joints structure feature as a complement, and combine both global and local features for posture description in our method. Then, linear discriminant analysis is used to reduce the feature dimension, and k-means clustering is utilized to generate codewords. Finally, these codewords are treated as discrete symbols for training hidden Markov models (HMMs) which are used for action recognition. Experimental results demonstrate that our method has better performance than other methods when testing on UTKinect-Action Dataset and MSR Action3D dataset.
AB - In this paper, we present a method for human action recognition using local joints structure and histograms of 3D joints. Global features like histograms of 3D joints [12] ignore the local structure information of the human body joints, which is also essential for accurate action recognition. To address this problem, we propose a local joints structure feature as a complement, and combine both global and local features for posture description in our method. Then, linear discriminant analysis is used to reduce the feature dimension, and k-means clustering is utilized to generate codewords. Finally, these codewords are treated as discrete symbols for training hidden Markov models (HMMs) which are used for action recognition. Experimental results demonstrate that our method has better performance than other methods when testing on UTKinect-Action Dataset and MSR Action3D dataset.
KW - Histograms of 3D joints
KW - Human action recognition
KW - Local joints structure
KW - Posture representation
UR - http://www.scopus.com/inward/record.url?scp=84922908174&partnerID=8YFLogxK
U2 - 10.1109/CIS.2014.82
DO - 10.1109/CIS.2014.82
M3 - Conference contribution
AN - SCOPUS:84922908174
T3 - Proceedings - 2014 10th International Conference on Computational Intelligence and Security, CIS 2014
SP - 185
EP - 188
BT - Proceedings - 2014 10th International Conference on Computational Intelligence and Security, CIS 2014
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 10th International Conference on Computational Intelligence and Security, CIS 2014
Y2 - 15 November 2014 through 16 November 2014
ER -