Skip to main content
placeholder image

Discriminative key pose extraction using extended LC-KSVD for action recognition

Conference Paper


Abstract


  • This paper presents a method for extracting discriminative

    key poses for skeleton-based action recognition. Poses

    are represented by normalized joint locations, velocities and

    accelerations of skeleton joints. An extended label consistent

    K-SVD (ELC-KSVD) algorithm is proposed for learning the

    common and action-specific dictionaries. Discriminative key poses

    are represented by the atoms of the action-specific dictionaries.

    With the specific dictionaries, sparse codes are obtained for

    representing action instances through max pooling and temporal

    pyramid. A SVM classifier is trained for action recognition. The

    proposed method was evaluated on the MSRC-12 gesture and

    MSR-Action 3D datasets. Experimental results have shown that

    the proposed method is effective in extracting discriminative key

    poses.

Authors


  •   Zhou, Lijuan (external author)
  •   Li, Wanqing
  •   Zhang, Yuyao (external author)
  •   Ogunbona, Philip O.
  •   Nguyen, Duc Thanh (external author)
  •   Zhang, Hanling (external author)

Publication Date


  • 2014

Citation


  • Zhou, L., Li, W., Zhang, Y., Ogunbona, P. O., Nguyen, D. & Zhang, H. (2014). Discriminative key pose extraction using extended LC-KSVD for action recognition. 2014 International Conference on digital Image Computing: Techniques and Applications, DICTA 2014 (pp. 1-8). United States: IEEE.

Scopus Eid


  • 2-s2.0-84922568989

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/3368

Has Global Citation Frequency


Start Page


  • 1

End Page


  • 8

Place Of Publication


  • United States

Abstract


  • This paper presents a method for extracting discriminative

    key poses for skeleton-based action recognition. Poses

    are represented by normalized joint locations, velocities and

    accelerations of skeleton joints. An extended label consistent

    K-SVD (ELC-KSVD) algorithm is proposed for learning the

    common and action-specific dictionaries. Discriminative key poses

    are represented by the atoms of the action-specific dictionaries.

    With the specific dictionaries, sparse codes are obtained for

    representing action instances through max pooling and temporal

    pyramid. A SVM classifier is trained for action recognition. The

    proposed method was evaluated on the MSRC-12 gesture and

    MSR-Action 3D datasets. Experimental results have shown that

    the proposed method is effective in extracting discriminative key

    poses.

Authors


  •   Zhou, Lijuan (external author)
  •   Li, Wanqing
  •   Zhang, Yuyao (external author)
  •   Ogunbona, Philip O.
  •   Nguyen, Duc Thanh (external author)
  •   Zhang, Hanling (external author)

Publication Date


  • 2014

Citation


  • Zhou, L., Li, W., Zhang, Y., Ogunbona, P. O., Nguyen, D. & Zhang, H. (2014). Discriminative key pose extraction using extended LC-KSVD for action recognition. 2014 International Conference on digital Image Computing: Techniques and Applications, DICTA 2014 (pp. 1-8). United States: IEEE.

Scopus Eid


  • 2-s2.0-84922568989

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/3368

Has Global Citation Frequency


Start Page


  • 1

End Page


  • 8

Place Of Publication


  • United States