Skip to main content
placeholder image

Mining mid-level features for action recognition based on effective skeleton representation

Conference Paper


Download full-text (Open Access)

Abstract


  • Recently, mid-level features have shown promising performance in computer vision. Mid-level features learned by incorporating class-level information are potentially more discriminative than traditional low-level local features. In this paper, an effective method is proposed to extract mid-level features from Kinect skeletons for 3D human action recognition. Firstly, the orientations of limbs connected by two skeleton joints are computed and each orientation is encoded into one of the 27 states indicating the spatial relationship of the joints. Secondly, limbs are combined into parts and the limb's states are mapped into part states. Finally, frequent pattern mining is employed to mine the most frequent and relevant (discriminative, representative and non-redundant) states of parts in continuous several frames. These parts are referred to as Frequent Local Parts or FLPs. The FLPs allow us to build powerful bag-of-FLP-based action representation. This new representation yields state-of-the-art results on MSR DailyActivity3D and MSR ActionPairs3D.

Authors


Publication Date


  • 2014

Citation


  • P. Wang, W. Li, P. Ogunbona, Z. Gao & H. Zhang, "Mining mid-level features for action recognition based on effective skeleton representation," in 2014 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2014, 2014, pp. 1-8.

Scopus Eid


  • 2-s2.0-84922566687

Ro Full-text Url


  • http://ro.uow.edu.au/cgi/viewcontent.cgi?article=4539&context=eispapers

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/3522

Has Global Citation Frequency


Start Page


  • 1

End Page


  • 8

Place Of Publication


  • United States

Abstract


  • Recently, mid-level features have shown promising performance in computer vision. Mid-level features learned by incorporating class-level information are potentially more discriminative than traditional low-level local features. In this paper, an effective method is proposed to extract mid-level features from Kinect skeletons for 3D human action recognition. Firstly, the orientations of limbs connected by two skeleton joints are computed and each orientation is encoded into one of the 27 states indicating the spatial relationship of the joints. Secondly, limbs are combined into parts and the limb's states are mapped into part states. Finally, frequent pattern mining is employed to mine the most frequent and relevant (discriminative, representative and non-redundant) states of parts in continuous several frames. These parts are referred to as Frequent Local Parts or FLPs. The FLPs allow us to build powerful bag-of-FLP-based action representation. This new representation yields state-of-the-art results on MSR DailyActivity3D and MSR ActionPairs3D.

Authors


Publication Date


  • 2014

Citation


  • P. Wang, W. Li, P. Ogunbona, Z. Gao & H. Zhang, "Mining mid-level features for action recognition based on effective skeleton representation," in 2014 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2014, 2014, pp. 1-8.

Scopus Eid


  • 2-s2.0-84922566687

Ro Full-text Url


  • http://ro.uow.edu.au/cgi/viewcontent.cgi?article=4539&context=eispapers

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/3522

Has Global Citation Frequency


Start Page


  • 1

End Page


  • 8

Place Of Publication


  • United States