Embedding motion and structure features for action recognition

Publication Type:
Journal Article
IEEE Transactions on Circuits and Systems for Video Technology, 2013, 23 (7), pp. 1182 - 1190
Issue Date:
Filename Description Size
Thumbnail2013001083OK.pdf1.81 MB
Adobe PDF
Full metadata record
We propose a novel method to model human actions by explicitly coding motion and structure features that are separately extracted from video sequences. Firstly, the motion template (one feature map) is applied to encode the motion information and image planes (five feature maps) are extracted from the volume of differences of frames to capture the structure information. The Gaussian pyramid and center-surround operations are performed on each of the six obtained feature maps, decomposing each feature map into a set of subband maps. Biologically inspired features are then extracted by successively applying Gabor filtering and max pooling on each subband map. To make a compact representation, discriminative locality alignment is employed to embed the high-dimensional features into a low-dimensional manifold space. In contrast to sparse representations based on detected interest points, which suffer from the loss of structure information, the proposed model takes into account the motion and structure information simultaneously and integrates them in a unified framework; it therefore provides an informative and compact representation of human actions. The proposed method is evaluated on the KTH, the multiview IXMAS, and the challenging UCF sports datasets and outperforms stateof-the-art techniques on action recognition.©2013 IEEE.
Please use this identifier to cite or link to this item: