2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (2008)
Anchorage, AK, USA
June 23, 2008 to June 28, 2008
Matti Pietikainen , Machine Vision Group, Infotech Oulu and Department of Electrical and Information Engineering P.O. Box 4500 FI-90014 University of Oulu, Finland
Guoying Zhao , Machine Vision Group, Infotech Oulu and Department of Electrical and Information Engineering P.O. Box 4500 FI-90014 University of Oulu, Finland
Feature definition and selection are two important aspects in visual analysis of motion. In this paper, spatiotemporal local binary patterns computed at multiple resolutions are proposed for describing dynamic events, combining static and dynamic information from different spatiotemporal resolutions. Appearance and motion are the key components for visual analysis related to movements. Ada-Boost algorithm is utilized for learning the principal appearance and motion from spatiotemporal descriptors derived from three orthogonal planes, providing important information about the locations and types of features for further analysis. In addition, learners are designed for selecting the most important features for each specific pair of different classes. The experiments carried out on diverse visual analysis tasks: facial expression recognition and visual speech recognition, show the effectiveness of the approach.
Matti Pietikainen, Guoying Zhao, "Principal appearance and motion from boosted spatiotemporal descriptors", 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 00, no. , pp. 1-8, 2008, doi:10.1109/CVPRW.2008.4563174