Sciweavers

Share
TCSV
2008

Human Activity Recognition Based on Silhouette Directionality

11 years 1 months ago
Human Activity Recognition Based on Silhouette Directionality
Recent advances in computer vision and pattern recognition have fuelled numerous initiatives that aim to intelligently recognize human activities. In this paper, we propose an algorithm for non-intrusive human activity recognition. We use an adaptive background-foreground separation technique to extract motion information and generate silhouettes (foreground) from the input videos. We then derive directionality based feature vectors (directional vectors) from the silhouette contours, and use the distinct data distribution of directional vectors in a vector space for clustering and recognition. We also exploit the dynamic characteristic of human motion in order to smooth decisions over time and reduce errors in activity recognition. Our approach is monocular, tolerant to moderate view changes, and can be applied to both frontal and lateral views of most activities. Experiments with short and long video sequences show robust recognition under conditions of varying view angles, zoom depth...
Meghna Singh, Anup Basu, Mrinal K. Mandal
Added 15 Dec 2010
Updated 15 Dec 2010
Type Journal
Year 2008
Where TCSV
Authors Meghna Singh, Anup Basu, Mrinal K. Mandal
Comments (0)
books