Abstract | ||
---|---|---|
This paper presents a novel technique for 2D human motion estimation using a single non calibrated camera. The user's five crucial human features (head, hands and feet) are ex- tracted, labeled and tracked, after silhouette segmentation. The crucial points candidates are defined as the local max- ima of the geodesic distance with respect to the center of gravity of the actor region (silhouette) following the silhou- ette boundary. Selected crucial points are then classified as head, hands or feet using a probabilistic approach weighted by a prior human model. The system can run at 50Hz paces on standard Personal Computers. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1109/ICIP.2005.1530522 | Image Processing, 2005. ICIP 2005. IEEE International Conference |
Keywords | Field | DocType |
feature extraction,image segmentation,motion estimation,probability,real-time systems,2D human motion estimation,features extraction,real-time applications,silhouette boundary,silhouette segmentation,silhouette-based probabilistic | Computer vision,Pattern recognition,Silhouette,Computer science,Segmentation,Feature extraction,Maxima and minima,Image segmentation,Artificial intelligence,Motion estimation,Probabilistic logic,Center of gravity | Conference |
Volume | ISSN | ISBN |
3 | 1522-4880 | 0-7803-9134-9 |
Citations | PageRank | References |
6 | 0.72 | 6 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Correa, P. | 1 | 6 | 0.72 |
Czyz, J. | 2 | 30 | 2.73 |
Umeda, T. | 3 | 8 | 1.15 |
Marques, F. | 4 | 19 | 2.01 |