| L. Tsap, D. Goldgof, and S. Sarkar, Model-based force-driven nonrigid motion recovery from sequences of range images without point correspondences, Image Vision Comput. 17(14), 1999, 997--1007. |
.... system by modeling degrees of freedom and by using the analysis by synthesis approach ( 18] Davis and Shah presented a tracking method by tting 3 D models (generalized cylinders) to ngers in a 2 D image [14] Otherwise, range data was used in motion analysis primarily in an o ine mode [19, 20]. Recent availability of less expensive, faster range data makes it a feasible additional source of information for tracking. This is the rst real time gesture tracking system that utilizes on demand range in both spatial and temporal representations (some initial results have previously ....
....for segmentation and tracking. Often, an object of interest can be separated from other objects or background by depth alone. In other cases, having fewer artifacts (that could complicate segmentation) in range information compared to intensity data is an important consideration for model matching [19]. Real time constraints such as temporal correlation produce a possibility of searching within a smaller region, based on the match in the previous frame. For the range image, this involves depth planes immediately surrounding the plane where a hand (or face) was found in the previous frame. ....
L. V. Tsap, D. B. Goldgof, and S. Sarkar. Model-based force-driven nonrigid motion recovery from sequences of range images without point correspondences. Image and Vision Computing Journal, 17(14):997-1007, November 1999.
No context found.
L. Tsap, D. Goldgof, and S. Sarkar, Model-based force-driven nonrigid motion recovery from sequences of range images without point correspondences, Image Vision Comput. 17(14), 1999, 997--1007.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC