Title :
2-D mesh-based tracking of deformable objects with occlusion
Author :
Toklu, Candemir ; Tekalp, A. Murat ; Erdem, A. Tanju ; Sezan, M.
Author_Institution :
Dept. of Electr. Eng., Rochester Univ., NY, USA
Abstract :
Many interactive video and multimedia applications, such as interactive TV, augmented reality and bit stream editing, demand object-based video modeling. These applications require accurate tracking of the boundary, local motion and intensity variations of each object. This paper proposes a new approach to track deformable objects in video sequences, which combines deformable contours and 2-D mesh models while addressing partial occlusion, including self-occlusion. Experimental results demonstrate successful tracking of objects with deformable boundaries in the presence of self-occlusion
Keywords :
edge detection; image sequences; interactive systems; mesh generation; motion estimation; tracking; video signal processing; 2-D mesh model; 2-D mesh-based tracking; augmented reality; bit stream editing; boundary; deformable contours; deformable objects; intensity variations; interactive TV; interactive video; local motion; multimedia applications; object-based video modeling; partial occlusion; self-occlusion; video sequences; Active contours; Augmented reality; Deformable models; Laboratories; Spline; Streaming media; TV; Tracking; Video compression; Video sequences;
Conference_Titel :
Image Processing, 1996. Proceedings., International Conference on
Conference_Location :
Lausanne
Print_ISBN :
0-7803-3259-8
DOI :
10.1109/ICIP.1996.559653