Title :
Understanding 3-dimensional dynamic environment fusing multiple images by mixed-state condensation algorithm
Author :
Hamasaki, Koji ; Nakajima, Taira ; Okatani, Takayuki ; Deguchi, Koichiro
Author_Institution :
Graduate Sch. of Inf. Sci., Tohoku Univ., Sendai, Japan
Abstract :
In this paper, we propose an efficient method for tracking multiple objects, which deals with occlusion situations in an image. We use the shape from silhouettes method to reconstruct objects 3D position using images taken from different directions. Then we track the objects´ reconstructed 3D positions by using the mixed-state condensation algorithm. The experimental results show the tracking of multiple objects robustly.
Keywords :
image reconstruction; iterative methods; probability; stereo image processing; tracking; 3D shape reconstruction; image reconstruction; iterative method; mixed-state condensation algorithm; mixed-state model; multiple objects tracking; occlusion; shape from silhouettes; transition probability; Cameras; Clutter; Computer vision; Feature extraction; Image reconstruction; Interference; Layout; Object recognition; Robustness; Shape;
Conference_Titel :
SICE 2002. Proceedings of the 41st SICE Annual Conference
Print_ISBN :
0-7803-7631-5
DOI :
10.1109/SICE.2002.1196619
