DocumentCode :
399685
Title :
Tracking multiple three-dimensional motions by using modified condensation algorithm and multiple images
Author :
Hamasaki, Koji ; Nakajima, Taka ; Okatani, Takayuki ; Deguchi, Koichiro
Author_Institution :
Graduate Sch. of Inf. Sci., Tohoku Univ., Sendai, Japan
Volume :
1
fYear :
2003
fDate :
27-31 Oct. 2003
Firstpage :
236
Abstract :
In this paper we present a system for tracking objects\´ 3D motions by using sampling algorithm. The system consists of three cameras and 1 PC. We modified the condensation algorithm [M.A. Isard et al., 1998] to track objects\´ 3D positions. The condensation algorithm is a kind of "factored sampling" and it can easily cope with multi-modal probability density of objects\´ positions. We track objects not in images but in 3D space. We use a condensation particle-set as a tracker and represent a position of a moving object by a center of tracker. Since we don\´t track directly in images, a great advantage of this method is not to need to deal with occlusions or objects\´ mutual interferences which happen in images.
Keywords :
multidimensional signal processing; object detection; probability; sampling methods; tracking; condensation particle-set; modified condensation algorithm; multimodal probability density; multiple images; multiple three-dimensional motions tracking; mutual interferences; object tracking; sampling algorithm; Cameras; Filtering algorithms; Image sampling; Interference; Iterative algorithms; Kalman filters; Layout; Particle tracking; Predictive models; Security;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Robots and Systems, 2003. (IROS 2003). Proceedings. 2003 IEEE/RSJ International Conference on
Print_ISBN :
0-7803-7860-1
Type :
conf
DOI :
10.1109/IROS.2003.1250634
Filename :
1250634
Link To Document :
بازگشت