Abstract | ||
---|---|---|
In this paper we present a new approach based on Markov Chain Monte Carlo (MCMC) for the stable monocular tracking of variable interacting targets in 3D space. The crucial problem with monocular tracking multiple targets is that mutual occlusions on the 2D image cause target conflict(change ID, merge targets...). We focus on the fact that multiple targets cannot occupy the same position in 3D space and propose to track multiple interacting targets using relative position of targets in 3D space. Experiments show that our system can stably track multiple humans that are interacting with each other |
Year | DOI | Venue |
---|---|---|
2008 | 10.1109/ICPR.2008.4761322 | ICPR |
Keywords | Field | DocType |
Markov processes,Monte Carlo methods,target tracking,video surveillance,2D image,3D space,Markov Chain Monte Carlo,monocular 3D tracking,multiple interacting targets,mutual occlusions,stable monocular tracking,variable interacting targets | Computer vision,Monte Carlo method,Markov process,Markov chain Monte Carlo,Computer science,Tracking system,Solid modeling,Artificial intelligence,Monocular,Merge (version control),3d tracking | Conference |
ISSN | Citations | PageRank |
1051-4651 | 1 | 0.36 |
References | Authors | |
3 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tatsuya Osawa | 1 | 29 | 3.76 |
Kyoko Sudo | 2 | 52 | 8.42 |
Hiroyuki Arai | 3 | 6 | 1.16 |
Hideki Koike | 4 | 1080 | 126.62 |