Paper Info
Title
MCMC based multi-body tracking using full 3D model of both target and environment
Abstract
In this paper, we present a new approach for the stable tracking of variable interacting targets under severe occlusion in 3D space. We formulate the state of multiple targets as a union state space of each target, and recursively estimate the multi-body configuration and the position of each target in 3D space by using the framework of Trans-dimensional Markov Chain Monte Carlo(MCMC). The 3D environmental model, which replicates the real-world 3D structure, is used for handling occlusions created by fixed objects in the environment, and reliably estimating the number of targets in the monitoring area. Experiments show that our system can stably track multiple humans that are interacting with each other and entering and leaving the monitored area.
Year
DOI
Venue
2007
10.1109/AVSS.2007.4425314
AVSS
Keywords
Field
DocType
fixed object,multi-body tracking,environmental model,multiple human,monitoring area,variable interacting target,monitored area,multiple target,trans-dimensional markov chain monte,multi-body configuration,union state space,markov chain monte carlo,markov processes,state space,monte carlo methods
Computer vision,Monte Carlo method,Markov process,Markov chain Monte Carlo,Computer science,Environmental model,Artificial intelligence,State space,Recursion
Conference
ISBN
Citations 
PageRank 
978-1-4244-1696-7
2
0.38
References 
Authors
7
6
Name
Order
Citations
PageRank
Tatsuya Osawa1293.76
Xiaojun Wu214710.96
Kyoko Sudo3528.42
Kaoru Wakabayashi4394.01
Hiroyuki Arai561.16
Takayuki Yasuno6285.76