Abstract | ||
---|---|---|
Many applications require the ability to track the 3-D motion of the subjects. We build a particle filter based framework for multimodal tracking using multiple cameras and multiple microphone arrays. In order to calibrate the resulting system, we propose a method to determine the lo- cations of all microphones using at least five loudspeakers and under assumption that for each loudspeaker there ex- ists a microphone very close to it. We derive the maximum likelihood (ML) estimator, which reduces to the solution of the non-linear least squares problem. We verify the correct- ness and robustness of the multimodal tracker and of the self-calibration algorithm both with Monte-Carlo simula- tions and on real data from three experimental setups. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1109/CVPR.2007.383525 | CVPR |
Keywords | Field | DocType |
Monte Carlo methods,image motion analysis,least squares approximations,particle filtering (numerical methods),teleconferencing,video signal processing,video surveillance,3D motion,Monte-Carlo simulations,maximum likelihood estimator,multimodal tracking,multiple cameras,multiple microphone arrays,nonlinear least squares problem,particle filter,self-calibration algorithm,smart videoconferencing,video surveillance | Least squares,Computer vision,Computer science,Particle filter,Correctness,Robustness (computer science),Artificial intelligence,Videoconferencing,Loudspeaker,Microphone,Estimator | Conference |
Volume | Issue | ISSN |
2007 | 1 | 1063-6919 |
Citations | PageRank | References |
1 | 0.36 | 26 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dmitry N. Zotkin | 1 | 171 | 19.06 |
Vikas C. Raykar | 2 | 864 | 73.74 |
Ramani Duraiswami | 3 | 1721 | 161.98 |
Larry S. Davis | 4 | 14201 | 2690.83 |