- Abstract:
-
We investigate a solution to the problem of multi-sensor perception and tracking by formulating it in the framework of Bayesian model selection. Humans robustly associate multi-sensory data as appropriate, but previous theoretical work has focused largely on purely integrative cases, leaving segregation unaccounted for and unexploited by machine perception systems. We illustrate a unifying, Bayesian solution to multi-sensor perception and tracking which accounts for both integration and segregation by explicit probabilistic reasoning about data association in a temporal context. Unsupervised learning of such a model with EM is illustrated for a real world audio-visual application.
- Copyright:
- 2006 by The University of Edinburgh. All Rights Reserved
- Links To Paper
- 1st Link
- Bibtex format
- @InProceedings{EDI-INF-RR-0879,
- author = {
Timothy Hospedales
and Joel Cartwright
and Sethu Vijayakumar
},
- title = {Structure Inference for Bayesian Multisensory Perception and Tracking},
- book title = {International Joint Conference on Artificial Intelligence (IJCAI 2007)},
- year = 2007,
- month = {Jan},
- pages = {2122-2128},
- doi = {http://www.ijcai.org/papers07/Papers/IJCAI07-342.p},
- url = {http://homepages.inf.ed.ac.uk/svijayak/publications/hospedales-IJCAI2007.pdf},
- }
|
