{"type":"ScholarlyArticle","title":"Structure Inference for Bayesian Multisensory Perception and Tracking","authors":[{"name":"Timothy M. Hospedales","slug":"timothy-m-hospedales","given":"Timothy M.","family":"Hospedales","affiliation":""},{"name":"Joel J. Cartwright","slug":"joel-j-cartwright","given":"Joel J.","family":"Cartwright","affiliation":""},{"name":"Sethu Vijayakumar","slug":"sethu-vijayakumar","given":"Sethu","family":"Vijayakumar","affiliation":""}],"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.","doi":null,"url":"https://ijcai.org/proceedings/2007/342","pdf":"https://ijcai.org/proceedings/2007/0342.pdf","markdown":"https://ijcai.org/proceedings/2007/342.md","bibtex":"https://ijcai.org/proceedings/2007/bibtex/342","volume":{"slug":"2007","title":"Proceedings of the Twentieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2007","url":"https://ijcai.org/proceedings/2007/","year":2007,"location":"Hyderabad, India","dates":"","editors":"Ramon López de Mántaras","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":null,"track":"","number":342,"pages":{"first":2122,"last":2127},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}