{"type":"ScholarlyArticle","title":"Object Identification in a Bayesian Context","authors":[{"name":"Timothy Huang","slug":"timothy-huang","given":"Timothy","family":"Huang","affiliation":"Computer Science Division University of California Berkeley , CA 94720 , USA"},{"name":"Stuart J. Russell","slug":"stuart-j-russell","given":"Stuart J.","family":"Russell","affiliation":"Computer Science Division University of California Berkeley , CA 94720 , USA"}],"abstract":"Object identification-the task of deciding that two observed objects are in fact one and the same object-is a fundamental requirement for any situated agent that reasons about individuals. Object identity, as represented by the equality operator between two terms in predicate calculus, is essentially a first-order concept. Raw sensory observations, on the other hand, are essentially propositionalespecially when formulated as evidence in standard probability theory. This paper describes patterns of reasoning that allow identity sentences to be grounded in sensory observations, thereby bridging the gap. We begin by defining a physical event space over which probabilities are defined. We then introduce an identity criterion, which selects those events that correspond to identity between observed objects. From this, we are able to compute the probability that any two objects are the same, given a stream of observations of many objects. We show that the appearance probability, which defines how an object can be expected to appear at subsequent observations given its current appearance, is a natural model for this type of reasoning. We apply the theory to the task of recognizing cars observed by cameras at widely separated sites in a freeway network, with new heuristics to handle the inevitable complexity of matching large numbers of objects and with online learning of appearance probability models . Despite extremely noisy observations, we are able to achieve high levels of performance.","doi":null,"url":"https://ijcai.org/proceedings/1997/184","pdf":"https://ijcai.org/proceedings/1997/0184.pdf","markdown":"https://ijcai.org/proceedings/1997/184.md","bibtex":"https://ijcai.org/proceedings/1997/bibtex/184","volume":{"slug":"1997","title":"Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 1997","url":"https://ijcai.org/proceedings/1997/","year":1997,"location":"Nagoya, Japan","dates":"","editors":"Martha E. Pollack","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":"Probabilistic Reasoning","track":"Probabilistic Reasoning","number":184,"pages":{"first":1276,"last":1282},"keywords":[],"videos":[],"references":[{"position":1,"raw":"[Bacchus et al., 1995] Fahiem Bacchus, Joseph Y. Halpern, and Hector Levesque. Reasoning about noisy sensors in the situation calculus. In Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence (/JCAI-95), pages 1933-1940, Montreal, Canada, August 1995.","title":"Reasoning about noisy sensors in the situation calculus","authors":"Bacchus","year":"1995","venue":"Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence (/JCAI-95)","doi":null,"url":null,"internal_url":"/proceedings/1995/248"},{"position":2,"raw":"Morgan Kaufmann.","title":null,"authors":"Morgan Kaufmann","year":null,"venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bar-Shalom and Fortmann, 1988] Yaakov Bar-Shalom and Thomas E. Fortmann. Tracking and Data Association. Academic Press, New York, 1988.","title":"Yaakov Bar-Shalom and Thomas E. Fortmann. Tracking and Data Association","authors":"Fortmann Bar-Shalom","year":"1988","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bar-Shalom, 1992] Yaakov Bar-Shalom, editor. Multitar- get multisensor tracking: Advanced applications. Artech House, Norwood, Massachusetts, 1992.","title":"Multitarget multisensor tracking: Advanced applications","authors":null,"year":"1992","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Cox and Hingorani, 1994] I.J. Cox and S.L. Hingorani. An efficient implementation and evaluation of Reid's multi- ple hypothesis tracking algorithm for visual tracking. In Proceedings of the 12th /APR International Conference on Pattern Recognition, volume I, pages 437-442, Jerusalem, Israel, October 1994.","title":"An efficient implementation and evaluation of Reid's multiple hypothesis tracking algorithm for visual tracking","authors":"Hingorani ; ] I J Cox, S L Cox, Hingorani","year":"1994","venue":"Proceedings of the 12th /APR International Conference on Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Cox, 1993] I.J. Cox. A review of statistical data associa- tion techniques for motion correspondence. International Journal of Computer Vision, 10:53-66, 1993.","title":"A review of statistical data association techniques for motion correspondence","authors":"I J Cox","year":"1993","venue":"International Journal of Computer Vision","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Malik and Russell , 1997] JitendraMalik and Stuart Russell. Traffic surveillance and detection technology development: New sensor technology final report. Research Report UCB- ITS-PRR-97-6, California PATH Program, 1997.","title":"JitendraMalik and Stuart Russell. Traffic surveillance and detection technology development: New sensor technology final report","authors":"Russell Malik","year":"1997","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"Petty et al., to appear] K. F. Petty, P. Bickel, J. Jiang, M. Ost- land, J. Rice, Y. Ritov, and F. Schoenberg. Accurate esti- mation of travel times from single-loop detectors. Trans- portation Research, Part B, to appear.","title":"Accurate estimation of travel times from single-loop detectors","authors":"Petty","year":null,"venue":"Transportation Research, Part B","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}