T
Tim Huang
Researcher at University of California, Berkeley
Publications - 8
Citations - 1112
Tim Huang is an academic researcher from University of California, Berkeley. The author has contributed to research in topics: Traffic flow & Bayesian probability. The author has an hindex of 6, co-authored 7 publications receiving 1098 citations.
Papers
More filters
Proceedings ArticleDOI
Towards robust automatic traffic scene analysis in real-time
Daphne Koller,Joseph Weber,Tim Huang,Jitendra Malik,Gary H. Ogasawara,Bhaskar D. Rao,Stuart Russell +6 more
TL;DR: Improvements in technologies for machine vision-based surveillance and high-level symbolic reasoning have enabled the authors to develop a system for detailed, reliable traffic scene analysis and preliminary results show that near real-time performance can be achieved without further improvements.
Proceedings Article
Object identification in a Bayesian context
Tim Huang,Stuart Russell +1 more
TL;DR: Patterns of reasoning are described that allow identity sentences to be grounded in sensory observations, thereby bridging the gap between standard probability theory and sensory observations.
Proceedings Article
The BATmobile: towards a Bayesian automated taxi
TL;DR: A new approach to this problem that uses a decision-theoretic architecture using dynamic probabilistic networks that provides a sound solution to the problems of sensor noise, sensor failure, and uncertainty about the behavior of other vehicles and about the effects of one's own actions is described.
Proceedings Article
Automatic symbolic traffic scene analysis using belief networks
Tim Huang,Daphne Koller,Jitendra Malik,Gary H. Ogasawara,Bhaskar D. Rao,Stuart Russell,Joseph Weber +6 more
TL;DR: The machine vision component of this system employs a contour tracker and an affine motion model based on Kalman filters to extract vehicle trajectories over a sequence of traffic scene images.
Journal ArticleDOI
Object identification: a Bayesian analysis with application to traffic surveillance
Tim Huang,Stuart Russell +1 more
TL;DR: In this article, the authors define a physical event space over which probabilities are defined, and then introduce an identity criterion, which selects those events that correspond to identity between observed objects, and compute the probability that any two objects are the same, given a stream of observations of many objects.