COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |
University of Cambridge > Talks.cam > Machine Learning Journal Club > Fast Visual Tracking By Temporal Consensus
Fast Visual Tracking By Temporal ConsensusAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Philip Sterne. A.H. Gee and R. Cipolla, ``Fast visual tracking by temporal consensus’’, Image and Vision Computing, 14(2):105-114, 1996. This is a somewhat dated paper with interesting points on doing visual tracking of head pose. They use a very simplistic and inaccurate feature (pixel/corner) tracker but nevertheless obtain very good pose recovery results. The paper can be downloaded here:
Abstract At the heart of every model-based visual tracker lies a pose estimation routine. Recent work has emphasized the use of least-squares techniques which employ all the available data to estimate the pose. Such techniques are, however, susceptible to the sort of spurious measurements produced by visual feature detectors, often resulting in an unrecoverable tracking failure. This paper investigates an alternative approach, where a minimal subset of the data provides the pose estimate, and a robust regression scheme selects the best subset. Bayesian inference in the regression stage combines measurements taken in one frame with predictions from previous frames, eliminating the need to further filter the pose estimates. The resulting tracker performs very well on the difficult task of tracking a human face, even when the face is partially occluded. Since the tracker is tolerant of noisy, computationally cheap feature detectors, frame-rate operation is comfortably achieved on standard hardware. This talk is part of the Machine Learning Journal Club series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsEngineering Department Structures Research Seminars Wolfson-HAT Foundation Annual Symposium Series on Personal Data Scott Polar Research Institute - Polar Physical Sciences SeminarOther talksThe Chemistry of Planet Formation and the Making of Habitable Planets Holonomic D-modules, b-functions, and coadmissibility Huntington´s disease and autophagy - insights from human and mouse model systems Adaptation in log-concave density estimation Computing High Resolution Health(care) 'Walking through Language – Building Memory Palaces in Virtual Reality' The Productivity Paradox: are we too busy to get anything done? Cambridge-Lausanne Workshop 2018 - Day 1 Back on the Agenda? Industrial Policy revisited Conference |