Search Contact information
University of Cambridge Home Department of Engineering
University of Cambridge > Engineering Department > Machine Intelligence Lab

Abstract for gee_tr207

Cambridge University Engineering Department Technical Report CUED/F-INFENG/TR207

FAST VISUAL TRACKING BY TEMPORAL CONSENSUS

Andrew Gee and Roberto Cipolla

February 1995

At the heart of every model-based visual tracker lies a pose estimation routine. Recent work has emphasised 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 rogue 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 reconciles 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.

Keywords: Visual tracking, pose estimation, robust regression, Bayesian inference, model acquisition

[3 MBytes compressed PostScript, 19 pages]


(ftp:) gee_tr207.ps.Z (http:) gee_tr207.ps.Z
PDF (automatically generated from original PostScript document - may be badly aliased on screen):
  (ftp:) gee_tr207.pdf | (http:) gee_tr207.pdf

If you have difficulty viewing files that end '.gz', which are gzip compressed, then you may be able to find tools to uncompress them at the gzip web site.

If you have difficulty viewing files that are in PostScript, (ending '.ps' or '.ps.gz'), then you may be able to find tools to view them at the gsview web site.

We have attempted to provide automatically generated PDF copies of documents for which only PostScript versions have previously been available. These are clearly marked in the database - due to the nature of the automatic conversion process, they are likely to be badly aliased when viewed at default resolution on screen by acroread.

© 2005 Cambridge University Engineering Dept
Information provided by milab-maintainer