University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Probabilistic Learning of Salient Patterns across Spatially Separated Uncalibrated Views

KaewTraKulPong, P and Bowden, R (2004) Probabilistic Learning of Salient Patterns across Spatially Separated Uncalibrated Views In: IDSS04 - Intelligent Distributed Surveillance Systems, Feb 2004, 2004-02-23 - 2004-02-23, London, UK.

Text (licence)
Available under License : See the attached licence file.

Download (33kB) | Preview


We present a solution to the problem of tracking intermittent targets that can overcome long-term occlusions as well as movement between camera views. Unlike other approaches, our system does not require topological knowledge of the site or labelled training patterns during the learning period. The approach uses the statistical consistency of data obtained automatically over an extended period of time rather than explicit geometric calibration to automatically learn the salient reappearance periods for objects. This allows us to predict where objects may reappear and within how long. We demonstrate how these salient reappearance periods can be used with a model of physical appearance to track objects between spatially separate regions in single and separated views.

Item Type: Conference or Workshop Item (Conference Paper)
Subjects : Computing
Divisions : Faculty of Engineering and Physical Sciences > Computing Science
Authors :
KaewTraKulPong, P
Bowden, R
Date : 23 February 2004
DOI : 10.1049/ic:20040095
Copyright Disclaimer : © Copyright 2004 IEEE
Uncontrolled Keywords : Surveillance, Target tracking, Object detection, Hidden feature removal, Object recognition
Depositing User : Symplectic Elements
Date Deposited : 26 Oct 2016 14:42
Last Modified : 31 Oct 2017 18:51

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800