Tracking Multiple Animals in Wildlife Footage

D Tweed, AD Calway

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

11 Citations (Scopus)

Abstract

We describe a method for tracking animals in wildlife footage. It uses a CONDENSATION particle filtering framework driven by learnt characteristics of specific animals. The key contribution is a periodic model of animal motion based on the relative positions over time of trackable features at significant body points. We also introduce techniques for maintaining a multimodal state density within the particle filter over time to enable consistent tracking of multiple animals. Initial experiments show that the approach has considerable potential.
Translated title of the contributionTracking Multiple Animals in Wildlife Footage
Original languageEnglish
Title of host publication16th International Conference on Pattern Recognition (ICPR 2002), Quebec, August
EditorsR Kasturi, D Laurendeau, C Suen
PublisherIEEE Computer Society
Pages20024 - 20027
Number of pages4
ISBN (Print)0769516963
Publication statusPublished - Aug 2002

Fingerprint Dive into the research topics of 'Tracking Multiple Animals in Wildlife Footage'. Together they form a unique fingerprint.

Cite this