Individual Animal Identification using Visual Biometrics on Deformable Coat Patterns

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

Abstract

In this paper we propose and evaluate a recognition approach to individual animal identification in patterned species based on video filmed in widely unconstrained, natural habitats. The key issue addressed is a distortion robust detection and comparison of unique, deforming camouflage markings as found in a wide range of species. We propose a coarse-to-fine methodology specifically extending and combining vision techniques in a three-stage approach, that is 1) a rapid, coarse key-view detection based on patch appearance, 2) pose estimation and 3D model fitting using a (pre-computed) dynamic Feature Prediction Tree (FPT)followed by bundle adjustment and 3) texture back-projection, extraction of unique phase singularities and final encoding using an extended variant of Shape Contexts. Distortion-robust animal identification is then achieved by solving associated bipartite graph matching tasks for pairsof templates. Independently producing time-stamped identification data, the system marks a first steptowards a partial automation of biological field observations that may permit for a truly non-intrusive behavioural as well as conservational analysis of population dynamics.
Translated title of the contributionIndividual Animal Identification using Visual Biometrics on Deformable Coat Patterns
Original languageEnglish
Title of host publication5th International Conference on Computer Vision Systems (ICVS 2007)
PublisherInternational Conference on Computer Vision Systems
Number of pages10
ISBN (Print)9783000209338
Publication statusPublished - 1 Mar 2007

Bibliographical note

ISBN: 9783000209338
Publisher: DOI:10.2390
Name and Venue of Conference: 5th International Conference on Computer Vision Systems (ICVS07)
Other identifier: 2000684

Fingerprint

Dive into the research topics of 'Individual Animal Identification using Visual Biometrics on Deformable Coat Patterns'. Together they form a unique fingerprint.

Cite this