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 contribution | Individual Animal Identification using Visual Biometrics on Deformable Coat Patterns |
---|---|
Original language | English |
Title of host publication | 5th International Conference on Computer Vision Systems (ICVS 2007) |
Publisher | International Conference on Computer Vision Systems |
Number of pages | 10 |
ISBN (Print) | 9783000209338 |
Publication status | Published - 1 Mar 2007 |
Bibliographical note
ISBN: 9783000209338Publisher: DOI:10.2390
Name and Venue of Conference: 5th International Conference on Computer Vision Systems (ICVS07)
Other identifier: 2000684