Dolphin fin pose correction using ICP in application to photo-identification

摘要

Photo-identification of dolphin individuals is a commonly used technique in ecological sciences to monitor state and health of individuals, as well as to study the social structure and distribution of a population. Uniqueness of some forms of damage sustained by the trailing edge of the dorsal fin throughout an individual's life allows it to be used to identify the individual. Traditional photo-identification involves a laborious manual process of matching each dolphin fin photograph captured in the field to a catalogue of known individuals. A number of efforts have been made in the past to automate this process through the use of digital image processing; however, none of them correct for the different fin orientations (3D pose) prior to performing matching in a robust way. This paper provides an overview of these existing methods and offers a novel approach of utilising the iterative closest point (ICP) algorithm for performing the projective registration of two fin shapes and shows that this proposed method is robust to segmentation noise, partial occlusions and new nicks and notches appearing since last encounter.