Segmentation methods for visual tracking of deep-ocean jellyfish using a conventional camera

Abstract

This paper presents a vision algorithm that enables automated jellyfish tracking using remotely operated vehicles (ROVs) or autonomous underwater vehicles (AUVs). The discussion focuses on algorithm design. The introduction provides a novel performance-assessment tool, called segmentation efficiency, which aids in matching potential vision algorithms to the jelly-tracking task. This general-purpose tool evaluates the inherent applicability of various algorithms to particular tracking applications. This tool is applied to the problem of tracking transparent jellyfish under uneven time-varying illumination in particle-filled scenes. The result is the selection of a fixed-gradient threshold-based vision algorithm. This approach, implemented as part of a pilot aid for the Monterey Bay Aquarium Research Institute's ROV Ventana, has demonstrated automated jelly tracking for as long as 89 min.