A Framework for Multi-View Multiple Object Tracking using Single-View Multi-Object Trackers on Fish Data

TL;DR

This paper develops a multi-view framework using stereo video inputs to improve fish tracking accuracy in underwater environments, adapting existing single-view models for ecological research.

Contribution

It introduces a novel multi-view tracking framework that enhances accuracy and 3D understanding of fish movements by integrating stereo video data with state-of-the-art models.

Findings

Achieved 47% relative accuracy in fish detection.

Enhanced tracking precision over single-view methods.

Produced 3D fish movement data from stereo matching.

Abstract

Multi-object tracking (MOT) in computer vision has made significant advancements, yet tracking small fish in underwater environments presents unique challenges due to complex 3D motions and data noise. Traditional single-view MOT models often fall short in these settings. This thesis addresses these challenges by adapting state-of-the-art single-view MOT models, FairMOT and YOLOv8, for underwater fish detecting and tracking in ecological studies. The core contribution of this research is the development of a multi-view framework that utilizes stereo video inputs to enhance tracking accuracy and fish behavior pattern recognition. By integrating and evaluating these models on underwater fish video datasets, the study aims to demonstrate significant improvements in precision and reliability compared to single-view approaches. The proposed framework detects fish entities with a relative accuracy of 47% and employs stereo-matching techniques to produce a novel 3D output, providing a more comprehensive understanding of fish movements and interactions