Underwater Object Tracker: UOSTrack for Marine Organism Grasping of Underwater Vehicles

TL;DR

UOSTrack is a novel underwater object tracking method that improves accuracy and stability for marine organism grasping by addressing sample imbalance and similar object exclusion through hybrid training and motion-based post-processing.

Contribution

The paper introduces UOSTrack, combining underwater-open air hybrid training and motion-based post-processing to enhance underwater object tracking performance.

Findings

Achieved up to 7.98% performance improvement over state-of-the-art methods.

Validated accuracy and stability in marine organism grasping tasks.

Effective handling of sample imbalance and similar object exclusion.

Abstract

A visual single-object tracker is an indispensable component of underwater vehicles (UVs) in marine organism grasping tasks. Its accuracy and stability are imperative to guide the UVs to perform grasping behavior. Although single-object trackers show competitive performance in the challenge of underwater image degradation, there are still issues with sample imbalance and exclusion of similar objects that need to be addressed for application in marine organism grasping. This paper proposes Underwater OSTrack (UOSTrack), which consists of underwater image and open-air sequence hybrid training (UOHT), and motion-based post-processing (MBPP). The UOHT training paradigm is designed to train the sample-imbalanced underwater tracker so that the tracker is exposed to a great number of underwater domain training samples and learns the feature expressions. The MBPP paradigm is proposed to exclude similar objects. It uses the estimation box predicted with a Kalman filter and the candidate boxes in the response map to relocate the lost tracked object in the candidate area. UOSTrack achieves an average performance improvement of 4.41% and 7.98% maximum compared to state-of-the-art methods on various benchmarks, respectively. Field experiments have verified the accuracy and stability of our proposed UOSTrack for UVs in marine organism grasping tasks. More details can be found at https://github.com/LiYunfengLYF/UOSTrack.