AquaFeat+: an Underwater Vision Learning-based Enhancement Method for Object Detection, Classification, and Tracking

TL;DR

AquaFeat+ is a modular underwater vision enhancement pipeline that improves object detection, classification, and tracking by focusing on feature enhancement tailored for robotic perception, validated on the FishTrack23 dataset.

Contribution

It introduces a novel plug-and-play architecture with end-to-end training that enhances features specifically for perception tasks in underwater environments.

Findings

Significant improvement in detection, classification, and tracking metrics.

Effective end-to-end training guided by application-specific loss.

Validated on FishTrack23 dataset with strong results.

Abstract

Underwater video analysis is particularly challenging due to factors such as low lighting, color distortion, and turbidity, which compromise visual data quality and directly impact the performance of perception modules in robotic applications. This work proposes AquaFeat+, a plug-and-play pipeline designed to enhance features specifically for automated vision tasks, rather than for human perceptual quality. The architecture includes modules for color correction, hierarchical feature enhancement, and an adaptive residual output, which are trained end-to-end and guided directly by the loss function of the final application. Trained and evaluated in the FishTrack23 dataset, AquaFeat+ achieves significant improvements in object detection, classification, and tracking metrics, validating its effectiveness for enhancing perception tasks in underwater robotic applications.