AquaFeat+: an Underwater Vision Learning-based Enhancement Method for Object Detection, Classification, and Tracking
This addresses the challenge of low lighting, color distortion, and turbidity in underwater environments for robotic applications, representing an incremental advancement in domain-specific vision enhancement.
The paper tackles the problem of poor visual data quality in underwater video analysis, which affects perception in robotics, by proposing AquaFeat+, a plug-and-play pipeline that enhances features for automated vision tasks, achieving significant improvements in object detection, classification, and tracking metrics on the FishTrack23 dataset.
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.