AquaFeat: A Features-Based Image Enhancement Model for Underwater Object Detection

• Emanuel C. Silva FURG
• Tatiana T. Schein FURG
• Stephanie L. Brião FURG
• Guilherme L. M. Costa FURG
• Felipe G. Oliveira FURG / UFAM
• Gustavo P. Almeida FURG
• Eduardo L. Silva FURG
• Sam S. Devincenzi FURG
• Karina S. Machado FURG
• Paulo L. J. Drews FURG

Resumo

The severe image degradation in underwater environments impairs object detection models, as traditional image enhancement methods are often not optimized for such downstream tasks. To address this, we propose AquaFeat, a novel, plug-and-play module that performs task-driven feature enhancement. Our approach integrates a multi-scale feature enhancement network trained end-to-end with the detector's loss function, ensuring the enhancement process is explicitly guided to refine features most relevant to the detection task. When integrated with YOLOv8m on challenging underwater datasets, AquaFeat achieves state-of-the-art Precision (0.877) and Recall (0.624), along with competitive m A P scores (mAP_0.5 of 0.677 and mAP_0.5:0.95 of 0.421). By delivering these accuracy gains while maintaining a practical processing speed of 46.5 FPS, our model provides an effective and computationally efficient solution for real-world applications, such as marine ecosystem monitoring and infrastructure inspection.

Palavras-chave: Graphics, Degradation, Biological system modeling, Computational modeling, Object detection, Inspection, Feature extraction, Marine ecosystems, Image enhancement, Monitoring