Underwater-YCC: Underwater Target Detection Optimization Algorithm Based on YOLOv7

Underwater target detection using optical images is a challenging yet promising area that has witnessed significant progress. However, fuzzy distortions and irregular light absorption in the underwater environment often lead to image blur color bias, particularly for small targets. Consequently, existing methods have yield satisfactory results. To address this issue, we propose Underwater-YCC optimization algorithm based on You Only Look Once (YOLO) v7 enhance accuracy of detecting targets underwater. Our utilizes Convolutional Block Attention Module (CBAM) obtain fine-grained semantic information by selecting an optimal position through multiple experiments. Furthermore, employ Conv2Former as Neck component network blurred images. Finally, apply Wise-IoU, which effective improving assigning weights between high- low-quality experiments URPC2020 dataset demonstrate achieves mean Average Precision (mAP) up 87.16% complex environments.