SGL-YOLO: Lightweight Underwater Object Detection Algorithm Based on Feature Fusion

To address the issues of high environmental complexity, insufficient model performance, and low computational efficiency in underwater image analysis, this paper proposes a lightweight underwater object detection algorithm named SGL-YOLO, which is based on an enhanced YOLOv8 framework. In the backbone network, we introduce a newly designed SCA-C2f module that replaces the original C2f module, thereby improving feature discrimination and representation capabilities. To solve the problem of insufficient feature fusion in the neck network, a global-local cross-layer aligned bidirectional feature pyramid network (GLCA-BiFPN) is constructed, which improves the detection performance of small objects while reducing the model parameters and computational cost. A lightweight shared convolutional detection head (LSCD) is introduced in the head to optimize the computational efficiency. Finally, the WIoU is adopted to replace the CIoU loss function, thereby improving the accuracy of bounding box regression. SGL-YOLO achieves outstanding results on the DUO dataset. Compared with YOLOv8, the model parameters are reduced by 45.2%, the model computational complexity is decreased by 27.2%, and the average detection accuracy is increased by 1.1%, achieving a good balance between detection accuracy and detection speed.