水下小目标快速识别的改进YOLO方法应用与验证OA

To address the constraints of detection capability,real-time performance,and computational resources in rapid obstacle identification for large-scale underactuated unmanned underwater vehicles(UUVs),a high-recall,rapid recognition method for small targets is investigated.A fast small-target recognition model based on an improved YOLO architecture is proposed.GhostNet is introduced as the backbone network,and the computational load is reduced by 48.75%through feature map reuse and linear transformation strategies.The convolutional block attention module(CBAM)is embedded in the neck network to enhance the feature response for small targets.Additionally,a dynamic weighted Focal-EIoU loss function is designed to alleviate the imbalance between positive and negative samples.Ablation and comparative experiments are conducted on a self-constructed sonar image dataset of fishing nets.The improved model's performance metrics are as follows:the AP50 score reached 97.5%,with an increase of 1.3%over the baseline model;the mAP is improved by 5.7%to 58.4%;and the recall rate has increased by 3.2%to 97.3%.The comprehensive performance surpasses that of mainstream models such as YOLOv8n and YOLOv11n.The triple synergistic optimization effectively balances detection speed and accuracy for underwater sonar images,significantly reduces the miss-detection rate for small underwater targets,and improves the robustness of underwater small target recognition.This research provides reliable technical support for real-time obstacle avoidance in large-scale underactuated UUVs.