计算机工程与应用2025，Vol.61Issue(6)：96-105,10.DOI:10.3778/j.issn.1002-8331.2408-0411
改进YOLOv8的轻量化水下生物检测模型
Improving Lightweight Underwater Biological Detection Model of YOLOv8
摘要
Abstract
Efficient detection of underwater biological resources in complex natural environments is of great significance to China's fisheries.In order to solve the problems of weak detection ability and insufficient model generalization of YOLO series for complex underwater environments,a method for underwater biological target detection based on improved YOLOv8n,SGDC-YOLOv8,is proposed.Firstly,the idea of deep supervision is integrated into the detection head,using shared receptive field attention convolution to improve detection accuracy while optimizing the receptive field.An addi-tional supervised loss function is introduced to achieve efficient parameter sharing in the detection head.Secondly,in order to reduce computational costs and parameter count,a lightweight gated regularization unit convolution module is designed to reduce the burden on the model.Aiming at the problem of easily blurred or lost features of underwater biologi-cal targets,shallow mixed pool downsampling module and deep maximum pool downsampling module are proposed to optimize multi-scale feature fusion and ensure the accuracy and completeness of key data.Finally,a convolutional and attention fusion CAFM module is added to the network to enhance global and local feature modeling.The experimental results on the publicly available dataset DUO show that compared to the baseline model YOLOv8n,SGDC-YOLOv8 increases by 2.5 percentage points at mAP@50,and 1.8 percentage points in mAP@50-95.It results in a decrease of 14.62%in parameter count and 15.85%in computational complexity.FPS increases to 146.2,which is also the best perfor-mance compared to other mainstream object detection models.关键词
水下目标检测/YOLOv8/轻量化/深度监督Key words
underwater target detection/YOLOv8/lightweight/depth supervision分类
信息技术与安全科学引用本文复制引用
闵锋,张雨薇,刘煜晖,刘彪..改进YOLOv8的轻量化水下生物检测模型[J].计算机工程与应用,2025,61(6):96-105,10.基金项目
国家自然科学基金(62171328). （62171328）
