文献类型：期刊文献

中文题名：基于YOLOv8优化的海洋牧场海珍类生物目标检测模型

英文题名：Optimization Based on YOLOv8 for Marine Ranch Valuable Marine Organisms Target Detection Model

作者：麦仁贵[1,2];刘雯景[2,3];王骥[2,3];周涛[2,3];刘侦龙[1,2]

机构：[1]广东海洋大学数学与计算机学院,广东湛江524088;[2]广东省智慧海洋传感网及其装备工程技术研究中心,广东湛江524088;[3]广东海洋大学电子与信息工程学院,广东湛江524088

年份：2026

卷号：56

期号：5

起止页码：168

中文期刊名：中国海洋大学学报(自然科学版)

外文期刊名：Periodical of Ocean University of China

收录：北大核心2023、、北大核心

基金：广东省普通高校重点领域新一代信息技术专项项目(2020ZDZX3008);广东省人工智能领域重点专项项目(2019KZDZX1046)资助。

语种：中文

中文关键词：海珍类生物;目标检测;YOLOv8;残差注意力机制;双向特征金字塔

外文关键词：valuable marine organisms;object detection;YOLOv8;residual attention mechanism;bidirectional feature pyramid

中文摘要：针对目前海洋牧场区域水下海珍类生物目标检测存在检测精度不高、漏检和误检的问题,本文提出了基于YOLOv8(You only look once v8)模型改进的水下海珍类生物目标检测方法。本文设计了一种新的残差注意力机制,并将其嵌入到YOLOv8模型的主干网络中,增强特征提取过程中对水下目标细节特征的注意力;在颈部网络中引入具有自适应特征融合的双向特征金字塔,更好地融合了深层特征图的强语义信息和浅层特征图的定位信息,突出了目标和环境的差异性。实验表明,改进后的YOLOv8模型的平均精度均值(mAP@0.5)为92.98%,比原YOLOv8模型提高了1.36个百分点,平均精度均值(mAP@0.5∶0.95)为76.71%,比原YOLOv8模型提高了3.7个百分点;与主流的目标检测模型Faster R-CNN、SSD、RetinaNet、YOLOv6和YOLOv7相比,mAP@0.5分别提高了1.57个百分点、1.74个百分点、3.17个百分点、4.68个百分点和1.47个百分点。本文提出的模型在复杂海底环境中检测精度高、稳定性好,可为海洋牧场水下资源的科学管理提供技术支持。

外文摘要：In response to the challenges of low detection accuracy,missed detections,and false detections in identifying valuable marine organisms in marine ranch areas,this study introduces an enhanced algorithm for detecting rare underwater marine species using the YOLOv8 model.Firstly,a new residual attention mechanism was designed and integrated into the backbone network of the YOLOv8 model to improve focus on the detailed features of underwater targets during feature extraction.Next,a bidirectional feature pyramid with adaptive feature fusion and feature selection characteristics is incorporated into the neck network to effectively combine the strong semantic information of deep feature maps with the localization information of shallow feature maps.This emphasizes the distinctions between the target and the surroundings.The experiment showed that the mean Average Precision(mAP@0.5)of the enhanced YOLOv8 model was 92.98%,which is 1.36 percentage point higher than the original YOLOv8 model.Additionally,the mean Average Precision(mAP@0.5∶0.95)was 76.71%,indicating a 3.7 percentage point improvement over the original YOLOv8 model.Compared with mainstream object detection models such as Faster RCNN,SSD,RetinaNet,YOLOv6,and YOLOv7,the improved model has shown an increase of 1.57 percentage point,1.74 percentage point,3.17 percentage point,4.68 percentage point,and 1.47 percentage point respectively in mAP@0.5.The model proposed in this paper demonstrates high detection accuracy and robust stability in complex seabed environments.It can provide technical support for the scientific management of underwater resources in marine ranches.