|本期目录/Table of Contents|

[1]陈颖,周海峰,郑东强,等.基于改进YOLOv8n的船舶目标检测算法[J].集美大学学报(自然科学版),2026,31(2):176-188.
　CHEN Ying,ZHOU Haifeng,ZHENG Dongqiang,et al.Ship Target Detection Algorithm Based on Improved YOLOv8n[J].Journal of Jimei University,2026,31(2):176-188.
点击复制

基于改进YOLOv8n的船舶目标检测算法(PDF)
分享到：

《集美大学学报（自然科学版）》[ISSN:1007-7405/CN:35-1186/N]

卷:
第31卷
期数:
2026年第2期
页码:
176-188
栏目:
船海与交通运输工程
出版日期:
2026-03-28

文章信息/Info

Title:
Ship Target Detection Algorithm Based on Improved YOLOv8n
作者:
陈颖1; 2; 周海峰1; 2; 郑东强3; 张兴杰4; 黄金满5
（1.集美大学轮机工程学院，福建 厦门 361021；2.福建省船舶与海洋工程重点实验室，福建 厦门 361021；3.集美大学海洋装备与机械工程学院，福建 厦门 361021；4.集美大学航海学院，福建 厦门361021；5.厦门安麦信自动化科技有限公司，福建 厦门 361001）
Author(s):
CHEN Ying1; 2; ZHOU Haifeng1; 2; ZHENG Dongqiang3; ZHANG Xingjie4; HUANG Jinman5
(1.School of Marine Engineering,Jimei University,Xiamen 361021,China;2.Key Laboratory of Shipping and Ocean Engineering of Fujian Province,Xiamen 361021,China;3.School of Marine Equipment and Mechanical Engineering,Xiamen 361021,China;4.School of Navigation,Jimei University,Xiamen 361021,China;5.Xiamen Anmaixin Automation Technology Co., Ltd.,Xiamen 361001,China)
关键词:
船舶目标; 目标检测; YOLOv8n; 特征提取; 特征融合
Keywords:
ship targets; object detection; YOLOv8n; feature extraction; feature fusion
分类号:
-
DOI:
-
文献标志码:
A
摘要:
为了解决船舶图像目标检测任务中船舶目标尺度多样、背景环境复杂导致的漏检误检等问题，提出一种用于船舶目标检测的DSAMPNYOLOv8n算法模型。引入动态蛇形卷积(dynamic snake convolution，DSC)和无参数注意力机制（simple parameter-free attention mechanism,SimAM），提高YOLOv8n网络在复杂环境下对检测目标的特征提取和融合能力；构建多尺度渐近特征金字塔网络（asymptotic feature pyramid network，AFPN）实现多尺度特征信息交换，增强特征融合效果，提高模型对不同尺度船舶目标的检测能力。使用Seaships船舶数据集对改进算法模型进行实验验证，结果表明，相较于YOLOv8n算法，优化后的算法DSAMPN-YOLOv8n的精确率、召回率和mAP@0.5分别提升了6.0%、6.7%、3.6%，实验结果验证了改进方法的准确性和有效性。
Abstract:
To address the challenges of missed and false detections in ship image target detection tasks caused by diverse ship target scales and complex background environments,a DSAMPNYOLOv8n algorithm model for ship target detection was proposed.The model introduces dynamic snake convolution (DSC) and simple parameter-free attention mechanism to enhance the YOLOv8n network’s ability to extract and integrate features in complex environments.Additionally,a multi-scale asymptotic feature pyramid network (AFPN) was constructed to facilitate multi-scale feature exchange,improving feature fusion and enhancing the model’s capability to detect ship targets of different scales.The proposed algorithm model was experimentally validated using the Seaships dataset.Results showed that,in comparing with those from the YOLOv8n algorithm,the optimized DSAMPNYOLOv8n algorithm achieves improvements in precision,recall,mAP@0.5 by 6.0%,6.7%,3.6%,respectively.These findings validate the accuracy and effectiveness of the proposed method.

参考文献/References:

相似文献/References:

[1]葛旭阳,黄尚锋,蔡国榕.基于三维立方体损失的点云目标检测算法[J].集美大学学报(自然科学版),2021,26(3):280.
　GE Xuyang,HUANG Shangfeng,CAI Guorong.Point Cloudobject Detection Algorithm Based on 3D Cube Loss[J].Journal of Jimei University,2021,26(2):280.
[2]陈立媛,杨神化,索永峰,等.不同船舶目标电磁散射仿真[J].集美大学学报(自然科学版),2021,26(6):519.
　CHEN Liyuan,YANG Shenhua,SUO Yongfeng,et al.Electromagnetic Scattering Simulation Analysis of Different Targets Ship Types[J].Journal of Jimei University,2021,26(2):519.
[3]郑东强,周海峰,曾伟民,等.基于多维空间离散基准的目标检测网络设计[J].集美大学学报(自然科学版),2024,29(3):282.
　ZHENG Dongqiang,ZHOU Haifeng,ZENG Weimin,et al.The Design of Object Detection Network Based on Multidimensional Space Discrete Datum[J].Journal of Jimei University,2024,29(2):282.

备注/Memo

备注/Memo:
更新日期/Last Update: 2026-04-21