改进YOLOv8的SAR影像船舰目标检测模型

doi:10.13474/j.cnki.11-2246.2024.1204

测绘通报 ›› 2024, Vol. 0 ›› Issue (12): 18-23.doi: 10.13474/j.cnki.11-2246.2024.1204

改进YOLOv8的SAR影像船舰目标检测模型

杨明秋, 陈国坤, 左小清, 董燕

昆明理工大学国土资源工程学院, 云南昆明 650093

收稿日期:2024-03-11 发布日期:2024-12-27
通讯作者: 陈国坤,E-mail:chengk@radi.ac.cn E-mail:chengk@radi.ac.cn
作者简介:杨明秋(1995-),男,硕士生,主要从事遥感图像目标检测方面的研究工作。E-mail:3037058867@qq.com
基金资助:
国家自然科学基金(42161067);云南省重大科技专项计划(202202AD080010)

Improving the SAR image ship target detection model of YOLOv8

YANG Mingqiu, CHEN Guokun, ZUO Xiaoqing, DONG Yan

Faculty of Land and Resources Engineering, Kunming University of Science And Technology, Kunming 650093, China

Received:2024-03-11 Published:2024-12-27

摘要/Abstract

摘要： 在SAR影像船舰目标检测任务中,受近海岸区域背景复杂和船舰目标多尺度等因素影响,船舰目标在检测过程中出现检测精度不高、漏检的问题。针对上述问题,本文提出了一种基于YOLOv8s改进的SAR影像船舰目标检测模型,并在SSDD和HRSID数据集上进行试验验证,效果优于其他经典算法。

关键词: 船舰目标检测, SAR影像, 残差增强, 可变形卷积, 动态稀疏注意力

Abstract: In the SAR image ship target detection task, due to factors such as complex coastal background and multi-scale ship targets, ship targets may have low detection accuracy and missed detections during the detection process. In response to the above issues, this article proposes an improved SAR image ship target detection model based on YOLOv8s, and conducts experimental verification by SSDD and HRSID datasets, with better performance than other classical algorithms.

Key words: ship target detection, SAR imaging, residual enhancement, deformable convolution, dynamic sparse attention

中图分类号:

P237

杨明秋, 陈国坤, 左小清, 董燕. 改进YOLOv8的SAR影像船舰目标检测模型[J]. 测绘通报, 2024, 0(12): 18-23.

YANG Mingqiu, CHEN Guokun, ZUO Xiaoqing, DONG Yan. Improving the SAR image ship target detection model of YOLOv8[J]. Bulletin of Surveying and Mapping, 2024, 0(12): 18-23.

参考文献

[1] LIU Wei,ANGUELOV D,ERHAN D,et al.SSD:single shot MultiBox detector[M]//Computer Vision-ECCV 2016.Cham:Springer International Publishing,2016:21-37.
[2] GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition.Columbus:IEEE,2014:580-587.
[3] GIRSHICK R.Fast R-CNN[C]//Proceedings of 2015 IEEE International Conference on Computer Vision.Santiago:IEEE,2015:1440-1448.
[4] REN Shaoqing,HE Kaiming,GIRSHICK R,et al.Faster R-CNN:towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.
[5] 苏常旺,胡少伟,张海丰,等.基于改进YOLOX算法的给水管道内缺陷智能识别与定位[J].测绘通报,2023(12):70-75.
[6] 李健伟,曲长文,彭书娟.SAR图像舰船目标联合检测与方向估计[J].武汉大学学报(信息科学版),2019,44(6):901-907.
[7] 耿晓蒙.面向近岸复杂场景的SAR影像目标智能检测方法研究[J].测绘学报,2023,52(11):4
[8] CHANG Lena,CHEN Yiting,WANG J H,et al.Modified Yolov3 for ship detection with visible and infrared images[J].Electronics,2022,11(5):739.
[9] CHEN Haiwei,ZHOU Guohui,JIANG Huixin.Student behavior detection in the classroom based on improved YOLOv8[J].Sensors,2023,23(20):8385.
[10] ZHU Xingkui,LYU Shuchang,WANG Xu,et al.TPH-YOLOv5:improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios[C]//Proceedings of 2021 IEEE/CVF International Conference on Computer Vision Workshops.Montreal:IEEE,2021:2778-2788.
[11] GUPTA C,GILL N S,GULIA P,et al.A novel finetuned YOLOv6 transfer learning model for real-time object detection[J].Journal of Real-time Image Processing,2023,20(3):42.
[12] YU Bingqi,JIAO Licheng,LIU Xu,et al.Entire Deformable ConvNets for semantic segmentation[J].Knowledge-based Systems,2022,250:108871.
[13] ZHU Lei,WANG Xinjiang,KE Zhanghan,et al.BiFormer:vision transformer with Bi-level routing attention[C]//Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Vancouver:IEEE,2023:10323-10333.
[14] ZHANG T,ZHANG X,LI J,et al.SAR ship detection dataset (SSDD):official release and comprehensive data analysis[J].Remote Sensing,2021,13(18):3690.
[15] WEI Shunjun,ZENG Xiangfeng,QU Qizhe,et al.HRSID:a high-resolution SAR images dataset for ship detection and instance segmentation[J].IEEE Access,2020,8:120234-120254.

改进YOLOv8的SAR影像船舰目标检测模型

Improving the SAR image ship target detection model of YOLOv8

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 11

编辑推荐

Metrics

本文评价

[1]	蓝贵文, 徐梓睿, 任新月, 钟展, 郭瑞东, 范冬林. 基于YOLOv8n改进的航拍输电线路图像多类电力部件检测算法[J]. 测绘通报, 2024, 0(9): 38-43,49.
[2]	段玉, 刘善伟, 万剑华, MUHAMMAD Yasir, 郑爽. 多尺度融合卷积神经网络支持下的SAR影像变化检测[J]. 测绘通报, 2023, 0(12): 31-37.
[3]	柳林, 孙毅, 李万武. 基于CNN海上钻井平台检测模型的构建及训练算法分析[J]. 测绘通报, 2022, 0(7): 26-32,99.
[4]	刘剑, 王冬至. 基于SAR影像的广东省垦造水田监测应用研究[J]. 测绘通报, 2021, 0(12): 79-82.
[5]	付睢宁, 卢小平, 卢遥. 适用于SAR影像的偏微分ROF去噪算法[J]. 测绘通报, 2018, 0(11): 16-19.
[6]	余莎莎, 余洁, 朱腾, 王彦兵. 一种改进的MCSM/H-PSO全极化SAR影像分类方法[J]. 测绘通报, 2018, 0(11): 53-57.
[7]	刘晓君, 韩芳, 赵磊. 一种改进的SAR影像边缘检测方法[J]. 测绘通报, 2017, 0(9): 56-59.
[8]	贾洪果, 刘路遥, 韦博文, 张梦意, 武燕, 章昊. 基于形状与纹理特征的高分辨率SAR影像桥梁目标自动提取方法[J]. 测绘通报, 2017, 0(12): 82-85.
[9]	秦晓琼, 廖明生, 杨梦诗, 王寒梅, 杨天亮. 应用高分辨率PS-InSAR技术监测上海动迁房歪斜形变[J]. 测绘通报, 2016, 0(6): 18-21,86.
[10]	陈华, 邓喀中, 张以文, 范洪冬, 杨俊凯. 结合SIFT和RANSAC算法的InSAR影像配准[J]. 测绘通报, 2015, 0(12): 30-33.
[11]	程丹范洪冬邓喀中姚国标. 基于MSER的SAR影像配准算法[J]. 测绘通报, 2014, 0(12): 28-31.