计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (6A): 240600118-8.doi: 10.11896/jsjkx.240600118

• 图像处理&多媒体技术 • 上一篇    下一篇

基于改进PPYOLOE-R的遥感图像舰船目标检测

陈天鹏, 胡建文, 李海涛   

  1. 长沙理工大学电气与信息工程学院 长沙 410114
  • 出版日期:2025-06-16 发布日期:2025-06-12
  • 通讯作者: 胡建文(117780631@qq.com)
  • 作者简介:(1183108098@qq.com)
  • 基金资助:
    国家自然科学基金面上项目(62271087);湖南省自然科学基金(2024JJ5039,2023JJ60141);长沙市自然科学基金(kq2208403)

Ships Detection in Remote Sensing Images Based on Improved PPYOLOE-R

CHEN Tianpeng, HU Jianwen, LI Haitao   

  1. School of Electrical and Information Engineering,Changsha University of Science and Technology,Changsha 410114,China
  • Online:2025-06-16 Published:2025-06-12
  • About author:CHEN Tianpeng,born in 1996,master.His main research interests include artificial intelligence and object detection.
    HU Jianwen,born in 1985,Ph.D,postgraduate supervisor.His main research interests include artificial intelligence,computer vision and machine learning.
  • Supported by:
    National Natural Science Foundation of China(62271087),Natural Science Foundation of Hunan Provincial(2024JJ5039,2023JJ60141) and Natural Science Foundation of Changsha(kq2208403).

PDF (PC)

43

摘要： 遥感图像背景复杂,处于遥感图像中的舰船目标与港口背景语义信息较为相似,并且部分舰船目标尺寸小且密集排列,现有深度学习目标检测算法易出现漏检、误检、精度不理想等问题。针对此问题,提出一种改进PPYOLOE-R的遥感图像舰船目标检测算法,以PPYOLOE-R为基线,在颈部网络引入置换注意力机制,增强模型的特征提取能力;引入一种改进的Focal Loss,该损失可以关联类别分数与定位分数,对类别标签进行软化处理,提高模型对难易样本的区分能力。提取DOTA数据集中的舰船类别,制作DOTA_ships舰船数据集。在HRSC2016数据集和DOTA_ships舰船数据集上的实验结果表明,该方法的平均精确度分别为90.02%,89.90%,检测速度分别为48.2 FPS,41.5 FPS,召回率分别为97.9%,97.3%,平均精确度和召回率在对比方法中均为最优,检测速度仅次于PPYOLOE-R。

关键词: 遥感图像, 舰船目标检测, PPYOLOE-R, 置换注意力, Focal Loss

Abstract: The background of the remote sensing image is complex,the ships in remote sensing image are similar to the harbor background.Additionally,small and densely arranged ship objects pose challenges for existing deep learning detection algorithms,leading to issues like missed detection,incorrectdetection,and poor accuracy.This paper proposes an improved PPYOLOE-R object detection algorithm for ships in remote sensing images.In this paper,PPYOLOE-R is used as the baseline,and a shuffle attention is introduced in the neck network to enhance the feature extraction capability of the model.This paper introduces an improved Focal Loss,which can combines the category score with the localization score,softens the category labels,and improves the ability to distinguish between difficult and easy samples of model.The ship categoryin the DOTA dataset is extracted to produce the DOTA_ships dataset.Experimental results on the HRSC2016 dataset and DOTA_ships dataset show that the proposed method achieves an average precision of 90.02% and 89.90%,detection speeds of 48.2FPS and 41.5FPS,and recalls of 97.9% and 97.3%,respectively.The average precision and recall are optimal among the compared methods,and the detection speed is second to the PPYOLOE-R.

Key words: Remote sensing image, Ships detection, PPYOLOE-R, Shuffle attention, Focal Loss

中图分类号: 

  • TP391
[1]NAN X H,DING L.A Review of Typical Target Detection Algorithms for Deep Learning[J].Computer Applications Research,2020,37(S2):15-21.
[2]LIU J Q,LIU Z,ZHANG X Y.Review of Maritime Target Detection in Visible Bands of Optical Remote Sensing Images[J].Compute Science,2020,47(3):116-123.
[3]CHEN T P,HU J W.Overview of deep learning for oriented ro-tating object detection in remote sensing images[J].Computer Applications Research,2024,41(2):329-340.
[4]DING R L,LI J,ZHANG M.Ship Target Detection in Remote Sensing Image Based on S-HOG[J].Compute Science,2020,47(S2):248-252.
[5]ZOU H X,KUANG G Y,YU W X.Detection of Ship Targetsfrom SAR ImageryBased on Feature Vector Matching[J].Mo-dern Radar,2004(8):25-29.
[6]JIANG L B,WANG Z,HU W D.A ROI-based Infrared ShipTarget Detection Approach[J].Infrared Technology,2006(9):535-539.
[7]YIN Y,HUANG H,ZHANG Z X.Research on Ship Detection Technology Based on Optical Remote Sensing Image[J].Compute Science,2019,46(3):82-87.
[8]HUANG Z X,WU F L,FU Y.Review of deep learning-based algorithms forship target detection from remote sensing images[J].Optics and Precision Engineering,2023,31(15):2295-2318.
[9]ZHAO Q C,WU Y Q,YUAN Y B.Research Progress of Ship Target Detection and Recognition Methods in Optical Remote Sensing Images[J].Chinese Journal of Aeronautics,2023,31(15):2295-2318.
[10]WU W L,FANG J,WU Y.Small ship target YOLOv4detection based on improvedin complex scene[J].Transducer and Microsystem Technologies,2023,42(12):119-122.
[11]BOCHKOVSKIY A,WANG C Y,LIAO H Y M.Yolov4:Optimal speed and accuracy of object detection[J].arXiv:2004.10934,2020.
[12]ZHOU C Y.Analysis of Real time Remote Sensing Image ShipTarget Rotation Detection Algorithm for YOLOv7[J].Research and Design,2024,41(1):28-29.
[13]WANG C Y,BOCHKOVSKIY A,LIAO H Y M.YOLOv7:Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2023:7464-7475.
[14]LIU Y,SHAO Z,TENG Y,et al.NAM:Normalization-basedattention module[J].arXiv:2111.12419,2021.
[15]DING J,XUE N,LONG Y,et al.Learning roi transformer for oriented object detection in aerial images [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:2849-2858.
[16]REN S,HE K,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,2016,39(6):1137-1149.
[17]XIE X X,CHENG G,WANG J B,et al.Oriented R-CNN for object detection [C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2021:3520-3529.
[18]ZHOUG Q,HUANG L,SUN Q.Fine-grained detection method for remote sensing ship targets with improved Oriented R-CNN[J].Computer Engineering and Applications,2024,60(15):307-317.
[19]SONG Z N,LI S,YANG J M,et al.Remote sensing ship target detection based on feature and region localization enhancement[J].Computer Engineering,2023,49(8):257-264.
[20]CHE S W,WANG Y L.An Improved YOLOv7-Based Ship Target Detection Algorithm for Optical Remote Sensing Images[J].Electronics Optics & Control,2024,31(5):34-39,65.
[21]LI C,ZHOU A,YAO A.Omni-dimensional dynamic convolution[J].arXiv:2209.07947,2022.
[22]WANG X,WANG G,DANG Q,et al.PP-YOLOE-R:An efficient anchor-free rotated object detector[J].arXiv:2211.02386,2022.
[23]ZHANG Q L,YANG Y B.Sa-net:Shuffle attention for deep convolutional neural networks[C]//ICASSP 2021－2021 IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP).IEEE,2021:2235-2239.
[24]XU S,WANG X,LV W,et al.PP-YOLOE:An evolved version of YOLO[J].arXiv:2203.16250,2022.
[25]LLERENA J M,ZENI L F,KRISTEN L N,et al.Gaussian bounding boxes and probabilistic intersection-over-union for object detection[J].arXiv:2106.06072,2021.
[26]DING X,ZHANG X,MA N,et al.Repvgg:Making vgg-style convnets great again[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:13733-13742.
[27]WANG C Y,LIAO H Y M,WU Y H,et al.CSPNet:A new backbone that can enhance learning capability of CNN[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops.2020:390-391.
[28]SU S,WANG X,LV W,et al.PP-YOLOE:An evolved version of YOLO[J].arXiv:2203.16250,2022.
[29]LIN T Y,GOYAL P,GIRSHICK R,et al.Focal loss for dense object detection[C]//Proceedings of the IEEE International Conference on Computer Vision.2017:2980-2988.
[30]LI X,WANG W,WU L,et al.Generalized focal loss:Learning qualified and distributed bounding boxes for dense object detection[J].Advances in Neural Information Processing Systems,2020,33:21002-21012.
[31]LIU Z,YUAN L,WENG L,et al.A high resolution optical satellite image dataset for ship recognition and some new baselines[C]//ICPRAM.2017:324-331.
[32]XIA G S,BAI X,DING J,et al.DOTA:a large-scale dataset for object detection in aerial images [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:3974-3983.
[33]LI W,CHEN Y,HU K,et al.Oriented reppoints for aerial object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2022:1829-1838.
[34]ZHOU Y,YANG X,ZHANG G,et al.Mmrotate:A rotated object detection benchmark using pytorch[C]//Proceedings of the 30th ACM International Conference on Multimedia.2022:7331-7334.
[35]CHEN T P,HU J W.Ships Detection in Remote Sensing Images Based on Improved FCOS[J/OL].https://www.jsjkx.com/CN/article/openArticlePDF.jsp?id=22451.
[36]GAO L,GAO H,WANG Y,et al.Center-Ness and Repulsion:Constraints to Improve Remote Sensing Object Detection via RepPoints[J].Remote Sensing,2023,15(6):1479.
[37]GUO Z,LIU C,ZHANG X,et al.Beyond bounding-box:Con-vex-hull feature adaptation for oriented and densely packed object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:8792-8801.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发