| 237 | 0 | 21 |
| 下载次数 | 被引频次 | 阅读次数 |
针对遥感图像目标检测中存在图像分辨率低、小目标特征信息不足以及检测难度大等问题，提出一种基于改进YOLO11的遥感图像目标检测算法SO-YOLO。首先，设计一个新的卷积神经网络(CNN)构建块SDOD-Conv,由空间到深度转换层和全维动态卷积组成，代替主干网络中的跨步卷积和池化层，加强特征提取，在特征提取过程中避免细粒度信息损失；其次，在颈部网络中引入空间和通道重建卷积(SCConv),压缩特征之间的空间和通道冗余，减少冗余计算并促进代表性特征学习；最后，采用Inner-IoU损失函数作为回归损失，通过引入比例因子的辅助边界框计算IoU损失，获得更快、更准确的回归结果。在HRSC2016数据集和DOTA数据集上的实验结果表明，相较于YOLO11,改进后算法的平均精度均值分别提高了2.3%和2.0%,表明改进算法具有良好的检测性能。
Abstract：To solve the problems of low image resolution and insufficient feature information of small targets and difficulty of target detection in remote sensing image, a remote sensing image detection method based on SO-YOLO is proposed on the basis of YOLO11 model.First, a new convolutional neural network(CNN)building block SDOD-Conv is designed, which consists of a space-to-depth layer and a full-dimensional dynamic convolution, replacing each stride convolution layer and pooling layer in the backbone network, to enhance the feature extraction and avoid the loss of fine-grained information during the feature extraction process.Second, Introducing Spatial and Channel Reconstruction Convolution(SCConv)into the neck network to compress spatial and channel redundancies in features, redundant computation is reduced and discriminative feature learning is enhanced.Finally, the Inner-IoU loss function is used as the regression loss, and the IoU loss is computed by introducing an auxiliary bounding box for the scale factor to obtain faster and more efficient regression results.The improved algorithm is verified on the HRSC2016 data set and DOTA data set, which are improved by 2.1% and 1.5% respectively, compared to the average accuracy of YOLO11,and demonstrates good detection performance.
[1] 侯林静，李芳.基于改进EAF-YOLO的轻量化遥感图像检测[J].沈阳理工大学学报，2025,44(2):7-12.HOU L J,LI F.J.Improved EAF-YOLO for lightweight detection of remote sensing images[J].Journal of Shen yang Ligong University,2025,44(2):7-12.(in Chinese)
[2] 曾祥津，刘耿焕，陈建明，等.基于多尺度分层残差网络的光学遥感图像微小目标检测[J].光子学报，2024,53(8):254-266.ZENG X J,LIU G H,CHEN J M,et al.A multi-scale hierarchical residual network-based method for tiny object detection in optical remote sensing images[J].Acta Photonica Sinica,2024,53(8):254-266.(in Chinese)
[3] CARION N,MASSA F,SYNNAEVE G,et al.End-to-end object detection with transformers[C]//European Conference on Computer Vision.Cham,Germany:Springer International Publishing,2020:213-229.
[4] GIRSHICK R.Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision.Seoul,Korea:IEEE,2015:1440-1448.
[5] REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:unified,real-time object detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Seattle,WA,USA:IEEE,2016:779-788.
[6] 郑文轩，谭忠，杨瑛.光学遥感图像目标检测的CNN-Transformer多尺度融合算法[J/OL].计算机工程与应用，1-15[2025-04-3].http://kns.cnki.net/kcms/detail/11.2127.tp.20250414.1454.015.html.Zheng W X,TAN Z,YANG Y.CNN-Transformer multi-scale fusion algorithm for optical remote sensing images object detection[J/OL].Computer Engineering and Applications,1-15[2025-04-3].http://kns.cnki.net/kc ms/detail/11.2127.tp.20250414.1454.015.html.(in Chinese)
[7] 王杨，范祥祥，于得水，等.基于金字塔视觉Transformer的遥感图像显著性目标检测[J].安徽科技学院学报，2025,39(2):49-58.WANG Y,FAN X X,YU D S,et al.Salient object detection in remote sensing images based on pyramid vision Transformer[J].Journal of Anhui Science and Technology Unive rsity,2025,39(2):49-58.(in Chinese)
[8] 沈涛，张秀再，许岱.改进RT-DETR的遥感图像小目标检测算法[J/OL].计算机科学，2025:1-13[2025-03-27].http:// kns.cnki.net/kcms/detail/50.1075.tp.20250307.0953.002.html.SHEN T,ZHANG X Z,XU D.Improved RT-DETR algor ithm for small object detection in remote sensing images[J/OL].Computer Science,2025:1-13[2025-03-27].http://kns.cnki.net/kcms/detail/50.1075.tp.20250307.0953.002.html.(in Chinese)
[9] 吕周澍.基于改进YOLOv8算法的遥感影像小目标精准识别研究[J].兰州石化职业技术大学学报，2025,25(1):43-47.LV Z S.Remote sensing images with improved YOLOv8 algorithm for small targets accurate recognition [J].Journal of Lanzhou Petrochemical University of Vocational Technology,2025,25(1):43-47.(in Chinese)
[10] 陈谢发，李敏，赵晶钰，等.基于双层注意力机制的遥感小目标检测算法[J].火箭军工程大学学报，2025,39(1):60-66.CHEN X F,LI M,ZHAO J Y,et al.Remote sensing small object detection algorithm based on dual-layer attention mechanism[J].Journal of Rocket Force University of Engineering,2025,39(1):60-66.(in Chinese)
[11] 帖军，秦锦添，郑禄，等.融合感受野扩增与特征增强的遥感小目标检测[J].激光杂志，2024,45(12):81-91.TIE J,QIN J T,ZHENG L,et al.Remote sensing small target detection integrating receptive field amplification and feature enhancement[J].Laser Journal,2024,45(12):81-91.(in Chinese)
[12] SU N,HUANG Z B,YAN Y M,et al.Detect larger at once:large-area remote-sensing image arbitrary-oriented ship detection[J].IEEE Geoscience and Remote Sensing Letters,2022,19:1-5.
[13] 陶健.基于空洞卷积与空间注意力的遥感影像小目标检测方法[J].测绘与空间地理信息，2024,47(10):104-107,111.TAO J.Small target detection method in remote sensing images based on atrous convolution and spatial attention[J].Geomatics & Spatial Information Technology,2024,47(10):104-107,111.(in Chinese)
[14] WANG J W,DING J,GUO H W,et al.Mask OBB:a semantic attention-based mask oriented bounding box representation for multi-category object detection in aerial images[J].Remote Sensing,2019,11(24):2930.
[15] SUNKARA R,LUO T.No more strided convolutions or pooling:a new CNN building block for low-resolution images and small objects[M]//Machine Learning and Knowledge Discovery in Databases.Cham,Switzerland:Springer Nature,2023:443-459.
[16] ZHAO Z,DONG M.Channel-spatial dynamic convolution:an exquisite omni-dimensional dynamic convolution[C]//2023 8th International Conference on Intelligent Computing and Signal Processing(ICSP).Beijing,China:IEEE,2023:1707-1711.
[17] 夏淑芳，尹昊楠，瞿中.ETF-YOLO11n:交通图像的多尺度特征融合目标检测方法[J/OL].计算机科学，2025:1-10[2025-04-07].http://kns.cnki.net/kcms/detail/50.1075.tp.20250331.1410.032.html.XIA S F,YIN H N,QU Z.ETF-YOLO11n:An object detection method based on multi-scale feature fusion for traffic images[J/OL].Computer Science,2025:1-10[2025-04-07].http://kns.cnki.net/kcms/detail/50.1075.tp.2025-0331.1410.032.html.(in Chinese)
[18] LIU Z K,WANG H Z,WENG L B,et al.Ship rotated bounding box space for ship extraction from high-resolution optical satellite images with complex backgrounds[J].IEEE Geoscience and Remote Sensing Letters,2016,13(8):1074-1078.
[19] 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.Salt Lake City,UT,USA:IEEE,2018:3974-3983.
[20] HAN J M,DING J,LI J,et al.Align deep features for oriented object detection[J].IEEE Transactions on Geoscience and Remote Sensing.2021,60:5602511.
[21] XIE 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.Seoul,Korea:IEEE,2021:3520-3529.
[22] 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.Long Beach,CA,USA:IEEE,2019:2844-2853.
基本信息:
中图分类号:TP751
引用信息:
[1]王佳,李芳.基于SO-YOLO的遥感图像目标检测算法[J].沈阳理工大学学报,2026,45(02):47-52+60.
基金信息:
国家自然科学基金项目(62102272)