面向遥感图像小目标检测的改进YOLOv3算法

doi:10.3778/j.issn.1002-8331.2012-0064

摘要/Abstract

摘要：

针对YOLOv3目标检测算法在遥感图像小目标检测方面精度较低的缺点，提出了一种改进的YOLOv3目标检测算法——YOLOv3-CS。根据对backbone中不同尺度特征重要性的分析重构了backbone，即增加具有丰富位置信息的浅层特征对应的卷积层深度，以此增强backbone对小目标特征的提取能力，引入RFB结构增大浅层特征图的感受野来提升小目标检测精度，优化了anchor boxes及其分配原则。在RSOD数据集的实验结果表明，YOLOv3-CS算法与YOLOv3相比，mAP提高6.49%，F1提高4.85%，所需存储空间降低12.58%，其中backbone的改进和RFB的引入对小目标检测的精度提升较为明显，说明提出的目标检测算法在遥感图像小目标检测方面有较高的优势。

关键词: 小目标检测, YOLOv3, 遥感图像

Abstract:

Aiming at low accuracy of the YOLOv3 object detection model in small object detection, an improved YOLOv3 object detection model-YOLOv3-CS is proposed. Firstly, based on analyzing the importance of different scale features in the backbone network, the backbone network is reconstructed, that is to increase the depth of convolutional layer corresponding to the shallow feature with rich location information and improve the ability of small target feature extraction in the backbone network. Secondly, the RFB structure is introduced to increase the sensing field of shallow feature maps for improving the detection accuracy of small objects. Finally, the anchor boxes and their allocation principles are optimized. Experimental results on RSOD-dataset show that the YOLOv3-CS model can increase map by 6.49%, F1 by 4.85%, and model size by 12.58% in comparison with YOLOv3. Among them, the reconstruction of backbone and the introduction of RFB can improve the accuracy of small target detection obviously, which shows that the proposed target detection algorithm has higher advantages in the detection of small targets in remote sensing images.

Key words: small object detection, YOLOv3, remote sensing images

王建军，魏江，梅少辉，王健. 面向遥感图像小目标检测的改进YOLOv3算法[J]. 计算机工程与应用, 2021, 57(20): 133-141.

WANG Jianjun, WEI Jiang, MEI Shaohui, WANG Jian. Improved YOLOv3 for Small Object Detection in Remote Sensing Images[J]. Computer Engineering and Applications, 2021, 57(20): 133-141.

参考文献

[1] KRIZHEVSKY A，SUTSKEVER I，HINTON G E.ImageNet classification with deep convolutional neural networks[C]//Proceedings of NIPS，2012：1097-1105.
[2] 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，2016：779-788.
[3] REDMON J，FARHADI A.YOLO9000：better，faster，stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：7263-7271.
[4] REDMON J，FARHADI A.Yolov3：an incremental improvement[J].arXiv：1804.02767，2018.
[5] BOCHKOVSKIY A，WANG C Y，LIAO H Y M.YOLOv4：optimal speed and accuracy of object detection[J].arXiv：2004.10934，2020.
[6] LIU W，ANGUELOV D，ERHAN D，et al.SSD：single shot multibox detector[C]//European Conference on Computer Vision.Cham：Springer，2016：21-37.
[7] 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.
[8] GIRSHICK R，DONAHUE J，DARRELL T，et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2014：580-587.
[9] GIRSHICK R.Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision，2015：1440-1448.
[10] REN S，HE K，GIRSHICK R，et al.Faster R-CNN：towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems，2015：91-99.
[11] HE K，GKIOXARI G，DOLLáR P，et al.Mask R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision，2017：2961-2969.
[12] LIN T Y，DOLLáR P，GIRSHICK R，et al.Feature pyramid networks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：2117-2125.
[13] LI J，LIANG X，WEI Y，et al.Perceptual generative adversarial networks for small object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：1222-1230.
[14] KISANTAL M，WOJNA Z，MURAWSKI J，et al.Augmentation for small object detection[J].arXiv：1902.07296，2019.
[15] LIU S，HUANG D.Receptive field block net for accurate and fast object detection[C]//Proceedings of the European Conference on Computer Vision（ECCV），2018：385-400.
[16] YU F，KOLTUN V.Multi-scale context aggregation by dilated convolutions[J].arXiv：1511.07122，2015.
[17] HE K，ZHANG X，REN S，et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016：770-778.
[18] HE Y，LIU P，WANG Z，et al.Filter pruning via geometric median for deep convolutional neural networks acceleration[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2019：4340-4349.
[19] SZEGEDY C，LIU W，JIA Y，et al.Going deeper with convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2015：1-9.
[20] 魏玮，蒲玮，刘依.改进YOLOv3在航拍目标检测中的应用[J].计算机工程与应用，2020，56（7）：17-23.
WEI Wei，PU Wei，LIU Yi.Application of improved YOLOv3 in aerial target detection[J].Computer Engineering and Applications，2020，56（7）：17-23.
[21] 唐志刚.基于YOLO V3的航拍车辆图像检测方法研究[D].赣州：江西理工大学，2020.
TANG Zhigang.Research on image detection method of aerial vehicle based on YOLO V3[D].Ganzhou：Jiangxi University of Science and Technology，2020.
[22] 吴锦涛.基于深度学习的图像小目标检测方法研究[D].成都：电子科技大学，2020.
WU Jintao.Research on image small target detection method based on deep learning[D].Chengdu：University of Electronic Science and Technology of China，2020.
[23] 张富凯，杨峰，李策.基于改进YOLOv3的快速车辆检测方法[J].计算机工程与应用，2019，55（2）：12-20.
ZHANG Fukai，YANG Feng，LI Ce.Fast vehicle detection method based on improved YOLOv3[J].Computer Engineering and Applications，2019，55（2）：12-20.