改进YOLOv3模型的GF-2卫星影像车辆检测Vehicle detection in GF-2 satellite images based on improved YOLOv3 model
彭新月,张吴明,钟若飞
摘要(Abstract)：
针对卫星影像上车辆的漏检问题,该文对深度学习YOLOv3模型进行了网络改进,并用于高分二号卫星影像车辆检测。该方法通过减少原特征提取网络darknet-53的层数来降低网络复杂度,并在原YOLOv3模型3个尺度的基础上进行了尺度扩充以提高对小目标的检测能力。实验结果表明,改进后的YOLOv3模型较好地克服了多数深度学习算法不擅长检测小目标的短板,不仅检测结果比原算法更为精确,而且训练和检测速度也更快,具有一定的优势。
关键词(KeyWords)： 高分二号卫星;遥感图像;YOLOv3;车辆检测;深度学习
基金项目(Foundation): 国家自然科学基金面上项目(41971380,41671414,42071444);; 广西自然科学基金—创新研究团队项目(2019GXNSFGA245001);; 遥感科学国家重点实验室开放基金项目(OFSLRSS201920)
作者(Author): 彭新月,张吴明,钟若飞
DOI: 10.16251/j.cnki.1009-2307.2021.12.020
参考文献(References)：
- [1] 刘亚萍，姚剑.基于Edge Boxes和深度学习的车辆检测[J].黑龙江科技信息，2016(1):102.(LIU Yaping,YAO Jian.Detection based on Edge Boxes and deep learning[J].Heilongjiang Science and Technology Information,2016(1):102.)
- [2] 杨映波，周欣，曾珍，等.基于卷积神经网络预处理的Hog特征车辆检测算法[J].现代计算机(专业版),2018(36):58-62.(YANG Yingbo,ZHOU Xin,ZENG Zhen,et al.Vehicle detection algorithm based on convolutional neural network preprocessing and histogram of oriented gradient[J].Modern Computer,2018(36):58-62.)
- [3] 黄国捷.基于深度学习的遥感图像车辆目标检测[D].苏州：苏州大学，2019.(HUANG Guojie.Vehicle detection from remote sensing images based on deep learning[D].Suzhou:Soochow University,2019.)
- [4] 刘玮，王新梅，魏龙生.整体视觉结构模型及其在道路环境感知中的应用[J].计算机工程，2016,42(10):26-31.(LIU Wei,WANG Xinmei,WEI Longsheng.Overall visual structure model and its application in road environment perception[J].Computer Engineering,2016,42(10):26-31.)
- [5] 龚静，曹立，亓琳，等.基于YOLOv2算法的运动车辆目标检测方法研究[J].电子科技，2018,31(6):5-8.(GONG Jing,CAO Li,QI Lin,et al.Moving vehicle target detection based on YOLOv2 algorithm[J].Electronic Science and Technology,2018,31(6):5-8.)
- [6] 孙秉义，文珊珊，吴昊，等.基于深度学习的高分辨率遥感图像车辆检测[J].东华大学学报(自然科学版),2018,44(4):520-525.(SUN Bingyi,WEN Shanshan,WU Hao,et al.Vehicle detection in high-resolution remote sensing images based on deep learning[J].Journal of Donghua University(Natural Science),2018,44(4):520-525.)
- [7] 姚慧丹.高分辨率遥感影像车辆检测方法研究[D].株洲：湖南工业大学，2015.(YAO Huidan.Research on vehicle detection from high resolution remote sensing image[D].Zhuzhou:Hunan University of Technology,2015.)
- [8] EIKVIL L,AURDAL L,KOREN H.Classification-based vehicle detection in high-resolution satellite images[J].ISPRS Journal of Photogrammetry and Remote Sensing,2009,64(1):65-72.
- [9] LIANG P P,TEODORO G,LING H B,et al.Multiple kernel learning for vehicle detection in wide area motion imagery[C]//The 15th International Conference on Information Fusion.[S.l.]:IEEE,2012:1629-1636.
- [10] LIU W,YAMAZAKI F,VU T T.Automated vehicle extraction and speed determination from QuickBird satellite images[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2011,4(1):75-82.
- [11] SUN H,SUN X,WANG H Q,et al.Automatic target detection in high-resolution remote sensing images using spatial sparse coding bag-of-words model[J].IEEE Geoscience and Remote Sensing Letters,2012,9(1):109-113.
- [12] LECUN Y,BENGIO Y,HINTON G.Deep learning[J].Nature,2015,521(7553):436-444.
- [13] 王金传，谭喜成，王召海，等.基于Faster R-CNN深度网络的遥感影像目标识别方法研究[J].地球信息科学学报，2018,20(10):1500-1508.(WANG Jinchuan,TAN Xicheng,WANG Zhaohai,et al.Faster R-CNN deep learning network based object recognition of remote sensing image[J].Journal of Geo-information Science,2018,20(10):1500-1508.)
- [14] 付伟锋，邹维宝.深度学习在遥感影像分类中的研究进展[J].计算机应用研究，2018,35(12):3521-3525.(FU Weifeng,ZOU Weibao.Review of remote sensing image classification based on deep learning[J].Application Research of Computers,2018,35(12):3521-3525.)
- [15] 李欣，韦宏卫，张洪群.结合深度学习的单幅遥感图像超分辨率重建[J].中国图象图形学报，2018,23(2):209-218.(LI Xin,WEI Hongwei,ZHANG Hongqun.Super-resolution reconstruction of single remote sensing image combined with deep learning[J].Journal of Image and Graphics,2018,23(2):209-218.)
- [16] 付发，未建英，张丽娜.基于卷积网络的遥感图像建筑物提取技术研究[J].软件工程，2018,21(6):4-7.(FU Fa,WEI Jianying,ZHANG Lina.A study of building extraction from remote sensing imagery based on convolution network[J].Software Engineering,2018,21(6):4-7.)
- [17] GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition.[S.l.]:IEEE,2014:580-587.
- [18] GIRSHICK R.Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision (ICCV).[S.l.]:IEEE,2015.
- [19] REN S Q,HE K M,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.
- [20] REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:unified,real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).[S.l.]:IEEE,2016:779-788.
- [21] REDMON J,FARHADI A.YOLO9000:better,faster,stronger[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).[S.l.]:IEEE,2017:6517-6525.
- [22] REDMON J,FARHADI A.YOLOv3:an incremental improvement[J/OL].[2021-02-08].https://pjreddie.com/media/files/papers/YOLOv3.pdf.
- [23] 梁鸿，王庆玮，张千，等.小目标检测技术研究综述[J].计算机工程与应用，2021,57(1):17-28.(LIANG Hong,WANG Qingwei,ZHANG Qian,et al.Small object detection technology:a review[J].Computer Engineering and Applications,2021,57(1):17-28.)
- [24] LIU W,ANGUELOV D,ERHAN D,et al.SSD:single shot Multibox detector[C]//Proceedings of the 2016 European Conference on Computer Vision.Cham:Springer,2016:21-37.
- [25] 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.[S.l.]:IEEE,2017.