融合改进密集连接和分布排序损失的遥感图像检测

doi:10.11896/jsjkx.200800001

计算机科学 ›› 2021, Vol. 48 ›› Issue (9): 168-173.doi: 10.11896/jsjkx.200800001

• 计算机图形学&多媒体 • 上一篇下一篇

融合改进密集连接和分布排序损失的遥感图像检测

袁磊¹, 刘紫燕¹, 朱明成¹, 马珊珊¹, 陈霖周廷²

1 贵州大学大数据与信息工程学院贵阳550025
2 贵州理工学院航空航天工程学院贵阳550003

收稿日期:2020-08-01 修回日期:2020-09-10 出版日期:2021-09-15 发布日期:2021-09-10
通讯作者: 刘紫燕(Leizy@sina.com)
作者简介:17508561920@163.com
基金资助:
贵州省科学技术基金资助项目(黔科合基础[2016]1054);贵州省联合资金资助项目(黔科合LH字[2017]7226);贵州大学2017年度学术新苗培养及创新探索专项(黔科合平台人才[2017]5788);贵州省科技计划项目(黔科合基础[2017]1069);贵州省教育厅创新群体重大研究项目(黔教合KY字[2018]026);贵州省普通高等学校工程研究中心(黔教合KY字[2018]007);贵州省科技计划重点项目([2019]1416)

Improved YOLOv3 Remote Sensing Target Detection Based on Improved Dense Connection and Distributional Ranking Loss

YUAN Lei¹, LIU Zi-yan¹, ZHU Ming-cheng¹, MA Shan-shan¹, CHEN Lin-zhou-ting²

1 College of Big Data and Information Engineering,Guizhou University,Guiyang 550025,China
2 School of Aerospace Engineering,Guizhou Institute of Technology,Guiyang 550003,China

Received:2020-08-01 Revised:2020-09-10 Online:2021-09-15 Published:2021-09-10
About author:YUAN Lei,born in 1995,postgraduate.His main research interests include deep learning and object detection.
LIU Zi-yan,born in 1974,associate professor,postgraduate supervisor,is a member of China Computer Federation.Her main research interests include wireless communication system,mobile robot and big data mining analysis.
Supported by:
Science and Technology Foundation of Guizhou Province,China([2016] 1054),Joint Funding Project of Guizhou Province,China([2017]7226),Special Project on the Training and Innovation of New Academic Seedlings of Guizhou University in 2017,China([2017] 5788),Science and Technology Program of Guizhou Province,China([2017] 1069),Major Research Projects on Innovative Groups of Guizhou Provincial Department of Education([2018]026),Engineering Research Center of Ordinary Colleges and Universities of Guizhou Province([2018]007) and Key Projects of Science and Technology Program of Guizhou Province([2019]1416)

摘要/Abstract

摘要： 针对遥感图像中小目标尺寸较小、样本分布不均匀、特征不明显等问题,提出一种改进的YOLOv3目标检测算法。在使用Stitcher数据增强解决小目标样本分布不均匀的问题后,提出VOVDarkNet-53基础网络,将DarkNet-53基础网络中第4次下采样后的8个残差模块减少为4个残差模块。然后采用VOVNet的密集连接方式,使网络利用更多的浅层小目标特征信息,增加网络感受野。最后,采用分布排序损失改进YOLOv3中的分类损失,解决单阶段目标检测器正负样本不平衡的问题。实验使用YOLOv3目标检测算法和改进后的YOLOv3算法在HRRSD遥感数据集上进行对比。结果表明,改进后的YOLOv3算法对小目标和中目标的检测精确度分别提升了7.2%和2.1%,尽管对大目标的检测精度下降了1%,但在平均单张图片处理时间几乎不变的情况下,平均检测精度均值(mAP)提升了4.1%,召回率和准确率也有所提升。

关键词: YOLOv3, 基础网络, 目标检测, 样本不平衡, 遥感图像

Abstract: Aiming at solving the problems of small object size,uneven sample distribution,and unclear features in remote sensing images,an improved YOLOv3 object detection algorithm is proposed.The Stitcher data enhancement method is used to solve the problem of uneven distribution of small object samples.The VOVDarkNet-53 is proposed.The residual modules of the fourth downsampling in DarkNet-53 are reduced from eight to four.And then the dense connection mode of VOVNet is adopted to extract lower features of small objects to increase the network receptive field.The distributional ranking loss is used to improve the classification loss in YOLOv3 to solve the problem of imbalance between positive and negative samples in single-stage object detector.Comparative experiments are carried out on HRRSD remote sensing datasets by using YOLOv3 object detection algorithm and improved YOLOv3 algorithm.The results demonstrate that the proposed algorithm can achieve better performance of higher detection accuracy of the improved YOLOv3 algorithm for small objects and medium objects are improved by 7.2% and 2.1%,respectively.Although the detection accuracy for large objects is reduced by 1%,the average detection accuracy (mAP) is improved by 4.1%,and the recall and accuracy are also improved.

Key words: Baseline, Object detection, Remote sensing image, Sample imbalance, YOLOv3

中图分类号:

TP391.4

袁磊, 刘紫燕, 朱明成, 马珊珊, 陈霖周廷. 融合改进密集连接和分布排序损失的遥感图像检测[J]. 计算机科学, 2021, 48(9): 168-173. https://doi.org/10.11896/jsjkx.200800001

YUAN Lei, LIU Zi-yan, ZHU Ming-cheng, MA Shan-shan, CHEN Lin-zhou-ting. Improved YOLOv3 Remote Sensing Target Detection Based on Improved Dense Connection and Distributional Ranking Loss[J]. Computer Science, 2021, 48(9): 168-173. https://doi.org/10.11896/jsjkx.200800001

参考文献

[1]HUANG G Q.Research on Satellite Image Target Detection andrecognition based on Deep Learning[D].Hangzhou:Zhejiang University,2019.
[2]PANG J,LI C,SHI J,et al.R²-CNN:Fast Tiny Object Detection in Large-Scale Remote Sensing Images[J].IEEE Transactions on Geoscience and Remote Sensing,2019,57(8):5512-5524.
[3]SHERMEYER J,VAN ETTEN A.The Effects of Super-Resolution on Object Detection Performance in Satellite Imagery[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.2019:1432-1441.
[4]RUSSAKOVSKY O,DENG J,SU H,et al.ImageNet LargeScale Visual Recognition Challenge[J].International Journal of Computer Vision,2015,115(3):211-252.
[5]EVERINGHAM M,GOOL L V,WILLIAMS C K I,et al.The Pascal Visual Object Classes (VOC) Challenge[J].International Journal of Computer Vision,2010,88(2):303-338.
[6]LIN T,MAIRE M,BELONGIE S,et al.Microsoft COCO:Common Objects in Context[C]//European Conference on Compu-ter Vision.2014:740-755.
[7]LIU Y,WANG Y,WANG S,et al.CBNet:A Novel Composite Backbone Network Architecture for Object Detection[C]//National Conference on Artificial Intelligence.2020.
[8]TAN M,PANG R,LE Q V,et al.EfficientDet:Scalable and Efficient Object Detection[EB/OL].(2019-11-09) [2020-08-01].https://arxiv.org/abs/1911.09070.pdf.
[9]SONG G,LIU Y,WANG X,et al.Revisiting the Sibling Head in Object Detector[EB/OL].(2020-03-07) [2020-08-01].https://arxiv.org/abs/2003.07540.pdf.
[10]GHIASI G,TAN M,JIN P,et al.SpineNet:Learning Scale-Permuted Backbone for Recognition and Localization[EB/OL].(2019-12-05)[2020-08-01].https://arxiv.org/abs/1912.05027.
[11]LIN T,GOYAL P,GIRSHICK R,et al.Focal Loss for DenseObject Detection[C]//International Conference on Computer Vision.2017:2999-3007.
[12]REDMON J,FARHADI A.YOLOv3:An Incremental Improvement[EB/OL].(2018-04-08) [2020-07-01].https://arxiv.org/abs/1804.02767.
[13]TIAN Z,SHEN C,CHEN H,et al.FCOS:Fully Convolutional One-Stage Object Detection[C]//International Conference on Computer Vision.2019:9627-9636.
[14]LAW H,DENG J.CornerNet:Detecting Objects as Paired Keypoints[C]//European Conference on Computer Vision.2018:765-781.
[15]ZHU W T,XIE B R,WANG M,et al.A review of aircraft target detection in optical remote sensing images[J].Computer Scien-ce,2020,47(S2):165-171.
[16]BELL S,ZITNICK C L,BALA K,et al.Inside-Outside Net:Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks[C]//Computer Vision and Pattern Recognition.2016:2874-2883.
[17]ZHANG M,LI J,DING R L,et al.Research on remote sensing image target detection technology based on improved YOLO-V2 algorithm[J].Computer Science,2020,547 (S1):176-180.
[18]LONG Y,GONG Y,XIAO Z,et al.Accurate Object Localization in Remote Sensing Images Based on Convolutional Neural Networks[J].IEEE Transactions on Geoscience & RemoteSen-sing,2017,55(5):2486-2498.
[19]CHEN Y,ZHANG P,LI Z,et al.Stitcher:Feedback-driven Data Provider for Object Detection[EB/OL].(2020-04-12) [2020-08-01].https://arxiv.org/abs/2004.12432.
[20]LEE Y,PARK J.CenterMask:Real-Time Anchor-Free Instance Segmentation[EB/OL].(2019-11-06) [2020-08-01].https://arxiv.org/abs/1911.06667.pdf.
[21]QIAN Q,CHEN L,LI H,et al.DR Loss:Improving Object Detection by Distributional Ranking[EB/OL].(2019-07-10) [2020-08-01].https://arxiv.org/abs/1907.10156.

相关文章 15

[1]	王坤姝, 张泽辉, 高铁杠. 基于Hachimoji DNA和QR分解的遥感图像可逆隐藏算法 Reversible Hidden Algorithm for Remote Sensing Images Based on Hachimoji DNA and QR Decomposition 计算机科学, 2022, 49(8): 127-135. https://doi.org/10.11896/jsjkx.210700216
[2]	刘冬梅, 徐洋, 吴泽彬, 刘倩, 宋斌, 韦志辉. 基于边框距离度量的增量目标检测方法 Incremental Object Detection Method Based on Border Distance Measurement 计算机科学, 2022, 49(8): 136-142. https://doi.org/10.11896/jsjkx.220100132
[3]	王灿, 刘永坚, 解庆, 马艳春. 基于软标签和样本权重优化的Anchor Free目标检测算法 Anchor Free Object Detection Algorithm Based on Soft Label and Sample Weight Optimization 计算机科学, 2022, 49(8): 157-164. https://doi.org/10.11896/jsjkx.210600240
[4]	郝强, 李杰, 张曼, 王路. 基于改进YOLOv3的空间非合作目标部件识别算法 Spatial Non-cooperative Target Components Recognition Algorithm Based on Improved YOLOv3 计算机科学, 2022, 49(6A): 358-362. https://doi.org/10.11896/jsjkx.210700048
[5]	祝文韬, 兰先超, 罗唤霖, 岳彬, 汪洋. 改进Faster R-CNN的光学遥感飞机目标检测 Remote Sensing Aircraft Target Detection Based on Improved Faster R-CNN 计算机科学, 2022, 49(6A): 378-383. https://doi.org/10.11896/jsjkx.210300121
[6]	马宾, 付永康, 王春鹏, 李健, 王玉立. 基于GDIoU损失函数的YOLOv4绝缘子高效定位算法 High Performance Insulators Location Scheme Based on YOLOv4 with GDIoU Loss Function 计算机科学, 2022, 49(6A): 412-417. https://doi.org/10.11896/jsjkx.210600089
[7]	陈永平, 朱建清, 谢懿, 吴含笑, 曾焕强. 基于外接圆半径差损失的实时安全帽检测算法 Real-time Helmet Detection Algorithm Based on Circumcircle Radius Difference Loss 计算机科学, 2022, 49(6A): 424-428. https://doi.org/10.11896/jsjkx.220100252
[8]	陈佳舟, 赵熠波, 徐阳辉, 马骥, 金灵枫, 秦绪佳. 三维城市场景中的小物体检测 Small Object Detection in 3D Urban Scenes 计算机科学, 2022, 49(6): 238-244. https://doi.org/10.11896/jsjkx.210400174
[9]	胡伏原, 万新军, 沈鸣飞, 徐江浪, 姚睿, 陶重犇. 深度卷积神经网络图像实例分割方法研究进展 Survey Progress on Image Instance Segmentation Methods of Deep Convolutional Neural Network 计算机科学, 2022, 49(5): 10-24. https://doi.org/10.11896/jsjkx.210200038
[10]	徐涛, 陈奕仁, 吕宗磊. 基于改进YOLOv3的机坪工作人员反光背心检测研究 Study on Reflective Vest Detection for Apron Workers Based on Improved YOLOv3 Algorithm 计算机科学, 2022, 49(4): 239-246. https://doi.org/10.11896/jsjkx.210200119
[11]	张侣, 周博文, 吴亮红. 基于改进卷积注意力模块与残差结构的SSD网络 SSD Network Based on Improved Convolutional Attention Module and Residual Structure 计算机科学, 2022, 49(3): 211-217. https://doi.org/10.11896/jsjkx.201200019
[12]	陈贵强, 何军. 自然场景下遥感图像超分辨率重建算法研究 Study on Super-resolution Reconstruction Algorithm of Remote Sensing Images in Natural Scene 计算机科学, 2022, 49(2): 116-122. https://doi.org/10.11896/jsjkx.210700095
[13]	赫晓慧, 邱芳冰, 程淅杰, 田智慧, 周广胜. 基于边缘特征融合的高分影像建筑物目标检测 High-resolution Image Building Target Detection Based on Edge Feature Fusion 计算机科学, 2021, 48(9): 140-145. https://doi.org/10.11896/jsjkx.200800002
[14]	龚浩田, 张萌. 基于关键点检测的无锚框轻量级目标检测算法 Lightweight Anchor-free Object Detection Algorithm Based on Keypoint Detection 计算机科学, 2021, 48(8): 106-110. https://doi.org/10.11896/jsjkx.200700161
[15]	李琳, 刘学亮, 赵烨, 纪平. 结合乐高滤波器和SSD的低光照图像融合检测方法 Low Light Image Fusion Detection Method Based on Lego Filter and SSD 计算机科学, 2021, 48(7): 213-218. https://doi.org/10.11896/jsjkx.200800127

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

融合改进密集连接和分布排序损失的遥感图像检测

Improved YOLOv3 Remote Sensing Target Detection Based on Improved Dense Connection and Distributional Ranking Loss

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0