基于全卷积网络的高分辨遥感影像目标检测

doi:10.13474/j.cnki.11-2246.2018.0014

测绘通报 ›› 2018, Vol. 0 ›› Issue (1): 77-82.doi: 10.13474/j.cnki.11-2246.2018.0014

基于全卷积网络的高分辨遥感影像目标检测

徐逸之^1,2, 姚晓婧¹, 李祥^1,2, 周楠³, 胡媛^1,2

1. 中国科学院遥感与数字地球研究所, 北京 100094;
2. 中国科学院大学, 北京 100049;
3. 苏州中科天启遥感科技有限公司, 江苏苏州 215163

收稿日期:2017-04-05 出版日期:2018-01-25 发布日期:2018-02-05
通讯作者: 李祥。E-mail:lixiang01@radi.ac.cn E-mail:lixiang01@radi.ac.cn
作者简介:徐逸之(1993-),男,硕士生,研究方向为地理信息系统研究与应用、数据挖掘。E-mail:sysu_xuyizhi@163.com
基金资助:
江苏省测绘地理信息科研项目（JSCHKY201720）；国家自然科学基金（41701438）；科技基金性工作专项重点项目（2014FY210800）

Object Detection in High Resolution Remote Sensing Images Based on Fully Convolution Networks

XU Yizhi^1,2, YAO Xiaojing¹, LI Xiang^1,2, ZHOU Nan³, HU Yuan^1,2

1. Institute of Remote Sensing and Digital Earth, CAS, Beijing 100094, China;
2. University of Chinese Academy of Sciences, Beijing 100049, China;
3. Imagesky Remote Sensing Technology Co. Ltd., Suzhou 215163, China

Received:2017-04-05 Online:2018-01-25 Published:2018-02-05

摘要/Abstract

摘要：

目标检测是遥感图像分析处理中的研究热点之一，具有十分重要的科研和应用价值。传统遥感影像目标检测方法多使用人工构造的浅层次特征，结合支持向量机、随机森林、Adaboost等分类器进行目标识别，难以充分挖掘和利用影像中的深层特征。近年来，深度学习，特别是卷积神经网络在图像认知方面取得了巨大成功。在目标检测领域，以Faster R-CNN算法为代表的方法取得了突破性进展，检测精度大幅提高，检测速度达到了近实时的性能。但是，Faster R-CNN算法由于使用了感兴趣区域（RoI）池化层，各个RoI计算不共享，因此检测速度依然有待提高。R-FCN基于全卷积网络结构，同时采用位置敏感池化来引入平移变化，抵消全卷积网络造成的平移不变形问题，检测精度和效率都有了很大的提高。本文阐述了R-FCN算法原理，并运用于高分辨遥感影像目标检测分析了不同参数和网络结构对R-FCN检测效果的影响，比较了利用Fast R-CNN、Faster R-CNN和R-FCN 3种算法进行飞机识别的性能。试验结果表明，利用R-FCN进行飞机识别定位可以达到99.3%的准确率和每张图180 ms的检测速度。

关键词: 高分辨率遥感, 深度学习, 全卷积网络, R-FCN, 飞机检测

Abstract:

Object detection is one of the research hotspots in remote sensing image analysis and processing,and has very important research and application value.Traditional remote sensing image target detection method uses the shallow artificial feature,and combines with classifiers,such as support vector machine,random forest and Adaboost,to realize object detection task.In recent years,deep learning,especially convolution neural network (CNN),has achieved great success in image recognition.In the field of target detection,the Faster R-CNN algorithm has made a breakthrough,the detection accuracy has been greatly improved,and the detection procedure has achieved nearly real-time performance.However,the Faster R-CNN algorithm uses RoI (region of interests) pooling layer,the RoI-wise calculation is not shared,so the detection speed is still unsatisfying.R-FCN,however,is based on the fully convolution network structure,and the position-sensitive pool is used to tackle the translation variance problem,which is concealed by the convolution neural network,thus lead to performance improvement.In this paper,the principle of R-FCN is described and applied to the detection of high-resolution remote sensing images.Different parameters and network structure are analyzed to find the best configuration.The performance of three popular algorithms,including Fast R-CNN,Faster R-CNN and R-FCN are compared.Experimental results show that R-FCN can achieve 99.3% precision and achieve at a test-time speed of 180 ms per image.

Key words: high resolution remote sensing, deep learning, fully convolution networks, R-FCN, aircraft detection

中图分类号:

P237

徐逸之, 姚晓婧, 李祥, 周楠, 胡媛. 基于全卷积网络的高分辨遥感影像目标检测[J]. 测绘通报, 2018, 0(1): 77-82.

XU Yizhi, YAO Xiaojing, LI Xiang, ZHOU Nan, HU Yuan. Object Detection in High Resolution Remote Sensing Images Based on Fully Convolution Networks[J]. 测绘通报, 2018, 0(1): 77-82.

参考文献

[1] 刘扬,付征叶,郑逢斌.高分辨率遥感影像目标分类与识别研究进展[J].地球信息科学学报,2015,17(9):1080-1091.
[2] DALAL N,TRIGGS B.Histograms of Oriented Gradients for Human Detection[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR'05).[S.l.]:IEEE,2005.
[3] LOWE D G.Object Recognition from Local Scale-invariant Features[C]//Proceedings of the 7th IEEE International Conference on Computer Vision.Kerkyra:IEEE,1999.
[4] LOWE D G.Distinctive Image Features from Scale-invariant Keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[5] HINTON G E,SALAKHUTDINOV R R.Reducing the Dimensionality of Data with Neural Networks[J].Science,2006,313(5786):504-507.
[6] COLLOBERT R,WESTON J.A Unified Architecture for Natural Language Processing:Deep Neural Networks with Multitask Learning[C]//Proceedings of the 25th International Conference on Machine Learning.Helsinki:ACM,2008.
[7] BENGIO Y.Learning Deep Architectures for AI[J].Foundations and Trends in Machine Learning,2009,2(1):1-127.
[8] MOHAMED A,SAINATH T N,DAHL G,et al.Deep Belief Networks Using Discriminative Features for Phone Recognition[C]//IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP).Pragve:IEEE,2011.
[9] CHAN T,JIA K,GAO S,et al.PCANet:A Simple Deep Learning Baseline for Image Classification?[J].IEEE Transactions on Image Processing,2015,24(12):5017-5032.
[10] KAVUKCUOGLU K,RANZATO M,LECUN Y.Fast Inference in Sparse Coding Algorithms with Applications to Object Recognition[C]//Proceedings of OPT 2008.[S.l.]:[s.n.],2008.
[11] SILVER D,HUANG A,MADDISON C J,et al.Mastering the Game of Go with Deep Neural Networks and Tree Search[J].Nature,2016,529(7587):484-489.
[12] ZHANG F,DU B,ZHANG L.Scene Classification via a Gradient Boosting Random Convolutional Network Framework[J].IEEE Transactions on Geoscience and Remote Sensing,2016,54(3):1793-1802.
[13] HU W,HUANG Y,WEI L,et al.Deep Convolutional Neural Networks for Hyperspectral Image Classification[J].Journal of Sensors,2015(2015):1-12.
[14] MA X,GENG J,WANG H.Hyperspectral Image Classification via Contextual Deep Learning[J].EURASIP Journal on Image and Video Processing,2015.https://doi.org/10.1186/s13640-015-0071-8.
[15] CHEN X,XIANG S,LIU C,et al.Aircraft Detection by Deep Belief Nets[C]//20132nd IAPR Asian Conference on Pattern Recognition(ACPR 2013).Naha:IEEE,2013:54-58.
[16] CHEN X,XIANG S,LIU C,et al.Vehicle Detection in Satellite Images by Hybrid Deep Convolutional Neural Networks[J].IEEE Geoscience and Remote Sensing Letters,2014,11(10):1797-1801.
[17] DIAO W,SUN X,DOU F,et al.Object Recognition in Remote Sensing Images Using Sparse Deep Belief Networks[J].Remote Sensing Letters,2015,6(10):745-754.
[18] HAN J,ZHANG D,CHENG G,et al.Object Detection in Optical Remote Sensing Images Based on Weakly Supervised Learning and High-level Feature Learning[J].IEEE Transactions on Geoscience and Remote Sensing,2015,53(6):3325-3337.
[19] 高常鑫,桑农.基于深度学习的高分辨率遥感影像目标检测[J].测绘通报,2014(S1):108-111.
[20] 王万国,田兵,刘越,等.基于RCNN的无人机巡检图像电力小部件识别研究[J].地球信息科学学报,2017,19(2):256-263.
[21] 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.Las Vegas:IEEE,2016.
[22] SZEGEDY C,LIU W,JIA Y,et al.Going Deeper with Convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Boston:IEEE,2015.
[23] DAI J,LI Y,HE K,et al.R-FCN:Object Detection via Region-based Fully Convolutional Networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas:IEEE,2016.
[24] GIRSHICK R.Fast r-cnn[C]//Proceedings of the IEEE International Conference on Computer Vision.[S.l.]:IEEE,2005.
[25] 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,2017,39(6):1137-1149.
[26] SHRIVASTAVA A,GUPTA A,GIRSHICK R.Training Region-based Object Detectors with Online Hard Example Mining[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas:IEEE,2016.

基于全卷积网络的高分辨遥感影像目标检测

Object Detection in High Resolution Remote Sensing Images Based on Fully Convolution Networks

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	刘立, 董先敏, 刘娟, 文学虎. 人机融合智能的遥感解译生产新方法[J]. 测绘通报, 2022, 0(7): 118-123,137.
[2]	蔡柔丹. 一种基于用户异步轨迹的身份识别智能方法[J]. 测绘通报, 2022, 0(7): 158-162,167.
[3]	滕文鑫, 张建辰, 邵杰. 集成时空邻近与卷积网络车道级高精度定位算法[J]. 测绘通报, 2022, 0(6): 1-5,61.
[4]	张晋赫, 秦育罗, 张在岩, 宋伟东, 朱洪波. 复杂场景下农村道路裂缝分割方法[J]. 测绘通报, 2022, 0(5): 74-78,88.
[5]	潘建平, 付占宝, 程卫华, 陆世安, 李鑫, 孙博文, 黄桂萍. 基于地表类型的山地海绵城市生态建设评估[J]. 测绘通报, 2022, 0(5): 84-88.
[6]	陈智朗, 付振华, 朱紫阳, 王慧慧, 刘沁雯, 杨钰灵, 许耿然. 基于HRNet的高分辨率遥感影像建筑物变化信息提取[J]. 测绘通报, 2022, 0(5): 126-132.
[7]	师芸, 石龙龙, 牛敏杰, 赵侃. 基于单阶段实例分割网络的黄土滑坡多任务自动识别[J]. 测绘通报, 2022, 0(4): 26-31.
[8]	王雪, 梁珂, 隋立春, 钟棉卿, 朱剑锋. 膨胀卷积与金字塔表达的深度学习模型用于农村建筑物提取[J]. 测绘通报, 2022, 0(4): 61-65.
[9]	高鸣, 周鑫鑫, 刘琦, 杨光迪, 吴长彬. 深度学习网络支持下的农房侵占耕地自动化监测[J]. 测绘通报, 2022, 0(3): 47-53.
[10]	孙琴琴, 蔡国印, 杨柳忠, 张宁, 杜明义. 城市尺度典型地表要素综合提取方法研究[J]. 测绘通报, 2022, 0(2): 62-66.
[11]	张自强, 刘涛, 杜萍, 锁旭宏, 杨国林. 图残差神经网络支持下的建筑物群组模式分类[J]. 测绘通报, 2022, 0(1): 1-7.
[12]	车子杰, 高飞, 吴兆福, 李振轩. 基于改进U-Net网络的多源遥感影像洪涝灾害信息提取与变化分析[J]. 测绘通报, 2022, 0(1): 26-32.
[13]	程瑞, 高建, 邢强, 孙中昶. 一种优化的Faster R-CNN小目标检测方法[J]. 测绘通报, 2021, 0(9): 21-27.
[14]	杨素妨, 杜林. 多特征流形鉴别嵌入的高分辨率遥感影像分类[J]. 测绘通报, 2021, 0(9): 37-42.
[15]	耿万轩, 周维勋, 金双根. 基于LDCNN特征提取的多核SVM高分辨率遥感影像场景分类[J]. 测绘通报, 2021, 0(8): 14-21.