基于仿射不变离散哈希的遥感图像多目标分类
|
摘要
遥感图像的多目标分类是一个具有挑战性的课题.首先,由于数据的复杂性以及算法对存储的高需求,传统分类方法很难兼顾到分类的精度和速度;其次,遥感成像过程中产生的仿射变换,使得目标的快速解译难以实现.为此,提出一种基于仿射不变离散哈希(AIDH)的遥感图像多目标分类方法.该方法采用具有低存储、高效率优势的监督离散哈希框架,结合仿射不变优化因子,构造仿射不变离散哈希,通过将具有相同语义信息的仿射变换样本约束到相似的二值码空间实现分类精度的提高.实验结果表明,在NWPU VHR-10和RSDO-dataset两个数据集下,相比于经典的哈希方法和分类方法,所提方法在具备了高效性的同时,其精度也得到了保证.
The multi-object classification of remote sensing images has been a challenging task. Firstly, due to the complexity of the data and the high requirement of storage, the traditional classification methods are difficult to achieve both the accuracy and speed of the classification. Secondly, the affine transformation caused by the remote sensing imaging process, the real-time performance of the object interpretation is difficult to be realized. To solve the problem, a multi-object classification of remote sensing image is proposed based on affine-invariant discrete hashing(AIDH). This method uses supervised discrete hashing with the advantage of low storage and high efficiency, jointed with affine-invariant factor, to construct affine-invariant discrete hashing. By constraining the affine transform samples with the same semantic information to the similar binary code space, the method achieves the enhancement on classification precision.Experiments show that under the two datasets of NWPU VHR-10 and RSDO-dataset, the method presented in this paper is more efficient than classical hash method and classification method, and it is also guaranteed in accuracy.
The multi-object classification of remote sensing images has been a challenging task. Firstly, due to the complexity of the data and the high requirement of storage, the traditional classification methods are difficult to achieve both the accuracy and speed of the classification. Secondly, the affine transformation caused by the remote sensing imaging process, the real-time performance of the object interpretation is difficult to be realized. To solve the problem, a multi-object classification of remote sensing image is proposed based on affine-invariant discrete hashing(AIDH). This method uses supervised discrete hashing with the advantage of low storage and high efficiency, jointed with affine-invariant factor, to construct affine-invariant discrete hashing. By constraining the affine transform samples with the same semantic information to the similar binary code space, the method achieves the enhancement on classification precision.Experiments show that under the two datasets of NWPU VHR-10 and RSDO-dataset, the method presented in this paper is more efficient than classical hash method and classification method, and it is also guaranteed in accuracy.
引文
[1]Zhang NJ,Zhang J,Zhang X,Lang HT.Task distribution balancing for parallel two-parameter CFAR ship detection.Journal of Remote Sensing,2016,2:344-351(in Chinese with English abstract).
[2]Zhen JX,Fu J,Fu X.Aircraft target recognition in remote sensing images based on distribution of the feature points and invariant moments.Journal of Image and Graphics,2014,4:592-602(in Chinese with English abstract).
[3]Chen Z,Ma HC,Zhang L.Cloverleaf interchange boundary extraction from airborne LiDAR data based on advanced neighborhood structure and contour analysis.Journal of Remote Sensing,2013,17(5):1146-1157(in Chinese with English abstract).
[4]Cheng G,Han JW,Zhou PC,Guo L.Multi-class geospatial object detection and geographic image classification based on collection of part detectors.ISPRS Journal of Photogrammetry&Remote Sensing,2014,98(1):119-132.
[5]Cheng G,Zhou PC,Yao XW,Yao C,Zhang YB,Han JW.Object detection in VHR optical remote sensing images via learning rotation-invariant HOG feature.In:Proc.of the Int’l Workshop on EORSA.2016.433-436.
[6]Chen XM.The study of disaster target automatic classification based on high-resolution remote sensing images[Ph.D.Thesis].Beijing:China University of Geosciences,2016(in Chinese with English abstract).
[7]Hou YT,Peng JY,Hao LW,Wang R.Research of classification method for natural images based on adaptive feature-weighted K-nearest neighbors.Application Research of Computers,2014,31(3):957-960(in Chinese with English abstract).
[8]Bosch A,Zisserman A,Munoz X.Image classification using random forests and ferns.In:Proc.of the IEEE Int’l Conf.on Computer Vision.2007.14-21.
[9]Wu W,Nie JY,Gao GL.Improved SVM multiple classifiers for image annotation.Computer Engineering&Science,2015,37(7):1338-1343(in Chinese with English abstract).
[10]Wright J,Yang AY,Ganesh A,Sastry SS,Ma Y.Robust face recognition via sparse representation.IEEE Trans.on Pattern Analysis and Machine Intelligence,2009,31(2):210-227.
[11]Zhao LJ,Tang P.Scalability analysis of typical remote sensing data classification methods:A case of remote sensing image scene.Journal of Remote Sensing,2016,20(2):157-171(in Chinese with English abstract).
[12]Wang XM,Zhang HL.Hyperspectral remote sensing image classification using geodesic-based KNN.Journal of Shanxi Coalmining Administrators College,2013,26(4):135-137(in Chinese with English abstract).
[13]Pal M.Random forest classifier for remote sensing classification.Int’l Journal of Remote Sensing,2005,26(1):217-222.
[14]Zhao CH,Liu W,Xu Y,Wen JH.A spectral-spatial SVM-based multi-layer learning algorithm for hyperspectral image classification.Remote Sensing Letters,2018,9(3):218-227.
[15]Wu SL,Chen HD,Bai Y,Zhu GK.A remote sensing image classification method based on sparse representation.Multimedia Tools and Applications,2016,75(19):12137-12154.
[16]Bulley H,Bishop MP,Shroder JF.Integration of classification tree analyses and spatial metrics to assess changes in supraglacial lakes in the Karakoram Himalaya.Int’l Journal of Remote Sensing,2012,34(2):387-411.
[17]Sisodia PS,Tiwari V,Kumar A.Analysis of supervised maximum likelihood classification for remote sensing image.In:Recent Advances&Innovations in Engineering.2014.1-4.
[18]Cheng G,Zhou PC,Han JW.Learning rotation-invariant convolutional neural networks for object detection in VHR optical remote sensing images.IEEE Trans.on Geoscience and Remote Sensing,2016,54(12):7405-7415.
[19]Meher Sk.Knowledge-encoded granular neural networks for hyperspectral remote sensing image classification.IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2015,8(6):2439-2446.
[20]Wang JD,Shen HT,Song JK,Ji JQ.Hashing for similarity search:A survey.Computer Science,2014,1-29.
[21]Gionis A,Indyk P,Motwani R.Similarity search in high dimensions via hashing.In:Proc.of the 25th VLDB Conf.1999,8(2):518-529.
[22]Weiss Y,Torralba A,Fergus R.Spectral hashing.In:Proc.of the Int’l Conf.on Neural Information Processing Systems(NIPS).2008,282(3):1753-1760.
[23]Jiang QY,Li WJ.Scalable graph hashing with feature transformation.In:Proc.of the Int’l Conf.on Artificial Intelligence(ICAI).2015,9(3):2248-2254.
[24]Shen FM,Shen CH,Shi QF,Hengel AVD,Tang ZM.Inductive hashing on manifolds.In:Proc.of the Computer Vision and Pattern Recognition(CVPR).2013.1562-1569.
[25]Liu W,Wang J,Ji RR,et al.Supervised hashing with kernels.In:Proc.of the Computer Vision and Pattern Recognition(CVPR).2012.2074-2081.
[26]Norouzi M,Blei DM.Minimal loss hashing for compact binary codes.In:Proc.of the Int’l Conf.on Machine Learning(ICML).2011.353-360.
[27]Shen FM,Shen CH,Liu W,Shen HT.Supervised discrete hashing.In:Proc.of the Computer Vision and Pattern Recognition(CVPR).2015.37-45.
[28]Kang WC,Li WJ,Zhou ZH.Column sampling based discrete supervised hashing.In:American Association for Artificial Intelligence(AAAI).2016.http://cs.nju.edu.cn/lwj/paper/AAAI16_COSDISH.pdf
[29]Xu H,Liu YZ,Sun QS.Object classification of remote sensing images based on rotation-invariant discrete hashing.In:Proc.of the Pacific RIM Conf.on Multimedia.2017.264-274.
[30]Shen XB.Study of multi-view embedding learning techniques with applications[Ph.D.Thesis].Nanjing:Nanjing University of Science and Technology,2017(in Chinese with English abstract).
[31]Tang T.Affine invariant feature and its application to target recognition in remote sensing images[Ph.D.Thesis].Changsha:National University of Defense Technology,2006(in Chinese with English abstract).
[32]Wang FG,Feng XC,Zhang XB.Stationary wavelet transform for affine invariant image object recognition.Computer Engineering and Applications,2007,43(21):239-241(in Chinese with English abstract).
[33]Zhang JY,Chen Q,Bai XJ,Sun QS,Xia DS.Affine invariant feature extraction algorithm based on generalized canonical correlation analysis.Journal of Electronics&Information Technology,2009,31(10):2465-2469(in Chinese with English abstract).
[34]Gao F,Wen XJ.A new method for affine invariants extraction based on affine geometry.Journal of Image and Graphics,2011,16(3):389-397(in Chinese with English abstract).
[35]Kong J,Sun QS,Ji ZX,Liu YZ.A novel fast object detection method in remote sensing image based on affine-invariant supervised discrete hashing.Journal of Nanjing University Natural Science,2019,55(1):49-60(in Chinese with English abstract).
[36]Long Y,Gong YP,Xiao ZF,Liu Q.Accurate object localization in remote sensing images based on convolutional neural networks.IEEE Trans.on Geosciences and Remote Sensing,2017,55(5):2486-2498.
[37]Liu J,Guo J,He ZL.Scene classification based on gist and PHOG feature.Computer Engineering,2015,41(4):232-235(in Chinese with English abstract).
[1]张临杰,张杰,张晰,郎海涛.任务分配均衡的双参数CFAR舰船检测并行算法.遥感学报,2016,2:344-351.
[2]曾接贤,付俊,符祥.特征点和不变矩结合的遥感图像飞机目标识别.中国图像图形学报,2014,4:592-602.
[3]陈卓,马洪超,张良.改进邻域结构与轮廓分析的LiDAR点云立交桥提取.遥感学报,2013,17(5):1146-1157.
[6]程希萌.基于高分遥感影像的灾害目标自动分类技术[博士学位论文].北京:中国地质大学,2016.
[7]侯玉婷,彭进业,郝露微,王瑞.基于KNN的特征自适应加权自然图像分类研究.计算机应用研究,2014,31(3):957-960.
[9]吴伟,聂建云,高光来.一种基于改进的支持向量机多分类器图像标方法.计算机工程与科学,2015,37(7):1338-1343.
[11]赵理君,唐娉.典型遥感数据分类方法的适用性分析--以遥感图像场景分类为例.遥感学报,2016,20(2):157-171.
[12]王小美,张红利.基于测地距离的KNN高光谱遥感图像分类.山西煤炭管理干部学院学报,2013,26(4):135-137.
[30]沈肖波.多视图嵌入学习方法及其应用研究[博士学位论文].南京:南京理工大学,2017.
[31]唐涛.图像仿射不变特征及其在遥感图像目标识别中的应用[博士学位论文].长沙:国防科技大学,2006.
[32]王凤国,冯象初,张小波.平稳小波变换在仿射不变性目标识别中的应用.计算机工程与应用,2007,43(21):239-241.
[33]张洁玉,陈强,白小晶,孙权森,夏德深.基于广义典型相关分析的仿射不变特征提取方法.电子与信息学报,2009,31(10):2465-2469.
[34]高峰,文项坚.利用仿射几何的仿射不变特征提取方法.中国图像图形学报,2011,16(3):389-397.
[35]孔颉,孙权森,纪则轩,刘亚洲.基于仿射不变离散哈希的遥感图像快速目标检测新方法.南京大学学报(自然科学),2019,55(1):49-60.
[37]刘静,郭建,贺遵亮.基于Gist和PHOG特征的场景分类.计算机工程,2015,41(4):232-235.
[2]Zhen JX,Fu J,Fu X.Aircraft target recognition in remote sensing images based on distribution of the feature points and invariant moments.Journal of Image and Graphics,2014,4:592-602(in Chinese with English abstract).
[3]Chen Z,Ma HC,Zhang L.Cloverleaf interchange boundary extraction from airborne LiDAR data based on advanced neighborhood structure and contour analysis.Journal of Remote Sensing,2013,17(5):1146-1157(in Chinese with English abstract).
[4]Cheng G,Han JW,Zhou PC,Guo L.Multi-class geospatial object detection and geographic image classification based on collection of part detectors.ISPRS Journal of Photogrammetry&Remote Sensing,2014,98(1):119-132.
[5]Cheng G,Zhou PC,Yao XW,Yao C,Zhang YB,Han JW.Object detection in VHR optical remote sensing images via learning rotation-invariant HOG feature.In:Proc.of the Int’l Workshop on EORSA.2016.433-436.
[6]Chen XM.The study of disaster target automatic classification based on high-resolution remote sensing images[Ph.D.Thesis].Beijing:China University of Geosciences,2016(in Chinese with English abstract).
[7]Hou YT,Peng JY,Hao LW,Wang R.Research of classification method for natural images based on adaptive feature-weighted K-nearest neighbors.Application Research of Computers,2014,31(3):957-960(in Chinese with English abstract).
[8]Bosch A,Zisserman A,Munoz X.Image classification using random forests and ferns.In:Proc.of the IEEE Int’l Conf.on Computer Vision.2007.14-21.
[9]Wu W,Nie JY,Gao GL.Improved SVM multiple classifiers for image annotation.Computer Engineering&Science,2015,37(7):1338-1343(in Chinese with English abstract).
[10]Wright J,Yang AY,Ganesh A,Sastry SS,Ma Y.Robust face recognition via sparse representation.IEEE Trans.on Pattern Analysis and Machine Intelligence,2009,31(2):210-227.
[11]Zhao LJ,Tang P.Scalability analysis of typical remote sensing data classification methods:A case of remote sensing image scene.Journal of Remote Sensing,2016,20(2):157-171(in Chinese with English abstract).
[12]Wang XM,Zhang HL.Hyperspectral remote sensing image classification using geodesic-based KNN.Journal of Shanxi Coalmining Administrators College,2013,26(4):135-137(in Chinese with English abstract).
[13]Pal M.Random forest classifier for remote sensing classification.Int’l Journal of Remote Sensing,2005,26(1):217-222.
[14]Zhao CH,Liu W,Xu Y,Wen JH.A spectral-spatial SVM-based multi-layer learning algorithm for hyperspectral image classification.Remote Sensing Letters,2018,9(3):218-227.
[15]Wu SL,Chen HD,Bai Y,Zhu GK.A remote sensing image classification method based on sparse representation.Multimedia Tools and Applications,2016,75(19):12137-12154.
[16]Bulley H,Bishop MP,Shroder JF.Integration of classification tree analyses and spatial metrics to assess changes in supraglacial lakes in the Karakoram Himalaya.Int’l Journal of Remote Sensing,2012,34(2):387-411.
[17]Sisodia PS,Tiwari V,Kumar A.Analysis of supervised maximum likelihood classification for remote sensing image.In:Recent Advances&Innovations in Engineering.2014.1-4.
[18]Cheng G,Zhou PC,Han JW.Learning rotation-invariant convolutional neural networks for object detection in VHR optical remote sensing images.IEEE Trans.on Geoscience and Remote Sensing,2016,54(12):7405-7415.
[19]Meher Sk.Knowledge-encoded granular neural networks for hyperspectral remote sensing image classification.IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2015,8(6):2439-2446.
[20]Wang JD,Shen HT,Song JK,Ji JQ.Hashing for similarity search:A survey.Computer Science,2014,1-29.
[21]Gionis A,Indyk P,Motwani R.Similarity search in high dimensions via hashing.In:Proc.of the 25th VLDB Conf.1999,8(2):518-529.
[22]Weiss Y,Torralba A,Fergus R.Spectral hashing.In:Proc.of the Int’l Conf.on Neural Information Processing Systems(NIPS).2008,282(3):1753-1760.
[23]Jiang QY,Li WJ.Scalable graph hashing with feature transformation.In:Proc.of the Int’l Conf.on Artificial Intelligence(ICAI).2015,9(3):2248-2254.
[24]Shen FM,Shen CH,Shi QF,Hengel AVD,Tang ZM.Inductive hashing on manifolds.In:Proc.of the Computer Vision and Pattern Recognition(CVPR).2013.1562-1569.
[25]Liu W,Wang J,Ji RR,et al.Supervised hashing with kernels.In:Proc.of the Computer Vision and Pattern Recognition(CVPR).2012.2074-2081.
[26]Norouzi M,Blei DM.Minimal loss hashing for compact binary codes.In:Proc.of the Int’l Conf.on Machine Learning(ICML).2011.353-360.
[27]Shen FM,Shen CH,Liu W,Shen HT.Supervised discrete hashing.In:Proc.of the Computer Vision and Pattern Recognition(CVPR).2015.37-45.
[28]Kang WC,Li WJ,Zhou ZH.Column sampling based discrete supervised hashing.In:American Association for Artificial Intelligence(AAAI).2016.http://cs.nju.edu.cn/lwj/paper/AAAI16_COSDISH.pdf
[29]Xu H,Liu YZ,Sun QS.Object classification of remote sensing images based on rotation-invariant discrete hashing.In:Proc.of the Pacific RIM Conf.on Multimedia.2017.264-274.
[30]Shen XB.Study of multi-view embedding learning techniques with applications[Ph.D.Thesis].Nanjing:Nanjing University of Science and Technology,2017(in Chinese with English abstract).
[31]Tang T.Affine invariant feature and its application to target recognition in remote sensing images[Ph.D.Thesis].Changsha:National University of Defense Technology,2006(in Chinese with English abstract).
[32]Wang FG,Feng XC,Zhang XB.Stationary wavelet transform for affine invariant image object recognition.Computer Engineering and Applications,2007,43(21):239-241(in Chinese with English abstract).
[33]Zhang JY,Chen Q,Bai XJ,Sun QS,Xia DS.Affine invariant feature extraction algorithm based on generalized canonical correlation analysis.Journal of Electronics&Information Technology,2009,31(10):2465-2469(in Chinese with English abstract).
[34]Gao F,Wen XJ.A new method for affine invariants extraction based on affine geometry.Journal of Image and Graphics,2011,16(3):389-397(in Chinese with English abstract).
[35]Kong J,Sun QS,Ji ZX,Liu YZ.A novel fast object detection method in remote sensing image based on affine-invariant supervised discrete hashing.Journal of Nanjing University Natural Science,2019,55(1):49-60(in Chinese with English abstract).
[36]Long Y,Gong YP,Xiao ZF,Liu Q.Accurate object localization in remote sensing images based on convolutional neural networks.IEEE Trans.on Geosciences and Remote Sensing,2017,55(5):2486-2498.
[37]Liu J,Guo J,He ZL.Scene classification based on gist and PHOG feature.Computer Engineering,2015,41(4):232-235(in Chinese with English abstract).
[1]张临杰,张杰,张晰,郎海涛.任务分配均衡的双参数CFAR舰船检测并行算法.遥感学报,2016,2:344-351.
[2]曾接贤,付俊,符祥.特征点和不变矩结合的遥感图像飞机目标识别.中国图像图形学报,2014,4:592-602.
[3]陈卓,马洪超,张良.改进邻域结构与轮廓分析的LiDAR点云立交桥提取.遥感学报,2013,17(5):1146-1157.
[6]程希萌.基于高分遥感影像的灾害目标自动分类技术[博士学位论文].北京:中国地质大学,2016.
[7]侯玉婷,彭进业,郝露微,王瑞.基于KNN的特征自适应加权自然图像分类研究.计算机应用研究,2014,31(3):957-960.
[9]吴伟,聂建云,高光来.一种基于改进的支持向量机多分类器图像标方法.计算机工程与科学,2015,37(7):1338-1343.
[11]赵理君,唐娉.典型遥感数据分类方法的适用性分析--以遥感图像场景分类为例.遥感学报,2016,20(2):157-171.
[12]王小美,张红利.基于测地距离的KNN高光谱遥感图像分类.山西煤炭管理干部学院学报,2013,26(4):135-137.
[30]沈肖波.多视图嵌入学习方法及其应用研究[博士学位论文].南京:南京理工大学,2017.
[31]唐涛.图像仿射不变特征及其在遥感图像目标识别中的应用[博士学位论文].长沙:国防科技大学,2006.
[32]王凤国,冯象初,张小波.平稳小波变换在仿射不变性目标识别中的应用.计算机工程与应用,2007,43(21):239-241.
[33]张洁玉,陈强,白小晶,孙权森,夏德深.基于广义典型相关分析的仿射不变特征提取方法.电子与信息学报,2009,31(10):2465-2469.
[34]高峰,文项坚.利用仿射几何的仿射不变特征提取方法.中国图像图形学报,2011,16(3):389-397.
[35]孔颉,孙权森,纪则轩,刘亚洲.基于仿射不变离散哈希的遥感图像快速目标检测新方法.南京大学学报(自然科学),2019,55(1):49-60.
[37]刘静,郭建,贺遵亮.基于Gist和PHOG特征的场景分类.计算机工程,2015,41(4):232-235.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |