改进的基于深度学习的遥感图像分类算法
|
摘要
针对传统的基于深度学习的遥感图像分类算法未能有效融合多种深度学习特征,且分类器性能欠佳的问题,提出一种改进的基于深度学习的高分辨率遥感图像分类算法。首先,设计并搭建一个七层卷积神经网络;其次,将高分辨率遥感图像样本输入到该网络中进行网络训练,得到最后两个全连接层输出作为遥感图像两种不同的高层特征;再次,针对该网络第五层池化层输出,采用主成分分析(PCA)进行降维,作为遥感图像的第三种高层特征;然后,将上述三种高层特征通过串联的形式进行融合,得到一种有效的基于深度学习的遥感图像特征;最后,设计了一种基于逻辑回归的遥感图像分类器,可以对遥感图像进行有效分类。与传统基于深度学习的遥感图像分类算法相比,所提算法分类准确率有较高提升。实验结果表明,该算法在分类准确率、误分类率和Kappa系数上表现优异,能实现良好的分类效果。
In order to solve the problem that the traditional deep learning based remote sensing image classification algorithms cannot effectively fuse multiple deep learning features and their classifiers have poor performance,an improved high-resolution remote sensing image classification algorithm based on deep learning was proposed.Firstly,a seven-layer convolutional neural network was designed and constructed.Secondly,the high-resolution remote sensing images were input into the network to train it,and the last two fully connected layer outputs were taken as two different high-level features for the remote sensing images.Thirdly,Principal Component Analysis(PCA)was applied to the output of the fifth pooling layer in the network,and the obtained dimensionality reduction result was taken as the third high-level features for the remote sensing images.Fourthly,the above three kinds of features were concatenated to get an effective deep learning based remote sensing image feature.Finally,a logical regression based classifier was designed for remote sensing image classification.Compared with the traditional deep learning algorithms,the accuracy of the proposed algorithm was increased.The experimental results show that the proposed algorithm performs excellent in terms of classification accuracy,misclassification rate and Kappa coefficient,and achieves good classification results.
In order to solve the problem that the traditional deep learning based remote sensing image classification algorithms cannot effectively fuse multiple deep learning features and their classifiers have poor performance,an improved high-resolution remote sensing image classification algorithm based on deep learning was proposed.Firstly,a seven-layer convolutional neural network was designed and constructed.Secondly,the high-resolution remote sensing images were input into the network to train it,and the last two fully connected layer outputs were taken as two different high-level features for the remote sensing images.Thirdly,Principal Component Analysis(PCA)was applied to the output of the fifth pooling layer in the network,and the obtained dimensionality reduction result was taken as the third high-level features for the remote sensing images.Fourthly,the above three kinds of features were concatenated to get an effective deep learning based remote sensing image feature.Finally,a logical regression based classifier was designed for remote sensing image classification.Compared with the traditional deep learning algorithms,the accuracy of the proposed algorithm was increased.The experimental results show that the proposed algorithm performs excellent in terms of classification accuracy,misclassification rate and Kappa coefficient,and achieves good classification results.
引文
[1]WANG X,SHEN S,NING C,et al.Multi-class remote sensing objects recognition based on discriminative sparse representation[J].Applied Optics,2016,55(6):1381-1394.
[2]WANG X,XIONG X,NING C,et al.Integration of heterogeneous features for remote sensing scene classification[J].Journal of Applied Remote Sensing,2018,12(1):015023.
[3]NING C,LIU W,ZHANG G,et al.Enhanced synthetic aperture radar automatic target recognition method based on novel features[J].Applied Optics,2016,55(31):8893-8904.
[4]SIRMACEK B,UNSALAN C.Urban-area and building detection using SIFT keypoints and graph theory[J].IEEE Transactions on Geoscience and Remote Sensing,2009,47(4):1156-1167.
[5]TUERMER S,KURZ F,REINARTZ P,et al.Airborne vehicle detection in dense urban areas using Ho G features and disparity maps[J].IEEE Journal of Selected Topics in Applied Earth Observations&Remote Sensing,2013,6(6):2327-2337.
[6]CHEN C,ZHANG B,SU H,et al.Land-use scene classification using multi-scale completed local binary patterns[J].Signal,Image&Video Processing,2016,10(4):745-752.
[7]DENG J,DONG W,SOCHER R,et al.Image Net:a large-scale hierarchical image database[C]//Proceedings of the 2009 IEEEConference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE,2009:248-255.
[8]HINTON G E,OSINDERO S,TEH Y-W.A fast learning algorithm for deep belief nets[J].Neural Computation,2006,18(7):1527-1554.
[9]刘大伟,韩玲,韩晓勇.基于深度学习的高分辨率遥感影像分类研究[J].光学学报,2016,36(4):0428001.(LIU D W,HANL,HAN X Y.High spatial resolution remote sensing image classification based on deep learning[J].Acta Optica Sinica,2016,36(4):0428001.)
[10]曲景影,孙显,高鑫.基于CNN模型的高分辨率遥感图像目标识别[J].国外电子测量技术,2016,35(8):45-50.(QU J Y,SUN X,GAO X.Remote sensing image target recognition based on CNN[J].Foreign Electronic Measurement Technology,2016,35(8):45-50.)
[11]周敏,史振威,丁火平.遥感图像飞机目标分类的卷积神经网络方法[J].中国图象图形学报,2017,22(5):702-708.(ZHOU M,SHI Z W,DING H P.Aircraft classification in remote-sensing images using convolutional neural networks[J].Journal of Image and Graphics,2017,22(5):702-708.)
[12]黄洁,姜志国,张浩鹏,等.基于卷积神经网络的遥感图像舰船目标检测[J].北京航空航天大学学报,2017,43(09):1841-1848.(HUANG J,JIANG Z G,ZHANG H P,et al.Ship object detection in remote sensing images using convolutional neural networks[J].Journal of Beijing University of Aeronautics and Astronsutics,2017,43(9):1841-1848.)
[13]LECUN Y,BOTTOU L,BENGIO Y,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[14]GAO L,CHEN P-Y,YU S.Demonstration of convolution kernel operation on resistive cross-point array[J].IEEE Electron Device Letters,2016,37(7):870-873.
[15]GIRSHICK R,IANDOLAA F,DARRELL T,et al.Deformable part models are convolutional neural networks[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition.Washington,DC:IEEE Computer Society,2015:437-446.
[16]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Image Net classification with deep convolutional neural networks[C]//Proceedings of the 25th International Conference on Neural Information Processing Systems.Lake Tahoe,NV:Curran Associates Inc.,2012:1097-1105.
[17]HINTON G E.How neural networks learn from experience[J].Scientific American,1992,267(3):145-151.
[18]BOUVRIE J.Notes on convolutional neural networks[EB/OL].[2018-04-18].http://cogprints.org/5869/.
[19]RUMELHART D E,HINTON G E,WILLAMS R J.Learning representations by back-propagating errors[J].Nature,1986,323(6088):533-536.
[20]HOTELLING H.Analysis of a complex of statistical variables into principal components[J].Journal of Educational Psychology,1933,24(6):417-520.
[2]WANG X,XIONG X,NING C,et al.Integration of heterogeneous features for remote sensing scene classification[J].Journal of Applied Remote Sensing,2018,12(1):015023.
[3]NING C,LIU W,ZHANG G,et al.Enhanced synthetic aperture radar automatic target recognition method based on novel features[J].Applied Optics,2016,55(31):8893-8904.
[4]SIRMACEK B,UNSALAN C.Urban-area and building detection using SIFT keypoints and graph theory[J].IEEE Transactions on Geoscience and Remote Sensing,2009,47(4):1156-1167.
[5]TUERMER S,KURZ F,REINARTZ P,et al.Airborne vehicle detection in dense urban areas using Ho G features and disparity maps[J].IEEE Journal of Selected Topics in Applied Earth Observations&Remote Sensing,2013,6(6):2327-2337.
[6]CHEN C,ZHANG B,SU H,et al.Land-use scene classification using multi-scale completed local binary patterns[J].Signal,Image&Video Processing,2016,10(4):745-752.
[7]DENG J,DONG W,SOCHER R,et al.Image Net:a large-scale hierarchical image database[C]//Proceedings of the 2009 IEEEConference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE,2009:248-255.
[8]HINTON G E,OSINDERO S,TEH Y-W.A fast learning algorithm for deep belief nets[J].Neural Computation,2006,18(7):1527-1554.
[9]刘大伟,韩玲,韩晓勇.基于深度学习的高分辨率遥感影像分类研究[J].光学学报,2016,36(4):0428001.(LIU D W,HANL,HAN X Y.High spatial resolution remote sensing image classification based on deep learning[J].Acta Optica Sinica,2016,36(4):0428001.)
[10]曲景影,孙显,高鑫.基于CNN模型的高分辨率遥感图像目标识别[J].国外电子测量技术,2016,35(8):45-50.(QU J Y,SUN X,GAO X.Remote sensing image target recognition based on CNN[J].Foreign Electronic Measurement Technology,2016,35(8):45-50.)
[11]周敏,史振威,丁火平.遥感图像飞机目标分类的卷积神经网络方法[J].中国图象图形学报,2017,22(5):702-708.(ZHOU M,SHI Z W,DING H P.Aircraft classification in remote-sensing images using convolutional neural networks[J].Journal of Image and Graphics,2017,22(5):702-708.)
[12]黄洁,姜志国,张浩鹏,等.基于卷积神经网络的遥感图像舰船目标检测[J].北京航空航天大学学报,2017,43(09):1841-1848.(HUANG J,JIANG Z G,ZHANG H P,et al.Ship object detection in remote sensing images using convolutional neural networks[J].Journal of Beijing University of Aeronautics and Astronsutics,2017,43(9):1841-1848.)
[13]LECUN Y,BOTTOU L,BENGIO Y,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[14]GAO L,CHEN P-Y,YU S.Demonstration of convolution kernel operation on resistive cross-point array[J].IEEE Electron Device Letters,2016,37(7):870-873.
[15]GIRSHICK R,IANDOLAA F,DARRELL T,et al.Deformable part models are convolutional neural networks[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition.Washington,DC:IEEE Computer Society,2015:437-446.
[16]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Image Net classification with deep convolutional neural networks[C]//Proceedings of the 25th International Conference on Neural Information Processing Systems.Lake Tahoe,NV:Curran Associates Inc.,2012:1097-1105.
[17]HINTON G E.How neural networks learn from experience[J].Scientific American,1992,267(3):145-151.
[18]BOUVRIE J.Notes on convolutional neural networks[EB/OL].[2018-04-18].http://cogprints.org/5869/.
[19]RUMELHART D E,HINTON G E,WILLAMS R J.Learning representations by back-propagating errors[J].Nature,1986,323(6088):533-536.
[20]HOTELLING H.Analysis of a complex of statistical variables into principal components[J].Journal of Educational Psychology,1933,24(6):417-520.