基于改进的三维卷积神经网络的高光谱遥感影像分类技术研究
|
摘要
高光谱遥感影像数据具有多样化的光谱信息和空间信息,然而传统的高光谱影像分类只是针对目标的光谱特征进行处理。基于三维空间滤波操作可以作为一种简单高效的提取高光谱影像光谱和空间特征的方式,基于此提出一种改进的三维卷积神经网络框架以实现更加准确的高光谱遥感影像分类。利用高光谱遥感影像数据立方体有效地提取光谱-空间组合特征,而不依赖于任何预处理或后期处理。另外,与其他传统的基于深度学习的方法相比,该方法去除了池化层,从而达到所需参数更少,模型规模更小,更容易训练的效果。将该方法与其他基于深度学习的高光谱遥感影像分类方法进行了比较,并使用两个真实场景的高光谱遥感影像数据集作为测试。实验结果表明,该方法在地物分类准确度方面较传统的基于深度学习的高光谱遥感影像分类方法取得了更好的分类效果。
Hyperspectral remote sensing image contains both rich spectral and spatial information. However,traditional hyperspectral image classification is usually based on spectral features. Based on three-dimensional spatial filtering,it can be used as a simple and effective method to extract spectral spatial features of hyperspectral images. An improved three-dimensional convolutional neural network framework is proposed for accurate hyperspectral remote sensing image classification. The data cube effectively extracts spectral-spatial combination features without relying on any pre-processing or post-processing. In addition,compared to other traditional deep learningbased methods,a smaller model size which requires fewer parameters,and less likelihood of overfitting can be much easier to train. This method is compared with other hyperspectral remote sensing image classification methods based on deep learning,and is tested on two hyperspectral remote sensing image datasets. Compared to traditional deep learning methods,3 D-CNN gets better accuracy among the results of hyperspectral images.
Hyperspectral remote sensing image contains both rich spectral and spatial information. However,traditional hyperspectral image classification is usually based on spectral features. Based on three-dimensional spatial filtering,it can be used as a simple and effective method to extract spectral spatial features of hyperspectral images. An improved three-dimensional convolutional neural network framework is proposed for accurate hyperspectral remote sensing image classification. The data cube effectively extracts spectral-spatial combination features without relying on any pre-processing or post-processing. In addition,compared to other traditional deep learningbased methods,a smaller model size which requires fewer parameters,and less likelihood of overfitting can be much easier to train. This method is compared with other hyperspectral remote sensing image classification methods based on deep learning,and is tested on two hyperspectral remote sensing image datasets. Compared to traditional deep learning methods,3 D-CNN gets better accuracy among the results of hyperspectral images.
引文
[1]张兵,高连如.高光谱图像分类与目标检测[M].北京:科学出版社,2011.
[2]Hu Wei,Huang Yangyu,Wei Li,et al.Deep convolutional neural networks for hyperspectral image classification[J].Journal of Sensors,2015,2015(2):1-12.
[3]Sun Le,Wu Zebin,Liu Jianjun,et al.Supervised spectralspatial hyperspectral image classification with weighted Markov random fields[J].IEEE Transactions on Geoscience and Remote Sesing,2015,53(3):1490-1503.
[4]LACAR F M,LEWIS M M,GRIERSON I T.Use of hyperspectral imagery for mapping grape varieties in the Barossa valley[J].Proceedings of the IEEE 2001 International Geoscience and Remote Sensing Symposium,2001,6:2875-2877.
[5]Li Deren,Zhang Liangpei,Xia Guisong.Automatic analysis and mining of remote sensing big data[J].Acta Geodaetica Et Cartographica Sinica,2014,43(12):1211-1216.
[6]包健,厉小润.K均值算法实现遥感图像的非监督分类[J].机电工程,2008,25(3):77-80.
[7]SONG L,CHENG Y M,ZHAO Y Q.Hyper-spectrum classification based on sparse representation model and auto-regressive model[J].Acta Optica Sinica,2012,32(3):322-328.
[8]朱建华,刘政凯,俞能海.一种多光谱遥感图象的自适应最小距离分类方法[J].中国图象图形学报,2000,5(1):21-24.
[9]MELGANI F,BRUZZONE L.Classification of hyperspectral remote sensing images with support vector machines[C].IEEE Transactions on Geosciences and Remote Sensing,2004,42(8):1778-1790.
[10]HONG Y,HSU K,SOROOSHIAN S,et al.Precipitation estimation from remotely sensed imagery using an artificial neural networkcloud classification system[J].Journal of Applied Meteorology,2004,43(12):1834-1853.
[11]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Imagenet classification with deep convolutional neural networks[C].Proceedings of the 25th International Conference on Neural Information Processing Systems,2012:1097-1105.
[12]CIRESAN D,MEIER U,SCHMIDHUBER J.Multi-column deep neural networks for image classification[C].2012 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).IEEE,2012:3642-3649.
[13]Jia Kun,Li Qiangzi,Tian Yichen,et al.A review of classification methodsof remote sensing imagery[J].Spectroscopy and Spectral Analysis,2011,31(10):2618-2623.
[14]Chen Yushi,Jiang Hanlu,Li Chunyang,et al.Deep feature extraction and classification of hyperspectral images based on convolutional neural networks[J].IEEE Tranctions on Geoscience&Remote Sensing,2016,54(10):1-20.
[15]Yue Jun,Zhao Wenzhi,Mao Shanjun,et al.Spectral-spatial classification of Hyperspectral images using deep convolutional neutral networks[J].Remote Sensing Letters,2015,6(6):468-477.
[16]Zhao Wenzhi,Du Shihong.Learning multiscale and deep representations for classifying remotely sensed imagery[J].ISPRS Journal of Photogrammetry and Remote Sensing,2016,113:155-165.
[17]Mei Shaohui,Ji Jingyu,Hou Junhui,et al.Learning sensor-specific spatial-spectral features of hyperspectral images via convolutional neural networks[J].IEEE Transactions on Geoscience and Remote Sensing,2017,55(8):4520-4533.
[18]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Image Net classification with deep convolutional neural networks[C].International Conference on Neural Information Processing Systems,2012,25(2):1097-1105.
[19]GIRSHICK R.Fast R-CNN[C].Proceedings of the International Conference on Computer Vision,Santiago,Chile,2015:1440-1448.
[20]LIU F,SHEN C,LIN G.Deep convolutional neural fields for depth estimation from a single image[C].Proceedings of the Conference on Computer Vision and Pattern Recognition,Boston,MA,USA,2015:5162-5170.
[21]MOU L C,GHAMISI P,ZHU X X.Deep recurrent neural networks for hyperspectral image classification[J].IEEETransactions on Geoscience and Remote Sensing,2017,55(7):3639-3655.
[2]Hu Wei,Huang Yangyu,Wei Li,et al.Deep convolutional neural networks for hyperspectral image classification[J].Journal of Sensors,2015,2015(2):1-12.
[3]Sun Le,Wu Zebin,Liu Jianjun,et al.Supervised spectralspatial hyperspectral image classification with weighted Markov random fields[J].IEEE Transactions on Geoscience and Remote Sesing,2015,53(3):1490-1503.
[4]LACAR F M,LEWIS M M,GRIERSON I T.Use of hyperspectral imagery for mapping grape varieties in the Barossa valley[J].Proceedings of the IEEE 2001 International Geoscience and Remote Sensing Symposium,2001,6:2875-2877.
[5]Li Deren,Zhang Liangpei,Xia Guisong.Automatic analysis and mining of remote sensing big data[J].Acta Geodaetica Et Cartographica Sinica,2014,43(12):1211-1216.
[6]包健,厉小润.K均值算法实现遥感图像的非监督分类[J].机电工程,2008,25(3):77-80.
[7]SONG L,CHENG Y M,ZHAO Y Q.Hyper-spectrum classification based on sparse representation model and auto-regressive model[J].Acta Optica Sinica,2012,32(3):322-328.
[8]朱建华,刘政凯,俞能海.一种多光谱遥感图象的自适应最小距离分类方法[J].中国图象图形学报,2000,5(1):21-24.
[9]MELGANI F,BRUZZONE L.Classification of hyperspectral remote sensing images with support vector machines[C].IEEE Transactions on Geosciences and Remote Sensing,2004,42(8):1778-1790.
[10]HONG Y,HSU K,SOROOSHIAN S,et al.Precipitation estimation from remotely sensed imagery using an artificial neural networkcloud classification system[J].Journal of Applied Meteorology,2004,43(12):1834-1853.
[11]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Imagenet classification with deep convolutional neural networks[C].Proceedings of the 25th International Conference on Neural Information Processing Systems,2012:1097-1105.
[12]CIRESAN D,MEIER U,SCHMIDHUBER J.Multi-column deep neural networks for image classification[C].2012 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).IEEE,2012:3642-3649.
[13]Jia Kun,Li Qiangzi,Tian Yichen,et al.A review of classification methodsof remote sensing imagery[J].Spectroscopy and Spectral Analysis,2011,31(10):2618-2623.
[14]Chen Yushi,Jiang Hanlu,Li Chunyang,et al.Deep feature extraction and classification of hyperspectral images based on convolutional neural networks[J].IEEE Tranctions on Geoscience&Remote Sensing,2016,54(10):1-20.
[15]Yue Jun,Zhao Wenzhi,Mao Shanjun,et al.Spectral-spatial classification of Hyperspectral images using deep convolutional neutral networks[J].Remote Sensing Letters,2015,6(6):468-477.
[16]Zhao Wenzhi,Du Shihong.Learning multiscale and deep representations for classifying remotely sensed imagery[J].ISPRS Journal of Photogrammetry and Remote Sensing,2016,113:155-165.
[17]Mei Shaohui,Ji Jingyu,Hou Junhui,et al.Learning sensor-specific spatial-spectral features of hyperspectral images via convolutional neural networks[J].IEEE Transactions on Geoscience and Remote Sensing,2017,55(8):4520-4533.
[18]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Image Net classification with deep convolutional neural networks[C].International Conference on Neural Information Processing Systems,2012,25(2):1097-1105.
[19]GIRSHICK R.Fast R-CNN[C].Proceedings of the International Conference on Computer Vision,Santiago,Chile,2015:1440-1448.
[20]LIU F,SHEN C,LIN G.Deep convolutional neural fields for depth estimation from a single image[C].Proceedings of the Conference on Computer Vision and Pattern Recognition,Boston,MA,USA,2015:5162-5170.
[21]MOU L C,GHAMISI P,ZHU X X.Deep recurrent neural networks for hyperspectral image classification[J].IEEETransactions on Geoscience and Remote Sensing,2017,55(7):3639-3655.
© 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 |