High spatial resolution remote sensing image classification based on deep learning

被引：0

作者：

Liu D. ^{[1
,2
]}

Han L. ^{[1
]}

Han X. ^{[1
]}

机构：

[1] School of Geology Engineering and Geomatics, Chang'an University, Xi'an, 710054, Shaanxi

[2] Department of Information Engineering, Armed Police Engineering University, Xi'an, 710086, Shaanxi

来源：

Guangxue Xuebao/Acta Optica Sinica | 2016年 / 36卷 / 04期

关键词：

Deep belief networks; Deep learning; High spatial resolution; Nonsubsampled contourlet transform; Remote sensing; Remote sensing image classification; Texture;

D O I：

10.3788/AOS201636.0428001

中图分类号：

学科分类号：

摘要：

A classification method based on deep learning is proposed for the classification of high spatial resolution remote sensing images. The texture features of the images are calculated through nonsubsampled contourlet transform, the deep learning common model-deep belief networks (DBN) are used to classify the high spatial resolution remote sensing images based on spectral and texture features. The proposed method is compared with the DBN classification method based on single spectral information, the support vector machine (SVM) method and the traditional neural network (NN) classification method. Experimental results show that comparing with the single spectral information, the use of spectral and texture information can effectively improve the classification accuracy of high spatial resolution remote sensing images, and comparing with methods of SVM and NN, the DBN method can accurately explore the distribution law of the high spatial resolution remote sensing images and improve the accuracy of classification. © 2016, Chinese Lasers Press. All right reserved.

引用

页数：9

共 25 条

[1]

Luo B., Zhang L., Robust autodual morphological profiles for the classification of high-resolution satellite images, IEEE Transactions on Geoscience and Remote Sensing, 52, 2, pp. 1451-1462, (2014)

[2]

Pacifici F., Chini M., Emery W.J., A neural network approach using multi-scale textural metrics from very high-resolution panchromatic imagery for urban land-use classification, Remote Sensing of Environment, 113, 6, pp. 1276-1292, (2009)

[3]

Huang X., Zhang L., An SVM ensemble approach combining spectral, structural, and semantic features for the classification of highresolution remotely sensed imagery, IEEE Transactions on Geoscience and Remote Sensing, 51, 1, pp. 257-272, (2013)

[4]

Liu C., Hong L., Chen J., Et al., Fusion of pixel-based and multi-scale region-based features for the classification of high-resolution remote sensing image, Journal of Remote Sensing, 19, 2, pp. 228-239, (2015)

[5]

Bengio Y., Learning deep architectures for AI, Foundations and Trends in Machine Learning, 2, 1, pp. 1-127, (2009)

[6]

Bottou L., Large-scale Kjernel Machines, pp. 321-359, (2007)

[7]

Hinton G.E., Salakhutdinov R.R., Reducing the dimensionality of data with neural networks, Science, 313, 5786, pp. 504-507, (2006)

[8]

Yu D., Deng L., Deep learning and its applications to signal and information processing, IEEE Signal Processing Magazine, 28, 1, pp. 145-154, (2011)

[9]

Jones N., The learning machines, Nature, 505, 7842, pp. 146-148, (2014)

[10]

Yu K., Jia L., Chen Y., Et al., Deep learning: Yesterday, today and tomorrow, Journal of Computer Research and Development, 50, 9, pp. 1799-1804, (2013)

← 1 2 3 →