Combining Fourier Spectrum Texture and Spectral Information for Land Cover Classification with High Resolution Remote Sensing Images

DIAN Yuanyong; YANG Guang; FANG Shenghui

doi:10.13203/j.whugis20140952

Volume 42 Issue 3

Mar. 2017

Turn off MathJax

Article Contents

Abstract

References

Geomatics and Information Science of Wuhan University > 2017 > 42(3): 362-368. > DOI: 10.13203/j.whugis20140952

DIAN Yuanyong, YANG Guang, FANG Shenghui. Combining Fourier Spectrum Texture and Spectral Information for Land Cover Classification with High Resolution Remote Sensing Images[J]. Geomatics and Information Science of Wuhan University, 2017, 42(3): 362-368. DOI: 10.13203/j.whugis20140952

Citation:

PDF (5166 KB)

Combining Fourier Spectrum Texture and Spectral Information for Land Cover Classification with High Resolution Remote Sensing Images

1.
Institute of Garden Forestry, Huazhong Agriculture University, Wuhan 430070, China
2.
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China

Funds:

The National High Technology Research and Development Program of China (863 Program) 2012AA12A304

The National High Technology Research and Development Program of China (863 Program) 2013AA102401

the Fundamental Research Funds for the Central Universities 2014QC018

the Open Fund of Major Laboratory Program of Geography National Condition Monitoring National Administration of Surveying, Mapping and Geo-information 2013NGC05

More Information

Author Bio:
DIAN Yuanyong, PhD, specializes in remote sensing technology on resource environment. E-mail:dianyuanyong@126.com
Received Date: October 22, 2015
Published Date: March 04, 2017

Graphical Abstract

Abstract

Abstract

The extraction of textural features gives more information in many pattern recognition issues. The textural features are widely exploited in the classification problems. In this study, the high resolution images were employed as the research object.Textural features and spectral features were combined to solve the problems of land cover classification. The paper designed a classification strategy based on Fourier spectrum texture. The spectral image was submitted to the principal components analysis (PCA) and r-spectrum was extracted from the first two principal components as the textural features. The common power spectrum might be insufficient because of the lack of the feature number. However, it would bring redundancy when taking into account each sample spectrum associated with each frequency. In fact, it could be divided and quantified flexibly. Consequently, new features were yielded through the method. In this study, different scenarios associated with different input features were designed. Support vector machine (SVM) was employed as the classifier. The algorithm was tested on hyperspectral dataset acquired in Salinas area and QuickBird images acquired in Jiufeng area. Results showed that the combination of textural features and spectral features could obviously improve the accuracy; the textural features extracted by Fourier r-spectrum could be applied well to the classification problems of high resolution remote sensing images; the classification accuracy was higher than the one that is based on the whole sample spectrum and the commongray-level co-occurrence matrix (GLCM); it was suitable to move the window pixel by pixel when extracting the textural features; adaptive weight would better deal with the problems of multiple features; the textural features extracted from the first and second principle components had complementary properties. In addition, the extraction of textural information from multi-feature pictures was superior to single feature picture.
- high resolution,
- r-spectrum,
- textural feature,
- principal component analysis

FullText(HTML)

References (20)

References

[1]	万幼川, 宋杨.基于高分辨率遥感影像分类的地图更新方法[J].武汉大学学报·信息科学版, 2005, 30(2):105-109 http://ch.whu.edu.cn/CN/Y2005/V30/I2/105 Wan Youchuan, Song Yang. Application of Maps Revision Based on Classification of High Resolution Satellite Images[J]. Geomatics and Information Science of Wuhan University, 2005, 30(2):105-109 http://ch.whu.edu.cn/CN/Y2005/V30/I2/105
[2]	Hanta-Kasari M, Parkkinen J, Jaaskelainen T, et al. Generalized Co-occurrence Matrix for Multispectral Texture Analysis[C]. The 13th International Conference on Pattern Recognition, Piscataway, USA, 1996
[3]	Wang Keqi, Bai Xuebing. Classification of Wood Surface Texture Based on Gauss-MRF Model[J]. Journal of Forestry Research, 2006, 17(1): 57-61 doi: 10.1007/s11676-006-0014-4
[4]	Kumaresan R. Spectral Analysis[M]. Boca Raton, USA: CNC Press, 1993:1 143-1 169
[5]	Fanelli A, Leo A, Ferri M. Remote Sensing Images Data Fusion: A Wavelet Transform Approach for Urban Analysis[C]. IEEE/ISPRS Joint Workshop on Remote Sensing and Data Fusion over Urban Areas, Piscataway, USA, 2002
[6]	Mugglestone M A, Renshaw E. Detection of Geological Lineations on Aerial Photographs Using Two-dimensional Spectral Analysis[J]. Computers & Geosciences, 1998, 24(8): 771-784 https://www.researchgate.net/publication/229351297_Detection_of_geological_lineations_on_aerial_photographs_using_two-dimensional_spectral_analysis
[7]	Couteron P. Quantifying Change in Patterned Semi-arid Vegetation by Fourier Analysis of Digitised Aerial Photographs[J]. International Journal of Remote Sensing, 2002, 23(17):3 407-3 425 doi: 10.1080/01431160110107699
[8]	Proisy C, Couteron P, Fromard F. Predicting and Mapping Mangrove Biomass from Canopy Grain Analysis Using Fourier-based Ordination of IKONOS Images[J]. Remote Sensing of Environment, 2007, 109(3):379-392 doi: 10.1016/j.rse.2007.01.009
[9]	Proisy C, Mougin E, Fromard F, et al. On the Influence of Canopy Structure on the Polarimetric Radar Response from Mangrove Forest[J]. International Journal of Remote Sensing, 2002, 23(20):4 197-4 210 doi: 10.1080/01431160110107725
[10]	于浩, 齐志红, 张晓萍, 等.基于傅里叶变换的梯田纹理特征提取[J].国土资源遥感, 2008, 20(2): 39-41 http://www.cnki.com.cn/Article/CJFDTOTAL-GTYG200802009.htm Yu Hao, Qi Zhihong, Zhang Xiaoping, et al. Extraction of Terraced Field Texture Features Based on Fourier Transformation[J]. Remote Sensing for Land and Resources, 2008, 20(2): 39-41 http://www.cnki.com.cn/Article/CJFDTOTAL-GTYG200802009.htm
[11]	王焕平, 刘勇.基于窗口傅里叶变换功率谱分析的盐田地区高分辨率遥感影像分割分类方法探讨[J].遥感技术与应用, 2011, 26(2):233-238 http://www.cnki.com.cn/Article/CJFDTOTAL-YGJS201102016.htm Wang Huanping, Liu Yong. The Study on Classification of High Resolution Remote Sensing Image in Saline Area Based on Window Fourier Transform Power Spectrum Analysis[J]. Remote Sensing Technology and Application, 2011, 26(2):233-238 http://www.cnki.com.cn/Article/CJFDTOTAL-YGJS201102016.htm
[12]	Zhang Lefei, Zhang Liangpei, Tao Dacheng. On Combining Multiple Features for Hyperspectral Remote Sensing Image Classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2012, 50(3):879-893 doi: 10.1109/TGRS.2011.2162339
[13]	Tang Xiaoou, Stewart W K. Optical and Sonar Image Classification: Wavelet Packet Transform vs Fourier Transform[J]. Computer Vision and Image Understanding, 2000, 79(1): 25-46 doi: 10.1006/cviu.2000.0843
[14]	Couteron P. Textural Ordination Based on Fourier Spectral Decomposition: A Method to Analyze and Compare Landscape Patterns[J]. Landscape Ecology, 2006, 21(4):555-567 doi: 10.1007/s10980-005-2166-6
[15]	Cortes C, Vapnik V. Support Vector Networks[J]. Machine Learning, 1995, 20(3): 273-297
[16]	Vapnik V. Statistical Learning Theory[M]. New York: Springer Press, 1998: 732-739
[17]	Vapnik V, Levin E. Measuring the VC Dimension of a Learning Machirie[J]. Neural Computation, 1994, 6(5):811-876
[18]	Sontag E. VC Dimension of Neural Networks[M]. New York: Springer Press, 1998
[19]	Stone M. Cross-validatory Choice and Assessment of Statistical Predictions[J]. Journal of Royal Statistical Soc (Series B), 1974, 36(2):111-147 http://www.oalib.com/references/5177921
[20]	Tenenbaum J, Silva V, Langford J. A Global Geometric Framework for Nonlinear Dimensionality Reduction[J]. Science, 2000, 290(5 500):2 319-2 323 doi: 10.1126/science.290.5500.2319

Cited By

Get Citation

PDF

XML

Article views (1625) PDF downloads (540)

Combining Fourier Spectrum Texture and Spectral Information for Land Cover Classification with High Resolution Remote Sensing Images

Abstract

References

Catalog

Related

Combining Fourier Spectrum Texture and Spectral Information for Land Cover Classification with High Resolution Remote Sensing Images

Abstract

References

Catalog

Related

Export File

Citation

Format

Content