Spectrum and Spatial Invariant Based Remote Sensing Image Classification

Abstract:

Multispectral remote sensing images are used as research objects for different band images are highly complementary. Pixel is the basic element for image classification. Spectral information and two order invariant moments are proposed to describe pixel characteristics. The self-organizing feature map neural network is used to realize an unsupervised classification. A fringe area of Qingdao is studied and its classification map is obtained using this method. Experimental results show that the classification accuracy is satisfactory by the proposed method.

• Periodical: Applied Mechanics and Materials (Volumes 263-266)
• Pages: 905-908
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.263-266.905
• Online since: December 2012
• Authors: Jin Mei Liu, Zhong Wei Li, Guo Yu Wang
• Keywords: Invariant Moment, Remote Sensing Image Classification, Spectrum

References

[1] G. Cakir, F. Sivrikaya, S. Keles, Forest cover change and fragmentation using Landsat data in Maçka state forest enterprise in Turkey, Environ Monit Assess. 137 (2008):51-66.

DOI: 10.1007/s10661-007-9728-9

[2] S. Andre´fouet, M. Guzman, Distribution, Status and geomorphology-biodiversity relationship in Kuna Yala (San Blas) Archipelago, Caribbean Panama, Coral Reefs. 24 (2005) 31-42.

DOI: 10.1007/s00338-004-0444-4

[3] P. H. Gowda, L. Chavez , D. Colaizzi, R. Evett, A. Howell, ET mapping for agricultural water management: present status and challenges, Irrigate Science. 26 (2008) 223-237.

DOI: 10.1007/s00271-007-0088-6

[4] R. M. Haralick, K. Shanmugam, Texture features for image classification, IEEE Trans. on Sys, Man, and Cyb. 6 (1973) 610-621.

[5] S. W. Myint, Fractal approaches in texture analysis and classification of remotely sensed data: comparisons with spatial autocorrelation techniques and simple descriptive statistics, International Journal of Remote Sensing. 9(2003) 1925-1947.

DOI: 10.1080/01431160210155992

[6] T. Ojala, M. Pietikainen, T. Maenpaa, Multiresolution grayscale and rotation invariant texture classification with local binary patterns, IEEE Trans on Pattern Analysis and Machine Inteligence. 7 (2002) 971-986.

DOI: 10.1109/tpami.2002.1017623

[7] M.Guler, T. Yomralihoglu, S. Reis, Using landsat data to determine land use/land cover changes in Samsun, Turkey, Environ Monit Assess. 127 (2007) 155-167.

DOI: 10.1007/s10661-006-9270-1

[8] J. Zhang, Fully-fuzzy supervised classification of sub-urban land cover from remotely sensed imagery: statistical and artificial neural network approaches, International Journal of Remote Sensing. 4(2001) 615-628.

DOI: 10.1080/01431160050505883

[9] F. Melgani, L. Bruzzone, Classification of hyperspectral remote sensing images with support vector machines, IEEE Transactions on Geoscience and Remote Sensing. 8(2004) 1778-1790.

DOI: 10.1109/tgrs.2004.831865

[10] Z. Kato , J. Zerubia, M. Berthod, Unsupervised parallel image classification using Markovian models, Pattern Recognition. 32 (1999) 591-604.

DOI: 10.1016/s0031-3203(98)00104-6

[11] M.A.T. Figueiredo, A.K. Jain, Unsupervised learning of finite mixture models, IEEE Transactions on Pattern Analysis and Machine Intelligence. 3(2002) 1-16.

DOI: 10.1109/34.990138

[12] W.Cao, A remote sensing image fusion method based on PCA transform and wavelet packet transform, Proceedings of IEEE. 2(2003) 975-981.

DOI: 10.1109/icnnsp.2003.1280764

[13] T. Kohonen; E. Oja; O. Simula; A. Visa; J. Kangas, Engineering applications of the self-organizing map, Proceedings of IEEE. 84(1996) 1358-1384.

DOI: 10.1109/5.537105