Fusing Remote Sensing Images Using a Statistical Model

Abstract:

Enhance spectral fusion quality is the one of most significant targets in the field of remote sensing image fusion. In this paper, a statistical model based fusion method is proposed, which is the improved method for fusing remote sensing images on the basis of the framework of Principal Component Analysis(PCA) and wavelet decomposition-based image fusion. PCA is applied to the source images. In order to retain the entropy information of data, we select the principal component axes based on entropy contribution(ECA). The first entropy component and panchromatic image(PAN) are performed a multiresolution decompositon using wavelet transform. The low frequency subband fused by weighted aggregation approach and high frequency subband fused by statistical model. High resolution multispectral image is then obtained by an inverse wavelet and ECA transform. The experimental results demonstrate that the proposed method can retain the spectral information and spatial information in the fusion of PAN and multi-spectral image(MS).

• Periodical: Applied Mechanics and Materials (Volumes 263-266)
• Pages: 416-420
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.263-266.416
• Online since: December 2012
• Authors: Xiao Qing Luo*, Xiao Jun Wu
• Keywords: Entropy, Image Fusion, Principal Component Analysis (PCA), Remote Sensing, Wavelet

References

[1] T. M. Tu, S. C. Su, H. C. Shyu, and P. S. Huang. Information Fusion ，Vol. 2,No. 3,(2001),pp.177-186.

[2] Yesou H，Besnus Y，Polet Y． ISPRS Journal of Photogrammetry and Remote Sensing. Vol. 48,No. 5,(1993),pp.23-26．

[3] Shettigara V K. Photogrammetric Engineering and Remote Sensing , Vol. 58,No. 5,(1992),pp.561-567．

[4] B Aizzi, L Alparone, A Barducci, et al. Multispectral fusion of multisensor image data by the generalized Laplacian pyramid . In: Proceedings of Geoscience and Remote Sensing Symposium. New Jersey: IEEE Press, (1999).

DOI: 10.1109/igarss.1999.774572

[5] P.S. Chavez Jr., S.C. Sides, J.A. Anderson. Photogramm. Eng. Remote Sensing , Vol. 57,No. 3,(1991),pp.295-303.

[6] Li Shutao，James T Kwok. Information Fusion, Vol. 3,No. 1,(2002),pp.17-23.

[7] She Eryong, Wang Runsheng, Xu xuewen. Acta electronica sinica, Vol. 36,No. 3,(2008),pp.490-493.In Chinese

[8] Xia Youshen, Henry Leung, Eloi Bossé. IEEE Transactions on neural networks, Vol. 13,No. 2,(2002),pp.320-329.

[9] Robert Jenssen. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 32,No. 5,(2010),pp.847-860.

[10] Tian J，Chen J，Zhang C． Multispectral image fusion based on fractal features. Proceedings of SPIE．Bellingham; (2004).

[11] Xiaoqing Luo, Xiaojun Wu. Optical Engineering , Vol. 49,No. 4,(2010),pp.047006-13.