A new scheme for decomposition of mixed pixels based on nonnegative matrix factorization

The simplex-based methods are a kind of the most important and widely used methods for the decomposition of mixed pixels in multispectral and hyperspectral remote sensing images, which need a strong basic hypothesis that there is at least one pure pixel for every endmember existing in the images. N- FINDR is of typical sense in this kind of methods, and it also needs this basic hypothesis. Unfortunately, the precision for the decomposition of mixed pixels will be seriously influenced if this hypothesis cannot be met in practice. This paper presents a new scheme based on Nonnegative Matrix Factorization (NMF) to solve this problem. In addition, some appropriate constrains are introduced into NMF for the decomposition of mixed pixels. Experimental results obtained from both artificial simulated and real-world remote sensing data demonstrate that the proposed scheme for decomposition of mixed pixels has excellent analytical performance.

[1]  Chein-I Chang,et al.  Multispectral and hyperspectral image analysis with convex cones , 1999, IEEE Trans. Geosci. Remote. Sens..

[2]  José M. Bioucas-Dias,et al.  Vertex component analysis: a fast algorithm to unmix hyperspectral data , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[3]  H. Sebastian Seung,et al.  Learning the parts of objects by non-negative matrix factorization , 1999, Nature.

[4]  E. Oja,et al.  Independent Component Analysis , 2001 .

[5]  Mario Winter,et al.  N-FINDR: an algorithm for fast autonomous spectral end-member determination in hyperspectral data , 1999, Optics & Photonics.

[6]  Michael L. Mavrovouniotis,et al.  Convex-Cone Classification of Pyrolysis Mass Spectra of Biological Agents , 1994 .

[7]  Chein-I Chang,et al.  Estimation of subpixel target size for remotely sensed imagery , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[8]  Qian Du,et al.  An interference rejection-based radial basis function neural network for hyperspectral image classification , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[9]  H. Sebastian Seung,et al.  Algorithms for Non-negative Matrix Factorization , 2000, NIPS.

[10]  M. Daigo,et al.  Pattern decomposition method in the albedo space for Landsat TM and MSS data analysis , 2000 .

[11]  Mark L. G. Althouse,et al.  Least squares subspace projection approach to mixed pixel classification for hyperspectral images , 1998, IEEE Trans. Geosci. Remote. Sens..

[12]  P. D. Heermann,et al.  Classification of multispectral remote sensing data using a back-propagation neural network , 1992, IEEE Trans. Geosci. Remote. Sens..

[13]  J. Boardman.  Automating spectral unmixing of AVIRIS data using convex geometry concepts , 1993 .

[14]  Bicheng Li,et al.  A remote sensing image classification method based on evidence theory and neural networks , 2003, International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003.

[15]  J. Boardman,et al.  Mapping target signatures via partial unmixing of AVIRIS data: in Summaries , 1995 .