Neural network hyperspectral unmixing with spectral information divergence objective

Hyperspectral unmixing is a challenging inverse problem that involves determining the fractional abundances of the representive material (endmembers) in each pixel. In this paper, we develop a neural network autoencoder, that dynamically exploits the sparsity of the abundances and enforces the abundance sum constraint (ASC) for hyperspectral unmixing. Instead of using the conventional mean square error (MSE) objective function, we use the spectral information divergence (SID) measure. Experiments are performed using a real hyperspectral dataset and we compare results obtained using both MSE and SID. It is demonstrated by qualitative inspection that using SID gives significantly better results than using MSE.

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

[2]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[3]  Fabio Del Frate,et al.  Pixel Unmixing in Hyperspectral Data by Means of Neural Networks , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[4]  S. Kullback,et al.  Information Theory and Statistics , 1959 .

[5]  L. Rudin,et al.  Nonlinear total variation based noise removal algorithms , 1992 .

[6]  Ian T. Jolliffe,et al.  Principal Component Analysis , 2002, International Encyclopedia of Statistical Science.

[7]  Jin Chen,et al.  Generalization of Subpixel Analysis for Hyperspectral Data With Flexibility in Spectral Similarity Measures , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[8]  Chein-I. Chang Spectral information divergence for hyperspectral image analysis , 1999, IEEE 1999 International Geoscience and Remote Sensing Symposium. IGARSS'99 (Cat. No.99CH36293).

[9]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[10]  Antonio J. Plaza,et al.  Hyperspectral Unmixing Overview: Geometrical, Statistical, and Sparse Regression-Based Approaches , 2012, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[11]  Johannes R. Sveinsson,et al.  Blind Hyperspectral Unmixing Using Total Variation and $\ell_q$ Sparse Regularization , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[12]  Rui Guo,et al.  Hyperspectral image unmixing using autoencoder cascade , 2015, 2015 7th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS).

[13]  Antonio J. Plaza,et al.  Collaborative Sparse Regression for Hyperspectral Unmixing , 2014, IEEE Transactions on Geoscience and Remote Sensing.