A Bayesian approach to visualization-oriented hyperspectral image fusion

In this paper, we propose a Bayesian approach towards fusion of hyperspectral images for the purpose of efficient visualization. Fusion has been posed as an estimation problem where the observed hyperspectral bands have been related to the fused image through a first order model of image formation. The parameters of the model indicate the quality of the pixel captured locally. As visualization is our primary aim of fusion, we expect higher contribution of the ''visually important'' pixels towards the final fused image. We propose a two-step framework for fusion of hyperspectral image, where the first step identifies the quality of each pixel of the data based on some of the local quality measures of the hyperspectral data. Subsequently, we formulate the problem of the estimation of the fused image in a MAP framework. We incorporate the total variation (TV) norm-based prior which preserves the sharp discontinuities in the fused image. The fused images, thus, appear sharp and natural where the edges and boundaries have been retained. We have provided visual as well as quantitative results to substantiate the effectiveness of the proposed technique.

[1]  Christine Pohl,et al.  Multisensor image fusion in remote sensing: concepts, methods and applications , 1998 .

[2]  Robert A. Schowengerdt,et al.  Remote sensing, models, and methods for image processing , 1997 .

[3]  Gene H. Golub,et al.  A Nonlinear Primal-Dual Method for Total Variation-Based Image Restoration , 1999, SIAM J. Sci. Comput..

[4]  Steven K. Rogers,et al.  Perceptual-based image fusion for hyperspectral data , 1997, IEEE Trans. Geosci. Remote. Sens..

[5]  E. M. Winter,et al.  Anomaly detection from hyperspectral imagery , 2002, IEEE Signal Process. Mag..

[6]  Tuan Vo-Dinh,et al.  A hyperspectral imaging system for in vivo optical diagnostics. Hyperspectral imaging basic principles, instrumental systems, and applications of biomedical interest. , 2004, IEEE engineering in medicine and biology magazine : the quarterly magazine of the Engineering in Medicine & Biology Society.

[7]  C. Ramesh,et al.  Fusion performance measures and a lifting wavelet transform based algorithm for image fusion , 2002, Proceedings of the Fifth International Conference on Information Fusion. FUSION 2002. (IEEE Cat.No.02EX5997).

[8]  Michael Elad,et al.  Fast and robust multiframe super resolution , 2004, IEEE Transactions on Image Processing.

[9]  Mrityunjay Kumar,et al.  A Total Variation-Based Algorithm for Pixel-Level Image Fusion , 2009, IEEE Transactions on Image Processing.

[10]  Robert A. Schowengerdt,et al.  Remote Sensing, Third Edition: Models and Methods for Image Processing , 2006 .

[11]  Stanley Osher,et al.  Image Decomposition and Restoration Using Total Variation Minimization and the H1 , 2003, Multiscale Model. Simul..

[12]  Subhasis Chaudhuri,et al.  Visualization of Hyperspectral Images Using Bilateral Filtering , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[13]  Pramod K. Varshney,et al.  An Image Fusion Approach Based on Markov Random Fields , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[14]  P. Wintz,et al.  Information Extraction, SNR Improvement, and Data Compression in Multispectral Imagery , 1973, IEEE Trans. Commun..

[15]  Pramod K. Varshney,et al.  A novel approach for image fusion based on Markov Random Fields , 2008, 2008 42nd Annual Conference on Information Sciences and Systems.

[16]  Subhasis Chaudhuri,et al.  An Optimization-Based Approach to Fusion of Hyperspectral Images , 2012, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[17]  Jan Kautz,et al.  Exposure Fusion , 2007 .

[18]  G. Qu,et al.  Information measure for performance of image fusion , 2002 .

[19]  Peter Wonka,et al.  Interactive Hyperspectral Image Visualization Using Convex Optimization , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[20]  George A. Lampropoulos,et al.  Fusion of hyperspectral data using segmented PCT for color representation and classification , 2005, IEEE Transactions on Geoscience and Remote Sensing.

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

[22]  Rick S. Blum,et al.  A statistical signal processing approach to image fusion for concealed weapon detection , 2002, Proceedings. International Conference on Image Processing.

[23]  B. Guo,et al.  Hyperspectral image fusion using spectrally weighted kernels , 2005, 2005 7th International Conference on Information Fusion.

[24]  Subhasis Chaudhuri,et al.  A novel approach to quantitative evaluation of hyperspectral image fusion techniques , 2013, Inf. Fusion.

[25]  Begüm Demir,et al.  A Low-Complexity Approach for the Color Display of Hyperspectral Remote-Sensing Images Using One-Bit-Transform-Based Band Selection , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[26]  Ravi K. Sharma,et al.  Probabilistic Image Sensor Fusion , 1998, NIPS.

[27]  Maya R. Gupta,et al.  Linear Fusion of Image Sets for Display , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[28]  Stavri G. Nikolov,et al.  Image fusion: Advances in the state of the art , 2007, Inf. Fusion.

[29]  Fadil Santosa,et al.  Recovery of Blocky Images from Noisy and Blurred Data , 1996, SIAM J. Appl. Math..

[30]  Pramod K. Varshney,et al.  Evaluation of ICA based fusion of hyperspectral images for color display , 2007, 2007 10th International Conference on Information Fusion.

[31]  P. Lions,et al.  Image recovery via total variation minimization and related problems , 1997 .

[32]  Elizabeth Pattey,et al.  Impact of nitrogen and environmental conditions on corn as detected by hyperspectral reflectance , 2002 .

[33]  Chein-I Chang,et al.  Automatic spectral target recognition in hyperspectral imagery , 2003 .

[34]  J. Scott Tyo,et al.  Principal-components-based display strategy for spectral imagery , 2003, IEEE Trans. Geosci. Remote. Sens..

[35]  Alexandre Jouan,et al.  Land use mapping with evidential fusion of features extracted from polarimetric synthetic aperture radar and hyperspectral imagery , 2004, Inf. Fusion.