Reconstruction of Hyperspectral Imagery From Random Projections Using Multihypothesis Prediction

Reconstruction of hyperspectral imagery from spectral random projections is considered. Specifically, multiple predictions drawn for a pixel vector of interest are made from spatially neighboring pixel vectors within an initial non-predicted reconstruction. A two-phase hypothesis-generation procedure based on partitioning and merging of spectral bands according to the correlation coefficients between bands is proposed to fine-tune the hypotheses. The resulting prediction is used to generate a residual in the projection domain. This residual being typically more compressible than the original pixel vector leads to improved reconstruction quality. To appropriately weight the hypothesis predictions, a distance-weighted Tikhonov regularization to an ill-posed least-squares optimization is proposed. Experimental results demonstrate that the proposed reconstruction significantly outperforms alternative strategies not employing multihypothesis prediction.

[1]  Thomas S. Huang,et al.  Distributed Video Coding using Compressive Sampling , 2009, 2009 Picture Coding Symposium.

[2]  James E. Fowler,et al.  Residual Reconstruction for Block-Based Compressed Sensing of Video , 2011, 2011 Data Compression Conference.

[3]  Gary J. Sullivan,et al.  Multi-hypothesis motion compensation for low bit-rate video coding , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[4]  James E. Fowler,et al.  Compressive-Projection Principal Component Analysis , 2009, IEEE Transactions on Image Processing.

[5]  Chen Chen,et al.  Compressed-sensing recovery of images and video using multihypothesis predictions , 2011, 2011 Conference Record of the Forty Fifth Asilomar Conference on Signals, Systems and Computers (ASILOMAR).

[6]  James E. Fowler,et al.  Video Compressed Sensing with Multihypothesis , 2011, 2011 Data Compression Conference.

[7]  Paolo Gamba,et al.  A collection of data for urban area characterization , 2004, IGARSS 2004. 2004 IEEE International Geoscience and Remote Sensing Symposium.

[8]  M E Gehm,et al.  Single-shot compressive spectral imaging with a dual-disperser architecture. , 2007, Optics express.

[9]  Yonina C. Eldar,et al.  Reduce and Boost: Recovering Arbitrary Sets of Jointly Sparse Vectors , 2008, IEEE Transactions on Signal Processing.

[10]  Trac D. Tran,et al.  Distributed Compressed Video Sensing , 2009, 2009 43rd Annual Conference on Information Sciences and Systems.

[11]  Lei Zhang,et al.  Band-Subset-Based Clustering and Fusion for Hyperspectral Imagery Classification , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[12]  James E. Fowler,et al.  Block-Based Compressed Sensing of Images and Video , 2012, Found. Trends Signal Process..

[13]  Jon Atli Benediktsson,et al.  Spectral–Spatial Classification of Hyperspectral Imagery Based on Partitional Clustering Techniques , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[14]  David B. Dunson,et al.  Nonparametric Bayesian Dictionary Learning for Analysis of Noisy and Incomplete Images , 2012, IEEE Transactions on Image Processing.

[15]  J. Tropp.  Algorithms for simultaneous sparse approximation. Part II: Convex relaxation , 2006, Signal Process..

[16]  Massimo Fornasier,et al.  Recovery Algorithms for Vector-Valued Data with Joint Sparsity Constraints , 2008, SIAM J. Numer. Anal..

[17]  David B. Dunson,et al.  Multitask Compressive Sensing , 2009, IEEE Transactions on Signal Processing.

[18]  A. N. Tikhonov,et al.  Solutions of ill-posed problems , 1977 .

[19]  Joel A. Tropp,et al.  ALGORITHMS FOR SIMULTANEOUS SPARSE APPROXIMATION , 2006 .

[20]  Joel A. Tropp,et al.  Algorithms for simultaneous sparse approximation. Part I: Greedy pursuit , 2006, Signal Process..

[21]  David A. Landgrebe,et al.  Signal Theory Methods in Multispectral Remote Sensing , 2003 .

[22]  W. B. Johnson,et al.  Extensions of Lipschitz mappings into Hilbert space , 1984 .

[23]  B. Parlett.  The Symmetric Eigenvalue Problem , 1981 .

[24]  Dianne P. O'Leary,et al.  The Use of the L-Curve in the Regularization of Discrete Ill-Posed Problems , 1993, SIAM J. Sci. Comput..

[25]  Jong Chul Ye,et al.  Motion estimated and compensated compressed sensing dynamic magnetic resonance imaging: What we can learn from video compression techniques , 2010 .

[26]  Trac D. Tran,et al.  Hyperspectral Image Classification Using Dictionary-Based Sparse Representation , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[27]  Guillermo Sapiro,et al.  Dictionary Learning for Noisy and Incomplete Hyperspectral Images , 2012, SIAM J. Imaging Sci..

[28]  Qian Du,et al.  Segmented Principal Component Analysis for Parallel Compression of Hyperspectral Imagery , 2009, IEEE Geoscience and Remote Sensing Letters.

[29]  Rachel Ward,et al.  Compressed Sensing With Cross Validation , 2008, IEEE Transactions on Information Theory.

[30]  Qian Du,et al.  Reconstructions from Compressive Random Projections of Hyperspectral Imagery , 2011 .

[31]  E.J. Candes,et al.  An Introduction To Compressive Sampling , 2008, IEEE Signal Processing Magazine.

[32]  James E. Fowler,et al.  Classification and Reconstruction From Random Projections for Hyperspectral Imagery , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[33]  Bhaskar D. Rao,et al.  An Empirical Bayesian Strategy for Solving the Simultaneous Sparse Approximation Problem , 2007, IEEE Transactions on Signal Processing.

[34]  James E. Fowler,et al.  Decoder-side dimensionality determination for compressive-projection principal component analysis of hyperspectral data , 2011, 2011 18th IEEE International Conference on Image Processing.

[35]  Qian Du,et al.  Reconstruction From Random Projections of Hyperspectral Imagery With Spectral and Spatial Partitioning , 2013, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.