Online deconvolution for pushbroom hyperspectral imaging systems

This paper introduces a framework based on the LMS algorithm for sequential deconvolution of hyperspectral images acquired by industrial pushbroom imaging systems. Considering a sequential model of image blurring phenomenon, we derive a sliding-block zero-attracting LMS algorithm with spectral regularization. The role of each hyper-parameter is discussed. The performance of the algorithm is evaluated using real hyperspectral data.

[1]  Nikolas P. Galatsanos,et al.  Least squares restoration of multichannel images , 1991, IEEE Trans. Signal Process..

[2]  Miran Bürmen,et al.  Deconvolution-based restoration of SWIR pushbroom imaging spectrometer images. , 2016, Optics express.

[3]  David Mary,et al.  Blind and Fully Constrained Unmixing of Hyperspectral Images , 2014, IEEE Transactions on Image Processing.

[4]  Richard G. Baraniuk,et al.  Sparsity and Structure in Hyperspectral Imaging : Sensing, Reconstruction, and Target Detection , 2014, IEEE Signal Processing Magazine.

[5]  Claude Cariou,et al.  Automatic Georeferencing of Airborne Pushbroom Scanner Images With Missing Ancillary Data Using Mutual Information , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[6]  Petra Tatzer,et al.  Industrial application for inline material sorting using hyperspectral imaging in the NIR range , 2005, Real Time Imaging.

[7]  Nikolas P. Galatsanos,et al.  Digital restoration of multichannel images , 1989, IEEE Trans. Acoust. Speech Signal Process..

[8]  J. Giovannelli,et al.  Positive deconvolution for superimposed extended source and point sources , 2005, astro-ph/0507691.

[9]  Bosoon Park,et al.  Transportable Spectrophotometer System for On-Line Classification of Poultry Carcasses , 1996 .

[10]  Dongrong Xu,et al.  Review of spectral imaging technology in biomedical engineering: achievements and challenges , 2013, Journal of biomedical optics.

[11]  Miran Bürmen,et al.  Push-broom hyperspectral image calibration and enhancement by 2D deconvolution with a variant response function estimate. , 2014, Optics express.

[12]  Charles Soussen,et al.  Fast Positive Deconvolution of Hyperspectral Images , 2013, IEEE Transactions on Image Processing.

[13]  Jie Chen,et al.  Nonnegative Least-Mean-Square Algorithm , 2011, IEEE Transactions on Signal Processing.

[14]  Michael K. Ng,et al.  Deblurring and Sparse Unmixing for Hyperspectral Images , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[15]  Jie Chen,et al.  Nonlinear Unmixing of Hyperspectral Data Based on a Linear-Mixture/Nonlinear-Fluctuation Model , 2013, IEEE Transactions on Signal Processing.

[16]  Michael Elad,et al.  Superresolution restoration of an image sequence: adaptive filtering approach , 1999, IEEE Trans. Image Process..

[17]  Sheng Zhang,et al.  Transient analysis of zero attracting NLMS algorithm without Gaussian inputs assumption , 2014, Signal Process..

[18]  B. R. Hunt,et al.  Karhunen-Loeve multispectral image restoration, part I: Theory , 1984 .

[19]  S. Thomas Alexander,et al.  Adaptive Signal Processing , 1986, Texts and Monographs in Computer Science.

[20]  Li Liu,et al.  Recent Developments in Hyperspectral Imaging for Assessment of Food Quality and Safety , 2014, Sensors.

[21]  El-Hadi Djermoune,et al.  Regularization Parameter Estimation for Non-Negative Hyperspectral Image Deconvolution , 2016, IEEE Transactions on Image Processing.

[22]  A. Hero,et al.  Regularized Least-Mean-Square Algorithms , 2010, 1012.5066.

[23]  José Carlos M. Bermudez,et al.  Statistical Analysis of the LMS Algorithm Applied to Super-Resolution Image Reconstruction , 2006, IEEE Transactions on Signal Processing.