Accuracy assessment of blind and semi-blind restoration methods for hyperspectral images

M. Zhang (1) , B. Vozel (1) , K. Chehdi (1) , M. Uss (2) , S. Abramov (2) , V. Lukin (2)

1 IETR - Institut d'Électronique et des Technologies du numéRique
2 Kharkov National University

Hyperspectral images acquired by remote sensing systems are generally degraded by noise and can be sometimes more severely degraded by blur. When no knowledge is available about the degradations present or the original image, blind restoration methods must be considered. Otherwise, when a partial information is needed, semi-blind restoration methods can be considered. Numerous semi-blind and quite advanced methods are available in the literature. So to get better insights and feedback on the applicability and potential efficiency of a representative set of four semi-blind methods recently proposed, we have performed a comparative study of these methods in objective terms of blur filter and original image error estimation accuracy. In particular, we have paid special attention to the accurate recovering in the spectral dimension of original spectral signatures. We have analyzed peculiarities and factors restricting the applicability of these methods. Our tests are performed on a synthetic hyperspectral image, degraded with various synthetic blurs (out-of-focus, gaussian, motion) and with signal independent noise of typical levels such as those encountered in real hyperspectral images. This synthetic image has been built from various samples from classified areas of a real-life hyperspectral image, in order to benefit from realistic reference spectral signatures to recover after synthetic degradation. Conclusions, practical recommendations and perspectives are drawn from the results experimentally obtained.

Keywords: Additive noise; Constrained optimization; Image reconstruction; Independent component analysis; Optimization; Remote sensing; Restoration; Signal processing; Spectroscopy; Alternating direction method of multipliers; Alternating minimization; Augmented Lagrangians; Regularization parameters; Remote sensing images; Semi-blind; Sparse distribution; Stopping criteria; Total variation; Image processing; remote sensing images; additive noise; semi-blind image restoration; sparse distribution; alternating minimization; regularization parameter; augmented Lagrangian; alternating direction method of multipliers (ADMM); total variation; stopping criteria

Domains: Computer Science [cs]; Networking and Internet Architecture [cs.NI]; Engineering Sciences [physics]; Electronics

M. Zhang, B. Vozel, K. Chehdi, M. Uss, S. Abramov, et al.. Accuracy assessment of blind and semi-blind restoration methods for hyperspectral images. Image and Signal Processing for Remote Sensing XXII, Sep 2016, Edinburgh, United Kingdom. ⟨10.1117/12.2240950⟩. ⟨hal-01484534⟩