• Corpus ID: 207871101

Spatial Sparse subspace clustering for Compressive Spectral imaging

@article{Zhu2019SpatialSS,
  title={Spatial Sparse subspace clustering for Compressive Spectral imaging},
  author={Jianchen Zhu and Tong Zhang and Shengjie Zhao and Carlos Hinojosa and Zengli Liu and Gonzalo R. Arce},
  journal={ArXiv},
  year={2019},
  volume={abs/1911.01671}
}
This paper aims at developing a clustering approach with spectral images directly from CASSI compressive measurements. The proposed clustering method first assumes that compressed measurements lie in the union of multiple low-dimensional subspaces. Therefore, sparse subspace clustering (SSC) is an unsupervised method that assigns compressed measurements to their respective subspaces. In addition, a 3D spatial regularizer is added into the SSC problem, thus taking full advantages of the spatial… 

References

SHOWING 1-10 OF 15 REFERENCES
Spectral–Spatial Sparse Subspace Clustering for Hyperspectral Remote Sensing Images
TLDR
A novel spectral-spatial sparse subspace clustering S4C algorithm for hyperspectral remote sensing images is proposed by treating each kind of land-cover class as a subspace and considering the spectral and spatial properties of HSIs.
Hyperspectral Blind Reconstruction From Random Spectral Projections
  • G. Martín, J. Bioucas-Dias
  • Computer Science
    IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • 2016
TLDR
Spatial compressive acquisition conceived to spaceborne sensors systems which are characterized by scarce onboard computing and storage resources and by communication links with reduced bandwidth achieves perfect reconstruction in noise-free hyperspectral images (HSIs) and is very competitive in noisy data.
Higher-order computational model for coded aperture spectral imaging.
TLDR
This paper develops a higher-order precision model for the optical sensing in CASSI that includes a more accurate discretization of the underlying signals, leading to image reconstructions less dependent on calibration.
Restricted Isometry Property in coded aperture compressive spectral imaging
  • Henry Arguello, G. Arce
  • Computer Science, Mathematics
    2012 IEEE Statistical Signal Processing Workshop (SSP)
  • 2012
TLDR
The Restricted Isometry Property (RIP) for the projection matrices used in CASSI provides guidelines for the minimum number of FPA measurement shots needed for image reconstruction and provides the optimal transmittance parameters for the set of code apertures used in the acquisition process.
Sparse Subspace Clustering: Algorithm, Theory, and Applications.
TLDR
An algorithm to cluster high-dimensional data points that lie in a union of low-dimensional subspaces is proposed and studied, which does not require initialization, can be solved efficiently, and can handle data points near the intersections of subspace.
Colored Coded Aperture Design by Concentration of Measure in Compressive Spectral Imaging
TLDR
The colored coded apertures are optimized such that the number of projections is minimized while the quality of reconstruction is maximized and better satisfy the restricted isometry property in CASSI.
Spectral Unmixing of Hyperspectral Imagery Using Multilayer NMF
TLDR
Results in comparison with previously proposed methods show that the multilayer approach can unmix data more effectively.
Computational Snapshot Multispectral Cameras: Toward dynamic capture of the spectral world
TLDR
It is proposed that undersampling-based multispectral cameras can be understood and compared by examining the efficiency of their sampling schemes, which are formulated as the spectral sensing coherence information between their sensing matrices and spectrum-specific bases learned from a large-scale multisectral image database.
Adaptive total variation-based spectral deconvolution with the split Bregman method.
TLDR
Simulated and real spectra experiments manifest that this algorithm can satisfactorily recover the overlap peaks as well as suppress noise and are robust to the regularization parameter.
Single disperser design for coded aperture snapshot spectral imaging.
TLDR
A single disperser spectral imager is presented that exploits recent theoretical work in the area of compressed sensing to achieve snapshot spectral imaging and can be used to capture spatiospectral information of a scene that consists of two balls illuminated by different light sources.
...
1
2
...