Discriminative sparse representations in hyperspectral imagery

Castrodad, Alexey; Xing, Zhengming; Greer, John B.; Bosch, Edward H.; Carin, Lawrence; Sapiro, Guillermo

doi:10.1109/icip.2010.5651568

Cited by 18 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hyperspectral images, meaning those that provide a dense spectral sampling at each pixel, have proven useful in many domains, including remote sensing [2,3,5,22,35], medical diagnosis [10,29,33], and biometrics [31], and it seems likely that they can simplify the analysis of everyday scenes as well.…”

Section: Introductionmentioning

confidence: 99%

Statistics of real-world hyperspectral images

2011

View full text Add to dashboard Cite

Hyperspectral images provide higher spectral resolution than typical RGB images by including per-pixel irradiance measurements in a number of narrow bands of wavelength in the visible spectrum. The additional spectral resolution may be useful for many visual tasks, including segmentation, recognition, and relighting. Vision systems that seek to capture and exploit hyperspectral data should benefit from statistical models of natural hyperspectral images, but at present, relatively little is known about their structure. Using a new collection of fifty hyperspectral images of indoor and outdoor scenes, we derive an optimized "spatio-spectral basis" for representing hyperspectral image patches, and explore statistical models for the coefficients in this basis.

show abstract

Section: Introductionmentioning

confidence: 99%

Statistics of real-world hyperspectral images

2011

View full text Add to dashboard Cite

show abstract

“…In [15], the authors applied a sparse framework for HSI classification and subsequently exploited sparsity for the classification task in a graphical model [16], [17] and a kernel space [18], [19]. There are a number of additional works that invoke sparse representation specifically for HSI classification-for example, [20] adopted sparse representation in the special case that very few labeled training samples are available; [21] considered discriminative sparse representation; while [22] introduced sparse representation in semisupervised learning.…”

Section: Introductionmentioning

confidence: 99%

Nearest Regularized Subspace for Hyperspectral Classification

Tramel

Prasad

et al. 2014

IEEE Trans. Geosci. Remote Sensing

218

View full text Add to dashboard Cite

Abstract-A classifier that couples nearest-subspace classification with a distance-weighted Tikhonov regularization is proposed for hyperspectral imagery. The resulting nearest-regularizedsubspace classifier seeks an approximation of each testing sample via a linear combination of training samples within each class. The class label is then derived according to the class which best approximates the test sample. The distance-weighted Tikhonov regularization is then modified by measuring distance within a locality-preserving lower-dimensional subspace. Furthermore, a competitive process among the classes is proposed to simplify parameter tuning. Classification results for several hyperspectral image data sets demonstrate superior performance of the proposed approach when compared to other, more traditional classification techniques.

show abstract

“…There are a number of ways to solve this problem, but a common way is to use an alternating set of convex minimization problems, first solving for the dictionary D, and then doing SC to obtain the α abundance vector [5], [6]. This iteration continues until convergence on a final dictionary and set of abundance vectors.…”

Section: Dictionary Learningmentioning

confidence: 98%

A framework for dictionary learning based hyperspectral pixel classification

Pound

Gunther

Moon

et al. 2012

2012 Conference Record of the Forty Sixth Asilomar Conference on Signals, Systems and Computers (ASILOMAR)

View full text Add to dashboard Cite

This paper explores the utility of using dictionary learning as a preprocessing stage in the data reduction of hyperspectral data for the express purpose of improving detection and classification of materials. This paper sets up the general framework, and discusses some of the preliminary research from pairing a random forest classifier with dictionary learning. I. HYPERSPECTRAL DATAHyperspectral imaging (HSI) is the process of measuring or collecting an image across hundreds of spectral bands. This high spectral sample density warrants calling this a spectrum. Because of the nature of the sensor, HSI data forms a cube with the normal spatial dimensions and a third, spectral dimension. An example that demonstrates the idea of an HSI cube is in Fig 1.Fig. 1. A representation of a hyperspectral cube, illustrating both the spatial dimensions and the spectral dimension.The high spectral content of each pixel in an HSI cube can provide sufficient information to be able to classify materials based on their spectral signatures. Because of This work was supported by the Department of Energy under Grant No. this, it is used in many different fields including atmospheric sciences, geological surveys, medical imaging, and defense efforts. II. LINEAR MIXING MODELHSI pixels are commonly modeled using a linear mixing model, that is, each measured pixel x is a linear combination of some spectra from the constituent materials that are present in that pixel. Mathematically, this iswhere n is an AWGN noise vector, M is made up of spectral signatures of materials, and a provides the amounts corresponding to the contribution of each material to the pixel x. This linear mixing model is almost universally used in unmixing hyperspectral data. As an example of where the linearity is discussed in detail see [1] and references therein. III. PHYSICAL REALITIESGiven high enough spatial resolution, the assumption can be made that each pixel is a linear combination of only a few materials. For example, if each pixel corresponds to a 30 meter square on the ground, then there is the possibility of numerous different materials; whereas with a ground resolution of 1 meter then there are most likely only a few materials comprising a single pixel. If, in conjunction with high resolution, the given library M of spectra contains a large number of materials, probably more than would normally be present in any given scene, then the a in the linear mixing model is most likely very sparse, usually with only a few components that are nonzero. Thus it can be assumed that x = k a k m k , k ∈ K = {i|a i = 0}, |K| dim(a).

show abstract

Discriminative sparse representations in hyperspectral imagery

Cited by 18 publications

References 13 publications

Statistics of real-world hyperspectral images

Statistics of real-world hyperspectral images

Nearest Regularized Subspace for Hyperspectral Classification

A framework for dictionary learning based hyperspectral pixel classification

Contact Info

Product

Resources

About