A collection of data for urban area characterization

Gamba, Paolo

doi:10.1109/igarss.2004.1368947

Cited by 101 publications

(39 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is divided into three classes, have 81 bands and a pixel size of 5.6m. The second dataset Pavia [7] is also from an airborne sensor (DAIS)ḑ epicting urban landcover pixels over Pavia, Italy. The dataset has 71 bands and 2.6m pixels.…”

Section: Resultsmentioning

confidence: 99%

Improving Hyperspectral Classifiers: The Difference Between Reducing Data Dimensionality and Reducing Classifier Parameter Complexity

Berge

Solberg

2007

Image Analysis

View full text Add to dashboard Cite

Abstract. Hyperspectral data is usually high dimensional, and there is often a scarcity of available ground truth pixels . Thus the task of applying even a simple classifier such as the Gaussian Maximum Likelihood (GML) classifier usually forces the analyst to reduce the complexity of the implicit parameter estimation task. For decades, the common perception in the literature has been that the solution to this has been to reduce data dimensionality. However, as can be seen from a result by Cover [1], reducing dimensionality increases the risk of making the classification problem more complex.Using the simple GML classifier we compare state of the art dimensionality reduction strategies with a recently proposed strategy for sparsing of parameter estimates in full dimension [2]. Results show that reducing parameter estimation complexity by fitting sparse models in full dimension have a slight edge on the common approaches.

show abstract

Section: Resultsmentioning

confidence: 99%

Improving Hyperspectral Classifiers: The Difference Between Reducing Data Dimensionality and Reducing Classifier Parameter Complexity

Berge

Solberg

2007

Image Analysis

View full text Add to dashboard Cite

show abstract

“…In our experiments, the hyperspectral datasets employed were collected by the Reflective Optics System Imaging Spectrometer (ROSIS) sensor [11]. The images have 115 spectral bands with a spectral coverage from 0.43 to 0.86 μm, and a spatial resolution of 1.3 m. Two scenes are used in our experiment.…”

Section: Experiments and Analysismentioning

confidence: 99%

Locality-preserving nonnegative matrix factorization for hyperspectral image classification

Prasad

Fowler

et al. 2012

2012 IEEE International Geoscience and Remote Sensing Symposium

View full text Add to dashboard Cite

Feature extraction based on nonnegative matrix factorization is considered for hyperspectral image classification. One shortcoming of most remote-sensing data is low spatial resolution, which causes a pixel to be mixed with several pure spectral signatures, or endmembers. To counter this effect, locality-preserving nonnegative matrix factorization is employed in order to extract an endmembers-based feature representation as well as to preserve the intrinsic geometric structure of hyperspectral data. Subsequently, a Gaussian mixture model classifier is employed in the induced-feature subspace. Experimental results demonstrate that the proposed classification system significantly outperforms traditional approaches even in instances of limited training data and severe pixel mixing.

show abstract

“…The first image, Pavia [3], is of an urban scene taken by an airborne sensor. It has 71 bands, a pixel size of 2.6 m and the ground truth consists of nine classes.…”

Section: Data Setsmentioning

confidence: 99%

Forming Different-Complexity Covariance-Model Subspaces through Piecewise-Constant Spectra for Hyperspectral Image Classification

Jensen

Loog

2011

Image Analysis

View full text Add to dashboard Cite

Abstract.A key factor in classifiers based on the normal (or Gaussian) distribution is the modeling of covariance matrices. When the number of available training pixels is limited, as often is the case in hyperspectral image classification, it is necessary to limit the complexity of these covariance models. An alternative to reducing the complexity uniformly over the whole feature space, is to form orthogonal subspaces and reduce the model complexity within them separately, e.g., forming full-complexity within-class, or interior-class, subspace models, and reduced-complexity exterior-class subspace models. We propose to use subspaces created by forming fewer and wider spectral bands, instead of the more general principal component analysis transform (PCA), in an attempt to exploit a-priori knowledge of the data to create more generalizable subspaces. We investigate the resulting classifiers by studying their performances on four hyperspectral data sets. On each data set, experiments where run using different training set sizes. The results indicate that the classifiers seem to benefit from using this more data-specific approach to forming subspaces.

show abstract

A collection of data for urban area characterization

Cited by 101 publications

References 9 publications

Improving Hyperspectral Classifiers: The Difference Between Reducing Data Dimensionality and Reducing Classifier Parameter Complexity

Improving Hyperspectral Classifiers: The Difference Between Reducing Data Dimensionality and Reducing Classifier Parameter Complexity

Locality-preserving nonnegative matrix factorization for hyperspectral image classification

Forming Different-Complexity Covariance-Model Subspaces through Piecewise-Constant Spectra for Hyperspectral Image Classification

Contact Info

Product

Resources

About