Contribution of band selection and fusion for hyperspectral classification

Chehata, Nesrine; Bris, Arnaud Le; Najjar, Safa

doi:10.1109/whispers.2014.8077484

Cited by 6 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This has also been demonstrated for the classification of hyperspectral data, e.g. in (Melgani and Bruzzone, 2004;Le Bris et al, 2014;Chehata et al, 2014;Keller et al, 2016;Keller et al, 2017).…”

Section: Classification Of Hyperspectral Datamentioning

confidence: 89%

Revisiting Existing Classification Approaches for Building Materials Based on Hyperspectral Data

Ilehag

Weinmann

Schenk

et al. 2017

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Classification of materials found in urban areas using remote sensing, in particular with hyperspectral data, has in recent times increased in importance. This study is conducting classification of materials found on building using hyperspectral data, by using an existing spectral library and collected data acquired with a spectrometer. Two commonly used classification algorithms, Support Vector Machine and Random Forest, were used to classify the materials. In addition, dimensionality reduction and band selection were performed to determine if selected parts of the full spectral domain, such as the Short Wave Infra-Red domain, are sufficient to classify the different materials. We achieved the best classification results for the two datasets using dimensionality reduction based on a Principal Component Analysis in combination with a Random Forest classification. Classification using the full domain achieved the best results, followed by the Short Wave Infra-Red domain.

show abstract

Section: Classification Of Hyperspectral Datamentioning

confidence: 89%

Revisiting Existing Classification Approaches for Building Materials Based on Hyperspectral Data

Ilehag

Weinmann

Schenk

et al. 2017

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…Filter-based methods focus on evaluating relatively simple relations between features and classes and possibly also among features. These relations are typically quantified via a score function which is directly applied to the given training data [4,6,24,29]. Such a classifier-independent scheme typically results in simplicity and efficiency.…”

Section: Dimensionality Reduction (Dr) Vs Feature Selection (Fs)mentioning

confidence: 99%

Unsupervised Feature Selection Based on Ultrametricity and Sparse Training Data: A Case Study for the Classification of High-Dimensional Hyperspectral Data

2018

View full text Add to dashboard Cite

In this paper, we investigate the potential of unsupervised feature selection techniques for classification tasks, where only sparse training data are available. This is motivated by the fact that unsupervised feature selection techniques combine the advantages of standard dimensionality reduction techniques (which only rely on the given feature vectors and not on the corresponding labels) and supervised feature selection techniques (which retain a subset of the original set of features). Thus, feature selection becomes independent of the given classification task and, consequently, a subset of generally versatile features is retained. We present different techniques relying on the topology of the given sparse training data. Thereby, the topology is described with an ultrametricity index. For the latter, we take into account the Murtagh Ultrametricity Index (MUI) which is defined on the basis of triangles within the given data and the Topological Ultrametricity Index (TUI) which is defined on the basis of a specific graph structure. In a case study addressing the classification of high-dimensional hyperspectral data based on sparse training data, we demonstrate the performance of the proposed unsupervised feature selection techniques in comparison to standard dimensionality reduction and supervised feature selection techniques on four commonly used benchmark datasets. The achieved classification results reveal that involving supervised feature selection techniques leads to similar classification results as involving unsupervised feature selection techniques, while the latter perform feature selection independently from the given classification task and thus deliver generally versatile features.

show abstract

“…On the other hand, feature selection techniques can be applied which allow gaining predictive accuracy and improving computational efficiency with respect to both time and memory consumption, while retaining meaningful features (Guyon and Elisseeff, 2003;Saeys et al, 2007;Zhao et al, 2010). In the context of classifying hyperspectral data, feature selection techniques resulting in only the consideration of reflectance values across specific spectral bands have been used in several investigations (Melgani and Bruzzone, 2004;Le Bris et al, 2014;Chehata et al, 2014;Keller et al, 2016Keller et al, , 2017. Such techniques may also allow assessing the importance of single spectral bands for land-cover and land-use classification (Le Keller et al, 2016).…”

Section: Related Workmentioning

confidence: 99%

Investigations on the Potential of Hyperspectral and Sentinel-2 Data for Land-Cover / land-Use Classification

Weinmann

Maier

Florath

et al. 2018

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

<p><strong>Abstract.</strong> The automated analysis of large areas with respect to land-cover and land-use is nowadays typically performed based on the use of hyperspectral or multispectral data acquired from airborne or spaceborne platforms. While hyperspectral data offer a more detailed description of the spectral properties of the Earth’s surface and thus a great potential for a variety of applications, multispectral data are less expensive and available in shorter time intervals which allows for time series analyses. Particularly with the recent availability of multispectral Sentinel-2 data, it seems desirable to have a comparative assessment of the potential of both types of data for land-cover and land-use classification. In this paper, we focus on such a comparison and therefore involve both types of data. On the one hand, we focus on the potential of hyperspectral data and the commonly applied techniques for data-driven dimensionality reduction or feature selection based on these hyperspectral data. On the other hand, we aim to reason about the potential of Sentinel-2 data and therefore transform the acquired hyperspectral data to Sentinel-2-like data. For performance evaluation, we provide classification results achieved with the different types of data for two standard benchmark datasets representing an urban area and an agricultural area, respectively.</p>

show abstract

Contribution of band selection and fusion for hyperspectral classification

Cited by 6 publications

References 12 publications

Revisiting Existing Classification Approaches for Building Materials Based on Hyperspectral Data

Revisiting Existing Classification Approaches for Building Materials Based on Hyperspectral Data

Unsupervised Feature Selection Based on Ultrametricity and Sparse Training Data: A Case Study for the Classification of High-Dimensional Hyperspectral Data

Investigations on the Potential of Hyperspectral and Sentinel-2 Data for Land-Cover / land-Use Classification

Contact Info

Product

Resources

About