Assessment of Component Selection Strategies in Hyperspectral Imagery

Ibarrola-Ulzurrun, Edurne; Marcello, Javier; Gonzalo-Martín, Consuelo

doi:10.3390/e19120666

Cited by 20 publications

(14 citation statements)

References 33 publications

(60 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Several transforms have been proposed in the last decades to extract reliable information, reducing redundancy and noise. Traditional feature-extraction techniques, mainly applied to reduce the dimensionality of hyperspectral data, are PCA, ICA, and MNF [51].…”

Section: • Image Transformsmentioning

confidence: 99%

See 1 more Smart Citation

Seabed Mapping in Coastal Shallow Waters Using High Resolution Multispectral and Hyperspectral Imagery

et al. 2018

Self Cite

View full text Add to dashboard Cite

Coastal ecosystems experience multiple anthropogenic and climate change pressures. To monitor the variability of the benthic habitats in shallow waters, the implementation of effective strategies is required to support coastal planning. In this context, high-resolution remote sensing data can be of fundamental importance to generate precise seabed maps in coastal shallow water areas. In this work, satellite and airborne multispectral and hyperspectral imagery were used to map benthic habitats in a complex ecosystem. In it, submerged green aquatic vegetation meadows have low density, are located at depths up to 20 m, and the sea surface is regularly affected by persistent local winds. A robust mapping methodology has been identified after a comprehensive analysis of different corrections, feature extraction, and classification approaches. In particular, atmospheric, sunglint, and water column corrections were tested. In addition, to increase the mapping accuracy, we assessed the use of derived information from rotation transforms, texture parameters, and abundance maps produced by linear unmixing algorithms. Finally, maximum likelihood (ML), spectral angle mapper (SAM), and support vector machine (SVM) classification algorithms were considered at the pixel and object levels. In summary, a complete processing methodology was implemented, and results demonstrate the better performance of SVM but the higher robustness of ML to the nature of information and the number of bands considered. Hyperspectral data increases the overall accuracy with respect to the multispectral bands (4.7% for ML and 9.5% for SVM) but the inclusion of additional features, in general, did not significantly improve the seabed map quality.

show abstract

Section: • Image Transformsmentioning

confidence: 99%

“…We used pixel and object-based supervised classifiers [51,58,59]. Specifically, Maximum Likelihood (ML), Spectral Angle Mapper (SAM), and Support Vector Machine (SVM) algorithms were assessed.…”

Section: Classificationmentioning

confidence: 99%

Seabed Mapping in Coastal Shallow Waters Using High Resolution Multispectral and Hyperspectral Imagery

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…Regarding the dimensionality reduction of CASI imagery, a selection of the suitable components was carried out analyzing the eigenvalues and the standard deviation values of the entropy (Ibarrola‐Ulzurrun et al. ). Besides, a visual assessment of the MNF components was made to determine which components are spatially coherent and which contain noise.…”

Section: Resultsmentioning

confidence: 99%

“…In a previous study, Ibarrola‐Ulzurrun et al. compare the performance of different dimensionality reduction techniques and assessed strategies for selecting the most suitable number of components to increase the performance in the classification of CASI imagery. The study concluded that minimum noise fraction (MNF) was the most suitable dimensionality reduction technique, which has also been supported by other authors (Melgani and Bruzzone , Tarabalka et al.…”

Section: Methodsmentioning

confidence: 99%

Temporal dynamic analysis of a mountain ecosystem based on multi‐source and multi‐scale remote sensing data

et al. 2019

Self Cite

View full text Add to dashboard Cite

Citation: Ibarrola-Ulzurrun, E., J. Marcello, C. Gonzalo-Mart ın, and J. L. Mart ın-Esquivel. 2019. Temporal dynamic analysis of a mountain ecosystem based on multi-source and multi-scale remote sensing data. Ecosphere 10(6):Abstract. During the last decades, ecosystems have suffered a decline in natural resources due to climate change and anthropogenic pressure. Specifically, the European rabbit introduced by humans, as well as drought episodes, have led to a change in the vegetation structure of a mountainous ecosystem: Teide National Park in Spain. Teide managers studied, with field-based traditional methods, how the two keystone vegetation species, Spartocytisus supranubius and Pterocephalus lasiospermus, have changed their dynamics in this vulnerable and heterogenic ecosystem. However, remote sensing is an important tool for classifying, monitoring, and managing large areas in a fast and economic way. This work proposes a methodological framework to monitor the changes produced in this protected area using multi-source remote sensing imagery. The results strengthen and extend the analysis followed by the National Park managers, demonstrating that S. supranubius has decreased its population while P. lasiospermus has increased. Moreover, this study presents thematic maps of the species of interest, as well as its specific coverage at different dates, providing quantitative data difficult to get with traditional approaches.

show abstract

“…Recently, many band selection methods have been proposed, and they can be grouped into two main categories: supervised band selection [9][10][11] and unsupervised band selection methods [12][13][14][15]. The supervised methods first divide data set into training samples and test samples.…”

Section: Introductionmentioning

confidence: 99%

An Efficient Clustering Method for Hyperspectral Optimal Band Selection via Shared Nearest Neighbor

Wang

2019

Remote Sensing

View full text Add to dashboard Cite

A hyperspectral image (HSI) has many bands, which leads to high correlation between adjacent bands, so it is necessary to find representative subsets before further analysis. To address this issue, band selection is considered as an effective approach that removes redundant bands for HSI. Recently, many band selection methods have been proposed, but the majority of them have extremely poor accuracy in a small number of bands and require multiple iterations, which does not meet the purpose of band selection. Therefore, we propose an efficient clustering method based on shared nearest neighbor (SNNC) for hyperspectral optimal band selection, claiming the following contributions: (1) the local density of each band is obtained by shared nearest neighbor, which can more accurately reflect the local distribution characteristics; (2) in order to acquire a band subset containing a large amount of information, the information entropy is taken as one of the weight factors; (3) a method for automatically selecting the optimal band subset is designed by the slope change. The experimental results reveal that compared with other methods, the proposed method has competitive computational time and the selected bands achieve higher overall classification accuracy on different data sets, especially when the number of bands is small.

show abstract

Assessment of Component Selection Strategies in Hyperspectral Imagery

Cited by 20 publications

References 33 publications

Seabed Mapping in Coastal Shallow Waters Using High Resolution Multispectral and Hyperspectral Imagery

Seabed Mapping in Coastal Shallow Waters Using High Resolution Multispectral and Hyperspectral Imagery

Temporal dynamic analysis of a mountain ecosystem based on multi‐source and multi‐scale remote sensing data

An Efficient Clustering Method for Hyperspectral Optimal Band Selection via Shared Nearest Neighbor

Contact Info

Product

Resources

About