Journal ArticleDOI
Methodology For Hyperspectral Band Selection
Peter Bajcsy,Peter Groves +1 more
Reads0
Chats0
TLDR
In this article, the authors presented a new methodology for combining unsupervised and supervised methods under classification accuracy and computational requirement constraints that is designed to perform hyperspectral band selection and statistical modeling method selection.Abstract:
While hyperspectral data are very rich in information, processing the hyperspectral data poses several challenges regarding computational requirements, information redundancy removal, relevant information identification, and modeling accuracy. In this paper we present a new methodology for combining unsupervised and supervised methods under classification accuracy and computational requirement constraints that is designed to perform hyperspectral band (wavelength range) selection and statistical modeling method selection. The band and method selections are utilized for prediction of continuous ground variables using airborne hyperspectral measurements. The novelty of the proposed work is in combining strengths of unsupervised and supervised band selection methods to build a computationally efficient and accurate band selection system. The unsupervised methods are used to rank hyperspectral bands while the accuracy of the predictions of supervised methods are used to score those rankings. We conducted experiments with seven unsupervised and three supervised methods. The list of unsupervised methods includes information entropy, first and second spectral derivative, spatial contrast, spectral ratio, correlation, and principal component analysis ranking combined with regression, regression tree, and instance-based supervised methods. These methods were applied to a data set that relates ground measurements of soil electrical conductivity with airborne hyperspectral image values. The outcomes of our analysis led to a conclusion that the optimum number of bands in this domain is the top four to eight bands obtained by the entropy unsupervised method followed by the regression tree supervised method evaluation. Although the proposed band selection approach is demonstrated with a data set from the precision agriculture domain, it applies in other hyperspectral application domains.read more
Citations
More filters
Journal ArticleDOI
Evaluation of random forest and adaboost tree-based ensemble classification and spectral band selection for ecotope mapping using airborne hyperspectral imagery
TL;DR: Two tree-based ensemble classification algorithms are assessed: Adaboost and Random Forest, based on standard classification accuracy, training time and classification stability, and both outperform a neural network classifier in dealing with hyperspectral data.
Journal ArticleDOI
Advances in Hyperspectral Image and Signal Processing: A Comprehensive Overview of the State of the Art
Pedram Ghamisi,Naoto Yokoya,Jun Li,Wenzhi Liao,Sicong Liu,Javier Plaza,Behnood Rasti,Antonio Plaza +7 more
TL;DR: Rigorous and innovative methodologies are required for hyperspectral image (HSI) and signal processing and have become a center of attention for researchers worldwide.
Journal ArticleDOI
Similarity-Based Unsupervised Band Selection for Hyperspectral Image Analysis
TL;DR: The experimental result shows that the proposed unsupervised band selection algorithms based on band similarity measurement can yield a better result in terms of information conservation and class separability than other widely used techniques.
Journal ArticleDOI
Band Selection for Hyperspectral Image Classification Using Mutual Information
TL;DR: A new strategy is described to estimate the MI using a priori knowledge of the scene, reducing reliance on a "ground truth" reference map, by retaining bands with high associated MI values (subject to the so-called "complementary" conditions).
Journal ArticleDOI
Hyperspectral Band Selection: A Review
Weiwei Sun,Qian Du +1 more
TL;DR: Current hyperspectral band selection methods are reviewed, which can be classified into six main categories: ranking based, searching based, clustering based, sparsity based, embedding-learning based, embedded learning based, and hybrid-scheme based.
References
More filters
Book
Data Mining: Concepts and Techniques
TL;DR: This book presents dozens of algorithms and implementation examples, all in pseudo-code and suitable for use in real-world, large-scale data mining projects, and provides a comprehensive, practical look at the concepts and techniques you need to get the most out of real business data.
Journal ArticleDOI
Classification and Regression Trees.
Book
Advanced engineering electromagnetics
TL;DR: In this article, the authors introduce the notion of circular cross-section waveguides and cavities, and the moment method is used to compute the wave propagation and polarization.
Journal ArticleDOI
On the mean accuracy of statistical pattern recognizers
TL;DR: The overall mean recognition probability (mean accuracy) of a pattern classifier is calculated and numerically plotted as a function of the pattern measurement complexity n and design data set size m, using the well-known probabilistic model of a two-class, discrete-measurement pattern environment.
Remote sensing: The quantitative approach
S. M. Davis,David A. Landgrebe,T. L. Phillips,Philip H. Swain,R. M. Hoffer,J. C. Lindenlaub,L. F. Silva +6 more
TL;DR: In this paper, the authors describe the traitement de donnees reference record created on 2005-06-20, modified on 2016-08-08 and used for remote sensing.