E-Book, Englisch, 434 Seiten, E-Book
Camps-Valls / Bruzzone Kernel Methods for Remote Sensing Data Analysis
1. Auflage 2009
ISBN: 978-0-470-74900-5
Verlag: John Wiley & Sons
Format: PDF
Kopierschutz: Adobe DRM (»Systemvoraussetzungen)
E-Book, Englisch, 434 Seiten, E-Book
ISBN: 978-0-470-74900-5
Verlag: John Wiley & Sons
Format: PDF
Kopierschutz: Adobe DRM (»Systemvoraussetzungen)
Kernel methods have long been established as effective techniquesin the framework of machine learning and pattern recognition, andhave now become the standard approach to many remote sensingapplications. With algorithms that combine statistics and geometry,kernel methods have proven successful across many differentdomains related to the analysis of images of the Earth acquiredfrom airborne and satellite sensors, including natural resourcecontrol, detection and monitoring of anthropic infrastructures(e.g. urban areas), agriculture inventorying, disaster preventionand damage assessment, and anomaly and target detection.
Presenting the theoretical foundations of kernel methods (KMs)relevant to the remote sensing domain, this book serves as apractical guide to the design and implementation of these methods.Five distinct parts present state-of-the-art research related toremote sensing based on the recent advances in kernel methods,analysing the related methodological and practical challenges:
* Part I introduces the key concepts of machine learning forremote sensing, and the theoretical and practical foundations ofkernel methods.
* Part II explores supervised image classification includingSuper Vector Machines (SVMs), kernel discriminant analysis,multi-temporal image classification, target detection with kernels,and Support Vector Data Description (SVDD) algorithms for anomalydetection.
* Part III looks at semi-supervised classification withtransductive SVM approaches for hyperspectral image classificationand kernel mean data classification.
* Part IV examines regression and model inversion, including theconcept of a kernel unmixing algorithm for hyperspectral imagery,the theory and methods for quantitative remote sensing inverseproblems with kernel-based equations, kernel-based BRDF(Bidirectional Reflectance Distribution Function), and temperatureretrieval KMs.
* Part V deals with kernel-based feature extraction and providesa review of the principles of several multivariate analysis methodsand their kernel extensions.
This book is aimed at engineers, scientists and researchersinvolved in remote sensing data processing, and also those workingwithin machine learning and pattern recognition.
