Kernel methods for remote sensing data analysis

Kernel Methods for Remote Sensing Data Analysis presents the theoretical foundations of kernel methods relevant to the remote sensing domain and provides apractical guide to the design and implementation of these methods. The book is organised into four parts. The first part comprises three background chapters on the key aspects of remote sensing, and the theoretical and practical foundations of kernel methods, written by leading experts in both communities. Theremaining three parts address the most recent research developments of KMs inremote sensing for supervised classification, semi-supervised classification,and regression (model inversion). Part II explores supervised image classification including Super Vector Machines (SVMs), kernel discriminant analysis, multi-temporal image classification, target detection with kernels and Support Vector Data Description (SVDD) algorithms for anomaly detection. Part III looksat semi-supervised classification with transductive SVM approaches for hyperspectral image classification and kernel mean data classification. PART IV examines function approximation and estimation using kernel fully constrained least squares abundance estimates, regularized kernel-based BRDF (Bidirectional Reflectance Distribution Function) model inversion methods and temperature retrieval KMs. Supplementary material in the form of open-source implementations ofthe proposed algorithms will also be available to the reader.

• ISBN: 978-0-470-72211-4
• Editorial: John Wiley & Sons
• Encuadernacion: Cartoné
• Páginas: 440
• Fecha Publicación: 23/10/2009
• Nº Volúmenes: 1
• Idioma: Inglés