A support vector domain method for change detection in multitemporal images

Authors:
F. Bovolo;G. Camps-Valls;L. Bruzzone
Affiliations:
Dept. of Information Engineering and Computer Science, University of Trento, Via Sommarive, 38123 Povo, Italy;Image Processing Laboratory (IPL), Universitat de València, Spain;Dept. of Information Engineering and Computer Science, University of Trento, Via Sommarive, 38123 Povo, Italy
Venue:
Pattern Recognition Letters
Year:
2010

Citing 7
Cited 2

Outliers in statistical pattern recognition and an application to automatic chromosome classification

Pattern Recognition Letters
Support vector domain description

Pattern Recognition Letters - Special issue on pattern recognition in practice VI
Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond

Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond
Support Vector Data Description

Machine Learning
Kernel Methods for Pattern Analysis

Kernel Methods for Pattern Analysis
Kernel Methods in Bioengineering, Signal And Image Processing

Kernel Methods in Bioengineering, Signal And Image Processing
Image change detection algorithms: a systematic survey

IEEE Transactions on Image Processing

Gradual land cover change detection based on multitemporal fraction images

Pattern Recognition
Density weighted support vector data description

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.10

Visualization

Abstract

This paper formulates the problem of distinguishing changed from unchanged pixels in multitemporal remote sensing images as a minimum enclosing ball (MEB) problem with changed pixels as target class. The definition of the sphere-shaped decision boundary with minimal volume that embraces changed pixels is approached in the context of the support vector formalism adopting a support vector domain description (SVDD) one-class classifier. SVDD maps the data into a high dimensional feature space where the spherical support of the high dimensional distribution of changed pixels is computed. Unlike the standard SVDD, the proposed formulation of the SVDD uses both target and outlier samples for defining the MEB, and is included here in an unsupervised scheme for change detection. To this purpose, nearly certain training examples for the classes of both targets (i.e., changed pixels) and outliers (i.e., unchanged pixels) are identified by thresholding the magnitude of the spectral change vectors. Experimental results obtained on two different multitemporal and multispectral remote sensing images demonstrate the effectiveness of the proposed method.