Kernel-Based Framework for Multitemporal and Multisource Remote Sensing Data Classification and Change Detection

Abstract

The multitemporal classification of remote sensing images is a challenging problem, in which the efficient combination of different sources of information (e.g., temporal, contextual, or multisensor) can improve the results. In this paper, we present a general framework based on kernel methods for the integration of heterogeneous sources of information. Using the theoretical principles in this framework, three main contributions are presented. First, a novel family of kernel-based methods for multitemporal classification of remote sensing images is presented. The second contribution is the development of nonlinear kernel classifiers for the well-known difference and ratioing change detection methods by formulating them in an adequate high-dimensional feature space. Finally, the presented methodology allows the integration of contextual information and multisensor images with different levels of nonlinear sophistication. The binary support vector (SV) classifier and the one-class SV domain description classifier are evaluated by using both linear and nonlinear kernel functions. Good performance on synthetic and real multitemporal classification scenarios illustrates the generalization of the framework and the capabilities of the proposed algorithms.

A Review of Kernel Methods in Remote Sensing Data Analysis

“…The most successful kernel method are the support vector machines as extensively reported in [6]. SVMs have been applied to both multispectral [22,23] and hyperspectral [6,24,9] data in a wide range of domains, including object recognition [25], land cover and multi-temporal classification [26,27,9], and urban monitoring [28].…”

“…This method is a recent kernel-based development that only considers samples belonging to the class of interest in order to learn the underlying data class distribution. The method was originally introduced for anomaly detection [7], then analyzed for dealing with incomplete and unreliable training data [8], and recently reformulated for change detection [9].…”

“…Composite kernels have been specifically designed and applied for the efficient combination of multitemporal, multisensor and multisource information [9,71]. The previous approaches exploited some properties of kernel methods (such as the direct sum of Hilbert spaces, see Section 1.2.3) to combine kernels dedicated to process different signal sources, e.g.…”

Clustering of Multi-Temporal Fully Polarimetric L-Band Sar Data for Agricultural Land Cover Mapping

“…To avoid working in the potentially high-dimensional space, the dot product can be evaluated directly using a nonlinear function in input space by means of the kernel trick (Camps-Valls et al, 2008). Every function that meets the Mercer's condition can be used as a kernel function.…”

“…The main idea of using a kernel function in the similarity criteria is to compute the distance between pixels in feature space (Camps-Valls et al, 2008). Feature space due to its inherent properties enable us to clustering nonlinear datasets simpler and more efficient.…”