A Review of Kernel Methods in Remote Sensing Data Analysis

Abstract

Summary. Kernel methods have proven effective in the analysis of images of the Earth acquired by airborne and satellite sensors. Kernel methods provide a consistent and well-founded theoretical framework for developing nonlinear techniques and have useful properties when dealing with low number of (potentially high dimensional) training samples, the presence of heterogenous multimodalities, and different noise sources in the data. These properties are particularly appropriate for remote sensing data analysis. In fact, kernel methods have improved results of parametric linear methods and neural networks in applications such as natural resource control, detection and monitoring of anthropic infrastructures, agriculture inventorying, disaster prevention and damage assessment, anomaly and target detection, biophysical parameter estimation, band selection, and feature extraction.This chapter provides a survey of applications and recent theoretical developments of kernel methods in the context of remote sensing data analysis. The specific methods developed in the fields of supervised classification, semisupervised classification, target detection, model inversion, and nonlinear feature extraction are revised both theoretically and through experimental (illustrative) examples. The emergent fields of transfer, active, and structured learning, along with efficient parallel implementations of kernel machines, are also revised.

Quantifying Vegetation Biophysical Variables from Imaging Spectroscopy Data: A Review on Retrieval Methods

“…The flexibility offered by kernel methods allows us to transform almost any linear algorithm that can be expressed in terms of dot products, while still using only linear algebra operations. Kernel methods provide a consistent theoretical framework for developing nonlinear techniques and have useful properties when dealing with a low number of (potentially high-dimensional) training samples, and outliers and noise in the data (Gómez-Chova et al 2011;Tuia et al 2018). Given these attractive properties, kernel-based regression methods seem perfectly suited to extract nonlinear information related to vegetation properties from imaging spectroscopy data.…”

Solving Adaptive Image Restoration Problems via a Modified Projection Algorithm

“…with inverting a forward model. To this aim, one has to produce an accurate and robust model able to predict physical, chemical, geological, or atmospheric parameters from spectra, such as surface temperature, water vapour, and ozone; see, for example, [31]. Denoising images could be part of the accurate and robust model.…”

Combining transductive and active learning to improve object-based classification of remote sensing images

“…This percentage indicates the proportion of the data set that was randomly sampled to create the training set. We evaluated the classification performance using the F-measure (Gómez-Chova et al 2011). We used F-measure instead of general accuracy due to its ability to better describe classifier performance on unbalanced data sets.…”