Kernel Anomalous Change Detection for Remote Sensing Imagery

TL;DR

This paper introduces a nonlinear kernel-based approach for anomalous change detection in remote sensing imagery, significantly improving detection accuracy and reducing false alarms across various real-world scenarios.

Contribution

It extends existing anomalous change detectors to nonlinear kernel methods using reproducing kernel Hilbert space theory, enhancing detection performance in remote sensing applications.

Findings

Kernel methods outperform linear detectors in accuracy.

Reduced false-alarm rates with nonlinear approaches.

Effective in diverse scenarios like droughts and urbanization.

Abstract

Anomalous change detection (ACD) is an important problem in remote sensing image processing. Detecting not only pervasive but also anomalous or extreme changes has many applications for which methodologies are available. This paper introduces a nonlinear extension of a full family of anomalous change detectors. In particular, we focus on algorithms that utilize Gaussian and elliptically contoured (EC) distribution and extend them to their nonlinear counterparts based on the theory of reproducing kernels' Hilbert space. We illustrate the performance of the kernel methods introduced in both pervasive and ACD problems with real and simulated changes in multispectral and hyperspectral imagery with different resolutions (AVIRIS, Sentinel-2, WorldView-2, and Quickbird). A wide range of situations is studied in real examples, including droughts, wildfires, and urbanization. Excellent performance in terms of detection accuracy compared to linear formulations is achieved, resulting in improved detection accuracy and reduced false-alarm rates. Results also reveal that the EC assumption may be still valid in Hilbert spaces. We provide an implementation of the algorithms as well as a database of natural anomalous changes in real scenarios http://isp.uv.es/kacd.html.