Hyperspectral Anomaly Detection Based on Chessboard Topology

Abstract

Without any prior information, hyperspectral anomaly detection is devoted to locating targets of interest within a specific scene by exploiting differences in spectral characteristics between various land covers. Traditional methods originated from the signal processing perspective, and most of them rely heavily on specific model assumptions. Due to the model-driven attributes, such methods cannot mine the deep-level features of data to adapt to the variability of scenes, and cannot fully extract the information of land covers contained in images to accurately separate anomalies from background. By independently designing a chessboard-shaped topological framework that avoids making any distribution assumptions but directly mines high-dimensional data features to break through the limitations of traditional detectors, this paper proposes a novel chessboard topology-based anomaly detection (CTAD) method, which constructs a chessboard-shaped topology to dissect images and extract detailed information of land covers adaptively, thereby enabling highly accurate detection. Extensive experimental results on HSIs in real scenes demonstrate that the proposed CTAD can be adapted to the variability of scenes by autonomously learning data features, and exhibits strong generalization and detection capabilities, facilitating practical applications.