Segmentation-Based Weighting Strategy for Hyperspectral Anomaly Detection

Abstract

Background information extraction and modeling have always been the cores of hyperspectral anomaly detection (AD) algorithms. In this letter, a simple and efficient weighting strategy based on image segmentation is proposed. The strategy integrates detection results with spatial information from segmentation, and the background is suppressed in the fusion results. First, an improved graph-based image-segmentation algorithm is adopted to isolate potential anomaly targets from the background. The segmentation is based on the spectral similarity of adjacent pixels and can extract the potential target well even if the global background is complex. Then, a weight matrix is constructed according to the segmentation result, and two types of background, narrow boundaries and large homogeneous areas, are suppressed and assigned small weights. Finally, the normalized weight matrix is combined with the detection results of AD algorithms. Experiments conducted on different data sets show that the proposed strategy is efficient and robust and can improve the detection performance and robustness of AD algorithms.