Interference-Suppressed and Cluster-Optimized Hyperspectral Target Extraction Based on Density Peak Clustering

Target extraction can provide a prior knowledge for spectral unmixing, unsupervised hyperspectral image classification, and unsupervised target detection tasks, which is of great practice. Considering that the traditional endmember extraction algorithms such as automatic target generation process (ATGP) and simplex growing algorithm (SGA) are sensitive to the burst noise caused by hyperspectral sensor imaging and cannot extract the appropriate target set to simultaneously guide the various tasks, a weighted target extraction algorithm based on the density peak clustering (DPC) is proposed in this article. First, DPC is extended to hyperspectral images, and the decision graph is generated according to the density and distance of each pixel to effectively classify the regions with different attributes such as burst noise, cluster center, cluster boundary, and cluster core. On the basis, three DPC-based weighted vectors are designed, and the weighted target extraction algorithms W-ATGP and W-SGA are put forward which allocates a lower weight than the core pixel to the interference so as to reduce its impact on ATGP and SGA while obtaining the high-quality targets for various tasks. The experimental results on three datasets show that the accuracies of the target sets extracted by W-ATGP and W-SGA are higher than that of ATGP and SGA, no matter as the prior knowledge of spectral unmixing, unsupervised hyperspectral image classification, or unsupervised target detection, which verifies the effectiveness of the proposed methods.