CAJ | 학술논문

针对SVDD背景建模时混入异常点造成的检测率下降的问题，提出了基于主成分建模的SVDD方法并应用于高光谱图像异常检测。利用高光谱图像的光谱特征提取背景的主要成分，并分别对不同成分构建超球体，形成单种背景成分SVDD模型，最后利用综合决策函数对单个SVDD背景模型进行综合判断待检测像元，从而实现高光谱图像异常像元的检测。用仿真数据和真实数据对算法的性能进行验证，并将其与SVDD方法进行性能比较。结果表明，新算法在低虚警概率下较之SVDD模型有更高的检测概率，实验结果证明了算法的有效性。
침대SVDD배경건모시혼입이상점조성적검측솔하강적문제，제출료기우주성분건모적SVDD방법병응용우고광보도상이상검측。이용고광보도상적광보특정제취배경적주요성분，병분별대불동성분구건초구체，형성단충배경성분SVDD모형，최후이용종합결책함수대단개SVDD배경모형진행종합판단대검측상원，종이실현고광보도상이상상원적검측。용방진수거화진실수거대산법적성능진행험증，병장기여SVDD방법진행성능비교。결과표명，신산법재저허경개솔하교지SVDD모형유경고적검측개솔，실험결과증명료산법적유효성。
An SVDD algorithm based on the principal component modeling is presented for hyperspectral anomaly detection , in order to solve the problem of its low detection rate caused by mixing abnormal points in the process of modeling background .This method extracts the principal components of the background samples by using the hyper-spectral image’ s spectral signature , and then uses these different components to build different super spheres re-spectively , forms different single background component SVDD models by these super spheres , finally uses the inte-grated decision function to judge these SVDD background models to detect any anomalies .The performance of the algorithm is verified by simulated and real data .The results show that the proposed method can obtain a higher de-tection rate under low false rate than the algorithm based on SVDD , verifying the effectiveness of this proposed method.