标题:A Discriminative Metric Learning Based Anomaly Detection Method

作者:Du, B (Du, Bo); Zhang, LP (Zhang, Liangpei)

卷:52 期:11 页:6844-6857 DOI:10.1109/TGRS.2014.2303895 出版年:NOV 2014

摘要:Due to the high spectral resolution, anomaly detection from hyperspectral images provides a new way to locate potential targets in a scene, especially those targets that are spectrally different from the majority of the data set. Conventional Mahalanobis-distance-based anomaly detection methods depend on the background statistics to construct the anomaly detection metric. One of the main problems with these methods is that the Gaussian distribution assumption of the background may not be reasonable. Furthermore, these methods are also susceptible to contamination of the conventional background covariance matrix by anomaly pixels. This paper proposes a new anomaly detection method by effectively exploiting a robust anomaly degree metric for increasing the separability between anomaly pixels and other background pixels, using discriminative information. First, the manifold feature is used so as to divide the pixels into the potential anomaly part and the potential background part. This procedure is called discriminative information learning. A metric learning method is then performed to obtain the robust anomaly degree measurements. Experiments with three hyperspectral data sets reveal that the proposed method outperforms other current anomaly detection methods. The sensitivity of the method to several important parameters is also investigated.

地址:[Du, Bo] Wuhan Univ, Sch Comp Sci, Wuhan 430072, Peoples R China.

[Zhang, Liangpei] Wuhan Univ, Remote Sensing Grp, State Key Lab Informat Engn Surveying Mapping & R, Wuhan 430072, Peoples R China.

通讯作者地址:Du, B (通讯作者),Wuhan Univ, Sch Comp Sci, Wuhan 430072, Peoples R China.

电子邮件地址:remoteking@whu.edu.cn; zlp62@whu.edu.cn

ISSN:0196-2892

电子 ISSN:1558-0644