Comparative Analysis of Covariance Matrix Estimation for Anomaly Detection in Hyperspectral Images

Santiago Velasco-Forero (1) , Marcus Chen (2) , Alvina Goh (3) , Sze Kim Pang (4)

1 CMM - Centre de Morphologie Mathématique
2 Nanyang Technological University [Singapour]
3 Department of Mathematics [Singapore]
4 DSO National Laboratories

Covariance matrix estimation is fundamental for anomaly detection, especially for the Reed and Xiaoli Yu (RX) detector. Anomaly detection is challenging in hyperspectral images because the data has a high correlation among dimensions, heavy tailed distributions and multiple clusters. This paper comparatively evaluates modern techniques of covariance matrix estimation based on the performance and volume the RX detector. To address the different challenges, experiments were designed to systematically examine the robustness and effectiveness of various estimation techniques. In the experiments, three factors were considered, namely, sample size, outlier size, and modification in the distribution of the sample. !

Mots clés: Hyperspectral Remote Sensing Image; Covariance Estimation

Domaines: Traitement du signal et de l'image [eess.SP]

Santiago Velasco-Forero, Marcus Chen, Alvina Goh, Sze Kim Pang. Comparative Analysis of Covariance Matrix Estimation for Anomaly Detection in Hyperspectral Images. IEEE Journal of Selected Topics in Signal Processing, 2015, pp.1-11. ⟨10.1109/JSTSP.2015.2442213⟩. ⟨hal-01159878⟩