Hyperspectral Anomaly Detection with Multivariate Skewed t Background Model Çok-deǧişkenli Çarpik t Arkaplan Modeli ile Hiperspektral Anomali Tespiti

Kayabol K., Aytekin E. B., Arisoy S., Kuruoglu E. E.

30th Signal Processing and Communications Applications Conference, SIU 2022, Safranbolu, Turkey, 15 - 18 May 2022 identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/siu55565.2022.9864954
  • City: Safranbolu
  • Country: Turkey
  • Keywords: anomaly detection, autoencoder, hyperspectral image, multivariate skewed t-distribution, variational Bayes approach
  • Kocaeli University Affiliated: No


© 2022 IEEE.In this paper, autoencoder-based multivariate skewed t-distribution is proposed for hyperspectral anomaly detection. In the proposed method, the reconstruction error between the hyperspectral images reconstructed by the autoencoder and the original hyperspectral images is calculated and is modeled with a multivariate skewed t-distribution. The parameters of the distribution are estimated using the variational Bayes approach, and a distribution-based rule is determined for anomaly detection. The experimental results show that the proposed method has better performance when compared to the RX, LRASR and DAEAD anomaly detection methods.