Asymptotically CFAR Unsupervised Target Detection and Discrimination in Hyperspectral Images with Anomalous Component Pursuit (ACP) - Archive ouverte HAL
Article Dans Une Revue IEEE Transactions on Geoscience and Remote Sensing Année : 2010

Asymptotically CFAR Unsupervised Target Detection and Discrimination in Hyperspectral Images with Anomalous Component Pursuit (ACP)

Alexis Huck
  • Fonction : Auteur
  • PersonId : 952886
Mireille Guillaume
  • Fonction : Auteur
  • PersonId : 868703

Résumé

This paper addresses the problem of anomaly detection in hyperspectral images. We propose and exploit a data model to establish the link between two main approaches in the area of anomaly detection, which are Hypothesis Testing (HT) and Projection Pursuit (PP). We show that joining these two approaches enables to overcome some limitations of each method taken separately. Indeed, the resulting detection algorithm, namely ACP (for Anomalous Component Pursuit) has an asymptotically constant false alarm rate, like HT-based detectors, and enables anomaly spectral discrimination, including the estimation of the number of classes. We assess the ACP algorithm on real-world data, in terms of detection and discrimination, and discuss some theoretic limitations.
Fichier non déposé

Dates et versions

hal-00948179 , version 1 (17-02-2014)

Identifiants

Citer

Alexis Huck, Mireille Guillaume. Asymptotically CFAR Unsupervised Target Detection and Discrimination in Hyperspectral Images with Anomalous Component Pursuit (ACP). IEEE Transactions on Geoscience and Remote Sensing, 2010, 48 (11), pp 3980-3991. ⟨10.1109/TGRS.2010.2063434⟩. ⟨hal-00948179⟩
69 Consultations
0 Téléchargements

Altmetric

Partager

More