SV-Training and Kernel Change Detection Algorithm for the Abrupt Modification in EMI Data for Buried Metallic Target Localization and Identification - Analyse et Décision en Traitement du Signal et Images Accéder directement au contenu
Article Dans Une Revue Applied Computational Electromagnetics Society Journal (ACES Journal) Année : 2015

SV-Training and Kernel Change Detection Algorithm for the Abrupt Modification in EMI Data for Buried Metallic Target Localization and Identification

Résumé

In this paper, we propose a new method to identify and to locate buried metallic object in ElectroMagnetic Induction (EMI) data based on the Kernel Change Detection (KCD) algorithm. The signature of the object in the EMI data is typically of low amplitude. Particularly, in the case where two objects are located at dierent depths, the amplitude of the deeper buried object is negligible compared to that of the other object. This would result in the fact that, the EMI system can not detect this object and consequently increases miss rate or False Negative Rate (FNR). The aim of the proposed method is to calculate a decision index for each EMI measurement in a so-called hypotheses space using KCD algorithm . The amplitude of these decision indexes in the case of objects at dierent depths are in the same range. The data resulting from this space are easier to process. To validate the proposed method, we have tested it on real EMI data derived from a series of measurements on real objects.
Fichier non déposé

Dates et versions

hal-01132608 , version 1 (17-03-2015)

Identifiants

  • HAL Id : hal-01132608 , version 1

Citer

Yacine Matriche, Saïd Moussaoui, Mouloud Feliachi, Abdelhalim Zaoui, Mohammed Abdellah. SV-Training and Kernel Change Detection Algorithm for the Abrupt Modification in EMI Data for Buried Metallic Target Localization and Identification. Applied Computational Electromagnetics Society Journal (ACES Journal), 2015, 30 (1), pp.132-139. ⟨hal-01132608⟩
181 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More