Aircraft classification with a low resolution infrared sensor - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2011

Aircraft classification with a low resolution infrared sensor

Résumé

Existing computer simulations of aircraft infrared signature do not account for the dispersion induced by uncertainty on input data, such as aircraft aspect angles and meteorological conditions. As a result, they are of little use to estimate the detection performance of IR optronic systems: in that case, the scenario encompasses a lot of possible situations that must indeed be addressed, but can not be singly simulated. In this paper, we focus on low resolution infrared sensors and we propose a methodological approach for performing a classification of different aircraft on the resulting set of low resolution infrared images. It is based on a maximum likelihood classification which takes advantage of Bayesian dense deformable template models estimation. This method is illustrated in a typical scenario, over a database of 30 000 simulated aircraft images. Assuming a white noise background model, classification performances are very promising, and appear to be more noise-robust than support vector machines ones
Fichier non déposé

Dates et versions

hal-01303722 , version 1 (18-04-2016)

Identifiants

Citer

Florian Maire, Sidonie Lefebvre, Éric Moulines, Randal Douc. Aircraft classification with a low resolution infrared sensor. SSP 2011 : Statistical Signal Processing Workshop, Jun 2011, Nice, France. pp.761 - 764, ⟨10.1109/SSP.2011.5967815⟩. ⟨hal-01303722⟩
103 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More