Skip to Main content Skip to Navigation
Conference papers

Détection des lignes aéroportuaires par méthode de filtrage particulaire: Évaluation de fonctions d'observations

Abstract : This paper presents a method for ground marks detection in airport areas by using particle fil- tering (sequential Monte-Carlo method). The ground mark is considered as a succession of thumbnails linked by a Markov chain. We make an analogy between the spatial detection of lines in an image and the temporal tracking of a vehicle with a similar dynamic model. Then we propose a solution by particle filtering. The particles represent the characteristics of thumbnails, we use an image classifier to assign a weight to each par- ticle from the thumbnails. Three classifiers are compared, the first is based on the Gabor filter, the second one exploits a polynomial SVM on a wavelets decomposition and the third one learn how to represent and classify a thumbnail by a CNN. The results are validated on real and simu- lated images.
Document type :
Conference papers
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03339641
Contributor : Ccsd Sciencesconf.Org Connect in order to contact the contributor
Submitted on : Thursday, September 9, 2021 - 3:40:04 PM
Last modification on : Tuesday, October 19, 2021 - 11:18:07 PM

File

orasis2021_v2.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03339641, version 1
`

Citation

Esteban Perrotin, Claire Meymandi-Nejad, Ariane Herbulot, Michel Devy, Fabrice Bousquet. Détection des lignes aéroportuaires par méthode de filtrage particulaire: Évaluation de fonctions d'observations. ORASIS 2021, Centre National de la Recherche Scientifique [CNRS], Sep 2021, Saint Ferréol, France. ⟨hal-03339641⟩

Share

Metrics

Record views

45

Files downloads

17