Non supervised perceptual model for target recognition in UAVs

Abstract : Today, drones play an interesting role in the so-called Revolution 4.0. One of the problems studied by various companies and research groups are the precision landing techniques since many applications, such as package delivery or object tracking, use this drone feature. In this paper, we propose a non-supervised model that allows to detect and recognize a set of landing targets using the Gestalt principles. This proposed method is capable of recognizing different coded landing targets robustly under outdoor non-controlled light conditions. In comparison with thresholding techniques and other methods, this work deals with image degradations caused by shadows, change of scale, noise and camera target deformation.
Liste complète des métadonnées

Littérature citée [12 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01793695
Contributeur : Eric Bazan <>
Soumis le : mercredi 16 mai 2018 - 18:31:14
Dernière modification le : mercredi 30 mai 2018 - 15:42:59

Fichier

 Accès restreint
Fichier visible le : 2019-05-16

Connectez-vous pour demander l'accès au fichier

Identifiants

  • HAL Id : hal-01793695, version 1

Citation

Eric Bazan, Petr Dokládal, Eva Dokladalova. Non supervised perceptual model for target recognition in UAVs. 2018. 〈hal-01793695〉

Partager

Métriques

Consultations de la notice

71