%0 Conference Paper %F Oral %T Non supervised perceptual model for target recognition in UAVs %+ Centre de Morphologie Mathématique (CMM) %+ Laboratoire d'Informatique Gaspard-Monge (LIGM) %A Bazan, Eric %A Dokládal, Petr %A Dokladalova, Eva %< avec comité de lecture %B Reconnaissance des Formes, Image, Apprentissage et Perception RFIAP %C Marne la Vallée, France %8 2018-06-26 %D 2018 %Z Computer Science [cs]/Image Processing [eess.IV] %Z Engineering Sciences [physics]/Signal and Image processing %Z Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Conference papers %X 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 this drone feature can be used in applications such as package delivery or object tracking. 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 to recognize different coded landing targets in a robust way under outdoor non-controlled light conditions. Comparing to thresholding techniques and other methods, this work deals with image degradations caused by shadows, change of scale, noise and camera target deformation. %G English %2 https://enpc.hal.science/hal-01790867/document %2 https://enpc.hal.science/hal-01790867/file/RFIAP_2018%20%281%29.pdf %L hal-01790867 %U https://enpc.hal.science/hal-01790867 %~ INSTITUT-TELECOM %~ ENSMP %~ ENPC %~ CNRS %~ LIGM_A3SI %~ ENSMP_CMM %~ PARISTECH %~ LIGM %~ CV_LIGM %~ PSL %~ ENSMP_DEP_MS %~ ESIEE-PARIS %~ ENSMP_DR %~ ENSMP-PSL %~ UNIV-EIFFEL %~ UPEM-UNIVEIFFEL %~ ESIEE-UNIVEIFFEL %~ TEST3-HALCNRS