Skip to Main content Skip to Navigation
Theses

Contribution à la modélisation d'environnements par vision monoculaire dans un contexte de robotique aéro-terrestre

Abstract : This thesis mainly deal with planar areas detection from monocular images and low-budget sensors. These works allow safe landing area detection for UAV and ground/air coopération with traversability maps fusion. In using homographies' properties, we segment the regions of images that are the projections of a plane surface. An extensive study has been made on robust linear estimators in a context of homography estimation from matched points. Synthesis datas were used in order to highlight the influence of the parameters of the environment on the quality of estimated homographies. These results were confronted thereafter with real data. These techniques allow the segmentation of matched points belonging to a plane zone. In order to produce a dense description (continues) of planar zones, we proposed an improvement of the Zero-mean Normal Cross Correlation score. By considering an adaptive model of the influence of the luminosity variances on the scores of correlation, we introduced an automatic segmentation method of planar zones which offer good results. The introduction of probabilistic models enabled us to fuze iteratively the observations, and to build local grids which represent the probability of flatness on zones. Finally with the aim of the co-operation between air and terrestrial robots, we extended this work to the context of terrestrial robotics and the fusion of aéro-terrestrial models.
Document type :
Theses
Complete list of metadatas

Cited literature [47 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-00181794
Contributor : Emilie Marchand <>
Submitted on : Wednesday, October 24, 2007 - 3:31:20 PM
Last modification on : Monday, October 19, 2020 - 11:09:50 AM
Long-term archiving on: : Monday, April 12, 2010 - 12:20:12 AM

Identifiers

  • HAL Id : tel-00181794, version 1

Citation

Sébastien Bosch. Contribution à la modélisation d'environnements par vision monoculaire dans un contexte de robotique aéro-terrestre. Automatique / Robotique. Université Paul Sabatier - Toulouse III, 2007. Français. ⟨tel-00181794⟩

Share

Metrics

Record views

378

Files downloads

394