Localization estimation for autonomous aerial navigation by matching images with different resolutions

Authors:
Kamel Bensebaa;Mauricio Pozzobon Martins
Affiliations:
Institute for Advanced Studies, Brazilian General Command for Aerospace Technology, São José dos Campos, SP, Brazil;Institute for Advanced Studies, Brazilian General Command for Aerospace Technology, São José dos Campos, SP, Brazil
Venue:
CISST'08 Proceedings of the 2nd WSEAS International Conference on Circuits, Systems, Signal and Telecommunications
Year:
2008

Citing 4
Cited 0

Representation of local geometry in the visual system

Biological Cybernetics
A computational approach for corner and vertex detection

International Journal of Computer Vision
Evaluation of Interest Point Detectors

International Journal of Computer Vision - Special issue on a special section on visual surveillance
Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography

Communications of the ACM

Quantified Score

Hi-index	0.00

Visualization

Abstract

Reliable localization is an essential component of a successful Autonomous Aerial Navigation. In order to get a precise position before navigation uncertainty becomes incorrigible, the main objective of this work is to investigate efficient algorithms for localization estimation for Autonomous Aerial Navigation by matching Images with Different Resolutions. In this work, we present an approach to localize the UAV (Unmanned Aerial Vehicle) in flight using matching images with different resolutions: a high-resolution image and a low-resolution one. This method consists of firstly to detect the landmarks or feature points in the images using the Harris corner detector. Secondly the method consists of automatic extraction of correspondence points between the first UAV video frame and a georeferengeced image. Finally we use a geometric model estimation to map the high-resolution image onto a low-resolution image, which results in position estimation of the UAV.