A Study of Virtual Visual Servoing Sensitivity in the Context of Image/GIS Registration for Urban Environments

Abstract : This paper studies the sensitivity of pose estima- tion to the 2D measure noise when using virtual visual servoing. Attempting to apply virtual visual servoing to image/Geographic Information System (GIS) reg- istration, the robustness to the noise in images is an important factor to the accuracy of estimation. To an- alyze the impact of different levels of noise, a series of image/GIS registration tests based on synthetic in- put image are studied. Also, RANSAC is introduced to improve the robustness of the method. We also com- pare some different strategies in choosing geometrical features and in the treatment of projection error vec- tor in virtual visual servoing, providing a guide for parametrization.
Type de document :
Communication dans un congrès
Fifteenth IAPR International Conference on Machine Vision Application, 2017, Nagoya, Japan. 2017
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01526972
Contributeur : Myriam Servières <>
Soumis le : mardi 23 mai 2017 - 17:04:41
Dernière modification le : jeudi 21 février 2019 - 11:06:02

Identifiants

  • HAL Id : hal-01526972, version 1

Citation

Hengyang Wei, Muriel Pressigout, Luce Morin, Myriam Servières, Guillaume Moreau. A Study of Virtual Visual Servoing Sensitivity in the Context of Image/GIS Registration for Urban Environments. Fifteenth IAPR International Conference on Machine Vision Application, 2017, Nagoya, Japan. 2017. 〈hal-01526972〉

Partager

Métriques

Consultations de la notice

348