SPIDAR Calibration based on neural networks versus optical tracking - Interactions, Réalité Augmentée, Robotique Ambiante Accéder directement au contenu
Communication Dans Un Congrès Année : 2010

SPIDAR Calibration based on neural networks versus optical tracking

Résumé

This paper aims to present all the study done on the SPIDAR tracking and haptic device, in order to improve accuracy on the given position. Firstly we proposed a new semi-automatic initialization technique for this device using an optical tracking system. We also propose an innovative way to perfom calibration of 3D tracking device using virtual reality. Then, we used a two-layered feedforward neural network to reduce the location errors. We obtained very good results with this calibration, since we reduced the mean error by more than 50%.
Fichier non déposé

Dates et versions

hal-00745328 , version 1 (25-10-2012)

Identifiants

  • HAL Id : hal-00745328 , version 1

Citer

Pierre Boudoin, Hichem Maaref, Samir Otmane, Malik Mallem. SPIDAR Calibration based on neural networks versus optical tracking. 6th International Workshop on Artificial Neural Networks and Intelligent Information Processing (ANNIIP 2010), in Conjunction with ICINCO, Jun 2010, Funchal, France. pp.87--98. ⟨hal-00745328⟩
61 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More