ICRA 2011 Paper Abstract


Paper WeP214.4

Laroche, Edouard (University of Strasbourg), Kagami, Shingo (Tohoku University), Cuvillon, Loic (Strasbourg I University)

Hybrid Kalman Filter for Improvement of Camera-Based Position Sensor

Scheduled for presentation during the Regular Sessions "Visual Tracking" (WeP214), Wednesday, May 11, 2011, 16:10−16:25, Room 5J

2011 IEEE International Conference on Robotics and Automation, May 9-13, 2011, Shanghai International Conference Center, Shanghai, China

This information is tentative and subject to change. Compiled on July 14, 2020

Keywords Visual Tracking, Computer Vision for Robotics and Automation, Motion Control of Manipulators


When using a camera as a position sensor, the measurement is limited in bandwidth, mainly due to the blur effects. The knowledge of an accurate model of the camera is then necessary to reconstruct the trajectory from the measurements given by the camera. This paper deals with the reconstruction of the continuous-time trajectory from the discrete-time measurements provided by the camera and shows the improvement obtained by using an accurate camera model. In the proposed methodology, a Kalman filter is used for the data fusion between the model and the measurement. The tuning and implementation of the filter are discussed in the specific context of the camera measurement. The system is evaluated in the context of a biomedical application: the reconstruction of the movement of a beating-heart.



Technical Content © IEEE Robotics & Automation Society

This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2020 PaperCept, Inc.
Page generated 2020-07-14  16:30:00 PST  Terms of use