Authors:
Hugo Silva
1
;
Alexandre Bernardino
2
and
Eduardo Silva
1
Affiliations:
1
ISEP, Portugal
;
2
IST, Portugal
Keyword(s):
Visual Navigation, Stereo Vision, Visual Odometry, Egomotion.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Computer Vision, Visualization and Computer Graphics
;
Motion, Tracking and Stereo Vision
;
Optical Flow and Motion Analyses
;
Pattern Recognition
;
Robotics
;
Software Engineering
;
Stereo Vision and Structure from Motion
;
Tracking and Visual Navigation
Abstract:
We present a novel approach to 6D visual odometry for vehicles with calibrated stereo cameras. A dense probabilistic egomotion (5D) method is combined with robust stereo feature based approaches and Extended Kalman Filtering (EKF) techniques to provide high quality estimates of vehicle’s angular and linear velocities. Experimental results show that the proposed method compares favorably with state-the-art approaches, mainly in the estimation of the angular velocities, where significant improvements are achieved.