Silva, Hugo MiguelBernardino, AlexandreSilva, Eduardo2015-12-292015-12-292013978-989-8565-48-8http://hdl.handle.net/10400.22/7284Proceedings of the International Conference on Computer Vision Theory and Applications, 361-365, 2013, Barcelona, SpainWe 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.engVisual NavigationStereo Vision,Visual OdometryEgomotionconference object10.5220/0004196103610365