6D Visual Odometry with Dense Probabilistic Egomotion Estimation

Silva, Hugo Miguel; Bernardino, Alexandre; Silva, Eduardo

http://hdl.handle.net/10400.22/7284

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
COM_SilvaH_2013_LSA.pdf		404.72 KB	Adobe PDF	Download

Send Feedback

Authors

Silva, Hugo Miguel

Bernardino, Alexandre

Silva, Eduardo

Abstract(s)

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.