A common prerequisite for many vision-based driver assistance systems is the knowledge of the vehicle's own movement. In this paper we propose a novel approach for estimating the egomotion of the vehicle from a sequence of stereo images. Our method is directly based on the trifocal geometry between image triples, thus no time expensive recovery of the 3-dimensional scene structure is needed. The only assumption we make is a known camera geometry, where the calibration may also vary over time. We employ an Iterated Sigma Point Kalman Filter in combination with a RANSAC-based outlier rejection scheme which yields robust frame-to-frame motion estimation even in dynamic environments. A high-accuracy inertial navigation system is used to evaluate our results on challenging real-world video sequences. Experiments show that our approach is clearly superior compared to other filtering techniques in terms of both, accuracy and run-time.
Visual odometry based on stereo image sequences with RANSAC-based outlier rejection scheme
2010 IEEE Intelligent Vehicles Symposium ; 486-492
01.06.2010
1481929 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
British Library Conference Proceedings | 2010
|Performance evaluation of 1-point-RANSAC visual odometry
British Library Online Contents | 2011
|Radar odometry with recursive-RANSAC
IEEE | 2016
|Combining Edge and One-Point RANSAC Algorithm to Estimate Visual Odometry
BASE | 2018
|Monocular Outlier Detection for Visual Odometry
British Library Conference Proceedings | 2017
|