Visual odometry has been promoted as a fundamental component for intelligent vehicles. Relying solely on monocular image cues would be desirable. Nevertheless, this is a challenge especially in dynamically varying urban areas due to scale ambiguities, independent motions, and measurement noise. We propose to use probabilistic learning with auxiliar depth cues. Specifically, we developed an expert model that specializes monocular egomotion estimation units on typical scene structures, i.e. statistical variations of scene depth layouts. The framework adaptively selects the best fitting expert. For on-line estimation of egomotion, we adopted a probabilistic subspace flow estimation method. Learning in our framework consists of two components: 1) Partitioning of datasets of video and ground truth odometry data based on unsupervised clustering of dense stereo depth profiles and 2) training a cascade of subspace flow expert models. A probabilistic quality measure from the estimates of the experts provides a selection rule overall leading to improvements of egomotion estimation for long test sequences.
Experts of probabilistic flow subspaces for robust monocular odometry in urban areas
2012 IEEE Intelligent Vehicles Symposium ; 661-667
2012-06-01
2049557 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Experts of Probabilistic Flow Subspaces for Robust Monocular Odometry in Urban Areas
British Library Conference Proceedings | 2012
|Robust Monocular Visual Odometry by Uncertainty Voting
British Library Conference Proceedings | 2011
|Robust stereo visual odometry from monocular techniques
IEEE | 2015
|Ground Vehicle Monocular Visual Odometry
IEEE | 2019
|