Estimating vehicle ego-motion and piecewise planar scene structure from optical flow in a continuous framework

• Verfasst von: Neufeld, Andreas [VerfasserIn]
• Verfasst von: Berger, Johannes Peter [VerfasserIn]
• Verfasst von: Becker, Florian [VerfasserIn]
• Verfasst von: Lenzen, Frank [VerfasserIn]
• Verfasst von: Schnörr, Christoph [VerfasserIn]
• Titel: Estimating vehicle ego-motion and piecewise planar scene structure from optical flow in a continuous framework
• Verf.angabe: Andreas Neufeld, Johannes Berger, Florian Becker, Frank Lenzen, Christoph Schnörr
• Umfang: 12 S.
• Fussnoten: Gesehen am 07.03.2019
• Titel Quelle: Enthalten in: Pattern Recognition
• Jahr Quelle: 2015
• Band/Heft Quelle: (2015), S. 41-52
• ISBN Quelle: 978-3-319-24947-6
• DOI: doi:10.1007/978-3-319-24947-6_4
• Datenträger: Online-Ressource
• Sprache: eng
• K10plus-PPN: 1588415449

Abstract

We propose a variational approach for estimating egomotion and structure of a static scene from a pair of images recorded by a single moving camera. In our approach the scene structure is described by a set of 3D planar surfaces, which are linked to a SLIC superpixel decomposition of the image domain. The continuously parametrized planes are determined along with the extrinsic camera parameters by jointly minimizing a non-convex smooth objective function, that comprises a data term based on the pre-calculated optical flow between the input images and suitable priors on the scene variables. Our experiments demonstrate that our approach estimates egomotion and scene structure with a high quality, that reaches the accuracy of state-of-the-art stereo methods, but relies on a single sensor that is more cost-efficient for autonomous systems.