Probabilistic Models for 3D Urban Scene Understanding from Movable Platforms
Abstract:
This work is a contribution to understanding multi-object traffic scenes from video sequences. All data is provided by a camera system which is mounted on top of the autonomous driving platform AnnieWAY. The proposed probabilistic generative model reasons jointly about the 3D scene layout as well as the 3D location and orientation of objects in the scene. In particular, the scene topology, geometry as well as traffic activities are inferred from short video sequences.
| Zugehörige Institution(en) am KIT | Institut für Mess- und Regelungstechnik mit Maschinenlaboratorium (MRT) |
| Publikationstyp | Hochschulschrift |
| Jahr | 2013 |
| Sprache | Englisch |
| Identifikator | ISBN: 978-3-7315-0081-0 ISSN: 1613-4214 URN: urn:nbn:de:0072-360641 KITopen ID: 1000036064 |
| Verlag | KIT Scientific Publishing, Karlsruhe |
| Umfang | V, 162 S. |
| Serie | Schriftenreihe / Institut für Mess- und Regelungstechnik, Karlsruher Institut für Technologie ; 025 |
| Abschlussart | Dissertation |
| Fakultät | Fakultät für Maschinenbau (MACH) |
| Institut | Institut für Mess- und Regelungstechnik mit Maschinenlaboratorium (MRT) |
| Prüfungsdaten | 19.04.2013 |
| Referent/Betreuer | Prof. C. Stiller |
| Schlagworte | scene understanding, computer vision, machine learning |