Probabilistic Models for 3D Urban Scene Understanding from Movable Platforms

Beschreibung

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.
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.

Autor*in

Andreas Geiger

Themen in »Probabilistic Models for 3D Urban Scene Understanding from Movable Platforms«

computer vision machine learning scene understanding

Stimmen zu »Probabilistic Models for 3D Urban Scene Understanding from Movable Platforms«

Details

Link teilen