DocumentCode :
3428253
Title :
Understanding High-Level Semantics by Modeling Traffic Patterns
Author :
Hongyi Zhang ; Geiger, Andreas ; Urtasun, Raquel
Author_Institution :
Peking Univ., Beijing, China
fYear :
2013
fDate :
1-8 Dec. 2013
Firstpage :
3056
Lastpage :
3063
Abstract :
In this paper, we are interested in understanding the semantics of outdoor scenes in the context of autonomous driving. Towards this goal, we propose a generative model of 3D urban scenes which is able to reason not only about the geometry and objects present in the scene, but also about the high-level semantics in the form of traffic patterns. We found that a small number of patterns is sufficient to model the vast majority of traffic scenes and show how these patterns can be learned. As evidenced by our experiments, this high-level reasoning significantly improves the overall scene estimation as well as the vehicle-to-lane association when compared to state-of-the-art approaches.
Keywords :
image processing; inference mechanisms; traffic engineering computing; 3D urban scenes; autonomous driving; high-level reasoning; high-level semantic understanding; traffic patterns; traffic scenes; vehicle-to-lane association; Geometry; Roads; Semantics; Solid modeling; Splines (mathematics); Three-dimensional displays; Vehicles;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision (ICCV), 2013 IEEE International Conference on
Conference_Location :
Sydney, NSW
ISSN :
1550-5499
Type :
conf
DOI :
10.1109/ICCV.2013.379
Filename :
6751491
Link To Document :
بازگشت