Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Monocular 3D scene modeling and inference: Understanding multi-object traffic scenes

 
: Wojek, Christian; Roth, Stefan; Schindler, Konrad; Schiele, Bernt

:

Daniilidis, K.:
Computer Vision. ECCV 2010, 11th European Conference on Computer Vision. Proceedings. Pt.IV : Heraklion, Crete, Greece, September 5-11, 2010
Berlin: Springer, 2010 (Lecture Notes in Computer Science 6314)
ISBN: 3-642-15560-X
ISBN: 978-3-642-15560-4
ISBN: 978-3-642-15561-1
ISSN: 0302-9743
S.467-481
European Conference on Computer Vision (ECCV) <11, 2010, Heraklion>
Englisch
Konferenzbeitrag
Fraunhofer IGD ()
Traffic analysis; 3D tracking; scene understanding; sampling; Forschungsgruppe Visual Inference (VINF)

Abstract
Scene understanding has (again) become a focus of computer vision research, leveraging advances in detection, context modeling, and tracking. In this paper, we present a novel probabilistic 3D scene model that encompasses multi-class object detection, object tracking, scene labeling, and 3D geometric relations. This integrated 3D model is able to represent complex interactions like inter-object occlusion, physical exclusion between objects, and geometric context. Inference allows recovering 3D scene context and performing 3D multiobject tracking from a mobile observer, for objects of multiple categories, using only monocular video as input. In particular, we show that a joint scene tracklet model for the evidence collected over multiple frames substantially improves performance. The approach is evaluated for two different types of challenging onboard sequences. We first show a substantial improvement to the state-of-the-art in 3D multi-people tracking. Moreover, a similar performance gain is achieved for multi-class 3D tracking of cars and trucks on a new, challenging dataset.

: http://publica.fraunhofer.de/dokumente/N-141696.html