Sciweavers

Share

Publication

Probabilistic Parameter Selection for Learning Scene Structure from Video

9 years 12 months ago
Probabilistic Parameter Selection for Learning Scene Structure from Video
We present an online learning approach for robustly combining unreliable observations from a pedestrian detector to estimate the rough 3D scene geometry from video sequences of a static camera. Our approach is based on an entropy modelling framework, which allows to simultaneously adapt the detector parameters, such that the expected information gain about the scene structure is maximised. As a result, our approach automatically restricts the detector scale range for each image region as the estimation results become more confident, thus improving detector run-time and limiting false positives.
Michael D. Breitenstein, Eric Sommerlade, Bastian
Added 10 Dec 2009
Updated 14 Dec 2009
Type Conference
Year 2008
Where BMVC
Authors Michael D. Breitenstein, Eric Sommerlade, Bastian Leibe, Luc Van Gool, Ian Reid
Comments (0)
books