PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Probabilistic Parameter Selection for Learning Scene Structure from Video
Michael Breitenstein, Eric Sommerlade, Bastian Leibe, Luc Van Gool and Ian Reid
In: BMVC 2008, September 2008, Leeds, UK.


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.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
ID Code:5045
Deposited By:Michael Breitenstein
Deposited On:24 March 2009