This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Search for Publication

Year(s) from:  to 
Keywords (separated by spaces):

Probabilistic Parameter Selection for Learning Scene Structure from Video

Michael D. Breitenstein, Eric Sommerlade, Bastian Leibe, Luc van Gool and Ian Reid
British Machine Vision Conference (BMVC'08)
Leeds, September 2008


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.

Download in pdf format
  author = {Michael D. Breitenstein and Eric Sommerlade and Bastian Leibe and Luc van Gool and Ian Reid},
  title = {Probabilistic Parameter Selection for Learning Scene Structure from Video},
  booktitle = {British Machine Vision Conference (BMVC'08)},
  year = {2008},
  month = {September},
  keywords = {}