Please use this identifier to cite or link to this item:
|Scopus||Web of Science®||Altmetric|
|Title:||Probabilistic parameter selection for learning scene structure from video|
Van Gool, L.
|Citation:||Proceedings of the British Machine Vision Conference 1-4 September 2008 / M. Everingham and C. Needham (eds.): pp.32.1-32.10|
|Conference Name:||British Machine Vision Conference (19th : 2008 : Leeds, UK)|
|M. D. Breitenstein, E. Sommerlade, B. Leibe, L. Van Gool, I. Reid|
|Abstract:||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.|
|Rights:||© BMVA August 2008|
|Appears in Collections:||Computer Science publications|
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.