Title: Learning a Scene Background Model via Classification
Authors: Lin, Horng-Horng
Liu, Tyng-Luh
Chuang, Jen-Hui
資訊工程學系
Department of Computer Science
Keywords: Background modeling;boosting;classification;tracking;SVM
Issue Date: 1-May-2009
Abstract: Learning to efficiently construct a scene background model is crucial for tracking techniques relying on background subtraction. Our proposed method is motivated by criteria leading to what a general and reasonable background model should be, and realized by a practical classification technique. Specifically, we consider a two-level approximation scheme that elegantly combines the bottom-up and top-down information for deriving a background model in real time. The key idea of our approach is simple but effective: If a classifier can be used to determine which image blocks are part of the background, its outcomes can help to carry out appropriate blockwise updates in learning such a model. The quality of the solution is further improved by global validations of the local updates to maintain the interblock consistency. And a complete background model can then be obtained based on a measurement of model completion. To demonstrate the effectiveness of our method, various experimental results and comparisons are included.
URI: http://dx.doi.org/10.1109/TSP.2009.2014810
http://hdl.handle.net/11536/7264
ISSN: 1053-587X
DOI: 10.1109/TSP.2009.2014810
Journal: IEEE TRANSACTIONS ON SIGNAL PROCESSING
Volume: 57
Issue: 5
Begin Page: 1641
End Page: 1654
Appears in Collections:Articles


Files in This Item:

  1. 000265437900001.pdf