A Local Discriminative Model for Background Subtraction

Adrian Ulges; Thomas Breuel

In: 30th Annual DAGM Symposium. Annual Symposium of the German Association for Pattern Recognition (DAGM-2008), June 10-13, Munich, Germany, Pages 507-516, Springer, 6/2008.


Conventional background subtraction techniques that up- date a background model online have difficulties with correctly segment- ing foreground objects if sudden brightness changes occur. Other meth- ods that learn a global scene model offline suffer from projection errors. To overcome these problems, we present a different approach that is local and discriminative, i.e. for each pixel a classifier is trained to decide whether the pixel belongs to the background or foreground. Such a model requires significantly less tuning effort and shows a better robustness, as we will demonstrate in quantitative experiments on self-created and standard benchmarks. Finally, segmentation is improved by 18 % by integrating the probabilistic evidence provided by the local classifiers with a graph cut segmentation algorithm.


2008-IUPR-17Mar_1723.pdf (pdf, 731 KB )

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence