TU Berlin

Communication Systems GroupScientific Publications

Page Content

to Navigation

Scientific Publications

Splitting Gaussians in Mixture Models
Citation key 1363Evangelio2012
Author Rubén Heras Evangelio and Michael Pätzold and Thomas Sikora
Title of Book 9th IEEE International Conference on Advanced Video and Signal-Based Surveillance
Year 2012
DOI 10.1109/AVSS.2012.69
Address Beijing, China
Month sep
Note ISBN: 978-1-4673-2499-1
Abstract Gaussian mixture models have been extensively used and enhanced in the surveillance domain because of their ability to adaptively describe multimodal distributions in real-time with low memory requirements. Nevertheless, they still often suffer from the problem of converging to poor solutions if the main mode stretches and thus over-dominates weaker distributions. Based on the results of the Split and Merge EM algorithm, in this paper we propose a solution to this problem. Therefore, we define an appropriate splitting operation and the corresponding criterion for the selection of candidate modes, for the case of background subtraction. The proposed method achieves better background models than state-of-the-art approaches and is low demanding in terms of processing time and memory requirements, therefore making it especially appealing in the surveillance domain.
Link to publication Download Bibtex entry


Quick Access

Schnellnavigation zur Seite über Nummerneingabe