Machine Vision and Applications

, Volume 20, Issue 6, pp 395–409

Non-parametric statistical background modeling for efficient foreground region detection


    • Computer Vision LabUniversity of Nevada
  • Mircea Nicolescu
    • Computer Vision LabUniversity of Nevada
  • George Bebis
    • Computer Vision LabUniversity of Nevada
  • Monica Nicolescu
    • Robotics LaboratoryUniversity of Nevada
Original Paper

DOI: 10.1007/s00138-008-0134-2

Cite this article as:
Tavakkoli, A., Nicolescu, M., Bebis, G. et al. Machine Vision and Applications (2009) 20: 395. doi:10.1007/s00138-008-0134-2


Most methods for foreground region detection in videos are challenged by the presence of quasi-stationary backgrounds—flickering monitors, waving tree branches, moving water surfaces or rain. Additional difficulties are caused by camera shake or by the presence of moving objects in every image. The contribution of this paper is to propose a scene-independent and non-parametric modeling technique which covers most of the above scenarios. First, an adaptive statistical method, called adaptive kernel density estimation (AKDE), is proposed as a base-line system that addresses the scene dependence issue. After investigating its performance we introduce a novel general statistical technique, called recursive modeling (RM). The RM overcomes the weaknesses of the AKDE in modeling slow changes in the background. The performance of the RM is evaluated asymptotically and compared with the base-line system (AKDE). A wide range of quantitative and qualitative experiments is performed to compare the proposed RM with the base-line system and existing algorithms. Finally, a comparison of various background modeling systems is presented as well as a discussion on the suitability of each technique for different scenarios.


Non-parametric density estimationRecursive modelingBackground subtractionBackground modelingQuasi-stationary backgrounds

Copyright information

© Springer-Verlag 2008