Non-parametric statistical background modeling for efficient foreground region detection

Authors:
Alireza Tavakkoli;Mircea Nicolescu;George Bebis;Monica Nicolescu
Affiliations:
University of Nevada, Computer Vision Lab, Reno, USA;University of Nevada, Computer Vision Lab, Reno, USA;University of Nevada, Computer Vision Lab, Reno, USA;University of Nevada, Robotics Laboratory, Reno, USA
Venue:
Machine Vision and Applications
Year:
2009

Citing 0
Cited 4

Combining SOM and local minimum enclosing spheres for novelty detection

CCDC'09 Proceedings of the 21st annual international conference on Chinese control and decision conference
Rain or Snow Detection in Image Sequences Through Use of a Histogram of Orientation of Streaks

International Journal of Computer Vision
Vision-Based Fingertip-Writing Character Recognition

Journal of Signal Processing Systems
Steering kernel-based video moving objects detection with local background texture dictionaries

Computers and Electrical Engineering

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.