Loading...
An adaptive real-time background subtraction and moving shadows detection
Author(s)
Thongkamwitoon, T.
Aramvith, S.
Chalidabhongse, T. H.
Date Issued
December 1, 2004
Type
Conference Paper
Abstract
This paper presents a statistical adaptive real-time background subtraction algorithm that is very robust to moving shadows and dynamic scene environment. The algorithm enhances the previously developed method reported in [4] by adding adaptation of modeling correspond to dynamic background using adaptive brightness and color distortion. In addition, we propose a novel "vivacity factor" to measure activities of foreground objects. It is used to delay the adaptation rate for the area of often-occurred moving foregrounds. Our method provides a solution to real-time moving object and shadow detection in dynamic background scene from video stream. We also develop the learning-rate control mechanism that was not addressed by most background subtraction algorithms.
Citation
2004 IEEE International Conference on Multimedia and Expo Icme, 2, 1459-1462, 2004