 |
International Journal of Computer Science and Research
ISSN : 2210-9668
|
|
|
|
Abstract
| Title |
: |
RBF Approach to Background Modelling for Background Subtraction in Video Objects |
| Authors |
: |
Sivabalakrishnan.M, Dr.D.Manjula |
| Keywords |
: |
Background Subtraction, Foreground Detection, neural network, RBF |
| Issue Date |
: |
September 2010 |
| Abstract |
: |
Background Subtraction is a widely used approach to detect moving objects from static cameras. Many different methods have been proposed over the recent years and there are a number of object extraction algorithms proposed in the literature, most approaches work efficiently only in constrained environments where the background is relatively simple and static. Nowadays background modeling and subtraction algorithms are commonly used in object detection and tracking applications. The goal is to obtain a clean background and then detect moving objects by comparing it with the current frame. This paper presents a RBF neural network architecture is proposed to form an unsupervised Bayesian classifier for this application domain. The constructed classifier efficiently handles the segmentation in natural-scene sequences with complex background motion and changes in illumination. The weights of the proposed RBF serve as a model of the background and are temporally updated to reflect the observed statistics of background. The segmentation performance of the proposed RBF neural network is qualitatively and quantitatively examined and compared with fuzzy and classical background subtraction method. Our experimental results demonstrate that proposed system is much more efficient, robust and accurate than classical approaches |
| Page(s) |
: |
35-42 |
| ISSN |
: |
2210-9668 |
| Source |
: |
Vol. 1, No.1 |
|
|
|
|
|