High Impact Factor : 4.396 icon | Submit Manuscript Online icon |

Real-time Fire Detection for Video Surveillance Applications using Multi Experts System.(FULL)

Author(s):

Sanket R.Salve , GES'S R.H.Sapat college of engginering,nashik; Siddhant S. Shinde, GES'S R.H.Sapat college of engginering,nashik; Sayali P. Patil, GES'S R.H.Sapat college of engginering,nashik; Vikas B.Shelke, GES'S R.H.Sapat college of engginering,nashik

Keywords:

Image Segmentation, Bag-of-Words, Fire Detection

Abstract

In this proposed system the method able to detect fire by analyzing the Videos acquired by surveillance cameras is introduced. Two main novelties have been introduced first, complementary Information, respectively based on colour, shape variation and Motion analysis, are combined by a multi expert system. Second, a novel descriptor based on a bag-of-words approach has been proposed for representing motion. The previous systems were developed but the results were not much significant as they were having their own limitations. Some of them were working on colour while some on shape or motion hence they had own drawbacks. Our system will try to overcome those as we are proposing the system that will have a separate module for shape variation, a module for colour evaluation and a module for motion evaluation. The multi expert based system takes the input of all this modules and then the decisions taken by the experts are combined by a MES (multi expert system) classifier based on a weighted voting rule, which finally assigns a class to each blob. The Main advantage deriving from this approach lies in the fact that the overall performance of the system can be significantly increases with a relatively small effort.

Other Details

Paper ID: IJSRDV4I40102
Published in: Volume : 4, Issue : 4
Publication Date: 01/07/2016
Page(s): 20-23

Article Preview

Download Article