Video Analysis and Knowledge based Fire Detection

S. Liu, Z. Man, S. Kumar, and Y. Cai (Singapore)


Fire detection, Surveillance system, Video analysis.


This objective of this project is to design a robust algorithm for detecting the fire at the earliest stage. The major techniques used in the project are video analysis and knowledge-based inference rule. Key issues for the proposed system include background learning and updating, foreground segmentation, features extraction, and decision-making process. Three features are defined to describe the nature of a fire: number of pixels occupied by the foreground, pixel intensity and color temperature. Experimental results are given in support of good performance of the new algorithm for fire detection.

Important Links:

Go Back