Video-Based Early Flame Detection for Vessels by Using the Fuzzy Color Clustering Algorithm

Abstract

This paper presents a video-based flame alarm detection method for vessels to detect the flames by using clustering algorithm. First, the dominant flame color lookup table (DFCLT) is created by using the fuzzy c-means clustering algorithm. Then, the changed video frames are automatically selected, and the changed regions are figured out from these frames. Finally, we announce elementary, medium, or emergency flame alarms by comparing the pixels of changed regions with the DFCLT. The experimental results indicate that the proposed flame detection approach can detect dangerous flames, effectively and efficiently.