一种基于粗糙集的火焰区域提取方法

A Rough Sets Based Flame Regions Detecting Method

针对目前基于视频的火焰区域提取方法的不足,提出了一种基于粗糙集的火焰区域提取方法。该方法通过综合分析火焰区域在HSI、RGB色彩空间中的分布规律,以及火焰区域的色彩分布特征和闪烁特征,依据粗糙集理论对被检测的视频图像进行子图像划分,并在此基础上利用集合运算提取火焰区域。实验表明,该方法具有较好的准确性、可靠性和鲁棒性。

The theory of the rough sets is a new mathematics tool which is used to process fuzzy and indetermination problem. A flame regions detecting method based on rough sets is put forward, which combines color analysis of flame regions based on the HSI and RGB color models, spatial color variation analysis and flame flicker analysis. Using this new method, an image is divided into different several sub-images based on rough sets. The flame regions are detected with set operations. The experimental results show that the flame detecting method is accurate, effective, and robust.