基于连续帧图像面积变化的火灾探测方法

A fire detection method based on the area variety of consecutive frames

针对传统视频火灾探测方法误报率高、适用性弱的缺点,基于火焰在连续帧图像上的面积变化规律,提出了一种新的火灾探测方法。首先利用RGB-HSI颜色模型筛选出单帧图像中的疑似火焰区域,再结合区域跟踪算法和面积极大值统计计算出疑似火焰区域的闪烁频率,从而实现火灾探测。酒精火和远距离强光背景下的火焰探测实验证明:该方法能够排除常见干扰源的影响,对于室内火灾探测具有一定的实用价值。

Against the week robustness to interference and poor adaptability of traditional video fire detection method, and based on the flame area variety of consecutive frames, a new fire detection method was proposed. Firstly, the areas similar to fire are detected out through RGB--HIS color model. Then, the flicker frequency of these areas was calculated with region tracking algorithm and maximum areas statistics, and the fire areas were detected out. Experiments of alcohol fire and flame detection in the background of long distance light showed that the proposed method can eliminate the influence of common in- terferences, and has a certain practical significance for indoor fire detection.