基于YCbCr颜色空间的火焰图像分割方法

Flame image segmentation method based on YCbCr color space

视频火焰检测对消防安全具有重要的实际意义。火焰颜色信息在视频火灾检测中起着举足轻重的作用,众多学者提出了基于不同颜色空间的多种火焰颜色检测算法。针对目前视频火焰颜色检测算法检测率低、误检率高、适应性差等不足,提出基于颜色空间的火焰图像分割方法。通过研究火焰图像在颜色空间上的分布情况,分析火焰像素对应的Y,Cb和Cr分量的关系,总结出火焰像素的约束条件。在不同场景下进行火焰目标提取,通过与文献中其他三种方法比较表明提出的方法检测率高、误报率低,并具有较好的适应性。

Video fire detection has important practical significance for fire safety. The flame color information plays an important role in video file detection,and many scholars have presented a variety of flame color detection algorithms based on different color space. Aimed at low detection rate, high false-alarm rate and poor adaptability in current flame color detection algorithm, a flame color segmentation method based on YCbCr color space is proposed. The constraints of the flame pixels is summed up by studying the distribution of the flame in YCbCr color space and the relationship between the Y, Cb and Cr components of flame pixels. The performance of the proposed method is tested under different scenarios ,the results are compared with three other methods in the literature and the proposed method is shown to have a higher detection rate,a lower false rate and better adaptability.