融合色彩和轮廓特征的火焰检测
Fusion of Flame Color and Its Contour for Fire Detection
-
摘要: 基于图像的火焰检测能适应大空间和恶劣环境火灾预防应用的需要, 首先分析了火焰图像的色彩及轮廓信息等重要特征, 然后提出了基于连通区域面积阈值化的单像素宽度目标轮廓特征的抽取方法, 再应用所建立的火焰检测色彩模型, 融合火焰色彩和边缘轮廓动态变化等特性, 实现了在视频序列图像中火焰的自动检测.实验结果显示, 该方法能实时检测火焰, 误判率低.Abstract: Fire detection based on sequences of images is more suitable for the need in big room or badly environment.Color and contour are the important features of a flame image.A new color model used to detect flame in an image is found.The method to extract the contour feature of a flame image is also developed based on threshold of flame area.According to the color distribution and comparability of the edge of flame in image sequences, flames in video sequences are detected by fusion of its color information and dynamic contour.Many experiments show that the system is able to work well and get high detection rate with a low false positive rate.