摘要
研究了一种基于大位移区域动态特征的阴燃火检测方法。利用改进的快速Horn-Schunck光流算法计算各像素点光流矢量,根据光流矢量纵向分量大小对运动区域和非运动区域进行区域分割,通过计算运动区域像素点光流矢量平均方向和平均速度对烟雾和其他干扰源进行区分,利用颜色模型对烟雾进行判断。试验表明,该算法能有效排除常见干扰源的干扰并对阴燃火进行识别,具有较高的准确性和鲁棒性。
A smoldering fire recognition method based on the dy-namic characteristics of large displacement was studied.First,an improved fast Horn-Schunck optical flow algorithm was used to ob-tain optical flow vector by which the image segmentation was per-formed on the moving area and the non-moving area according to the dynamic characteristics.By calculating the mean direction and the average velocity of the optical flow vector in the motional area,the smoke and other interference sources were distinguished.Final-ly,the smoke model was determined by the color model.Tests showed that this method can effectively eliminate the common in-terference sources and identify the smoke area with high accuracy and robustness.
作者
袁鹏
侯新国
卜乐平
欧阳继能
YUAN Peng;HOU Xin-guo;BU Le-ping;OUYANG Ji-neng(College of Electrical Engineering,Naval University of Engi.neering,Hubei Wuhan 430033,China)
出处
《消防科学与技术》
CAS
北大核心
2018年第5期597-601,共5页
Fire Science and Technology
关键词
阴燃火
检测
运动区域
动态特征
光流法
smolder
detection
moving area
dynamic characteris-tics
optical flow
