基于图像特征的火焰识别与检测技术研究  

Research on the detection and identification technology based on the features of fire image

作　　者：仇国庆[1] 陈军鸽[1] 李明[1] 涂乐飞[1] 

机构地区：[1]重庆邮电大学网络化控制与智能仪器仪表教育部重点实验室,重庆400000

出　　处：《自动化与仪器仪表》2012年第3期25-27,共3页Automation & Instrumentation

基　　金：重庆市重点自然科学基金项目支持(CSTC;2009BA0040);国家自然科学基金项目支持(60905066)

摘　　要：提出了一种基于火焰图像特征的火灾火焰检测及识别算法。将火焰颜色、变化率作为火灾火焰检测与识别的判据,在火焰颜色模型和变化率的基础上引入火焰尖角以及圆形度对火灾火焰图像进行进一步判定。实验结果表明,该算法能有效提高火灾火焰检测与识别的准确率,排除干扰源。An algorithm of fire detection and recognition is put forward.The flame＇s color and movement characteristics are chosen as the criteria.The fire images are further detected and recognized by the algorithm of the flame sharp and flame circularity based on an analysis of the flame model and the differential model.The results of the experiments show that this algorithm can successfully detect and recognize the gas fire.

关 键 词：火焰图像 火焰颜色模型 变化率 火焰尖角 火焰圆形度 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]