摘要
提出了一种采用烟雾颜色混合模型和多特征组合的视频烟雾检测算法。首先利用混合高斯背景模型提取烟雾视频的运动区域;然后使用新的烟雾颜色混合模型从运动区域中确定出疑似烟雾区域;最后采用烟雾的动态特征(运动速度均值和方差,运动方向,面积增长率)组合分析对疑似烟雾区域进行烟雾识别,剔除非烟雾区域。通过不同类型烟雾视频的实验结果表明:对于光照正常,烟雾浓的烟雾类型,本文算法取得了96.57%平均检测成功率;对于光照弱或烟雾浓度稀薄的烟雾类型,本文算法取得了87.67%平均检测成功率。
A video-based smoke detection algorithm using smoke color mixture model and multi-feature combination is proposed. The algorithm first employs mixture Gaussian background model to obtain the motion region of video, and then combines it with smoke color hybrid model to extract suspected smoke regions. Finally,the combination of smoke＇s dynamic features （mean velocity and variance of moving ve- locity, motion direction, area growth rate） is used to identify smoke and exclude non-smoke from the sus- pected smoke regions. The experimental results conducted on the different types of smoke videos show that the average detection rate of the proposed method for thick smoke with normal illumination is 96. 57% ,while that for thin smoke or smoke with weak illumination is 87.67%. The algorithm outperforms other state-of-the-art algorithms and has a wide range of applications.
出处
《光电子．激光》
EI
CAS
CSCD
北大核心
2017年第7期751-758,共8页
Journal of Optoelectronics·Laser
基金
国家自然科学基金(61401132
61501152)
浙江省自然科学基金(LY17F020027)资助项目
关键词
烟雾检测
混合高斯背景模型
烟雾颜色混合模型
动态特征
smoke detection
mixture Gaussian background model
smoke color hybrid model
dynamic characteristics
