基于码本模型和多特征的早期烟雾检测  

Early smoke detection based on codebook model and multiple features

作　　者：姜明新[1,2] 王洪玉[1] 蔡兴洋[1] 

机构地区：[1]大连理工大学电子信息与电气工程学部,大连116024 [2]大连民族学院信息与通信工程学院,大连116600

出　　处：《中国图象图形学报》2012年第9期1102-1108,共7页Journal of Image and Graphics

基　　金：国家自然基金项目(61172058);中央高校基本科研业务费专项基金项目(DC10010103);辽宁省教育厅基金项目(L2012476)

摘　　要：提出一种基于码本模型和多特征的早期烟雾检测算法。首先,利用码本模型进行前景提取;然后,结合烟雾的颜色模型和形状特征模型检测前景中的疑似烟雾区域;最后,利用烟雾的动态特性,有效地降低误检率,提高算法的鲁棒性。通过ROC曲线对比,实验结果表明,该算法具有良好的烟雾检测能力。同时,能够满足实时性要求,具有较高的实用价值。An early smoke detection algorithm based on codebook model and multiple features is presented in this paper. First, the foreground is obtained by using the codebook algorithm. Second, the model of color distribution and the model of shape feathers of smoke are applied to detect the suspected smoke area in the foreground. Finally, the false alarm rate is re-duced effectively by using dynamic features in the diffusion process of smoke. Comparing with other algorithms using ROC curve, the experimental results show that our algorithm has good detection performance and achieves real-time requirement which is very important for many apphcations.

关 键 词：烟雾检测 码本模型 多特征 ROC曲线 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]