基于超像素分割与闪频特征判别的视频火焰检测  

Video Flame Detection Based on Super Pixel Segmentation and Flash Frequency Feature Discrimination

作　　者：张慧珍[1,2] 严云洋 刘以安[1] 周静波 高尚兵[2] Zhang Huizhen1,2 ,Yan Yunyang1,2 , Liu Yi＇an1 , Zhou Jingbo2 , Gao Shangbing2(1. School of Internet of Things Engineering, jiangnan University, Wuxi, 214122, China; 2. Faculty of Computer ＆ Software En gineering, Huaiyin Institute of Technology, Huaian, 223003, Chin)

机构地区：[1]江南大学物联网工程学院,无锡214122 [2]淮阴工学院计算机与软件工程学院,淮安223003

出　　处：《数据采集与处理》2018年第3期512-520,共9页Journal of Data Acquisition and Processing

基　　金：国家自然科学基金(61402192)资助项目;江苏省"六大人才高峰"(2013DZXX-023)资助项目;江苏省"333工程"(BRA2013208)资助项目;江苏省"青蓝工程"资助项目;淮安市"533工程"资助项目;淮安市科技计划(HAG2013057;HAG2013059)资助项目

摘　　要：视频监控已经成为当今火灾防范的主要方法。视频火焰算法层出不穷,但多为训练各种分类器做最后的分类,这需要提前准备大量相关的视频火焰样本来做训练,在视频火焰样本不够的情况下往往不能达到很高的检测率。本文提出一种基于超像素分割并结合闪频特征进行判断识别的方法。首先在Lab颜色空间上利用超像素分割方法将待检测图像分割出近似均匀的若干个小区域,并以其形心点代表一个超像素,结合RGB颜色空间与Lab颜色空间中的静态特征,根据提出的一定规则提取出火焰候选区域,最终利用此区域内提取的闪频特征判别其是否为火焰。实验证明,该算法在样本较少的情况下检测率较高。Fire prevention has gradually dominated by video surveillance. There are many various algorithms of video flame,but most of them require lots of video flame samples to perform the training for the final classification. The results often fail to achieve a high detection rate if flame samples are not enough. So a new method that uses the super pixel segmentation and the flash frequency for recognition is proposed in this paper. In the Lab color space,the cencroids of each region are represented as a super pixel after some approximate homogeneous regions are segmented in the flame picture based on super pixel segmentation. The candidate regions are extracted based on the RGB and Lab color features according to some rules. At last whether the candidate region is a flame is determined by the flash frequency characteristics. Experimental result presents good performance with high detection rate in the case of small samples.

关 键 词：火焰检测 超像素分割 颜色模型 闪频判别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]