计算机应用与软件2016，Vol.33Issue(12)：248-252,5.DOI:10.3969/j.issn.1000-386x.2016.12.059
基于视频的实时烟雾检测算法
REAL-TIME SMOKE DETECTION ALGORITHM BASED ON VEDIO
摘要
Abstract
In order to solve the three problems of low accuracy,poor adaptability and slow speed,and improve the efficiency of real-time smoke detection,a modified block based real-time smoke detection algorithm is put forward.Firstly,motion blocks are obtained by background subtraction method and the model of normalized YIQ color space will be used for the color detection.Then the motion blocks in connected are-as are used to estimate the direction of the fast movement on a time domain,and the smoke area is obtained.Finally,the influence of abnormal movement piece is eliminated.The experimental results show that the algorithm is simple and effective.Besides,it is able to compute rapidly and adapt to the scene illumination change,detecting the smoke in real time.关键词
烟雾检测/实时/背景减除/运动块Key words
Smoke detection/Real time/Background subtraction/Motion block分类
信息技术与安全科学引用本文复制引用
张建明,黄继风..基于视频的实时烟雾检测算法[J].计算机应用与软件,2016,33(12):248-252,5.基金项目
上海市教委科研创新重点项目（14ZZ125）。 （）
