| 一种飘动性分析的视频烟雾快速检测新算法 |
| |
| 引用本文： | 谢振平,王涛,刘渊,王士同.一种飘动性分析的视频烟雾快速检测新算法[J].微电子学与计算机,2011,28(10). |
| |
| 作者姓名： | 谢振平 王涛 刘渊 王士同 |
| |
| 作者单位： | 江南大学数字媒体学院,江苏无锡,214122 |
| |
| 基金项目： | 2009年度江苏省高校科研成果产业化推进项目 |
| |
| 摘 要： | 针对DSP视频监控系统中,实时视频烟雾检测功能的需求,提出一种基于烟雾飘动性分析的快速视频烟雾检测算法.相比于现有相关算法,在完成对给定视频样本学习后,该算法无需存储视频的历史帧数据,也不需要学习场景背景,而直接对原始视频图像分块提取烟雾飘动特征,然后经Bayesian决策输出检测结论.结合提出的一组新颖的视频烟雾飘动特征,新算法同时获得了较低的计算复杂度和较高的检测性能.综合来看,新算法能更好地适用于实时视频监控系统中的烟雾检测需求.
|
| 关 键 词： | 视频烟雾检测 实时监控系统 烟雾飘动性 Bayesian决策 |
A Fast Video Smoke Detection Algorithm by Analyzing Fluttering |
| |
| XIE Zhen-ping,WANG Tao,LIU Yuan,WANG Shi-tong.A Fast Video Smoke Detection Algorithm by Analyzing Fluttering[J].Microelectronics & Computer,2011,28(10). |
| |
| Authors: | XIE Zhen-ping WANG Tao LIU Yuan WANG Shi-tong |
| |
| Affiliation: | XIE Zhen-ping,WANG Tao,LIU Yuan,WANG Shi-tong(School of Digital Media,Jiangnan University,Wuxi 214122,China) |
| |
| Abstract: | Towards the requirement of real-time smoke detection in DSP surveillance system,a novel fast video smoke detection algorithm is proposed.Compared with current video smoke detection algorithms,new algorithm does not demand storing historic frame images of video sequence,and does not require learning background image of monitoring scene.According to extracted fluttering characteristics of smoke for independent image block,Bayesian decision method is used to determine whether smoke is existent.Derived from abo... |
| |
| Keywords: | video smoke detection real-time surveillance system fluttering characteristics of smoke bayesian decision |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
