一种基于背景剪除的视频检测方法  

Detection of object security in crowed environment

作　　者：苏锡杰 邹星星[2] 

机构地区：[1]广西福利彩票发行中心,广西南宁530022 [2]广西大学计算机与电子信息学院,广西南宁530004

出　　处：《大众科技》2015年第12期3-5,8,共4页Popular Science & Technology

摘　　要：文章主要针对视频监控系统中滞留物体和遗失物体的侦测问题,提出了一种实时的监测方法。该方法主要包括以下步骤:首先,利用背景剪除算法进行目标物体的分割;然后,将提取目标划分为动态或静态物体;最后,采用一种决策模型计算所发生事件的置信度,并且在置信度偏离设定阈值时自动触发警报。实验结果验证文章算法有效性。This paper aimed at automatic identifies events of abandoned and stolen objects detection in video surveillance system, a new method was proposed. The method mainly include following steps： the first processing phrase is object extraction, involving a background subtraction algorithm which dynamically updates background. Extracted objects are classified as static or dynamic objects. Last, a decision-making model is employed to calculate a confidence score for the classification about event, and an alarm will be automatically triggered if the score of corresponding action is higher than a pre-defined threshold. Also, the robustness and efficiency of the method was tested.

关 键 词：视频监控 双重背景剪除 目标分类 决策模型 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]