Fast background subtraction algorithm by statistical background updating

摘要：

　　As the first step of many machine vision tasks,background subtraction is required to be simple and fast.In this paper,we propose a fast background subtraction algorithm,which aims to speed up conventional algorithm by calculating distributions of foreground both in the horizontal and vertical directions instead ofconventional pixel-wise methods while updating the background.The algorithm in this paper is mainly an improvement of the multi-frame average background updating algorithm,and we use the ordinary background subtraction to obtain foreground objects.For high-resolution videos,we can use background areaswhich are not updatedfor further acceleratinginpost-processing step of background subtraction.

关键词： background subtraction background updating image processing object detection statistical method

作者: Yang Liuxu Shi Hongmei Guo Baoqing

作者单位: School of Mechanical and Electronic Control Engineering,Beijing Jiaotong University,Beijing 100044 China

会议类型: 国际会议

会议名称: The Fifth International Symposium on Test Automation & Instrumentation(2014第五届国际测试自动化与仪器仪表学术会议)

会议地点: 北京

会议语种:英文

页码: 239-245

在线出版日期: 2014-09-23（万方平台首次上网日期，不代表论文的发表时间）