摘要
运动目标检测是智能视觉监控系统的重要组成部分,其主要功能是检测监控场景中的运动目标,为高层运动分析提供必要的信息。文章提出一种快速运动目标检测算法,以帧差法和背景减法为基础,快速实现背景提取、背景更新、运动目标检测的功能。实验结果表明,该算法计算量小,检测目标完整,能够满足实时监控系统的要求。
The moving object detection technology is the most basic composition of the intelligent video surveillance system,which can detect the moving object in a visual scene and provide the necessary data for advanced motion analysis.A fast detection algorithm for moving object is presented in this paper,which integrates the temporal difference method and the background subtraction method.The background modeling,background update and moving object detection can be implemented quickly by using the algorithm.The experimental results show that the algorithm is efficient in computation and the detected object is integral.It can satisfy the requirement of the real-time video surveillance system.
出处
《合肥工业大学学报（自然科学版）》
CAS
CSCD
北大核心
2012年第2期180-183,共4页
Journal of Hefei University of Technology：Natural Science
基金
安徽省科技计划资助项目(08020303095)
关键词
视频监控
运动目标检测
时域差分
背景减除
video surveillance
moving target detection
temporal difference
background subtraction
