Current Issue Cover
融合光流速度与背景建模的目标检测方法

张水发,张文生,丁欢,杨柳(中国科学院自动化研究所,北京 100190)

摘 要
为了克服传统基于像素的背景建模方法不能很好地描述背景运动的问题,提出了一种融合光流速度与背景建模的目标检测方法。结合像素的灰度信息、空间信息和时间信息计算出每个像素的光流速度,利用光流速度在时间域上的统计信息为背景建立光流速度场模型。利用建立的背景模型快速、准确地实现运动目标的检测。实验结果表明,融合光流速度的背景建模方法能有效地描述背景的运动,显著降低运动背景产生的噪音,鲁棒地实现运动目标检测。
关键词
Background modeling and object detecting based on optical flow velocity field

Zhang Shuifa,Zhang Wensheng,Ding Huan,Yang Liu(Institute of Automation, Chinese Academy of Science)

Abstract
The traditional pixelbased background model cannot represent the background motion efficiently. In this paper, a novel strategy is proposed to model background and track moving objects based on optical flow velocity field. Statistics on intensity, spatial and temporal information of pixels are extracted to generate the optical flow field, which is used to formulate a novel background model for tracking moving objects efficiently and exactly. This opticalflowfieldbased strategy can reduce noise generated by background motion significantly and track moving objects robustly, as illustrated in our experiments.
Keywords
QQ在线


订阅号|日报