›› 2015, Vol. 28 ›› Issue (5): 27-.

• 论文 • 上一篇    下一篇

铁路视频监控中运动目标检测算法研究

李露,詹强   

  1. (1.兰州交通大学 电子与信息工程学院,甘肃 兰州 730070;
    2.柳州铁道职业技术学院 信息技术学院,广西 柳州 545616)
  • 出版日期:2015-05-15 发布日期:2015-05-19
  • 作者简介:李露(1992—),女,硕士研究生。研究方向:铁路视频监控中运动目标的检测。Email:514409130@qq.com。詹强(1981—),男,硕士,讲师。研究方向:无线通信。

Research on Algorithm of Moving Target Detection in Railway Video Surveillance

LI Lu,ZHAN Qiang   

  1. (1.School of Electronic and Information Engineering,Lanzhou Jiaotong University,Lanzhou 730070,China;
    2.School of Information Technology,Liuzhou Railway Vocational Technical Collage,Liuzhou 545616,China)
  • Online:2015-05-15 Published:2015-05-19

摘要:

运动目标的正确检测影响着运动目标能否被正确跟踪与分类,因此成为视频监控系统研究中的一项重要课题。文中对运动目标检测算法进行研究,实现对铁路沿线前方目标的有效识别,针对得到的视频序列,通过混合高斯模型进行背景建模,并与混合差分算法结合实现前景的提取与检测。通过与混合差法相比较,其仿真结果表明,该算法具有一定的可行性。

关键词: 目标检测, 视频监控, 背景建模

Abstract:

The correct detection of moving targets ensures their correct tracking and classification.Thus it becomes an important subject in the study of the video surveillance system.This paper focuses on the research of the moving targets detection algorithm to achieve the recognition of the target ahead along the railway.First,background modeling is carried out on the video sequence through the Gauss mixture model,and together with the hybrid differential algorithm the prospects are extracted and detected.A comparison of the algorithm with the hybrid differential algorithm shows that the algorithm proposed in this paper has certain feasibility.

Key words: target detection;video surveillance;background modeling

中图分类号: 

  • TP275