计算机工程与应用 ›› 2010, Vol. 46 ›› Issue (26): 5-6.DOI: 10.3778/j.issn.1002-8331.2010.26.002

• 博士论坛 • 上一篇    下一篇

强噪声场景下运动模板的检测与跟踪技术研究

吴 刚1,2,唐振民2,杨静宇2   

  1. 1.南京工程学院 车辆工程系,南京 211167
    2.南京理工大学 计算机科学与技术学院,南京 210094
  • 收稿日期:2010-04-14 修回日期:2010-07-26 出版日期:2010-09-11 发布日期:2010-09-11
  • 通讯作者: 吴 刚

Detection and tracking based on motion template under strong disturbance

WU Gang1,2,TANG Zhen-min2,YANG Jing-yu2   

  1. 1.Department of Vehicle Engineering,Nanjing Institute of Technology,Nanjing 211167,China
    2.School of Computer Science & Technology,Nanjing University of Science and Technology,Nanjing 210094,China
  • Received:2010-04-14 Revised:2010-07-26 Online:2010-09-11 Published:2010-09-11
  • Contact: WU Gang

摘要: 针对目前多数运动车辆检测与跟踪算法在雨雪等强噪声场景下抗噪能力较弱这一难点问题,提出应用运动模板方法解决强噪声场景下运动车辆的检测与跟踪问题。通过针对标准测试视频的对比实验,相对其他几种典型的目标检测与跟踪算法,运动模板的检测方法具有以下特点:抗强噪声的能力、多目标检测和方向检测。基于车辆的检测与跟踪实验验证了运动模板方法在强噪声场景下对运动目标的实时检测与跟踪能力。

关键词: 运动检测, 跟踪, 运动模板, 强噪声

Abstract: Aiming at the difficulty on the subject about moving object’s detection and tracking,motion template is applied to resolving move vehicle’s detection and tracking under strong disturbance.Compared with other typical measurements in experiment,the method does well on several points:The ability resisting strong disturbance,multi-object’s detection and directional detection.It has as a quality of practical navigation and control about self-determined robot and unpiloted vehicle based on real-time computer vision.

Key words: movement detection, tracking, motion template, strong disturbance

中图分类号: