欢迎访问《兵工学报》官方网站,今天是

兵工学报 ›› 2005, Vol. 26 ›› Issue (6): 766-770.

• 论文 • 上一篇    下一篇

基于计算机视觉的人体运动目标检测

傅莉1,2,方帅1,徐心和1,3   

  1. 1.东北大学教育部暨辽宁省流程工业综合自动化重点实验室,辽宁沈阳110004; 2.沈阳大学机械工程学院,辽宁沈阳110044;3.清华大学智能技术与系统国家重点实验室,北京,100084
  • 收稿日期:2004-12-01 上线日期:2014-12-25
  • 通讯作者: 傅莉
  • 基金资助:
    国家自然科学基金资助项目(60475036)

Human Motion Target Detection Based on Computer Vision

FU Li1,2, FANG Shuai1, XU Xin-he1,3   

  1. 1. Key Laboratory of Process Industry Automation, Ministry of Education, Northeastern University, Shenyang,Liaoning 110004,China; 2. School of Mechanical Engineering, Shenyang University, Shenyang, Liaoning 110044,China; 3.The State Key Laboratory of Intelligence Technology and System, Tsinghua University, Beijing 100084,China
  • Received:2004-12-01 Online:2014-12-25
  • Contact: FU Li

摘要: 基于计算机视觉的人体运动目标检测是计算机视觉领域中倍受关注的前沿课题。本文采用小波变换的方法,有效地处理了普通CCD摄像机所采集的人体运动图像的模糊,同时,去除了阴影对图像处理的负面影响,较好地提取出基于标志点的人体运动图像的边缘,为人体步态分析系统的研发提出了一个切实可行的方法。

关键词: 信息处理技术 , 计算机图像处理 , 目标检测 , 小波变换 , 图像恢复 , 阴影去除

Abstract: Human motion target detection based on computer vision is a cutting edge research topic causing in?creasing attention in the field of computer vision research. Wavelet transform method was used to solve for the ambiguous edges in human motion imaging. The shadow ’ s negative effect to the image processing was removed. The edge’s extraction was successfully realized. So this is an effective method for the research of human motion analysis system.

Key words: information processing technique , computer image processing , object detection , wavelet transform , image restoration , shadow removing

中图分类号: