广东工业大学学报 ›› 2013, Vol. 30 ›› Issue (4): 65-69.doi: 10.3969/j.issn.1007-7162.2013.04.011

• 综合研究 • 上一篇    下一篇

基于biSCAN和SVM的机器人目标识别新算法研究

夏琴晔,杨宜民   

  1. 广东工业大学 自动化学院,广东 广州 510006
  • 收稿日期:2012-12-28 出版日期:2013-12-30 发布日期:2013-12-30
  • 作者简介:夏琴晔(1987-),女,硕士研究生,主要研究方向为控制理论与控制工程.
  • 基金资助:

    广东省自然科学基金资助项目(S2011010004006)

Research on a New Algorithm for Robots  Recognition of Objects Based on biSCAN and SVM

Xia Qin-ye,  Yang Yi-ming   

  1. School of Automation, Guangdong University of Technology, Guangzhou 510006,China
  • Received:2012-12-28 Online:2013-12-30 Published:2013-12-30

摘要: 针对机器人足球比赛环境容易受光照变化影响,造成目标识别率低、光照自适应性差的问题,采用c1c2 c3彩色不变的特征,利用biSCAN算法设置一系列从圆形图像中心出发且与图像半径为同方向的径向扫描线来提取目标所在区域,并用支持向量机(support vector machine,SVM)进行目标识别.实验表明,该方法提高了目标识别率,具有较强的光照自适应能力.

关键词: 机器人;c1c2 c3彩色不变特征;biSCAN;支持向量机

Abstract: Robot soccer environment is vulnerable to changes in illumination, which results in the low recognition rate, the poor illumination adaptability. In order to solve these problems, it adopts c1c2 c3  color invariant features, uses biSCAN to set a few ways of radial scanning which start from the image center and along the radius to extract the object area, and then uses SVM to recognize the object. Experimental results show that the method improves the object recognition rate and the ability to adapt to illumination.

Key words: robot;c1c2 c color invariant features; biSCAN; support vector machine(SVM)

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!