计算机应用 ›› 2013, Vol. 33 ›› Issue (08): 2341-2345.

• 多媒体处理技术 • 上一篇    下一篇

彩色结构光系统高低强度条纹的颜色聚类方法

陆军1,高乐2,张鑫1   

  1. 1. 哈尔滨工程大学 自动化学院,哈尔滨 150001;
    2. 中国航空无线电电子研究所,上海 200233
  • 收稿日期:2013-03-06 修回日期:2013-04-27 出版日期:2013-08-01 发布日期:2013-09-11
  • 通讯作者: 陆军
  • 作者简介:陆军(1969-),男,黑龙江哈尔滨人,教授,博士,主要研究方向:计算机视觉、智能控制;
    高乐(1987-),男,辽宁铁岭人,硕士,主要研究方向:计算机视觉;
    张鑫(1988-),男,河南周口人,硕士,主要研究方向:机器人与智能控制。
  • 基金资助:
    黑龙江省自然科学基金资助项目;人力资源和社会保障部留学人员科技活动择优资助项目;中央高校基本科研业务费专项资金资助项目

Color clustering method for high and low intensity stripes of color structured light system

LU Jun1,GAO Le2,ZHANG Xin1   

  1. 1. College of Automation, Harbin Engineering University, Harbin Heilongjiang 150001,China
    2. Chinese Aeronautical Radio Electronics Research Institute, Shanghai 200233,China
  • Received:2013-03-06 Revised:2013-04-27 Online:2013-09-11 Published:2013-08-01
  • Contact: LU Jun

摘要: 基于De Bruijn序列的彩色结构光编码作为空间编码的一种,具有测量速度快的特点。其中,彩色条纹的识别是关键问题之一。针对高低强度相间的4色De Bruijn序列条纹投射模式的特点,在L*a*b*颜色空间中,通过L值的线性二次差分滤波实现了对捕获的彩色结构光高低强度条纹的分割。利用主成分分析和K均值聚类思想,设计了自适应颜色聚类方法,实现了对4种高低强度颜色的识别。实验结果表明,该方法对环境光等因素具有较好的鲁棒性,满足彩色结构光视觉测量对精度要求高以及信息提取简单的要求。

关键词: De Bruijn序列, 条纹分割, K均值, 颜色聚类, 主成分分析

Abstract: Color coded structured light based on De Bruijn sequence is a kind of spatial code method that is characterized by rapid shape measurement. The recognition of color stripes is a key issue. Considering projected De Bruijn stripe pattern combining four colors with high and low intensity, segmentation of high and low intensity stripes was implemented by using linear filter of second derivative of L channel in L*a*b* color space. Adaptive color clustering was designed by employing Principal Component Analysis (PCA) and K-means clustering. The recognition of four colors with two intensities was finished. The experimental results indicate that the proposed method is robust to factors such as ambient light and it satisfies demand for high precision and simple extraction of information to structured light vision measurement.

Key words: De Bruijn sequence, stripe segmentation, K-means, color clustering, Principal Component Analysis (PCA)

中图分类号: