机器视觉中基于彩色伪随机编码特征点匹配的研究  

The correspondence between the surface to be recovered and its images based on multicolor pseudo-random array in machine vision

作　　者：廖素引[1] 马修水[1] 费业泰[2] 李桂华[1] 

机构地区：[1]安徽大学电子科学与技术学院,合肥230039 [2]合肥工业大学仪器仪表学院,合肥230009

出　　处：《现代制造工程》2008年第4期16-18,57,共4页Modern Manufacturing Engineering

基　　金：国家自然科学基金资助项目(50275049)

摘　　要：为研究基于单幅二维图像不标定欧氏重构三维场景的理论,介绍一种采用伪随机编码结构光照明主动视觉技术。利用伪随机序列的窗口特性,使被编码结构光照明的场景表面每一个特征点都具有唯一的代码,可以唯一地被辨识。实验表明,该编码结构光主动视觉系统,可以比较容易地解决被动视觉系统中难以解决的特征点匹配问题,实验效果良好。In order to study the theory of uncalibrated 3D Euclidean reconstruction based on single image. Introduces an effective active-machine technique with structured light illumination which applies pseudo-random color code. Each interest point on scene surface can be identified exclusively according to the window property of pseudo-random array. It is found out that this active machine system can solve the correspondence between images in the passive machine system. The results of the experiment are satisfying.

关 键 词：机器视觉 主动视觉系统 伪随机编码原理 特征点匹配 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]