Computer Engineering and Applications ›› 2007, Vol. 43 ›› Issue (30): 50-52.

• 学术探讨 • Previous Articles     Next Articles

Study on camera calibration for binocular vision based on GEP

CHEN Yun-liang1,YANG Juan1,YANG Jie2,LI De-hua2   

  1. 1.Department of Computer,China University of Geosciences,Wuhan 430074,China
    2.Institute of Pattern Recognition and Artificial Intelligence,Huazhong University of Science and Technology,Wuhan 430074,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-10-21 Published:2007-10-21
  • Contact: CHEN Yun-liang

基于GEP的双目视觉摄像机标定方法研究

陈云亮1,杨 娟1,杨 捷2,李德华2   

  1. 1.中国地质大学 计算机学院,武汉 430074
    2.华中科技大学 图像识别与人工智能研究所,武汉 430074
  • 通讯作者: 陈云亮

Abstract: To achieve precise visual measurement,an accurate camera calibration method is required,and traditional binocular calibration metods have many limitation.A novel method in camera calibration for binocular vision is proposed and implemented.It introduces the Genetic Expression Programming(GEP) theory to discover valid coordinate model automatically.Compares with traditional algorithm,the experiments show that the proposed binocular calibration method based on GEP can effectively obtain high accuracy and speed up the algorithm remarkably.It also has a practical value.

摘要: 摄像机标定是精密视觉测量的基础,传统的标定方法具有很多的缺陷。提出了一种新的双目视觉摄像机标定方法,通过引入基因表达式程序设计算法,挖掘其中潜在的坐标函数关系。将GEP标定方法与同类方案进行了比较,实验结果表明:新算法有效地提高了标定精度,加快了运算时间,具有较高的实用价值。