摘要
在分析Intel开源计算机视觉库OpenCV及CVUT特点的基础上,结合畸变参数的影响,研究了摄像机模型和坐标转换关系,以及双目图像三维重构过程,提出一种基于CVUT的摄像机标定方法和双目图像三维重构方法.实验表明,该方法与传统的OpenCV标定方法以及Matlab的标定方法相比,标定周期短、精度较高,可以较好地构建二维图像的三维信息,程序执行稳定且鲁棒性较强,可广泛用于立体视觉等领域.
The Intel open-source computer vision library OpenCV and CVUT is introduced firstly.Considering the distortion parameter influence,the camera model and coordinate transformation is analyzed,as well as binocular image 3Dreconstruction process.A calibration method and binocular image3 Dreconstruction procedures based on CVUT is proposed.By comparing with traditional calibration methods which based on OpenCV or Matlab,it is shown that the method has short calibration cycle and high precision,and can build a better 3Dinformation of the two dimensional image.The program is stable and robust,and can be widely used in stereo vision,etc.
作者
周鹏
车进
张英
Zhou Peng Che Jin Zhang Ying(School of Physics and Electronic-Electrical Engineering, Ningxia University, Yinchuan 750021, China Ningxia Key Laboratory of Intelligent Sensing for Desert Information, Ningxia Vniversity, Yinchuan 750021, China)
出处
《宁夏大学学报（自然科学版）》
CAS
2016年第3期306-310,共5页
Journal of Ningxia University(Natural Science Edition)
基金
国家自然科学基金资助项目(61162020)
关键词
OPENCV
CVUT
摄像机标定
三维重构
open source computer vision
computer vision utility tools
camera calibration
3D reconstruction
