摘要
传统的内窥镜只能提供清晰的图像,无法进行三维测量和三维重建。该文提出一种基于立体视觉原理的双目内窥镜系统,用于实现三维测量和三维重建,并开发了一套基于双目内窥镜的散斑三维重建系统。为了提高系统的标定精度和三维重建质量,该文提出一种高精度双目内窥镜标定参数优化方法及基于光轴双次旋转的立体校正算法。其中,测量系统由一个结构光照明系统和双目内窥镜组成。该实验首先通过结构光照明系统将带随机散斑点的图片以投影的方式将被测物体表面特征化,然后经双目内窥镜立体成像后进行极线校正和立体匹配,最后根据三角测量原理重建出物体的三维信息。实验结果表明,该系统与传统方法相比,对圆锥、球等标准体的测量精度均有显著提升。
The traditional binocular endoscope can only provide clear images,and can not carry out three-dimensional measurement/reconstruction.In this paper,a binocular endoscope system based on the stereo vision principle is proposed to realize three-dimensional measurement/reconstruction,and a speckle three-dimensional reconstruction system based on a binocular endoscope is developed.To improve the calibration accuracy and 3D reconstruction quality of the system,a high-precision binocular endoscope calibration parameters optimization method and a stereo correction algorithm based on twice rotation of the optical axis are proposed in this paper.The measurement system consists of a structured light illumination system and a binocular endoscope.Firstly,the image with random speckle is characterized by projection through the structured light illumination system,and then the epipolar correction and stereo matching are carried out after stereo imaging by the binocular endoscope.Finally,the three-dimensional information of the object is reconstructed according to the principle of triangulation.The experimental results show that compared with the traditional method,the measurement accuracy of standard bodies such as cone and ball is significantly improved.
作者
郭俊广
谷飞飞
叶于平
宋展
GUO Junguang;GU Feifei;YE Yuping;SONG Zhan(Shenzhen Institute of Advanced Technology,Chinese Academy of Sciences,Shenzhen 518055,China;University of Chinese Academy of Sciences,Beijing 100039,China;Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems,Shenzhen 518055,China)
出处
《集成技术》
2022年第1期13-26,共14页
Journal of Integration Technology
基金
广东省重点领域研发计划项目(2020B090925001)
深圳市技术攻关面上项目(JSGG20191129114035610)
深圳市科技计划资助项目(RCBS20200714114921207)。
关键词
双目内窥镜
散斑
标定参数优化
立体校正
三维重建
binocular endoscope
speckle
calibration parameters optimization
stereo rectification
3D reconstruction