基于运动恢复的双目视觉三维重建系统设计

王欣; 袁坤; 于晓; 章明朝

doi:10.3788/OPE.20142205.1379

您当前的位置：

首页 >

文章列表页 >

基于运动恢复的双目视觉三维重建系统设计

信息科学 | 更新时间：2020-08-13

- 基于运动恢复的双目视觉三维重建系统设计
- Design of binocular vision 3D reconstruction system based on motion recovery
- 光学精密工程 2014年22卷第5期页码：1379-1387
- 作者机构：
  
  1. 中国科学院长春光学精密机械与物理研究所,吉林长春,中国,130033
  2. 空军航空大学,吉林长春,130022
  3. 吉林大学计算机科学与技术学院,吉林长春,130012
- 作者简介：
- 基金信息：
  
  吉林省科技发展计划资助项目（No.201105016）()
- DOI：10.3788/OPE.20142205.1379
  中图分类号： TP391.4
- 收稿日期：2013-05-24，
  
  修回日期：2013-07-03，
  
  纸质出版日期：2014-05-25
- 稿件说明：
移动端阅览
王欣, 袁坤, 于晓等. 基于运动恢复的双目视觉三维重建系统设计[J]. 光学精密工程, 2014,22(5): 1379-1387

WANG Xin, YUAN Kun, YU Xiao etc. Design of binocular vision 3D reconstruction system based on motion recovery[J]. Editorial Office of Optics and Precision Engineering, 2014,22(5): 1379-1387
王欣, 袁坤, 于晓等. 基于运动恢复的双目视觉三维重建系统设计[J]. 光学精密工程, 2014,22(5): 1379-1387 DOI： 10.3788/OPE.20142205.1379.

WANG Xin, YUAN Kun, YU Xiao etc. Design of binocular vision 3D reconstruction system based on motion recovery[J]. Editorial Office of Optics and Precision Engineering, 2014,22(5): 1379-1387 DOI： 10.3788/OPE.20142205.1379.

摘要

对基于双目立体视觉的一种三维重建系统进行了改进和扩展。将视差细化处理环节引入现有系统，使原视差及相邻视差的匹配代价拟合为一条二次曲线，并为该曲线重新寻找更加精确的视差。进一步将运动恢复计算环节引入系统，通过估计当前视角的摄像机运动矩阵和以跟踪点和摄像机运动矩阵为参数构造能量函数，对能量函数进行优化来有效缩小误差，恢复出准确的运动矩阵。实验结果表明：新增的视差细化处理环节有效提升了重建点云的精度，使细化前后三维重建结果误差平均减少了16.3%，避免了片状点云现象；新增的运动恢复优化环节，能够精确地恢复摄像机的运动矩阵，优化后三维重建结果平均重投影误差减少了95.5%；重构后不同视角的点云之间不再孤立，重建模型整体拼接自然。

Abstract

An 3D reconstruction system based on binocular stereo vision was improved to obtain higher accuracy and larger scale of 3D reconstruction.A disparity refinement procedure was introduced to the system

so that the matching cost between the original parallax and the adjacent disparity was fitted into a quadratic curve and to re-find a more accurate parallax for the curve. Then

the motion recovery calculation was further applies to estimation of the camera motion matrices and the tracking points and camera motion matrices were taken as the parameters to construct the energy function. Furthermore

the energy function was optimized to reduce errors effectively and reconstruct the motion matrix accurately. Experimental results indicate that the proposed refinement procedure effectively improves the accuracy of reconstruction of point clouds and reduces the error by 16.3 percent in average with avoiding the scale point cloud phenomenon. As the motion recovery calculation steps recover the camera motion matrix accurately

the optimized method reduces the mean re-projection error by 95.5 percent. The point clouds achieved from different angle images are no longer isolated and the reconstructed models are integrated naturally.

关键词

Keywords

references

全燕鸣, 黎淑梅, 麦青群. 基于双目视觉的工件尺寸在机三维测量[J]. 光学精密工程, 2013, 21(4):1054-1061. QUAN Y M, LI SH M, MAI Q Q.On-machine 3D measurement of workpiece dimensions based on binocular vision [J].Opt.Precision Eng. , 2013, 21(4):1054-1061.(in Chinese)

姜宏志, 赵慧洁, 梁宵月,等. 基于极线校正的快速相位立体匹配[J]. 光学精密工程, 2011, 19(10):2520-2525. JIANG H ZH, ZHAO H J, LIANG X Y, et al.Phase-based stereo matching using epipolar line rectification[J].Opt.Precision Eng., 2011, 19(10):2520-2525.(in Chinese)

BROWN M, LOWE D G.Unsupervised 3D object recognition and reconstruction in unordered datasets.Fifth International Conference on 3D Digital Imaging and Modeling, 2005:56-63.

SCHARSTEIN D,SZELISKI R.A taxonomy and evaluation of dense two-frame stereo correspondence algorithms [J].International Journal of Computer Vision,2002,47(1-3):7-42.

SHRIVASTHAVA P, VUNDAVILLI P R, PRATIHAR D K.An approach for 3D reconstruction of environment using stereo-vision system.IEEE Region 10 and The Third International Conference on Industrial and Information Systems, 2008, 1-7.

JIA W D,YI W J,JAFAR S.et al..3D image reconstruction and human body tracking using stereo vision and kinect technology.2012 IEEE International Conference on Electro/Information Technology, 2012:1-4.

YOON K J,SHIN M G.Recognizing 3D objects with 3D information from stereo vision.International Conference on Pattern Recognition, 2010, 4020-4023.

SUN J H, JEON B S, LIM J W,et al..Stereo vision based 3D modeling system for mobile robot.International Conference on Control, Automation and Systems, 2010:71-75.

ZHANG ZH Y.A flexible new technique for camera calibration [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000, 22(11):1330-1334.

FUSIELLO A, TRUCCO E,VERRI A.A compact algorithm for rectification of stereo pairs [J].Machine Vision and Applications, 2000, 12(1):16-22.

SHIMIZU M, OKUTOMI M.Precise sub-pixel estimation on area-based matching [J].systems and computers in Japan,2002,33(7):1-10.

HARTLEY R,ZISSERMAN A.Multiple View Geometry in Computer Vision [M].Cambridge:Cambridge University Press,2004.

DAVID G, LOWE.Distinctive image features from scale-invariant keypoints [J].International Journal of Computer Vision, 2004, 60(2):91-110.

HARTLEY R I.In Defense of the 8-point algorithm.IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(6):580-593.

LOURAKI M I A,ARGYROS A.SBA:A software package for generic sparse bundle adjustment [J].ACM Transactions on Mathematical Software, 2009, 36(1):1-30.

浏览量

166

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

MEMS振镜式结构光三维重建综述

复杂坡面拟合的异源点云配准及三维地形精细重建

强环境噪声下的双目视觉受电弓轨旁异常检测

基于双投射结构光系统的多尺度点云融合

柔性铰接板振动视觉测量与小波神经网络控制