首页 > 论文 > 激光与光电子学进展 > 55卷 > 9期(pp:91503--1)

基于ICP与SFM的双目立体视觉三维重构算法

Binocular Stereo Vision Three-Dimensional Reconstruction Algorithm Based on ICP and SFM

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

目前常见的多角度融合三维重构算法主要包括迭代最近点(ICP)算法与运动恢复结构(SFM)算法。针对两种算法的不足, 结合双目相机特点, 提出一种将ICP与SFM相结合的双目立体视觉多角度融合三维重构算法。首先, 采用SFM算法通过双目相机在目标周围拍摄n组图像对, 在每组双目图像对中手动选取目标的初始匹配特征点, 计算其三维坐标, 生成n组三维点云; 接着, 通过ICP算法计算并优化n组三维点云之间的旋转矩阵与平移向量完成融合, 通过Delaunay三角剖分与纹理映射恢复出目标的立体几何形状。实验结果表明:本文算法根据双目相机特点, 集合了ICP算法与SFM算法的优点, 并最大限度地克服了两种算法的不足, 重构效果良好。

Abstract

Currently, the commonly used multi-angle fusion three-dimensional (3D) reconstruction algorithm mainly includes the iterative closest point (ICP) algorithm and the structure from motion (SFM) algorithm. Aiming at the shortcomings of the above algorithms, we propose a multi-angle fusion 3D reconstruction algorithm with binocular stereo based on ICP and SFM. Firstly, the n groups of photos are taken around the target with binocular cameras by using the SFM algorithm. Then, we manually select the matching feature points of target in each group of binocular images, and calculate the 3D coordinate of matching feature points to generate the n groups of 3D point cloud. Subsequently, the rotation matrix and translation vector within the n groups of 3D point cloud are calculated and optimized by ICP algorithm. Finally, the n groups of 3D point are fused, and the 3D geometry of target is recovered by Delaunay triangle. The experimental results show that, the proposed algorithm takes advantages of the binocular cameras, overcomes the disadvantages of ICP and SFM algorithm, and has good vision effect for 3D reconstruction of target.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391

DOI:10.3788/lop55.091503

所属栏目:机器视觉

基金项目:河北省重点研发计划(17227206D)

收稿日期:2018-03-19

修改稿日期:2018-04-11

网络出版日期:2018-04-17

作者单位    点击查看

刘一凡:河北农业大学机电工程学院, 河北 保定 071001
蔡振江:河北农业大学机电工程学院, 河北 保定 071001

联系人作者:蔡振江(czj65@163.com)

【1】Besl P J, McKay N D. A method for registration of 3-D shapes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992, 14(2): 239-256.

【2】Zhou L M, Bu K, Dong Y W, et al. Rapid registration technology of turbine blade based on simplified cloud data[J]. Computer Integrated Manufacturing Systems, 2012, 18(5): 988-992.
周丽敏, 卜昆, 董一巍, 等. 基于简化点云带动的涡轮叶片快速配准技术研究[J]. 计算机集成制造系统, 2012, 18(5): 988-992.

【3】Chen J, Wu X J, Yu-Wang M, et al. 3D shape modeling using a self-developed hand-held 3D laser scanner and an efficient HT-ICP point cloud registration algorithm[J]. Optics & Laser Technology, 2013, 45: 414-423.

【4】Wei S B, Wang S Q, Zhou C H, et al. An iterative closest point algorithm based on biunique correspondence of point clouds for 3D reconstruction[J]. Acta Optica Sinica, 2015, 35(5): 0515003.
韦盛斌, 王少卿, 周常河, 等. 用于三维重建的点云单应性迭代最近点配准算法[J]. 光学学报, 2015, 35(5): 0515003.

【5】Zhong Y, Zhang M. Automatic registration technology of point cloud based on improved ICP algorithm[J]. Control Engineering of China, 2014, 21(1): 37-40.
钟莹, 张蒙. 基于改进ICP算法的点云自动配准技术[J]. 控制工程, 2014, 21(1): 37-40.

【6】Xie J, Hsu Y F, Feris R S, et al. Fine registration of 3D point clouds fusing structural and photometric information using an RGB-D camera[J]. Journal of Visual Communication and Image Representation, 2015, 32: 194-204.

【7】Huang Y, Da F P, Tao H J. An automatic registration algorithm for point cloud based on feature extraction[J]. Chinese Journal of Lasers, 2015, 42(3): 0308002.
黄源, 达飞鹏, 陶海跻. 一种基于特征提取的点云自动配准算法[J]. 中国激光, 2015, 42(3): 0308002.

【8】Deng W J, Ye J Y, Zhang T. Acquisition and denoising algorithm of laser point cloud oriented to robot polishing[J]. Acta Optica Sinica, 2016, 36(8): 0814002.
邓文君, 叶景杨, 张铁. 面向机器人磨抛的激光点云获取及去噪算法[J]. 光学学报, 2016, 36(8): 0814002.

【9】Chen M L, Lu W X, Wan Y C, et al. Automatic registration of terrestrial point clouds without additional information[J]. Chinese Journal of Lasers, 2016, 43(4): 0414003.
陈茂霖, 卢维欣, 万幼川, 等. 无附加信息的地面激光点云自动拼接方法[J]. 中国激光, 2016, 43(4): 0414003.

【10】Chen H, Ma S W, Andreas N. Non-synchronous point cloud algorithm for 3D reconstruction based on laser scanning and SFM[J]. Chinese Journal of Scientific Instrument, 2016, 37(5): 1148-1157.
陈辉, 马世伟, Andreas N. 基于激光扫描和SFM的非同步点云三维重构方法[J]. 仪器仪表学报, 2016, 37(5): 1148-1157..

【11】Guo M, Hu L L, Li J. Local point cloud reconstruction of ceramic bowl based on image sequences[J]. Acta Optica Sinica, 2017, 37(12): 1215002.
郭萌, 胡辽林, 李捷. 基于多幅图像的陶瓷碗表面缺陷的局部点云重建[J]. 光学学报, 2017, 37(12):1215002.

【12】Zeng L L, Gai S Y, Da F P, et al. Hole filling algorithm of three-dimensional point cloud based on structure from motion[J]. Acta Optica Sinica, 2018, 38(6): 0610002.
曾露露, 盖绍彦, 达飞鹏, 等. 基于从运动中恢复结构的三维点云孔洞修补算法研究[J]. 光学学报, 2018, 38(6): 0610002.

【13】Gong Y S, Zhang Y, Wen Y, et al. Kinect-based data-driven 3D modeling[J]. Journal of Computer Aided Design & Computer Graphics, 2014, 26(11): 1957-1965.
宫钰嵩, 张岩, 文艳, 等. Kinect扫描数据驱动的几何建模方法[J]. 计算机辅助设计与图形学学报, 2014, 26(11): 1957-1965.

【14】Heinly J, Schonberger J L, Dunn E, et al. Reconstructing the world* in six days*(as captured by the yahoo 100 million image dataset)[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015: 3287-3295.

【15】Zhang G, Vela P A. Good features to track for visual SLAM[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015: 1373-1382.

【16】Yu Z H. Research on acquisition and visualization of three dimensional data for collection of cultural relics[D]. Guangzhou: South China University of Technology, 2016.
俞朝晖. 面向馆藏文物的三维数据获取及可视化研究[D]. 广州: 华南理工大学, 2016.

【17】Zhao B. Research on interior close quarter three-dimensional laser scanning technique[D]. Zhenjiang: Jiangsu University of Science and Technology, 2017.
赵彬. 室内近距离三维激光扫描技术研究[D]. 镇江: 江苏科技大学, 2017.

【18】Yang Y. Structure from motion based on binocular vision[D]. Chengdu: University of Electronic Science and Technology of China, 2016.
杨阳. 基于双目视觉的运动恢复结构[D]. 成都: 电子科技大学, 2016

【19】Feng W W, Chen X Y, Yu H L, et al. Multi-view 3D reconstruction based on constraint Delauney triangle[J]. Computer Applications and Software, 2017, 34(7): 120-124.
冯文雯, 陈珝玥, 余虹亮, 等. 基于约束Delaunay三角形的多视3D重建[J]. 计算机应用与软件, 2017, 34(7): 120-124.

引用该论文

Liu Yifan,Cai Zhenjiang. Binocular Stereo Vision Three-Dimensional Reconstruction Algorithm Based on ICP and SFM[J]. Laser & Optoelectronics Progress, 2018, 55(9): 091503

刘一凡,蔡振江. 基于ICP与SFM的双目立体视觉三维重构算法[J]. 激光与光电子学进展, 2018, 55(9): 091503

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF