面向场景重构的多序列间配准

杨磊; 李桂菊; 王丽荣

doi:10.3788/OPE.20152302.0557

您当前的位置：

首页 >

文章列表页 >

面向场景重构的多序列间配准

信息科学 | 更新时间：2020-08-13

- 面向场景重构的多序列间配准
- Registration between multiple sequences for scene reconstruction
- 光学精密工程 2015年23卷第2期页码：557-565
- 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. 中国科学院大学北京,中国,100049
  3. 长春大学电子信息与工程学院,吉林长春,130022
- 作者简介：
- 基金信息：
  
  国家自然科学基金资助项目 (No.61172111)()
- DOI：10.3788/OPE.20152302.0557
  中图分类号： TP391.4
- 收稿日期：2013-11-15，
  
  修回日期：2013-12-23，
  
  纸质出版日期：2015-02-25
- 稿件说明：
移动端阅览
杨磊, 李桂菊, 王丽荣. 面向场景重构的多序列间配准[J]. 光学精密工程, 2015,23(2): 557-565

YANG Lei, LI Gui-ju, Wang Li-rong. Registration between multiple sequences for scene reconstruction[J]. Editorial Office of Optics and Precision Engineering, 2015,23(2): 557-565
杨磊, 李桂菊, 王丽荣. 面向场景重构的多序列间配准[J]. 光学精密工程, 2015,23(2): 557-565 DOI： 10.3788/OPE.20152302.0557.

YANG Lei, LI Gui-ju, Wang Li-rong. Registration between multiple sequences for scene reconstruction[J]. Editorial Office of Optics and Precision Engineering, 2015,23(2): 557-565 DOI： 10.3788/OPE.20152302.0557.

摘要

针对传统的单序列扩展式场景重构方法易丢失场景信息

数据利用率低下等问题

提出一种面向场景重构的多序列间配准的方法。该方法采用相似变换作为配准模型

完成对不同参考坐标系下尺度、旋转、平移相分离的初始配准;然后通过拟合观测平面来抑制噪声点并筛选公共可见点;最终对不同尺度、方位的序列进行配准

配准结果可直接用于后续的重构中。实验表明:通过相应噪声抑制

使得各序列的系统初始重投影误差降低了17.69%到46.86%

终止重投影误差降低了27.5%到71.96%。配准后从相同的47幅图像中可重构10 596个场景点

相比传统单序列方法的3 893个场景点

该方法更充分有效地利用了观测图像

使最终拟合的场景曲面包含了更多的场景细节。

Abstract

As traditional single sequence scene reconstruction method is easy to loss scene information and has a lower data utilization

this paper proposes an approach to the registration between multiple sequences for scene reconstruction. The method uses a similarity transformational as the registration model and proposes the separating initial registration method to deal with the scale

rotation and translation respectively. Then

it fits the observed plane to suppress the noise data and select the co-visible points. Finally

the registration between multiple sequences with different scales

positions is performed and the registration results are applied in successive subsequent reconstruction. The experiment shows that the initial error has been reduced from 17.69% to 46.86%

and the terminated error reduced from 27.5% to 71.96% after suppression of noise data along the oriented orientation. Moreover

the 10 596 vertices are reconstructed from 47 frame images

more better than 3 893 vertices reconstructed by traditional single sequential method. The proposed method full makes use of the observation images and allows the ultimate fitting surface of the scene to have more scene details.

关键词

Keywords

references

HARTLRY R, ZISSERMAN A. Multiple View Geometry in Computer Vision[M]. Cambridge:Cambridge University Press, 2003: 151-360.

李畅, 刘亚文, 胡敏, 等. 面向街景立面三维重建的近景影像直线匹配方法研究[J]. 武汉大学学报:信息科学版, 2010,35(12):1461-1465.

LI CH, LIU Y W, HU M, et al.. Study on street elevation 3D reconstruction oriented straight line matching for close-range images[J]. Geomatics and Information Science of Wuhan University, 2010,35(12):1461-1465.

冯萍, 魏振忠. 光笔式大视场三维视觉测量系统[J]. 光学精密工程, 2013, 21(9): 2217-2224.

FENG P, WEI ZH ZH. Light probe based large FOV 3D vision measurement system [J]. Opt. Precision Eng., 2013, 21(9): 2217-2224.

STURM P F. Critical motion sequences for monocular self-calibration and uncalibrated Euclidean reconstruction [C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE, 1997: 1100-1105.

SNAVELY N, SEITZ S M, SZELISKI R. Modeling the world from internet photo collections[J]. International Journal of Computer Vision, 2008, 80(2): 189-210.

黄风山, 刘恩福, 方忆湘, 等. 基于智能三坐标测量机的零件位姿单目立体视觉识别[J]. 光学精密工程, 2013, 21(5): 1326-1332.

HUANG F SH,LIU E F, FANG Y X, et al.. Single camera stereo vision recognization for Parts’ pose based on intelligent three coordinate measuring machine [J].Opt. Precision Eng., 2013, 21(5): 1326-1332.

陈庭旺, 王庆. 面向大规模场景的三维线段检测算法[J]. 计算机辅助设计与图形学学报, 2011, 23(5):790-796.

CHEN T W,W Q. A 3D line segment detection algorithm for large-scale scenes [J]. Journal of Computer-Aided Design & Computer Graphics, 2011, 23(5):790-796.

GOESELE M, SNAVELY N, CURLESS B, et al.. Multi-view stereo for community photo collections [C]. IEEE 11th International Conference on Computer Vision,ICCV 2007, 2007: 1-8.

CORNELIS N, LEIBE B, CORNELIS K, et al.. 3D urban scene modeling integrating recognition and reconstruction[J]. International Journal of Computer Vision, 2008, 78(2-3): 121-141.

NEWCOMBE R A, DAVISON A J. Live dense reconstruction with a single moving camera[C]. IEEE Conference on Computer Vision and Pattern Recognition(CVPR) 2010, 2010: 1498-1505.

PULLI K. Multi-view registration for large data sets [C]. Proceedings of Second International Conference on 3-D Digital Imaging and Modeling, 1999: 160-168.

KAHL F, HARTLEY R. Multiple-view geometry under the L1-Norm[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2008, 30(9): 1603-1617.

陈辉, 龙爱群, 彭玉华. 由未标定手持相机拍摄的图片构造全景图[J]. 计算机学报, 2009,32(2):328-335.

CHEN H, LONG A Q, PENG Y H. Building panoramas from photographs taken with an uncalibrated hand-held camera [J].Chinese Journal of Computers, 2009,32(2):328-335.

HARTLEY R, KAHL F, OLSSON C, et al.. Verifying global minima for L2 minimization problems in multiple view geometry [J]. International Journal of Computer Vision, 2013, 101(2): 288-304.

LEPETIT V, MORENO F, FUA P. EPNP: An accurate o(n) solution to the pnp problem[J]. International Journal of Computer Vision, 2009, 81(2): 155-166.

浏览量

317

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

面向干涉包裹相位的多等级噪声抑制网络

顾及最优分配和最佳掩码的点云部件分割

局部阈值自适应的地面点云分割

基于光纤布拉格光栅的扑翼机器人三维扑动变形测量

面向点云识别网络的显著图生成