非合作纹理目标单目位姿计算

冯肖维; 谢安安; 肖健梅; 王锡淮

doi:10.3788/OPE.20202808.1775

您当前的位置：

首页 >

文章列表页 >

非合作纹理目标单目位姿计算

信息科学 | 更新时间：2020-08-14

- 非合作纹理目标单目位姿计算
- Monocular pose calculation of non-cooperation textured object
- 光学精密工程 2020年28卷第8期页码：1775-1784
- 作者机构：
  
  上海海事大学电气自动化系, 上海 201306
- 作者简介：
  
  [ "冯肖维(1982-), 男, 上海人, 博士, 讲师, 2004年、2007年、2011年于上海大学分别获得学士、硕士、博士学位, 主要从事非线性系统控制、机器人技术、机器视觉等方面的研究。E-mail:xwfeng1982@163.com" ]
  [ "谢安安(1995-), 男, 江西吉安人, 硕士研究生, 2017年于南昌航空大学获得学士学位, 主要研究方向为机器视觉与图像处理等。E-mail:xiean1972@qq.com" ]
- 基金信息：
  
  国家自然科学基金资助项目(61503241);国家自然科学基金资助项目(61801287)
- DOI：10.3788/OPE.20202808.1775
  中图分类号： TP391
- 收稿日期：2020-03-11，
  
  修回日期：2020-04-17，
  
  录用日期：2020-4-17，
  
  纸质出版日期：2020-08-25
- 稿件说明：
移动端阅览
冯肖维, 谢安安, 肖健梅, 等. 非合作纹理目标单目位姿计算[J]. 光学精密工程, 2020,28(8):1775-1784.

Xiao-wei* FENG, An-an Xie, Jian-mei Xiao, et al. Monocular pose calculation of non-cooperation textured object[J]. Optics and precision engineering, 2020, 28(8): 1775-1784.
冯肖维, 谢安安, 肖健梅, 等. 非合作纹理目标单目位姿计算[J]. 光学精密工程, 2020,28(8):1775-1784. DOI： 10.3788/OPE.20202808.1775.

Xiao-wei* FENG, An-an Xie, Jian-mei Xiao, et al. Monocular pose calculation of non-cooperation textured object[J]. Optics and precision engineering, 2020, 28(8): 1775-1784. DOI： 10.3788/OPE.20202808.1775.

摘要

为了实时测量非合作纹理运动目标相对位姿，提出一种单目视觉同步建模与位姿计算方法。选择具有良好特征共视关系与分布的模型帧，增量式恢复目标三维共视特征模型，实现非合作目标的合作化，并依靠运动预测模型实现基于特征跟踪的位姿计算。根据模型对应网格的拓扑关系估计目标表面未知区域特征三维信息，结合网格面法向场进行局部光束平差优化，同时利用闭环优化抑制尺度漂移，在减少特征模型恢复误差的同时提高位姿计算精度。实验结果表明，在非结构化环境中能够在线恢复目标三维信息，实现目标相对位姿准确计算，特征平均重投影误差小于1.5 pixel，位姿计算平均绝对误差为4.29 mm和1.54°，平均计算时间小于120 ms，为基于单目视觉的在线三维感知与测量建模提供技术支撑。

Abstract

To measure the relative pose of moving non-cooperation textured objects in real time

a monocular simultaneous modeling and pose calculation method was proposed. A 3D covisibility model was incrementally constructed with frames containing the highest covisibility of features and best distribution to achieve cooperation between non-cooperation objects. Subsequently

the relative pose of the object was calculated via feature tracking by the motion prediction model. The mesh of the model was used to restore the 3D information of feature points that were distributed in an unknown area of the object surface. To reduce model error and improve the accuracy of pose estimation

bundle adjustment optimization was performed using a facet normal field

and the scale drift was reduced using closed-loop optimization. Experiments show that the method isa real-time online system that can recover 3D information of object in unstructured environments and accurately estimate relative poses in unstructured environments to provide technical support for 3D sensing and measurement modeling based on monocular vision. The mean reprojection error(MRE) of the features using the proposed method is less than 1.5 pixels

and the mean absolute error(MAE) of pose calculation is 4.29 mm and 1.54° while the average time consumption is less than 120 ms.

关键词

Keywords

references

J LI , J A BESADA , A M BERNARDOS . A novel system for object pose estimation using fused vision and inertial data . Information Fusion , 2016 . 33 15 - 28 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=0d3d93fa2d637a343546e1893cd74f91 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=0d3d93fa2d637a343546e1893cd74f91 .

S SHARMA , S D'AMICO . Comparative assessment of techniques for initial pose estimation using monocular vision . Acta Astronautica , 2016 . 123 435 - 445 . DOI: 10.1016/j.actaastro.2015.12.032 http://doi.org/10.1016/j.actaastro.2015.12.032 .

X WANG , H YU , D FENG . Pose estimation in runway end safety area using geometry structure features . The Aeronautical Journal , 2016 . 120 ( 1226 ): 675 - 691 . DOI: 10.1017/aer.2016.16 http://doi.org/10.1017/aer.2016.16 .

KLEIN G, MURRAY D. Parallel tracking and mapping for small AR workspaces[C]. International Symposium on Mixed and Augmented Reality, Nara, Japan , 2007: 225-234.

周婧 , 高印寒 , 刘长英 , 等 . 基于自适应算法的单目视觉系统的姿态解算 . 光学精密工程 , 2012 . 20 ( 12 ): 2796 - 2803 . http://ope.lightpublishing.cn/thesisDetails?columnId=1998833&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1998833&Fpath=&index=-1&l=zh .

J ZHOU , Y H GAO , CH Y LIU , 等 . Attitude calculation of single camera visual system based on adaptive algorithm . Opt. Precision Eng. , 2012 . 20 ( 12 ): 2796 - 2803 . http://ope.lightpublishing.cn/thesisDetails?columnId=1998833&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1998833&Fpath=&index=-1&l=zh .

D J CRANDALL , A OWENS , N SNAVELY , 等 . SfM with MRFs: Discrete-continuous optimization for large-scale structure from motion . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2013 . 35 ( 12 ): 2841 - 2853 . http://cn.bing.com/academic/profile?id=5a83d4f3d55fc9823ef6a9762a986c67&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=5a83d4f3d55fc9823ef6a9762a986c67&encoded=0&v=paper_preview&mkt=zh-cn .

SEGAL S, CARMI A, GURFIL P. Vision-based relative state estimation of non-cooperative spacecraft under modeling uncertainty[C]. Aerospace Conference, MT, USA , 2011: 1-8.

R MUR-ARTAL , J M MONTIEL , J D TARDOS . ORB-SLAM: a Versatile and Accurate Monocular SLAM System . IEEE Transactions on Robotics , 2015 . 31 ( 5 ): 1147 - 1163 . DOI: 10.1109/TRO.2015.2463671 http://doi.org/10.1109/TRO.2015.2463671 .

AUGENSTEIN S, ROCK S M. Simultaneous estimation of target pose and 3-D shape using the FastSLAM algorithm[C]. Proceedings of the AIAA Guidance, Navigation and Control Conference, Chicago, USA , 2009: 1-15.

MOURAGON E, DEKEYSER F, SAYD P, et al . Real time localization and 3D reconstruction[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York, USA , 2006: 363-370.

H STRASDAT , J M M MONTIEL , A J DAVISON . Visual SLAM: Why filter . Image and Vision Computing , 2012 . 30 ( 2 ): 65 - 77 . DOI: 10.1016/j.imavis.2012.02.009 http://doi.org/10.1016/j.imavis.2012.02.009 .

刘宗明 , 张宇 , 卢山 , 等 . 非合作旋转目标闭环检测与位姿优化 . 光学精密工程 , 2017 . 25 ( 4 ): 504 - 511 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gxjmgc201704027 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gxjmgc201704027 .

Z M LIU , Y ZHANG , SH LU , 等 . Closed-loop detection and pose optimization of non-cooperation rotating targets . Opt. Precision Eng. , 2017 . 25 ( 4 ): 504 - 511 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gxjmgc201704027 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gxjmgc201704027 .

RUBLEE E, RABAUD V, KONOLIGE K, et al . ORB: an efficient alternative to SIFT or SURF[C]. IEEE International Conference on Computer Vision, Barcelona, Spain , 2011: 2564-2571.

R HARTLEY , A ZISSERMAN . Multiple View Geometry in Computer Vision, 2nd ed , : UK Cambridge University Press , 2004 .

冯肖维 , 姜晨 , 何敏 , 等 . 三维距离图像基于特征估计的自适应平滑 . 光学精密工程 , 2019 . 27 ( 12 ): 2693 - 2701 . http://ope.lightpublishing.cn/thesisDetails?columnId=2140670&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=2140670&Fpath=&index=-1&l=zh .

X W FENG , CH JIANG , M HE , 等 . Adaptive smoothing for three-dimensional range image based on feature estimation . Opt. Precision Eng. , 2019 . 27 ( 12 ): 2693 - 2701 . http://ope.lightpublishing.cn/thesisDetails?columnId=2140670&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=2140670&Fpath=&index=-1&l=zh .

S LI , C XU , M XIE . A robust o(n) solution to the perspective-n-point problem . IEEE Transactions on Pattern Analysis & Machine Intelligence , 2012 . 34 ( 7 ): 1444 - 1450 . http://cn.bing.com/academic/profile?id=f654fceef3af6f42f393b31b6e37f1c4&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=f654fceef3af6f42f393b31b6e37f1c4&encoded=0&v=paper_preview&mkt=zh-cn .

浏览量

478

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于单目视觉的火箭回收高度测量技术研究

自适应视觉惯性地磁紧耦合定位系统

面向激光跟踪测量的大范围高精度姿态测量

基于深度学习和PnP模型的激光跟踪仪自动姿态测量

基于三维模型的单目车辆位姿估计