[1]张 磊,郭志阳,李红兵,等.基于OpenGL的目标物3维位姿估计研究[J].江西师范大学学报(自然科学版),2019,(05):462-468.[doi:10.16357/j.cnki.issn1000-5862.2019.05.04]
　ZHANG Lei,GUO Zhiyang,LI Hongbing,et al.The 3D Pose Estimation of the Object Based on OpenGL[J].Journal of Jiangxi Normal University:Natural Science Edition,2019,(05):462-468.[doi:10.16357/j.cnki.issn1000-5862.2019.05.04]
点击复制

基于OpenGL的目标物3维位姿估计研究()
分享到：

《江西师范大学学报》（自然科学版）[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2019年05期
页码:
462-468
栏目:
出版日期:
2019-10-10

文章信息/Info

Title:
The 3D Pose Estimation of the Object Based on OpenGL
文章编号:
1000-5862(2019)05-0462-07
作者:
张 磊1; 2; 郭志阳1; 李红兵3; 戴丽娟1; 4; 张兴国1
1.南通大学机械工程学院,江苏 南通 226019; 2.约克大学拉德松学院机械工程系,加拿大 多伦多 M3J 1P3; 3.上海交通大学仪器科学与工程系,上海 200240; 4.德州大学阿灵顿分校心理系,美国 德克萨斯州阿灵顿 76019
Author(s):
ZHANG Lei1; 2; GUO Zhiyang1; LI Hongbing3; DAI Lijuan1; 4; ZHANG Xingguo1
1.School of Mechanical Engineering,Nantong University,Nantong Jiangsu 226019,China; 2.Department of Mechanical Engineering,Lassonde School of Engineering,York University,Toronto M3J 1P3,Canada; 3.Department of Instrument Science and Engineering,Shanghai Jiaotong University,Shanghai 200240,China; 4.Department of Psychology,University of Texas at Arlington 76019,USA
关键词:
OpenGL;  虚拟现实;  位姿估计;  外参数标定
Keywords:
OpenGL;  virtual reality;  pose estimation;  external parameter calibration
分类号:
TP 391
DOI:
10.16357/j.cnki.issn1000-5862.2019.05.04
文献标志码:
A
摘要:
针对目标物在3维空间中的位姿估计存在获取困难、稳定性差和精度偏低等问题,采用将虚拟信息与实际图像信息相对应的方式,提出了一种基于OpenGL的目标物3维位姿估计方法.从理论上分析了虚拟与实际成像模型之间的关系,利用OpenGL构建了虚拟空间的模型; 在技术上基于VC环境引入OpenGL库,通过虚拟视觉跟踪将目标物的OpenGL模型在显示窗口的投影匹配于实际目标图像,以匹配状态下的虚拟模型的位姿作为实际目标物的3维位姿,通过“最小化重投影误差”目标函数优化3维位姿值.实验结果表明, 该方法可借助虚拟空间获取目标物位姿,可避免采用标定法实现的繁琐与不稳定问题,而且位姿估计精度相比传统方法更高,达到了优良水平.
Abstract:
In the research of pose estimation for an object in the space,most existing methods have the problem of low precision and difficulty in direct acquisition.A 3D pose estimation method based on OpenGL is proposed by matching the image information with the virtual information in this paper.The relationship between virtual and real imaging models is theoretically analyzed and the actual projection is simulated by constructing a virtual space based on OpenGL.In technical level,the actual target image is matched by virtual visual tracking model and optimized with the "Bundle adjustment".The experimental results show that the proposed method can obtain the object pose parameters from the virtual space.It avoids the instability of calibration-based methods,and can achieve good accuracy in pose estimation.

参考文献/References:

[1] Zhong Zhun,Lei Mingyi,Li Shaozi,et al.Re-ranking object proposals for object detection in automatic driving[EB/OL].[2018-12-19].https://arxiv.org/pdf/1605.05904.pdf.
[2] Kuindersma S,Deits R,Fallon M,et al.Optimization-based locomotion planning,estimation,and control design for the atlas humanoid robot[J].Autonomous Robots,2016,40(3):429-455.
[3] Kim Y,Bang H.Decentralized control of multiple unmanned aircraft for target tracking and obstacle avoidance[EB/OL].[2018-12-23].https://www.researchgate.net/publication/303924107_Decentralized_Control_of_Multiple_Unmanned_Aircraft_for_Target_Tracking_and_Obstacle_Avoidance.
[4] 赵沁平,周彬,李甲,等.虚拟现实技术研究进展[J].科技导报,2016,34(14):71-75.
[5] Fischler M A,Bolles R C.Random sample consensus:a paradigm for model fitting with applications to image analysis and automated cartography[EB/OL].[2018-12-28].https://www.researchgate.net/publication/215458581_Random_Sample_Consensus_A_Paradigm_for_Model_Fitting_with_Applications_To_Image_Analysis_and_Automated_Cartography.
[6] Bhanu B.CAD-based Robot Vision[J].Computer,1987,20(8):13-16.
[7] Harris C.Tracking with Rigid Objects[M].Massachusetts:MIT Press,1992.
[8] Song Kaitai,Wu Chenghei,Jiang Sinyi.CAD-based pose estimation design for random bin picking using a RGB-D camera[J].Journal of Intelligent and Robotic Systems,2017,87(3/4):455-470.
[9] Chen Chinghang,Ramanan D.3D human pose estimation=2D pose estimation+matching[EB/OL].[2018-12-28].https://arxiv.org/pdf/1612.06524.pdf.
[10] Mehta D,Sridhar S,Sotnychenko O,et al.VNect:real-time 3D human pose estimation with a single RGB camera[J].Acm Transactions on Graphics,2017,36(4):44-46.
[11] Tsai C Y.CAD model-based 3D object pose estimation using an edge-based nonlinear model fitting algorithm[EB/OL].[2018-12-28].http://teacher.tku.edu.tw/StfFdDtl.aspx?tid=6887464.
[12] Gavriilidis A,Stahlschmidt C,Velten J,et al.Automatic extrinsic camera parameters estimation for a mobile ToF camera application[C]∥IEEE International Symposium on Intelligent Control.New York:IEEE,2015:41-46.
[13] 张磊,张志胜,史金飞,等.一种快速检测图像角点特征的线搜索式方法[J].自动化学报,2010,36(4):509-521.
[14] 徐德,谭民,李原.机器人视觉测量与控制[M].北京:国防工业出版社,2016.
[15] 张祖勋,苏国中,郑顺义,等.OpenGL成像机理及其与摄影测量方位元素的相关分析[J].武汉大学学报:信息科学版,2004,29(7):570-574.
[16] Lepetit V,Fua P.Monocular model-based 3d tracking of rigid objects:a survey[EB/OL].[2018-12-28].http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.84.8498.
[17] Miyagawa I,Arai H,Koike H.Simple camera calibration from a single image using five points on two orthogonal 1-D objects[EB/OL].[2018-12-28].http://med.wanfangdata.com.cn/Paper/Detail/PeriodicalPaper_PM20129859.
[18] Zhang Zhengyou.A flexible new thnique for camera calibration[EB/OL].[2018-12-30].https://www.microsoft.com/en-us/research/publication/a-flexible-new-technique-for-camera-calibration/?from=http%3A%2F%2Fresearch.microsoft.com%2Fen-us%2Fum%2Fpeople%2Fzhang%2Fpapers%2Ftr98-71.pdf.
[19] 张磊,许映秋,徐海黎.基于角点特征的3D视觉精确跟踪研究[J].光电子技术,2012,32(4):251-257.
[20] Kyriakoulis N,Gasteratos A.Color-based monocular visuoi-
nertial 3-D pose estimation of a volant robot[J].IEEE Transactions on Instrumentation and Measurement,2010,59(10):2706-2715.
[21] 张磊,张兴国.基于李群代数表达帧间位姿变化矩阵的3D视觉跟踪研究[J].江西师范大学学报:自然科学版,2012,36(5):466-471.

相似文献/References:

[1]金芳晓,谢 叻.基于虚拟现实的人机工程MTM和NIOSH方法研究[J].江西师范大学学报(自然科学版),2017,(04):338.
　JIN Fangxiao,XIE Le.The Research Ergonomics on MTM and NIOSH Method Based on Virtual Reality[J].Journal of Jiangxi Normal University:Natural Science Edition,2017,(05):338.
[2]肖英剑,揭安全*,李宏伟*,等.一种增强代码理解的代码可视化工具JavaCity[J].江西师范大学学报(自然科学版),2023,(06):652.[doi:10.16357/j.cnki.issn1000-5862.2023.06.13]
　XIAO Yingjian,JIE Anquan*,LI Hongwei*,et al.JavaCity:A Code Visualization Tool to Enhance Code Understanding[J].Journal of Jiangxi Normal University:Natural Science Edition,2023,(05):652.[doi:10.16357/j.cnki.issn1000-5862.2023.06.13]

备注/Memo

备注/Memo:
收稿日期:2019-03-16基金项目:江苏省“六大人才高峰”(2015-ZBZZ-023),上海市自然科学基金(18ZR1421300),上海市高新技术课题(181511108202),2017年度江苏省政府留学奖学金和 2018年度江苏省政府留学奖学金资助项目.作者简介:张 磊(1973-),男,江苏南通人,副教授,博士,主要从事机器人视觉和触觉的研究.E-mail:zhangleint@ntu.edu.cn
更新日期/Last Update: 2019-10-10