计算机科学 ›› 2015, Vol. 42 ›› Issue (6): 299-302.doi: 10.11896/j.issn.1002-137X.2015.06.063

• 图形图像与模式识别 • 上一篇    下一篇

基于视觉标记的增强现实系统建模及配准误差问题研究

张国亮,吴琰翔,王展妮,王田   

  1. 华侨大学计算机科学与技术学院 厦门361021,华侨大学计算机科学与技术学院 厦门361021,华侨大学计算机科学与技术学院 厦门361021,华侨大学计算机科学与技术学院 厦门361021
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受国家自然科学基金(61202468),福建省自然科学基金(2013J05091),华侨大学高层次人才科研启动项目(11BS107)资助

Research on Augmented Reality System Modeling and Registration Error Based on Simple Visual Marker

ZHANG Guo-liang, WU Yan-xiang, WANG Zhan-ni and WANG Tian   

  • Online:2018-11-14 Published:2018-11-14

摘要: 针对当前基于视觉的增强现实系统标记大、成本高的缺陷,提出一套结合简单组合标记的增强现实系统的实现方案。基于弱透视模型,以色彩和形状作为融合特征,研究了利用冗余特征实现标记物体的3D位姿还原方法。为使配准方案能够适应普通的视觉采集设备,提出根据摄像机标定时得到的扭曲参数对渲染后的模型进行再扭曲的配准修正方法。结合OpenCV和OpenGL中的空间变换的概念,给出了虚拟和物理世界配准融合的解决方案,并基于统计学数学模型,提出降低配准时的误差以及提升配准稳定性的方案。实验结果表明,提出的算法能有效地将静态标签的抖动降低至亚像素级。

关键词: 增强现实,位姿估计,弱透视模型,图像配准,标记检测

Abstract: An image registration strategy was studied based on simple visual marker,which is furthered to build augmented reality system.Firstly,color and shape were selected as integrated feature to ensure the reliability of marker detection.Redundant features were utilized to calculate pose of visual markers based on weak perspective model.Secondly,to make image registration be suitable for common vision capture device,rendered model was redistorted according to calibration distortion parameters.Finally,based on space transformation in OpenCV and OpenGL,virtual and real registration was discussed and implemented with visual marker detection result.

Key words: Augmented reality,Pose estimation,Weak perspective model,Image registration,Marker detection

[1] Veronica Teichrieb,et al.A Survey of online monocular markerless augmented reality[J].International Journal of Modeling and Simulation for the Petroleum Industry,2007,1(1):1-7
[2] 赵敏,刘秉琦,武东升.增强现实装配和维修系统的技术研究[J].光学仪器,2012,34(2):16-22 Zhao Min,Liu Bing-qi,Wu Dong-sheng.Study on the techniques of augmented reality installation and maintenance system[J].Optical Instruments,2012,34(2):16-22
[3] 黄季冬,胡绍卿.基于ARToolkit Plus的增强现实系统实现及框架研究[J].计算机与数字工程,2012,40(4):102-104 Hyabg Ji-dong,Hu Shao-qing.An implementation of augmented reality system based on ARToolkit plus and MVC framework[J].Computer & Digital Engineering,2012,40(4):102-104
[4] 王峻峰,陈亭,李世其,等.BRIEF算法在基于增强现实的产品装配引导中的应用研究[J].机械科学与技术,2013,32(2):213-216 Wang Jun-feng,Chen Ting,Li Shi-qi,et al.Applying BRIEF algorithm to product assembly guidance based on augmented reali-ty[J].Mechanical Science and Technology for Aerospace Engineering,2013,32(2):213-216
[5] 邱世广,荆旭,范秀敏.增强现实环境下的汽车A立柱视野评估方法[J].计算机辅助设计与图形学学报,2012,24(1):128-135 Qiu Shi-guang,Jing Xu,Fan Xiu-min.Automotive a-pillar evaluation using augmented reality[J].Journal of Computer-Aided Design & Computer Graphics,2012,24(1):128-135
[6] Marshall G.Project glass:what you need to know [EB/OL].http://www.techradar.com/news/video/project-glass-what-you-need-to-know-1078114,2012-04-30
[7] 罗斌,王涌天,沈浩,等.增强现实混合跟踪技术综述[J].自动化学报,2013,9(8):1185-1201 Luo Bin,Wang Yong-Tian,Shen Hao,et al.Overview of hybrid tracking in augmented reality[J].Acta Automatica Sinica,2013,9(8):1185-1201
[8] Bergamasco F,et al.Rune-Tag:A high accuracy fiducial marker with strong occlusion resilience[C]∥2013 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).2011:113-120
[9] Laganière R.OPENCV2 computer vision application programming cookbook [M].Packt Publishing,2011
[10] Haemel N,Wright R,Sellers G,et al.OPENGL superbible fifth edition [M].Addison-Wesley,2010:7-125

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!