期刊文献+

基于标识与平面间单应性矩阵的虚实注册方法 被引量:11

A new registration method based on marker and interplane-homographies
下载PDF
导出
摘要 提出了一种基于单应性矩阵与平面标识相结合的三维注册算法,解决了标识部分被遮挡情况下的虚实注册问题,提高了系统的健壮性、可用性.该方法将直接求解三维注册矩阵问题分解为利用图像间的匹配特征点来计算相邻两帧图像间的单应性关系,并利用该单应性关系恢复最终注册矩阵.就实验结果与ARToolkit的注册性能作了比较,结果表明该算法能够解决标识部分遮挡情况下的虚实注册问题,在健壮性方面明显优于ARToolkit. Augmented reality (AR) copes with the problem of dynamically augmenting or enhancing the real world with computer generated virtual objects. Registration is one of the most pivotal problems currently limiting AR applications. This paper illustrated a novel registration method based on homographies and known markers. Our method really improves the robustness and practicability of augmented reality systems. The proposed method distinguishes itself in following ways: the final registration matrix is calculated using the homographies between consecutive frames, by which we can achieve registration even when markers are partly occluded. After discussing the registration method in detail, we also give the experiment result and compare its registration performance with ARToolkit. The robustness of our algorithm is superior to ARToolkit obviously.
出处 《华中科技大学学报(自然科学版)》 EI CAS CSCD 北大核心 2006年第10期55-57,共3页 Journal of Huazhong University of Science and Technology(Natural Science Edition)
关键词 三维注册 增强现实 单应性矩阵 3D-registration augmented reality homography
  • 相关文献

参考文献4

  • 1Hartley R I, Zisserman A. Multiple view geometry in computer vision[M]. London: Cambridge University Press, 2000.
  • 2Emanuele T, Alessandro V. Introductory techniques for 3D computer vision[M]. Englewood Cliffs: Prentice-Hall, 1998.
  • 3Zhang Z, Deriche R, Faugeras O, et al. A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry[J]. Artificial Intelligence, 1995, 78(1-2): 87-119.
  • 4Fischler M A, Bolles R C. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography[J]. Communications of the ACM, 1981, 24(6): 381-395.

同被引文献63

  • 1陈睿,刘国翌,赵国英,张俊,李华.基于序列蒙特卡罗方法的3D人体运动跟踪[J].计算机辅助设计与图形学学报,2005,17(1):85-92. 被引量:21
  • 2胡士强,敬忠良.粒子滤波算法综述[J].控制与决策,2005,20(4):361-365. 被引量:291
  • 3章国锋,秦学英,董子龙,华炜,鲍虎军.面向增强视频的基于结构和运动恢复的摄像机定标[J].计算机学报,2006,29(12):2104-2111. 被引量:10
  • 4姜雪原,马广富,胡庆雷.基于粒子滤波和UKF联合滤波的卫星姿态估计[J].哈尔滨工业大学学报,2007,39(3):337-341. 被引量:10
  • 5KatoH. ARTooKit [EB/OL]. http://www.hitl.washington.edu/artoolkit/, 2003.
  • 6Uchiyama S, Takemoto K, Satoh K, et al. MR platform: a basic body on which mixed reality [C]//Proceedings of International Symposium on Mixed and Augmented Reality, Darmstadt, Germany, 2002: 246-320.
  • 7M Sanjeev Arulampalam, Simon Maskell, Neil Gordon, et al. A tutorial on particle filters for online nonlinear/non-gaussian bayesian tracking [J]. IEEE Transactions on Signal Processing, 2002, 50(2): 174-188.
  • 8Gordon N, Salmond D. Novel approach to nonlinear/ non-gaussian bayesian state estimation [C]//Proc of Institute Engineering, 1993: 107-113.
  • 9Edward Rosten, Tom Drummond. Fusing points and lines for high performance tracking [C]//IEEE International Conference on Computer Vision, 2005: 1508-1511.
  • 10OpenCV. Open source computer vision library [EB/OL]. http://www.intel.com/research/mrl/research/opencv/.

引证文献11

二级引证文献47

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部