期刊文献+

一种基于奇异值分解的分层重构算法 被引量:6

An Algorithm of Hierarchical Reconstruction Based on SVD
下载PDF
导出
摘要 以仿射投影来逼近透视投影 ,采用共轭梯度法迭代估计射影深度 ,通过测量矩阵的奇异值分解实现射影重构 .在摄象机内参数已知的情况下 ,求解一个满足欧氏重构条件的 4× 4非奇异矩阵 ,由此矩阵将射影重构变换为欧氏重构 . Affine projection is used to approximate perspective projection, projective depths are iteratively estimated by using the conjugate gradient method, and the projective reconstruction is obtained by SVD of the measurement matrix. Under the circumstances in which the intrinsic parameters of camera are known, a 4x4 non singular matrix satisfying the conditions of euclidean reconstruction is evaluated, with which projective reconstruction is transformed into euclidean reconstruction. The result indicates that the algorithm is effective.
出处 《中国科学技术大学学报》 CAS CSCD 北大核心 2001年第5期571-576,共6页 JUSTC
基金 国家 8 6 3计划资助项目 (86 3 980 4 0 9)
  • 相关文献

参考文献7

  • 1[1]Faugeras O. What can been seen in three dimensions with an uncalibrated stereo rig[A]. Proc. ECCV'92[C]. Santa Margherita Ligure, Italy: Springer-verlag, 1992. 563~578.
  • 2[2]Hartley R. Stereo from uncalibrated cameras[A]. Proc.CVPR'92[C]. Urbana-Champaign. Illinois: IEEE Computer Society, 1992. 761~764.
  • 3[3]Frangois G. Hierarchical visual perception with calibration[R]. Report of research, 1996, No:3002, INRIA, France.
  • 4[4]Tomasi C, Kanade T. Shape and motion from image streams under orthography: a factori-zation method[J]. International Journal of Computer Vision, 1992,9(2):137~154.
  • 5[5]Poelman C, Kanade T. A paraperspective factorization method for shape and motion recovery[A]. Proc.ECCV'3[C], Stockholm :Springer-Verlag, 1994, Vol.2.97~108.
  • 6[6]Christy C, Horaud R. Euclidean reconstruction: from paraperspective to perspective[A]. Proc. ECCV'4[C], Cambridge: Springer-Verlag, 1996, 2:129~140.
  • 7[7]Sturm P, Triggs B. A factorization based algorithm for multi-image projective structure and motion[A]. Proc. ECCV'4[C], Cambridge: Springer-Verlag, 1996, 2:709~720.

同被引文献58

引证文献6

二级引证文献18

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