期刊文献+

采用标记点的弹性连接体三维建模与运动估计

3D Modeling and Motion Estimation of Elastic Articulated Objects from Image Points
下载PDF
导出
摘要 为了采用非常少的参数就能反映人肢体皮肤的变形,提出了一种新的旋转圆锥曲面进行弹性连接体(人体)三维建模,模型包括了人体三维骨架和代表人肢体皮肤的变形曲面方程,每个肢体只需调整一个变形参数就能反映出人肢体皮肤的变形.根据双目图像序列的标记点估计人体三维变形和运动参数,包括了骨架的运动参数估计和变形曲面的变形参数确定.实验结果表明:模型能正确地反映人肢体皮肤的变形,运动估计算法能精确地估计人体运动参数. This paper presented a new method of elastic articulated objects (human bodies) modeling based on a new revolving conic surface. The model includes 3D object skeleton and deformable surfaces which can represent the deformation of human body surfaces. The deformation of human body surfaces can be represented by adjusting only one deformation parameter for each limb. Then, the 3D deformation and motion parameters are determined by corresponding 2D image points with volume invariable constraint from a sequences of stereo images. The algorithm presented in this paper includes motion parameter estimation of the skeleton and parameter determination of deformable surface.
出处 《上海交通大学学报》 EI CAS CSCD 北大核心 2008年第10期1627-1630,共4页 Journal of Shanghai Jiaotong University
基金 中国博士后科学基金资助项目(20070421018)
关键词 弹性连接体 人体建模 旋转圆锥曲面 运动估计 elastic articulated object human body modeling revolving conic surface motion estimation
  • 相关文献

参考文献11

  • 1Moeslund T B, Hilton A, Kruger V. A survey of advances in vision-based human motion capture and analysis[J]. Computer Vision and Image Understanding, 2006, 104(2): 90-126.
  • 2Nahas M, Huitric H, Saintourens M. Animation of a B-spline figure[J]. Visual Computer, 1988, 3 (5) : 272-276.
  • 3Petland A, Horowitz B. Recovery of nonrigid motion and structure[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1991, 13(7) : 730-742.
  • 4Min K H, Baek S M, Lee G A, etal. Anatomicallybased modeling and animation of human upper limbs [ C]//Proceedings of International Conference on Human Modeling and Animation. Seoul, Korea:IEEE Computer Society Press, 2000 : 1-14.
  • 5Plankers R, Fua P. Articulated soft objects for multiview shape and motion capture[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2003, 25(9): 1182-1187.
  • 6Sminchisescu C. Estimation algorithms for ambiguous visual models-Three dimensional human modeling and motion reconstruction in monocular video sequences[D]. Paris: INRIA, 2002.
  • 7D'Apuzzo N, Plankers R, Gruen A, etal. Modelling human bodies from video sequences [C]//Proceedings of Electronic Imaging. San Jose, California: SPIE Press, 1999: 1-12.
  • 8Jain R C, Kasturi R, Schunk B. Machine Vision [M]. New York: McGraw Hill Inc, 1995.
  • 9Zhang X Y, Liu Y C, Huang T S. Articulated joint estimation from motion using two monocular images [J]. Pattern Recognition Letters, 2004, 25 (10): 1097-1106.
  • 10Zhang X Y, Liu Y C, Huang T S. Motion analysis of articulated objects from monocular images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(4):625-663.

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