Graphics enhanced version of this site

Mei Han
PhD Student

No longer a member of RI.

Jump to: Research interests | Keywords | Labs & Groups | Projects | Publications

My research interests are in the geometric modeling from video sequences. Currently, I'm working on the subspace constraints embedded within the information integrated over video sequences, and focusing on the problems of 3D modeling, camera calibration, motion segmentation and gesture recognition.

artificial intelligence, computer graphics, computer vision, geometric modeling, gesture recognition, image processing, machine learning, stereo vision, video systems, and visual tracking

• Vision for Virtual Environments - Using techniques from computer vision and robotics, we are developing novel sensing and display technologies to support practical, useful virtual environments.

• Modeling by Videotape - Factorization method of solving the structure-from-motion problem
• Reconfigurable Vision Machine - Developing new hardware and software for high performance computer vision.

• Reconstruction of a Scene with Multiple Linearly Moving Objects
  M. Han and T. Kanade
  International Journal of Computer Vision, Vol. 59, No. 3, September, 2004, pp. 285 - 300.
  Download: pdf [1920 KB] copyrighted

• A perspective factorization method for Euclidean reconstruction with uncalibrated cameras
  M. Han and T. Kanade
  Journal of Visualization and Computer Animation, Vol. 13, No. 4, September, 2002, pp. 211 - 223.
  Download: pdf [1305 KB] copyrighted

• Highlight detection and classification of baseball game video with Hidden Markov Models
  P. Chang, M. Han, and Y. Gong
  Proceedings of the International Conference on Image Processing (ICIP '02), 2002. [Abstract]
  Download: pdf [391 KB] copyrighted

• Multiple motion scene reconstruction from uncalibrated views
  M. Han and T. Kanade
  Proceedings of the Eighth IEEE International Conference on Computer Vision (ICCV '01), Vol. 1, July, 2001, pp. 163 - 170. [Abstract]
  Download: pdf [866 KB] copyrighted

• Liner and Bilinear Subspace Methods for Structure from Motion
  M. Han
  doctoral dissertation, tech. report CMU-RI-TR-01-13, Robotics Institute, Carnegie Mellon University, February, 2001.
  Download: pdf [1974 KB], ps.gz [7295 KB] copyrighted

• Creating 3D Models with Uncalibrated Cameras
  M. Han and T. Kanade
  proceeding of IEEE Computer Society Workshop on the Application of Computer Vision (WACV2000), December, 2000. [Abstract]
  Download: pdf [294 KB] copyrighted

• Reconstruction of a Scene with Multiple Linearly Moving Objects
  M. Han and T. Kanade
  Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR '00), June, 2000. [Abstract]
  Download: pdf [262 KB], ps.gz [1173 KB] copyrighted

• Scene Reconstruction from Multiple Uncalibrated Views
  M. Han and T. Kanade
  tech. report CMU-RI-TR-00-09, Robotics Institute, Carnegie Mellon University, January, 2000. [Abstract]
  Download: pdf [423 KB], ps.gz [3899 KB] copyrighted

• The Factorization Method with Linear Motions
  M. Han and T. Kanade
  tech. report CMU-RI-TR-99-23, Robotics Institute, Carnegie Mellon University, October, 1999. [Abstract]
  Download: pdf [181 KB], ps.gz [849 KB], ps.z [917 KB] copyrighted

• Perspective Factorization Methods for Euclidean Reconstruction
  M. Han and T. Kanade
  tech. report CMU-RI-TR-99-22, Robotics Institute, Carnegie Mellon University, August, 1999. [Abstract]
  Download: pdf [1004 KB], ps.gz [3354 KB] copyrighted