Graphics enhanced version of this site

Qifa Ke
Systems Scientist, RI/CS

No longer a member of RI.

For more information, see my personal homepage.

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

Video analysis, image understanding, subspace learning

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

• Vision for Safe Driving - Computer vision algorithms and systems for automotive safe driving applications.

• Reconfigurable Vision Machine - Developing new hardware and software for high performance computer vision.
• Textureless Layers - Techniques for the 3D reconstruction of scenes consisting of constant intensity piecewise planar regions (layers).

• Quasiconvex Optimization for Robust Geometric Reconstruction
  Q. Ke and T. Kanade
  IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 29, No. 10, October, 2007, pp. 1834 - 1847. [Abstract]
  Download: pdf [1512 KB] copyrighted

• Uncertainty Models in Quasiconvex Optimization for Geometric Reconstruction
  Q. Ke and T. Kanade
  2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 1, June, 2006, pp. 1199 - 1205. [Abstract]
  Download: pdf [646 KB] copyrighted

• Quasiconvex Optimization for Robust Geometric Reconstruction
  Q. Ke and T. Kanade
  tech. report CMU-RI-TR-05-57, Robotics Institute, Carnegie Mellon University, November, 2005. [Abstract]
  Download: pdf [980 KB] copyrighted

• Quasiconvex Optimization for Robust Geometric Reconstruction
  Q. Ke and T. Kanade
  IEEE International Conference on Computer Vision (ICCV 2005), Vol. 2, October, 2005, pp. 986 - 993. [Abstract]
  Download: pdf [293 KB] copyrighted

• Robust L1 Norm Factorization in the Presence of Outliers and Missing Data by Alternative Convex Programming
  Q. Ke and T. Kanade
  IEEE Conference on Computer Vision and Pattern > Recognition (CVPR 2005), June, 2005. [Abstract]
  Download: pdf [849 KB] copyrighted

• Real-Time and 3D Vision for Autonomous Small and Micro Air Vehicles
  T. Kanade, O. Amidi, and Q. Ke
  43rd IEEE Conference on Decision and Control (CDC 2004), December, 2004. [Abstract]
  Download: pdf [1335 KB] copyrighted

• Robust Subspace Clustering by Combined Use of kNND Metric and SVD Algorithm
  Q. Ke and T. Kanade
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2004), IEEE, June, 2004. [Abstract]
  Download: pdf [422 KB] copyrighted

• Textureless Layers
  Q. Ke, S. Baker, and T. Kanade
  tech. report CMU-RI-TR-04-17, Robotics Institute, Carnegie Mellon University, March, 2004. [Abstract]
  Download: pdf [412 KB] copyrighted

• A Robust Subspace Approach to Extracting Layers from Image Sequences
  Q. Ke
  doctoral dissertation, tech. report CMU-CS-03-173, Computer Science Department, Carnegie Mellon University, August, 2003. [Abstract]
  Download: pdf [3211 KB], ps.gz [3244 KB] copyrighted

• Transforming Camera Geometry to A Virtual Downward-Looking Camera: Robust Ego-Motion Estimation and Ground-Layer Detection
  Q. Ke and T. Kanade
  IEEE International Conference on Computer Vision and Pattern Recognition (CVPR 2003), June, 2003. [Abstract]
  Download: pdf [1020 KB] copyrighted