Graphics enhanced version of this site

Steven Shafer
Associate Professor of Computer Science and Robotics (Adjunct)

No longer a member of RI.

For more information, see my personal homepage.

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

My research is in computer vision, making computers see. My particular interests are in using vision to enhance human-computer interaction, especially in combination with speech recognition; and in understanding the physics of image formation, including color, highlights, texture, shadows, lighting, and the imaging system.

computer vision and human-computer interaction

• Calibrated Imaging Lab - High precision vision and imaging lab

• Depth From Focus and Defocus - Focus interpretation is a valuable alternative to stereo vision because it doesn't require solving correspondence for depth recovery.
• Spatial Frequency - Our space / frequency representation has proven useful for solving the combined problem of segmentation and shape from texture.
• Zoom Lens Calibration - We have developed new algorithms and techniques to build models for cameras with automated zoom lenses

• Moment and Hypergeometric Filters for High Precision Computation of Focus, Stereo and Optical Flow
  Y. Xiong and S. Shafer
  International Journal of Computer Vision, Vol. 22, No. 1, February, 1997, pp. 25-59.

• Performance Analysis of Color and Black & White Cameras
  J. Dey, N. Salzman, and S. Shafer
  tech. report CMU-RI-TR-97-07, Robotics Institute, Carnegie Mellon University, February, 1997. [Abstract]
  Download: pdf [553 KB], ps.gz [3639 KB] copyrighted

• Physics-Based Segmentation: Moving Beyond Color
  B. Maxwell and S. Shafer
  Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, June, 1996, pp. 742 - 749. [Abstract]
  Download: pdf [94 KB], ps.gz [103 KB] copyrighted

• A Taxonomy for Stereo Computer Vision Experiments
  M. Maimone and S. Shafer
  ECCV Workshop on Performance Characteristics of Vision Algorithms, April, 1996, pp. 59 - 79.
  Download: pdf [897 KB], ps.gz [1206 KB] copyrighted

• Physics-Based Segmentation: Looking Beyond Color
  B. Maxwell and S. Shafer
  Proceedings of Image Understanding Workshop, 1996.
  Download: pdf [232 KB], ps.gz [274 KB] copyrighted

• Dense Structure from a Dense Optical Flow Sequence
  Y. Xiong and S. Shafer
  Proceedings of the 1995 International Symposium on Computer Vision, November, 1995, pp. 1 - 6. [Abstract]
  Download: pdf [673 KB] copyrighted

• Physics-Based Segmentation: Looking Beyond Color
  B. Maxwell and S. Shafer
  tech. report CMU-RI-TR-95-37, Robotics Institute, Carnegie Mellon University, October, 1995. [Abstract]
  Download: pdf [2159 KB] copyrighted

• Modeling Foreshortening in Stereo Vision using Local Spatial Frequency
  M. Maimone and S. Shafer
  Proceedings of the 1995 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS '95), Vol. 1, August, 1995, pp. 519 - 524. [Abstract]
  Download: pdf [574 KB] copyrighted

• Moment Filters for High Precision Computation of Focus and Stereo
  Y. Xiong and S. Shafer
  IEEE/RSJ International Conference on Intelligent Robots and Systems,'Human Robot Interaction and Cooperative Robots', August, 1995, pp. 108 - 113. [Abstract]
  Download: pdf [1016 KB], ps.gz [1068 KB], ps.z [1436 KB] copyrighted

• Hypergeometric Filters for Optical Flow and Affine Matchine
  Y. Xiong and S. Shafer
  The Fifth International Conference on Computer Vision, June, 1995, pp. 771-776.
  Download: pdf [652 KB], ps.gz [691 KB], ps.z [850 KB] copyrighted