Graphics enhanced version of this site

Peng Chang
PhD Student

No longer a member of RI.

Jump to: Research interests | Keywords | Projects | Publications

I develop vision algorithms that can track targets, recover camera motion and 3D scene simultaneousely. I am especially interested in making the algorithms robust against occlusions and abrupt camera motions. The strength of my approach lies on the faithful representation of the uncertainty in the vision algorithms. For more results, please check my personal web page.

After an internship in NEC USA Corp., I became very interested in high dimensional multi-media data mining and knowledge discovery problem.

computer vision, pattern recognition, and visual tracking

• Tactical Mobile Robotics - As part of the DARPA Tactial Mobile Robotics program, we are developing techniques for semi-autonomous navigation of a small robot in urban environments.
• Unmanned Ground Vehicles - Developing autonomous navigation capabilities for mobile robots driving in complex, unstructured outdoor terrain.

Note: This list may not be comprehensive. It contains only those publications in the RI publications database. Entries are listed in reverse chronological order.

• Robust Tracking and Structure from Motion with Sampling Method
  P. Chang
  doctoral dissertation, tech. report CMU-RI-TR-02-33, Robotics Institute, Carnegie Mellon University, February, 2003. [Abstract]
  Download: pdf [10341 KB] copyrighted

• Robust tracking and structure from motion through sampling based uncertainty representation
  P. Chang and M. Hebert
  Proceedings of ICRA '02, May, 2002. [Abstract]
  Download: pdf [2299 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

• Omni-directional structure from motion
  P. Chang and M. Hebert
  Proceedings of the 2000 IEEE Workshop on Omnidirectional Vision, June, 2000, pp. 127 - 133. [Abstract]
  Download: pdf [424 KB] copyrighted

• Experiments with Driving Modes for Urban Robots
  M. Hebert, R. MacLachlan, and P. Chang
  Proceedings of SPIE, 1999. [Abstract]
  Download: pdf [2200 KB] copyrighted

• Object Recognition with Color Cooccurrence Histogram
  P. Chang and J. Krumm
  Proceedings of CVPR '99, 1999. [Abstract]
  Download: pdf [225 KB], ps.gz [1171 KB] copyrighted

• Omni-directional Visual Servoing for Human-Robot interaction
  P. Chang and M. Hebert
  Proceedings of the 1998 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS '98), Vol. 3, October, 1998, pp. 1801 - 1807. [Abstract]
  Download: pdf [355 KB], ps.gz [676 KB] copyrighted