a tracker frame

Finding and Tracking People

Much research on this topic sees it as a problem in probabilistic inference.  I think the significance of  the probability and algorithmic aspects of
this problem is much overrated; the major difficulties are vision problems.  One has to reason about what things look like, reason about appropriate
feature representations, then determine how to find instances of the people in each frame.  

I wrote an extensive review of this area (nearly 500 citations in it!)

David A. Forsyth, Okan Arikan, Leslie Ikemoto, James O' Brien, Deva Ramanan, Computational Studies of Human Motion: Part 1, Tracking and Motion Synthesis, Foundations and Trends¨ in Computer Graphics and Vision Volume 1 Issue 2/3 (255pp), 2006 

My sometime student, Deva Ramanan, has been especially active in this area, and his work is worth reading closely.

Current students who have worked in this area include: Alex Sorokin, Duan Tran and Du Tran

Finding People

  1. M.M. Fleck, D.A. Forsyth and C. Bregler, ``Finding naked people,'' Proc. European Conf. on Computer Vision , Edited by: Buxton, B.; Cipolla, R. Berlin, Germany: Springer-Verlag, 1996. p. 593-602                                                                                                             
  2. Forsyth, D.A.; Fleck, M.M. ``Identifying nude pictures'', Proceeding. Third IEEE Workshop on Applications of Computer Vision. 103-108, 1996.    
  3. Forsyth, D.A. and Fleck, M.M., ``Body Plans,'' Proc. CVPR-97, 678-83, 1997.
  4. Forsyth, D.A. and Fleck, M. M., ``Automatic Detection of Human Nudes,'' International Journal of Computer Vision , 32 , 1, 63-77, August, 1999   
  5. Ioffe, S. and Forsyth, D.A., ``Learning to find pictures of people,'' in M. S. Kearns, S. A. Solla, and D. A. Cohn, editors, Advances in Neural Information Processing Systems 11 , MIT Press, Cambridge, MA, 1999
  6. Duan Tran and D.A. Forsyth, "Configuration estimates improve pedestrian finding," Proc NIPS 2007.


Tracking people

  1. S. Ioffe and D.A. Forsyth, ``Human tracking with mixtures of trees,'' Proc. IEEE InternationalConference on Computer Vision , pp. 690-695, July, 2001  
  2. Ramanan, D. and Forsyth, D. A. "Finding and tracking people from the bottom up" in Proceedings of Computer Vision and Pattern Recognition (CVPR), Madison, Wisconsin, June 2003. 
  3. Ramanan, D. and Forsyth, D. A. "Automatic Annotation of Everyday Movements" Neural Info. Proc. Systems (NIPS), Vancouver, Canada, Dec 2003. poster (Longer technical report version)       
  4. Ramanan, D. and Forsyth, D. A. "Using Temporal Coherence to Build Models of Animals" Intl. Conf. on Computer Vision (ICCV), Nice, France, Oct 2003. talk slides (talk video 82MB streaming)    
  5. Ramanan, D., Forsyth, D. A., Zisserman, A."Strike a Pose: Tracking People by Finding Stylized Poses." Computer Vision and Pattern Recognition (CVPR), San Diego, CA, June 2005                                 
  6. Ramanan, D., Forsyth, D. A., Barnard, K. "Detecting, Localizing, and Recovering Kinematics of Textured Animals." Computer Vision and Pattern Recognition (CVPR), San Diego, CA, June 2005.                            
  7. Ramanan, D.; Forsyth, D.A.; Barnard, K.;, "Building models of animals from video" Pattern Analysis and Machine Intelligence, IEEE Transactions on Volume 28, Issue 8, Aug. 2006 Page(s):1319 - 1334                                                                                                                                             
  8. Ramanan, D; Forsyth, D.A.; Zisserman, A; "Tracking People by Learning Their Appearance," IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 29, no 1, pp 65-81, 2007.