CS 598 Applications of Computer Vision

Modules

1. Human Motion: 3D and 2D
   • Class notes:
     • Extensive notes on human tracking, animation and activity recognition
     • Revised version of above notes on human tracking, animation and activity recognition
   • General Readings:
     • C. Taylor. Reconstruction of articulated objects from point correspondences in a single uncalibrated image. In IEEE Conf. on Computer Vision and Pattern Recognition, pages 677-84, 2000.
     • C. Taylor. Reconstruction of articulated objects from point correspondences in a single uncalibrated image. CVIU, 80(3):349-363, December 2000.
     • C. Barron and I. Kakadiaris. Estimating anthropometry and pose from a single uncalibrated image. CVIU, 81(3):269-284, March 2001.
     • G. Mori, , and J. Malik. Estimating human body configurations using shape context matching. In European Conference on Computer Vision LNCS 2352, volume 3, pages 666-680, 2002.
   • Readings for Presentation:
     • V. Athitsos and S. Sclaroff. An appearance-based framework for 3d hand shape classification and camera viewpoint estimation. In AFGR02, pages 40-45, 2002.
     • V. Athitsos and S. Sclaroff. Estimating 3d hand pose from a cluttered image. In CVPR03, pages II: 432-439, 2003.
     • M. Lee and I. Cohen. Human upper body pose estimation in static images. In ECCV04, pages Vol II: 126-138, 2004.
     • M. Lee and I. Cohen. Proposal maps driven mcmc for estimating human body pose in static images. In CVPR04, pages II: 334-341, 2004.
     • G. Shakhnarovich, P. Viola, and T. Darrell. Fast pose estimation with parameter-sensitive hashing. In ICCV03, pages 750-757, 2003.
     • A. Agarwal and B. Triggs. Learning to track 3d human motion from silhouettes. In ICML 04: Proceedings of the twenty-first international conference on Machine learning, page 2, New York, NY, USA, 2004. ACM Press.
     • G. Mori, , and J. Malik. Estimating human body configurations using shape context matching. In European Conference on Computer Vision LNCS 2352, volume 3, pages 666-680, 2002.
     • C. Sminchisescu and A. Telea. Human pose estimation from silhouettes: A consistent approach using distance level sets. In WSCG02, page 413, 2002.
     • K.-M. G. Cheung, S. Baker, and T. Kanade. Shape-from-silhouette across time part ii: Applications to human modeling and markerless motion tracking. Int. J. Comput. Vision, 63(3):225-245, 2005.
     • R. Pl"ankers and P. Fua. Tracking and modeling people in video sequences. Comput. Vis. Image Underst., 81(3):285-302, 2001
2. Human Motion: Tracking in 3D
   • Background: Particle Filters
     • D.A. Forsyth, Tracking with non-linear dynamic models, orphaned chapter that didn't make it into Forsyth+Ponce, 2001.
   • Particle filters with MCMC
     • K. Choo and D. Fleet. People tracking using hybrid monte carlo filtering. In ICCV01, pages II: 321-328, 2001.
   • Annealed Particle Filters
     • J. Deutscher and I. Reid. Articulated body motion capture by stochastic search. IJCV, 61(2):185-205, February 2005
   • Reduced Dimension Models
     • H. Sidenbladh, M. J. Black, and D. J. Fleet. Stochastic tracking of 3d human figures using 2d image motion. In European Conference on Computer Vision, 2000
   • Randomized Search
     • C. Sminchisescu and B. Triggs. Estimating articulated human motion with covariance scaled sampling. The International Journal of Robotics Research, 22(6):371-391, 2003.

   • Human Motion: Data Association Methods
     • Detecting People with static templates
       • N. Dalal and B. Triggs. Histograms of oriented gradients for human detection. In IEEE Conf. on Computer Vision and Pattern Recognition, pages I: 886-893, 2005.
     • Detecting People with motion templates
       • P. Viola, M. Jones, and D. Snow. Detecting pedestrians using patterns of motion and appearance. Int. J. Computer Vision, 63(2):153 -161, July 2005.
     • Detecting People using body parts
       • A. Mohan, C. Papageorgiou, and T. Poggio. Example-based object detection in images by components. IEEE T. Pattern Analysis and Machine Intelligence, 23(4):349-361, April 2001.
       • D. Forsyth and M. Fleck. Body plans. In IEEE Conf. on Computer Vision and Pattern Recognition, pages 678-683, 1997.
       • R. Ronfard, C. Schmid, and B. Triggs. Learning to parse pictures of people. In Euro- pean Conference on Computer Vision, page IV: 700 ff., 2002.
     • Detecting People using codebooks
       • B. Leibe, E. Seemann, and B. Schiele. Pedestrian detection in crowded scenes. In IEEE Conf. on Computer Vision and Pattern Recognition, pages I: 878-885, 2005.
     • Tracking with Templates
       • S. Ioffe and D. Forsyth. Human tracking with mixtures of trees. In Int. Conf. on Computer Vision, pages I: 690-695, 2001.
       • K. Toyama and A. Blake. Probabilistic tracking with exemplars in a metric space. Int. J. Computer Vision, 48(1):9-19, June 2002.
       • D. Ramanan and D. Forsyth. Automatic annotation of everyday movements. In Proc. Neural Information Processing Systems, 2003.
       • D. Ramanan and D. Forsyth. Finding and tracking people from the bottom up. In IEEE Conf. on Computer Vision and Pattern Recognition, pages II: 467-474, 2003.
       • D. Ramanan, D. Forsyth, and A. Zisserman. Strike a pose: Tracking people by finding stylized poses. In IEEE Conf. on Computer Vision and Pattern Recognition, pages I: 271-278, 2005.
       • N. Howe. Silhouette lookup for automatic pose tracking. In IEEE Workshop on Artic- ulated and Non-Rigid Motion, page 15, 2004.
       • N. R. Howe, M. E. Leventon, andW. T. Freeman. Bayesian reconstruction of 3d human motion from single-camera video. In S. Solla, T. Leen, and K.-R. Muller, editors, Advances in Neural Information Processing Systems 12, pages 820-26. MIT Press, 2000.
   • Activities, Gestures, Sign
     • Activity as a pattern of motion
     • A. A. Efros, A. C. Berg, G. Mori, and J. Malik. Recognizing action at a distance. In ICCV 03: Proceedings of the Ninth IEEE International Conference on Computer Vision, pages 726-733, Washington, DC, USA, 2003. IEEE Computer Society.
     • Activity with finite state models
     • Layered representations for learning and inferring office activity from multiple sensory channels Nuria Olivera, Ashutosh Garg, Eric Horvitz Computer Vision and Image Understanding 96 (2004) 163¡V180
     • M. Brand. Shadow puppetry. In Int. Conf. on Computer Vision, pages 1237-1244, 1999.
     • A. Bobick and A.Wilson. A state based approach to the representation and recognition of gesture. IEEE T. Pattern Analysis and Machine Intelligence, 19(12):1325-1337, December 1997.
     • X. Feng and P. Perona. Human action recognition by sequence of movelet codewords. In 3D Data Processing Visualization and Transmission, 2002. Proceedings. First Inter- national Symposium on, pages 717-721, 2002.
     • T. Zhao and R. Nevatia. Tracking multiple humans in complex situations. IEEE T. Pattern Analysis and Machine Intelligence, 26(9):1208-1221, September 2004.
     • Sign Language
     • Computer Vision and Image Understanding 81, 358¡V384 (2001) A Framework for Recognizing the Simultaneous Aspects of American Sign Language Christian Vogler and Dimitris Metaxas
     • T. Starner, J. Weaver, and A. Pentland. Real-time american sign language recognition using desk and wearable computer based video. IEEE T. Pattern Analysis and Machine Intelligence, 20(12):1371-1375, 1998.