Robust multiple car tracking with occlusion reasoning
ECCV '94 Proceedings of the third European conference on Computer vision (vol. 1)
X Vision: a portable substrate for real-time vision applications
Computer Vision and Image Understanding
Human motion analysis: a review
Computer Vision and Image Understanding
EigenTracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume I - Volume I
ICONDENSATION: Unifying Low-Level and High-Level Tracking in a Stochastic Framework
ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume I - Volume I
Color-Based Probabilistic Tracking
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
Singularity Analysis for Articulated Object Tracking
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Model-based tracking of self-occluding articulated objects
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Real-time hand tracking using a mean shift embedded particle filter
Pattern Recognition
Trajectory-based representation of human actions
ICMI'06/IJCAI'07 Proceedings of the ICMI 2006 and IJCAI 2007 international conference on Artifical intelligence for human computing
ICCSA'06 Proceedings of the 6th international conference on Computational Science and Its Applications - Volume Part I
Hi-index | 0.00 |
Successful tracking of articulated hand motion is the firststep in many computer vision applications such as gesturerecognition. However the nonrigidity of the hand, complexbackground scenes, and occlusion make tracking a challengingtask. We divide and conquer tracking by decomposingcomplex motion into non-rigid motion and rigid motion.A learning-based algorithm for analyzing non-rigid motionis presented. In this method, appearance-based models arelearned from image data, and underlying motion patternsare explored using a generative model. Non-linear dynamicsof the articulation such as fast appearance deformationcan thus be analyzed without resorting to a complex kinematicmodel. We approximate the rigid motion as planarmotion which can be approached by a filtering method. Weunify our treatments of nonrigid motion and rigid motioninto a single, robust Bayesian framework and demonstratethe efficacy of this method by performing successful trackingin the presence of significant occlusion clutter.