Understanding belief propagation and its generalizations
Exploring artificial intelligence in the new millennium
Tracking Articulated Body by Dynamic Markov Network
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Automatic acquisition and initialization of articulated models
Machine Vision and Applications - Special issue: Human modeling, analysis, and synthesis
Lucas-Kanade 20 Years On: A Unifying Framework
International Journal of Computer Vision
Visual Hand Tracking Using Nonparametric Belief Propagation
CVPRW '04 Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'04) Volume 12 - Volume 12
Unsupervised Learning of Object Features from Video Sequences
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Automatic Kinematic Chain Building from Feature Trajectories of Articulated Objects
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Building Models of Animals from Video
IEEE Transactions on Pattern Analysis and Machine Intelligence
Incremental discovery of object parts in video sequences
Computer Vision and Image Understanding
Unsupervised Learning of Skeletons from Motion
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part III
An iterative image registration technique with an application to stereo vision
IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2
| Hi-index | 0.00 |
We propose a new framework that allows simultaneous modelling and tracking of articulated objects in real time. We introduce a non-probabilistic graphical model and a new type of message that propagates explicit motion information for realignment of feature constellations across frames. These messages are weighted according to the rigidity of the relations between the source and destination features. We also present a method for learning these weights as well as the spatial relations between connected feature points, automatically identifying deformable and rigid object parts. Our method is extremely fast and allows simultaneous learning and tracking of nonrigid models containing hundreds of feature points with negligible computational overhead.