Efficient Region Tracking With Parametric Models of Geometry and Illumination
IEEE Transactions on Pattern Analysis and Machine Intelligence
Least squares conformal maps for automatic texture atlas generation
Proceedings of the 29th annual conference on Computer graphics and interactive techniques
Texture Mapping Using Surface Flattening via Multidimensional Scaling
IEEE Transactions on Visualization and Computer Graphics
Contour Tracking by Stochastic Propagation of Conditional Density
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume I - Volume I
ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume II - Volume II
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
Interpreting Face Images Using Active Appearance Models
FG '98 Proceedings of the 3rd. International Conference on Face & Gesture Recognition
View-Based Active Appearance Models
FG '00 Proceedings of the Fourth IEEE International Conference on Automatic Face and Gesture Recognition 2000
Hi-index | 0.00 |
Visual tracking is one of the fundamental problems incomputer vision. The pose of an object extracted throughconsecutive frames has a variety of applications rangingfrom robot navigation to camera based man-machine interfaces.In this paper we examine the use of Active AppearanceModels (AAM) for the task of visual tracking. The originalActive Appearance Model is limited to have all pointsof the model visible in all frames. We introduce a notion ofvisibility uncertainty for the points in the AAM, removingthe above limitation and therefore allowing the object tocontain self-occlusions. The visibility uncertainty is easilyintegrated into the existing AAM framework, keeping modelinitialization time to a minimum.We have experiments illustratingthat the extension allow AAMs to track through selfocclusions at near real-time.