Carnegie Mellon Robotics Institute
Iain Matthews, Takahiro Ishikawa, and Simon Baker
Proceedings of the British Machine Vision Conference, September, 2003.
| Download |
|
| Abstract |
| Template tracking is a well studied problem in computer vision which dates back to the Lucas-Kanade algorithm of 1981. Since then the paradigm has been extended in a variety of ways including: arbitrary parametric transformations of the template, and linear appearance variation. These extensions have been combined, culminating in non-rigid appearance models such as Active Appearance Models (AAMs) and Active Blobs. One question that has received very little attention is how to update the template over time so that it remains a good model of the object being tracked. This paper proposes an algorithm to update the template that avoids the "drifting" problem of the naive update algorithm. Our algorithm can be interpreted as a heuristic to avoid local minima. It can also be extended to templates with linear appearance variation. This extension can be used to convert (update) a generic, person-independent AAM into a person specific AAM. |
| Notes |
Sponsor: Denso Corporation, US Department of Defense Grant ID: N41756-03-C4024 Associated Center(s) / Consortia:
Vision and Autonomous Systems Center Associated Lab(s) / Group(s):
Vision for Safe Driving and Face Group Associated Project(s):
Template Update, Face Model Building and Fitting, Car Tracking |
| Text Reference |
| Iain Matthews, Takahiro Ishikawa, and Simon Baker, "The Template Update Problem," Proceedings of the British Machine Vision Conference, September, 2003. |
| BibTeX Reference |
|
@inproceedings{Matthews_2003_4433, author = "Iain Matthews and Takahiro Ishikawa and Simon Baker", title = "The Template Update Problem", booktitle = "Proceedings of the British Machine Vision Conference", month = "September", year = "2003", } |
| The Robotics Institute is part of the School of Computer Science, Carnegie Mellon University. Contact Us | Update Instructions |