ProjectLinearPredictors

Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

THIS WEBPAGE IS DEPRECATED - please visit our new website

Linear Predictors

Linear Predictors

Linear Predictors

Scientific Director: Dr. Slobodan Ilic , Prof. Dr. Nassir Navab

Contact Person(s): David Tan

Keywords: Computer Vision

Abstract

We address the problem of fast and robust tracking of free-form templates. For this we use Linear Predictors, introduced by Jurie & Dhome in 'Hyperplane Approximation for Template Matching', 2002. This approach allows to track templates at high frame-rates (>1000Hz) very robustly. However, the involved learning requires a significant amount of time and is therefore not suitable for many tasks where the environment is not known a-priori. Within this project we introduced several methods addressing this problem, starting with an adaptive approach that starts with learning a small template and then iteratively grows it over time. This approach also allows to adapt the size and shape of the tracked template during tracking, making it possible to handle occlusions. To speed-up the direct learning of large templates, we introduced two different approaches, a reformulation of the learning equations and a dimensionality reduction step. Both resulting in speed-ups up to two orders of magnitude.

Publications

2014
D. J. Tan , S. Holzer, N. Navab, S. Ilic
Deformable Template Tracking in 1ms (Oral)
British Machine Vision Conference, Nottingham, UK, September 1, 2014 (bib)
2012
S. Holzer, S. Ilic, N. Navab
Multi-Layer Adaptive Linear Predictors for Real-Time Tracking
IEEE Transactions on Pattern Analysis and Maschine Intelligence (TPAMI). (bib)
S. Holzer, S. Ilic, D. J. Tan , N. Navab
Efficient Learning of Linear Predictors using Dimensionality Reduction (Oral)
Asian Conference on Computer Vision (ACCV), Korea, Daejeon, November 2012 (bib)
S. Holzer, M. Pollefeys , S. Ilic, D. J. Tan , N. Navab
Online Learning of Linear Predictors for Real-Time Tracking
12th European Conference on Computer Vision (ECCV), Firenze, Italy, October 2012. (bib)
2010
S. Holzer, S. Ilic, N. Navab
Adaptive Linear Predictors for Real-Time Tracking
IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, California (USA), June 2010. (bib)

Team

Contact Person(s)

David Tan
Dr. David Tan

Working Group

David Tan
Dr. David Tan
Slobodan Ilic
Dr. Slobodan Ilic
Stefan Holzer
M.Sc. Stefan Holzer

Location



Technische Universität München
Institut für Informatik / I16
Boltzmannstr. 3
85748 Garching bei München

Tel.: +49 89 289-17058
Fax: +49 89 289-17059
Visit our lab at Garching.



internal project page

Please contact David Tan for available student projects within this research project.

Video Results

  • Linear Predictors ECCV2012: Learning using the approach of Jurie & Dhome.

  • Linear Predictors ECCV2012: Learning using our approach.

  • Linear Predictors ECCV2012: Non-Planar Scene.

  • Linear Predictors ECCV2012: Tracking in the dark.

References

[1] Jurie, F., Dhome, M.: Hyperplane approximation for template matching. IEEE Transactions on Pattern Analysis and Machine Intelligence (2002)


Edit | Attach | Refresh | Diffs | More | Revision r1.7 - 29 Aug 2016 - 12:27 - DavidTan

Lehrstuhl für Computer Aided Medical Procedures & Augmented Reality    rss.gif