Efficient Tracking as Linear Program on Weak Binary Classifiers

Authors:
Michael Grabner;Christopher Zach;Horst Bischof
Affiliations:
Microsoft Photogrammetry, Graz, Austria and Institute for Computer Graphics and Vision, Graz University of Technology,;Department of Computer Science, University of North Carolina, Chapel Hill,;Institute for Computer Graphics and Vision, Graz University of Technology,
Venue:
Proceedings of the 30th DAGM symposium on Pattern Recognition
Year:
2008

Citing 16
Cited 0

The weighted majority algorithm

Information and Computation
Non-parametric local transforms for computing visual correspondence

ECCV '94 Proceedings of the third European conference on Computer Vision (Vol. II)
Bagging predictors

Machine Learning
A decision-theoretic generalization of on-line learning and an application to boosting

Journal of Computer and System Sciences - Special issue: 26th annual ACM symposium on the theory of computing & STOC'94, May 23–25, 1994, and second annual Europe an conference on computational learning theory (EuroCOLT'95), March 13–15, 1995
Ensemble Methods in Machine Learning

MCS '00 Proceedings of the First International Workshop on Multiple Classifier Systems
Dynamic Weighted Majority: A New Ensemble Method for Tracking Concept Drift

ICDM '03 Proceedings of the Third IEEE International Conference on Data Mining
Sparse Bayesian Learning for Efficient Visual Tracking

IEEE Transactions on Pattern Analysis and Machine Intelligence
On-line Boosting and Vision

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Keypoint Recognition Using Randomized Trees

IEEE Transactions on Pattern Analysis and Machine Intelligence
Ensemble Tracking

IEEE Transactions on Pattern Analysis and Machine Intelligence
Robust Real-Time Pattern Matching Using Bayesian Sequential Hypothesis Testing

IEEE Transactions on Pattern Analysis and Machine Intelligence
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
On-line ensemble SVM for robust object tracking

ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part I
Feature harvesting for tracking-by-detection

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part III
Learning efficient linear predictors for motion estimation

ICVGIP'06 Proceedings of the 5th Indian conference on Computer Vision, Graphics and Image Processing
Support vector tracking

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper demonstrates how a simple, yet effective, set of features enables to integrate ensemble classifiers in optical flow based tracking. In particular, gray value differences of pixel pairs are used for generating binary weak classifiers, forming the respective object representation. For the tracking step an affine motion model is proposed. By using hinge loss functions, the motion estimation problem can be formulated as a linear program. Experiments demonstrate robustness of the proposed approach and include comparisons to conventional tracking methods.