Rank-Constrained Tracking

(by Bryan Poling, Gilad Lerman & Arthur Szlam)

Supplemental Webpage

Code (C++/OpenCV)

Feature Tracking Dataset

Video Spotlight

Qualitative Results On Real Videos

Synthetic Experiment Results Files


Poling, B., Lerman, G., Szlam, A.: Better Feature Tracking Through Subspace Constraints. Computer Vision and Pattern Recognition, 2014. CVPR 2014. URL: TBD (Preprint: arxiv:1405.2316, Appendix (supplemental text))


University of Minnesota Math/Physics Seminar - 2014 (Slides)
Demonstration videos (low-light indoor scene):
KLT tracker with gyro-homography initialization
Gradient descent tracker with gyro-homography initialization
Rank-penalized tracker

Support Acknowledgement

This work was supported by NSF award DMS-09-56072, the Sloan foundation, the University of Minnesota Doctoral Dissertation Fellowship Program, and the Feinberg Foundation Visiting Faculty Program Fellowship of the Weizmann Institute of Science.

Back to Gilad Lerman's webpage

Last Modified Monday June 02, 2014
The views and opinions expressed in this page are strictly those of the page author. The contents of this page have not been reviewed or approved by the University of Minnesota.