Better feature tracking through subspace constraints

Bryan Poling, Gilad Lerman, Arthur Szlam

Research output: Chapter in Book/Report/Conference proceedingConference contribution

14 Scopus citations

Abstract

Feature tracking in video is a crucial task in computer vision. Usually, the tracking problem is handled one feature at a time, using a single-feature tracker like the Kanade-Lucas-Tomasi algorithm, or one of its derivatives. While this approach works quite well when dealing with high-quality video and 'strong' features, it often falters when faced with dark and noisy video containing low-quality features. We present a framework for jointly tracking a set of features, which enables sharing information between the different features in the scene. We show that our method can be employed to track features for both rigid and non-rigid motions (possibly of few moving bodies) even when some features are occluded. Furthermore, it can be used to significantly improve tracking results in poorly-lit scenes (where there is a mix of good and bad features). Our approach does not require direct modeling of the structure or the motion of the scene, and runs in real time on a single CPU core.

Original languageEnglish (US)
Title of host publicationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
PublisherIEEE Computer Society
Pages3454-3461
Number of pages8
ISBN (Electronic)9781479951178, 9781479951178
DOIs
StatePublished - Sep 24 2014
Event27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014 - Columbus, United States
Duration: Jun 23 2014Jun 28 2014

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)1063-6919

Other

Other27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014
CountryUnited States
CityColumbus
Period6/23/146/28/14

Keywords

  • Feature Tracking
  • Low-Rank Regularization
  • Optical Flow
  • nonconvex optimization

Fingerprint

Dive into the research topics of 'Better feature tracking through subspace constraints'. Together they form a unique fingerprint.

Cite this