ML Anthology

Unified Real-Time Tracking and Recognition with Rotation-Invariant Fast Features

Gabriel Takacs, Vijay Chandrasekhar, Sam S. Tsai, David M. Chen, Radek Grzeszczuk, Bernd Girod
CVPR 2010 pp. 934-941
doi:10.1109/CVPR.2010.5540116 /cvpr/2010/takacs2010cvpr-unified/

Abstract

We present a method that unifies tracking and video content recognition with applications to Mobile Augmented Reality (MAR). We introduce the Radial Gradient Transform (RGT) and an approximate RGT, yielding the Rotation-Invariant, Fast Feature (RIFF) descriptor. We demonstrate that RIFF is fast enough for real-time tracking, while robust enough for large scale retrieval tasks. At 26× the speed, our tracking-scheme obtains a more accurate global affine motion-model than the Kanade Lucas Tomasi (KLT) tracker. The same descriptors can achieve 94% retrieval accuracy from a database of 10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">4</sup> images.

PDF CVPR Semantic Scholar

Cite

Text

Takacs et al. "Unified Real-Time Tracking and Recognition with Rotation-Invariant Fast Features." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010. doi:10.1109/CVPR.2010.5540116

Markdown

[Takacs et al. "Unified Real-Time Tracking and Recognition with Rotation-Invariant Fast Features." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010.](https://mlanthology.org/cvpr/2010/takacs2010cvpr-unified/) doi:10.1109/CVPR.2010.5540116

BibTeX

@inproceedings{takacs2010cvpr-unified,
  title     = {{Unified Real-Time Tracking and Recognition with Rotation-Invariant Fast Features}},
  author    = {Takacs, Gabriel and Chandrasekhar, Vijay and Tsai, Sam S. and Chen, David M. and Grzeszczuk, Radek and Girod, Bernd},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2010},
  pages     = {934-941},
  doi       = {10.1109/CVPR.2010.5540116},
  url       = {https://mlanthology.org/cvpr/2010/takacs2010cvpr-unified/}
}