Unified real-time tracking and recognition with rotation-invariant fast features (2010)
| Venue: | IN [PROC. IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR’10 |
| Citations: | 15 - 8 self |
BibTeX
@INPROCEEDINGS{Takacs10unifiedreal-time,
author = {Gabriel Takacs and Vijay Chandrasekhar and Sam Tsai and David Chen and Radek Grzeszczuk and Bernd Girod},
title = {Unified real-time tracking and recognition with rotation-invariant fast features},
booktitle = {IN [PROC. IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR’10},
year = {2010},
publisher = {}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
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 trackingscheme obtains a more accurate global affine motionmodel than the Kanade Lucas Tomasi (KLT) tracker. The same descriptors can achieve 94^% retrieval accuracy from a database of 10 4 images.
