SURFTrac: Efficient Tracking and Continuous Object Recognition using Local Feature Descriptors

DMCA

SURFTrac: Efficient Tracking and Continuous Object Recognition using Local Feature Descriptors (2009)

Cached

Download Links

by Duy-nguyen Ta , Wei-chao Chen , Natasha Gelfand , Kari Pulli

Venue:	In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR09
Citations:	29 - 3 self

BibTeX

@INPROCEEDINGS{Ta09surftrac:efficient,
    author = {Duy-nguyen Ta and Wei-chao Chen and Natasha Gelfand and Kari Pulli},
    title = {SURFTrac: Efficient Tracking and Continuous Object Recognition using Local Feature Descriptors},
    booktitle = {In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR09},
    year = {2009}
}

OpenURL

Abstract

We present an efficient algorithm for continuous image recognition and feature descriptor tracking in video which operates by reducing the search space of possible interest points inside of the scale space image pyramid. Instead of performing tracking in 2D images, we search and match candidate features in local neighborhoods inside the 3D image pyramid without computing their feature descriptors. The candidates are further validated by fitting to a motion model. The resulting tracked interest points are more repeatable and resilient to noise, and descriptor computation becomes much more efficient because only those areas of the image pyramid that contain features are searched. We demonstrate our method on real-time object recognition and label augmentation running on a mobile device. 1.

Keyphrases

local feature descriptor continuous object recognition efficient tracking image pyramid feature descriptor scale space image pyramid continuous image recognition descriptor computation efficient algorithm real-time object recognition local neighborhood possible interest point label augmentation contain feature candidate feature motion model tracked interest point mobile device search space

DMCA