DMCA
Robust Fragments-based Tracking using the Integral Histogram (2006)
Cached
Download Links
- [www.cs.technion.ac.il]
- [www.cs.technion.ac.il]
- DBLP
Other Repositories/Bibliography
| Venue: | In IEEE Conf. Computer Vision and Pattern Recognition (CVPR |
| Citations: | 224 - 0 self |
BibTeX
@INPROCEEDINGS{Adam06robustfragments-based,
author = {Amit Adam and Ehud Rivlin and Ilan Shimshoni},
title = {Robust Fragments-based Tracking using the Integral Histogram},
booktitle = {In IEEE Conf. Computer Vision and Pattern Recognition (CVPR},
year = {2006},
pages = {798--805}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
We present a novel algorithm (which we call “Frag-Track”) for tracking an object in a video sequence. The template object is represented by multiple image fragments or patches. The patches are arbitrary and are not based on an object model (in contrast with traditional use of modelbased parts e.g. limbs and torso in human tracking). Every patch votes on the possible positions and scales of the object in the current frame, by comparing its histogram with the corresponding image patch histogram. We then minimize a robust statistic in order to combine the vote maps of the multiple patches. A key tool enabling the application of our algorithm to tracking is the integral histogram data structure [18]. Its use allows to extract histograms of multiple rectangular regions in the image in a very efficient manner. Our algorithm overcomes several difficulties which cannot be handled by traditional histogram-based algorithms [8, 6]. First, by robustly combining multiple patch votes, we are able to handle partial occlusions or pose change. Second, the geometric relations between the template patches allow us to take into account the spatial distribution of the pixel intensities- information which is lost in traditional histogram-based algorithms. Third, as noted by [18], tracking large targets has the same computational cost as tracking small targets. We present extensive experimental results on challenging sequences, which demonstrate the robust tracking achieved by our algorithm (even with the use of only gray-scale (noncolor) information). 1.
Keyphrases
integral histogram traditional histogram-based algorithm video sequence robust statistic traditional use multiple rectangular region large target object model pixel intensity information template object pose change integral histogram data structure multiple patch challenging sequence modelbased part robust tracking geometric relation partial occlusion template patch algorithm overcomes several difficulty multiple patch vote efficient manner multiple image fragment spatial distribution present extensive experimental result possible position key tool novel algorithm current frame computational cost human tracking corresponding image patch histogram vote map small target
