DMCA
Object Tracking by Asymmetric Kernel Mean Shift with Automatic Scale and Orientation Selection (2007)
| Venue: | in Proc. IEEE Conference on Computer Vision and Pattern Recognition |
| Citations: | 35 - 0 self |
BibTeX
@INPROCEEDINGS{Yilmaz07objecttracking,
author = {Alper Yilmaz},
title = {Object Tracking by Asymmetric Kernel Mean Shift with Automatic Scale and Orientation Selection},
booktitle = {in Proc. IEEE Conference on Computer Vision and Pattern Recognition},
year = {2007},
pages = {1--6}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Tracking objects using the mean shift method is performed by iteratively translating a kernel in the image space such that the past and current object observations are similar. Traditional mean shift method requires a symmetric kernel, such as a circle or an ellipse, and assumes constancy of the object scale and orientation during the course of tracking. In a tracking scenario, it is not uncommon to observe objects with complex shapes whose scale and orientation constantly change due to the camera and object motions. In this paper, we present an object tracking method based on the asymmetric kernel mean shift, in which the scale and orientation of the kernel adaptively change depending on the observations at each iteration. Proposed method extends the traditional mean shift tracking, which is performed in the image coordinates, by including the scale and orientation as additional dimensions and simultaneously estimates all the unknowns in a few number of mean shift iterations. The experimental results show that the proposed method is superior to the traditional mean shift tracking in the following aspects: 1) it provides consistent object tracking throughout the video; 2) it is not effected by the scale and orientation changes of the tracked objects; 3) it is less prone to the background clutter. 1.
Keyphrases
asymmetric kernel mean shift orientation selection object tracking automatic scale traditional mean shift tracking image space following aspect tracked object complex shape image coordinate background clutter mean shift method orientation change tracking scenario mean shift iteration object scale object motion experimental result consistent object additional dimension traditional mean shift method current object observation symmetric kernel traditional mean shift
