Tracking Non-Rigid, Moving Objects Based on Color Cluster Flow
Abstract
In this contribution we present an algorithm for tracking non-rigid, moving objects in a sequence of colored images, which were recorded by a non-stationary camera. The application background is vision-based driving assistance in the inner city. In an initial step, object parts are determined by a divisive clustering algorithm, which is applied to all pixels in the first image of the sequence. The feature space is defined by the color and position of a pixel. For each new image the clusters of the previous image are adapted iteratively by a parallel k-means clustering algorithm. Instead of tracking single points, edges, or areas over a sequence of images, only the centroids of the clusters are tracked. The proposed method remarkably simplifies the correspondence problem and also ensures a robust tracking behaviour.
Cite
Text
Heisele et al. "Tracking Non-Rigid, Moving Objects Based on Color Cluster Flow." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997. doi:10.1109/CVPR.1997.609329Markdown
[Heisele et al. "Tracking Non-Rigid, Moving Objects Based on Color Cluster Flow." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997.](https://mlanthology.org/cvpr/1997/heisele1997cvpr-tracking/) doi:10.1109/CVPR.1997.609329BibTeX
@inproceedings{heisele1997cvpr-tracking,
title = {{Tracking Non-Rigid, Moving Objects Based on Color Cluster Flow}},
author = {Heisele, Bernd and Kressel, Ulrich and Ritter, W.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {1997},
pages = {257-260},
doi = {10.1109/CVPR.1997.609329},
url = {https://mlanthology.org/cvpr/1997/heisele1997cvpr-tracking/}
}