Automatic Tracker Selection W.r.t Object Detection Performance
Abstract
The tracking algorithm performance depends on video content. This paper presents a new multi-object tracking approach which is able to cope with video content variations. First the object detection is improved using Kanade-Lucas-Tomasi (KLT) feature tracking. Second, for each mobile object, an appropriate tracker is selected among a KLT-based tracker and a discriminative appearance-based tracker. This selection is supported by an online tracking evaluation. The approach has been experimented on three public video datasets. The experimental results show a better performance of the proposed approach compared to recent state of the art trackers.
Cite
Text
Chau et al. "Automatic Tracker Selection W.r.t Object Detection Performance." IEEE/CVF Winter Conference on Applications of Computer Vision, 2014. doi:10.1109/WACV.2014.6836012Markdown
[Chau et al. "Automatic Tracker Selection W.r.t Object Detection Performance." IEEE/CVF Winter Conference on Applications of Computer Vision, 2014.](https://mlanthology.org/wacv/2014/chau2014wacv-automatic/) doi:10.1109/WACV.2014.6836012BibTeX
@inproceedings{chau2014wacv-automatic,
title = {{Automatic Tracker Selection W.r.t Object Detection Performance}},
author = {Chau, Duc Phu and Brémond, François and Thonnat, Monique},
booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
year = {2014},
pages = {870-876},
doi = {10.1109/WACV.2014.6836012},
url = {https://mlanthology.org/wacv/2014/chau2014wacv-automatic/}
}