Multiple Object Tracking with Motion and Appearance Cues
Abstract
Due to better video quality and higher frame rate, the performance of multiple object tracking issues has been greatly improved in recent years. However, in real application scenarios, camera motion and noisy per frame detection results degrade the performance of trackers significantly. High-speed and high-quality multiple object trackers are still in urgent demand. In this paper, we propose a new multiple object tracker following the popular tracking-by-detection scheme. We tackle the camera motion problem with an optical flow network and utilize an auxiliary tracker to deal with the missing detection problem. Besides, we use both the appearance and motion information to improve the matching quality. The experi-mental results on the VisDrone-MOT dataset show that our approach can improve the performance of multiple object tracking significantly while achieving a high efficiency.
Cite
Text
Li et al. "Multiple Object Tracking with Motion and Appearance Cues." IEEE/CVF International Conference on Computer Vision Workshops, 2019. doi:10.1109/ICCVW.2019.00025Markdown
[Li et al. "Multiple Object Tracking with Motion and Appearance Cues." IEEE/CVF International Conference on Computer Vision Workshops, 2019.](https://mlanthology.org/iccvw/2019/li2019iccvw-multiple/) doi:10.1109/ICCVW.2019.00025BibTeX
@inproceedings{li2019iccvw-multiple,
title = {{Multiple Object Tracking with Motion and Appearance Cues}},
author = {Li, Weiqiang and Mu, Jiatong and Liu, Guizhong},
booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
year = {2019},
pages = {161-169},
doi = {10.1109/ICCVW.2019.00025},
url = {https://mlanthology.org/iccvw/2019/li2019iccvw-multiple/}
}