Robust Multi-Object Tracking Using Re-Identification Features and Graph Convolutional Networks

Christian Lusardi, Abu Md Niamul Taufique, Andreas E. Savakis

ICCVW 2021 pp. 3861-3870

doi:10.1109/ICCVW54120.2021.00433 /iccvw/2021/lusardi2021iccvw-robust/

Abstract

We propose a graph neural network-based framework for multi-object tracking that combines detection and association along with the use of a novel re-identification feature. We explore the combination of multiple appearance features within our framework to obtain a better representation and improve tracking accuracy. Data augmentations with random erase and random noise are utilized to improve robustness during tracking. We consider various types of losses during training, including a unique application of the triplet loss to improve overall network performance. Results are presented on the UAVDT benchmark dataset for aerial-based vehicle tracking under various conditions.

ICCVW Semantic Scholar

Cite

Text

Lusardi et al. "Robust Multi-Object Tracking Using Re-Identification Features and Graph Convolutional Networks." IEEE/CVF International Conference on Computer Vision Workshops, 2021. doi:10.1109/ICCVW54120.2021.00433

Markdown

[Lusardi et al. "Robust Multi-Object Tracking Using Re-Identification Features and Graph Convolutional Networks." IEEE/CVF International Conference on Computer Vision Workshops, 2021.](https://mlanthology.org/iccvw/2021/lusardi2021iccvw-robust/) doi:10.1109/ICCVW54120.2021.00433

BibTeX

@inproceedings{lusardi2021iccvw-robust,
  title     = {{Robust Multi-Object Tracking Using Re-Identification Features and Graph Convolutional Networks}},
  author    = {Lusardi, Christian and Taufique, Abu Md Niamul and Savakis, Andreas E.},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2021},
  pages     = {3861-3870},
  doi       = {10.1109/ICCVW54120.2021.00433},
  url       = {https://mlanthology.org/iccvw/2021/lusardi2021iccvw-robust/}
}