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

Christian Lusardi, Abu Md Niamul Taufique, Andreas Savakis; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2021, pp. 3868-3877

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.

Related Material

[pdf]
[bibtex]
@InProceedings{Lusardi_2021_ICCV, author = {Lusardi, Christian and Taufique, Abu Md Niamul and Savakis, Andreas}, title = {Robust Multi-Object Tracking Using Re-Identification Features and Graph Convolutional Networks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2021}, pages = {3868-3877} }