Title | ||
---|---|---|
Robust Multi-Object Tracking Using Re-Identification Features and Graph Convolutional Networks |
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. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/ICCVW54120.2021.00433 | 2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2021) |
DocType | ISSN | Citations |
Conference | 2473-9936 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Christian Lusardi | 1 | 0 | 0.34 |
Abu Md Niamul Taufique | 2 | 0 | 1.35 |
Andreas Savakis | 3 | 377 | 41.10 |