Online tracking of ants based on deep association metrics method, dataset and evaluation.pdf (5.18 MB)
Download file

Online tracking of ants based on deep association metrics: method, dataset and evaluation

Download (5.18 MB)
journal contribution
posted on 28.02.2022, 17:15 by Xiaoyan Cao, Shihui Guo, Juncong Lin, Wenshu Zhang, Minghong Liao
Tracking movement of insects in a social group (such as ants) is challenging, because the individuals are not only similar in appearance but also likely to perform intensive body contact and sudden movement adjustment (start/stop, direction changes). To address this challenge, we introduce an online multi-object tracking framework that combines both the motion and appearance information of ants. We obtain the appearance descriptors by using the ResNet model for offline training on a small (N=50) sample dataset. For online association, a cosine similarity metric computes the matching degree between historical appearance sequences of the trajectory and the current detection. We validate our method in both indoor (lab setup) and outdoor video sequences. The results show that our model obtains 99.3% ± 0.5% MOTA and 91.9% ± 2.1% MOTP across 24,050 testing samples in five indoor sequences, with real-time tracking performance. In an outdoor sequence, we achieve 99.3% MOTA and 92.9% MOTP across 22,041 testing samples. The datasets and code are made publicly available for future research in relevant domains.

History

Published in

Pattern Recognition

Publisher

Elsevier

Version

AM (Accepted Manuscript)

Citation

Cao, X., Guo, S., Lin, J., Zhang, W. and Liao, M. (2020) 'Online tracking of ants based on deep association metrics: method, dataset and evaluation', Pattern Recognition, p.107233. https://doi.org/10.1016/j.patcog.2020.107233

Print ISSN

0031-3203

Cardiff Met Affiliation

  • Cardiff School of Technologies

Cardiff Met Authors

Wenshu Zhang

Copyright Holder

© The Publisher

Language

en