Loughborough University
Browse
1-s2.0-S1077314222001473-main (1).pdf (1.91 MB)

A multi-object tracker using dynamic Bayesian networks and a residual neural network based similarity estimator

Download (1.91 MB)
journal contribution
posted on 2022-10-21, 11:00 authored by Mohamad SaadaMohamad Saada, Christos Kouppas, Baihua LiBaihua Li, Qinggang MengQinggang Meng

In this paper we introduce a novel multi-object tracker based on the tracking-by-detection paradigm. This tracker utilises a Dynamic Bayesian Network for predicting objects’ positions through filtering and updating in real-time. The algorithm is trained and then tested using the MOTChallenge challenge benchmark of video sequences. After initial testing, a state-of-the-art residual neural network for extracting feature descriptors is used. This ResNet feature extractor is integrated into the tracking algorithm for object similarity estimation to further enhance tracker performance. Finally, we demonstrate the effects of object detection on tracker performance using a custom trained state of the art You Only Look Once (YOLO) V5 object detector. Results are analysed and evaluated using the MOTChallenge Evaluation Kit, followed by a comparison to state-of-the-art methods.

History

School

  • Science

Department

  • Computer Science

Published in

Computer Vision and Image Understanding

Volume

225

Publisher

Elsevier

Version

  • VoR (Version of Record)

Rights holder

© The Authors

Publisher statement

This is an Open Access Article. It is published by Elsevier under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International Licence (CC BY-NC-ND). Full details of this licence are available at: https://creativecommons.org/licenses/by-nc-nd/4.0/

Acceptance date

2022-09-26

Publication date

2022-09-30

Copyright date

2022

ISSN

1077-3142

eISSN

1090-235X

Language

  • en

Depositor

Dr Mohamad Saada. Deposit date: 27 September 2022

Article number

103569

Usage metrics

    Loughborough Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC