Multi-Objective Dynamic Tracking Based on Deep Learning

DOI

10.2991/978-94-6463-864-6_57How to use a DOI?

Keywords

Multiple Object Tracking; Target Detection; Data Association; Multi-Modal Fusion

Abstract

This article surveys the present research situation and development tendencies of multi-object tracking (MOT) technology relying on deep learning. Firstly, it introduces the basic concepts and key technologies of MOT, including core components such as target detection, data association, and trajectory prediction, and focuses on analyzing challenges like object blockage and look alterations in complicated circumstances. Secondly, it conducts a detailed comparison of the performance characteristics of sensors such as optical cameras, lidars, and millimeter-wave radars and their application effects in multi-modal fusion. On the methodological front, it comprehensively sums up the research advancements of target detection algorithms relying on deep learning (for example, the YOLO series and Faster R-CNN) and tracking algorithms (such as GNN and Transformer). Currently, the hot research areas are spatio - temporal relationship modeling and anti - blockage algorithms. Ultimately, it sums up the application accomplishments of Multiple Object Tracking (MOT) in domains like security surveillance and smart transportation. It also deliberates on existing problems like data quality and real-time capability and anticipates future development paths such as multi-sensor integration and lightweight architectures.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Jingze Yu
PY  - 2025
DA  - 2025/10/23
TI  - Multi-Objective Dynamic Tracking Based on Deep Learning
BT  - Proceedings of the 2025 2nd International Conference on Electrical Engineering and Intelligent Control (EEIC 2025)
PB  - Atlantis Press
SP  - 668
EP  - 687
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-864-6_57
DO  - 10.2991/978-94-6463-864-6_57
ID  - Yu2025
ER  -