FastTrackTr:Towards Fast Multi-Object Tracking with Transformers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liao, Pan, Yang, Feng, Wu, Di, Yu, Jinwen, Zhao, Wenhui, Zhang, Dingwen
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915417274974208
author Liao, Pan
Yang, Feng
Wu, Di
Yu, Jinwen
Zhao, Wenhui
Zhang, Dingwen
author_facet Liao, Pan
Yang, Feng
Wu, Di
Yu, Jinwen
Zhao, Wenhui
Zhang, Dingwen
contents Transformer-based multi-object tracking (MOT) methods have captured the attention of many researchers in recent years. However, these models often suffer from slow inference speeds due to their structure or other issues. To address this problem, we revisited the Joint Detection and Tracking (JDT) method by looking back at past approaches. By integrating the original JDT approach with some advanced theories, this paper employs an efficient method of information transfer between frames on the DETR, constructing a fast and novel JDT-type MOT framework: FastTrackTr. Thanks to the superiority of this information transfer method, our approach not only reduces the number of queries required during tracking but also avoids the excessive introduction of network structures, ensuring model simplicity. Experimental results indicate that our method has the potential to achieve real-time tracking and exhibits competitive tracking accuracy across multiple datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2411_15811
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FastTrackTr:Towards Fast Multi-Object Tracking with Transformers
Liao, Pan
Yang, Feng
Wu, Di
Yu, Jinwen
Zhao, Wenhui
Zhang, Dingwen
Computer Vision and Pattern Recognition
Artificial Intelligence
Transformer-based multi-object tracking (MOT) methods have captured the attention of many researchers in recent years. However, these models often suffer from slow inference speeds due to their structure or other issues. To address this problem, we revisited the Joint Detection and Tracking (JDT) method by looking back at past approaches. By integrating the original JDT approach with some advanced theories, this paper employs an efficient method of information transfer between frames on the DETR, constructing a fast and novel JDT-type MOT framework: FastTrackTr. Thanks to the superiority of this information transfer method, our approach not only reduces the number of queries required during tracking but also avoids the excessive introduction of network structures, ensuring model simplicity. Experimental results indicate that our method has the potential to achieve real-time tracking and exhibits competitive tracking accuracy across multiple datasets.
title FastTrackTr:Towards Fast Multi-Object Tracking with Transformers
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2411.15811