METFormer: A Motion Enhanced Transformer for Multiple Object Tracking

Jianjun Gao, Kim Hui Yap, Yi Wang, Kratika Garg, Boon Siew Han

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

Abstract

Multiple object tracking (MOT) is an important task in computer vision, especially video analytics. Transformer-based methods are emerging approaches using both tracking and detection queries. However, motion modeling in existing transformer-based methods lacks effective association capability. Thus, this paper introduces a new METFormer model, a Motion Enhanced TransFormer-based tracker with a novel global-local motion context learning technique to mitigate the lack of motion information in existing transformer-based methods. The global-local motion context learning technique first centers on difference-guided global motion learning to obtain temporal information from adjacent frames. Based on global motion, we leverage context-aware local object motion modelling to study motion patterns and enhance the feature representation for individual objects. Experimental results on the benchmark MOT17 dataset show that our proposed method can surpass the state-of-the-art Trackformer [21] by 1.8% on IDF1 and 21.7% on ID Switches under public detection settings.

Original languageEnglish
Title of host publicationISCAS 2023 - 56th IEEE International Symposium on Circuits and Systems, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-5
ISBN (Electronic)9781665451093
DOIs
Publication statusPublished - Jul 2023
Externally publishedYes
Event56th IEEE International Symposium on Circuits and Systems, ISCAS 2023 - Monterey, United States
Duration: 21 May 202325 May 2023

Publication series

NameProceedings - IEEE International Symposium on Circuits and Systems
Volume2023-May
ISSN (Print)0271-4310

Conference

Conference56th IEEE International Symposium on Circuits and Systems, ISCAS 2023
Country/TerritoryUnited States
CityMonterey
Period21/05/2325/05/23

Keywords

  • Motion Modeling
  • Multiple Object Tracking
  • Tracking by Attention
  • Transformer

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'METFormer: A Motion Enhanced Transformer for Multiple Object Tracking'. Together they form a unique fingerprint.

Cite this