A two stage multi object tracking algorithm with transformer and attention mechanism

In the field of engineering safety, multi-object tracking encounters difficulties in effectively conducting object detection due to occlusion, as well as the issue of experiencing frequent switching of target identity ID switches (IDs). In response to the issues above, this paper proposes a multi-ob...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Scientific reports Ročník 15; číslo 1; s. 31414 - 14
Hlavní autori: Hou, Mingxing, Wu, Yiming, Shi, Hong, Mu, Xiaofang
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: London Nature Publishing Group UK 26.08.2025
Nature Publishing Group
Nature Portfolio
Predmet:
639/166
639/705
639/705/117
Accuracy
Algorithms
Attention mechanism
Boxes
Deep learning
Design
Humanities and Social Sciences
Localization
Multi-object tracking
multidisciplinary
Neural networks
Occlusion
Re-identification
Safety engineering
Science
Science (multidisciplinary)
Two-stage association
You Only Look Once Version 8
Two-stage association
Attention mechanism
Multi-object tracking
Re-identification
You Only Look Once Version 8
ISSN:2045-2322, 2045-2322
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:In the field of engineering safety, multi-object tracking encounters difficulties in effectively conducting object detection due to occlusion, as well as the issue of experiencing frequent switching of target identity ID switches (IDs). In response to the issues above, this paper proposes a multi-object tracking model that integrates improved You Only Look Once Version 8 (YOLOv8) and High-Performance Multi-Object Tracking by Tracking Bytes (ByteTrack). The model architecture is based on the paradigm of tracking-by-detection. In the detection stage, we combine the coordinate attention mechanism to propose the Coordinate Attention Spatial Pyramid Pooling - Fast Conv (CASPPFC) module, and combine it with improved Efficient Vision Transformer (EfficientViT) to enhance the YOLOv8 backbone network, effectively reducing false positives and false negatives caused by occlusion. In the first stage of tracking association, we propose the Omni-Scale Network-Coordinate Attention (OSNet-CA) network as the Re-identification (Re-ID) feature extraction method to capture target information more effectively. In the second stage of association, we adopt the Efficient Intersection over Union (EIoU) improvement method to comprehensively consider the positional relationships between targets. The effectiveness of the improved model is validated on the Multi-Object Tracking 2017 (MOT17) and Multi-Object Tracking 2020 (MOT20) datasets. The results indicate that our tracking model achieved 80.5% Multiple Object Tracking Accuracy (MOTA), 79.3% Identification F1 Score (IDF1), and 64.2% Higher Order Tracking Accuracy (HOTA) on the MOT17 test set, and 77.8% MOTA, 76.9% IDF1, and 62.4% HOTA on the MOT20 test set. This tracking model can achieve high-precision pedestrian tracking, effectively reducing ID switches and enhancing tracking robustness, timely detection of hazardous events in the engineering safety field to ensure personnel safety.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-025-16389-4