Online Multi-Object Tracking Based on Record Confidence and Hierarchical Association for Cyber-Physical Social Intelligence

As a vital technology in Cyber-Physical Social Intelligence (CPSI), Multi-Object-Tracking (MOT) can support comprehensive perception and analysis of the physical environment and social virtual space, promoting an in-depth understanding of human behavior, object movement, and social interaction. Most...

Full description

Saved in:
Bibliographic Details
Main Authors: Jieming Yang, Dezhen Feng, Yuan Gao, Cong Liu
Format: Article
Language:English
Published: Tsinghua University Press 2025-06-01
Series:Big Data Mining and Analytics
Subjects:
Online Access:https://www.sciopen.com/article/10.26599/BDMA.2025.9020024
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850067579038597120
author Jieming Yang
Dezhen Feng
Yuan Gao
Cong Liu
author_facet Jieming Yang
Dezhen Feng
Yuan Gao
Cong Liu
author_sort Jieming Yang
collection DOAJ
description As a vital technology in Cyber-Physical Social Intelligence (CPSI), Multi-Object-Tracking (MOT) can support comprehensive perception and analysis of the physical environment and social virtual space, promoting an in-depth understanding of human behavior, object movement, and social interaction. Most MOT methods often adopt simple interpolation or prediction strategies when dealing with temporarily lost targets, but ignore the comprehensive consideration of the state of the target before its reappearance. This approach may lead to an incomplete understanding of the target’s behavior and dynamics, which affects the accuracy and depth of the comprehensive understanding of social and physical space interactions in the real world. To improve it, we propose an online multi-object tracking method based on Record Confidence and Hierarchical Association (RCHA), which is represented as RCHA-Track. The Kalman filter combined with an Enhanced Correlation Coefficient (ECC) provides more accurate motion prediction under the influence of camera motion. The record confidence is designed to evaluate the loss status of the unseen object and refine the tracking trajectory. The normally tracked targets and the temporarily lost targets are combined to perform a hierarchical association based on the number of lost frames to achieve more accurate data associations. Compared with the latest ByteTrack, RCHA-Track improves MOTA, IDF1, and HOTA by 1.7%, 1.6%, and 1.3% on the benchmark dataset MOT17, and 1.3%, 2.1%, and 2.0% on MOT20, respectively, achieving state-of-the-art performance. Extensive ablation experiments demonstrate the effectiveness of each key module in the proposed RCHA-Track.
format Article
id doaj-art-a71b22cc101e4da28256d644d02d65f2
institution DOAJ
issn 2096-0654
2097-406X
language English
publishDate 2025-06-01
publisher Tsinghua University Press
record_format Article
series Big Data Mining and Analytics
spelling doaj-art-a71b22cc101e4da28256d644d02d65f22025-08-20T02:48:16ZengTsinghua University PressBig Data Mining and Analytics2096-06542097-406X2025-06-018485186610.26599/BDMA.2025.9020024Online Multi-Object Tracking Based on Record Confidence and Hierarchical Association for Cyber-Physical Social IntelligenceJieming Yang0Dezhen Feng1Yuan Gao2Cong Liu3School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Computer Science and technology, Hainan University, Haikou 570228, ChinaSchool of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan 430074, ChinaAs a vital technology in Cyber-Physical Social Intelligence (CPSI), Multi-Object-Tracking (MOT) can support comprehensive perception and analysis of the physical environment and social virtual space, promoting an in-depth understanding of human behavior, object movement, and social interaction. Most MOT methods often adopt simple interpolation or prediction strategies when dealing with temporarily lost targets, but ignore the comprehensive consideration of the state of the target before its reappearance. This approach may lead to an incomplete understanding of the target’s behavior and dynamics, which affects the accuracy and depth of the comprehensive understanding of social and physical space interactions in the real world. To improve it, we propose an online multi-object tracking method based on Record Confidence and Hierarchical Association (RCHA), which is represented as RCHA-Track. The Kalman filter combined with an Enhanced Correlation Coefficient (ECC) provides more accurate motion prediction under the influence of camera motion. The record confidence is designed to evaluate the loss status of the unseen object and refine the tracking trajectory. The normally tracked targets and the temporarily lost targets are combined to perform a hierarchical association based on the number of lost frames to achieve more accurate data associations. Compared with the latest ByteTrack, RCHA-Track improves MOTA, IDF1, and HOTA by 1.7%, 1.6%, and 1.3% on the benchmark dataset MOT17, and 1.3%, 2.1%, and 2.0% on MOT20, respectively, achieving state-of-the-art performance. Extensive ablation experiments demonstrate the effectiveness of each key module in the proposed RCHA-Track.https://www.sciopen.com/article/10.26599/BDMA.2025.9020024multi-object trackingdeep learningobject detectionneural network
spellingShingle Jieming Yang
Dezhen Feng
Yuan Gao
Cong Liu
Online Multi-Object Tracking Based on Record Confidence and Hierarchical Association for Cyber-Physical Social Intelligence
Big Data Mining and Analytics
multi-object tracking
deep learning
object detection
neural network
title Online Multi-Object Tracking Based on Record Confidence and Hierarchical Association for Cyber-Physical Social Intelligence
title_full Online Multi-Object Tracking Based on Record Confidence and Hierarchical Association for Cyber-Physical Social Intelligence
title_fullStr Online Multi-Object Tracking Based on Record Confidence and Hierarchical Association for Cyber-Physical Social Intelligence
title_full_unstemmed Online Multi-Object Tracking Based on Record Confidence and Hierarchical Association for Cyber-Physical Social Intelligence
title_short Online Multi-Object Tracking Based on Record Confidence and Hierarchical Association for Cyber-Physical Social Intelligence
title_sort online multi object tracking based on record confidence and hierarchical association for cyber physical social intelligence
topic multi-object tracking
deep learning
object detection
neural network
url https://www.sciopen.com/article/10.26599/BDMA.2025.9020024
work_keys_str_mv AT jiemingyang onlinemultiobjecttrackingbasedonrecordconfidenceandhierarchicalassociationforcyberphysicalsocialintelligence
AT dezhenfeng onlinemultiobjecttrackingbasedonrecordconfidenceandhierarchicalassociationforcyberphysicalsocialintelligence
AT yuangao onlinemultiobjecttrackingbasedonrecordconfidenceandhierarchicalassociationforcyberphysicalsocialintelligence
AT congliu onlinemultiobjecttrackingbasedonrecordconfidenceandhierarchicalassociationforcyberphysicalsocialintelligence