Contrastive Transformer Network for Track Segment Association with Two-Stage Online Method

Interrupted and multi-source track segment association (TSA) are two key challenges in target trajectory research within radar data processing. Traditional methods often rely on simplistic assumptions about target motion and statistical techniques for track association, leading to problems such as u...

Full description

Saved in:
Bibliographic Details
Main Authors: Zongqing Cao, Bing Liu, Jianchao Yang, Ke Tan, Zheng Dai, Xingyu Lu, Hong Gu
Format: Article
Language:English
Published: MDPI AG 2024-09-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/16/18/3380
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850259631588245504
author Zongqing Cao
Bing Liu
Jianchao Yang
Ke Tan
Zheng Dai
Xingyu Lu
Hong Gu
author_facet Zongqing Cao
Bing Liu
Jianchao Yang
Ke Tan
Zheng Dai
Xingyu Lu
Hong Gu
author_sort Zongqing Cao
collection DOAJ
description Interrupted and multi-source track segment association (TSA) are two key challenges in target trajectory research within radar data processing. Traditional methods often rely on simplistic assumptions about target motion and statistical techniques for track association, leading to problems such as unrealistic assumptions, susceptibility to noise, and suboptimal performance limits. This study proposes a unified framework to address the challenges of associating interrupted and multi-source track segments by measuring trajectory similarity. We present TSA-cTFER, a novel network utilizing contrastive learning and TransFormer Encoder to accurately assess trajectory similarity through learned Representations by computing distances between high-dimensional feature vectors. Additionally, we tackle dynamic association scenarios with a two-stage online algorithm designed to manage tracks that appear or disappear at any time. This algorithm categorizes track pairs into easy and hard groups, employing tailored association strategies to achieve precise and robust associations in dynamic environments. Experimental results on real-world datasets demonstrate that our proposed TSA-cTFER network with the two-stage online algorithm outperforms existing methods, achieving 94.59% accuracy in interrupted track segment association tasks and 94.83% in multi-source track segment association tasks.
format Article
id doaj-art-d4b46ae3438a441ca30c9e4f2b4d76e9
institution OA Journals
issn 2072-4292
language English
publishDate 2024-09-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-d4b46ae3438a441ca30c9e4f2b4d76e92025-08-20T01:55:49ZengMDPI AGRemote Sensing2072-42922024-09-011618338010.3390/rs16183380Contrastive Transformer Network for Track Segment Association with Two-Stage Online MethodZongqing Cao0Bing Liu1Jianchao Yang2Ke Tan3Zheng Dai4Xingyu Lu5Hong Gu6School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaXi’an Electronic Engineering Research Institute, Xi’an 710199, ChinaSchool of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaInterrupted and multi-source track segment association (TSA) are two key challenges in target trajectory research within radar data processing. Traditional methods often rely on simplistic assumptions about target motion and statistical techniques for track association, leading to problems such as unrealistic assumptions, susceptibility to noise, and suboptimal performance limits. This study proposes a unified framework to address the challenges of associating interrupted and multi-source track segments by measuring trajectory similarity. We present TSA-cTFER, a novel network utilizing contrastive learning and TransFormer Encoder to accurately assess trajectory similarity through learned Representations by computing distances between high-dimensional feature vectors. Additionally, we tackle dynamic association scenarios with a two-stage online algorithm designed to manage tracks that appear or disappear at any time. This algorithm categorizes track pairs into easy and hard groups, employing tailored association strategies to achieve precise and robust associations in dynamic environments. Experimental results on real-world datasets demonstrate that our proposed TSA-cTFER network with the two-stage online algorithm outperforms existing methods, achieving 94.59% accuracy in interrupted track segment association tasks and 94.83% in multi-source track segment association tasks.https://www.mdpi.com/2072-4292/16/18/3380radar data processingtrack segment associationcontrastive learningtransformer encoderonline association
spellingShingle Zongqing Cao
Bing Liu
Jianchao Yang
Ke Tan
Zheng Dai
Xingyu Lu
Hong Gu
Contrastive Transformer Network for Track Segment Association with Two-Stage Online Method
Remote Sensing
radar data processing
track segment association
contrastive learning
transformer encoder
online association
title Contrastive Transformer Network for Track Segment Association with Two-Stage Online Method
title_full Contrastive Transformer Network for Track Segment Association with Two-Stage Online Method
title_fullStr Contrastive Transformer Network for Track Segment Association with Two-Stage Online Method
title_full_unstemmed Contrastive Transformer Network for Track Segment Association with Two-Stage Online Method
title_short Contrastive Transformer Network for Track Segment Association with Two-Stage Online Method
title_sort contrastive transformer network for track segment association with two stage online method
topic radar data processing
track segment association
contrastive learning
transformer encoder
online association
url https://www.mdpi.com/2072-4292/16/18/3380
work_keys_str_mv AT zongqingcao contrastivetransformernetworkfortracksegmentassociationwithtwostageonlinemethod
AT bingliu contrastivetransformernetworkfortracksegmentassociationwithtwostageonlinemethod
AT jianchaoyang contrastivetransformernetworkfortracksegmentassociationwithtwostageonlinemethod
AT ketan contrastivetransformernetworkfortracksegmentassociationwithtwostageonlinemethod
AT zhengdai contrastivetransformernetworkfortracksegmentassociationwithtwostageonlinemethod
AT xingyulu contrastivetransformernetworkfortracksegmentassociationwithtwostageonlinemethod
AT honggu contrastivetransformernetworkfortracksegmentassociationwithtwostageonlinemethod