Robust Tracking Method for Small and Weak Multiple Targets Under Dynamic Interference Based on Q-IMM-MHT

In complex environments, traditional multi-target tracking methods often encounter challenges such as strong clutter interference and interruptions in target trajectories, which can result in insufficient tracking accuracy and robustness. To address these issues, this paper presents an improved mult...

Full description

Saved in:
Bibliographic Details
Main Authors: Ziqian Yang, Hongbin Nie, Yuxuan Liu, Chunjiang Bian
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/4/1058
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850080922886471680
author Ziqian Yang
Hongbin Nie
Yuxuan Liu
Chunjiang Bian
author_facet Ziqian Yang
Hongbin Nie
Yuxuan Liu
Chunjiang Bian
author_sort Ziqian Yang
collection DOAJ
description In complex environments, traditional multi-target tracking methods often encounter challenges such as strong clutter interference and interruptions in target trajectories, which can result in insufficient tracking accuracy and robustness. To address these issues, this paper presents an improved multi-target tracking algorithm, termed Q-IMM-MHT. This method integrates Multiple Hypothesis Tracking (MHT) with Interactive Multiple Model (IMM) and introduces a Q-learning-based adaptive model switching strategy to dynamically adjust model selection in response to variations in the target’s motion patterns. Furthermore, the algorithm utilizes Support Vector Machines (SVMs) for anomaly detection and trajectory recovery, thereby enhancing the accuracy of data association and the overall robustness of the system. Experimental results indicate that under high noise conditions, the Root Mean Square Error (RMSE) of position estimation decreases to 0.74 pixels, while the RMSE of velocity estimation falls to 0.04 pixels/frame. Compared to traditional methods such as the Unscented Kalman Filter (UKF), IMM, and CIMM, the RMSE is reduced by at least 10.84% and 42.86%, respectively. In scenarios characterized by target trajectory interruptions and clutter interference, the algorithm maintains an association accuracy exceeding 46.3% even after 30 frames of interruption, significantly outperforming other methods. These findings demonstrate that the Q-IMM-MHT algorithm offers substantial performance improvements in multi-target tracking tasks within complex environments, effectively enhancing both tracking accuracy and stability, with considerable application value and extensive potential for future use.
format Article
id doaj-art-fa6163e44b4f4a21bf82b8a417b2c125
institution DOAJ
issn 1424-8220
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-fa6163e44b4f4a21bf82b8a417b2c1252025-08-20T02:44:50ZengMDPI AGSensors1424-82202025-02-01254105810.3390/s25041058Robust Tracking Method for Small and Weak Multiple Targets Under Dynamic Interference Based on Q-IMM-MHTZiqian Yang0Hongbin Nie1Yuxuan Liu2Chunjiang Bian3National Space Science Center, Chinese Academy of Sciences, Beijing 100190, ChinaNational Space Science Center, Chinese Academy of Sciences, Beijing 100190, ChinaNational Space Science Center, Chinese Academy of Sciences, Beijing 100190, ChinaNational Space Science Center, Chinese Academy of Sciences, Beijing 100190, ChinaIn complex environments, traditional multi-target tracking methods often encounter challenges such as strong clutter interference and interruptions in target trajectories, which can result in insufficient tracking accuracy and robustness. To address these issues, this paper presents an improved multi-target tracking algorithm, termed Q-IMM-MHT. This method integrates Multiple Hypothesis Tracking (MHT) with Interactive Multiple Model (IMM) and introduces a Q-learning-based adaptive model switching strategy to dynamically adjust model selection in response to variations in the target’s motion patterns. Furthermore, the algorithm utilizes Support Vector Machines (SVMs) for anomaly detection and trajectory recovery, thereby enhancing the accuracy of data association and the overall robustness of the system. Experimental results indicate that under high noise conditions, the Root Mean Square Error (RMSE) of position estimation decreases to 0.74 pixels, while the RMSE of velocity estimation falls to 0.04 pixels/frame. Compared to traditional methods such as the Unscented Kalman Filter (UKF), IMM, and CIMM, the RMSE is reduced by at least 10.84% and 42.86%, respectively. In scenarios characterized by target trajectory interruptions and clutter interference, the algorithm maintains an association accuracy exceeding 46.3% even after 30 frames of interruption, significantly outperforming other methods. These findings demonstrate that the Q-IMM-MHT algorithm offers substantial performance improvements in multi-target tracking tasks within complex environments, effectively enhancing both tracking accuracy and stability, with considerable application value and extensive potential for future use.https://www.mdpi.com/1424-8220/25/4/1058multi-target trackingpoint targetmultiple hypothesis trackinginteractive multiple modeladaptive model switching
spellingShingle Ziqian Yang
Hongbin Nie
Yuxuan Liu
Chunjiang Bian
Robust Tracking Method for Small and Weak Multiple Targets Under Dynamic Interference Based on Q-IMM-MHT
Sensors
multi-target tracking
point target
multiple hypothesis tracking
interactive multiple model
adaptive model switching
title Robust Tracking Method for Small and Weak Multiple Targets Under Dynamic Interference Based on Q-IMM-MHT
title_full Robust Tracking Method for Small and Weak Multiple Targets Under Dynamic Interference Based on Q-IMM-MHT
title_fullStr Robust Tracking Method for Small and Weak Multiple Targets Under Dynamic Interference Based on Q-IMM-MHT
title_full_unstemmed Robust Tracking Method for Small and Weak Multiple Targets Under Dynamic Interference Based on Q-IMM-MHT
title_short Robust Tracking Method for Small and Weak Multiple Targets Under Dynamic Interference Based on Q-IMM-MHT
title_sort robust tracking method for small and weak multiple targets under dynamic interference based on q imm mht
topic multi-target tracking
point target
multiple hypothesis tracking
interactive multiple model
adaptive model switching
url https://www.mdpi.com/1424-8220/25/4/1058
work_keys_str_mv AT ziqianyang robusttrackingmethodforsmallandweakmultipletargetsunderdynamicinterferencebasedonqimmmht
AT hongbinnie robusttrackingmethodforsmallandweakmultipletargetsunderdynamicinterferencebasedonqimmmht
AT yuxuanliu robusttrackingmethodforsmallandweakmultipletargetsunderdynamicinterferencebasedonqimmmht
AT chunjiangbian robusttrackingmethodforsmallandweakmultipletargetsunderdynamicinterferencebasedonqimmmht