EHTracker: Toward Fine-Grained Localization for Satellite Video Target Tracking

Deep learning (DL)-based methods have shown great potential in the satellite video target tracking community. Nevertheless, most of the methods are still plagued by poor localization capabilities and background interference problems. In this article, we propose EHTracker, a Siamese-based tracker bas...

Full description

Saved in:
Bibliographic Details
Main Authors: Jianwei Yang, Yuhan Liu, Yanxing Liu, Ziming Wang, Jiawei Li, Guangyao Zhou, Wenzhi Wang, Yuxin Hu
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10811782/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850189978800226304
author Jianwei Yang
Yuhan Liu
Yanxing Liu
Ziming Wang
Jiawei Li
Guangyao Zhou
Wenzhi Wang
Yuxin Hu
author_facet Jianwei Yang
Yuhan Liu
Yanxing Liu
Ziming Wang
Jiawei Li
Guangyao Zhou
Wenzhi Wang
Yuxin Hu
author_sort Jianwei Yang
collection DOAJ
description Deep learning (DL)-based methods have shown great potential in the satellite video target tracking community. Nevertheless, most of the methods are still plagued by poor localization capabilities and background interference problems. In this article, we propose EHTracker, a Siamese-based tracker based on enhanced head network, specifically for tiny targets in satellite videos. EHTracker enhances the localization capability for tiny objects through the proposed enhanced head network, while the proposed background suppression module (BSM) improves the network's ability to suppress background interference. Specifically, to alleviate the problem of overlapping between the foreground and background in the classification branch, we propose a multihead graph attention refinement module (MGARM). Second, to enable the regression branch to determine the location of feature-poor small targets more accurately, we introduce a gradual regression strategy (GRS). MGARM and GRS together constitute the enhanced head network component of EHTracker. Further, in order to work with the enhanced head network to achieve classification and localization of small targets that lack distinctive features, we design a BSM. Extensive experiments are implemented on the SatSOT dataset and SV248S dataset, and the experimental results show that our method achieves state-of-the-art tracking performance.
format Article
id doaj-art-598bf1c3469f4bff92c5ef8ba8504e09
institution OA Journals
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-598bf1c3469f4bff92c5ef8ba8504e092025-08-20T02:15:28ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01185582559910.1109/JSTARS.2024.352099710811782EHTracker: Toward Fine-Grained Localization for Satellite Video Target TrackingJianwei Yang0https://orcid.org/0000-0001-5228-8462Yuhan Liu1https://orcid.org/0000-0003-4328-6427Yanxing Liu2https://orcid.org/0009-0007-8604-933XZiming Wang3https://orcid.org/0000-0001-7907-4472Jiawei Li4https://orcid.org/0009-0009-1220-7598Guangyao Zhou5https://orcid.org/0000-0002-1560-2114Wenzhi Wang6Yuxin Hu7https://orcid.org/0009-0009-5334-9592Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaDeep learning (DL)-based methods have shown great potential in the satellite video target tracking community. Nevertheless, most of the methods are still plagued by poor localization capabilities and background interference problems. In this article, we propose EHTracker, a Siamese-based tracker based on enhanced head network, specifically for tiny targets in satellite videos. EHTracker enhances the localization capability for tiny objects through the proposed enhanced head network, while the proposed background suppression module (BSM) improves the network's ability to suppress background interference. Specifically, to alleviate the problem of overlapping between the foreground and background in the classification branch, we propose a multihead graph attention refinement module (MGARM). Second, to enable the regression branch to determine the location of feature-poor small targets more accurately, we introduce a gradual regression strategy (GRS). MGARM and GRS together constitute the enhanced head network component of EHTracker. Further, in order to work with the enhanced head network to achieve classification and localization of small targets that lack distinctive features, we design a BSM. Extensive experiments are implemented on the SatSOT dataset and SV248S dataset, and the experimental results show that our method achieves state-of-the-art tracking performance.https://ieeexplore.ieee.org/document/10811782/Graph attentionsatellite video trackingsiamese networktiny object
spellingShingle Jianwei Yang
Yuhan Liu
Yanxing Liu
Ziming Wang
Jiawei Li
Guangyao Zhou
Wenzhi Wang
Yuxin Hu
EHTracker: Toward Fine-Grained Localization for Satellite Video Target Tracking
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Graph attention
satellite video tracking
siamese network
tiny object
title EHTracker: Toward Fine-Grained Localization for Satellite Video Target Tracking
title_full EHTracker: Toward Fine-Grained Localization for Satellite Video Target Tracking
title_fullStr EHTracker: Toward Fine-Grained Localization for Satellite Video Target Tracking
title_full_unstemmed EHTracker: Toward Fine-Grained Localization for Satellite Video Target Tracking
title_short EHTracker: Toward Fine-Grained Localization for Satellite Video Target Tracking
title_sort ehtracker toward fine grained localization for satellite video target tracking
topic Graph attention
satellite video tracking
siamese network
tiny object
url https://ieeexplore.ieee.org/document/10811782/
work_keys_str_mv AT jianweiyang ehtrackertowardfinegrainedlocalizationforsatellitevideotargettracking
AT yuhanliu ehtrackertowardfinegrainedlocalizationforsatellitevideotargettracking
AT yanxingliu ehtrackertowardfinegrainedlocalizationforsatellitevideotargettracking
AT zimingwang ehtrackertowardfinegrainedlocalizationforsatellitevideotargettracking
AT jiaweili ehtrackertowardfinegrainedlocalizationforsatellitevideotargettracking
AT guangyaozhou ehtrackertowardfinegrainedlocalizationforsatellitevideotargettracking
AT wenzhiwang ehtrackertowardfinegrainedlocalizationforsatellitevideotargettracking
AT yuxinhu ehtrackertowardfinegrainedlocalizationforsatellitevideotargettracking