UAV Visual Object Tracking Based on Spatio-Temporal Context

To balance the real-time and robustness of UAV visual tracking on a single CPU, this paper proposes an object tracker based on spatio-temporal context (STCT). STCT integrates the correlation filter and Siamese network into a unified framework and introduces the target’s motion model, enabling the tr...

Full description

Saved in:
Bibliographic Details
Main Authors: Yongxiang He, Chuang Chao, Zhao Zhang, Hongwu Guo, Jianjun Ma
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Drones
Subjects:
Online Access:https://www.mdpi.com/2504-446X/8/12/700
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846104995220422656
author Yongxiang He
Chuang Chao
Zhao Zhang
Hongwu Guo
Jianjun Ma
author_facet Yongxiang He
Chuang Chao
Zhao Zhang
Hongwu Guo
Jianjun Ma
author_sort Yongxiang He
collection DOAJ
description To balance the real-time and robustness of UAV visual tracking on a single CPU, this paper proposes an object tracker based on spatio-temporal context (STCT). STCT integrates the correlation filter and Siamese network into a unified framework and introduces the target’s motion model, enabling the tracker to adapt to target scale variations and effectively address challenges posed by rapid target motion, etc. Furthermore, a spatio-temporal regularization term based on the dynamic attention mechanism is proposed, and it is introduced into the correlation filter to suppress the aberrance of the response map. The filter solution is provided through the alternating direction method of multipliers (ADMM). In addition, to ensure efficiency, this paper proposes the average maximum response value-related energy (AMRE) for adaptive tracking state evaluation, which considers the time context of the tracking process in STCT. Experimental results show that the proposed STCT tracker can achieve a favorable balance between tracking robustness and real-time performance for UAV object tracking while running at ∼38 frames/s on a low-cost CPU.
format Article
id doaj-art-679536ac117e407f8aa38b5c40a890d5
institution Kabale University
issn 2504-446X
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Drones
spelling doaj-art-679536ac117e407f8aa38b5c40a890d52024-12-27T14:21:42ZengMDPI AGDrones2504-446X2024-11-0181270010.3390/drones8120700UAV Visual Object Tracking Based on Spatio-Temporal ContextYongxiang He0Chuang Chao1Zhao Zhang2Hongwu Guo3Jianjun Ma4College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410000, ChinaCollege of Intelligence Science and Technology, National University of Defense Technology, Changsha 410000, ChinaCollege of Intelligence Science and Technology, National University of Defense Technology, Changsha 410000, ChinaCollege of Intelligence Science and Technology, National University of Defense Technology, Changsha 410000, ChinaCollege of Intelligence Science and Technology, National University of Defense Technology, Changsha 410000, ChinaTo balance the real-time and robustness of UAV visual tracking on a single CPU, this paper proposes an object tracker based on spatio-temporal context (STCT). STCT integrates the correlation filter and Siamese network into a unified framework and introduces the target’s motion model, enabling the tracker to adapt to target scale variations and effectively address challenges posed by rapid target motion, etc. Furthermore, a spatio-temporal regularization term based on the dynamic attention mechanism is proposed, and it is introduced into the correlation filter to suppress the aberrance of the response map. The filter solution is provided through the alternating direction method of multipliers (ADMM). In addition, to ensure efficiency, this paper proposes the average maximum response value-related energy (AMRE) for adaptive tracking state evaluation, which considers the time context of the tracking process in STCT. Experimental results show that the proposed STCT tracker can achieve a favorable balance between tracking robustness and real-time performance for UAV object tracking while running at ∼38 frames/s on a low-cost CPU.https://www.mdpi.com/2504-446X/8/12/700UAV object trackingthe correlation filterSiamese networksspatio-temporal context
spellingShingle Yongxiang He
Chuang Chao
Zhao Zhang
Hongwu Guo
Jianjun Ma
UAV Visual Object Tracking Based on Spatio-Temporal Context
Drones
UAV object tracking
the correlation filter
Siamese networks
spatio-temporal context
title UAV Visual Object Tracking Based on Spatio-Temporal Context
title_full UAV Visual Object Tracking Based on Spatio-Temporal Context
title_fullStr UAV Visual Object Tracking Based on Spatio-Temporal Context
title_full_unstemmed UAV Visual Object Tracking Based on Spatio-Temporal Context
title_short UAV Visual Object Tracking Based on Spatio-Temporal Context
title_sort uav visual object tracking based on spatio temporal context
topic UAV object tracking
the correlation filter
Siamese networks
spatio-temporal context
url https://www.mdpi.com/2504-446X/8/12/700
work_keys_str_mv AT yongxianghe uavvisualobjecttrackingbasedonspatiotemporalcontext
AT chuangchao uavvisualobjecttrackingbasedonspatiotemporalcontext
AT zhaozhang uavvisualobjecttrackingbasedonspatiotemporalcontext
AT hongwuguo uavvisualobjecttrackingbasedonspatiotemporalcontext
AT jianjunma uavvisualobjecttrackingbasedonspatiotemporalcontext