A Novel Anti-Drift Visual Object Tracking Algorithm Based on Sparse Response and Adaptive Spatial-Temporal Context-Aware

Correlation filter (CF) based trackers have gained significant attention in the field of visual single-object tracking, owing to their favorable performance and high efficiency; however, existing trackers still suffer from model drift caused by boundary effects and filter degradation. In visual trac...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yinqiang Su, Jinghong Liu, Fang Xu, Xueming Zhang, Yujia Zuo
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	visual tracking sparse learning adaptive spatial-temporal context correlation filters high-confidence updating Science Q
Acceso en línea:	https://doaj.org/article/4b2d700425ef4600a1307b14775ae402
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:4b2d700425ef4600a1307b14775ae402
record_format	dspace
spelling	oai:doaj.org-article:4b2d700425ef4600a1307b14775ae4022021-11-25T18:55:17ZA Novel Anti-Drift Visual Object Tracking Algorithm Based on Sparse Response and Adaptive Spatial-Temporal Context-Aware10.3390/rs132246722072-4292https://doaj.org/article/4b2d700425ef4600a1307b14775ae4022021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/22/4672https://doaj.org/toc/2072-4292Correlation filter (CF) based trackers have gained significant attention in the field of visual single-object tracking, owing to their favorable performance and high efficiency; however, existing trackers still suffer from model drift caused by boundary effects and filter degradation. In visual tracking, long-term occlusion and large appearance variations easily cause model degradation. To remedy these drawbacks, we propose a sparse adaptive spatial-temporal context-aware method that effectively avoids model drift. Specifically, a global context is explicitly incorporated into the correlation filter to mitigate boundary effects. Subsequently, an adaptive temporal regularization constraint is adopted in the filter training stage to avoid model degradation. Meanwhile, a sparse response constraint is introduced to reduce the risk of further model drift. Furthermore, we apply the alternating direction multiplier method (ADMM) to derive a closed-solution of the object function with a low computational cost. In addition, an updating scheme based on the APCE-pool and Peak-pool is proposed to reveal the tracking condition and ensure updates of the target’s appearance model with high-confidence. The Kalam filter is adopted to track the target when the appearance model is persistently unreliable and abnormality occurs. Finally, extensive experimental results on OTB-2013, OTB-2015 and VOT2018 datasets show that our proposed tracker performs favorably against several state-of-the-art trackers.Yinqiang SuJinghong LiuFang XuXueming ZhangYujia ZuoMDPI AGarticlevisual trackingsparse learningadaptive spatial-temporal contextcorrelation filtershigh-confidence updatingScienceQENRemote Sensing, Vol 13, Iss 4672, p 4672 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	visual tracking sparse learning adaptive spatial-temporal context correlation filters high-confidence updating Science Q
spellingShingle	visual tracking sparse learning adaptive spatial-temporal context correlation filters high-confidence updating Science Q Yinqiang Su Jinghong Liu Fang Xu Xueming Zhang Yujia Zuo A Novel Anti-Drift Visual Object Tracking Algorithm Based on Sparse Response and Adaptive Spatial-Temporal Context-Aware
description	Correlation filter (CF) based trackers have gained significant attention in the field of visual single-object tracking, owing to their favorable performance and high efficiency; however, existing trackers still suffer from model drift caused by boundary effects and filter degradation. In visual tracking, long-term occlusion and large appearance variations easily cause model degradation. To remedy these drawbacks, we propose a sparse adaptive spatial-temporal context-aware method that effectively avoids model drift. Specifically, a global context is explicitly incorporated into the correlation filter to mitigate boundary effects. Subsequently, an adaptive temporal regularization constraint is adopted in the filter training stage to avoid model degradation. Meanwhile, a sparse response constraint is introduced to reduce the risk of further model drift. Furthermore, we apply the alternating direction multiplier method (ADMM) to derive a closed-solution of the object function with a low computational cost. In addition, an updating scheme based on the APCE-pool and Peak-pool is proposed to reveal the tracking condition and ensure updates of the target’s appearance model with high-confidence. The Kalam filter is adopted to track the target when the appearance model is persistently unreliable and abnormality occurs. Finally, extensive experimental results on OTB-2013, OTB-2015 and VOT2018 datasets show that our proposed tracker performs favorably against several state-of-the-art trackers.
format	article
author	Yinqiang Su Jinghong Liu Fang Xu Xueming Zhang Yujia Zuo
author_facet	Yinqiang Su Jinghong Liu Fang Xu Xueming Zhang Yujia Zuo
author_sort	Yinqiang Su
title	A Novel Anti-Drift Visual Object Tracking Algorithm Based on Sparse Response and Adaptive Spatial-Temporal Context-Aware
title_short	A Novel Anti-Drift Visual Object Tracking Algorithm Based on Sparse Response and Adaptive Spatial-Temporal Context-Aware
title_full	A Novel Anti-Drift Visual Object Tracking Algorithm Based on Sparse Response and Adaptive Spatial-Temporal Context-Aware
title_fullStr	A Novel Anti-Drift Visual Object Tracking Algorithm Based on Sparse Response and Adaptive Spatial-Temporal Context-Aware
title_full_unstemmed	A Novel Anti-Drift Visual Object Tracking Algorithm Based on Sparse Response and Adaptive Spatial-Temporal Context-Aware
title_sort	novel anti-drift visual object tracking algorithm based on sparse response and adaptive spatial-temporal context-aware
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/4b2d700425ef4600a1307b14775ae402
work_keys_str_mv	AT yinqiangsu anovelantidriftvisualobjecttrackingalgorithmbasedonsparseresponseandadaptivespatialtemporalcontextaware AT jinghongliu anovelantidriftvisualobjecttrackingalgorithmbasedonsparseresponseandadaptivespatialtemporalcontextaware AT fangxu anovelantidriftvisualobjecttrackingalgorithmbasedonsparseresponseandadaptivespatialtemporalcontextaware AT xuemingzhang anovelantidriftvisualobjecttrackingalgorithmbasedonsparseresponseandadaptivespatialtemporalcontextaware AT yujiazuo anovelantidriftvisualobjecttrackingalgorithmbasedonsparseresponseandadaptivespatialtemporalcontextaware AT yinqiangsu novelantidriftvisualobjecttrackingalgorithmbasedonsparseresponseandadaptivespatialtemporalcontextaware AT jinghongliu novelantidriftvisualobjecttrackingalgorithmbasedonsparseresponseandadaptivespatialtemporalcontextaware AT fangxu novelantidriftvisualobjecttrackingalgorithmbasedonsparseresponseandadaptivespatialtemporalcontextaware AT xuemingzhang novelantidriftvisualobjecttrackingalgorithmbasedonsparseresponseandadaptivespatialtemporalcontextaware AT yujiazuo novelantidriftvisualobjecttrackingalgorithmbasedonsparseresponseandadaptivespatialtemporalcontextaware
_version_	1718410521936396288

A Novel Anti-Drift Visual Object Tracking Algorithm Based on Sparse Response and Adaptive Spatial-Temporal Context-Aware

Ejemplares similares