Railway Foreign Object Tracking Based on Correlation Filtering of Optimized Regularization Model

Aiming at problems such as the untrustworthy association between spatial regularization weight and intrusive foreign object in complex railway scenes, as well as the degradation of correlation filter model, fully excavate the expressive ability of deep space features, and a foreign object tracking a...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Tao Hou, Yannan Chen, Caiwen Bao, Yuhu Chen
Formato:	article
Lenguaje:	EN
Publicado:	Tamkang University Press 2021
Materias:	railway foreign object tracking correlation filtering depth space time perception spatial regularization model update Engineering (General). Civil engineering (General) TA1-2040 Chemical engineering TP155-156 Physics QC1-999
Acceso en línea:	https://doaj.org/article/cc829408d0a14d58aff3eaf7b38fad5d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:cc829408d0a14d58aff3eaf7b38fad5d
record_format	dspace
spelling	oai:doaj.org-article:cc829408d0a14d58aff3eaf7b38fad5d2021-11-23T18:01:59ZRailway Foreign Object Tracking Based on Correlation Filtering of Optimized Regularization Model10.6180/jase.202204_25(2).00152708-99672708-9975https://doaj.org/article/cc829408d0a14d58aff3eaf7b38fad5d2021-11-01T00:00:00Zhttp://jase.tku.edu.tw/articles/jase-202204-25-2-0015https://doaj.org/toc/2708-9967https://doaj.org/toc/2708-9975Aiming at problems such as the untrustworthy association between spatial regularization weight and intrusive foreign object in complex railway scenes, as well as the degradation of correlation filter model, fully excavate the expressive ability of deep space features, and a foreign object tracking algorithm based on correlation filtering with depth space and time perception regularization is put forward. Firstly, select the fifth-level convolution feature of the Visual Geometry Group (VGG) network to extract the spatial area information of the foreign object, which is used to solve the regularization guide weight. Secondly, a regularization term based on depth space is added to the objective function, whose aim is to establish a more reliable association between the spatial regularization weight and the invading foreign object. Thirdly, the time perception term is added to establish the connection between the filters in time. Finally, based on the depth space, a simple and effective model update strategy is proposed. On the public OBT datasets and complex railway scenes, the tracking results of the algorithm in this paper and the existing multiple algorithms are compared and analyzed. The results show that in complex railway scenes, the algorithm in this paper is superior to other algorithms in distance accuracy and success rate. The tracking speed is 23.1FPS, which basically meets the real-time requirements. Therefore, the correlation filtering algorithm of the improved regularization model is of great significance to railway safety.Tao HouYannan ChenCaiwen BaoYuhu ChenTamkang University Pressarticlerailway foreign object trackingcorrelation filteringdepth spacetime perceptionspatial regularizationmodel updateEngineering (General). Civil engineering (General)TA1-2040Chemical engineeringTP155-156PhysicsQC1-999ENJournal of Applied Science and Engineering, Vol 25, Iss 2, Pp 295-306 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	railway foreign object tracking correlation filtering depth space time perception spatial regularization model update Engineering (General). Civil engineering (General) TA1-2040 Chemical engineering TP155-156 Physics QC1-999
spellingShingle	railway foreign object tracking correlation filtering depth space time perception spatial regularization model update Engineering (General). Civil engineering (General) TA1-2040 Chemical engineering TP155-156 Physics QC1-999 Tao Hou Yannan Chen Caiwen Bao Yuhu Chen Railway Foreign Object Tracking Based on Correlation Filtering of Optimized Regularization Model
description	Aiming at problems such as the untrustworthy association between spatial regularization weight and intrusive foreign object in complex railway scenes, as well as the degradation of correlation filter model, fully excavate the expressive ability of deep space features, and a foreign object tracking algorithm based on correlation filtering with depth space and time perception regularization is put forward. Firstly, select the fifth-level convolution feature of the Visual Geometry Group (VGG) network to extract the spatial area information of the foreign object, which is used to solve the regularization guide weight. Secondly, a regularization term based on depth space is added to the objective function, whose aim is to establish a more reliable association between the spatial regularization weight and the invading foreign object. Thirdly, the time perception term is added to establish the connection between the filters in time. Finally, based on the depth space, a simple and effective model update strategy is proposed. On the public OBT datasets and complex railway scenes, the tracking results of the algorithm in this paper and the existing multiple algorithms are compared and analyzed. The results show that in complex railway scenes, the algorithm in this paper is superior to other algorithms in distance accuracy and success rate. The tracking speed is 23.1FPS, which basically meets the real-time requirements. Therefore, the correlation filtering algorithm of the improved regularization model is of great significance to railway safety.
format	article
author	Tao Hou Yannan Chen Caiwen Bao Yuhu Chen
author_facet	Tao Hou Yannan Chen Caiwen Bao Yuhu Chen
author_sort	Tao Hou
title	Railway Foreign Object Tracking Based on Correlation Filtering of Optimized Regularization Model
title_short	Railway Foreign Object Tracking Based on Correlation Filtering of Optimized Regularization Model
title_full	Railway Foreign Object Tracking Based on Correlation Filtering of Optimized Regularization Model
title_fullStr	Railway Foreign Object Tracking Based on Correlation Filtering of Optimized Regularization Model
title_full_unstemmed	Railway Foreign Object Tracking Based on Correlation Filtering of Optimized Regularization Model
title_sort	railway foreign object tracking based on correlation filtering of optimized regularization model
publisher	Tamkang University Press
publishDate	2021
url	https://doaj.org/article/cc829408d0a14d58aff3eaf7b38fad5d
work_keys_str_mv	AT taohou railwayforeignobjecttrackingbasedoncorrelationfilteringofoptimizedregularizationmodel AT yannanchen railwayforeignobjecttrackingbasedoncorrelationfilteringofoptimizedregularizationmodel AT caiwenbao railwayforeignobjecttrackingbasedoncorrelationfilteringofoptimizedregularizationmodel AT yuhuchen railwayforeignobjecttrackingbasedoncorrelationfilteringofoptimizedregularizationmodel
_version_	1718416181782642688

Railway Foreign Object Tracking Based on Correlation Filtering of Optimized Regularization Model

Ejemplares similares