Edge-Aware Multi-Level Interactive Network for Salient Object Detection of Strip Steel Surface Defects

The performance of the salient object detection of strip surface defects has been promoted largely by deep learning based models. However, due to the complexity of strip surface defects, the existing models perform poorly in the challenging scenes such as noise disturbance, and low contrast between...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xiaofei Zhou, Hao Fang, Xiaobo Fei, Ran Shi, Jiyong Zhang
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Salient object detection surface defects multi-level feature fusion edge Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/9b824aa28ef74f439a04dcebef8b3ee5
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9b824aa28ef74f439a04dcebef8b3ee5
record_format	dspace
spelling	oai:doaj.org-article:9b824aa28ef74f439a04dcebef8b3ee52021-11-18T00:03:42ZEdge-Aware Multi-Level Interactive Network for Salient Object Detection of Strip Steel Surface Defects2169-353610.1109/ACCESS.2021.3124814https://doaj.org/article/9b824aa28ef74f439a04dcebef8b3ee52021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9598922/https://doaj.org/toc/2169-3536The performance of the salient object detection of strip surface defects has been promoted largely by deep learning based models. However, due to the complexity of strip surface defects, the existing models perform poorly in the challenging scenes such as noise disturbance, and low contrast between defect regions and background. Meanwhile, the detection results of existing models often suffer from coarse boundary details. Therefore, we propose a novel saliency model, namely an Edge-aware Multi-level Interactive Network, to detect the defects from the strip steel surface. Concretely, our model adopts the U-shape architecture where the two crucial points are the interactive feature integration and the edge-guided saliency fusion. Firstly, except the skip connection that combines the same stage of encoder and decoder, we deploy another connection, where the features from adjacent levels of encoder are transferred to the same stage of decoder. By this way, we are able to provide an effective fusion of multi-level deep features, yielding a well depiction for defects. Secondly, to give well-defined boundaries for prediction results, we add the edge extraction branch after each decoder block, where the progressive feature aggregation endows the edge with precise details and complete object cues. Meanwhile, together with the edge extraction branches, we deploy the saliency prediction branch at each decoder stage. After that, coupled with the fine edge information, we fuse all outputs of saliency prediction branches into the final saliency map, where the edge cue steers the saliency result to pay more attention to the boundary details. Following this way, we can provide a high-quality saliency map which can accurately locate and segment the defects. Extensive experiments are performed on the public dataset, and the results prove the effectiveness and robustness of our model which consistently outperforms the state-of-the-art models.Xiaofei ZhouHao FangXiaobo FeiRan ShiJiyong ZhangIEEEarticleSalient object detectionsurface defectsmulti-level featurefusionedgeElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 149465-149476 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Salient object detection surface defects multi-level feature fusion edge Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Salient object detection surface defects multi-level feature fusion edge Electrical engineering. Electronics. Nuclear engineering TK1-9971 Xiaofei Zhou Hao Fang Xiaobo Fei Ran Shi Jiyong Zhang Edge-Aware Multi-Level Interactive Network for Salient Object Detection of Strip Steel Surface Defects
description	The performance of the salient object detection of strip surface defects has been promoted largely by deep learning based models. However, due to the complexity of strip surface defects, the existing models perform poorly in the challenging scenes such as noise disturbance, and low contrast between defect regions and background. Meanwhile, the detection results of existing models often suffer from coarse boundary details. Therefore, we propose a novel saliency model, namely an Edge-aware Multi-level Interactive Network, to detect the defects from the strip steel surface. Concretely, our model adopts the U-shape architecture where the two crucial points are the interactive feature integration and the edge-guided saliency fusion. Firstly, except the skip connection that combines the same stage of encoder and decoder, we deploy another connection, where the features from adjacent levels of encoder are transferred to the same stage of decoder. By this way, we are able to provide an effective fusion of multi-level deep features, yielding a well depiction for defects. Secondly, to give well-defined boundaries for prediction results, we add the edge extraction branch after each decoder block, where the progressive feature aggregation endows the edge with precise details and complete object cues. Meanwhile, together with the edge extraction branches, we deploy the saliency prediction branch at each decoder stage. After that, coupled with the fine edge information, we fuse all outputs of saliency prediction branches into the final saliency map, where the edge cue steers the saliency result to pay more attention to the boundary details. Following this way, we can provide a high-quality saliency map which can accurately locate and segment the defects. Extensive experiments are performed on the public dataset, and the results prove the effectiveness and robustness of our model which consistently outperforms the state-of-the-art models.
format	article
author	Xiaofei Zhou Hao Fang Xiaobo Fei Ran Shi Jiyong Zhang
author_facet	Xiaofei Zhou Hao Fang Xiaobo Fei Ran Shi Jiyong Zhang
author_sort	Xiaofei Zhou
title	Edge-Aware Multi-Level Interactive Network for Salient Object Detection of Strip Steel Surface Defects
title_short	Edge-Aware Multi-Level Interactive Network for Salient Object Detection of Strip Steel Surface Defects
title_full	Edge-Aware Multi-Level Interactive Network for Salient Object Detection of Strip Steel Surface Defects
title_fullStr	Edge-Aware Multi-Level Interactive Network for Salient Object Detection of Strip Steel Surface Defects
title_full_unstemmed	Edge-Aware Multi-Level Interactive Network for Salient Object Detection of Strip Steel Surface Defects
title_sort	edge-aware multi-level interactive network for salient object detection of strip steel surface defects
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/9b824aa28ef74f439a04dcebef8b3ee5
work_keys_str_mv	AT xiaofeizhou edgeawaremultilevelinteractivenetworkforsalientobjectdetectionofstripsteelsurfacedefects AT haofang edgeawaremultilevelinteractivenetworkforsalientobjectdetectionofstripsteelsurfacedefects AT xiaobofei edgeawaremultilevelinteractivenetworkforsalientobjectdetectionofstripsteelsurfacedefects AT ranshi edgeawaremultilevelinteractivenetworkforsalientobjectdetectionofstripsteelsurfacedefects AT jiyongzhang edgeawaremultilevelinteractivenetworkforsalientobjectdetectionofstripsteelsurfacedefects
_version_	1718425240637276160

Edge-Aware Multi-Level Interactive Network for Salient Object Detection of Strip Steel Surface Defects

Ejemplares similares