Detection of Schools in Remote Sensing Images Based on Attention-Guided Dense Network

The detection of primary and secondary schools (PSSs) is a meaningful task for composite object detection in remote sensing images (RSIs). As a typical composite object in RSIs, PSSs have diverse appearances with complex backgrounds, which makes it difficult to effectively extract their features usi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Han Fu, Xiangtao Fan, Zhenzhen Yan, Xiaoping Du
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	primary and secondary schools detection remote sensing images attention mechanism FPN Geography (General) G1-922
Acceso en línea:	https://doaj.org/article/6ba730b1215f494da6a1fccc7d169df6
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6ba730b1215f494da6a1fccc7d169df6
record_format	dspace
spelling	oai:doaj.org-article:6ba730b1215f494da6a1fccc7d169df62021-11-25T17:52:50ZDetection of Schools in Remote Sensing Images Based on Attention-Guided Dense Network10.3390/ijgi101107362220-9964https://doaj.org/article/6ba730b1215f494da6a1fccc7d169df62021-10-01T00:00:00Zhttps://www.mdpi.com/2220-9964/10/11/736https://doaj.org/toc/2220-9964The detection of primary and secondary schools (PSSs) is a meaningful task for composite object detection in remote sensing images (RSIs). As a typical composite object in RSIs, PSSs have diverse appearances with complex backgrounds, which makes it difficult to effectively extract their features using the existing deep-learning-based object detection algorithms. Aiming at the challenges of PSSs detection, we propose an end-to-end framework called the attention-guided dense network (ADNet), which can effectively improve the detection accuracy of PSSs. First, a dual attention module (DAM) is designed to enhance the ability in representing complex characteristics and alleviate distractions in the background. Second, a dense feature fusion module (DFFM) is built to promote attention cues flow into low layers, which guides the generation of hierarchical feature representation. Experimental results demonstrate that our proposed method outperforms the state-of-the-art methods and achieves 79.86% average precision. The study proves the effectiveness of our proposed method on PSSs detection.Han FuXiangtao FanZhenzhen YanXiaoping DuMDPI AGarticleprimary and secondary schools detectionremote sensing imagesattention mechanismFPNGeography (General)G1-922ENISPRS International Journal of Geo-Information, Vol 10, Iss 736, p 736 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	primary and secondary schools detection remote sensing images attention mechanism FPN Geography (General) G1-922
spellingShingle	primary and secondary schools detection remote sensing images attention mechanism FPN Geography (General) G1-922 Han Fu Xiangtao Fan Zhenzhen Yan Xiaoping Du Detection of Schools in Remote Sensing Images Based on Attention-Guided Dense Network
description	The detection of primary and secondary schools (PSSs) is a meaningful task for composite object detection in remote sensing images (RSIs). As a typical composite object in RSIs, PSSs have diverse appearances with complex backgrounds, which makes it difficult to effectively extract their features using the existing deep-learning-based object detection algorithms. Aiming at the challenges of PSSs detection, we propose an end-to-end framework called the attention-guided dense network (ADNet), which can effectively improve the detection accuracy of PSSs. First, a dual attention module (DAM) is designed to enhance the ability in representing complex characteristics and alleviate distractions in the background. Second, a dense feature fusion module (DFFM) is built to promote attention cues flow into low layers, which guides the generation of hierarchical feature representation. Experimental results demonstrate that our proposed method outperforms the state-of-the-art methods and achieves 79.86% average precision. The study proves the effectiveness of our proposed method on PSSs detection.
format	article
author	Han Fu Xiangtao Fan Zhenzhen Yan Xiaoping Du
author_facet	Han Fu Xiangtao Fan Zhenzhen Yan Xiaoping Du
author_sort	Han Fu
title	Detection of Schools in Remote Sensing Images Based on Attention-Guided Dense Network
title_short	Detection of Schools in Remote Sensing Images Based on Attention-Guided Dense Network
title_full	Detection of Schools in Remote Sensing Images Based on Attention-Guided Dense Network
title_fullStr	Detection of Schools in Remote Sensing Images Based on Attention-Guided Dense Network
title_full_unstemmed	Detection of Schools in Remote Sensing Images Based on Attention-Guided Dense Network
title_sort	detection of schools in remote sensing images based on attention-guided dense network
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/6ba730b1215f494da6a1fccc7d169df6
work_keys_str_mv	AT hanfu detectionofschoolsinremotesensingimagesbasedonattentionguideddensenetwork AT xiangtaofan detectionofschoolsinremotesensingimagesbasedonattentionguideddensenetwork AT zhenzhenyan detectionofschoolsinremotesensingimagesbasedonattentionguideddensenetwork AT xiaopingdu detectionofschoolsinremotesensingimagesbasedonattentionguideddensenetwork
_version_	1718411866736164864

Detection of Schools in Remote Sensing Images Based on Attention-Guided Dense Network

Ejemplares similares