High-Resolution Boundary Refined Convolutional Neural Network for Automatic Agricultural Greenhouses Extraction from GaoFen-2 Satellite Imageries

Agricultural greenhouses (AGs) are an important component of modern facility agriculture, and accurately mapping and dynamically monitoring their distribution are necessary for agricultural scientific management and planning. Semantic segmentation can be adopted for AG extraction from remote sensing...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xiaoping Zhang, Bo Cheng, Jinfen Chen, Chenbin Liang
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	Agricultural Greenhouses DCNN Semantic Segmentation high resolution context integration boundary refined Science Q
Acceso en línea:	https://doaj.org/article/6e58c899e6f546afa0684d38e63dd1e9
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6e58c899e6f546afa0684d38e63dd1e9
record_format	dspace
spelling	oai:doaj.org-article:6e58c899e6f546afa0684d38e63dd1e92021-11-11T18:50:56ZHigh-Resolution Boundary Refined Convolutional Neural Network for Automatic Agricultural Greenhouses Extraction from GaoFen-2 Satellite Imageries10.3390/rs132142372072-4292https://doaj.org/article/6e58c899e6f546afa0684d38e63dd1e92021-10-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/21/4237https://doaj.org/toc/2072-4292Agricultural greenhouses (AGs) are an important component of modern facility agriculture, and accurately mapping and dynamically monitoring their distribution are necessary for agricultural scientific management and planning. Semantic segmentation can be adopted for AG extraction from remote sensing images. However, the feature maps obtained by traditional deep convolutional neural network (DCNN)-based segmentation algorithms blur spatial details and insufficient attention is usually paid to contextual representation. Meanwhile, the maintenance of the original morphological characteristics, especially the boundaries, is still a challenge for precise identification of AGs. To alleviate these problems, this paper proposes a novel network called high-resolution boundary refined network (HBRNet). In this method, we design a new backbone with multiple paths based on HRNetV2 aiming to preserve high spatial resolution and improve feature extraction capability, in which the Pyramid Cross Channel Attention (PCCA) module is embedded to residual blocks to strengthen the interaction of multiscale information. Moreover, the Spatial Enhancement (SE) module is employed to integrate the contextual information of different scales. In addition, we introduce the Spatial Gradient Variation (SGV) unit in the Boundary Refined (BR) module to couple the segmentation task and boundary learning task, so that they can share latent high-level semantics and interact with each other, and combine this with the joint loss to refine the boundary. In our study, GaoFen-2 remote sensing images in Shouguang City, Shandong Province, China are selected to make the AG dataset. The experimental results show that HBRNet demonstrates a significant improvement in segmentation performance up to an IoU score of 94.89%, implying that this approach has advantages and potential for precise identification of AGs.Xiaoping ZhangBo ChengJinfen ChenChenbin LiangMDPI AGarticleAgricultural GreenhousesDCNNSemantic Segmentationhigh resolutioncontext integrationboundary refinedScienceQENRemote Sensing, Vol 13, Iss 4237, p 4237 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Agricultural Greenhouses DCNN Semantic Segmentation high resolution context integration boundary refined Science Q
spellingShingle	Agricultural Greenhouses DCNN Semantic Segmentation high resolution context integration boundary refined Science Q Xiaoping Zhang Bo Cheng Jinfen Chen Chenbin Liang High-Resolution Boundary Refined Convolutional Neural Network for Automatic Agricultural Greenhouses Extraction from GaoFen-2 Satellite Imageries
description	Agricultural greenhouses (AGs) are an important component of modern facility agriculture, and accurately mapping and dynamically monitoring their distribution are necessary for agricultural scientific management and planning. Semantic segmentation can be adopted for AG extraction from remote sensing images. However, the feature maps obtained by traditional deep convolutional neural network (DCNN)-based segmentation algorithms blur spatial details and insufficient attention is usually paid to contextual representation. Meanwhile, the maintenance of the original morphological characteristics, especially the boundaries, is still a challenge for precise identification of AGs. To alleviate these problems, this paper proposes a novel network called high-resolution boundary refined network (HBRNet). In this method, we design a new backbone with multiple paths based on HRNetV2 aiming to preserve high spatial resolution and improve feature extraction capability, in which the Pyramid Cross Channel Attention (PCCA) module is embedded to residual blocks to strengthen the interaction of multiscale information. Moreover, the Spatial Enhancement (SE) module is employed to integrate the contextual information of different scales. In addition, we introduce the Spatial Gradient Variation (SGV) unit in the Boundary Refined (BR) module to couple the segmentation task and boundary learning task, so that they can share latent high-level semantics and interact with each other, and combine this with the joint loss to refine the boundary. In our study, GaoFen-2 remote sensing images in Shouguang City, Shandong Province, China are selected to make the AG dataset. The experimental results show that HBRNet demonstrates a significant improvement in segmentation performance up to an IoU score of 94.89%, implying that this approach has advantages and potential for precise identification of AGs.
format	article
author	Xiaoping Zhang Bo Cheng Jinfen Chen Chenbin Liang
author_facet	Xiaoping Zhang Bo Cheng Jinfen Chen Chenbin Liang
author_sort	Xiaoping Zhang
title	High-Resolution Boundary Refined Convolutional Neural Network for Automatic Agricultural Greenhouses Extraction from GaoFen-2 Satellite Imageries
title_short	High-Resolution Boundary Refined Convolutional Neural Network for Automatic Agricultural Greenhouses Extraction from GaoFen-2 Satellite Imageries
title_full	High-Resolution Boundary Refined Convolutional Neural Network for Automatic Agricultural Greenhouses Extraction from GaoFen-2 Satellite Imageries
title_fullStr	High-Resolution Boundary Refined Convolutional Neural Network for Automatic Agricultural Greenhouses Extraction from GaoFen-2 Satellite Imageries
title_full_unstemmed	High-Resolution Boundary Refined Convolutional Neural Network for Automatic Agricultural Greenhouses Extraction from GaoFen-2 Satellite Imageries
title_sort	high-resolution boundary refined convolutional neural network for automatic agricultural greenhouses extraction from gaofen-2 satellite imageries
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/6e58c899e6f546afa0684d38e63dd1e9
work_keys_str_mv	AT xiaopingzhang highresolutionboundaryrefinedconvolutionalneuralnetworkforautomaticagriculturalgreenhousesextractionfromgaofen2satelliteimageries AT bocheng highresolutionboundaryrefinedconvolutionalneuralnetworkforautomaticagriculturalgreenhousesextractionfromgaofen2satelliteimageries AT jinfenchen highresolutionboundaryrefinedconvolutionalneuralnetworkforautomaticagriculturalgreenhousesextractionfromgaofen2satelliteimageries AT chenbinliang highresolutionboundaryrefinedconvolutionalneuralnetworkforautomaticagriculturalgreenhousesextractionfromgaofen2satelliteimageries
_version_	1718431707437203456

High-Resolution Boundary Refined Convolutional Neural Network for Automatic Agricultural Greenhouses Extraction from GaoFen-2 Satellite Imageries

Ejemplares similares