Remote Sensing Scene Image Classification Based on Dense Fusion of Multi-level Features

For remote sensing scene image classification, many convolution neural networks improve the classification accuracy at the cost of the time and space complexity of the models. This leads to a slow running speed for the model and cannot realize a trade-off between the model accuracy and the model run...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Cuiping Shi, Xinlei Zhang, Jingwei Sun, Liguo Wang
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	remote sensing scene image classification convolutional neural network (CNN) downsampling lightweight Science Q
Acceso en línea:	https://doaj.org/article/7ff1c25b3c504474bd786360b4763f16
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:7ff1c25b3c504474bd786360b4763f16
record_format	dspace
spelling	oai:doaj.org-article:7ff1c25b3c504474bd786360b4763f162021-11-11T18:55:00ZRemote Sensing Scene Image Classification Based on Dense Fusion of Multi-level Features10.3390/rs132143792072-4292https://doaj.org/article/7ff1c25b3c504474bd786360b4763f162021-10-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/21/4379https://doaj.org/toc/2072-4292For remote sensing scene image classification, many convolution neural networks improve the classification accuracy at the cost of the time and space complexity of the models. This leads to a slow running speed for the model and cannot realize a trade-off between the model accuracy and the model running speed. As the network deepens, it is difficult to extract the key features with a sample double branched structure, and it also leads to the loss of shallow features, which is unfavorable to the classification of remote sensing scene images. To solve this problem, we propose a dual branch multi-level feature dense fusion-based lightweight convolutional neural network (BMDF-LCNN). The network structure can fully extract the information of the current layer through 3 × 3 depthwise separable convolution and 1 × 1 standard convolution, identity branches, and fuse with the features extracted from the previous layer 1 × 1 standard convolution, thus avoiding the loss of shallow information due to network deepening. In addition, we propose a downsampling structure that is more suitable for extracting the shallow features of the network by using the pooled branch to downsample and the convolution branch to compensate for the pooled features. Experiments were carried out on four open and challenging remote sensing image scene data sets. The experimental results show that the proposed method has higher classification accuracy and lower model complexity than some state-of-the-art classification methods and realizes the trade-off between model accuracy and model running speed.Cuiping ShiXinlei ZhangJingwei SunLiguo WangMDPI AGarticleremote sensing scene imageclassificationconvolutional neural network (CNN)downsamplinglightweightScienceQENRemote Sensing, Vol 13, Iss 4379, p 4379 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	remote sensing scene image classification convolutional neural network (CNN) downsampling lightweight Science Q
spellingShingle	remote sensing scene image classification convolutional neural network (CNN) downsampling lightweight Science Q Cuiping Shi Xinlei Zhang Jingwei Sun Liguo Wang Remote Sensing Scene Image Classification Based on Dense Fusion of Multi-level Features
description	For remote sensing scene image classification, many convolution neural networks improve the classification accuracy at the cost of the time and space complexity of the models. This leads to a slow running speed for the model and cannot realize a trade-off between the model accuracy and the model running speed. As the network deepens, it is difficult to extract the key features with a sample double branched structure, and it also leads to the loss of shallow features, which is unfavorable to the classification of remote sensing scene images. To solve this problem, we propose a dual branch multi-level feature dense fusion-based lightweight convolutional neural network (BMDF-LCNN). The network structure can fully extract the information of the current layer through 3 × 3 depthwise separable convolution and 1 × 1 standard convolution, identity branches, and fuse with the features extracted from the previous layer 1 × 1 standard convolution, thus avoiding the loss of shallow information due to network deepening. In addition, we propose a downsampling structure that is more suitable for extracting the shallow features of the network by using the pooled branch to downsample and the convolution branch to compensate for the pooled features. Experiments were carried out on four open and challenging remote sensing image scene data sets. The experimental results show that the proposed method has higher classification accuracy and lower model complexity than some state-of-the-art classification methods and realizes the trade-off between model accuracy and model running speed.
format	article
author	Cuiping Shi Xinlei Zhang Jingwei Sun Liguo Wang
author_facet	Cuiping Shi Xinlei Zhang Jingwei Sun Liguo Wang
author_sort	Cuiping Shi
title	Remote Sensing Scene Image Classification Based on Dense Fusion of Multi-level Features
title_short	Remote Sensing Scene Image Classification Based on Dense Fusion of Multi-level Features
title_full	Remote Sensing Scene Image Classification Based on Dense Fusion of Multi-level Features
title_fullStr	Remote Sensing Scene Image Classification Based on Dense Fusion of Multi-level Features
title_full_unstemmed	Remote Sensing Scene Image Classification Based on Dense Fusion of Multi-level Features
title_sort	remote sensing scene image classification based on dense fusion of multi-level features
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/7ff1c25b3c504474bd786360b4763f16
work_keys_str_mv	AT cuipingshi remotesensingsceneimageclassificationbasedondensefusionofmultilevelfeatures AT xinleizhang remotesensingsceneimageclassificationbasedondensefusionofmultilevelfeatures AT jingweisun remotesensingsceneimageclassificationbasedondensefusionofmultilevelfeatures AT liguowang remotesensingsceneimageclassificationbasedondensefusionofmultilevelfeatures
_version_	1718431655254818816

Remote Sensing Scene Image Classification Based on Dense Fusion of Multi-level Features

Ejemplares similares