Learning Multi-Granularity Neural Network Encoding Image Classification Using DCNNs for Easter Africa Community Countries

Remote sensing scene classification is a fundamental responsibility of earth observation, aiming at identifying information granular for land cover classification. The multi-granular land use for multi-source remotely sensed image categories is now a principal task in remote sensing data augmentatio...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Musabe Jean Bosco, Guoyin Wang, Yves Hategekimana
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Convolutional neural networks (CNNs) fine-tuning granularity feature extraction machine learning and remote sensing (RS) Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/84c1802afbee468fae2d2069bf843364
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:84c1802afbee468fae2d2069bf843364
record_format	dspace
spelling	oai:doaj.org-article:84c1802afbee468fae2d2069bf8433642021-11-09T00:01:57ZLearning Multi-Granularity Neural Network Encoding Image Classification Using DCNNs for Easter Africa Community Countries2169-353610.1109/ACCESS.2021.3122569https://doaj.org/article/84c1802afbee468fae2d2069bf8433642021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9585087/https://doaj.org/toc/2169-3536Remote sensing scene classification is a fundamental responsibility of earth observation, aiming at identifying information granular for land cover classification. The multi-granular land use for multi-source remotely sensed image categories is now a principal task in remote sensing data augmentation and data selection. Understanding image representations are meaningful for the scene classification task. Training deep learning model-based approaches has to do with scene classification and brings about fantastic achievement. At the same time, these high-level approaches are computationally expensive and time–consuming. This paper introduces multi-granularity Neural Network Encoding architecture base on InceptionV3, InceptionReseNetV2, VGG16, and DenseNet201 architecture into remote sensing scene classification. To improve performance and to solve intra-class variation for multi-class scene issues remote sensing dataset. By using pre-trained CNN, activation function and ensemble learning have been adopting. InceptionV3 and VGG16 are used to extract features. InceptionResNetV2 use for fine-tuning, which consists of unfreezing the entre model and retraining the new data with a lower learning rate. The proposed fine-tune whole pre-trained model produces better results of test set up to 97.84 % than features extracted by InceptionResNetV2. Also, we use DCNNs ensemble average and weighted average to achieve better outcomes for 97.36% and 99.10%. In our experiments, we attempted to fine-tune the deep convolutional neural networks (DCNNs) training method for remote sensing scene classification on two public datasets UCM, SIRI-WHU, and one dataset I collected through the google earth engine from East Africa Community Countries (EACC) within nine classes within total 2112 labeled images. The results indicate that our proposed fine-tuning of the pre-trained model with few epochs and less computational time increases accuracy.Musabe Jean BoscoGuoyin WangYves HategekimanaIEEEarticleConvolutional neural networks (CNNs)fine-tuninggranularity feature extractionmachine learningand remote sensing (RS)Electrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 146703-146718 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Convolutional neural networks (CNNs) fine-tuning granularity feature extraction machine learning and remote sensing (RS) Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Convolutional neural networks (CNNs) fine-tuning granularity feature extraction machine learning and remote sensing (RS) Electrical engineering. Electronics. Nuclear engineering TK1-9971 Musabe Jean Bosco Guoyin Wang Yves Hategekimana Learning Multi-Granularity Neural Network Encoding Image Classification Using DCNNs for Easter Africa Community Countries
description	Remote sensing scene classification is a fundamental responsibility of earth observation, aiming at identifying information granular for land cover classification. The multi-granular land use for multi-source remotely sensed image categories is now a principal task in remote sensing data augmentation and data selection. Understanding image representations are meaningful for the scene classification task. Training deep learning model-based approaches has to do with scene classification and brings about fantastic achievement. At the same time, these high-level approaches are computationally expensive and time–consuming. This paper introduces multi-granularity Neural Network Encoding architecture base on InceptionV3, InceptionReseNetV2, VGG16, and DenseNet201 architecture into remote sensing scene classification. To improve performance and to solve intra-class variation for multi-class scene issues remote sensing dataset. By using pre-trained CNN, activation function and ensemble learning have been adopting. InceptionV3 and VGG16 are used to extract features. InceptionResNetV2 use for fine-tuning, which consists of unfreezing the entre model and retraining the new data with a lower learning rate. The proposed fine-tune whole pre-trained model produces better results of test set up to 97.84 % than features extracted by InceptionResNetV2. Also, we use DCNNs ensemble average and weighted average to achieve better outcomes for 97.36% and 99.10%. In our experiments, we attempted to fine-tune the deep convolutional neural networks (DCNNs) training method for remote sensing scene classification on two public datasets UCM, SIRI-WHU, and one dataset I collected through the google earth engine from East Africa Community Countries (EACC) within nine classes within total 2112 labeled images. The results indicate that our proposed fine-tuning of the pre-trained model with few epochs and less computational time increases accuracy.
format	article
author	Musabe Jean Bosco Guoyin Wang Yves Hategekimana
author_facet	Musabe Jean Bosco Guoyin Wang Yves Hategekimana
author_sort	Musabe Jean Bosco
title	Learning Multi-Granularity Neural Network Encoding Image Classification Using DCNNs for Easter Africa Community Countries
title_short	Learning Multi-Granularity Neural Network Encoding Image Classification Using DCNNs for Easter Africa Community Countries
title_full	Learning Multi-Granularity Neural Network Encoding Image Classification Using DCNNs for Easter Africa Community Countries
title_fullStr	Learning Multi-Granularity Neural Network Encoding Image Classification Using DCNNs for Easter Africa Community Countries
title_full_unstemmed	Learning Multi-Granularity Neural Network Encoding Image Classification Using DCNNs for Easter Africa Community Countries
title_sort	learning multi-granularity neural network encoding image classification using dcnns for easter africa community countries
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/84c1802afbee468fae2d2069bf843364
work_keys_str_mv	AT musabejeanbosco learningmultigranularityneuralnetworkencodingimageclassificationusingdcnnsforeasterafricacommunitycountries AT guoyinwang learningmultigranularityneuralnetworkencodingimageclassificationusingdcnnsforeasterafricacommunitycountries AT yveshategekimana learningmultigranularityneuralnetworkencodingimageclassificationusingdcnnsforeasterafricacommunitycountries
_version_	1718441396903346176

Learning Multi-Granularity Neural Network Encoding Image Classification Using DCNNs for Easter Africa Community Countries

Ejemplares similares