Performance Analysis in the Segmentation of urban asphalted roads in RGB satellite images using K-Means++ and SegNet

The design and manual insertion of new terrestrial roads into geographic databases is a frequent activity in geoprocessing and their demand usually occurs as the most up-to-date satellite imagery of the territory is acquired. Continually, new urban and rural occupations emerge, for which specific v...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	João Batista Pacheco Junior, Henrique Mariano Costa do Amaral
Formato:	article
Lenguaje:	EN ES
Publicado:	Asociación Española para la Inteligencia Artificial 2021
Materias:	Geoprocessing RGB image image segmentation K-Means Convolutional Neural Network Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/eca5a5268447432db666cde271886d9c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:eca5a5268447432db666cde271886d9c
record_format	dspace
spelling	oai:doaj.org-article:eca5a5268447432db666cde271886d9c2021-11-30T02:08:00ZPerformance Analysis in the Segmentation of urban asphalted roads in RGB satellite images using K-Means++ and SegNet10.4114/intartif.vol24iss68pp89-1031137-36011988-3064https://doaj.org/article/eca5a5268447432db666cde271886d9c2021-11-01T00:00:00Zhttps://journal.iberamia.org/index.php/intartif/article/view/671https://doaj.org/toc/1137-3601https://doaj.org/toc/1988-3064 The design and manual insertion of new terrestrial roads into geographic databases is a frequent activity in geoprocessing and their demand usually occurs as the most up-to-date satellite imagery of the territory is acquired. Continually, new urban and rural occupations emerge, for which specific vector geometries need to be designed to characterize the cartographic inputs and accommodate the relevant associated data. Therefore, it is convenient to develop a computational tool that, with the help of artificial intelligence, automates what is possible in this respect, since manual editing depends on the limits of user agility, and does it in images that are usually easy and free to access. To test the feasibility of this proposal, a database of RGB images containing asphalted urban roads is presented to the K-Means++ algorithm and the SegNet Convolutional Neural Network, and the performance of each was evaluated and compared for accuracy and IoU of road identification. Under the conditions of the experiment, K-Means++ achieved poor and unviable results for use in a real-life application involving tarmac detection in RGB satellite images, with average accuracy ranging from 41.67% to 64.19% and average IoU of 12.30% to 16.16%, depending on the preprocessing strategy used. On the other hand, the SegNet Convolutional Neural Network proved to be appropriate for precision applications not sensitive to discontinuities, achieving an average accuracy of 87.12% and an average IoU of 71.93%. João Batista Pacheco JuniorHenrique Mariano Costa do AmaralAsociación Española para la Inteligencia ArtificialarticleGeoprocessingRGB imageimage segmentationK-Means Convolutional Neural NetworkElectronic computers. Computer scienceQA75.5-76.95ENESInteligencia Artificial, Vol 24, Iss 68 (2021)
institution	DOAJ
collection	DOAJ
language	EN ES
topic	Geoprocessing RGB image image segmentation K-Means Convolutional Neural Network Electronic computers. Computer science QA75.5-76.95
spellingShingle	Geoprocessing RGB image image segmentation K-Means Convolutional Neural Network Electronic computers. Computer science QA75.5-76.95 João Batista Pacheco Junior Henrique Mariano Costa do Amaral Performance Analysis in the Segmentation of urban asphalted roads in RGB satellite images using K-Means++ and SegNet
description	The design and manual insertion of new terrestrial roads into geographic databases is a frequent activity in geoprocessing and their demand usually occurs as the most up-to-date satellite imagery of the territory is acquired. Continually, new urban and rural occupations emerge, for which specific vector geometries need to be designed to characterize the cartographic inputs and accommodate the relevant associated data. Therefore, it is convenient to develop a computational tool that, with the help of artificial intelligence, automates what is possible in this respect, since manual editing depends on the limits of user agility, and does it in images that are usually easy and free to access. To test the feasibility of this proposal, a database of RGB images containing asphalted urban roads is presented to the K-Means++ algorithm and the SegNet Convolutional Neural Network, and the performance of each was evaluated and compared for accuracy and IoU of road identification. Under the conditions of the experiment, K-Means++ achieved poor and unviable results for use in a real-life application involving tarmac detection in RGB satellite images, with average accuracy ranging from 41.67% to 64.19% and average IoU of 12.30% to 16.16%, depending on the preprocessing strategy used. On the other hand, the SegNet Convolutional Neural Network proved to be appropriate for precision applications not sensitive to discontinuities, achieving an average accuracy of 87.12% and an average IoU of 71.93%.
format	article
author	João Batista Pacheco Junior Henrique Mariano Costa do Amaral
author_facet	João Batista Pacheco Junior Henrique Mariano Costa do Amaral
author_sort	João Batista Pacheco Junior
title	Performance Analysis in the Segmentation of urban asphalted roads in RGB satellite images using K-Means++ and SegNet
title_short	Performance Analysis in the Segmentation of urban asphalted roads in RGB satellite images using K-Means++ and SegNet
title_full	Performance Analysis in the Segmentation of urban asphalted roads in RGB satellite images using K-Means++ and SegNet
title_fullStr	Performance Analysis in the Segmentation of urban asphalted roads in RGB satellite images using K-Means++ and SegNet
title_full_unstemmed	Performance Analysis in the Segmentation of urban asphalted roads in RGB satellite images using K-Means++ and SegNet
title_sort	performance analysis in the segmentation of urban asphalted roads in rgb satellite images using k-means++ and segnet
publisher	Asociación Española para la Inteligencia Artificial
publishDate	2021
url	https://doaj.org/article/eca5a5268447432db666cde271886d9c
work_keys_str_mv	AT joaobatistapachecojunior performanceanalysisinthesegmentationofurbanasphaltedroadsinrgbsatelliteimagesusingkmeansandsegnet AT henriquemarianocostadoamaral performanceanalysisinthesegmentationofurbanasphaltedroadsinrgbsatelliteimagesusingkmeansandsegnet
_version_	1718406897430691840

Performance Analysis in the Segmentation of urban asphalted roads in RGB satellite images using K-Means++ and SegNet

Ejemplares similares