A Modular System Based on U-Net for Automatic Building Extraction from very high-resolution satellite images

Recently, convolutional neural networks have grown in popularity in a variety of fields, such as computer vision and audio and text processing. This importance is due to the performance of this type of neural network in the state of the art, and in a wide variety of disciplines. However, the use of...

Full description

Saved in:
Bibliographic Details
Published in:E3S Web of Conferences 2022-01, Vol.351, p.1071
Main Authors: El Asri, Smail Ait, El Adib, Samir, Negabi, Ismail, Raissouni, Naoufal
Format: Article
Language:English
Subjects:
Artificial neural networks
Computer vision
High resolution
Image resolution
Modular systems
Neural networks
Remote sensing
Satellite imagery
Satellites
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c3061-42c6b90b3cd885d5286600f07969cb0dd9e7b3290dc6b97526faa18f310cba113
cites cdi_FETCH-LOGICAL-c3061-42c6b90b3cd885d5286600f07969cb0dd9e7b3290dc6b97526faa18f310cba113
container_end_page
container_issue
container_start_page 1071
container_title E3S Web of Conferences
container_volume 351
creator El Asri, Smail Ait
El Adib, Samir
Negabi, Ismail
Raissouni, Naoufal
description Recently, convolutional neural networks have grown in popularity in a variety of fields, such as computer vision and audio and text processing. This importance is due to the performance of this type of neural network in the state of the art, and in a wide variety of disciplines. However, the use of convolutional neural networks has not been widely used for remote sensing applications until recently. In this paper, we propose a CNN-based system capable of efficiently extracting buildings from very high-resolution satellite images, by combining the performances of the two architectures; U-Net and VGG19, which is obtained by putting two blocks in parallel based mainly on U-Net: The first block is a standard U-Net, and the second is designed by replacing the contraction path of standard U-Net with the pre-trained weights of VGG19.
doi_str_mv 10.1051/e3sconf/202235101071
format article
fullrecord <record><control><sourceid>proquest_doaj_</sourceid><recordid>TN_cdi_doaj_primary_oai_doaj_org_article_eb59a96ef8a34c4397b8a6994cdd4272</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><doaj_id>oai_doaj_org_article_eb59a96ef8a34c4397b8a6994cdd4272</doaj_id><sourcerecordid>2671970549</sourcerecordid><originalsourceid>FETCH-LOGICAL-c3061-42c6b90b3cd885d5286600f07969cb0dd9e7b3290dc6b97526faa18f310cba113</originalsourceid><addsrcrecordid>eNpNkUtPAjEQxzdGEwnyDTw08bwyfWx3ewTigwT1oJybbh-wZKHYdo18excwxtNMZn75z-OfZbcY7jEUeGxp1H7nxgQIoQUGDCW-yAaE8DLHhJHLf_l1NopxAwCYFBUDNsjaCXrxpmtVQO-HmOwWTVW0BvkdWuavNiHnA5p0yW9VajSadk1rmt0KPXynoHRqes4Fv0VfNhzQulmt82Cjb7tTJ6pk27ZJFjVbtbLxJrtyqo129BuH2fLx4WP2nC_enuazySLXFDjOGdG8FlBTbaqqMAWpOAdwUAoudA3GCFvWlAgwR64sCHdK4cpRDLpWGNNhNj_rGq82ch_66eEgvWrkqeDDSqrQn9NaaetCKMGtqxRlmlFR1pXiQjBtDCMl6bXuzlr74D87G5Pc-C7s-vVl_1UsSiiY6Cl2pnTwMQbr_qZikEeb5K9N8r9N9AfQ4YZs</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2671970549</pqid></control><display><type>article</type><title>A Modular System Based on U-Net for Automatic Building Extraction from very high-resolution satellite images</title><source>Publicly Available Content (ProQuest)</source><creator>El Asri, Smail Ait ; El Adib, Samir ; Negabi, Ismail ; Raissouni, Naoufal</creator><contributor>Gerasymov, O. ; Bennani Dosse, S. ; Slimani, K. ; Ait Kbir, M. ; Amrani, A. ; Bourekkadi, S.</contributor><creatorcontrib>El Asri, Smail Ait ; El Adib, Samir ; Negabi, Ismail ; Raissouni, Naoufal ; Gerasymov, O. ; Bennani Dosse, S. ; Slimani, K. ; Ait Kbir, M. ; Amrani, A. ; Bourekkadi, S.</creatorcontrib><description>Recently, convolutional neural networks have grown in popularity in a variety of fields, such as computer vision and audio and text processing. This importance is due to the performance of this type of neural network in the state of the art, and in a wide variety of disciplines. However, the use of convolutional neural networks has not been widely used for remote sensing applications until recently. In this paper, we propose a CNN-based system capable of efficiently extracting buildings from very high-resolution satellite images, by combining the performances of the two architectures; U-Net and VGG19, which is obtained by putting two blocks in parallel based mainly on U-Net: The first block is a standard U-Net, and the second is designed by replacing the contraction path of standard U-Net with the pre-trained weights of VGG19.</description><identifier>ISSN: 2267-1242</identifier><identifier>ISSN: 2555-0403</identifier><identifier>EISSN: 2267-1242</identifier><identifier>DOI: 10.1051/e3sconf/202235101071</identifier><language>eng</language><publisher>Les Ulis: EDP Sciences</publisher><subject>Artificial neural networks ; Computer vision ; High resolution ; Image resolution ; Modular systems ; Neural networks ; Remote sensing ; Satellite imagery ; Satellites</subject><ispartof>E3S Web of Conferences, 2022-01, Vol.351, p.1071</ispartof><rights>2022. This work is licensed under https://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c3061-42c6b90b3cd885d5286600f07969cb0dd9e7b3290dc6b97526faa18f310cba113</citedby><cites>FETCH-LOGICAL-c3061-42c6b90b3cd885d5286600f07969cb0dd9e7b3290dc6b97526faa18f310cba113</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2671970549?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>309,310,314,780,784,789,790,23930,23931,25140,25753,27924,27925,37012,44590</link.rule.ids></links><search><contributor>Gerasymov, O.</contributor><contributor>Bennani Dosse, S.</contributor><contributor>Slimani, K.</contributor><contributor>Ait Kbir, M.</contributor><contributor>Amrani, A.</contributor><contributor>Bourekkadi, S.</contributor><creatorcontrib>El Asri, Smail Ait</creatorcontrib><creatorcontrib>El Adib, Samir</creatorcontrib><creatorcontrib>Negabi, Ismail</creatorcontrib><creatorcontrib>Raissouni, Naoufal</creatorcontrib><title>A Modular System Based on U-Net for Automatic Building Extraction from very high-resolution satellite images</title><title>E3S Web of Conferences</title><description>Recently, convolutional neural networks have grown in popularity in a variety of fields, such as computer vision and audio and text processing. This importance is due to the performance of this type of neural network in the state of the art, and in a wide variety of disciplines. However, the use of convolutional neural networks has not been widely used for remote sensing applications until recently. In this paper, we propose a CNN-based system capable of efficiently extracting buildings from very high-resolution satellite images, by combining the performances of the two architectures; U-Net and VGG19, which is obtained by putting two blocks in parallel based mainly on U-Net: The first block is a standard U-Net, and the second is designed by replacing the contraction path of standard U-Net with the pre-trained weights of VGG19.</description><subject>Artificial neural networks</subject><subject>Computer vision</subject><subject>High resolution</subject><subject>Image resolution</subject><subject>Modular systems</subject><subject>Neural networks</subject><subject>Remote sensing</subject><subject>Satellite imagery</subject><subject>Satellites</subject><issn>2267-1242</issn><issn>2555-0403</issn><issn>2267-1242</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><sourceid>DOA</sourceid><recordid>eNpNkUtPAjEQxzdGEwnyDTw08bwyfWx3ewTigwT1oJybbh-wZKHYdo18excwxtNMZn75z-OfZbcY7jEUeGxp1H7nxgQIoQUGDCW-yAaE8DLHhJHLf_l1NopxAwCYFBUDNsjaCXrxpmtVQO-HmOwWTVW0BvkdWuavNiHnA5p0yW9VajSadk1rmt0KPXynoHRqes4Fv0VfNhzQulmt82Cjb7tTJ6pk27ZJFjVbtbLxJrtyqo129BuH2fLx4WP2nC_enuazySLXFDjOGdG8FlBTbaqqMAWpOAdwUAoudA3GCFvWlAgwR64sCHdK4cpRDLpWGNNhNj_rGq82ch_66eEgvWrkqeDDSqrQn9NaaetCKMGtqxRlmlFR1pXiQjBtDCMl6bXuzlr74D87G5Pc-C7s-vVl_1UsSiiY6Cl2pnTwMQbr_qZikEeb5K9N8r9N9AfQ4YZs</recordid><startdate>20220101</startdate><enddate>20220101</enddate><creator>El Asri, Smail Ait</creator><creator>El Adib, Samir</creator><creator>Negabi, Ismail</creator><creator>Raissouni, Naoufal</creator><general>EDP Sciences</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7ST</scope><scope>8FD</scope><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ATCPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>BHPHI</scope><scope>BKSAR</scope><scope>C1K</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FR3</scope><scope>GNUQQ</scope><scope>H8D</scope><scope>HCIFZ</scope><scope>KR7</scope><scope>L6V</scope><scope>L7M</scope><scope>M7S</scope><scope>PATMY</scope><scope>PCBAR</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><scope>PYCSY</scope><scope>SOI</scope><scope>DOA</scope></search><sort><creationdate>20220101</creationdate><title>A Modular System Based on U-Net for Automatic Building Extraction from very high-resolution satellite images</title><author>El Asri, Smail Ait ; El Adib, Samir ; Negabi, Ismail ; Raissouni, Naoufal</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c3061-42c6b90b3cd885d5286600f07969cb0dd9e7b3290dc6b97526faa18f310cba113</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Artificial neural networks</topic><topic>Computer vision</topic><topic>High resolution</topic><topic>Image resolution</topic><topic>Modular systems</topic><topic>Neural networks</topic><topic>Remote sensing</topic><topic>Satellite imagery</topic><topic>Satellites</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>El Asri, Smail Ait</creatorcontrib><creatorcontrib>El Adib, Samir</creatorcontrib><creatorcontrib>Negabi, Ismail</creatorcontrib><creatorcontrib>Raissouni, Naoufal</creatorcontrib><collection>CrossRef</collection><collection>Environment Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>Agricultural &amp; Environmental Science Collection</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest Natural Science Collection</collection><collection>Earth, Atmospheric &amp; Aquatic Science Collection</collection><collection>Environmental Sciences and Pollution Management</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>Engineering Research Database</collection><collection>ProQuest Central Student</collection><collection>Aerospace Database</collection><collection>SciTech Premium Collection</collection><collection>Civil Engineering Abstracts</collection><collection>ProQuest Engineering Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Engineering Database</collection><collection>Environmental Science Database</collection><collection>Earth, Atmospheric &amp; Aquatic Science Database</collection><collection>Publicly Available Content (ProQuest)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering collection</collection><collection>Environmental Science Collection</collection><collection>Environment Abstracts</collection><collection>Directory of Open Access Journals</collection><jtitle>E3S Web of Conferences</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>El Asri, Smail Ait</au><au>El Adib, Samir</au><au>Negabi, Ismail</au><au>Raissouni, Naoufal</au><au>Gerasymov, O.</au><au>Bennani Dosse, S.</au><au>Slimani, K.</au><au>Ait Kbir, M.</au><au>Amrani, A.</au><au>Bourekkadi, S.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Modular System Based on U-Net for Automatic Building Extraction from very high-resolution satellite images</atitle><jtitle>E3S Web of Conferences</jtitle><date>2022-01-01</date><risdate>2022</risdate><volume>351</volume><spage>1071</spage><pages>1071-</pages><issn>2267-1242</issn><issn>2555-0403</issn><eissn>2267-1242</eissn><abstract>Recently, convolutional neural networks have grown in popularity in a variety of fields, such as computer vision and audio and text processing. This importance is due to the performance of this type of neural network in the state of the art, and in a wide variety of disciplines. However, the use of convolutional neural networks has not been widely used for remote sensing applications until recently. In this paper, we propose a CNN-based system capable of efficiently extracting buildings from very high-resolution satellite images, by combining the performances of the two architectures; U-Net and VGG19, which is obtained by putting two blocks in parallel based mainly on U-Net: The first block is a standard U-Net, and the second is designed by replacing the contraction path of standard U-Net with the pre-trained weights of VGG19.</abstract><cop>Les Ulis</cop><pub>EDP Sciences</pub><doi>10.1051/e3sconf/202235101071</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2267-1242
ispartof E3S Web of Conferences, 2022-01, Vol.351, p.1071
issn 2267-1242
2555-0403
2267-1242
language eng
recordid cdi_doaj_primary_oai_doaj_org_article_eb59a96ef8a34c4397b8a6994cdd4272
source Publicly Available Content (ProQuest)
subjects Artificial neural networks
Computer vision
High resolution
Image resolution
Modular systems
Neural networks
Remote sensing
Satellite imagery
Satellites
title A Modular System Based on U-Net for Automatic Building Extraction from very high-resolution satellite images
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-02T18%3A49%3A30IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_doaj_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Modular%20System%20Based%20on%20U-Net%20for%20Automatic%20Building%20Extraction%20from%20very%20high-resolution%20satellite%20images&rft.jtitle=E3S%20Web%20of%20Conferences&rft.au=El%20Asri,%20Smail%20Ait&rft.date=2022-01-01&rft.volume=351&rft.spage=1071&rft.pages=1071-&rft.issn=2267-1242&rft.eissn=2267-1242&rft_id=info:doi/10.1051/e3sconf/202235101071&rft_dat=%3Cproquest_doaj_%3E2671970549%3C/proquest_doaj_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c3061-42c6b90b3cd885d5286600f07969cb0dd9e7b3290dc6b97526faa18f310cba113%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2671970549&rft_id=info:pmid/&rfr_iscdi=true