No Cover Image

Journal article 381 views 64 downloads

Manifold Explorer: Satellite Image Labelling and Clustering Tool with Using Deep Convolutional Autoencoders

Tulsi Patel, Mark Jones Orcid Logo, Thomas Redfern

Algorithms, Volume: 16, Issue: 10, Start page: 469

Swansea University Authors: Tulsi Patel, Mark Jones Orcid Logo

  • 64669.VOR.pdf

    PDF | Version of Record

    © 2023 by the authors. Licensee MDPI, Basel, Switzerland. Distributed under the terms of a Creative Commons Attribution 4.0 License (CC BY 4.0).

    Download (11.65MB)

Check full text

DOI (Published version): 10.3390/a16100469

Abstract

We present a novel approach to providing greater insight into the characteristics of an unlabelled dataset, increasing the efficiency with which labelled datasets can be created. We leverage dimension-reduction techniques in combination with autoencoders to create an efficient feature representation...

Full description

Published in: Algorithms
ISSN: 1999-4893
Published: MDPI AG 2023
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa64669
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2023-10-06T12:38:19Z
last_indexed 2023-10-06T12:38:19Z
id cronfa64669
recordtype SURis
fullrecord <?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>64669</id><entry>2023-10-06</entry><title>Manifold Explorer: Satellite Image Labelling and Clustering Tool with Using Deep Convolutional Autoencoders</title><swanseaauthors><author><sid>b7d4b35b18e3f66ce9aa77fb9280aa2f</sid><firstname>Tulsi</firstname><surname>Patel</surname><name>Tulsi Patel</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>2e1030b6e14fc9debd5d5ae7cc335562</sid><ORCID>0000-0001-8991-1190</ORCID><firstname>Mark</firstname><surname>Jones</surname><name>Mark Jones</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2023-10-06</date><deptcode>MACS</deptcode><abstract>We present a novel approach to providing greater insight into the characteristics of an unlabelled dataset, increasing the efficiency with which labelled datasets can be created. We leverage dimension-reduction techniques in combination with autoencoders to create an efficient feature representation for image tiles derived from remote sensing satellite imagery. The proposed methodology consists of two main stages. Firstly, an autoencoder network is utilised to reduce the high-dimensional image tile data into a compact and expressive latentfeature representation. Subsequently, features are further reduced to a two-dimensional embedding space using the manifold learning algorithm Uniform Manifold Approximation and Projection (UMAP) and t-distributed Stochastic Neighbour Embedding (t-SNE). This step enables the visualization of the image tile clusters in a 2D plot, providing an intuitive and interactive representation that can be used to aid rapid and geographically distributed image labelling. To facilitate the labelling process, our approach allows users to interact with the 2D visualization and label clusters based on their domain knowledge. In cases where certain classes are not effectively separated, users can re-apply dimension reduction to interactively refine subsets of clusters and achieve better class separation, enabling a comprehensively labelled dataset. We evaluate the proposed approach on real-world remote sensing satellite image datasets and demonstrate its effectiveness in achieving accurate and efficient image tile clustering and labelling. Users actively participate in the labelling process through our interactive approach, leading to enhanced relevance of the labelled data, by allowing domain experts to contribute their expertise and enrich the dataset for improved downstream analysis and applications.</abstract><type>Journal Article</type><journal>Algorithms</journal><volume>16</volume><journalNumber>10</journalNumber><paginationStart>469</paginationStart><paginationEnd/><publisher>MDPI AG</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic>1999-4893</issnElectronic><keywords>Manifold exploration, dimension reduction, labelling samples, remote sensing data</keywords><publishedDay>4</publishedDay><publishedMonth>10</publishedMonth><publishedYear>2023</publishedYear><publishedDate>2023-10-04</publishedDate><doi>10.3390/a16100469</doi><url>http://dx.doi.org/10.3390/a16100469</url><notes/><college>COLLEGE NANME</college><department>Mathematics and Computer Science School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MACS</DepartmentCode><institution>Swansea University</institution><apcterm>Other</apcterm><funders>EPSRC (EP/S021892/1)</funders><projectreference/><lastEdited>2024-07-11T15:33:28.2629924</lastEdited><Created>2023-10-06T13:33:45.2685973</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Tulsi</firstname><surname>Patel</surname><order>1</order></author><author><firstname>Mark</firstname><surname>Jones</surname><orcid>0000-0001-8991-1190</orcid><order>2</order></author><author><firstname>Thomas</firstname><surname>Redfern</surname><order>3</order></author></authors><documents><document><filename>64669__28943__cdeb6c75f3f14736bbfe1f3d39be92a8.pdf</filename><originalFilename>64669.VOR.pdf</originalFilename><uploaded>2023-11-06T15:39:01.8405329</uploaded><type>Output</type><contentLength>12219305</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>© 2023 by the authors. Licensee MDPI, Basel, Switzerland. Distributed under the terms of a Creative Commons Attribution 4.0 License (CC BY 4.0).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling v2 64669 2023-10-06 Manifold Explorer: Satellite Image Labelling and Clustering Tool with Using Deep Convolutional Autoencoders b7d4b35b18e3f66ce9aa77fb9280aa2f Tulsi Patel Tulsi Patel true false 2e1030b6e14fc9debd5d5ae7cc335562 0000-0001-8991-1190 Mark Jones Mark Jones true false 2023-10-06 MACS We present a novel approach to providing greater insight into the characteristics of an unlabelled dataset, increasing the efficiency with which labelled datasets can be created. We leverage dimension-reduction techniques in combination with autoencoders to create an efficient feature representation for image tiles derived from remote sensing satellite imagery. The proposed methodology consists of two main stages. Firstly, an autoencoder network is utilised to reduce the high-dimensional image tile data into a compact and expressive latentfeature representation. Subsequently, features are further reduced to a two-dimensional embedding space using the manifold learning algorithm Uniform Manifold Approximation and Projection (UMAP) and t-distributed Stochastic Neighbour Embedding (t-SNE). This step enables the visualization of the image tile clusters in a 2D plot, providing an intuitive and interactive representation that can be used to aid rapid and geographically distributed image labelling. To facilitate the labelling process, our approach allows users to interact with the 2D visualization and label clusters based on their domain knowledge. In cases where certain classes are not effectively separated, users can re-apply dimension reduction to interactively refine subsets of clusters and achieve better class separation, enabling a comprehensively labelled dataset. We evaluate the proposed approach on real-world remote sensing satellite image datasets and demonstrate its effectiveness in achieving accurate and efficient image tile clustering and labelling. Users actively participate in the labelling process through our interactive approach, leading to enhanced relevance of the labelled data, by allowing domain experts to contribute their expertise and enrich the dataset for improved downstream analysis and applications. Journal Article Algorithms 16 10 469 MDPI AG 1999-4893 Manifold exploration, dimension reduction, labelling samples, remote sensing data 4 10 2023 2023-10-04 10.3390/a16100469 http://dx.doi.org/10.3390/a16100469 COLLEGE NANME Mathematics and Computer Science School COLLEGE CODE MACS Swansea University Other EPSRC (EP/S021892/1) 2024-07-11T15:33:28.2629924 2023-10-06T13:33:45.2685973 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Tulsi Patel 1 Mark Jones 0000-0001-8991-1190 2 Thomas Redfern 3 64669__28943__cdeb6c75f3f14736bbfe1f3d39be92a8.pdf 64669.VOR.pdf 2023-11-06T15:39:01.8405329 Output 12219305 application/pdf Version of Record true © 2023 by the authors. Licensee MDPI, Basel, Switzerland. Distributed under the terms of a Creative Commons Attribution 4.0 License (CC BY 4.0). true eng https://creativecommons.org/licenses/by/4.0/
title Manifold Explorer: Satellite Image Labelling and Clustering Tool with Using Deep Convolutional Autoencoders
spellingShingle Manifold Explorer: Satellite Image Labelling and Clustering Tool with Using Deep Convolutional Autoencoders
Tulsi Patel
Mark Jones
title_short Manifold Explorer: Satellite Image Labelling and Clustering Tool with Using Deep Convolutional Autoencoders
title_full Manifold Explorer: Satellite Image Labelling and Clustering Tool with Using Deep Convolutional Autoencoders
title_fullStr Manifold Explorer: Satellite Image Labelling and Clustering Tool with Using Deep Convolutional Autoencoders
title_full_unstemmed Manifold Explorer: Satellite Image Labelling and Clustering Tool with Using Deep Convolutional Autoencoders
title_sort Manifold Explorer: Satellite Image Labelling and Clustering Tool with Using Deep Convolutional Autoencoders
author_id_str_mv b7d4b35b18e3f66ce9aa77fb9280aa2f
2e1030b6e14fc9debd5d5ae7cc335562
author_id_fullname_str_mv b7d4b35b18e3f66ce9aa77fb9280aa2f_***_Tulsi Patel
2e1030b6e14fc9debd5d5ae7cc335562_***_Mark Jones
author Tulsi Patel
Mark Jones
author2 Tulsi Patel
Mark Jones
Thomas Redfern
format Journal article
container_title Algorithms
container_volume 16
container_issue 10
container_start_page 469
publishDate 2023
institution Swansea University
issn 1999-4893
doi_str_mv 10.3390/a16100469
publisher MDPI AG
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
url http://dx.doi.org/10.3390/a16100469
document_store_str 1
active_str 0
description We present a novel approach to providing greater insight into the characteristics of an unlabelled dataset, increasing the efficiency with which labelled datasets can be created. We leverage dimension-reduction techniques in combination with autoencoders to create an efficient feature representation for image tiles derived from remote sensing satellite imagery. The proposed methodology consists of two main stages. Firstly, an autoencoder network is utilised to reduce the high-dimensional image tile data into a compact and expressive latentfeature representation. Subsequently, features are further reduced to a two-dimensional embedding space using the manifold learning algorithm Uniform Manifold Approximation and Projection (UMAP) and t-distributed Stochastic Neighbour Embedding (t-SNE). This step enables the visualization of the image tile clusters in a 2D plot, providing an intuitive and interactive representation that can be used to aid rapid and geographically distributed image labelling. To facilitate the labelling process, our approach allows users to interact with the 2D visualization and label clusters based on their domain knowledge. In cases where certain classes are not effectively separated, users can re-apply dimension reduction to interactively refine subsets of clusters and achieve better class separation, enabling a comprehensively labelled dataset. We evaluate the proposed approach on real-world remote sensing satellite image datasets and demonstrate its effectiveness in achieving accurate and efficient image tile clustering and labelling. Users actively participate in the labelling process through our interactive approach, leading to enhanced relevance of the labelled data, by allowing domain experts to contribute their expertise and enrich the dataset for improved downstream analysis and applications.
published_date 2023-10-04T15:33:27Z
_version_ 1804293538918170624
score 11.035634

Similar Items