No Cover Image

Conference Paper/Proceeding/Abstract 226 views

Farm Detection based on Deep Convolutional Neural Nets and Semi-supervised Green Texture Detection using VIS-NIR Satellite Image

Sara Sharifzadeh Orcid Logo, Jagati Tata, Bo Tan

Proceedings of the 8th International Conference on Data Science, Technology and Applications

Swansea University Author: Sara Sharifzadeh Orcid Logo

Full text not available from this repository: check for access using links below.

Check full text

DOI (Published version): 10.5220/0007954901000108

Abstract

Farm detection using low resolution satellite images is an important topic in digital agriculture. However, it has not received enough attention compared to high-resolution images. Although high resolution images are more efficient for detection of land cover components, the analysis of low-resoluti...

Full description

Published in: Proceedings of the 8th International Conference on Data Science, Technology and Applications
ISBN: 978-989-758-377-3
ISSN: 2184-285X
Published: SCITEPRESS - Science and Technology Publications 2019
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa65605
first_indexed 2024-03-23T15:11:47Z
last_indexed 2024-11-25T14:16:27Z
id cronfa65605
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2024-03-23T15:12:38.5298426</datestamp><bib-version>v2</bib-version><id>65605</id><entry>2024-02-09</entry><title>Farm Detection based on Deep Convolutional Neural Nets and Semi-supervised Green Texture Detection using VIS-NIR Satellite Image</title><swanseaauthors><author><sid>a4e15f304398ecee3f28c7faec69c1b0</sid><ORCID>0000-0003-4621-2917</ORCID><firstname>Sara</firstname><surname>Sharifzadeh</surname><name>Sara Sharifzadeh</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2024-02-09</date><deptcode>MACS</deptcode><abstract>Farm detection using low resolution satellite images is an important topic in digital agriculture. However, it has not received enough attention compared to high-resolution images. Although high resolution images are more efficient for detection of land cover components, the analysis of low-resolution images are yet important due to the low-resolution repositories of the past satellite images used for timeseries analysis, free availability and economic concerns. The current paper addresses the problem of farm detection using low resolution satellite images. In digital agriculture, farm detection has significant role for key applications such as crop yield monitoring. Two main categories of object detection strategies are studied and compared in this paper; First, a two-step semi-supervised methodology is developed using traditional manual feature extraction and modelling techniques; the developed methodology uses the Normalized Difference Moisture Index (NDMI), Grey Level Co-occurren ce Matrix (GLCM), 2-D Discrete Cosine Transform (DCT) and morphological features and Support Vector Machine (SVM) for classifier modelling. In the second strategy, high-level features learnt from the massive filter banks of deep Convolutional Neural Networks (CNNs) are utilised. Transfer learning strategies are employed for pretrained Visual Geometry Group Network (VGG-16) networks. Results show the superiority of the high-level features for classification of farm regions.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>Proceedings of the 8th International Conference on Data Science, Technology and Applications</journal><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher>SCITEPRESS - Science and Technology Publications</publisher><placeOfPublication/><isbnPrint>978-989-758-377-3</isbnPrint><isbnElectronic/><issnPrint>2184-285X</issnPrint><issnElectronic/><keywords>Classification, Supervised Feature Extraction, Convolutional Neural Nets (CNNs), Satellite Image, Digital Agriculture</keywords><publishedDay>1</publishedDay><publishedMonth>1</publishedMonth><publishedYear>2019</publishedYear><publishedDate>2019-01-01</publishedDate><doi>10.5220/0007954901000108</doi><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/><funders/><projectreference/><lastEdited>2024-03-23T15:12:38.5298426</lastEdited><Created>2024-02-09T01:16:19.5388472</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>Sara</firstname><surname>Sharifzadeh</surname><orcid>0000-0003-4621-2917</orcid><order>1</order></author><author><firstname>Jagati</firstname><surname>Tata</surname><order>2</order></author><author><firstname>Bo</firstname><surname>Tan</surname><order>3</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling 2024-03-23T15:12:38.5298426 v2 65605 2024-02-09 Farm Detection based on Deep Convolutional Neural Nets and Semi-supervised Green Texture Detection using VIS-NIR Satellite Image a4e15f304398ecee3f28c7faec69c1b0 0000-0003-4621-2917 Sara Sharifzadeh Sara Sharifzadeh true false 2024-02-09 MACS Farm detection using low resolution satellite images is an important topic in digital agriculture. However, it has not received enough attention compared to high-resolution images. Although high resolution images are more efficient for detection of land cover components, the analysis of low-resolution images are yet important due to the low-resolution repositories of the past satellite images used for timeseries analysis, free availability and economic concerns. The current paper addresses the problem of farm detection using low resolution satellite images. In digital agriculture, farm detection has significant role for key applications such as crop yield monitoring. Two main categories of object detection strategies are studied and compared in this paper; First, a two-step semi-supervised methodology is developed using traditional manual feature extraction and modelling techniques; the developed methodology uses the Normalized Difference Moisture Index (NDMI), Grey Level Co-occurren ce Matrix (GLCM), 2-D Discrete Cosine Transform (DCT) and morphological features and Support Vector Machine (SVM) for classifier modelling. In the second strategy, high-level features learnt from the massive filter banks of deep Convolutional Neural Networks (CNNs) are utilised. Transfer learning strategies are employed for pretrained Visual Geometry Group Network (VGG-16) networks. Results show the superiority of the high-level features for classification of farm regions. Conference Paper/Proceeding/Abstract Proceedings of the 8th International Conference on Data Science, Technology and Applications SCITEPRESS - Science and Technology Publications 978-989-758-377-3 2184-285X Classification, Supervised Feature Extraction, Convolutional Neural Nets (CNNs), Satellite Image, Digital Agriculture 1 1 2019 2019-01-01 10.5220/0007954901000108 COLLEGE NANME Mathematics and Computer Science School COLLEGE CODE MACS Swansea University 2024-03-23T15:12:38.5298426 2024-02-09T01:16:19.5388472 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Sara Sharifzadeh 0000-0003-4621-2917 1 Jagati Tata 2 Bo Tan 3
title Farm Detection based on Deep Convolutional Neural Nets and Semi-supervised Green Texture Detection using VIS-NIR Satellite Image
spellingShingle Farm Detection based on Deep Convolutional Neural Nets and Semi-supervised Green Texture Detection using VIS-NIR Satellite Image
Sara Sharifzadeh
title_short Farm Detection based on Deep Convolutional Neural Nets and Semi-supervised Green Texture Detection using VIS-NIR Satellite Image
title_full Farm Detection based on Deep Convolutional Neural Nets and Semi-supervised Green Texture Detection using VIS-NIR Satellite Image
title_fullStr Farm Detection based on Deep Convolutional Neural Nets and Semi-supervised Green Texture Detection using VIS-NIR Satellite Image
title_full_unstemmed Farm Detection based on Deep Convolutional Neural Nets and Semi-supervised Green Texture Detection using VIS-NIR Satellite Image
title_sort Farm Detection based on Deep Convolutional Neural Nets and Semi-supervised Green Texture Detection using VIS-NIR Satellite Image
author_id_str_mv a4e15f304398ecee3f28c7faec69c1b0
author_id_fullname_str_mv a4e15f304398ecee3f28c7faec69c1b0_***_Sara Sharifzadeh
author Sara Sharifzadeh
author2 Sara Sharifzadeh
Jagati Tata
Bo Tan
format Conference Paper/Proceeding/Abstract
container_title Proceedings of the 8th International Conference on Data Science, Technology and Applications
publishDate 2019
institution Swansea University
isbn 978-989-758-377-3
issn 2184-285X
doi_str_mv 10.5220/0007954901000108
publisher SCITEPRESS - Science and Technology Publications
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
document_store_str 0
active_str 0
description Farm detection using low resolution satellite images is an important topic in digital agriculture. However, it has not received enough attention compared to high-resolution images. Although high resolution images are more efficient for detection of land cover components, the analysis of low-resolution images are yet important due to the low-resolution repositories of the past satellite images used for timeseries analysis, free availability and economic concerns. The current paper addresses the problem of farm detection using low resolution satellite images. In digital agriculture, farm detection has significant role for key applications such as crop yield monitoring. Two main categories of object detection strategies are studied and compared in this paper; First, a two-step semi-supervised methodology is developed using traditional manual feature extraction and modelling techniques; the developed methodology uses the Normalized Difference Moisture Index (NDMI), Grey Level Co-occurren ce Matrix (GLCM), 2-D Discrete Cosine Transform (DCT) and morphological features and Support Vector Machine (SVM) for classifier modelling. In the second strategy, high-level features learnt from the massive filter banks of deep Convolutional Neural Networks (CNNs) are utilised. Transfer learning strategies are employed for pretrained Visual Geometry Group Network (VGG-16) networks. Results show the superiority of the high-level features for classification of farm regions.
published_date 2019-01-01T02:39:55Z
_version_ 1821280876879675392
score 11.047306

Similar Items