MERAL Myanmar Education Research and Learning Portal
Item
{"_buckets": {"deposit": "92606f39-b60b-4125-a51a-a03b6ab48e61"}, "_deposit": {"created_by": 7, "id": "8014", "owner": "7", "owners": [7], "owners_ext": {"displayname": "", "username": ""}, "pid": {"revision_id": 0, "type": "depid", "value": "8014"}, "status": "published"}, "_oai": {"id": "oai:meral.edu.mm:recid/00008014", "sets": ["1596119682566", "1596120465441", "user-ytu"]}, "communities": ["ytu"], "item_1583103067471": {"attribute_name": "Title", "attribute_value_mlt": [{"subitem_1551255647225": "Building footprint extraction in Yangon city from monocular optical satellite image using deep learning", "subitem_1551255648112": "en"}]}, "item_1583103085720": {"attribute_name": "Description", "attribute_value_mlt": [{"interim": "In this research, building footprints in Yangon City, Myanmar are extracted only from monocular optical satellite image by using conditional generative adversarial network (CGAN). Both training dataset and validating dataset are created from GeoEYE image of Dagon Township in Yangon City. Eight training models are created according to the change of values in three training parameters; learning rate, β1 term of Adam, and number of filters in the first convolution layer of the generator and the discriminator. The images of the validating dataset are divided into four image groups; trees, buildings, mixed trees and buildings, and pagodas. The output images of eight trained models are transformed to the vector images and then evaluated by comparing with manually digitized polygons using completeness, correctness and F1 measure. According to the results, by using CGAN, building footprints can be extracted up to 71% of completeness, 81% of correctness and 69% of F1 score from only monocular optical satellite image."}]}, "item_1583103108160": {"attribute_name": "Keywords", "attribute_value_mlt": [{"interim": "GeoEYE monocular RGB image"}, {"interim": "learning rate"}, {"interim": "momentum"}, {"interim": "pix2pix"}, {"interim": "pixel-based evaluation"}]}, "item_1583103120197": {"attribute_name": "Files", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_access", "date": [{"dateType": "Available", "dateValue": "2021-04-02"}], "displaytype": "preview", "download_preview_message": "", "file_order": 0, "filename": "Building footprint extraction in Yangon city from monocular optical satellite image using deep learning.pdf", "filesize": [{"value": "3.4 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensefree": "© 2020 Informa UK Limited, trading as Taylor \u0026 Francis Group", "licensetype": "license_free", "mimetype": "application/pdf", "size": 3400000.0, "url": {"url": "https://meral.edu.mm/record/8014/files/Building footprint extraction in Yangon city from monocular optical satellite image using deep learning.pdf"}, "version_id": "4b38003b-be04-4312-bc08-0a65f5a1c769"}]}, "item_1583103131163": {"attribute_name": "Journal articles", "attribute_value_mlt": [{"subitem_journal_title": "Geocarto International"}]}, "item_1583105942107": {"attribute_name": "Authors", "attribute_value_mlt": [{"subitem_authors": [{"subitem_authors_fullname": "Hein Thura Aung"}, {"subitem_authors_fullname": "Sao Hone Pha"}, {"subitem_authors_fullname": "Takeuchi, Wataru"}]}]}, "item_1583108359239": {"attribute_name": "Upload type", "attribute_value_mlt": [{"interim": "Publication"}]}, "item_1583108428133": {"attribute_name": "Publication type", "attribute_value_mlt": [{"interim": "Journal article"}]}, "item_1583159729339": {"attribute_name": "Publication date", "attribute_value": "2020-03-20"}, "item_1583159847033": {"attribute_name": "Identifier", "attribute_value": "10.1080/10106049.2020.1740949"}, "item_title": "Building footprint extraction in Yangon city from monocular optical satellite image using deep learning", "item_type_id": "21", "owner": "7", "path": ["1596119682566", "1596120465441"], "permalink_uri": "http://hdl.handle.net/20.500.12678/0000008014", "pubdate": {"attribute_name": "Deposited date", "attribute_value": "2021-04-02"}, "publish_date": "2021-04-02", "publish_status": "0", "recid": "8014", "relation": {}, "relation_version_is_last": true, "title": ["Building footprint extraction in Yangon city from monocular optical satellite image using deep learning"], "weko_shared_id": -1}
Building footprint extraction in Yangon city from monocular optical satellite image using deep learning
http://hdl.handle.net/20.500.12678/0000008014
http://hdl.handle.net/20.500.12678/00000080148eadaffc-8c00-4401-a52e-9be4d1500516
92606f39-b60b-4125-a51a-a03b6ab48e61
Name / File | License | Actions |
---|---|---|
Building footprint extraction in Yangon city from monocular optical satellite image using deep learning.pdf (3.4 MB)
|
© 2020 Informa UK Limited, trading as Taylor & Francis Group
|
Publication type | ||||||
---|---|---|---|---|---|---|
Journal article | ||||||
Upload type | ||||||
Publication | ||||||
Title | ||||||
Title | Building footprint extraction in Yangon city from monocular optical satellite image using deep learning | |||||
Language | en | |||||
Publication date | 2020-03-20 | |||||
Authors | ||||||
Hein Thura Aung | ||||||
Sao Hone Pha | ||||||
Takeuchi, Wataru | ||||||
Description | ||||||
In this research, building footprints in Yangon City, Myanmar are extracted only from monocular optical satellite image by using conditional generative adversarial network (CGAN). Both training dataset and validating dataset are created from GeoEYE image of Dagon Township in Yangon City. Eight training models are created according to the change of values in three training parameters; learning rate, β1 term of Adam, and number of filters in the first convolution layer of the generator and the discriminator. The images of the validating dataset are divided into four image groups; trees, buildings, mixed trees and buildings, and pagodas. The output images of eight trained models are transformed to the vector images and then evaluated by comparing with manually digitized polygons using completeness, correctness and F1 measure. According to the results, by using CGAN, building footprints can be extracted up to 71% of completeness, 81% of correctness and 69% of F1 score from only monocular optical satellite image. | ||||||
Keywords | ||||||
GeoEYE monocular RGB image, learning rate, momentum, pix2pix, pixel-based evaluation | ||||||
Identifier | 10.1080/10106049.2020.1740949 | |||||
Journal articles | ||||||
Geocarto International |