Geographical Information System Enhancement Using Active Learning-Enhanced Semantic Segmentation
Images captured by drones are increasingly used in various fields, including geographic information management. This study evaluates a procedure that incorporates active learning semantic segmentation for verifying the building registration ledger. Several semantic segmentation techniques were evalu...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-10-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/13/20/11254 |
_version_ | 1797447135598215168 |
---|---|
author | Sungkwan Youm Sunghyun Go |
author_facet | Sungkwan Youm Sunghyun Go |
author_sort | Sungkwan Youm |
collection | DOAJ |
description | Images captured by drones are increasingly used in various fields, including geographic information management. This study evaluates a procedure that incorporates active learning semantic segmentation for verifying the building registration ledger. Several semantic segmentation techniques were evaluated to extract building information, with ResNet identified as the most effective method for accurately recognizing building roofs. Using active learning, the training data were refined by removing instances with low similarity, leading to improved network performance of the model. The procedure was demonstrated to identify discrepancies between the building information system and the inferred label images, as well as to detect labeling errors on a training dataset. Through this research, the geographic information system dataset is enhanced with minimal human oversight, offering significant potential for urban planning and building detection advancements. |
first_indexed | 2024-03-09T13:50:29Z |
format | Article |
id | doaj.art-cb8d398736ab48a498251e66a4522044 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-09T13:50:29Z |
publishDate | 2023-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-cb8d398736ab48a498251e66a45220442023-11-30T20:51:28ZengMDPI AGApplied Sciences2076-34172023-10-0113201125410.3390/app132011254Geographical Information System Enhancement Using Active Learning-Enhanced Semantic SegmentationSungkwan Youm0Sunghyun Go1Department of Information & Communication Engineering, Wonkwang University, Iksan 54538, Republic of KoreaDepartment of Computer Software Engineering, Wonkwang University, Iksan 54538, Republic of KoreaImages captured by drones are increasingly used in various fields, including geographic information management. This study evaluates a procedure that incorporates active learning semantic segmentation for verifying the building registration ledger. Several semantic segmentation techniques were evaluated to extract building information, with ResNet identified as the most effective method for accurately recognizing building roofs. Using active learning, the training data were refined by removing instances with low similarity, leading to improved network performance of the model. The procedure was demonstrated to identify discrepancies between the building information system and the inferred label images, as well as to detect labeling errors on a training dataset. Through this research, the geographic information system dataset is enhanced with minimal human oversight, offering significant potential for urban planning and building detection advancements.https://www.mdpi.com/2076-3417/13/20/11254semantic segmentationUAVResNetmapbuildingactive learning |
spellingShingle | Sungkwan Youm Sunghyun Go Geographical Information System Enhancement Using Active Learning-Enhanced Semantic Segmentation Applied Sciences semantic segmentation UAV ResNet map building active learning |
title | Geographical Information System Enhancement Using Active Learning-Enhanced Semantic Segmentation |
title_full | Geographical Information System Enhancement Using Active Learning-Enhanced Semantic Segmentation |
title_fullStr | Geographical Information System Enhancement Using Active Learning-Enhanced Semantic Segmentation |
title_full_unstemmed | Geographical Information System Enhancement Using Active Learning-Enhanced Semantic Segmentation |
title_short | Geographical Information System Enhancement Using Active Learning-Enhanced Semantic Segmentation |
title_sort | geographical information system enhancement using active learning enhanced semantic segmentation |
topic | semantic segmentation UAV ResNet map building active learning |
url | https://www.mdpi.com/2076-3417/13/20/11254 |
work_keys_str_mv | AT sungkwanyoum geographicalinformationsystemenhancementusingactivelearningenhancedsemanticsegmentation AT sunghyungo geographicalinformationsystemenhancementusingactivelearningenhancedsemanticsegmentation |