Boundary Extraction Based on Dual Stream Deep Learning Model in High Resolution Remote Sensing Images
Boundary extraction in remote sensing has an important task in studies such as environmental observa-tion, risk management and monitoring urban growth. Although significant progress has been made in the different calculation methods proposed, there are issues that need improvement, especially in ter...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Çanakkale Onsekiz Mart University
2021-09-01
|
| Series: | Journal of Advanced Research in Natural and Applied Sciences |
| Subjects: | |
| Online Access: | https://dergipark.org.tr/en/download/article-file/1690319 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832095467219976192 |
|---|---|
| author | Umut Aydar Emin Özgür Avşar Özgün Akçay A. Cumhur Kınacı |
| author_facet | Umut Aydar Emin Özgür Avşar Özgün Akçay A. Cumhur Kınacı |
| author_sort | Umut Aydar |
| collection | DOAJ |
| description | Boundary extraction in remote sensing has an important task in studies such as environmental observa-tion, risk management and monitoring urban growth. Although significant progress has been made in the different calculation methods proposed, there are issues that need improvement, especially in terms of accuracy, efficiency and speed. In this study, dual stream network architecture of three different models that can obtain boundary extraction by using normalized Digital Surface Model (nDSM), Normalized Difference Vegetation Index (NDVI) and Near-Infrared (IR) band as the second stream, was explained. Model I is designed as the original HED, whereas the second stream of Model II, III, and IV use nDSM, nDSM + NDVI and nDSM + NDVI + IR, respectively. Thus, by comparing the models trained based on different data combinations, the contribution of different input data to the success of boundary extraction was revealed. For the training of the models, boundary maps produced from The International Society for Photogrammetry and Remote Sensing (ISPRS) Potsdam data set and input datasets augmented by rotation, mirroring and rotation were used. When the test results obtained from two-stream and multi-data-based models are evaluated, 11% better accuracy has achieved with Model IV compared to the original HED. The outcomes clearly revealed the importance of using multispectral band, height data and vegetation information as input data in boundary extraction beside commonly used RGB images. |
| format | Article |
| id | doaj-art-43d1a31b4c524b8eb9d52cb58fff3e4c |
| institution | Kabale University |
| issn | 2757-5195 |
| language | English |
| publishDate | 2021-09-01 |
| publisher | Çanakkale Onsekiz Mart University |
| record_format | Article |
| series | Journal of Advanced Research in Natural and Applied Sciences |
| spelling | doaj-art-43d1a31b4c524b8eb9d52cb58fff3e4c2025-02-05T17:58:10ZengÇanakkale Onsekiz Mart UniversityJournal of Advanced Research in Natural and Applied Sciences2757-51952021-09-017335836810.28979/jarnas.911130453Boundary Extraction Based on Dual Stream Deep Learning Model in High Resolution Remote Sensing ImagesUmut Aydar0https://orcid.org/0000-0002-3987-6435Emin Özgür Avşar1https://orcid.org/0000-0002-3804-1209Özgün Akçay2https://orcid.org/0000-0003-0474-7518A. Cumhur Kınacı3https://orcid.org/0000-0002-8832-5453ÇANAKKALE ONSEKİZ MART ÜNİVERSİTESİÇANAKKALE ONSEKİZ MART ÜNİVERSİTESİÇANAKKALE ONSEKİZ MART ÜNİVERSİTESİÇANAKKALE ONSEKİZ MART ÜNİVERSİTESİBoundary extraction in remote sensing has an important task in studies such as environmental observa-tion, risk management and monitoring urban growth. Although significant progress has been made in the different calculation methods proposed, there are issues that need improvement, especially in terms of accuracy, efficiency and speed. In this study, dual stream network architecture of three different models that can obtain boundary extraction by using normalized Digital Surface Model (nDSM), Normalized Difference Vegetation Index (NDVI) and Near-Infrared (IR) band as the second stream, was explained. Model I is designed as the original HED, whereas the second stream of Model II, III, and IV use nDSM, nDSM + NDVI and nDSM + NDVI + IR, respectively. Thus, by comparing the models trained based on different data combinations, the contribution of different input data to the success of boundary extraction was revealed. For the training of the models, boundary maps produced from The International Society for Photogrammetry and Remote Sensing (ISPRS) Potsdam data set and input datasets augmented by rotation, mirroring and rotation were used. When the test results obtained from two-stream and multi-data-based models are evaluated, 11% better accuracy has achieved with Model IV compared to the original HED. The outcomes clearly revealed the importance of using multispectral band, height data and vegetation information as input data in boundary extraction beside commonly used RGB images.https://dergipark.org.tr/en/download/article-file/1690319remote sensingphotogrammetryorthophotosdeep learningboundary extraction |
| spellingShingle | Umut Aydar Emin Özgür Avşar Özgün Akçay A. Cumhur Kınacı Boundary Extraction Based on Dual Stream Deep Learning Model in High Resolution Remote Sensing Images Journal of Advanced Research in Natural and Applied Sciences remote sensing photogrammetry orthophotos deep learning boundary extraction |
| title | Boundary Extraction Based on Dual Stream Deep Learning Model in High Resolution Remote Sensing Images |
| title_full | Boundary Extraction Based on Dual Stream Deep Learning Model in High Resolution Remote Sensing Images |
| title_fullStr | Boundary Extraction Based on Dual Stream Deep Learning Model in High Resolution Remote Sensing Images |
| title_full_unstemmed | Boundary Extraction Based on Dual Stream Deep Learning Model in High Resolution Remote Sensing Images |
| title_short | Boundary Extraction Based on Dual Stream Deep Learning Model in High Resolution Remote Sensing Images |
| title_sort | boundary extraction based on dual stream deep learning model in high resolution remote sensing images |
| topic | remote sensing photogrammetry orthophotos deep learning boundary extraction |
| url | https://dergipark.org.tr/en/download/article-file/1690319 |
| work_keys_str_mv | AT umutaydar boundaryextractionbasedondualstreamdeeplearningmodelinhighresolutionremotesensingimages AT eminozguravsar boundaryextractionbasedondualstreamdeeplearningmodelinhighresolutionremotesensingimages AT ozgunakcay boundaryextractionbasedondualstreamdeeplearningmodelinhighresolutionremotesensingimages AT acumhurkınacı boundaryextractionbasedondualstreamdeeplearningmodelinhighresolutionremotesensingimages |