Supervised Multi-Regional Segmentation Machine Learning Architecture for Digital Twin Applications in Coastal Regions ...
This study explores the use of a digital twin model and deep learning method to build a global terrain and altitude map based on USGS information. The goal is to artistically represent various landforms while incorporating precise elevation modifications in the terrain map and encoding land height i...
Main Authors: | , , , , , , |
---|---|
Format: | Report |
Language: | unknown |
Published: |
arXiv
2023
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2305.14460 https://arxiv.org/abs/2305.14460 |
id |
ftdatacite:10.48550/arxiv.2305.14460 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2305.14460 2023-06-11T04:17:24+02:00 Supervised Multi-Regional Segmentation Machine Learning Architecture for Digital Twin Applications in Coastal Regions ... Ahmadi, Mohsen Lonbar, Ahmad Gholizadeh Nouri, Mohammadsadegh Javidi, Amir Sharifzadeh Beris, Ali Tarlani Sharifi, Abbas Salimi-Tarazouj, Ali 2023 https://dx.doi.org/10.48550/arxiv.2305.14460 https://arxiv.org/abs/2305.14460 unknown arXiv arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ Image and Video Processing eess.IV FOS Electrical engineering, electronic engineering, information engineering Preprint CreativeWork article Article 2023 ftdatacite https://doi.org/10.48550/arxiv.2305.14460 2023-06-01T12:06:17Z This study explores the use of a digital twin model and deep learning method to build a global terrain and altitude map based on USGS information. The goal is to artistically represent various landforms while incorporating precise elevation modifications in the terrain map and encoding land height in the altitude map. A random selection of 5000 segments from the worldwide map guarantees the inclusion of significant characteristics in the subsets, with rescaling according to latitude accounting for distortions caused by map projection. The process of generating segmentation maps involves using unsupervised clustering and classification methods, segmenting the terrain into seven groups: Water, Grassland, Forest, Hills, Desert, Mountain, and Tundra. Each group is assigned a unique color, and median filtering is used to improve map characteristics. Random parameters are added to provide diversity and avoid duplication in overlapping image sets. The U-Net network is deployed for the segmentation task, with ... Report Tundra DataCite Metadata Store (German National Library of Science and Technology) |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
unknown |
topic |
Image and Video Processing eess.IV FOS Electrical engineering, electronic engineering, information engineering |
spellingShingle |
Image and Video Processing eess.IV FOS Electrical engineering, electronic engineering, information engineering Ahmadi, Mohsen Lonbar, Ahmad Gholizadeh Nouri, Mohammadsadegh Javidi, Amir Sharifzadeh Beris, Ali Tarlani Sharifi, Abbas Salimi-Tarazouj, Ali Supervised Multi-Regional Segmentation Machine Learning Architecture for Digital Twin Applications in Coastal Regions ... |
topic_facet |
Image and Video Processing eess.IV FOS Electrical engineering, electronic engineering, information engineering |
description |
This study explores the use of a digital twin model and deep learning method to build a global terrain and altitude map based on USGS information. The goal is to artistically represent various landforms while incorporating precise elevation modifications in the terrain map and encoding land height in the altitude map. A random selection of 5000 segments from the worldwide map guarantees the inclusion of significant characteristics in the subsets, with rescaling according to latitude accounting for distortions caused by map projection. The process of generating segmentation maps involves using unsupervised clustering and classification methods, segmenting the terrain into seven groups: Water, Grassland, Forest, Hills, Desert, Mountain, and Tundra. Each group is assigned a unique color, and median filtering is used to improve map characteristics. Random parameters are added to provide diversity and avoid duplication in overlapping image sets. The U-Net network is deployed for the segmentation task, with ... |
format |
Report |
author |
Ahmadi, Mohsen Lonbar, Ahmad Gholizadeh Nouri, Mohammadsadegh Javidi, Amir Sharifzadeh Beris, Ali Tarlani Sharifi, Abbas Salimi-Tarazouj, Ali |
author_facet |
Ahmadi, Mohsen Lonbar, Ahmad Gholizadeh Nouri, Mohammadsadegh Javidi, Amir Sharifzadeh Beris, Ali Tarlani Sharifi, Abbas Salimi-Tarazouj, Ali |
author_sort |
Ahmadi, Mohsen |
title |
Supervised Multi-Regional Segmentation Machine Learning Architecture for Digital Twin Applications in Coastal Regions ... |
title_short |
Supervised Multi-Regional Segmentation Machine Learning Architecture for Digital Twin Applications in Coastal Regions ... |
title_full |
Supervised Multi-Regional Segmentation Machine Learning Architecture for Digital Twin Applications in Coastal Regions ... |
title_fullStr |
Supervised Multi-Regional Segmentation Machine Learning Architecture for Digital Twin Applications in Coastal Regions ... |
title_full_unstemmed |
Supervised Multi-Regional Segmentation Machine Learning Architecture for Digital Twin Applications in Coastal Regions ... |
title_sort |
supervised multi-regional segmentation machine learning architecture for digital twin applications in coastal regions ... |
publisher |
arXiv |
publishDate |
2023 |
url |
https://dx.doi.org/10.48550/arxiv.2305.14460 https://arxiv.org/abs/2305.14460 |
genre |
Tundra |
genre_facet |
Tundra |
op_rights |
arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
op_doi |
https://doi.org/10.48550/arxiv.2305.14460 |
_version_ |
1768376549463031808 |