Validating a window view simulation engine based on open data and open source using semantic segmentation

The visual access to urban green spaces through window views plays a key role in increasing well-being, particularly for those with limited mobility. This study verifies a window view simulation engine around the Green Window View Index (GWVI) that combines open source approaches with open geospatia...

Full description

Saved in:
Bibliographic Details
Main Authors: A.-M. Bolte, T. Kistemann, T. Kötter, Y. Dehbi
Format: Article
Language:English
Published: Copernicus Publications 2025-07-01
Series:The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/219/2025/isprs-archives-XLVIII-G-2025-219-2025.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849245952748027904
author A.-M. Bolte
T. Kistemann
T. Kistemann
T. Kötter
Y. Dehbi
author_facet A.-M. Bolte
T. Kistemann
T. Kistemann
T. Kötter
Y. Dehbi
author_sort A.-M. Bolte
collection DOAJ
description The visual access to urban green spaces through window views plays a key role in increasing well-being, particularly for those with limited mobility. This study verifies a window view simulation engine around the Green Window View Index (GWVI) that combines open source approaches with open geospatial data. Using a pretrained DeepLab V3+ model on Cityscapes data set for semantic segmentation, the study compares the accuracy of simulated window views to photorealistic semantic segmentations. A total of 40 window views were examined, with 0.1 m and 2.0 m distance to the window. The validation metrics consist of overall accuracy (OAcc), mean accuracy (mAcc), mean intersection over union (mIoU), and individual IoU values for vegetation, sky, and buildings. The statistics show an mIoU of 0.53, with class-specific IoU values of 0.52 for vegetation, 0.64 for the sky, and 0.43 for buildings, an OAcc of 0.68, and an mAcc of 0.74. The approach has a low variance in visibility values, with a minor underestimating of vegetation (−6%), and an overestimation of sky (+5%) and buildings (+3%). These findings indicate that the simulation engine performs well, outlining its potential for analyzing window views in a variety of urban scenarios. Future large-scale crowdsourcing experiments are recommended to statistically support these findings.
format Article
id doaj-art-4d5da5eb55204fc59dc7b168f29c0a9d
institution Kabale University
issn 1682-1750
2194-9034
language English
publishDate 2025-07-01
publisher Copernicus Publications
record_format Article
series The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
spelling doaj-art-4d5da5eb55204fc59dc7b168f29c0a9d2025-08-20T03:58:40ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342025-07-01XLVIII-G-202521922410.5194/isprs-archives-XLVIII-G-2025-219-2025Validating a window view simulation engine based on open data and open source using semantic segmentationA.-M. Bolte0T. Kistemann1T. Kistemann2T. Kötter3Y. Dehbi4Institute of Geodesy and Geoinformation, University of Bonn, GermanyInstitute for Hygiene & Public Health, GeoHealth, University Hospital Bonn, GermanyDepartment of Geography, University of Bonn, GermanyInstitute of Geodesy and Geoinformation, University of Bonn, GermanyComputational Methods Lab, HafenCity University Hamburg, GermanyThe visual access to urban green spaces through window views plays a key role in increasing well-being, particularly for those with limited mobility. This study verifies a window view simulation engine around the Green Window View Index (GWVI) that combines open source approaches with open geospatial data. Using a pretrained DeepLab V3+ model on Cityscapes data set for semantic segmentation, the study compares the accuracy of simulated window views to photorealistic semantic segmentations. A total of 40 window views were examined, with 0.1 m and 2.0 m distance to the window. The validation metrics consist of overall accuracy (OAcc), mean accuracy (mAcc), mean intersection over union (mIoU), and individual IoU values for vegetation, sky, and buildings. The statistics show an mIoU of 0.53, with class-specific IoU values of 0.52 for vegetation, 0.64 for the sky, and 0.43 for buildings, an OAcc of 0.68, and an mAcc of 0.74. The approach has a low variance in visibility values, with a minor underestimating of vegetation (−6%), and an overestimation of sky (+5%) and buildings (+3%). These findings indicate that the simulation engine performs well, outlining its potential for analyzing window views in a variety of urban scenarios. Future large-scale crowdsourcing experiments are recommended to statistically support these findings.https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/219/2025/isprs-archives-XLVIII-G-2025-219-2025.pdf
spellingShingle A.-M. Bolte
T. Kistemann
T. Kistemann
T. Kötter
Y. Dehbi
Validating a window view simulation engine based on open data and open source using semantic segmentation
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
title Validating a window view simulation engine based on open data and open source using semantic segmentation
title_full Validating a window view simulation engine based on open data and open source using semantic segmentation
title_fullStr Validating a window view simulation engine based on open data and open source using semantic segmentation
title_full_unstemmed Validating a window view simulation engine based on open data and open source using semantic segmentation
title_short Validating a window view simulation engine based on open data and open source using semantic segmentation
title_sort validating a window view simulation engine based on open data and open source using semantic segmentation
url https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/219/2025/isprs-archives-XLVIII-G-2025-219-2025.pdf
work_keys_str_mv AT ambolte validatingawindowviewsimulationenginebasedonopendataandopensourceusingsemanticsegmentation
AT tkistemann validatingawindowviewsimulationenginebasedonopendataandopensourceusingsemanticsegmentation
AT tkistemann validatingawindowviewsimulationenginebasedonopendataandopensourceusingsemanticsegmentation
AT tkotter validatingawindowviewsimulationenginebasedonopendataandopensourceusingsemanticsegmentation
AT ydehbi validatingawindowviewsimulationenginebasedonopendataandopensourceusingsemanticsegmentation