Irregular Facades: A Dataset for Semantic Segmentation of the Free Facade of Modern Buildings

Semantic segmentation of building facades has enabled much intelligent support for architectural research and practice in the last decade. Faced with the free facade of modern buildings, however, the accuracy of segmentation decreased significantly, partly due to its low regularity of composition. T...

Full description

Saved in:
Bibliographic Details
Main Authors: Junjie Wei, Yuexia Hu, Si Zhang, Shuyu Liu
Format: Article
Language:English
Published: MDPI AG 2024-08-01
Series:Buildings
Subjects:
Online Access:https://www.mdpi.com/2075-5309/14/9/2602
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850258347194843136
author Junjie Wei
Yuexia Hu
Si Zhang
Shuyu Liu
author_facet Junjie Wei
Yuexia Hu
Si Zhang
Shuyu Liu
author_sort Junjie Wei
collection DOAJ
description Semantic segmentation of building facades has enabled much intelligent support for architectural research and practice in the last decade. Faced with the free facade of modern buildings, however, the accuracy of segmentation decreased significantly, partly due to its low regularity of composition. The freely organized facade composition is likely to weaken the features of different elements, thus increasing the difficulty of segmentation. At present, the existing facade datasets for semantic segmentation tasks were mostly developed based on the classical facades, which were organized regularly. To train the pixel-level classifiers for the free facade segmentation, this study developed a finely annotated dataset named Irregular Facades (IRFs). The IRFs consist of 1057 high-quality facade images, mainly in the modernist style. In each image, the pixels were labeled into six classes, i.e., Background, Plant, Wall, Window, Door, and Fence. The multi-network cross-dataset control experiment demonstrated that the IRFs-trained classifiers segment the free facade of modern buildings more accurately than those trained with existing datasets. The formers show a significant advantage in terms of average WMIoU (0.722) and accuracy (0.837) over the latters (average WMIoU: 0.262–0.505; average accuracy: 0.364–0.662). In the future, the IRFs are also expected to be considered the baseline for the coming datasets of freely organized building facades.
format Article
id doaj-art-6001fb4bb8d44f93a355c83236da2272
institution OA Journals
issn 2075-5309
language English
publishDate 2024-08-01
publisher MDPI AG
record_format Article
series Buildings
spelling doaj-art-6001fb4bb8d44f93a355c83236da22722025-08-20T01:56:11ZengMDPI AGBuildings2075-53092024-08-01149260210.3390/buildings14092602Irregular Facades: A Dataset for Semantic Segmentation of the Free Facade of Modern BuildingsJunjie Wei0Yuexia Hu1Si Zhang2Shuyu Liu3College of Architecture, Nanjing Tech University, Nanjing 211816, ChinaCollege of Architecture, Nanjing Tech University, Nanjing 211816, ChinaCollege of Art & Design, Nanjing Tech University, Nanjing 211816, ChinaCollege of Architecture, Nanjing Tech University, Nanjing 211816, ChinaSemantic segmentation of building facades has enabled much intelligent support for architectural research and practice in the last decade. Faced with the free facade of modern buildings, however, the accuracy of segmentation decreased significantly, partly due to its low regularity of composition. The freely organized facade composition is likely to weaken the features of different elements, thus increasing the difficulty of segmentation. At present, the existing facade datasets for semantic segmentation tasks were mostly developed based on the classical facades, which were organized regularly. To train the pixel-level classifiers for the free facade segmentation, this study developed a finely annotated dataset named Irregular Facades (IRFs). The IRFs consist of 1057 high-quality facade images, mainly in the modernist style. In each image, the pixels were labeled into six classes, i.e., Background, Plant, Wall, Window, Door, and Fence. The multi-network cross-dataset control experiment demonstrated that the IRFs-trained classifiers segment the free facade of modern buildings more accurately than those trained with existing datasets. The formers show a significant advantage in terms of average WMIoU (0.722) and accuracy (0.837) over the latters (average WMIoU: 0.262–0.505; average accuracy: 0.364–0.662). In the future, the IRFs are also expected to be considered the baseline for the coming datasets of freely organized building facades.https://www.mdpi.com/2075-5309/14/9/2602free facadeirregular facademodern buildingsemantic segmentationclassifier trainingIRFs
spellingShingle Junjie Wei
Yuexia Hu
Si Zhang
Shuyu Liu
Irregular Facades: A Dataset for Semantic Segmentation of the Free Facade of Modern Buildings
Buildings
free facade
irregular facade
modern building
semantic segmentation
classifier training
IRFs
title Irregular Facades: A Dataset for Semantic Segmentation of the Free Facade of Modern Buildings
title_full Irregular Facades: A Dataset for Semantic Segmentation of the Free Facade of Modern Buildings
title_fullStr Irregular Facades: A Dataset for Semantic Segmentation of the Free Facade of Modern Buildings
title_full_unstemmed Irregular Facades: A Dataset for Semantic Segmentation of the Free Facade of Modern Buildings
title_short Irregular Facades: A Dataset for Semantic Segmentation of the Free Facade of Modern Buildings
title_sort irregular facades a dataset for semantic segmentation of the free facade of modern buildings
topic free facade
irregular facade
modern building
semantic segmentation
classifier training
IRFs
url https://www.mdpi.com/2075-5309/14/9/2602
work_keys_str_mv AT junjiewei irregularfacadesadatasetforsemanticsegmentationofthefreefacadeofmodernbuildings
AT yuexiahu irregularfacadesadatasetforsemanticsegmentationofthefreefacadeofmodernbuildings
AT sizhang irregularfacadesadatasetforsemanticsegmentationofthefreefacadeofmodernbuildings
AT shuyuliu irregularfacadesadatasetforsemanticsegmentationofthefreefacadeofmodernbuildings