An Approach to Semantically Segmenting Building Components and Outdoor Scenes Based on Multichannel Aerial Imagery Datasets

As-is building modeling plays an important role in energy audits and retrofits. However, in order to understand the source(s) of energy loss, researchers must know the semantic information of the buildings and outdoor scenes. Thermal information can potentially be used to distinguish objects that ha...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yu Hou, Meida Chen, Rebekka Volk, Lucio Soibelman
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	building thermal modeling building semantic segmentation energy audits instance segmentation thermal and RGB data fusion Science Q
Acceso en línea:	https://doaj.org/article/4cb4002fb67b46269ae1ed9c5226e13b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:4cb4002fb67b46269ae1ed9c5226e13b
record_format	dspace
spelling	oai:doaj.org-article:4cb4002fb67b46269ae1ed9c5226e13b2021-11-11T18:54:39ZAn Approach to Semantically Segmenting Building Components and Outdoor Scenes Based on Multichannel Aerial Imagery Datasets10.3390/rs132143572072-4292https://doaj.org/article/4cb4002fb67b46269ae1ed9c5226e13b2021-10-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/21/4357https://doaj.org/toc/2072-4292As-is building modeling plays an important role in energy audits and retrofits. However, in order to understand the source(s) of energy loss, researchers must know the semantic information of the buildings and outdoor scenes. Thermal information can potentially be used to distinguish objects that have similar surface colors but are composed of different materials. To utilize both the red–green–blue (RGB) color model and thermal information for the semantic segmentation of buildings and outdoor scenes, we deployed and adapted various pioneering deep convolutional neural network (DCNN) tools that combine RGB information with thermal information to improve the semantic and instance segmentation processes. When both types of information are available, the resulting DCNN models allow us to achieve better segmentation performance. By deploying three case studies, we experimented with our proposed DCNN framework, deploying datasets of building components and outdoor scenes, and testing the models to determine whether the segmentation performance had improved or not. In our observation, the fusion of RGB and thermal information can help the segmentation task in specific cases, but it might also make the neural networks hard to train or deteriorate their prediction performance in some cases. Additionally, different algorithms perform differently in semantic and instance segmentation.Yu HouMeida ChenRebekka VolkLucio SoibelmanMDPI AGarticlebuilding thermal modelingbuilding semantic segmentationenergy auditsinstance segmentationthermal and RGB data fusionScienceQENRemote Sensing, Vol 13, Iss 4357, p 4357 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	building thermal modeling building semantic segmentation energy audits instance segmentation thermal and RGB data fusion Science Q
spellingShingle	building thermal modeling building semantic segmentation energy audits instance segmentation thermal and RGB data fusion Science Q Yu Hou Meida Chen Rebekka Volk Lucio Soibelman An Approach to Semantically Segmenting Building Components and Outdoor Scenes Based on Multichannel Aerial Imagery Datasets
description	As-is building modeling plays an important role in energy audits and retrofits. However, in order to understand the source(s) of energy loss, researchers must know the semantic information of the buildings and outdoor scenes. Thermal information can potentially be used to distinguish objects that have similar surface colors but are composed of different materials. To utilize both the red–green–blue (RGB) color model and thermal information for the semantic segmentation of buildings and outdoor scenes, we deployed and adapted various pioneering deep convolutional neural network (DCNN) tools that combine RGB information with thermal information to improve the semantic and instance segmentation processes. When both types of information are available, the resulting DCNN models allow us to achieve better segmentation performance. By deploying three case studies, we experimented with our proposed DCNN framework, deploying datasets of building components and outdoor scenes, and testing the models to determine whether the segmentation performance had improved or not. In our observation, the fusion of RGB and thermal information can help the segmentation task in specific cases, but it might also make the neural networks hard to train or deteriorate their prediction performance in some cases. Additionally, different algorithms perform differently in semantic and instance segmentation.
format	article
author	Yu Hou Meida Chen Rebekka Volk Lucio Soibelman
author_facet	Yu Hou Meida Chen Rebekka Volk Lucio Soibelman
author_sort	Yu Hou
title	An Approach to Semantically Segmenting Building Components and Outdoor Scenes Based on Multichannel Aerial Imagery Datasets
title_short	An Approach to Semantically Segmenting Building Components and Outdoor Scenes Based on Multichannel Aerial Imagery Datasets
title_full	An Approach to Semantically Segmenting Building Components and Outdoor Scenes Based on Multichannel Aerial Imagery Datasets
title_fullStr	An Approach to Semantically Segmenting Building Components and Outdoor Scenes Based on Multichannel Aerial Imagery Datasets
title_full_unstemmed	An Approach to Semantically Segmenting Building Components and Outdoor Scenes Based on Multichannel Aerial Imagery Datasets
title_sort	approach to semantically segmenting building components and outdoor scenes based on multichannel aerial imagery datasets
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/4cb4002fb67b46269ae1ed9c5226e13b
work_keys_str_mv	AT yuhou anapproachtosemanticallysegmentingbuildingcomponentsandoutdoorscenesbasedonmultichannelaerialimagerydatasets AT meidachen anapproachtosemanticallysegmentingbuildingcomponentsandoutdoorscenesbasedonmultichannelaerialimagerydatasets AT rebekkavolk anapproachtosemanticallysegmentingbuildingcomponentsandoutdoorscenesbasedonmultichannelaerialimagerydatasets AT luciosoibelman anapproachtosemanticallysegmentingbuildingcomponentsandoutdoorscenesbasedonmultichannelaerialimagerydatasets AT yuhou approachtosemanticallysegmentingbuildingcomponentsandoutdoorscenesbasedonmultichannelaerialimagerydatasets AT meidachen approachtosemanticallysegmentingbuildingcomponentsandoutdoorscenesbasedonmultichannelaerialimagerydatasets AT rebekkavolk approachtosemanticallysegmentingbuildingcomponentsandoutdoorscenesbasedonmultichannelaerialimagerydatasets AT luciosoibelman approachtosemanticallysegmentingbuildingcomponentsandoutdoorscenesbasedonmultichannelaerialimagerydatasets
_version_	1718431643781300224

An Approach to Semantically Segmenting Building Components and Outdoor Scenes Based on Multichannel Aerial Imagery Datasets

Ejemplares similares