Proportion Estimation for Urban Mixed Scenes Based on Nonnegative Matrix Factorization for High-Spatial Resolution Remote Sensing Images

High-spatial resolution urban scenes, which contain ecological, social, and environmental zones, are composed of diverse functional areas. Depicting urban scenes from both qualitative and quantitative aspects, i.e., scene classification and scene unmixing, are increasingly important tasks. The purpo...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Qiqi Zhu, Jiale Chen, Linlin Wang, Qingfeng Guan
Formato: article
Lenguaje:EN
Publicado: IEEE 2021
Materias:
Acceso en línea:https://doaj.org/article/f222f83121c247d38e84f1b4eba40b4e
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:f222f83121c247d38e84f1b4eba40b4e
record_format dspace
spelling oai:doaj.org-article:f222f83121c247d38e84f1b4eba40b4e2021-11-17T00:00:10ZProportion Estimation for Urban Mixed Scenes Based on Nonnegative Matrix Factorization for High-Spatial Resolution Remote Sensing Images2151-153510.1109/JSTARS.2021.3119988https://doaj.org/article/f222f83121c247d38e84f1b4eba40b4e2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9573506/https://doaj.org/toc/2151-1535High-spatial resolution urban scenes, which contain ecological, social, and environmental zones, are composed of diverse functional areas. Depicting urban scenes from both qualitative and quantitative aspects, i.e., scene classification and scene unmixing, are increasingly important tasks. The purpose of scene classification is to mark a scene as a separate category, and this approach is widely applied to qualitatively define scenes. However, with the rapid development of cities, urban scenes usually show a mixed nature, resulting in urban mixed scenes (UMSs). Traditional scene classification cannot describe the mix of urban scenes. Few studies have focused on the quantitative measurements of UMSs, which aim at discovering and analyzing the proportion of different subscenes. In this article, a scene unmixing framework based on nonnegative matrix factorization for UMSs (UnUMS) is proposed to estimate the mixing ratio of urban scenes. In the UnUMS, a deep feature representation is used for the high-dimensional representation of the image, and then a nonnegative matrix factorization strategy is used to estimate the proportion of UMSs. Finally, the UMS can be described by the proportion of each subscene. To confirm the robust generalizability of UnUMS, the WH-center Mix dataset with a set of small mixed scenes and the WH-hy LMix dataset with a large UMS image are utilized. The root-mean-square error and the newly proposed vector angular distance are utilized to quantitatively evaluate the effect of scene unmixing from different aspects. Experiments with the two datasets demonstrate that UnUMS can accurately estimate the proportions of different scenes for UMS.Qiqi ZhuJiale ChenLinlin WangQingfeng GuanIEEEarticleHigh-resolution imagerynonnegative matrix factorization (NMF)remote sensingscene unmixingurban mixed scene (UMS)Ocean engineeringTC1501-1800Geophysics. Cosmic physicsQC801-809ENIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 14, Pp 11257-11270 (2021)
institution DOAJ
collection DOAJ
language EN
topic High-resolution imagery
nonnegative matrix factorization (NMF)
remote sensing
scene unmixing
urban mixed scene (UMS)
Ocean engineering
TC1501-1800
Geophysics. Cosmic physics
QC801-809
spellingShingle High-resolution imagery
nonnegative matrix factorization (NMF)
remote sensing
scene unmixing
urban mixed scene (UMS)
Ocean engineering
TC1501-1800
Geophysics. Cosmic physics
QC801-809
Qiqi Zhu
Jiale Chen
Linlin Wang
Qingfeng Guan
Proportion Estimation for Urban Mixed Scenes Based on Nonnegative Matrix Factorization for High-Spatial Resolution Remote Sensing Images
description High-spatial resolution urban scenes, which contain ecological, social, and environmental zones, are composed of diverse functional areas. Depicting urban scenes from both qualitative and quantitative aspects, i.e., scene classification and scene unmixing, are increasingly important tasks. The purpose of scene classification is to mark a scene as a separate category, and this approach is widely applied to qualitatively define scenes. However, with the rapid development of cities, urban scenes usually show a mixed nature, resulting in urban mixed scenes (UMSs). Traditional scene classification cannot describe the mix of urban scenes. Few studies have focused on the quantitative measurements of UMSs, which aim at discovering and analyzing the proportion of different subscenes. In this article, a scene unmixing framework based on nonnegative matrix factorization for UMSs (UnUMS) is proposed to estimate the mixing ratio of urban scenes. In the UnUMS, a deep feature representation is used for the high-dimensional representation of the image, and then a nonnegative matrix factorization strategy is used to estimate the proportion of UMSs. Finally, the UMS can be described by the proportion of each subscene. To confirm the robust generalizability of UnUMS, the WH-center Mix dataset with a set of small mixed scenes and the WH-hy LMix dataset with a large UMS image are utilized. The root-mean-square error and the newly proposed vector angular distance are utilized to quantitatively evaluate the effect of scene unmixing from different aspects. Experiments with the two datasets demonstrate that UnUMS can accurately estimate the proportions of different scenes for UMS.
format article
author Qiqi Zhu
Jiale Chen
Linlin Wang
Qingfeng Guan
author_facet Qiqi Zhu
Jiale Chen
Linlin Wang
Qingfeng Guan
author_sort Qiqi Zhu
title Proportion Estimation for Urban Mixed Scenes Based on Nonnegative Matrix Factorization for High-Spatial Resolution Remote Sensing Images
title_short Proportion Estimation for Urban Mixed Scenes Based on Nonnegative Matrix Factorization for High-Spatial Resolution Remote Sensing Images
title_full Proportion Estimation for Urban Mixed Scenes Based on Nonnegative Matrix Factorization for High-Spatial Resolution Remote Sensing Images
title_fullStr Proportion Estimation for Urban Mixed Scenes Based on Nonnegative Matrix Factorization for High-Spatial Resolution Remote Sensing Images
title_full_unstemmed Proportion Estimation for Urban Mixed Scenes Based on Nonnegative Matrix Factorization for High-Spatial Resolution Remote Sensing Images
title_sort proportion estimation for urban mixed scenes based on nonnegative matrix factorization for high-spatial resolution remote sensing images
publisher IEEE
publishDate 2021
url https://doaj.org/article/f222f83121c247d38e84f1b4eba40b4e
work_keys_str_mv AT qiqizhu proportionestimationforurbanmixedscenesbasedonnonnegativematrixfactorizationforhighspatialresolutionremotesensingimages
AT jialechen proportionestimationforurbanmixedscenesbasedonnonnegativematrixfactorizationforhighspatialresolutionremotesensingimages
AT linlinwang proportionestimationforurbanmixedscenesbasedonnonnegativematrixfactorizationforhighspatialresolutionremotesensingimages
AT qingfengguan proportionestimationforurbanmixedscenesbasedonnonnegativematrixfactorizationforhighspatialresolutionremotesensingimages
_version_ 1718426084247076864