GEOSCENE MODELING AND ANALYSIS FOR URBAN FUNCTIONAL ZONES

Abstract. Urban functional zones are basic units for human socio-economic activities in cities. Urban functional zones play an important role in a wide range of urban studies, as they are fundamental to urban planning and management, urban resource allocation, as well as urban sustainable development evaluation. However, existing studies of urban functional zone modeling and mapping mainly employ state-of-the-art image segmentation and deep learning classification methods in computer science field to delineate and recognize urban functional zones, but ignore their heterogeneity, integration, multi-scale, and locality characteristics, so that the accuracy of urban functional zone modeling, mapping, and analysis is limited and interpretable, thus cannot comprehensively meet the requirements of downstream applications. This study, however, proposes a geoscene modeling and analysis framework for extracting urban functional zones, which first delineates urban functional zones by multiscale geoscene segmentation, then characterizes them by hierarchical semantic cognition, and finally recognizes their functional categories by linear Dirichlet mixture model. Although this paper does not present the detailed implementations of the geoscene modeling of urban functional zones, it illustrates the importance and the generally strategy of geoscene modeling in urban functional zone mapping and analysis. Additionally, urban functional zone mapping results of Baoshan District, Shanghai, in 2015 and 2020 are presented to verify the effectiveness of the proposed geoscene modeling strategy.

Standort
Deutsche Nationalbibliothek Frankfurt am Main
Umfang
Online-Ressource
Sprache
Englisch

Erschienen in
GEOSCENE MODELING AND ANALYSIS FOR URBAN FUNCTIONAL ZONES ; volume:XLVIII-3/W2-2022 ; year:2022 ; pages:91-96 ; extent:6
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ; XLVIII-3/W2-2022 (2022), 91-96 (gesamt 6)

Urheber
Zhang, X.
Du, S.

DOI
10.5194/isprs-archives-XLVIII-3-W2-2022-91-2022
URN
urn:nbn:de:101:1-2022110304380264834217
Rechteinformation
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
Letzte Aktualisierung
15.08.2025, 07:26 MESZ

Datenpartner

Dieses Objekt wird bereitgestellt von:
Deutsche Nationalbibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.

Beteiligte

  • Zhang, X.
  • Du, S.

Ähnliche Objekte (12)