Pular para o conteúdo principal

ETHNOS_APP

Início • Busca • Periódicos • Lista 0

Assessing and mapping public visual perception across urban public space typologies based on geotagged social media images

Dados Bibliográficos

ID21450503
AutoresChenghao Yang (0000-0003-4793-7864, Tsinghua University), Ye Zhang (0009-0002-2442-4804, Tsinghua University, autor correspondente)
Ano2026
Volume194
Páginas104097
Data de publicação2026-09-01
Peer ReviewedSim
Open AccessSim
TipoARTICLE
PeriódicoApplied Geography (JOURNAL)
Identificadores do periódicoISSN: 0143-6228 • E-ISSN: 1873-7730
EditoraElsevier BV (PUBLISHER)
DOI10.1016/j.apgeog.2026.104097
OpenAlexW7166705033
IdiomaEN
Referências citadas51

Urban public spaces are increasingly evaluated using social media data, yet comparative evidence on how public visual preferences vary across public space typologies and how these preferences cluster spatially remains limited. This study proposes a perception-driven deep learning framework to assess and map public visual perception across four urban public space typologies using geotagged Flickr data. Focusing on a high-density 2 km radius around Sydney's Darling Harbour, the framework integrates ResNet-50 image classification, Mask2Former panoptic segmentation, and GIS-based spatial analytics, with typologies validated against expert and MLLM consensus reaching a Cohen's κ of up to 0.92 and 0.81. Waterfront emerges as the dominant typology, drawing 52% of visual engagement, yet the highest positive perception does not concentrate in pure waterfront settings. Instead, it clusters in visual-hybrid nodes such as Darling Harbour, Tumbalong Park, and Darling Square, where blue, green, and built typologies co-occur. Tumblaong Park areas outperform every single type of environment across six perception dimensions, with Cohen's d reaching +0.48 for Beautiful and −0.81 for Depressing. After statistically controlling for visual composition, public space typology retains relatively independent explanatory power over perceived quality. Urban public space appeal is therefore contingent on integrated configurations rather than water frontage or greening alone, and the synergy of blue, green, and built elements drives positive experiences more than functional isolation. Beyond corroborating Sydney's Gehl-informed regeneration strategy, the framework provides a scalable, transferable workflow for translating unstructured visual data into evidence for human-centered urban design

Geovisualization · Panopticon · Perception · Public space · Social media · Space (punctuation) · Typology · Urban design · Urban planning · Land Use and Ecosystem Services · Urban Design and Spatial Analysis · Urban Green Space and Health

  • Use of Ranks in One-Criterion Variance Analysis

    William Kruskal, William H Kruskal et al.•Journal of the American…•1952

  • Contemporary Public Space, Part Two

    Matthew Carmona•Journal of Urban Design•2010

  • Representing place locales using scene elements

    Open Access•Fan Zhang, Ding Zhang et al.•Computers Environment and Urban…•2018

  • Places

    Open Access•Bolei Zhou, Agata Lapedriza et al.•IEEE Transactions on Pattern…•2018

  • Principles for public space design, planning to do better

    Open Access•Matthew Carmona•URBAN DESIGN International•2019

  • Social Media data

    Open Access•Pablo Martí Ciriquián, Pablo Martí et al.•Computers Environment and Urban…•2019

  • A beautiful place

    Open Access•Miroslav Despotović, Christoph Hauser et al.•Humanities and Social Sciences…•2025

  • From traditional to digital contexts

    Open Access•Zhaolian Xing, Ribing Zhao et al.•Humanities and Social Sciences…•2024

  • Crowd-Sourced City Images

    Open Access•Yao Shen, Yiyi Xu et al.•ISPRS International Journal of…•2021

  • Enhancing Place Emotion Analysis with Multi-View Emotion Recognition from Geo-Tagged Photos

    Open Access•Yu Wang, Shunping Zhou et al.•ISPRS International Journal of…•2024

  • Designing for possibility in public space

    Open Access•Quentin Stevens, Jonathan Daly et al.•URBAN DESIGN International•2024

  • Understanding the use of urban green spaces from user-generated geographic information

    Open Access•Vuokko Heikinheimo, Henrikki Tenkanen et al.•Landscape and Urban Planning•2020

  • Seeing green, staying longer? A causal analysis of visual green exposure and urban park engagement using mobility and panoramas data

    Open Access•Yichun Zhou, Xiyuan Ren et al.•Landscape and Urban Planning•2026

  • Measuring heterogeneous perception of urban space with massive data and machine learning

    Open Access•Tomás Ramírez, Tomas Eduardo Ramirez et al.•Landscape and Urban Planning•2021

  • Evaluating the subjective perceptions of streetscapes using street-view images

    Open Access•Yoshiki Ogawa, Takuya Oki et al.•Landscape and Urban Planning•2024

  • Understanding urban perception with visual data

    Open Access•Koichi Ito, Yuhao Kang et al.•Cities•2024

  • Understanding the user perspective on urban public spaces

    Open Access•Yihan Zhu, Ye Zhang et al.•Cities•2025

  • Understanding cities with machine eyes

    Open Access•Mohamed R Ibrahim, James Haworth et al.•Cities•2020

  • Social-media data for urban sustainability

    Open Access•Rositsa T Ilieva, Timon Mcphearson•Nature Sustainability•2018

  • Revisiting Lively Streets

    Open Access•Ved Mehta, Jennifer K Bosson•Journal of Planning Education and…•2018

  • Quantifying physical and psychological perceptions of urban scenes using deep learning

    Open Access•Yonglin Zhang, Shanlin Li et al.•Land Use Policy•2021

  • Measuring human perceptions of streetscapes to better inform urban renewal

    Open Access•Xiangyuan Ma, Chenyan Ma et al.•Cities•2021

  • The role of successful public spaces in historic centres. Insights from social media data

    Open Access•Álvaro Bernabeu-Bautista, Leticia Serrano-Estrada et al.•Cities•2023

  • Automatic assessment of public open spaces using street view imagery

    Open Access•Shuting Chen, Filip Biljecki•Cities•2023

  • What influenced the vitality of the waterfront open space? A case study of Huangpu River in Shanghai, China

    Open Access•Song Liu, Si-Qi Lai et al.•Cities•2021

  • Plausible or misleading? Evaluating the adaption of the place pulse 2.0 dataset for predicting subjective perception in Chinese urban landscapes

    Open Access•Jin Rui, Chenfan Cai•Habitat International•2025

  • Physical urban change and its socio-environmental impact

    Open Access•Yingjie Liu, Zeyu Wang et al.•Computers Environment and Urban…•2025

  • ZenSVI

    Open Access•Koichi Ito, Yihan Zhu et al.•Computers Environment and Urban…•2025

  • Public space and its publicness in people-oriented urban regeneration

    Open Access•Jingyi Zhu•Journal of Urban Affairs•2023

  • Exploring the impact of objective features and subjective perceptions of street environment on cycling preferences

    Open Access•Haibin Xu, Yiyi Jiang et al.•Cities•2025

  • Urban safety perception assessments via integrating multimodal large language models with street view images

    Open Access•Jiaxin Zhang, Yunqin Li et al.•Cities•2025

  • Popularity influence mechanism of coastal spaces in urban areas

    Open Access•Peijin Sun, Hanxu Zhao et al.•Cities•2025

Velocidade de citaçãohistorical
Altamente citadoNão
Ethnos_APP • Projeto Open Source • Licença MIT • Frontend v2.0.0 • Privacidade e Cookies • Documentação da API: api.ethnos.app/docs • Código da API: GitHub • DOI: 10.5281/zenodo.17049435 • Código do Frontend: GitHub • DOI: 10.5281/zenodo.17050053 • cruz.rio.br • Expectantes Misericordiae