Global Streetscapes — A comprehensive dataset of 10 million street-level images across 688 cities for urban science and analytics

ISPRS Journal of Photogrammetry and Remote Sensing, Journal Year: 2024, Volume and Issue: 215, P. 216 - 238

Published: July 16, 2024

Language: Английский

---

Images and deep learning in human and urban infrastructure interactions pertinent to sustainable urban studies: Review and perspective

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2025, Volume and Issue: unknown, P. 104352 - 104352

Published: Jan. 1, 2025

Language: Английский

---

Coverage and bias of street view imagery in mapping the urban environment

Computers Environment and Urban Systems, Journal Year: 2025, Volume and Issue: 117, P. 102253 - 102253

Published: Jan. 23, 2025

Language: Английский

---

Urban Perception Assessment from Street View Images Based on a Multifeature Integration Encompassing Human Visual Attention

Annals of the American Association of Geographers, Journal Year: 2024, Volume and Issue: 114(7), P. 1424 - 1442

Published: July 8, 2024

Language: Английский

---

Multi-level urban street representation with street-view imagery and hybrid semantic graph

ISPRS Journal of Photogrammetry and Remote Sensing, Journal Year: 2024, Volume and Issue: 218, P. 19 - 32

Published: Oct. 18, 2024

Language: Английский

---

Analysis and Optimization of the Spatial Patterns of Commercial Service Facilities Based on Multisource Spatiotemporal Data and Graph Neural Networks: A Case Study of Beijing, China

ISPRS International Journal of Geo-Information, Journal Year: 2025, Volume and Issue: 14(1), P. 23 - 23

Published: Jan. 9, 2025

As a crucial component of urban economic activities, the layout and optimization commercial spaces directly influence prosperity quality life residents. Therefore, comprehensively accurately characterizing distribution characteristics evolutionary patterns is essential for improving efficiency spatial allocation achieving scientific planning governance. This paper utilizes multisource spatiotemporal data, employing geographic analysis methods graph neural network models to explore structure service facilities in Beijing their relationships with population density land use, thereby detailed classification at natural neighborhood scale. The research findings indicate significant association between population, as well strong heterogeneity. There exists dissonance distribution, differences development across various regions pose challenges balanced development. Based on this, this provides specific recommendations optimizing structure, offering reference points future

Language: Английский

---

The Scale Effect of Street View Images and Urban Vitality Is Consistent with a Gaussian Function Distribution

Land, Journal Year: 2025, Volume and Issue: 14(2), P. 415 - 415

Published: Feb. 17, 2025

Street view images are often used to assess the impact of built environment on urban vitality from an eye-level perspective. However, influence analyzing scale accuracy assessment results is ignored. To find appropriate scale, we need quantify effect street and vitality. Therefore, in this study, Shenzhen selected as study area. Urban characterized by Weibo check-in records. VGG19 employed learn features performs regression analysis image records different sizes grids (100 m, 150 …, 1000 m). Finally, fit their correlation via a function. We that increases, between tends increase then decrease, which consistent with distribution law Gaussian This provides basis for selecting scales

Language: Английский

---

Environmental determinants of dynamic jogging patterns: Insights from trajectory big data analysis and interpretable machine learning

Applied Geography, Journal Year: 2025, Volume and Issue: 178, P. 103596 - 103596

Published: March 14, 2025

Language: Английский

---

Different perspectives are indispensable for public space quality: Exploring the relationship between urban design quality and physical disorder

Environment and Planning B Urban Analytics and City Science, Journal Year: 2025, Volume and Issue: unknown

Published: March 15, 2025

Public space quality is a multidimensional concept. Urban design and physical disorder represent it from the perspectives of maintenance, respectively. However, practical relationship between these two factors remains unclear, raising questions about necessity measuring multiple dimensions public simultaneously. Based on classical studies theories, this study developed index systems for both factors. Utilizing artificial virtual auditing deep learning models, including FCN SegNet, street visual Chinese cities was assessed urban using extensive view images. The correlation explored. results showed that Spearman coefficients were 0.308 −0.085 in cities, respectively, indicating weak or unclear correlations. Additionally, fit explanatory power linear nonlinear regression models constructed poor, further demonstrating difficult to predict explain one variable other. In robustness test, validated by control variables related vitality, cultural characteristics, development, considering impact distribution images, drilling down more granular extending scope wider area. levels maintenance streets cannot be conflated substituted, neither can independently overall alone. Both are indispensable, making crucial separately assess address issues different perspectives. These broaden our understanding high-visual-quality provide references planners stakeholders improving quality.

Language: Английский

---

Perception of urban street visual color environment based on the CEP-KASS framework

Landscape and Urban Planning, Journal Year: 2025, Volume and Issue: 259, P. 105359 - 105359

Published: April 9, 2025

Language: Английский

---