Environmental factors for outdoor jogging in Beijing: Insights from using explainable spatial machine learning and massive trajectory data

Landscape and Urban Planning, Journal Year: 2023, Volume and Issue: 243, P. 104969 - 104969

Published: Dec. 4, 2023

Language: Английский

---

Understanding urban perception with visual data: A systematic review

Cities, Journal Year: 2024, Volume and Issue: 152, P. 105169 - 105169

Published: June 21, 2024

Language: Английский

---

Integrating restorative perception into urban street planning: A framework using street view images, deep learning, and space syntax

Cities, Journal Year: 2024, Volume and Issue: 147, P. 104791 - 104791

Published: Jan. 22, 2024

Language: Английский

---

Unraveling nonlinear and interaction effects of multilevel built environment features on outdoor jogging with explainable machine learning

Cities, Journal Year: 2024, Volume and Issue: 147, P. 104813 - 104813

Published: Feb. 3, 2024

Language: Английский

---

Evaluating implied urban nature vitality in San Francisco: An interdisciplinary approach combining census data, street view images, and social media analysis

Urban forestry & urban greening, Journal Year: 2024, Volume and Issue: 95, P. 128289 - 128289

Published: March 15, 2024

Language: Английский

---

Investigating the civic emotion dynamics during the COVID-19 lockdown: Evidence from social media

Sustainable Cities and Society, Journal Year: 2024, Volume and Issue: 107, P. 105403 - 105403

Published: April 5, 2024

Language: Английский

---

Unraveling the effects of micro-level street environment on dockless bikeshare in Ithaca

Transportation Research Part D Transport and Environment, Journal Year: 2024, Volume and Issue: 132, P. 104256 - 104256

Published: May 30, 2024

Language: Английский

---

Day-to-Night Street View Image Generation for 24-Hour Urban Scene Auditing Using Generative AI

Journal of Imaging, Journal Year: 2024, Volume and Issue: 10(5), P. 112 - 112

Published: May 7, 2024

A smarter city should be a safer city. Nighttime safety in metropolitan areas has long been global concern, particularly for large cities with diverse demographics and intricate urban forms, whose citizens are often threatened by higher street-level crime rates. However, due to the lack of night-time appearance data, prior studies based on street view imagery (SVI) rarely addressed perceived issue, which can generate important implications prevention. This study hypothesizes that SVI effectively generated from widely existing daytime SVIs using generative AI (GenAI). To test hypothesis, this first collects pairwise day-and-night across four diverged landscapes construct comprehensive dataset. It then trains validates day-to-night (D2N) model fine-tuned brightness adjustment, transforming nighttime ones distinct forms tailored scene perception studies. Our findings indicate that: (1) performance D2N transformation varies significantly urban-scape variations related density; (2) proportion building sky views determinants accuracy; (3) within prevailed models, CycleGAN maintains consistency conversion, but requires abundant data. Pix2Pix achieves considerable accuracy when day-and-night-night available sensitive data quality. StableDiffusion yields high-quality images expensive training costs. Therefore, is most effective balancing accuracy, requirement, cost. contributes constructing first-of-its-kind dataset consisting various forms. The generator will provide cornerstone future heavily utilize audit environments.

Language: Английский

---

Beyond built environment: Unveiling the interplay of streetscape perceptions and cycling behavior

Sustainable Cities and Society, Journal Year: 2024, Volume and Issue: 109, P. 105525 - 105525

Published: May 20, 2024

As an important means of shared micro-mobility, bicycles have become a crucial component urban transportation in China. The impact the built environment on bicycling has been widely acknowledged. However, can streetscape perceptions influence bicycle-sharing volume (BSV) and supplement environment? We first obtained millions pieces shared-cycling data from Shenzhen Open Data Platform carried out geographical quantification BSV. for streetscape, we improved classification subjective perception based street view images using k-means clustering algorithm conducted predictions XGBoost. Through application different regression models, unveiled nonlinear spatial interdependencies between BSV as complement to environment. Our findings indicate that greenery, vivid street-front facades, diverse facilities promote Targeted strategies are proposed districts. For instance, planners provide incentives high-income groups central areas adopt active travel, increase supply suburban with high building density, particularly industrial villages. long-term planning recommendations derived macro-built analysis, in-depth quantitative assessment proffers human-centric, flexible blueprint design.

Language: Английский

---

Deciphering urban bike-sharing patterns: An in-depth analysis of natural environment and visual quality in New York's Citi bike system

Journal of Transport Geography, Journal Year: 2024, Volume and Issue: 115, P. 103799 - 103799

Published: Jan. 21, 2024

Bike-sharing offers a convenient and sustainable mode of transportation. Numerous studies have investigated the influence temporal variations in natural environment on cycling, as well impact physical street characteristics like networks infrastructures. However, few integrated compared effects visual quality cycling spatial dimension. As case study, we focused these two factors Citi Bike system weekdays weekends New York City, while accounting for sociodemographic functional factors. This study employed machine learning multiscale geographically weighted regression models at both station neighborhood scales comprehensive analysis their relationships. The results reveal that factors, particularly visibility, are more important associated with bike-sharing use. Among motorized traffic has negative weekday weekend cycling. When considering geographical location, sky openness exhibits an unfavorable specific areas. By combining our promotes optimal resource allocation development bike-friendly cities.

Language: Английский

---