What question did this study set out to answer?

To establish a scalable method for quantifying resident perceptions of street space quality and evaluate how specific physical street elements influence these spatial perceptions.

June 27, 2022ISPRS Journal of Photogrammetry and Remote SensingOpen Access

Measuring residents’ perceptions of city streets to inform better street planning through deep learning and space syntax

View Full Paper

Ask AI

Bookmark

Authors

LWLei Wang XHXin Han JHJie He

Discussion

Member takes

Overview

Computational spatial analysis reveals specific urban design elements driving positive and negative public perceptions, suggesting prioritized interventions for high-accessibility city streets.

Key Points

To establish a scalable method for quantifying resident perceptions of street space quality and evaluate how specific physical street elements influence these spatial perceptions.
Constructed a deep learning scoring model using street view images from the Binjiang district of Hangzhou, China, evaluating six perception dimensions: beautiful, wealthy, safety, lively, depressing, and boring.
Categorized street scenes into high- and low-quality spaces using the top 20% positive and negative scores, subsequently overlaying space syntax accessibility metrics to prioritize high-travel corridors.
Conducted multiple linear regression analyses to examine quantitative associations between spatial perception scores and physical street composition elements.
Positive street perceptions were significantly positively associated with the presence of plants and roads, and negatively associated with walls, ground surfaces, water, and fences.
Negative street perceptions were significantly positively associated with the visual prominence of walls and buildings.
Spatial overlay of accessibility indices successfully pinpointed high-priority urban segments exhibiting either extreme positive or negative quality along primary transit routes.

Cite This Study

Wang et al. (2022) studied this question.

synapsesocial.com/papers/69d7c8a705ee2ba81dbedefd https://doi.org/10.1016/j.isprsjprs.2022.06.011

View Full Paper

Ask AI

Bookmark

June 27, 2022ISPRS Journal of Photogrammetry and Remote SensingOpen Access

Measuring residents’ perceptions of city streets to inform better street planning through deep learning and space syntax

View Full Paper

Ask AI

Bookmark

Authors

LWLei Wang XHXin Han JHJie He

Discussion

Member takes

Overview

Computational spatial analysis reveals specific urban design elements driving positive and negative public perceptions, suggesting prioritized interventions for high-accessibility city streets.

Key Points

To establish a scalable method for quantifying resident perceptions of street space quality and evaluate how specific physical street elements influence these spatial perceptions.
Constructed a deep learning scoring model using street view images from the Binjiang district of Hangzhou, China, evaluating six perception dimensions: beautiful, wealthy, safety, lively, depressing, and boring.
Categorized street scenes into high- and low-quality spaces using the top 20% positive and negative scores, subsequently overlaying space syntax accessibility metrics to prioritize high-travel corridors.
Conducted multiple linear regression analyses to examine quantitative associations between spatial perception scores and physical street composition elements.
Positive street perceptions were significantly positively associated with the presence of plants and roads, and negatively associated with walls, ground surfaces, water, and fences.
Negative street perceptions were significantly positively associated with the visual prominence of walls and buildings.
Spatial overlay of accessibility indices successfully pinpointed high-priority urban segments exhibiting either extreme positive or negative quality along primary transit routes.

Cite This Study

Wang et al. (2022) studied this question.

synapsesocial.com/papers/69d7c8a705ee2ba81dbedefd https://doi.org/10.1016/j.isprsjprs.2022.06.011

Also Consider

Synapse has enriched 2 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark