What does this research mean for the field?

A deep learning-based framework integrating street-view imagery can reliably evaluate and map multidimensional streetscape perceptions—such as cultural character, spatial order, and visual comfort—revealing distinct spatial clustering patterns in historic districts. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

To establish a reproducible, multidimensional deep-learning framework for diagnosing human perception of historic streetscapes across cultural character recognition, spatial order, and visual comfort.

September 5, 2026LandOpen Access

A Multidimensional Framework for Diagnosing Streetscape Perception in Historic-District Renewal Using Street-View Imagery and Deep Learning

View Full Paper

Ask AI

Bookmark

Authors

JLJilong Li HCHongyang Chen PLPan Liao

Discussion

Member takes

Overview

Computational modeling study reveals distinct spatial clustering of visual comfort, order, and cultural perception across historic streets, indicating pathways for targeted urban conservation.

Key Points

To establish a reproducible, multidimensional deep-learning framework for diagnosing human perception of historic streetscapes across cultural character recognition, spatial order, and visual comfort.
Gathered 8,693 street-view images across 2,243 sampling points in the Pengcheng Qili historic district in Xuzhou, China.
Trained perception-prediction models combining pairwise comparison surveys, the Bradley–Terry probabilistic model, and a ResNet50 deep learning architecture.
Evaluated performance using five-fold stratified cross-validation and independent external validation, followed by multidimensional spatial statistical mapping.
Cultural character recognition demonstrated significant, localized spatial clustering centered primarily around key historical nodes and heritage-dense zones.
Spatial order and visual comfort exhibited distinct, linear corridor-like and broad network-like spatial patterns across the street grid.

Cite This Study

Li et al. (2026) studied this question.

synapsesocial.com/papers/6a9bd3e16b95aff0620eb099 https://doi.org/10.3390/land15091640

View Full Paper

Ask AI

Bookmark

September 5, 2026LandOpen Access

A Multidimensional Framework for Diagnosing Streetscape Perception in Historic-District Renewal Using Street-View Imagery and Deep Learning

View Full Paper

Ask AI

Bookmark

Authors

JLJilong Li HCHongyang Chen PLPan Liao

Discussion

Member takes

Overview

Computational modeling study reveals distinct spatial clustering of visual comfort, order, and cultural perception across historic streets, indicating pathways for targeted urban conservation.

Key Points

To establish a reproducible, multidimensional deep-learning framework for diagnosing human perception of historic streetscapes across cultural character recognition, spatial order, and visual comfort.
Gathered 8,693 street-view images across 2,243 sampling points in the Pengcheng Qili historic district in Xuzhou, China.
Trained perception-prediction models combining pairwise comparison surveys, the Bradley–Terry probabilistic model, and a ResNet50 deep learning architecture.
Evaluated performance using five-fold stratified cross-validation and independent external validation, followed by multidimensional spatial statistical mapping.
Cultural character recognition demonstrated significant, localized spatial clustering centered primarily around key historical nodes and heritage-dense zones.
Spatial order and visual comfort exhibited distinct, linear corridor-like and broad network-like spatial patterns across the street grid.

Cite This Study

Li et al. (2026) studied this question.

synapsesocial.com/papers/6a9bd3e16b95aff0620eb099 https://doi.org/10.3390/land15091640

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark