Visual perception-informed urban design toolkit: Computational urban morphology optimisation to inform real-time perceived safety
Bibliographic record
Abstract
The perceived safety of street scenes significantly affects the travel behaviors and social interactions of urban dwellers, particularly females, which ultimately matters to the inclusiveness of cities. Despite efforts to utilize street view imagery (SVI) for auditing perceived safety in urban areas, most studies remain analytical, with limited integration into urban design's form-based ideation workflow. The reason is mechanism dependency: few designers use both analytics (Python) and form-based design (Rhino) tools fluently. The outcome should not be overlooked: when the humanistic pedestrian experience cannot be explicitly integrated into the design process, the planning results may further marginalise disadvantaged groups. To bridge the gap between urban analytics and design, we propose a computational framework that automates the evaluation of pedestrian-oriented perceived safety in real-time, linking form-based urban design features, particularly greenery, to visual safety perception within urban canyons. By integrating datasets such as Place Pulse 2.0 and environmental attributes, the perceived safety of different urban canyons with varying urban forms and streetscape configurations can be seamlessly updated using machine learning in Rhino Grasshopper. Our tests show that in areas with the same urban density and height-width ratio, specific greenery configurations, such as tree density and green coverage, significantly improve perceived safety. Subsequently, urban canyon forms are categorised based on perceived safety outcomes to provide urban design guidelines. Notably, real-time visualisations from Stable Diffusion are further incorporated to improve the Rhino-based framework's usability in real life. This computational framework integrates visual perceptions into form-based urban form ideation (especially greenery characteristics): it alleviates the politics of difference in urban design practice, supporting the facilitation of more inclusive public spaces.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".