Analyzing Urban Crime Through Street View Imagery: Insights from Urban Micro Built Environment and Perceptions
Bibliographic record
Abstract
Understanding the relationship between urban crime and the built environment is crucial for developing effective crime prevention strategies, particularly in the context of rapid urban development and city planning. As cities grow, urbanization leads to environments that either promote or inhibit criminal activity, making it essential to explore the interactions between urban design and crime. This study investigates the impact of micro built environment (MBE) elements and place perceptions on crime occurrences in Toronto using street view imagery (SVI) data and machine learning models. We used logistic regression models and an XGBoost (Version 1.7.5) classifier to assess the significance of MBE and perception variables in classifying crime and non-crime intersections. Our findings reveal that intersections with criminal activity tend to be related to more mobility-related features, such as roads and vehicles, and fewer natural elements, such as vegetation. The “beautiful” and “depressing” perceptions emerged as the most significant variables in explaining crime events, surpassing the commonly studied “safety” perception. The XGBoost model achieved 86% accuracy, indicating that MBE and perception variables are strong predictors of crime risk. These findings suggest that enhancing vegetation and improving street aesthetics could serve as effective crime prevention measures in urban environments. However, limitations include the general nature of the perception model and the reliance on aggregated crime data. Future research should incorporate local perceptions and fine-scale crime data to provide more tailored insights for urban planning and crime prevention
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".