Automated Pedestrian Safety Analysis at a Signalized Intersection in New York City: Automated Data Extraction for Safety Diagnosis and Behavioral Study
Bibliographic record
Abstract
Automated computer vision techniques were used to analyze 2 h of video data collected at a major signalized intersection in New York City. The main objectives of this study were to diagnose pedestrian safety issues and identify contributing factors at the intersection and to demonstrate the feasibility of the automatic extraction of pedestrian data required for pedestrian behavior analysis—mainly pedestrian speed and gait parameters. The safety study was conducted with traffic conflict techniques. The main factor that contributed to the high number of pedestrian and vehicle conflicts was found to be pedestrian violations, mainly temporal violations in which pedestrians crossed the street during the “Don't Walk” or flashing “Don't Walk” phase. During the 2 h analyzed, about one-third of pedestrians were noncompliant with the signal timing or crosswalk boundary (17.9% spatial violations and 15.3% temporal violations). Pedestrian speed, step frequency, and step length were automatically extracted for 333 pedestrians and were found to follow the normal distribution with 95% confidence (mean and standard deviation of 1.47 ± 0.27 m/s, 1.96 ± 0.17 Hz, and 0.75 ± 0.14 m, respectively). Gait analysis showed that the walking speed for single pedestrians was 9% higher than for those who walked in groups. Males tended to be slightly faster than females, with higher step length but lower step frequency. Violators tended to have higher walking speeds compared with non-violators, and the difference in speed was dependent on step length but not on step frequency.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.004 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".