Road Hazard Stimuli: Annotated naturalistic road videos for studying hazard detection and scene perception
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Driving requires vision, yet there is little empirical data about how vision and cognition support safe driving. It is difficult to study perception during natural driving because the experimental rigor required would be dangerous and unethical to implement on the road. The driving environment is complex, dynamic, and immensely variable, making it extremely challenging to accurately replicate in simulation. Our proposed solution is to study vision using stimuli which reflect this inherent complexity by using footage of real driving situations. To this end, we curated a set of 750 crowd-sourced video clips (434 hazard and 316 no-hazard clips), which have been spatially, temporally, and categorically annotated. These annotations describe where the hazard appears, what it is, and when it occurs. In addition, perceived dangerousness changes from moment to moment and is not a simple binary detection judgement. To capture this more granular aspect of our stimuli, we asked 48 observers to rate the perceived hazardousness of 1356 brief video clips taken from these 750 source clips on a continuous scale. These ratings span the entire scale, have high interrater agreement, and are robust to driving history. This novel stimulus set is not only useful for understanding drivers' ability to detect hazards, but is also a tool for studying dynamic scene perception and other aspects of visual function. While this stimulus set was originally designed for behavioral studies, researchers interested in other areas such as traffic safety or computer vision may also find this dataset a useful resource.
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.
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 | 0.004 | 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 | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 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 it