Hazard Detection Prediction Model for Rural Roads Based on Hazard and Environment Properties
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This study addresses the critical issue of road safety in Iran, where rural roads account for over 70% of traffic fatalities, particularly among young and novice drivers. The research focuses on hazard detection, the initial step in preventing crashes, by investigating how specific hazard and environmental properties influence a driver’s ability to perceive danger. While previous literature has largely emphasized human factors like age and experience, this paper prioritizes the physical characteristics of hazards—such as size, color, contrast, motion, and lighting conditions—to develop a predictive model for hazard detection scores. The methodology employed a driving simulator named "Nasir," which replicates a two-lane rural highway environment using three LCD screens and realistic vehicle mechanics. The study involved 90 participants, divided equally into 45 experienced drivers (1–15 years of experience) and 45 novice drivers (less than one year of experience). Participants encountered various hazards, including pedestrians, animals, and objects, which varied in size, color, and mobility. Data were collected by recording the time of hazard detection (indicated by horn pressing), hazard trigger, and arrival at the hazard location. These metrics were used to calculate a Hazard Detection Indicator (RI), which was converted into a detection score ranging from 0 to 100. To analyze the complex interactions between variables, the researchers developed a Takagi-Sugeno fuzzy model using MATLAB, with inputs including hazard size, color wavelength, contrast, day/night conditions, warning signs, motion status, and driver experience. The results demonstrate significant variations in hazard detection based on environmental and hazard properties. Nighttime driving reduced detection ability by 35% for experienced drivers and 64% for novice drivers compared to daytime conditions. Motion played a crucial role, with moving hazards increasing detection ability by 9% for experienced drivers and 180% for novices compared to fixed hazards. Additionally, larger hazard sizes, higher contrast between the hazard and environment, and longer wavelength colors (under optimal conditions) improved detection scores. The fuzzy model revealed that these factors affect detection through nonlinear functions, with detection scores varying significantly under "best" (daytime, high contrast, moving, large) versus "worst" (nighttime, no contrast, fixed, small) hypothetical conditions. The significance of this research lies in its provision of a quantitative scoring model that predicts hazard detection based on specific hazard properties. This tool can assist in prioritizing road safety improvements, designing better hazard perception tests for driver licensing, and developing novel road safety audit methods. By highlighting the disproportionate vulnerability of novice drivers and the critical impact of visibility factors like contrast and lighting, the study offers actionable insights for reducing vehicle-pedestrian, vehicle-animal, and vehicle-object crashes on rural roads.
Provenance
The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | Crossref | — | — | 1 | 2026-06-08 |
| archive | success | canonical_url | — | — | 1 | 2026-06-09 |
| extract | success | pdftotext | — | — | 2 | 2026-06-09 |
| clean | success | clean | — | — | 1 | 2026-06-09 |
| chunk | success | chunk | — | — | 1 | 2026-06-09 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-09 |
| promote | success | — | — | — | 1 | 2026-06-08 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 1 | 2026-06-09 |
| tag | success | vector_similarity | — | — | 8 | 2026-06-11 |
| verify | success | — | — | — | 1 | 2026-06-09 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-09; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
- hazard perception
- hazard perception training
- rail grade crossings
- roadway lighting effects
- motorcycle conspicuity
- looked but failed to see
Information type
What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).
- Empirical Findings: crash risk outcomes