The Impact of Surrounding Road Objects and Conditions on Drivers Abrupt Heart Rate Changes
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 investigates the relationship between specific road objects and abrupt increases in drivers’ heart rate (HR), using HR as an objective proxy for stress. Motivated by the need to mitigate driver stress and negative emotions to improve safety and human-centered driving experiences, the authors hypothesize that stress-inducing environmental attributes, such as large vehicles or intersections, correlate with sudden HR spikes. Unlike prior research relying on subjective self-reports, this work utilizes naturalistic multimodal data to analyze real-time physiological and visual responses. The researchers analyzed data from the HARMONY naturalistic driving dataset, comprising approximately 2 hours of driving per participant from 15 individuals (ages 21–33). Data collection involved dual dash cameras recording interior and exterior views at 30 fps and Android smartwatches monitoring HR via photoplethysmography at 1 Hz. To identify stress events, the authors applied a Bayesian Change Point detection method to HR data, extracting segments with a high probability of change (≥0.8). For each detected change point, they analyzed 10 seconds of video prior to the event. Exterior frames were processed using a pre-trained Mask R-CNN algorithm to detect road objects (e.g., trucks, pedestrians, traffic lights), while interior frames were analyzed using Affectiva iMotion software to measure facial engagement, a metric of emotional expressivity. The results demonstrate that the probability of encountering specific road objects increases significantly as drivers approach an abrupt HR increase. Linear regression confirmed that the presence of traffic lights, trucks, pedestrians, and other vehicles rises significantly in the seconds preceding HR change points (p < 0.0001 for trucks, pedestrians, and vehicles). Notably, pedestrians and vehicles showed an abrupt spike ±1 second before the change point, suggesting immediate reactions to sudden environmental changes. Environmental analysis revealed that city driving involves a wider variety of stress-inducing objects compared to highways, where trucks were the primary trigger. Furthermore, drivers’ facial engagement increased significantly at the moment of HR change points, indicating a synchronized physiological and expressive response to environmental stressors. These findings establish a link between external visual stimuli and internal physiological states, supporting the hypothesis that specific road objects trigger measurable stress responses. The study implies that computer vision and wearable sensors can be integrated to detect and mitigate driver stress in real-time. This approach lays the groundwork for human-centered vehicle designs, such as empathetic routing systems that avoid high-stress environments, thereby enhancing driver well-being and safety. Future work aims to refine object detection accuracy and explore individual differences in stress responses.
Key finding
In naturalistic driving, the probability of stress-related exterior objects (large vehicles, pedestrians, intersections) rises in the seconds leading up to abrupt heart-rate increases, and facial engagement rises in the same window — exterior context predicts driver psychophysiological excursions.
Methodology
naturalistic
Sample size: HARMONY dataset (multi-participant)
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. Discovered via tag_papers on 2026-05-30.
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | — | — | — | 1 | 2026-05-07 |
| archive | success | canonical_url | — | — | 2 | 2026-06-03 |
| extract | success | cached | — | — | 2 | 2026-06-10 |
| clean | success | — | — | — | 1 | 2026-06-01 |
| chunk | success | — | — | — | 1 | 2026-06-01 |
| embed | success | — | — | — | 1 | 2026-06-02 |
| enrich | success | — | — | — | 1 | 2026-05-07 |
| promote | success | — | — | — | 3 | 2026-06-06 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 2 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 16 | 2026-06-11 |
| verify | partial | — | — | — | 2 | 2026-06-10 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified_with_issues.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
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: physiological data, behavioral performance data
- Methodological Resource: dataset resource