Multi-section landscape intervention for driving fatigue in extra-long tunnels: A real-road driving study based on visual perception and adaptation
Bibliographic record
Abstract
OBJECTIVE: The weak visual reference environment and prolonged driving duration in extra-long tunnels may induce driving fatigue accumulation, potentially compromising traffic safety. This study aims to investigate the impact mechanisms of multi-section landscape design on drivers' visual perception and adaptation capacities, and evaluate its effectiveness in alleviating driving fatigue. METHOD: This study was conducted in the Qinling Zhongnanshan Extra-Long Tunnel, which contained three special landscape zones. A total of thirty-two drivers were recruited to participate in real-world driving tests, and their eye movement behavior and pupil area data were collected using an eye tracker. The drivers' field of view was divided into six areas of interest (AOIs), and the spatial transfer characteristics of gaze points were analyzed. By combining kernel density estimation and visual sensitivity area (VSA) analysis, the differences in drivers' visual search breadth between the ordinary and fatigue-alleviating sections were compared. Additionally, the relative change rate of pupil area (RCRP) indicator was established to quantitatively evaluate the drivers' visual adaptation process to the landscape design. RESULTS: Landscape zones significantly improved drivers' visual perception patterns, with increased gaze transfer probabilities to roadside and top areas, and expanded horizontal VSA ranges. However, a noticeable contraction in gaze range occurred in the rear section of the tunnel, accompanied by a significantly decreased gaze transfer frequency. Pupil change analysis indicated that the landscape stimuli did not cause visual discomfort (RCRP < 20%), but revealed more sensitive pupil responses in middle and rear tunnel sections, suggesting a gradual decline in visual adaptation ability. CONCLUSION: The study demonstrates that multi-section landscape zones effectively regulate the allocation of drivers' visual attention by reconstructing the visual environment within tunnels. However, the intervention efficacy progressively attenuates with fatigue accumulation. Notably, drivers' visual adaptation capacity deteriorates prior to measurable declines in environmental perception. These findings provide critical evidence for optimizing fatigue-alleviating landscape design in extra-long tunnels.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".