基于临界闪光融合频率和多模态眼部特征的疲劳筛查方法
By capturing images of the driver's eyes under flickering in-vehicle light, and combining pupil diameter and reaction time, a user fatigue value is generated. This solves the problems of lag and individual differences in fatigue detection in existing technologies, and achieves real-time and accurate fatigue monitoring, which is suitable for central fatigue screening during driving.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- DIGITAL HUAHONG MEDICAL TECHNOLOGY (SHENZHEN) CO LTD
- Filing Date
- 2025-07-18
- Publication Date
- 2026-07-17
AI Technical Summary
Existing fatigue detection methods suffer from problems such as strong detection lag, significant individual differences, and sensitivity to external lighting and occlusion during driving, making it difficult to achieve highly reliable real-time fatigue monitoring, especially without affecting the execution of driving tasks.
By setting up light sources inside the vehicle to flash at different frequencies, continuous images of the driver's eyes are simultaneously acquired, and pupil diameter and reaction time are extracted. Combined with critical flash fusion frequency and multimodal eye features, user fatigue values are generated and monitored and compared in real time during driving, triggering fatigue signals and warnings.
It enables dynamic and intermittent fatigue screening without affecting driving behavior, improving the accuracy and applicability of central fatigue detection, reducing false alarms and missed alarms, and is suitable for continuous fatigue monitoring in actual driving processes.
Smart Images
Figure CN120983041B_ABST