Machine Vision and Biometric Analysis for Detecting Driver Fatigue in Intelligent Transportation Systems

The research focuses on the development of a real-time driver fatigue detection system that integrates visual analysis and galvanic skin response (GSR) sensor data within automotive safety frameworks. The proposed approach utilizes a camera-based monitoring system to track facial behaviors, such as eye closure and mouth movements, while simultaneously collecting physiological responses through GSR measurements. The visual and physiological data are processed and analyzed to detect signs of drowsiness, allowing the system to issue timely alerts to the driver or initiate safety measures, such as automated safe parking. By combining multiple data sources, the system aims to enhance the accuracy of drowsiness detection and minimize false alarms that could result from relying on a single modality. Evaluation of the system’s performance demonstrated its effectiveness in various simulated driving conditions, with the multi-modal approach providing improved detection rates compared to traditional methods. The challenges of detecting subtle fatigue indicators and environmental variability were addressed through advanced image processing techniques and adaptive thresholding. The findings suggest that the integration of visual and physiological cues offers a viable solution for enlightening driver safety by reducing the risk of accidents caused by fatigue-related impairment.