Driver Monitoring Systems: Advances, Challenges, and Future Directions in Noncontact Sensor Technologies: A Review

Non-contact driver monitoring systems have gained traction as non-intrusive and non-invasive methods for assessing driver state. This survey reviews camera, radar, microphone, and vehicle-based sensing modalities, examining their operational principles, recent research findings, and integration considerations. Machine learning’s central role in gaze tracking, activity recognition, vital signs monitoring, and driver state prediction, is also explored. The survey highlights key challenges including limited ecological validity, demographic bias, privacy and ethical risks, and the need for real-time performance under edge-computing constraints. It also identifies key future directions, including multimodal sensor fusion, resource-efficient deployment, and integration with automated driving systems. This survey is a scoping review based on structured database searches that maps progress in non-contact driver monitoring, prioritising the latest research in view of rapid advances in sensing hardware, computer vision, and embedded AI. The synthesised findings offer practical guidance for engineers, vehicle manufacturers, and policymakers on deploying robust, privacy-preserving, and real-time driver monitoring solutions to improve road safety.