The rapid development of road infrastructure, particularly expressways, has significantly improved transportation efficiency by reducing travel time. However, the increased frequency of accidents on these roads has raised safety concerns. According to statistics from the Indian Ministry of Road Transport and Highways, around 1.5 lakh people lose their lives on Indian roads each year. Surprisingly, an emerging cause of these accidents is attributed to "Driver Hypnotism." Long, congestion-free highways are believed to alter the state of mind of drivers, leading them into an unconscious state with their eyes open. This research proposes a deep learning-based model designed to efficiently detect driver hypnotism and implement appropriate countermeasures to reduce the likelihood of accidents on highways. The result shows that the accuracy rates of 71% in simulated driving experiments is obtained. The proposed method was compared with k-nearest neighbor (KNN) and random forest (RF). The results showed that the proposed model had better performance. This research provides a novel and convenient method to realize the driver’s road hypnosis detection function of the intelligent driver assistance system in practical applications.