Integrating Facial Indicators for Enhanced Road Safety by Using Deep Learning Models
摘要
Rising driver fatigue-related accidents are a significant concern. A device that detects and alerts fatigued drivers quickly may help prevent accidents. Rage, stress, and long-term health issues can result from driving. Interest in integrating new technology that understands human emotions into cars has increased. For years, researchers have studied real-time emotional intelligence. The suggested approach would reduce driver fatigue and exhaustion-related accidents, boosting transportation safety. Recently, this has become a major cause of accidents. Facial expressions and body movements indicate driver tiredness and weariness, which include yawning and eye fatigue. These traits indicate poor driver health. A CNN model can detect tiredness by counting blinks. It measures the space between the lower and upper lips and compares it to a threshold value to identify yawns. The mixing module alerts the driver if they yawn or become fatigued. The suggested approach would reduce road accidents and fatalities while contributing to technological advances.