Classification of Driver Behaviour Using External Observation Techniques for Autonomous Vehicles

-- Road traffic accidents remain a significant global concern, with human error, particularly distracted and impaired driving, among the leading causes. This study introduces a novel driver behavio u r classification system that uses external observation techniques to detect indicators of distraction and impairment. The proposed framework employs advanced computer vision methodologies, including real - time object tracking, lateral displacement analysi s, and lane position monitoring. The system iden tifies unsafe driving behaviour s such as excessive lateral movement and erratic trajectory patterns by implementing the YOLO object detection model and custom lane estimation algorithms. Unlike systems reliant on inter - vehicular communication, this vision - based approach enables behaviour al analysis of non - connected vehicles. Experimental evaluations on diverse video datasets demonstrate the framework ' s reliability and adaptability across varying road and environmental conditions. Road traffic accidents remain a significant global concern, with human error, particularly distracted and impaired driving, among the leading causes [1]. According to the World Health Organization's Global Status Report on Road Safety 2023, road traffic deaths reached an estimated 1.19 million people in 2021, with speeding, drunk driving, distracted driving, and unsafe vehicl es being primary contributors [1].