Classification of Driver Behaviour Using External Observation Techniques for Autonomous Vehicles
This addresses road safety by enabling autonomous vehicles to monitor non-connected vehicles for unsafe behaviors, though it is incremental as it builds on existing computer vision techniques.
The study tackled the problem of detecting distracted and impaired driving by developing a vision-based driver behavior classification system that analyzes external vehicle movements, achieving reliable performance across diverse road and environmental conditions in experimental evaluations.
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 behaviour 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 analysis, and lane position monitoring. The system identifies unsafe driving behaviours 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 behavioural analysis of non-connected vehicles. Experimental evaluations on diverse video datasets demonstrate the framework's reliability and adaptability across varying road and environmental conditions.