Enhancing Automative Face Recognition And With Distraction Detection System

Abstract

Driver Distraction Is A Significant Factor Contributing To Road Accidents Worldwide. According To Statistics, Distracted Drivers Are Three Times More Likely To Be Involved In A Crash Than Non-distracted Drivers. Therefore, Detecting Driver Distraction Is Crucial For Improving Road Safety. Many Previous Studies Have Proposed Various Methods For Driver Distraction Detection, Including Image-based, Sensor-based, And Machine Learning-based Approaches. However, These Methods Have Limitations In Terms Of Accuracy, Complexity, And Real-time Performance. This Project Proposes A Novel Approach To Driver Distraction Detection Using The You Only Look Once (YOLO) Object Detection Algorithm With A Convolutional Neural Network (CNN). The Proposed Model Consists Of Two Main Stages: Object Detection Using YOLO And Classification Of The Detected Objects. The YOLO Algorithm Is Used To Detect And Locate Various Objects In The Driver's Environment, Including The Driver's Face And Hands, And Other Objects That May Cause Distraction. Then, The Detected Objects Are Classified Using A CNN To Determine Whether The Driver Is Distracted Or Not. The Proposed Model Is Evaluated Using A Public Dataset And Achieves High Accuracy In Detecting Driver Distraction. And Also Analyse The Drowsiness Of Driver Based On Eye Features Using CNN Algorithm. The Proposed Method Has The Potential To Be Integrated Into Advanced Driver Assistance Systems To Improve Road Safety With Real Time Environments.

Keywords