Smart Driver Monitoring System with Live Alerts Using Flask YOLOv10

Project Code :TCMAPY1957

Objective

This project presents a Smart Driver Monitoring System that uses a YOLOv10 deep-learning model to detect various driver behaviors through a live camera feed. The system identifies actions such as drowsiness, distraction, phone use, drinking, eating, smoking, seatbelt status, and safe driving. A Flask-based web application is developed to manage user interaction, including registration, login, and access to the detection module. The trained model processes real-time video frames and displays detection results in the browser with good accuracy. An automated email alert feature notifies the administrator whenever unsafe behavior, especially drowsiness is detected. The system provides a simple and responsive interface using HTML, CSS, and JavaScript, ensuring smooth communication between the backend and frontend. Overall, the project demonstrates the successful integration of computer vision, deep learning, and web technology for driver safety monitoring.

Abstract

This project presents a Smart Driver Monitoring System built using Flask and YOLOv10 to detect unsafe driver behaviors through live camera input. The system identifies multiple driver states, including distracted, drowsy, drinking, eating, phone use, safe driving, seatbelt, and smoking. The detection workflow is supported by a custom dataset and a trained YOLOv10 model that processes video frames in a browser interface. When unsafe behavior such as drowsiness or distraction is identified, the system sends a notification email to the administrator for immediate attention. The platform includes user modules such as Home, Register, Login, Detection, and Logout, providing a complete and structured interface for users. The combination of Flask on the backend and HTML, CSS, and JavaScript on the frontend ensures seamless communication between the detection model and the user interface. This system aims to assist in monitoring driver conditions and promoting safer driving practices through automated identification and alerting. Its simple design and efficient processing make it suitable for projects focused on driver behavior analysis, safety systems, and computer-vision-based monitoring frameworks.

Keywords: Driver Monitoring, YOLOv10, Flask, Detection System, Drowsiness, Distraction, Email Alerts, Computer Vision, Safety Monitoring, Behavior Analysis

NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.