Published Paper Details:

This project presents an integrated system combining computer vision, deep learning, and IoT-based V2V (Vehicle-to-Vehicle) communication to improve road safety and enable smarter transportation solutions. The system is developed in three main stages. First, a real-time lane detection module is implemented using Python and OpenCV. It employs image processing techniques such as color thresholding, edge detection, and Hough Transform to accurately identify lane boundaries from a live camera feed, enhancing driver assistance and road alignment. Second, object detection is performed using the YOLOv3 deep learning model, which identifies surrounding vehicles, pedestrians, and other road objects from real-time video frames. YOLO's high-speed and accurate detection capability makes it suitable for safety-critical environments. The model processes input frames, applies non-maximum suppression to eliminate duplicate detections, and marks detected objects with bounding boxes and labels. Third, the V2V communication system is developed using the ESP32 microcontroller and IoT platform Blynk. This system monitors temperature and collision status using a DHT11 sensor and digital input pin. When critical conditions such as engine overheating or accidents are detected, alerts are displayed on an LCD and transmitted to a mobile application via Wi-Fi, enabling remote awareness. All three components work together to provide a robust and real-time vehicle monitoring and safety system. This approach not only aids in lane discipline and object awareness but also ensures timely communication in emergencies. The integration of vision-based detection, AI models, and IoT connectivity forms a foundation for future autonomous and connected vehicle technologies.