Published Paper Details:

Road safety is seriously threatened by foggy weather since it frequently results in decreased visibility and a higher chance of collisions. Conventional fog warning V2V communication systems are ineffective for real-time applications since they depend on infrastructure-based solutions or high-latency blockchain networks. To overcome these constraints, this study suggests a real-time fog detection and vehicle-to-vehicle (V2V) alert system that combines OpenCV-based image processing for fog detection with SUMO (Simulation of Urban MObility) to modify vehicle speed in low-visibility situations dynamically.The system records visual information in real-time, analyzes it to determine whether fog is present and how bad it is, and then sends out a warning. In the SUMO simulation, impacted cars are alerted when fog is detected, which causes them to slow down progressively to prevent crashes. This method is more affordable, lightweight, and scalable than sensor-dependent alternatives, allowing it to be adjusted for different road conditions without costly hardware installations.This system's low-latency warning transmission, which guarantees instant speed regulation upon identifying hazardous conditions, is one of its main advantages. Furthermore, realistic testing of traffic behavior in low visibility conditions is made possible by the SUMO-based simulation framework, which offers important insights into how cars ought to react in actual situations. According to experimental findings, dynamic speed adaption in foggy situations greatly improves road safety by lowering the likelihood of accidents and minimizing abrupt braking.