Road visibility is drastically reduced in adverse weather conditions such as fog, heavy rain, and haze due to the scattering and absorption of light by particles in the atmosphere. This reduction in visibility increases the chances of road accidents, which causes a serious threat to driver and passenger safety. To address this issue, various systems have been developed to detect vehicles and prevent collisions, particularly in low-visibility situations. This study focuses on creating an innovative solution by integrating IoT technology, including millimeter-wave (mmWave) radar, the Dark Channel Prior (DCP) algorithm, and YOLO Tiny, to enhance image clarity and improve vehicle detection accuracy. The use of DCP enhances visibility by removing haze from images, while YOLO Tiny ensures efficient and accurate real-time object detection. mmWave radar further strengthens the system by providing reliable detection even in dense fog. The use of ESP8266 also enables real-time communication of potential hazards between nearby vehicles, enabling a sort of Vehicle-to-Vehicle communication that alerts drivers. The proposed system is designed to deliver faster and more reliable results than existing methods, ensuring that drivers receive timely warnings to take preventive actions. The findings of this study demonstrate the effectiveness of combining IoT with advanced image processing techniques to improve road safety in low-visibility conditions. By reducing the risk of primary and secondary accidents, this solution paves the way for safer and more efficient transportation systems, even in challenging weather scenarios.