This study focuses on the use computer vision technology to collect data in real time and identify black ice on roadways in an effort to improve road safety and lower the probability of accidents. In order to continuously monitor environmental parameters, the system makes use of a variety of Internet of Things sensors, including those that measure temperature, humidity and road surface condition. Black ice has just been recognized as a main cause of transportation chances due to detecting problems on the road. It is vital to deliver traffic user with black ice notices before to tolerate commutation protection. The identity of black ice is a hard creativity, meanwhile it requires the fixing of monitoring places and demands often guide inspection. Together with a microcontroller and Real-Time Clock (RTC), these sensors collect vital data that is analysed to identify the occurrence of black ice. Using machine learning algorithms, which accurately forecast and identify black ice events, the real-time facts is sent to a cloud-based platform to study. Road officials and drivers receive instant warning from the system, ensuring prompt action. The data processing techniques, sensor integration and hardware and software architecture are all covered in detail in this study. It also covers system reliability, field trial findings and possible uses in smart cities. Suggested solution shows how IoT technology and road safety solutions may work together to detect black ice in an effective and scalable manner.