Urban traffic congestion has emerged as a critical challenge due to rapid urbanization and increased vehicle density. Smart Traffic Management Systems (STMS), enhanced by artificial intelligence and object detection techniques, have shown promising potential in addressing these issues through real-time monitoring, adaptive signal control, and data- driven decision-making. This literature survey systematically reviews recent approaches in STMS design, focusing on the application of computer vision models such as YOLO (You Only Look Once), IoT infrastructure, cloud computing, and embedded systems. Key contributions of each system are analyzed in terms of traffic flow optimization, environmental impact reduction, cost-effectiveness, and emergency response capabilities. Additionally, the survey identifies common challenges such as sensor reliability, high deployment costs, scalability limitations, and cybersecurity concerns. By synthesizing findings across diverse methodologies, this paper highlights emerging trends and provides a comprehensive foundation for future research aimed at developing robust, scalable, and intelligent traffic management frameworks for smart cities.