In this workshop, we will explore practical examples of how city surveillance cameras can be leveraged more effectively — particularly in traffic applications such as vehicle counting, travel time measurement, congestion detection, traffic violation monitoring, and identifying hazardous situations.

We will showcase modern AI-driven approaches, while also highlighting scenarios where even advanced methods may still fall short. Finally, we will touch on the role of large language models, such as ChatGPT, in supporting visual recognition tasks for smart city use cases — not only in transportation but across urban management as a whole.