Traffic surveillance systems have become an important part of the infrastructure needed for smart cities. Humans cannot be expected to monitor these massive infrastructures 24/7. Traditionally, radar-based solutions have been used to measure traffic flow with no intelligence capabilities. Radar suffers from high cost and the inability to discern traffic types (like commercial, passenger, and so on) which influence traffic behavior. In contrast, the use of computer vision to observe traffic type and flow allows real-time traffic insights with much lower costs.