With the exponential growth of vehicles on our streets, the need for finding an unoccupied parking spot today could most of the time be problematic, but even more in the coming future. Smart parking solutions have proved to be a helpful approach to facilitate the localization of unoccupied parking spots. In many smart parking solutions, sensors are used to determine the vacancy of a parking spot. The use of sensors can provide a highly accurate solution in terms of determining the status of parking lots. However, this is not ideal from a scalability point of view, since the need for installing and maintaining each of the sensors is not considered cost-effective. In the latest years vision based solutions have been considered more when building a smart parking solution, since cameras can easily be installed and used on a large parking area. Furthermore, the use of cameras can be developed to provide a more advanced solution for checking in at a parking spot and also for providing the information about whether a vehicle is placed unlawfully. In our thesis, we developed a dynamic vision-based smart parking prototype with the aim to detect vacant parking spots and illegally parked vehicles.