Automated Vehicle speed Estimation and License Plate Detection for Smart Cities Development

Currently, the vehicle count is increasing progressively, subsequently, are road crimes, and accident cases escalating. Even though the government of smart cities has imposed certain laws and traffic rules to reduce the number of road accidents and deaths, the younger generations are still doing rash driving. Therefore, there is an urgent need to implement an automated system to keep an eye on the speedy vehicles and take further actions for maintaining the development of smart cities. The major aim of the paper is to perform the practical implementation of the system using the available Pytesseract, Haar Cascade and dlib library. This model initially performs the detection of vehicles, then estimates the vehicle speed, and finally recognizes the license plates of the speedy vehicles. The paper provides a comparison using four different video datasets to analyze the performance of the implemented system. On the basis of the observations, the implemented model acquires a recall of 89.02% and a precision of 91.9%.