Vehicle tracking is no longer feasible due to population growth. It's a waste of time and resources. Tracking individual vehicles has become a very difficult task due to the tremendous development in the vehicular sector on a daily basis. This work proposes an automatic vehicle monitoring sys- tem for fast-moving automobiles using roadside sur- veillance cameras. In modern smart cities, license plate recognition systems are used in toll payment systems, parking charge payment systems, and residential access control. These electronic technologies are not only useful in people's daily lives, but it also provides management with safe and efficient services. An effective approach for rec- ognizing Indian automobile number plates has been im- plemented in the suggested algorithm. The proposed system is able to deal with noisy, low illumi- nated, cross angled, non-standard font number plates. This thesis presents effective deep learning-based ALPR (Au- tomatic License Plate Recognition) model using Character segmentation and CNN (Convolutional Neural Network) based recognition model. The experimental result gives an accuracy rate of f1 score of 94.94%.