A Smart Car Parking System Based on IoT with Gray Wolf Optimization-Probability Correlated Neural Network Recognition Methods

The use of vehicles is increasing every day because of the growing industrialization. Hence, parking the vehicles in the metropolitan cities could create the traffic congestion, which is one of the major problem need to be resolved in the smart city systems. For this purpose, this research work intends to develop a smart car parking system with proper controlling and monitoring units. The main motive of this work was to avoid the traffic congestion by developing an advanced car parking system with the help of Internet of Things (IoT) technology. Also, an image processing technique is utilized in this framework for identifying whether the car is present or not in the parking area. In which, an Anisotropic Diffusion Gaussian Filtering (ADGF) technique is utilized to preprocess the given image for improving the quality and reducing the noise effects. After that, the Grey Level Co-occurrence Matrix (GLCM) is employed to extract the contrast, correlation, energy and homogeneity features. After that, the suitable number of features are optimally selected by using the Grey Wolf Optimization (GWO) technique, which efficiently improves the speed of operation. Finally, the Probability Correlated Neural Network (PCNN) technique deployed for accurately recognizing that whether the car is present or not. For validation, the performance of this scheme is evaluated and compared by using various measures.