Design of Smart Open Parking Using Background Subtraction in the IoT Architecture

Abstract

The Internet of Things (IoT) has evolved and penetrated to our live since the end of the last century. Nowadays, many devices for any purpose are connected through the Internet. A smart node, in smart campus environment, can detect an availability of an open parking space by calculating the vehicle that enters or outs from the space. The node applies a background subtraction method, which is deployed in IoT architecture. The Gaussian Mixture Model (GMM) is utilized to determine foreground and background image, in order to detect a moving object at an open area. Furthermore, the node can discriminate the type of vehicle with a high accuracy. The result of vehicle type classification is transmitted by the node through the Internet, and then it is saved to the data server. We observe the designed system succeeds delivering a good performance in terms of average accuracy determining car and motorcycle are 93.47% and 91.73%, respectively.