Detection and counting of vehicles using deep learning in a parking lot area of a university institution

Abstract

This article describes the implementation of two artificial neural networks with deep learning for the detection and counting of vehicles in the main parking area of ​​a university institution in Lima-Peru, Universidad Ricardo Palma. Likewise, the objective set was to obtain the number of available parking spaces to reduce the consultation time by the security personnel of said institution. Convolutional neural networks were used: You Only Look Once v5 (YOLO v5) and Faster Region-based Convolutional Neural Network (Faster RCNN), and Transfer Learning was applied. The dataset was made up of images from the place and obtained from the web. To count vehicles, space limitation was used, by the line of interest (LOI) and region of interest (ROI). And, for the graphical user interface, the Tkinter library was chosen, which allowed the detected vehicles and available spaces to be numerically displayed. Finally, for real-time implementation, a mobile phone was installed above the third gate of the university itself, using the university's Internet network and connected to a laptop; and, the YOLO network was chosen, after evaluating the parameters of mAP, FPS, error rate and false positives.