ILL-Park: A Deep Learning Approach of Illegal Parking Detection
Keywords:
Selected:Deep Learning, Illegal parking detection, Object detectionAbstract
Illegal parking in the Philippines was prévalent, this is a critical problem in large, growing cities such as Metro Manila, Metro Cebu, Metro Davao, and other cities in the Philippines. Currently, the responsibility for detecting illegally parked vehicles has been left to law enforcement, which often requires manual inspection. The aim of this study is to detect public and private vehicles that are illegally parked on sidewalks and parked within the driving lane. To improve the efficiency of law enforcement for vehicle parking management, the researchers proposed an illegal parking detection based on an existing deep learning approach. Upon training Epoch 41/50 being the best model to be used having a 96.41 training accuracy and 92.13 validation accuracy.