Abstract—Traffic violations cause significant problems such as congestion, accidents, and deaths. It is highly desirable to have an effective automated system to detect and record these violations, thus improving traffic regulation enforcement and reducing human intervention. The proposed work aims to develop a cost-effective, efficient, and robust system that automatically detects traffic violations. The proposed system uses background subtraction technology to detect moving vehicles and the time and distance over which vehicles move to detect violations. The You Only Look Once (YOLO) and Convolutional Recurrent Neural Networks (CRNN) algorithms are utilized to identify the license plates (LPs) of violating vehicles with great accuracy, so that LPs are recognized using Optical Character Recognition (OCR) technology. The results achieved from our trial indicate promising system performance, with multiple violation realtime detection rate of 98.06% and an LP recognition accuracy of 98.22%. The superiority of the proposed work over other previous approaches has been proved in the comparison results.