Increasing the number of vehicles is challenging for governing the rules in traffic signals, so it is very important to accurately capture the character on the number plate. This study presents a novel approach utilizing a light-weighted customized YOLOv9 deep learning model integrated with IoT-enabled RFID technology. The system aims to overcome challenges posed by varying environmental conditions and high vehicle volumes, particularly in densely populated areas like India. The real-time object detection YOLO model detects number plates, and Optical Character Recognition (OCR) is used to extract characters from the detected number plate. RFID can be used to capture the number plates of multiple vehicles parallel in different weather conditions and different lighting conditions, which is difficult to identify by the ANPR camera. The literature review is expanded to provide a comprehensive analysis of existing methods, highlighting gaps addressed by our approach. The YOLOv9 custom model has the ability to detect and identify a vast array of objects in images and videos, with an accuracy of 98%. YOLO and RFID are used for two-step verification that will be directly implemented in smart traffic management systems.