A new AI-powered vehicle identification system uses computer vision to recognize vehicle attributes at gas stations, improving security and efficiency.
Researchers developed an AI-powered system to identify vehicles at gas stations, using image processing and deep learning techniques. The system can recognize attributes such as vehicle make, license plate, and fueling information. This approach eliminates the need for expensive hardware and reduces electronic waste, making it a more environmentally friendly option.
Abstract
In many countries around the world, retail fuel sales have to be recorded and monitored with specific vehicle information such as license plate by government institutions and station managers. Different hardware methods are utilized to achieve this goal such as UHF (Ultra high frequency) vehicle identification tags installed on the vehicles. To extract data from the tags, RFID-UHF antennas need to be installed on the nozzle for the recognition of vehicles today, which implies an increase in hardware costs per vehicle. Additionally, the electronic waste generated by the hardware used for vehicle recognition hurts the environment. In this study, the aim is to provide a comprehensive solution that enhances the modern automotive world's efficiency, security, and convenience. The core objective of this study is to design and implement a cutting-edge Vehicle Identification System (VIS) that leverages the power of Artificial Intelligence and Computer Vision. The proposed system has the ability to recognize various critical attributes of vehicles at gas stations, including the vehicle make, license plate, vehicle type, color, and fueling information. The system utilizes advanced Image Processing and Deep Learning techniques to achieve precise identification and classification, improving security, and law enforcement.
References
- 1.Deep learning with Python, F. Chollet
- 2.An Introduction to Convolutional Neural Networks, Keiron O'Shea and Ryan Nash
- 3.The Pascal Visual Object Classes Challenge, Mark Everingham Luc Van Gool
- 4.ImageNet Large Scale Visual Recognition Challenge, Olgsa Russakovsky Jia Deng Hao Su
- 5.ultralytics/yolov5 – github
- 6.Pytorch
- 7.PPOCRv3 More Attempts for the Improvement of Ultra Lightweight Ocr System
- 8.https://platesmania.com/Link
- 9.https://www.kaggle.com/Link
- 10.https://www.makesense.ai/Link
- 11.https://www.ultralytics.com/Link
- 12.https://docs.ultralytics.com/yolov5/tutorials/architecture_description/Link
- 13.PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System
- 14.Nvidia TensorRT