Real-Time Automatic License Plate Recognition Using YOLOv8, SORT Tracking, and Temporal Data Interpolation
Researchers have developed a new five-stage pipeline for real-time automatic license plate recognition (ALPR) designed to overcome challenges like poor lighting and high vehicle speeds. The system utilizes the YOLOv8 nano model for initial vehicle detection, followed by the SORT algorithm for tracking objects across frames. It then employs a specialized YOLOv8 detector for license plates, feeding the cropped images to an EasyOCR chain for character recognition, and incorporates temporal data interpolation to mend fragmented tracking paths. AI
IMPACT This research could improve the accuracy and reliability of automated license plate recognition systems in challenging real-world conditions.