Efficient License Plate Recognition in Videos Using Visual Rhythm and Accumulative Line Analysis
Victor Nascimento Ribeiro, Nina S. T. Hirata
TL;DR
The paper addresses the computational burden of video-based ALPR by introducing two single-frame-per-vehicle approaches: Visual Rhythm (VR) and Accumulative Line Analysis (ALA). VR builds time–spatial representations and uses YOLO for mark detection to select a frame for license-plate OCR, while ALA uses a fixed line with background subtraction to pinpoint the moment a vehicle fully crosses the line for frame extraction. Compared to traditional frame-by-frame methods, both approaches deliver substantial speedups, with VR demonstrating higher robustness across lighting variations and OCR performance comparable to multi-frame baselines; ALA offers higher frame rates but lower recognition accuracy, indicating room for robustness improvements. The methods are validated on real video data, with detailed preparation, parameter choices, and public release of code, suggesting practical impact for real-time ALPR in traffic monitoring and enforcement scenarios.
Abstract
Video-based Automatic License Plate Recognition (ALPR) involves extracting vehicle license plate text information from video captures. Traditional systems typically rely heavily on high-end computing resources and utilize multiple frames to recognize license plates, leading to increased computational overhead. In this paper, we propose two methods capable of efficiently extracting exactly one frame per vehicle and recognizing its license plate characters from this single image, thus significantly reducing computational demands. The first method uses Visual Rhythm (VR) to generate time-spatial images from videos, while the second employs Accumulative Line Analysis (ALA), a novel algorithm based on single-line video processing for real-time operation. Both methods leverage YOLO for license plate detection within the frame and a Convolutional Neural Network (CNN) for Optical Character Recognition (OCR) to extract textual information. Experiments on real videos demonstrate that the proposed methods achieve results comparable to traditional frame-by-frame approaches, with processing speeds three times faster.