Efficient License Plate Recognition in Videos Using Visual Rhythm and Accumulative Line Analysis

TL;DR

This paper introduces two efficient methods for license plate recognition in videos that significantly reduce computational load by extracting a single representative frame per vehicle and using novel analysis techniques, achieving comparable accuracy with faster processing.

Contribution

The paper presents Visual Rhythm and Accumulative Line Analysis methods for single-frame license plate recognition, reducing computational requirements while maintaining accuracy.

Findings

Processing speed is three times faster than traditional methods.

Methods achieve comparable recognition accuracy to frame-by-frame approaches.

Real video experiments validate the efficiency and effectiveness of the proposed techniques.

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.