Unified Chinese License Plate Detection and Recognition with High Efficiency

TL;DR

This paper introduces a large Chinese License Plate dataset and a unified, real-time detection and recognition network that achieves competitive performance efficiently.

Contribution

The work provides the largest Chinese LP dataset with detailed annotations and proposes a unified, high-efficiency detection and recognition network for Chinese license plates.

Findings

Achieved 30 fps inference at 640p resolution.

Demonstrated competitive performance on public benchmarks.

Provided the largest annotated Chinese LP dataset publicly.

Abstract

Recently, deep learning-based methods have reached an excellent performance on License Plate (LP) detection and recognition tasks. However, it is still challenging to build a robust model for Chinese LPs since there are not enough large and representative datasets. In this work, we propose a new dataset named Chinese Road Plate Dataset (CRPD) that contains multi-objective Chinese LP images as a supplement to the existing public benchmarks. The images are mainly captured with electronic monitoring systems with detailed annotations. To our knowledge, CRPD is the largest public multi-objective Chinese LP dataset with annotations of vertices. With CRPD, a unified detection and recognition network with high efficiency is presented as the baseline. The network is end-to-end trainable with totally real-time inference efficiency (30 fps with 640p). The experiments on several public benchmarks demonstrate that our method has reached competitive performance. The code and dataset will be publicly available at https://github.com/yxgong0/CRPD.