论文概要
研究领域: CV 作者: Huy Che, Dinh-Duy Phan, Duc-Lung Vu 发布时间: 2026-07-13 arXiv: 2607.11830
中文摘要
车牌字符检测是智能交通系统的关键组件，需要高准确率和计算效率以实现实时部署。尽管近期基于深度学习的方法显著提升了检测性能，但许多高准确率模型依赖大规模架构，带来大量计算开销，限制了其在资源受限设备上的适用性。本文提出MicroCharNet，一种专为车牌字符检测设计的超轻量模型。所提架构采用由C2f块组成的紧凑主干，集成CoordAtt模块以增强特征提取同时保留空间信息。轻量C3k2-based neck融合多级特征，后跟单级无锚检测头实现端到端预测。在UFPR-ALPR数据集上的实验表明，MicroCharNet以仅0.08M参数和0.096 GFLOPs实现竞争性检测准确率，同时优于多个近期YOLO基线。硬件级评估进一步确认其在边缘设备上实时部署的效率。这些结果表明精心设计的超轻量架构能有效平衡车牌字符检测中的准确率和效率。
原文摘要
License plate character detection is a crucial component of intelligent transportation systems, where high accuracy and computational efficiency are required for real-time deployment. Although recent deep learning-based methods have substantially improved detection performance, many high-accuracy models rely on large-scale architectures that incur substantial computational overhead, limiting their applicability to resource-constrained devices. In this paper, we propose MicroCharNet, an ultra-lightweight model specifically designed for license plate character detection. The proposed architecture employs a compact backbone composed of C2f blocks, integrated with CoordAtt module to enhance feature extraction while preserving spatial information. A lightweight C3k2-based neck fuses multi-level…
— 自动采集于 2026-07-15
#论文 #arXiv #CV #小凯