《计算机应用》唯一官方网站 ›› 2025, Vol. 45 ›› Issue (1): 301-307.DOI: 10.11772/j.issn.1001-9081.2024010121

• 多媒体计算与计算机仿真 • 上一篇    下一篇

基于多维空间卷积信息增强的低质车牌信息超分辨率重建

张睿1(), 惠永科1, 张延军2, 潘理虎1   

  1. 1.太原科技大学 计算机科学与技术学院,太原 030024
    2.太原科技大学 机械工程学院,太原 030024
  • 收稿日期:2024-02-02 修回日期:2024-04-24 接受日期:2024-04-24 发布日期:2024-05-09 出版日期:2025-01-10
  • 通讯作者: 张睿
  • 作者简介:张睿(1987—),男,山西太原人,副教授,博士,CCF高级会员,主要研究方向:智能信息处理、计算机视觉;zhangrui@tyust.edu.cn
    惠永科(1998—),男,河南南阳人,硕士研究生,主要研究方向:计算机视觉;
    张延军(1982—),男,山西太原人,教授,博士,主要研究方向:智能信息处理;
    潘理虎(1974—),男,山西太原人,教授,博士,CCF高级会员,主要研究方向:智能信息处理。
  • 基金资助:
    山西省基础研究计划项目(20210302123216);山西省产教融合研究生联合培养示范基地项目(2022JD11);山西省机械产品质量司法鉴定中心企业委托项目(2023254);太原科技大学研究生联合培养示范基地项目(JD2022004)

Super-resolution reconstruction for low-quality license plate information based on multi-dimensional spatial convolutional information enhancement

Rui ZHANG1(), Yongke HUI1, Yanjun ZHANG2, Lihu PAN1   

  1. 1.College of Computer Science and Technology,Taiyuan University of Science and Technology,Taiyuan Shanxi 030024,China
    2.School of Mechanical Engineering,Taiyuan University of Science and Technology,Taiyuan Shanxi 030024,China
  • Received:2024-02-02 Revised:2024-04-24 Accepted:2024-04-24 Online:2024-05-09 Published:2025-01-10
  • Contact: Rui ZHANG
  • About author:HUI Yongke, born in 1998, M. S. candidate. His research interests include computer vision.
    ZHANG Yanjun, born in 1982, Ph. D., professor. His research interests include intelligent information processing.
    PAN Lihu, born in 1974, Ph. D., professor. His research interests include intelligent information processing.
  • Supported by:
    Basic Research Program of Shanxi Province(20210302123216);Shanxi Provincial Industry-Education Integration Joint Graduate Training Demonstration Base Project(2022JD11);Enterprise Entrusted Project of Shanxi Provincial Machinery Product Quality Judicial Appraisal Center(2023254);Joint Graduate Training Demonstration Base Project of Taiyuan University of Science and Technology(JD2022004)

摘要:

现有交通监控终端采集到的车辆影像通常存在远景低分辨率现象,并伴随有强噪、模糊、过曝、欠曝等一些不确定性像素影响因素,导致车牌信息智能识别的精度难以保证。针对上述问题,提出基于多维空间卷积信息增强的低质车牌信息超分辨率重建(LL-SR)网络。首先,利用卷积挖掘空间与通道特征点的相关性,聚合浅层特征;其次,从不同感受野和不同维度挖掘特征图之间的关联关系,从而恢复车牌信息的高频细节;最后,对得到的不同尺度特征进行跨通道像素级融合和矫正,以减少无用特征在上下文的传播,实现低质车牌信息的超分辨率重建。在太原车牌(LT)和美国车牌(LU)数据集上的实验结果表明,所提网络的峰值信噪比(PSNR)和结构相似性(SSIM)分别为26.682 4 dB和0.820 3及22.356 7 dB和0.781 3,相较于NGramSwin(N-Gram in Swin transformers)和CARN(CAscading Residual Network)分别提升了0.210 9 dB和1.736 1 dB、0.005 7和0.033 0及0.472 8 dB和1.419 2 dB、0.019 6和0.039 9;且重建后的车牌信息具有更好的视觉效果。

关键词: 低质车牌信息, 高质量重建, 卷积计算, 交通监控

Abstract:

Vehicle images collected by the existing traffic monitoring terminals often have low resolution in distant view, accompanied by uncertain pixel influencing factors such as strong noise, blur, overexposure, and underexposure, making it difficult to ensure accuracy of intelligent recognition of license plate information. In response to the above issue, Super-Resolution reconstruction for Low-quality License plate information based on multi-dimensional spatial convolutional information enhancement (LL-SR) network was proposed. Firstly, the correlation of feature points in space and channels mined by convolution were used to aggregate shallow feature. Secondly, correlation between feature maps was mined from different receptive fields and different dimensions, so as to recover high-frequency details of license plate information. Finally, the obtained features of different scales were fused and corrected at pixel level across channels to reduce propagation of useless features in context, thus achieving super-resolution reconstruction of low-quality license plate information. Experimental results on License plate of Taiyuan (LT) and License plates of the United States of America (LU) datasets show that the Peak Signal-to-Noise Ratio (PSNR) and Structural SIMilarity (SSIM) of the proposed network are 26.682 4 dB, 0.820 3 and 22.356 7 dB, 0.781 3 respectively, which are improved by 0.210 9 dB, 1.736 1 dB; 0.005 7, 0.033 0; and 0.472 8 dB, 1.419 2 dB; 0.019 6, 0.039 9 respectively compared to those of NGramSwin (N-Gram in Swin transformers) and CARN (CAscading Residual Network). Moreover, the license plate information reconstructed by the proposed network has better visual effects.

Key words: low-quality license plate information, high-quality reconstruction, convolution computation, traffic monitoring

中图分类号: