基于多层级金字塔信息融合的曝光矫正方法  

Exposure correction method based on multi-level pyramid information fusion

作　　者：吴文江[1,2] 刘信君 郑飂默 王诗宇[1,2] 孙树杰 WU Wenjiang;LIU Xinjun;ZHENG Liaomo;WANG Shiyu;SUN Shujie(Shenyang Institute of Computing Technology,Chinese Academy of Sciences,Shenyang 110168,China;Shenyang CASNC Technology Co.,Ltd.,Shenyang 110168,China;University of Chinese Academy of Sciences,Beijing 100049,China;School of Electromechanical and Automotive Engineering,Yantai University,Yantai 264005,China)

机构地区：[1]中国科学院沈阳计算技术研究所,辽宁沈阳110168 [2]沈阳中科数控技术股份有限公司,辽宁沈阳110168 [3]中国科学院大学,北京100049 [4]烟台大学机电汽车工程学院,山东烟台264005

出　　处：《计算机集成制造系统》2024年第10期3578-3587,共10页Computer Integrated Manufacturing Systems

基　　金：国家自然科学基金资助项目(62002308);沈阳市中青年科技创新人才支持计划资助项目(RC210488);烟台市科技创新发展计划资助项目(2022JCYJ036);辽宁省博士科研启动基金计划资助项目(2023-BS-214)。

摘　　要：针对图像曝光不足和曝光过度的问题,设计了基于拉普拉斯金字塔结构的多层级信息融合曝光矫正网络,该网络每个层级的矫正模块采用类U-Net的编码器解码器架构。为了提高矫正模块的特征提取能力并减少模型参数量,设计了基于ConvNeXt-tiny的多尺度卷积编码器作为基本特征提取单元。针对图像上采样过程中可能出现的棋盘格伪影问题,提出一种基于双线性插值和亚像素卷积的双路上采样模块。通过定量和定性验证,在大规模曝光矫正数据集上均取得较好的结果。定位销定位实验显示,在不同对比度阈值下,应用该网络进行图像增强显著提升了特征可重复性、定位精度和稳定性。To address underexposure and overexposure in images,a multi-level information fusion exposure correction network based on the Laplacian pyramid structure was developed.Each network level adopted a U-Net-like encoder-decoder architecture in its correction module.A multi-scale convolutional encoder based on ConvNeXt-tiny was designed as the primary feature extraction unit to enhance feature extraction ability while reducing the model′s parameter count.To tackle the issue of checkerboard artifacts arising during image up-sampling,a dual-path up-sampling module combining bilinear interpolation and sub-pixel convolution was proposed.The network demonstrated effective results in both quantitative and qualitative validations on a large-scale exposure correction dataset.Dowel positioning experiments showed significant improvements in feature repeatability,positioning accuracy,and stability at varying contrast thresholds when the network was applied to image enhancement.

关 键 词：信息融合 曝光矫正 多尺度卷积编码器 双路上采样 

分 类 号：U238[交通运输工程—道路与铁道工程] TP391.41[自动化与计算机技术—计算机应用技术]