Exposure correction method based on multi-level pyramid information fusion

被引：0
|
作者：
Wu, Wenjiang [1 ,2 ]
Liu, Xinjun [1 ,3 ]
Zheng, Liaomo [1 ,2 ]
Wang, Shiyu [1 ,2 ]
Sun, Shujie [4 ]
机构：
[1] Shenyang Institute of Computing Technology, Chinese Academy of Sciences, Shenyang,110168, China
[2] Shenyang CASNC Technology Co., Ltd., Shenyang,110168, China
[3] University of Chinese Academy of Sciences, Beijing,100049, China
[4] School of Electromechanical and Automotive Engineering, Yantai University, Yantai,264005, China
来源：
Jisuanji Jicheng Zhizao Xitong/Computer Integrated Manufacturing Systems, CIMS | 2024年 / 30卷 / 10期
关键词：
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 mod-el 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 networkdemonstrated 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 accura- cy; and stability at varying contrast thresholds when the network was applied to image enhancement. © 2024 CIMS. All rights reserved;
D O I：
10.13196/j.cims.2023.0199
中图分类号：
学科分类号：
摘要：
引用
收藏
页码：3578 / 3587
相关论文
共 50 条
  • [31] Image fusion using a multi-level image decomposition and fusion method
    Tian, Yu
    Yang, Wenjing
    Wang, Ji
    APPLIED OPTICS, 2021, 60 (24) : 7466 - 7479
  • [32] An efficient method to improve iris recognition performance based on multi-level fusion
    Wang, Fenghua
    Zhang, Xinman
    2012 INTERNATIONAL WORKSHOP ON IMAGE PROCESSING AND OPTICAL ENGINEERING, 2012, 8335
  • [33] Damage Detection Method for Rail Surface Based on Multi-Level Feature Fusion
    Han Q.
    Liu J.
    Feng Q.
    Wang S.
    Dai P.
    Zhongguo Tiedao Kexue/China Railway Science, 2021, 42 (05): : 41 - 49
  • [34] An InSAR Interferogram Filtering Method Based on Multi-Level Feature Fusion CNN
    Yang, Wang
    He, Yi
    Yao, Sheng
    Zhang, Lifeng
    Cao, Shengpeng
    Wen, Zhiqing
    SENSORS, 2022, 22 (16)
  • [35] Action Recognition Method Based on Multi-Level Feature Fusion and Temporal Extension
    Wu, Haoyuan
    Xiong, Xin
    Min, Weidong
    Zhao, Haoyu
    Wang, Wenxiang
    Computer Engineering and Applications, 2023, 59 (07) : 134 - 142
  • [36] Systems Engineering for Information Fusion: Towards Enterprise Multi-Level Fusion Integration
    Solano, Marco A.
    Carbone, John
    2013 16TH INTERNATIONAL CONFERENCE ON INFORMATION FUSION (FUSION), 2013, : 121 - 128
  • [37] A phase field method based on multi-level correction for eigenvalue topology optimization
    Qian, Meizhi
    Hu, Xindi
    Zhu, Shengfeng
    COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 2022, 401
  • [38] Appearance-based gaze estimation with feature fusion of multi-level information elements
    Ren, Zhonghe
    Fang, Fengzhou
    Hou, Gaofeng
    Li, Zihao
    Niu, Rui
    JOURNAL OF COMPUTATIONAL DESIGN AND ENGINEERING, 2023, 10 (03) : 1080 - 1109
  • [39] Multi-dimension and Multi-level Information Fusion for Facial Expression Recognition
    Bie, Mei
    Xu, Huan
    Liu, Quanle
    Gao, Yan
    Che, Xiangjiu
    JOURNAL OF IMAGING SCIENCE AND TECHNOLOGY, 2023, 67 (04) : 1 - 11
  • [40] Multi-level information fusion for missing multi-label learning based on stochastic concept clustering
    Liu, Zhiming
    Li, Jinhai
    Zhang, Xiao
    Wang, Xizhao
    INFORMATION FUSION, 2025, 115
12345