Axis-Based Transformer UNet for RGB Remote Sensing Image Denoising

被引:0
|
作者
Zhu, Zhiliang [1 ]
Zhang, Siyi [1 ]
Qiu, Leiningxin [1 ]
Wang, Hui [1 ]
Luo, Guoliang [1 ]
机构
[1] East China Jiaotong Univ, Virtual Real & Interact Tech Inst, Nanchang 330013, Peoples R China
基金
中国国家自然科学基金;
关键词
Transformers; Noise reduction; Feature extraction; Remote sensing; Convolution; Image denoising; Task analysis; Axis-based transformer module; image denoising; remote sensing imagery;
D O I
10.1109/LSP.2024.3418717
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Remote sensing images are different from ordinary images in that they have higher resolution, contain information of a larger area, and are characterized by strip-like objects in many scenes. The traditional Transformer model based on the moving window to calculate the attention is difficult to obtain the overall features when extracting the features of strip-shaped objects and is easily interfered by the surrounding features. To address this problem, this paper innovatively designs an axial Transformer module and constructs a U-shaped hierarchical encoder-decoder structure network (ATUNet). The network improves its ability to extract global features and resist interference from irrelevant features through the axial attention mechanism. We synthesize multiple test sets with noise levels for experiments using three datasets, NWPU-RESISC45, UCMerced_LandUse, and OPTIMAL-31. The experiments show that our network has good resistance to high noise and generalization ability.
引用
收藏
页码:2515 / 2519
页数:5
相关论文
共 50 条
  • [31] An algorithm for remote sensing image denoising based on the combination of the improved BiShrink and DTCWT
    College of Information Science and Engineering, Xinjiang University, Urumqi 830046, China
    不详
    不详
    Procedia Eng., 1600, (470-474):
  • [32] NSCT Remote Sensing Image Denoising Based on Threshold of Free Distributed FDR
    Liu, Jihong
    Jia, Zhenhong
    Qin, Xizhong
    Yang, Jie
    Hu, Yingjie
    INTERNATIONAL CONFERENCE ON ADVANCES IN ENGINEERING 2011, 2011, 24 : 616 - 620
  • [33] Remote sensing image denoising based on improved semi-soft threshold
    Lei, Sai
    Lu, Mingming
    Lin, Jieqiong
    Zhou, Xiaoqin
    Yang, Xuemei
    SIGNAL IMAGE AND VIDEO PROCESSING, 2021, 15 (01) : 73 - 81
  • [34] Remote sensing image denoising based on improved semi-soft threshold
    Sai Lei
    Mingming Lu
    Jieqiong Lin
    Xiaoqin Zhou
    Xuemei Yang
    Signal, Image and Video Processing, 2021, 15 : 73 - 81
  • [35] An Algorithm for Remote Sensing Image Denoising Based on the Combination of the Improved BiShrink and DTCWT
    Li, Minghui
    Jia, Zhenhong
    Yang, Jie
    Hu, Yingjie
    Li, Dianjun
    INTERNATIONAL CONFERENCE ON ADVANCES IN ENGINEERING 2011, 2011, 24 : 470 - 474
  • [36] Denoising-Based Multiscale Feature Fusion for Remote Sensing Image Captioning
    Huang, Wei
    Wang, Qi
    Li, Xuelong
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2021, 18 (03) : 436 - 440
  • [37] Remote sensing image mining area change detection based on improved UNet siamese network
    Xiang Y.
    Zhao Y.
    Dong J.
    Meitan Xuebao/Journal of the China Coal Society, 2019, 44 (12): : 3773 - 3780
  • [38] Attention-Based Tri-UNet for Remote Sensing Image Pan-Sharpening
    Zhang, Wanwan
    Li, Jinjiang
    Hua, Zhen
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2021, 14 : 3719 - 3732
  • [39] RCST: Residual Context-Sharing Transformer Cascade to Approximate Taylor Expansion for Remote Sensing Image Denoising
    Huang, Zhenghua
    Yang, Yang
    Yu, Hao
    Li, Qian
    Shi, Yu
    Zhang, Yaozong
    Fang, Hao
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2025, 63
  • [40] Road Extraction Method of Remote Sensing Image Based on Deformable Attention Transformer
    Zhao, Ling
    Zhang, Jianing
    Meng, Xiujun
    Zhou, Wenming
    Zhang, Zhenshi
    Peng, Chengli
    SYMMETRY-BASEL, 2024, 16 (04):