A hyperspectral image reconstruction algorithm based on RGB image using multi-scale atrous residual convolution network

被引:7
|
作者
Hu, Shaoxiang [1 ]
Hou, Rong [2 ]
Ming, Luo [1 ]
Su, Meifang [1 ]
Chen, Peng [2 ]
机构
[1] Univ Elect Sci & Technol China, Sch Elect Sci & Engn, Chengdu, Peoples R China
[2] Sichuan Key Lab Conservat Biol Endangered Wildlife, Chengdu Res Base Giant Panda Breeding, Chengdu, Peoples R China
关键词
hyperspectral image reconstruction; deep learning; atrous convolution; marine science; multi-scale;
D O I
10.3389/fmars.2022.1006452
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Hyperspectral images are a valuable tool for remotely sensing important characteristics of a variety of landscapes, including water quality and the status of marine disasters. However, hyperspectral data are rare or expensive to obtain, which has spurred interest in low-cost, fast methods for reconstructing hyperspectral data from much more common RGB images. We designed a novel algorithm to achieve this goal using multi-scale atrous convolution residual network (MACRN). The algorithm includes three parts: low-level feature extraction, high-level feature extraction, and feature transformation. The high-level feature extraction module is composed of cascading multi-scale atrous convolution residual blocks (ACRB). It stacks multiple modules to form a depth network for extracting high-level features from the RGB image used as an input. The algorithm uses jump connection for residual learning, and the final high-level feature combines the output of the low-level feature extraction module and the output of the cascaded atrous convolution residual block element by element, so as to prevent gradient dispersion and gradient explosion in the deep network. Without adding too many parameters, the model can extract multi-scale features under different receptive fields, make better use of the spatial information in RGB images, and enrich the contextual information. As a proof of concept, we ran an experiment using the algorithm to reconstruct hyperspectral Sentinel-2 satellite data from the northern coast of Australia. The algorithm achieves hyperspectral spectral reconstruction in 443nm-2190nm band with less computational cost, and the results are stable. On the Realworld dataset, the reconstruction error MARE index is less than 0.0645, and the reconstruction time is less than 9.24S. Therefore, in the near infrared band, MACRN reconstruction accuracy is significantly better than other spectral reconstruction algorithms. MACRN hyperspectral reconstruction algorithm has the characteristics of low reconstruction cost and high reconstruction accuracy, and its advantages in ocean spectral reconstruction are more obvious.
引用
收藏
页数:9
相关论文
共 50 条
  • [21] MULTI-SCALE RESIDUAL NETWORK FOR IMAGE CLASSIFICATION
    Zhong, Xian
    Gong, Oubo
    Huang, Wenxin
    Yuan, Jingling
    Ma, Bo
    Li, Ryan Wen
    2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, : 2023 - 2027
  • [22] Fusiform multi-scale pixel self-attention network for hyperspectral images reconstruction from a single RGB image
    Jiang, Zhongmin
    Zhang, Wanyan
    Wang, Wenju
    VISUAL COMPUTER, 2023, 39 (08): : 3573 - 3584
  • [23] Multi-scale convolution underwater image restoration network
    Zhijie Tang
    Jianda Li
    Jingke Huang
    Zhanhua Wang
    Zhihang Luo
    Machine Vision and Applications, 2022, 33
  • [24] Fusiform multi-scale pixel self-attention network for hyperspectral images reconstruction from a single RGB image
    Zhongmin Jiang
    Wanyan Zhang
    Wenju Wang
    The Visual Computer, 2023, 39 : 3573 - 3584
  • [25] Multi-scale convolution underwater image restoration network
    Tang, Zhijie
    Li, Jianda
    Huang, Jingke
    Wang, Zhanhua
    Luo, Zhihang
    MACHINE VISION AND APPLICATIONS, 2022, 33 (06)
  • [26] The super-resolution reconstruction algorithm of multi-scale dilated convolution residual network
    Wang, Shanqin
    Zhang, Miao
    Miao, Mengjun
    FRONTIERS IN NEUROROBOTICS, 2024, 18
  • [27] Multi-Scale Transformer Network for Hyperspectral Image Denoising
    Hu, Shuai
    Hu, Yikun
    Lin, Junyan
    Gao, Feng
    Dong, Junyu
    IGARSS 2023 - 2023 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2023, : 7328 - 7331
  • [28] Hyperspectral image classification based on multi-scale hybrid convolutional network
    Yang, Yun
    Zhou, Yao
    Chen, Jia-ning
    CHINESE JOURNAL OF LIQUID CRYSTALS AND DISPLAYS, 2023, 38 (03) : 368 - 377
  • [29] Hyperspectral image quality based on convolutional network of multi-scale depth
    Liu, Lei
    Sun, Min
    Ren, Xiang
    Li, Xiuxian
    Zhang, Qiaoru
    Ma, Li
    Li, Yongning
    Song, Mo
    Journal of Visual Communication and Image Representation, 2020, 71
  • [30] Hyperspectral Image Classification Based on A Multi-Scale Weighted Kernel Network
    Sun Le
    Xu Bin
    Lu Zhenyu
    CHINESE JOURNAL OF ELECTRONICS, 2022, 31 (05) : 832 - 843