Multispectral Transforms Using Convolution Neural Networks for Remote Sensing Multispectral Image Compression

被引:35
|
作者
Li, Jin [1 ]
Liu, Zilong [2 ]
机构
[1] Univ Cambridge, Dept Engn, 9 JJ Thomson Ave, Cambridge CB3 0FA, England
[2] Natl Inst Metrol, Opt Div, Beijing 100029, Peoples R China
基金
中国国家自然科学基金;
关键词
multispectral image compression; convolution neural networks; Tucker Decomposition; CLASSIFICATION; ALGORITHM;
D O I
10.3390/rs11070759
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
A multispectral image is a three-order tensor since it is a three-dimensional matrix, i.e., one spectral dimension and two spatial position dimensions. Multispectral image compression can be achieved by means of the advantages of tensor decomposition (TD), such as Nonnegative Tucker Decomposition (NTD). Unfortunately, the TD suffers from high calculation complexity and cannot be used in the on-board low-complexity case (e.g., multispectral cameras) that the hardware resources and power are limited. Here, we propose a low-complexity compression approach for multispectral images based on convolution neural networks (CNNs) with NTD. We construct a new spectral transform using CNNs, where the CNNs are able to transform the three-dimension spectral tensor from large-scale to a small-scale version. The NTD resources only allocate the small-scale three-dimension tensor to improve calculation efficiency. We obtain the optimized small-scale spectral tensor by the minimization of original and reconstructed three-dimension spectral tensor in self-learning CNNs. Then, the NTD is applied to the optimized three-dimension spectral tensor in the DCT domain to obtain the high compression performance. We experimentally confirmed the proposed method on multispectral images. Compared to the case that the new spectral tensor transform with CNNs is not applied to the original three-dimension spectral tensor at the same compression bit-rates, the reconstructed image quality could be improved. Compared with the full NTD-based method, the computation efficiency was obviously improved with only a small sacrifices of PSNR without affecting the quality of images.
引用
收藏
页数:20
相关论文
共 50 条
  • [21] Multispectral image and fullcolor remote sensing image processing technology
    Cai, Jia
    Ma, Jing-xuan
    Wang, Jian-xia
    [J]. 2017 9TH INTERNATIONAL CONFERENCE ON MODELLING, IDENTIFICATION AND CONTROL (ICMIC 2017), 2017, : 551 - 555
  • [22] Multispectral and hyperspectral image fusion in remote sensing: A survey
    Vivone, Gemine
    [J]. INFORMATION FUSION, 2023, 89 : 405 - 417
  • [23] Multispectral remote sensing image classification with multiple features
    Yin, Qian
    Guo, Ping
    [J]. PROCEEDINGS OF 2007 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-7, 2007, : 360 - +
  • [24] MULTISTAGE ALGORITHM FOR LOSSLESS COMPRESSION OF MULTISPECTRAL REMOTE SENSING IMAGES
    Zamyatin, A.
    [J]. 100 YEARS ISPRS ADVANCING REMOTE SENSING SCIENCE, PT 1, 2010, 38 : 304 - 309
  • [25] Multispectral multisensor image fusion using wavelet transforms
    Lemeshewsky, GP
    [J]. VISUAL INFORMATION PROCESSING VIII, 1999, 3716 : 214 - 222
  • [26] Soil Heat Flux Modeling Using Artificial Neural Networks and Multispectral Airborne Remote Sensing Imagery
    Canelon, Dario J.
    Chavez, Jose L.
    [J]. REMOTE SENSING, 2011, 3 (08) : 1627 - 1643
  • [27] Efficient Compression for Remote Sensing: Multispectral Transform and Deep Recurrent Neural Networks for Lossless Hyper-Spectral Imagine
    Anuradha, D.
    Sekhar, Gillala Chandra
    Mishra, Annapurna
    Thapar, Puneet
    El-Ebiary, Yousef A. Baker
    Syamala, Maganti
    [J]. INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2024, 15 (02) : 531 - 541
  • [28] Quantifying Information Content in Multispectral Remote-Sensing Images Based on Image Transforms and Geostatistical Modelling
    Zhang, Ying
    Zhang, Jingxiong
    Yang, Wenjing
    [J]. REMOTE SENSING, 2020, 12 (05)
  • [29] Multispectral remote sensing of aerosols
    Lynch, DK
    [J]. ACTA ASTRONAUTICA, 1996, 38 (12) : 947 - 953
  • [30] An optimized approach to application of neural networks to classification of multispectral, remote sensing data.
    Toshniwal, M
    [J]. 2005 IEEE Networking, Sensing and Control Proceedings, 2005, : 235 - 240