Survey on Dehazing of Multispectral Images

被引:0
|
作者
Kayalvizhi, S. [1 ]
Karthikeyan, Badrinath [1 ]
Sathvik, Canchibalaji [1 ]
Gautham, Chadalavada [1 ]
机构
[1] Easwari Engn Coll, Dept Comp Sci & Engn, Chennai, India
来源
关键词
Dehazing; Multispectral images; Contrastive learning; CycleGAN; Deep learning; HAZE REMOVAL; SATELLITE DATA;
D O I
10.26713/cma.v14i2.2443
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
Images captured in hazy climate can be severely decayed by atmospheric particle scattering, which reduces disparity, and which makes it hard to identify features of an object with the naked human eye. Image defogging is done to get rid of the weather factor effects which in turn improves the image quality of the image. This article gives a brief summary regarding the image denoising techniques that have been proposed. We performed the various approaches in order to find out which is the best method for achieving the perfect result. All methods are analyzed and the corresponding subcategories are presented in accordance with the principles and characteristics. Then, the different methods of quality assessment are described, classified and confidentially discussed. To realize this, we use multispectral sensing. When using filters to divide the wavelengths, multispectral imaging can collect image data in specific wavelength ranges across the spectrum. It can allow for the extraction of additional data that the human eye's visible red, green, and blue color receptors cannot record. Its ideal use was for the identification and reconnaissance of military targets. This system was also used by ISRO to receive high resolution images from their satellite. The proposed method was applied to various types of multispectral images, where its effectiveness for visualizing spectral features was verified.
引用
收藏
页码:1113 / 1125
页数:13
相关论文
共 50 条
  • [21] Contrast-Based Stereoscopic Images Dehazing
    Qiu, Yimin
    Wu, Shiqian
    PROCEEDINGS OF THE 2015 10TH IEEE CONFERENCE ON INDUSTRIAL ELECTRONICS AND APPLICATIONS, 2015, : 603 - 608
  • [22] A novel dehazing model for remote sensing images
    Singh, Dilbag
    Kumar, Vijay
    COMPUTERS & ELECTRICAL ENGINEERING, 2018, 69 : 14 - 27
  • [23] Analysis of Various Dehazing Algorithms for Underwater Images
    Cecilia, S. Mary
    Murugan, S. Sakthivel
    Padmapriya, N.
    PROCEEDINGS OF THE 2019 INTERNATIONAL SYMPOSIUM ON OCEAN TECHNOLOGY (SYMPOL 2019), 2019, : 98 - 105
  • [24] Multispectral images error correction
    Piazza, E
    OCEANS '97 MTS/IEEE CONFERENCE PROCEEDINGS, VOLS 1 AND 2, 1997, : 3 - 7
  • [25] Fusion of reconstructed multispectral images
    Starovoitov, Valery
    Makarau, Aliaksei
    Zakharov, Igor
    Dovnar, Dmitry
    IGARSS: 2007 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, VOLS 1-12: SENSING AND UNDERSTANDING OUR PLANET, 2007, : 5146 - +
  • [26] CLASSIFICATION OF MULTISPECTRAL IMAGES.
    Hattori, Norihide
    Ishii, Naohiro
    Suzumura, Nobuo
    Systems, computers, controls, 1984, 15 (03): : 44 - 52
  • [27] Multispectral analysis of multimodal images
    Kvinnsland, Yngve
    Brekke, Njal
    Taxt, Torfinn M.
    Gruner, Renate
    ACTA ONCOLOGICA, 2009, 48 (02) : 277 - 284
  • [28] Kernel postprocessing of multispectral images
    Michalak M.
    ͆witoński A.
    Advances in Intelligent and Soft Computing, 2011, 95 (04): : 395 - 401
  • [29] Segmentation Algorithm of Multispectral Images
    Nikolaeva O.V.
    Mathematical Models and Computer Simulations, 2024, 16 (3) : 340 - 351
  • [30] Morphological partitioning of multispectral images
    Soille, P
    JOURNAL OF ELECTRONIC IMAGING, 1996, 5 (03) : 252 - 265