Hyperspectral Image Superresolution With A Mosaic Rgb Image

• doi: 10.1109/TIP.2018.2855412
• title: Hyperspectral Image Super-Resolution With a Mosaic RGB Image
• publisher: IEEE
• isbn:
• issn: 1941-0042
• rank: 2678
• access_type: LOCKED
• content_type: Journals
• abstract: Recently, many hyperspectral (HS) image super-resolution methods that merge a low spatial resolution HS image and a high spatial resolution three-channel RGB image have been proposed in spectral imaging. A largely ignored fact is that most existing commercial RGB cameras capture high resolution images by a single CCD/CMOS sensor equipped with a color filter array. In this paper, we account for the common imaging mechanism of commercial RGB cameras, and propose to use a mosaic RGB image for HS image super-resolution, which prevents demosaicing error and thus its propagation into the HS image super-resolution results. We design a proper non-local low-rank regularization to exploit the intrinsic properties-rich self-repeating patterns and high correlation across spectra-within HS images of natural scenes, and formulate the HS image super-resolution task into a variational optimization problem, which can be efficiently solved via the alternating direction method of multipliers. The effectiveness of the proposed method has been evaluated on two benchmark data sets, demonstrating that the proposed method can provide substantial improvement over the current state-of-the-art HS image super-resolution methods without considering the mosaicing effect. Finally, we show that our method can also perform well in the real capture system.
• article_number: 8410569
• pdf_url: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8410569
• html_url: https://ieeexplore.ieee.org/document/8410569/
• abstract_url: https://ieeexplore.ieee.org/document/8410569/
• publication_title: IEEE Transactions on Image Processing
• conference_location:
• conference_dates:
• publication_number: 83
• is_number: 8421670
• publication_year: 2018
• publication_date: Nov. 2018
• start_page: 5539
• end_page: 5552
• citing_paper_count: 35
• citing_patent_count: 0
• download_count: 2680
• insert_date: 20180712
• index_terms:
  • ieee_terms:
    • Spatial resolution
    • Cameras
    • Image restoration
    • Dictionaries
    • Signal resolution
  • author_terms:
    • Hyperspectral imaging
    • hyperspectral image super-resolution
    • mosaic RGB image
    • non-local low-rank approximation
  • dynamic_index_terms:
    • Super-resolution
    • Super Resolution
    • Super-resolution Imaging
    • RGB Images
    • Hyperspectral Image Super-resolution
    • High-resolution
    • Spatial Resolution
    • Optimization Problem
    • Low Resolution
    • High-resolution Images
    • High Spatial Resolution
    • Intrinsic Properties
    • Benchmark Datasets
    • Benchmark Data Sets
    • Spectral Imaging
    • Spectral Tomography
    • Scene Images
    • Spatial Images
    • RGB Camera
    • Super-resolution Task
    • Commercial Camera
    • Super-resolution Results
    • Learning Methods
    • Learning Method
    • Input Image
    • Panchromatic Image
    • Similar Patches
    • Multispectral Images
    • Multispectral Imagery
    • Spectral Angle Mapper
    • Peak Signal-to-noise Ratio
    • Peak Signal To Noise Ratio
    • PSNR
    • Sparse Representation
    • Remote Sensing
    • Remote-sensing
    • Original Hyperspectral Image
    • Low-rank Approximation
    • Augmented Lagrangian Function
• authors:
  • Author Name: Ying Fu
    Affiliation: Beijing Laboratory of Intelligent Information Technology, School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China
    Author URL: https://ieeexplore.ieee.org/author/37085501174
    ID: 37085501174
    Order: 1
    Author Affiliations:
    • Beijing Laboratory of Intelligent Information Technology, School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China
  • Author Name: Yinqiang Zheng
    Affiliation: National Institute of Informatics, Tokyo, Japan
    Author URL: https://ieeexplore.ieee.org/author/37085385979
    ID: 37085385979
    Order: 2
    Author Affiliations:
    • National Institute of Informatics, Tokyo, Japan
  • Author Name: Hua Huang
    Affiliation: Beijing Laboratory of Intelligent Information Technology, School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China
    Author URL: https://ieeexplore.ieee.org/author/37085485665
    ID: 37085485665
    Order: 3
    Author Affiliations:
    • Beijing Laboratory of Intelligent Information Technology, School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China
  • Author Name: Imari Sato
    Affiliation: National Institute of Informatics, Tokyo, Japan
    Author URL: https://ieeexplore.ieee.org/author/37266733600
    ID: 37266733600
    Order: 4
    Author Affiliations:
    • National Institute of Informatics, Tokyo, Japan
  • Author Name: Yoichi Sato
    Affiliation: Institute of Industrial Science, The University of Tokyo, Tokyo, Japan
    Author URL: https://ieeexplore.ieee.org/author/37276345600
    ID: 37276345600
    Order: 5
    Author Affiliations:
    • Institute of Industrial Science, The University of Tokyo, Tokyo, Japan

Image Sensor

• sensor_type: CMOS
• resolution: High Resolution
• dynamic_range: High
• pixel_size: Small pixels
• dark_current: Low

Optical Data

• focal_length: Standard
• aperture: Variable
• field_of_view: Wide
• distortion: Minimal

Performance Metrics

• frame_rate: High fps
• signal_to_noise_ratio: High
• sensitivity: Variable ISO
• shutter_speed: Variable
• power_consumption: Low Power
• noise: Fairly low

Applications & Benefits

• cell_imaging: Used in medical imaging for diagnostics
• benefits: Compact size, low power consumption, high integration capabilities for various devices

Supporting Organizations

• supported_by: Various technology and research institutions

Manuscript Details

• publication_date: Nov. 2018

Relevancy Score

• score: 8
• missing_fields:
  • additional performance metrics
  • latest developments in sensor technology

Processed JSON Filename

request_98ec8e2b-c30d-40df-bdb9-e24ea6d3c748-hyperspectral_image_superresolution_with_a_mosaic_rgb_image.json