• DocumentCode
    3286545
  • Title

    A large-scale solar image dataset with labeled event regions

  • Author

    Schuh, Michael A. ; Angryk, Rafal A. ; Pillai, Karthik Ganesan ; Banda, Juan M. ; Martens, Petrus C.

  • Author_Institution
    Dept. Comput. Sci., Montana State Univ., Bozeman, MT, USA
  • fYear
    2013
  • fDate
    15-18 Sept. 2013
  • Firstpage
    4349
  • Lastpage
    4353
  • Abstract
    This paper introduces a new public benchmark dataset of solar image data from the Solar Dynamics Observatory (SDO) mission. This is the first release, which contains over 15,000 images and nearly 24,000 solar events, spanning the first six months of 2012. It combines region-based event labels from six automated detection modules, ten pre-computed image parameters for each cell over a grid-based segmentation of the full resolution images, and a lower resolution version of the images for further analysis and visualization. Together, these components serve as a standardized, ready-to-use, solar image dataset for general image processing research, without requiring the necessary background knowledge to properly prepare it. We present here the fundamental dataset creation details and outline future improvements and opportunities as data collection continues for the coming years.
  • Keywords
    astronomical image processing; image resolution; image segmentation; solar system; SDO mission; automated detection modules; data collection; full resolution images; general image processing research; grid-based segmentation; labeled event regions; public benchmark dataset; region-based event labels; solar dynamics observatory mission; solar events; solar image dataset; computer vision; data mining; dataset benchmark; image processing; machine learning;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Image Processing (ICIP), 2013 20th IEEE International Conference on
  • Conference_Location
    Melbourne, VIC
  • Type

    conf

  • DOI
    10.1109/ICIP.2013.6738896
  • Filename
    6738896