• DocumentCode
    2554368
  • Title

    Detection of oil spills using feature extraction and threshold based segmentation techniques

  • Author

    Vyas, Garima ; Bhan, Anupama ; Gupta, Divya

  • Author_Institution
    Amity Sch. Of Eng. & Technol., Amity Univ., Noida, India
  • fYear
    2015
  • fDate
    19-20 Feb. 2015
  • Firstpage
    579
  • Lastpage
    583
  • Abstract
    Satellite images can improve the possibilities for the detection of oil spills as they cover large areas and offer an economical and easier way of continuous coast areas patrolling. There are many common techniques to detect dark formations on the SAR images. This paper mainly focuses on method with spot feature extraction and global thresholding. The main approach used in this paper is detecting the dark spots, using local and global threshold algorithms. For each dark spot, a number of features are calculated in order to classify the slick as either oil or other possible geographical or natural components of water. The proposed threshold algorithm, initially analyzes the SAR images, and then assigns a probability to the dark spot to indicate whether it is an oil spill or look alike.
  • Keywords
    feature extraction; geophysical image processing; geophysical techniques; image segmentation; marine pollution; oil pollution; synthetic aperture radar; coast areas patrolling; dark spot detection; global threshold algorithm; local threshold algorithm; oil spill detection; satellite images; spot feature extraction; threshold based segmentation technique; water geographical component; water natural component; Feature extraction; Image segmentation; MODIS; Remote sensing; Satellites; Standards; Synthetic aperture radar; Gamma Correction; Global Thresholding; Local Thresholding; Masking; Oil Spills;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Signal Processing and Integrated Networks (SPIN), 2015 2nd International Conference on
  • Conference_Location
    Noida
  • Print_ISBN
    978-1-4799-5990-7
  • Type

    conf

  • DOI
    10.1109/SPIN.2015.7095433
  • Filename
    7095433