Oil Spill Detection in SAR Images Using Texture Entropy Algorithm and Mahalanobis Classifier

  • Details
  • Share
African Journals Online
Publishing Date

Oil spill has become critical in some countries, especially for countries that have seas or oceans. The situation has caused damage to the environment and polluted the water. To reduce environment damage and protect life in water, plants and soil near to disaster area .Study and analysis should be carried out .The causes and factors that lead to the disaster of oil spill should be studied or investigated. To analyze the problem of oil spill we consider 2 algorithms. These methods help in the analysis and identification of oil spill in SAR images. Since the 1980s, satellite-borne synthetic aperture radar (SAR) has been investigated for early warning and monitoring of marine oil spills to permit effective satellite surveillance in the marine environment. Synthetic Aperture Radar (SAR) imaging system is used to monitor the marine system. Oil spill pollution plays a significant role in damaging marine ecosystem. One main advantages of SAR is that it can generate imagery under all weather conditions. Automated detection of oil spills from satellite SAR intensity imagery consists of three steps: Detection of dark spots , Extraction of features from the detected dark spots and classification of the dark spots into oil spills and look-alikes. Texture Entropy Algorithm is a method based on the utilization of texture algorithms for the discrimination of oil spill areas from the surrounding features, e.g. sea surface and look-alikes. Mahalanobis Classifier method first estimates covariance matrix and then Mahalanobis Distance is calculated for identification of oil spill or lookalike.