• Login
    View Item 
    •   TAMU-CC Repository Home
    • TAMU-CC Theses, Dissertations, and Graduate Projects
    • Theses
    • View Item
    •   TAMU-CC Repository Home
    • TAMU-CC Theses, Dissertations, and Graduate Projects
    • Theses
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Oil spill detection is SAR images using meta-heuristic search algorithms

    Thumbnail
    View/Open
    Manikonda_SaiVinjay_thesis.pdf (27.88Mb)
    Date Issued
    2018-05
    Author
    Manikonda, Sai Vinay Teja
    Metadata
    Show full item record
    URI
    https://tamucc-ir.tdl.org/handle/1969.6/87015
    Abstract
    In recent years, oil spill accidents have become increasingly frequent due to the development of marine transportation and massive oil exploitation. At present, satellite remote sensing is the principal method used to monitor oil spills. Extracting the locations and extent of oil spill spots accurately in remote sensing images reaps significant benefits in terms of risk assessment and clean-up work. Many oil spill detection methods are implemented using traditional K-means and OTSU methods. In this research, traditional segmentation methods K-means and Otsu are improved using Meta- heuristic search algorithms to increase the efficiency of oil spill detection. The Meta-heuristic algorithms that are used in this research are Genetic Algorithm, Simulated Annealing, and Particle swarm optimization. In this research, Two frameworks are implemented which have image enhancement stage, segmentation stage, and Oil Extraction stage. The two frameworks differ in the segmentation stage wherein one framework, segmentation is done based on clustering using Meta-heuristic search algorithms and in other, Segmentation is done based on thresholding using Meta-heuristic search algorithm. Two fitness functions are proposed in this research. Segmentation based clustering using Meta-heuristic Search algorithm with the proposed fitness functions is compared to the K-means clustering and Fuzzy c-means algorithm. Segmentation based thresholding using Meta-heuristic Search algorithm with the proposed fitness functions is compared to the Otsu segmentation method.
    Rights
    This material is made available for use in research, teaching, and private study, pursuant to U.S. Copyright law. The user assumes full responsibility for any use of the materials, including but not limited to, infringement of copyright and publication rights of reproduced materials. Any materials used should be fully credited with its source. All rights are reserved and retained regardless of current or future development or laws that may apply to fair use standards. Permission for publication of this material, in part or in full, must be secured with the author and/or publisher.
    Collections
    • College of Science and Engineering Theses and Dissertations
    • Theses

    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    TDL
    Theme by 
    Atmire NV
     

     

    Browse

    All of TAMU-CC RepositoryCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsDepartmentsThis CollectionBy Issue DateAuthorsTitlesSubjectsDepartments

    My Account

    Login

    Statistics

    View Usage Statistics

    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    TDL
    Theme by 
    Atmire NV