Shared more. Cited more. Safe forever.
    • advanced search
    • submit works
    • about
    • help
    • contact us
    • login
    View Item 
    •   MOspace Home
    • University of Missouri-Columbia
    • Graduate School - MU Theses and Dissertations (MU)
    • Theses and Dissertations (MU)
    • Theses (MU)
    • 2018 Theses (MU)
    • 2018 MU theses - Access restricted to UM
    • View Item
    •   MOspace Home
    • University of Missouri-Columbia
    • Graduate School - MU Theses and Dissertations (MU)
    • Theses and Dissertations (MU)
    • Theses (MU)
    • 2018 Theses (MU)
    • 2018 MU theses - Access restricted to UM
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.
    advanced searchsubmit worksabouthelpcontact us

    Browse

    All of MOspaceCommunities & CollectionsDate IssuedAuthor/ContributorTitleSubjectIdentifierThesis DepartmentThesis AdvisorThesis SemesterThis CollectionDate IssuedAuthor/ContributorTitleSubjectIdentifierThesis DepartmentThesis AdvisorThesis Semester

    Statistics

    Most Popular ItemsStatistics by CountryMost Popular AuthorsStatistics by Referrer

    A remote sensing analysis of the grand river grasslands using sentinel-2 satellite imagery : a comparison of land-use / land-cover classifications using per-pixel and object-oriented procedures

    Venigalla, Lasya
    View/Open
    [PDF] research.pdf (3.057Mb)
    Date
    2018
    Format
    Thesis
    Metadata
    [+] Show full item record
    Abstract
    [ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT AUTHOR'S REQUEST.] The important prerequisites for the proper use of land is to know how the land is covered and how it is being used currently. In this study, land-use and land-cover classifications were implemented over an area of the Grand River Grasslands (GRG), an area where restoration of a tallgrass prairie landscape is underway. The GRG is located in Harrison County, Missouri. The analysis was performed using Sentinel-2 10m spatial resolution satellite imagery. Imagery for two contrasting seasons was acquired to aid in the discrimination of cover types that exhibited a high degree of phenological variability. The analysis took a two-pronged approach. First, image objects were created by segmenting the sentinel-2 image data using the MeanShiftSegmentation algorithm in ArcPy. Multiple attributes corresponding to each segment were extracted from the Sentiniel-2 imagery. The resultant segmented attributed were then classified using the Classification and Regression Tree technique, See5, available within the R statistical computing package. The segments used to define the regression tree were labeled using field data collected through on the use of ground surveys as well as aerial imagery. Second, using the same field data and the See5 algorithm, an additional classification was run on a per-pixel basis. The two classifications were then compared to determine if one approach provided an improvement in classification accuracy over the other. There was an increase in the overall classification accuracy close to 11% when the CART technique was applied on the image at object-level than at pixel-level.
    URI
    https://hdl.handle.net/10355/66215
    Degree
    M.A.
    Thesis Department
    Geography (MU)
    Rights
    Access is limited to the campuses of the University of Missouri.
    This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 3.0 License.
    Collections
    • 2018 MU theses - Access restricted to UM
    • Geography electronic theses and dissertations (MU)

    Send Feedback
    hosted by University of Missouri Library Systems
     

     


    Send Feedback
    hosted by University of Missouri Library Systems