Title page for etd-0609117-235215


[Back to Results | New Search]

URN etd-0609117-235215
Author Yung-Da Sun
Author's Email Address No Public.
Statistics This thesis had been viewed 5355 times. Download 0 times.
Department Marine Environment and Engineering
Year 2016
Semester 2
Degree Ph.D.
Type of Document
Language zh-TW.Big5 Chinese
Title A Hybrid Seabed Classification Method Using Airborne Laser Bathymetric Data
Date of Defense 2017-05-22
Page Count 95
Keyword
  • gray co-occurrence matrices (GLCM)
  • Support Vector Machine (SVM)
  • K-means
  • Hybrid method
  • bathymetric LiDAR data
  • Abstract In recent years, Airborne Bathymetric Light Detection and Ranging (LiDAR) has been applied intensively to map coastal depth as well as for seabed classification. In this study, we proposed a hybrid K-means and Support Vector Machine (KSVM) algorithm based on depth-derived from bathymetric LiDAR, and texture analysis by second derivatives of gray-level co-occurrence matrices (GLCM). First, the calculated GLCM data set was used to sort K-means into various clusters. Second, training samples were selected on merged clusters before applying SVM classification. Finally, we evaluated the proposed hybrid algorithm in overall accuracy and the Kappa index. Compared to pure SVM, the proposed hybrid KSVM improved the overall accuracy by 24%, and the Kappa index by 0.31. The results showed that the proposed KSVM method provided promising results, in terms of accuracy and visual inspection. The benefits of the proposed classification method applied unsupervised classification of K-means as prior information for unseen seabed sediment types. This method was useful, particularly when only depth-derived information was available, or where the intensity/waveform had poor discrimination properties.
    Advisory Committee
  • Tian-Yuan Shih - chair
  • Liang-Hwei Lee - co-chair
  • Chih-Chung Kao - co-chair
  • Ming-Jer Huang - co-chair
  • Shiahn-wern Shyue - advisor
  • Files
  • etd-0609117-235215.pdf
  • Indicate in-campus at 4 year and off-campus access at 5 year.
    Date of Submission 2017-07-18

    [Back to Results | New Search]


    Browse | Search All Available ETDs

    If you have more questions or technical problems, please contact eThesys