A Bayesian marine debris detector using existing hydrographic data products

Conference Proceeding

Abstract

  • A detection methodology for marine debris presence after a natural disaster is described. The methodology is based both on a predictive model and a Bayesian hierarchical spatial method. The chosen fusion approach relies on auto-logistic regression to weight the outputs of multiple target detection algorithms, as well as to capture the intrinsic processes related to the presence of marine debris. The algorithms are applied to existing hydrographic data products (e.g., bathymetric surfaces, backscatter mosaics). The approach, in active development, is demonstrated and tested both with artificial and real survey data. The scalability of the technique permits its straightforward extension to additional detection algorithms for ad-hoc data products.
  • Status

    Publication Date

  • 2015
  • Published In

    Presented At Event

  • OCEANS 2015 - Genova  Conference
  • Keywords

  • Bayesian inference
  • DTM
  • MCMC
  • acoustic backscatter
  • hierarchical model
  • Start Page

  • 1
  • End Page

  • 10