Hyperbola detection with retinanet and comparison of hyperbola fitting methods in gpr data from an archaeological site

HIGHLIGHTS

• who: Tina Wunderlich et al. from the Institute Geosciences, Christian-Albrechts-University Kiel, Otto-Hahn-Platz, Kiel, Germany have published the paper: Hyperbola Detection with RetinaNet and Comparison of Hyperbola Fitting Methods in GPR Data from an Archaeological Site, in the Journal: (JOURNAL)
• what: Afterwards the authors show the further evaluation of the detected hyperbola, i.e., velocity derivation by different methods and clustering.
• how: In contrast in this study the authors used an dataset with diverse underground structures. The authors used RetinaNet which is based on Faster R-CNN combined with a . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

  If you don't have an account, you can create one here.