Published November 20, 2019 | Version 0.1
Software Open

Semi-supervised sea floor fault detection

Authors/Creators

  • 1. EURECOM
  • 2. Institut de Physique du Globe de Paris
  • 3. Bureau de Recherches Géologiques et Minières
  • 4. Université de Neuchâtel

Description

The interpretation of faults along mid-ocean ridges is an important task in order to better understand tectonic mechanisms. However, the analysis relies on the detection of fault lines which can be extremely laborious when picked manually from the bathymetry. The proposed method uses a semi-supervised convolutional network to detect faults. It employs the U-Net network (Ronneberger et al., 2015) and a so-called IoU metric (mean average precision at different intersection over union).

Files

intv0id/FaultsDetection-0.1.zip

Files (1.4 MB)

Name Size Download all
md5:a85f580b2352e949c9bb9d3e5a835673
1.4 MB Preview Download

Additional details

Related works

Is supplement to
https://github.com/intv0id/FaultsDetection/tree/0.1 (URL)

References

  • RONNEBERGER, Olaf, FISCHER, Philipp, et BROX, Thomas. U-net: Convolutional networks for biomedical image segmentation. In : International Conference on Medical image computing and computer-assisted intervention. Springer, Cham, 2015. p. 234-241.