Automatic detection of boulders by neural networks
A comparison of multibeam echo sounder and side-scan sonar performance

Neural networks show great promise in the automatic detection of boulders on the seafloor. Maps derived from bathymetric data show better performance compared to backscatter mosaics in this study. However, we find the lack of training data groundtruthed to a high standard the largest challenge for automated object detection based on acoustic data.

boulder detection | neural networks | hydrographic surveying | bathymetry | backscatter


Neuronale Netze sind sehr vielversprechend bei der automatischen Erkennung von Felsbrocken auf dem Meeresboden. Aus bathymetrischen Daten abgeleitete Karten zeigen in dieser Studie eine bessere Leistung im Vergleich zu Rückstreumosaiken. Die größte Herausforderung für die automatische Objekterkennung auf Basis akustischer Daten ist jedoch der Mangel an Trainingsdaten, die auf einem hohen Standard erprobt sind.

Erkennung von Felsbrocken | neuronale Netze | Seevermessung | Bathymetrie | Backscatter

  • Ausgabe: HN 119, Seite 6–17
  • DOI: 10.23784/HN119-01
  • Autor/en: Peter Feldens, Patrick Westfeld, Jennifer Valerius, Agata Feldens, Svenja Papenmeier

Sorry, this website uses features that your browser doesn’t support. Upgrade to a newer version of Firefox, Chrome, Safari, or Edge and you’ll be all set.

We use cookies on our website. Some of them are essential for the operation of the site, while others help us to improve this site and the user experience (tracking cookies). You can decide for yourself whether you want to allow cookies or not. Please note that if you reject them, you may not be able to use all the functionalities of the site.