Side-Scan Sonar Imaging: Automatic Boulder Identification

Jesper Haahr Christensen, Lars Valdemar Mogensen, Ole Ravn

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

Boulder surveys seek to identify prominent boulders which position may collide with planned cable routes, offshore wind farms, or other subsea activities. Data is collected using suitable sensor technologies such as bathymetry from multibeam echosounders and side-scan sonar imaging. Currently, the boulder identification process is a labor-intensive job that requires domain expertise to interpret the data and provide each identified target with accurate annotations. In this work, we describe the initial steps of our method used for automatic boulder identification in side-scan data. This covers identifying each boulder instance and further generates metadata for filtering, sorting, and report generation. In addition to being an automated process, our method can process several kilometers of side-scan data and identify thousands of boulders in less than a minute. This is not only orders of magnitudes faster than human processors but also with great accuracy results.
Original languageEnglish
Title of host publicationOCEANS 2021
Number of pages6
PublisherIEEE
Publication date23 Sep 2021
Pages1-6
Article number9705713
ISBN (Print)978-1-6654-2788-3
DOIs
Publication statusPublished - 23 Sep 2021
EventOceans 2021 - San Diego, United States
Duration: 20 Sep 202123 Sep 2021

Conference

ConferenceOceans 2021
Country/TerritoryUnited States
CitySan Diego
Period20/09/202123/09/2021

Keywords

  • Image segmentation
  • Visualization
  • Filtering
  • Shape
  • Oceans
  • Sonar
  • Imaging

Fingerprint

Dive into the research topics of 'Side-Scan Sonar Imaging: Automatic Boulder Identification'. Together they form a unique fingerprint.

Cite this