Towards Automated Classification of Seabed Substrates in Underwater Video

Matthew Pugh, Bernie Tiddeman, Hannah Mary Dee, Phil Hughes

Research output: Chapter in Book/Report/Conference proceedingConference Proceeding (Non-Journal item)

2 Citations (SciVal)
201 Downloads (Pure)


In this work, we present a system for the automated classiffication of seabed substrates in underwater video. Classiffication of seabed substrates traditionally requires manual analysis by a marine biologist, according to an established classiffication system. Accurate, consistent and robust classiffication is difficult in underwater video due to varying lighting conditions, turbidity and method of original recording. We have developed a system that uses ground truth data from marine biologists to train and test per-frame classiffiers. In this paper we present preliminary results of this using various feature representations (histograms, Gabor wavelets) and classiffiers (SVC, kNN) on both full-frame and patched-based analysis, achieving up to 93% accuracy.
Original languageEnglish
Title of host publicationComputer Vision for Analysis of Underwater lmagery Workshop
Subtitle of host publicationInternational Conference on Pattern Recognition
Place of PublicationStockholm
PublisherIEEE Press
Number of pages8
ISBN (Print)978-1-4799-6709-4
Publication statusPublished - 24 Aug 2014
Event22nd International Conference on Pattern Recognition - Stockholm Waterfront, Stockholm, Sweden
Duration: 24 Aug 201428 Aug 2014


Conference22nd International Conference on Pattern Recognition
Period24 Aug 201428 Aug 2014


  • underwater video analysis
  • texture
  • Gabor filters
  • substrate classification
  • machine learning


Dive into the research topics of 'Towards Automated Classification of Seabed Substrates in Underwater Video'. Together they form a unique fingerprint.

Cite this