Automated Quantification of Brittle Stars in Seabed Imagery Using Computer Vision Techniques.

Journal: Sensors (Basel, Switzerland)
Published Date:

Abstract

Underwater video surveys play a significant role in marine benthic research. Usually, surveys are filmed in transects, which are stitched into 2D mosaic maps for further analysis. Due to the massive amount of video data and time-consuming analysis, the need for automatic image segmentation and quantitative evaluation arises. This paper investigates such techniques on annotated mosaic maps containing hundreds of instances of brittle stars. By harnessing a deep convolutional neural network with pre-trained weights and post-processing results with a common blob detection technique, we investigate the effectiveness and potential of such segment-and-count approach by assessing the segmentation and counting success. Discs could be recommended instead of full shape masks for brittle stars due to faster annotation among marker variants tested. Underwater image enhancement techniques could not improve segmentation results noticeably, but some might be useful for augmentation purposes.

Authors

  • Kazimieras Buškus
    Faculty of Mathematics and Natural Sciences, Kaunas University of Technology, Studentu 50, LT-51368 Kaunas, Lithuania.
  • Evaldas Vaičiukynas
    Faculty of Informatics, Kaunas University of Technology, Studentu 50, LT-51368 Kaunas, Lithuania.
  • Antanas Verikas
    Faculty of Electrical and Electronics Engineering, Kaunas University of Technology, Studentu 50, LT-51368 Kaunas, Lithuania.
  • Saulė Medelytė
    Marine Research Institute, Klaipėda University, Universiteto 17, LT-92294 Klaipėda, Lithuania.
  • Andrius Šiaulys
    Marine Research Institute, Klaipėda University, Universiteto 17, LT-92294 Klaipėda, Lithuania.
  • Aleksej Šaškov
    Marine Research Institute, Klaipėda University, Universiteto 17, LT-92294 Klaipėda, Lithuania.