Long-term underwater camera surveillance for monitoring and analysis of fish populations

Abstract

Long-term monitoring of the underwater environment is still labour intensive work. Using underwater
\nsurveillance cameras to monitor this environment has
\nthe potential advantage to make the task become less
\nlabour intensive. Also, the obtained data can be stored
\nmaking the research reproducible. In this work, a system to analyse long-term underwater camera footage
\n(more than 3 years of 12 hours a day underwater camera footage from 10 cameras) is described. This system
\nuses video processing software to detect and recognise
\nfish species. This footage is processed on supercomputers, which allow marine biologists to request automatic
\nprocessing on these videos and afterwards analyse the
\nresults using a web-interface that allows them to display
\ncounts of fish species in the camera footage.