The aim was to develop processing technologies for subsea camera images to extract information about fish size distributions, fish behaviour, fish abundance and biomass. This technology is valuable for monitoring of wild and farmed fish stocks but also for bio-monitoring, where fish and animals are used as indicators for the state of the environment.
In the project, we used an underwater 3D range-gated camera to make accurate fish-length estimation of free-swimming fish. The system requires no manual work or contact with the fish and was done in-situ. We achieved length estimation errors in the order of 1% of manual-measured fish length. These results can further be refined into estimates of fish biomass and growth.