Biofouling Estimation in Mariculture
This paper presents an overview of advances in estimation of the biofouling state of fish cages as a part of the HEKTOR (Heterogeneous Autonomous Robotic System in Viticulture and Mariculture) project. Firstly, the developed framework for biofouling estimation is shown and explained in brief. A method using k-means clustering for labeling images of fish cages is outlined. It is followed by results of machine learning approaches for automatic inferring of semantic meaning of pixels in an image trained on a recorded dataset using said outlined method. Furthermore, a brief overview and results of contour detection on images classified by trained machine learning models are given. Moreover, a method of feature-based monocular camera distance estimation constrained by assumptions of the viewing angle is presented. All mentioned methods and algorithms fit together in order to produce an estimation of how biofouled the observed net is. The successfulness of the estimation depends on the viewing conditions while filming the cages. In good conditions the results are satisfactory and could be used by industrial fisheries in place of human labour. All the developed algorithms are fast enough so that the entire process from start to finish takes less than 1 second.