Automatic Determination of Sturgeon Size at Different Growth Stages Using Deep Learning Technologies

Abstract

Fish resources play a crucial role in Russia's economy, particularly given its vast coastline, extensive aquatic areas, and rich marine and freshwater resources. Preserving and replenishing fish resources due to agricultural activities, poaching, and environmental disasters is one of the pressing challenges in the modern world. In Russia, there is active construction and development of fish farms, fisheries, and biological laboratories, partly driven by economic constraints in recent years. One of the most valuable fish species is sturgeon, which requires specific conditions compared to, for example, catfish. Production personnel monitor compliance with conditions and observe the growth and activity of these fish. To enhance production efficiency, there has been a recent trend towards digitizing production and implementing cyber-physical systems. This paper proposes a method for automatically determining the sizes of sturgeon at different growth stages and outlines prospects for further research.