Researchers from Novosibirsk State University (NSU) are trying to create a neural network for counting Baikal perch larvae.
Hundreds of millions of young omuls are released into Lake Baikal and into the rivers that flow into it each year as part of the population renewal program. Specialists catch spawning fish to collect caviar. It is placed in incubators, where it develops into larvae without external threats released into the natural environment.
Currently, in “maternity hospitals for omul”, omul larvae are counted by the volumetric method on the Weiss apparatus. This is a laborious process and automatic counting equipment is designed for shrimp or small fish. The linear size of the larvae of the omul is ten millimeters.
NSU has created a product accounting system based on the principle of deep neural networks that is being tested to count glass containers on a conveyor. Neural networks will now be trained to recognize the omul larva in the same way as the human eye. Siberian specialists will develop a system to scatter water flow and larvae in order to accurately count the number of small objects moving in a continuous mass.
Pavel Zhikharev, one of the developers, a programmer at the Center for Applied Deep Learning at the NSU Higher Informatics College, said that the prototype of the developed device for counting larvae has already been tested, and the accuracy is 98%. The scientists expect that they will have time to complete work on developing the system before the omul larvae hatch en masse in the spring of next year.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
