VolRC RAS scientific journal (online edition)

Journal section "Mechanization, automation and informatization of agricultural production"

Practic of Implementing Convolutional Neural Networks in Agriculture and Agro-Industrial Complex

Alfer'ev D.A.

Volume 3, Issue 2, 2020

Alfer’ev D.A. Practic of Implementing Convolutional Neural Networks in Agriculture and Agro-Industrial Complex. Agricultural and Livestock Technology, 2020, vol. 3, no. 2. DOI: 10.15838/alt.2020.3.2.4 URL: http://azt-journal.ru/article/28585?_lang=en

DOI: 10.15838/alt.2020.3.2.4

Abstract   |   Authors   |   References
The development of computer equipment’s computation power has allowed to use the new tools for processing and analyzing data in the sphere of neuro-intelligence. Artificial neural networks are a modern tool for solving various types of problems, such as identification, forecasting and optimization. Although this tool has proven to be universal for solving various types of problems, it has not yet been widely used in some areas of knowledge. For example, at the moment, topologies of convolutional neural networks can be successfully used in the field of agriculture and agro-industrial complex. There is a large amount of information represented by graphical images, the main source of data when using machine computer vision methods in this area. In this regard, the purpose of the article is to review the modern achievements of computer vision in the agricultural sector and the agro-industrial complex, based on the architecture of convolutional neural networks, which, in turn, will allow specialists of the first level of agricultural areas, such as zootechnicians, agronomists and technologists, to use and implement this tool in their application projects. The author analyzes the basics of the computer vision theory characterizing its specifics and features; demonstrates the technology of convolution as a base-forming part of convolutional artificial neural networks; illustrates the examples from the practice of implementing this tool in the field of agriculture. In conclusion, the researcher highlights the features of currently implemented agricultural projects of machine computer vision, and indicates the prospects for its further development in this niche and digitalization of human life


monitoring, computer vision, machine learning, artificial neural networks, convolution

Article views

all: , this year: , this month: , today:

Article downloads

all: , this year: , this month: , today: