
Effect of recording device parameters on the operation of the sugar beet recognition algorithm in the early stages of growth
Author(s) -
M. A. Mirzaev,
A. I. Dyshakov
Publication year - 2021
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/1129/1/012062
Subject(s) - algorithm , value (mathematics) , computer science , quality (philosophy) , sugar beet , computer vision , artificial intelligence , mathematics , machine learning , agronomy , philosophy , epistemology , biology
This experiment makes it possible to estimate the influence of the distance from the recording device lens to the ground on the recognition algorithm by comparing the area of the recognized part of the plant. The experiments are based on the fact that the main error of the algorithm is to reduce the area of the recognized part of the plant with a significant deterioration of parameters. The study carried out a number of experiments including a gradual change of height from the minimum structurally possible value to the maximum at which there is a significant loss of quality under different lighting conditions ensuring normal operation of the vision algorithm.