Open AccessSelection of an algorithm for automatic classification of satellite images for the study of agricultural crops on the territory of Vietnam
Author(s) -
Б. Н. Олзоев,
Hongyi Huang,
Л. А. Пластинин,
В. Е. Гагин,
O V Danchenko
Publication year - 2021
Publication title -
iop conference series. earth and environmental science
Language(s) - English
Resource type - Journals
eISSN - 1755-1307
pISSN - 1755-1315
DOI - 10.1088/1755-1315/937/3/032082
Subject(s) - mahalanobis distance , algorithm , computer science , parallelepiped , field (mathematics) , satellite , statistical classification , agriculture , selection (genetic algorithm) , data mining , artificial intelligence , pattern recognition (psychology) , mathematics , geography , engineering , geometry , archaeology , pure mathematics , aerospace engineering
The paper is devoted to the choice of an algorithm for automatic controlled classification of multi-zone satellite images of Landsat 8 OLI for the purposes of agricultural crop research based on the analysis of various mathematical classification algorithms and comparison of the practical results of these algorithms when using the ENVI 5.4 software package. In the period from June to August 2020, a field survey was conducted by coordinating and ground-based object recognition for the purpose of compiling decryption standards based on images. The paper analyzes four frequently used popular algorithms for automatic controlled classification – maximum likelihood, minimum distance, Mahalanobis distance, parallelepiped. As a result, it is concluded that when classifying objects with very close brightness values, the maximum likelihood algorithm gives optimal and objective results. This conclusion was confirmed by the cameral method by evaluating the reliability of the classification results. The result of the study can be used for mapping agricultural crops and solving other problems of agricultural activity in Vietnam. The methodology presented in the paper can be applied when choosing controlled classification algorithms for other groups of plant complexes and objects based on remote sensing data from space.