A New Land-Cover Classification Approach in UAV-based Remote Sensing for Solution Ecological Tasks
Софія Іоганівна Альперт, Maksym Alpert · 16th International Conference Monitoring of Geological Processes and Ecological Condition of the Environment · 2022
Summary Nowadays application of UAVs gives a possibility to achieve data with a very high accuracy for solution of different ecological and agricultural problems. The classification of incomplete and high conflicting sources is one of the most important and difficult procedures in Remote Sensing. It has been proposed the new classification approach to applying Dezert-Smarandache Theory in UAV-based remote sensing problems. The classical Dezert-Smarandache fusion rule has been considered in this work. It has been noted, that this theory processes the contradictory information an deals with exhaustive and not mutually exclusive hypotheses. The numerical example has been considered in this work too. The proposed approach to applying the Dezert-Smarandache Theory in land-cover classification can be applied in numerous agricultural tasks, pest control in forestry, prevention of natural disasters, such as forest fires.