Agro-field Boundary Detection using Mask R-CNN from Satellite and Aerial Images
Temurbek KuchkorovTashkent university of information technologies nmaed after Muhammad al-Khwarizmi, Tashkent, UzbekistanTemur OchilovTashkent university of information technologies nmaed after Muhammad al-Khwarizmi, Tashkent, UzbekistanElyor GaybulloevTashkent university of information technologies nmaed after Muhammad al-Khwarizmi, Tashkent, UzbekistanNazokat SobitovaUzbek-Israel joint faculty, National University of Uzbekistan named after Mirzo Ulugbek, Tashkent, UzbekistanOrtik RuzibaevFaculty of Software engineering, Tashkent university of information technologies nmaed after Muhammad al-Khwarizmi, Tashkent, Uzbekistan
2021 International Conference on Information Science and Communications Technologies (ICISCT)conference2021en
ABI
Abstract
Agriculture is important to the food security and economic growth of most countries in the world, especially in developing countries. Accurate information on field boundaries has considerable importance in precision agriculture and greatly assists land administration systems. This paper proposes a deep learning-based approach, for detecting and boundary segmentation of agricultural fields based on the state-of-the-art instance segmentation approach, Mask Region Convolutional Neural Network (Mask R-CNN). This model can accurately detect each agricultural field in the satellite and aerial image. The experimental results indicate that our automated approach can detect agricultural fields more accurately.
Topics
Identifiers
Citations and references
Metrics — AkademScholar · Coming soon