GeoMultiTaskNet: remote sensing unsupervised domain adaptation using geographical coordinates

V Marsocci, N Gonthier, A Garioud… - Proceedings of the …, 2023 - openaccess.thecvf.com
Land cover maps are a pivotal element in a wide range of Earth Observation (EO)
applications. However, annotating large datasets to develop supervised systems for remote …

Monitoring urban expansion by coupling multi-temporal active remote sensing and landscape analysis: changes in the metropolitan area of cordoba (argentina) from …

F Marzialetti, P Gamba, A Sorriso, ML Carranza - Remote Sensing, 2023 - mdpi.com
Uncontrolled and unsustainable urban sprawl are altering the Earth's surface at
unprecedented rates. This research explores the potential of active remote sensors for …

Ensuring resilience and safety of the transportation system of Kyiv in planning the network of road tunnels

H Haiko, I Savchenko, A Shelestov - Case Studies on Transport Policy, 2024 - Elsevier
The analysis of risk mitigation in the transport infrastructure of the Kyiv city by using a system
of car tunnels was conducted, their ranking and construction priorities were determined. The …

Advanced method of land cover classification based on high spatial resolution data and convolutional neural network

A Shelestov, B Yailymov, H Yailymova, L Shumilo… - 2022 - repo.bibliothek.uni-halle.de
Based on modern satellite products Planet with high spatial resolution 3 meters, authors of
this paper improved the neural network methodology for constructing land cover …

Mathematical Model for Determining the Geometric Location of the Environmental Pollutant Based on Sensor Data

V Khaidurov, B Yailymov… - 2023 IEEE 12th …, 2023 - ieeexplore.ieee.org
The practical result of this work is the development of a generalized mathematical model for
determining the position of an environmental pollutant. Computer simulation was carried out …

Dynamic scale adaptation algorithm of image etalon functions

M Gavrikov, R Sinetsky - 2022 - repo.bibliothek.uni-halle.de
An algorithm for large-scale adaptation of prototype functions representing image classes is
proposed. The algorithm identifies the parameters of nonlinear scale distortions contained in …