Перегляд за Автор "Didur, V.O."

Зараз показуємо 1 - 1 з 1
  • Ескіз
    Документ
    Approach for Comparative Analysis of Effectiveness of using MobileNetV3 and ViT Neural Network Models for Graphical Localization of Destroyed Buildings Remains Areas
    (2025) Didur, V.O.; Molchanova, M.O.; Tyschenko, O.O.; Mazurets, O.V.; Мазурець, Олександр Вікторович
    This study presents a comparative analysis of MobileNetV3 and Vision Transformer (ViT) neural networks for graphical localization of destroyed building remains. A custom software solution was developed to process images from robotic systems, train both models on a labeled dataset, and evaluate their performance in realistic conditions. Results showed that both architectures achieved high accuracy, with ViT offering strong classification precision and MobileNetV3 excelling in efficiency for edge deployment. The findings highlight each model's potential for disaster response applications involving automated debris analysis.