Mazurets, O.V.Klimenko, V.I.Мазурець, Олександр Вікторович2025-12-262025-12-262025Mazurets O.V., Klimenko V.I., Shurypa M.O. Neural Network Assessment of Buildings Condition Based on Visual Data. Innovations of Modern Science and Education. Proceedings of IV International Scientific and Practical Conference. December 25-27, 2025. Vancouver, Canada. Pp. 120-129https://elar.khmnu.edu.ua/handle/123456789/20055The paper addresses the problem of automated assessment of building condition based on visual data in the context of post-war reconstruction and large-scale urban monitoring. A neural network–based approach is proposed that combines automatic building segmentation in aerial and UAV imagery with subsequent classification of structural condition. Lightweight single-stage segmentation models from the YOLOv8–YOLOv12 families were investigated, with particular attention to compact configurations suitable for resource-constrained deployment. The methodology includes image tiling, data augmentation, class balancing, and a multi-head architecture for joint instance segmentation and condition classification. Experimental results demonstrate that compact models with enhanced augmentation achieve the best trade-off between accuracy and efficiency, providing reliable building localization and acceptable performance for multi-class damage assessment. The proposed approach enables automated generation of damage maps and can support prioritization of engineering inspections and decision-making in post-war reconstruction and urban infrastructure management.enСтаття004.8