Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
January 22, 2026Photogrammetric Engineering & Remote Sensing

Deep Learning–based LOD-2 Building Modeling and Its Application to Solar Energy Estimation Using Unmanned Aerial Vehicle Imagery

View Full Paper
Ask AI
Bookmark
Share

Authors

IMIradaf MandayaJRJiann-Yeou Rau

Discussion

Loading...

Member takes

Overview

Research demonstrates solar energy potential in building models, indicating significant renewable energy opportunities.

Key Points

  • The research aims to estimate the annual solar energy potential and energy generation on roof planes using UAV imagery.
  • Used deep learning for building footprint extraction and roof-plane segmentation
  • Employed RANdom Sample Consensus (RANSAC) for robust fitting
  • Conducted multi-criteria selection based on parameters like orientation and slope
  • Estimated annual power generation of 553,219 kWh from roof planes
  • Demonstrated effectiveness of the method for solar energy estimation
  • Highlighted potential for reducing carbon emissions with rooftop photovoltaic systems

Cite This Study

Mandaya et al. (2026) studied this question.

synapsesocial.com/papers/6971bdcf642b1836717e2724https://doi.org/10.14358/pers.25-00144r3
View Full Paper
Ask AI
Bookmark
Share