Academic profile · UAV navigation · Geospatial AI
Assistant Professor and Department Chair
Department of Information Systems and Technologies
Cappadocia University
I develop visual and terrain-aware methods for robust UAV positioning when satellite navigation is unavailable or degraded. My work brings together remote sensing, photogrammetry and deep learning.
Turning aerial imagery and terrain structure into dependable position estimates.
Current research connects aerial imagery with terrain, elevation and cross-view evidence for dependable navigation and geospatial analysis.
UAV positioning can become unreliable when satellite navigation is blocked, degraded or deliberately disrupted. Visual observations must then be related to georeferenced map evidence despite changes in altitude, season, route and geography.
Image-only analysis can miss the topographic structure that governs scale, surface form, visibility and spatial change. Orthophotos and elevation products must be analysed as a connected geospatial system.
Archaeological traces can be subtle, spatially extensive and difficult to recognise consistently across large orthophoto and elevation datasets.
Journal article
Academic Platform Journal of Engineering and Smart Systems, 14(1), 46–54
Journal article
Çukurova Üniversitesi Mühendislik Fakültesi Dergisi, 40(1), 33–48
PhD thesis
Çukurova University, Institute of Natural and Applied Sciences
Active
The project examines morphological change, surface retreat and rockfall hazards affecting Cappadocia’s fairy chimneys and tuff formations, with the goal of producing an inventory and a risk-priority map.
2026 · 18 months
Active
This project adapts a ResNet50 regression model to estimate UAV altitude from nadir imagery collected under varied terrain, weather and illumination conditions.
2026 · 12 months
Active
The project investigates automatic archaeological site detection from digital elevation models and high-resolution orthophotos using deep learning and terrain-aware image analysis.
1 Oct 2025–present