Unmanned Aerial Vehicles (UAVs) are increasingly utilized in various industries for tasks ranging from surveillance to logistics. However, GPS signal loss in dense urban environments poses significant challenges to the safe and accurate navigation of UAVs. This paper proposes a vision-based position estimation system that leverages the Scale-Invariant Feature Transform (SIFT) algorithm to provide robust UAV navigation in GPSdenied environments. By detecting keypoints in high-resolution images captured by the UAV’s camera and matching these points across successive frames, the system calculates displacement and converts pixel-based movements into real-world metrics. Experimental results show that the proposed method provides a reliable alternative to GPS-based navigation with an average error rate of %6.09. The system’s real-time processing and adaptability to complex urban environments make it a viable tool for enhancing UAV navigation in GPS-compromised scenarios.