UAV Autonomous Positioning Based on Coastline Recognition and Matching

With the increasing diversification of unmanned aerial vehicle (UAV) applications, conventional positioning and navigation systems are confronted with significant challenges, particularly in Global Navigation Satellite System (GNSS)-denied environments. To address this issue, our study investigates noncooperative island environments and proposes the approach of “coastline identification followed by matching.” This approach involves matching coastline features extracted from UAV aerial imagery with reference coastlines obtained from Google Satellite Maps, thereby achieving precise UAV localization in GNSSdeprived conditions. Experimental results demonstrate a positioning success rate of $\mathbf{9 5 \%}$, establishing a practical approach for autonomous positioning that shows promise in both theoretical significance and practical value.