Shoreline Extraction Based on LiDAR Data Obtained Using an USV

: This article explores the use of Light Detection And Ranging (LiDAR) derived point clouds to extract the shoreline of the Lake K ł odno (Poland), based on their geometry properties. The data collection was performed using the Velodyne VLP ‐ 16 laser scanner, which was mounted on the HydroDron Unmanned Surface Vehicle (USV). A modified version of the shoreline extraction method proposed by Xu et al. was employed, comprising of the following steps: (1) classifying the point cloud using the Euclidean cluster extraction with a tolerance parameter of 1 m and min. cluster size of 10,000 points, (2) further filtration of boundary points by removing those with height above 1 m from the measured elevation of water surface, (3) manual determination of a curve consisting of 5 points located along the entire shoreline extraction region at a relatively constant distant from the coast, (4) removal of points that are further from the curve than the average distance, repeated twice. The method was tested on the scanned section of the lake shoreline for which Ground Control Points (GCP) were measured using a Global Navigation Satellite System (GNSS) Real Time Kinematic (RTK) receiver. Then, the results were compared to the ground truth data, obtaining an average position error of 2.12 m with a standard deviation of 1.11 m. The max error was 5.54 m, while the min. error was 0.41 m, all calculated on 281 extracted shoreline points. Despite the limitations of this parametric, semi ‐ supervised approach, those preliminary results demonstrate the potential for accurate shoreline extraction based on LiDAR data obtained using an USV. Further testing and optimisation of this method for larger scale and better generalisation for different waterbodies are necessary to fully assess its effectiveness and feasibility. In this context, it is essential to develop computationally efficient methods for approximating shorelines that can accurately determine their course based on a set of points.