Author(s): Keisuke Yoshida; Shijun Pan; Satoshi Nishiyama; Takashi Kojima

Linked Author(s): Shijun Pan, Keisuke Yoshida

Keywords: Irborne LiDAR Bathymetry; Cross-platform; Deep Learning; Green LiDAR System; Riverine Land Cover Classification

Abstract: This study employs a validated airborne Light Detection and Ranging (LiDAR) bathymetry system (ALB) and a UAV-borne Green LiDAR System (GLS) for cross-platform analysis of land cover classification (LCC). Furthermore, the study aims to visualize LiDAR data using high-contrast colour scales and improve the accuracy of land cover classification methods through image fusion techniques. If high-resolution aerial imagery is available, it needs to be downscaled to match the resolution of the low-resolution point clouds. The interchangeability of cross-platform data was assessed by comparing the interchangeability, which measures the absolute difference in overall accuracy (OA) or macro-F1 by comparing the cross-platform inter prediction. It is important to note that relying solely on aerial photographs is inadequate for achieving precise labelling, particularly under limited sunlight conditions that can result in misclassification. In such cases, LiDAR plays a crucial role in facilitating target recognition.

DOI: https://doi.org/10.3850/iahr-hic2483430201-355

Year: 2024