Exploring the effects of different combination ratios of multi-source remote sensing images on mangrove communities classification

作者：Bolin Fu, Shurong Zhang, Huajian Li, Hang Yao, Weiwei Sun, Mingming Jia, Yanli Yang, Hongchang He, Yuyang Li · 发表于：International Journal of Applied Earth Observation and Geoinformation · 年份：2024 · DOI：10.1016/j.jag.2024.104197 · 被引用次数：25 · 研究领域：Coastal wetland ecosystem dynamics、Remote Sensing and Land Use、Land Use and Ecosystem Services

• A novel UHRViT algorithm utilizes multi-scale feature extraction and interaction for mangrove species classification. • Evaluating the classification performance of UAV-RGB, UAV-LiDAR, and GF-3 polarimetric SAR data. • Exploring the effects of twelve combination ratios of active and passive data on mangrove species mapping. • Revealed classification accuracy changes across multi-sensor combination ratios and identified the optimal ratios. Mangroves are one of the most important marine ecosystems globally, their spatial distribution is crucial for promoting mangrove ecosystems conservation, restoration, and sustainable managements. This study proposed a novel Unet-Multi-Scale High-Resolution Vision Transformer (UHRViT) model for classifying mangrove species using unmanned aerial vehicle (UAV-RGB), UAV-LiDAR, and Gaofen-3 Synthetic Aperture Radar (GF-3 SAR) images. The UHRViT utilized a multi-scale high-resolution visual Transformer as its backbone network and was designed to a multi-branch U-shaped network structure to extract features of different scales layer by layer, and to facilitate the interaction of high and low-level semantic information. We further verified the classification performance superiority of UHRViT model by comparing to HRViT and HRNetV2 algorithms. We also systematically investigated the effects of active–passive image combination ratios on mangrove communities mapping. The results revealed that: UAV-RGB images exhibited the better classification accura...