基于高分辨率遥感影像和改进U-Net模型的滑坡提取——以汶川地区为例

白石, 唐攀攀, 苗朝, 金彩凤, 赵博, 万昊明

Information extraction of landslides based on high-resolution remote sensing images and an improved U-Net model: A case study of Wenchuan, Sichuan

BAI Shi, TANG Panpan, MIAO Zhao, JIN Caifeng, ZHAO Bo, WAN Haoming

表3 常用分割网络与改进后的U-Net网络评价指标对比结果

Tab.3 Comparison results of common segmentation network and improved U-Net network evaluation index

模型 IoU Precision Recall F1-score 浮点运算次数/109 参数量/106 U-Net+AC+DUC 0.76 0.84 0.90 0.85 192.8 56.5 ResU-Net 0.62 0.68 0.91 0.73 324.9 13.0 DeeplabV3+ 0.62 0.75 0.82 0.74 89.6 59.3 UperNet 0.65 0.79 0.82 0.76 183.1 126.1 HATNet 0.63 0.77 0.80 0.75 65.0 70.4 Convnext 0.54 0.86 0.62 0.69 193.7 138.0 Swin-Transformer 0.50 0.56 0.81 0.60 264.8 138.0