基于资源1号02D高光谱图像湿地水体分类方法对比——以白洋淀为例

陈民, 彭栓, 王涛, 吴雪芳, 刘润璞, 陈玉烁, 方艳茹, 阳平坚

A comparative study of water body classification of wetlands based on hyperspectral images from the ZY1-02D satellite: A case study of the Baiyangdian wetland

CHEN Min, PENG Shuan, WANG Tao, WU Xuefang, LIU Runpu, CHEN Yushuo, FANG Yanru, YANG Pingjian

表4 基于邻域范围光谱的湿地分类精度

Tab.4 Wetland classification accuracy using different patch-based methods

模型 每类样本的分类准确率 OA/% mAP/% F1 R/% 湖泊水面/% 内陆滩涂/% 村庄/% 沼泽/% 水浇地/% ResNet 98.68 90.65 99.85 96.57 95.88 96.67 99.14 0.97 98.06 CNN2D1D 99.03 87.31 99.56 93.65 96.44 96.03 98.90 0.96 97.83 CNN3D 98.69 88.45 99.47 94.83 96.68 96.20 98.93 0.97 97.78 ViT 99.66 93.22 98.48 97.50 99.06 98.11 99.69 0.98 98.96 SSRN 99.55 97.99 99.80 99.30 99.04 99.19 99.93 0.99 99.50 SSTN 99.47 97.37 99.80 99.96 99.14 99.05 99.83 0.99 99.41