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3 基于单点光谱的湿地分类精度
Tab.3 Wetland classification accuracy based on different pixel-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/% 沼泽地/% 水浇地/%
SVM 97.51 59.66 99.27 46.75 92.60 83.90 89.73 0.82 89.30
AdaBoost 98.17 69.96 99.61 71.90 93.29 89.48 95.61 0.89 93.23
RF 97.72 61.96 98.43 57.54 91.51 85.33 92.67 0.84 90.06
CNN1D 97.51 84.76 99.56 90.11 96.10 94.54 98.13 0.95 95.75
RNN 95.80 87.08 99.13 85.68 96.09 94.03 97.74 0.94 94.95
SSTN(Pixel) 96.87 83.94 98.53 89.34 94.99 93.79 97.55 0.94 95.07
ViT(Pixel) 97.09 88.59 99.38 91.91 95.00 95.11 98.50 0.95 95.83