基于Sentinel-2影像的围海养殖信息提取

为了能够利用遥感图像快速准确地提取围海养殖矢量信息，本文选取养殖水体、堤坝及育苗室等交错分布的海参围海养殖区域作为研究区域，根据研究区域Sentinel-2遥感影像的光谱特征，选用归一化差异水体指数（Normalized Difference Water Index，NDWI）、改进归一化差异水体指数（Modified Normalized Difference Water Index，MNDWI）和增强水体指数（Enhanced Water Index，EWI）三类水体指数，分别进行提取实验，利用同时期高空间分辨率的高分二号卫星（GF-2）影像作为参考，验证不同方法的提取精度，精度评价结果表明：相较MNDWI和EWI两类水体指数，NDWI的分类精度更高，且利用NDWI提取研究区域的围海养殖信息的效果更好，所以该方法可在养殖区域的动态监测和规划管理中发挥数据支撑作用。

Information Extraction of Sea-Enclosed Aquaculture Based on Sentinel-2 Remote Sensing Images

In order to use remote sensing images to extract quickly and accurately the vector information of sea-enclosed aquaculture, some scattered enclosed sea cucumber aquaculture areas such as aquaculture water bodies, dams and nursery rooms are selected as the study area. According to the spectral characteristics of Sentinel-2 remote sensing images in the study area, three kinds of water body indices, including Normalized Difference Water Index (NDWI), Modified Normalized Difference Water Index (MNDWI) and Enhanced Water Index (EWI), are selected and used to carry out the information extraction experiments respectively. The extraction accuracy of each method is then verified by using the high spatial resolution GF-2 satellite image in the same period as the reference. The results of accuracy evaluation show that comparing with MNDWI and EWI, the classification accuracy is higher and the information extraction effect can be better by using NDWI, indicating that the water body index method can play a data-supporting role in the dynamic monitoring and planning management of aquaculture areas.