异质背景下黄河三角洲潮沟的遥感提取方法

以黄河三角洲为研究区域,针对该区域潮滩背景异质性强、潮沟宽度不一和潮沟各向异性强等特点,选取高分二号多光谱影像作为数据源,首先利用归一化水体指数(NDWI)和最大类间方差法(OTSU)提取宽阔潮沟,其次,使用改进的模糊C均值算法(MFCM)和多尺度高斯匹配滤波(MGMF),在削弱潮滩背景异质性的基础上增强细小潮沟,接着利用自适应阈值分割提取细小潮沟,最后合并细小潮沟和宽阔潮沟,形成完整的潮沟网络.不仅充分利用了高分二号影像的空间分辨率和光谱信息,也顾及了线状要素的几何特征,保证了潮沟提取结果的空间连续性.在4个局部测试区域,提取结果的Kappa系数大于0.8,总体精度高于97%,优于最大似然法和支持向量机.结果表明: 本研究提出的方法能够较完整地提取不同类型的潮沟,表现出较好的提取精度和稳定性,能够为潮沟的实时动态监测及其发育演化规律研究提供科学参考.

Extracting method of tidal creek features under heterogeneous background at Yellow River Delta using remotely sensed imagery.

The Yellow River Delta exhibits irregular tidal flat, with tidal creeks that vary in width and experience tidal creek current anisotropy. Given such characteristics, the GF-2 multi-spectral image was selected as the data source to characterize the details of tidal creeks. First, the normali-zed difference water index (NDWI) and OTSU classification were used to delineate the wide tidal creeks. Second, the modified fuzzy C-means clustering algorithm (MFCM) and multi-scale Gaussian matching filter (MGMF) were used to enhance the narrow tidal creeks on the basis of weakening the heterogeneity of tidal flat background. Then, the adaptive threshold segmentation was conducted to delineate the narrow tidal creeks. Finally, the complete tidal creek networks were delineated by combining the wide and narrow tidal creeks. We fully used the spatial resolution and spectral information of the GF-2 image and took into account the geometric features of the linear features, ensuring the spatial continuity of the tidal creek extraction results. In the four tested areas, the Kappa coefficient was greater than 0.8 and the overall accuracy was greater than 97%, which performed better than the maximum likelihood method and support vector machine. The results showed that the proposed method could completely differentiate different types of tidal creeks, with good extraction accuracy and stability. The method could provide scientific reference for real-time dynamic monitoring of tidal creek and its development and evolution.