| 空-谱角匹配与多指数法相结合的OLI遥感影像水体提取 |
| |
| 引用本文： | 张启华,王胜利,孙磊,蒋毅.空-谱角匹配与多指数法相结合的OLI遥感影像水体提取[J].测绘通报,2019,0(12):71-76. |
| |
| 作者姓名： | 张启华 王胜利 孙磊 蒋毅 |
| |
| 作者单位： | 江苏省地质测绘院,江苏 南京,211102 |
| |
| 基金项目： | 国家自然科学基金（41401093；41601405） |
| |
| 摘 要： | 针对复杂环境条件下水体遥感提取结果不连续且易与植被、建筑物、阴影相混淆的难题，基于Landsat 8 OLI影像，以石家庄市平山县岗南水库和宿迁市骆马湖附近河流为研究区，提出了一种空-谱角匹配与多指数法相结合的水体信息提取方法；并与单波段阈值法、归一化差分水体指数法（NDWI）、光谱角匹配法（SAM）、自动水体提取指数法（AWEI）和一类支持向量机法（OC-SVM）的水体提取结果进行对比分析和精度评定。试验结果表明，本文提出的方法兼顾了多特征之间的互补性优势，引入的空间信息有效地抑制了噪声的干扰，且以像素为基元的提取策略较好地保持了水体的边缘信息，避免了出现平滑掉细节信息的情况；与传统方法相比，本文方法受植被、建筑和阴影的干扰最小，对细小水体也具备较好的识别能力。
|
| 关 键 词： | OLI影像 空-谱信息 LBV变换 一类支持向量机 水体提取 |
| 收稿时间： | 2019-02-25 |
Water body extraction from OLI remote sensing images based on spatial-spectral angle matching and multi-index method |
| |
| ZHANG Qihua,WANG Shengli,SUN Lei,JIANG Yi.Water body extraction from OLI remote sensing images based on spatial-spectral angle matching and multi-index method[J].Bulletin of Surveying and Mapping,2019,0(12):71-76. |
| |
| Authors: | ZHANG Qihua WANG Shengli SUN Lei JIANG Yi |
| |
| Institution: | Jiangsu Geologic Surveying and Mapping Institute, Nanjing 211102, China |
| |
| Abstract: | Aiming at the disadvantage of low precision of water body remote sensing extraction under complex environment, a water body information extraction method based on space-spectral angle matching and multi-index method is proposed. Compared with single-band threshold method, normalized difference water index method (NDWI), spectral angle matching method (SAM), automatic water extraction index method (AWEI) and one-class support vector machine (OC-SVM), the water extraction results are analyzed and the accuracy is evaluated. Experiments in two research areas on Landsat 8 OLI images show that the new method takes into account the complementary advantages of multi-features. The spatial information introduced can effectively suppress noise and the pixel-based extraction strategy can maintain the edge information of the water body better, and avoid the situation of smoothing the details. Compared with traditional methods, this method is least disturbed by vegetation, buildings and shadows, and has better recognition ability for small water bodies. |
| |
| Keywords: | OLI images spatial-spectral feature LBV transformation one-class support vector machine water body extraction |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《测绘通报》浏览原始摘要信息 |
| 点击此处可从《测绘通报》下载免费的PDF全文 |
|
