基于高分遥感影像的黄土高原地区水体高精度提取

High-precise extraction for water on the Loess Plateau region from high resolution satellite image

黄土高原地区水体特征复杂多样,基于高空间分辨率遥感影像在大面积范围内,现有提取方法很难兼顾精度与效率,故提出一种新型的水体精细化自动提取方法。首先,在全局范围内根据不同的水体类型使用面向对象的影像分析技术按照不同的规则方法初步提取水体的主体部分,形成水体的种子区域;然后,在局部范围内根据同一地物的光谱相似性,进行区域种子生长,实现水体的高精度提取。结果表明,使用该方法提取的水体边缘可以较好地与影像吻合,更能保证水体的完整性,有效减少干扰信息,提升运算效率。

In the Loess Plateau region,it is difficult to extract the complex water automatically and accurately in a large area,and hence a new water extraction method is proposed in this paper,which combines the object-based image analysis and seeded region growing algorithm. In the first step,it uses object-based image analysis to extract the main part of the water body according to the different water features and form the seeds region of water area. Then based on the result,the seeds grew to the precise shape of water. Extraction result shows that the method is effective,high precise and high efficient.