基于线状特征增强的TM遥感影像细小河流提取方法

混合像元效应是导致难以从TM影像中提取细小河流的主要原因。提出一种综合多种数字图像处理技术的细小河流自动识别方法。首先，利用阈值分割区分水体指数影像中的细小河流与面状水体；第二，对水体指数进行线状信息增强，突出线状河流信息，并抑制其他地物信息；第三，利用双阈值线段追踪方法，提取影像中的细小河流；第四，通过三种方法分别去除阴影、道路和其他类型噪声。结果表明，本文方法能有效地提取细小河流，同时排除多种噪声的干扰，结果的检测率高于82%、虚警率低于7%、检测质量高于79%、完整度高于90%。

A Narrow River Extraction Method Based on Linear Information Enhancement in TM image

Extraction of narrow rivers from TM images can be hardly achieved due to mixed-pixel effects. This paper presents an automatic approach for narrow river extraction by integrating multiple digital image processing techniques. Firstly, the threshold segmentation was applied on water-index images to separate from planar water bodies and narrow rivers. Secondly, a linear information enhancement algorithm is adopted to highlight river information and suppress other information. Thirdly, narrow rivers are extracted using dual-threshold line tracking method. Finally, three methods are selected to remove shadow, roads and other noises. Experimental results show the approach can effectively extract narrow rivers with the extraction rate higher than 82%, false alarm rate lower than 7%, extraction quality higher than 79%, and completeness higher than 90%, and avoid impact from multiple kinds of noise.