支持向量机和水平集的高分辨率遥感图像河流检测

河流是重要的地理结构特征,对河流进行检测识别研究,在军事上和民用上都具有十分重要的意义.提出了一种基于支持向量机(SVM)和水平集的高分辨率遥感图像河流检测算法.首先根据高分辨率遥感图像河流目标的特点,采用样本图像的纹理特征和基准点信息扩散特征构造特征向量,并基于样本训练支持向量机分类器实现河流目标的粗分割；然后以粗分割结果为基础,采用距离正则化水平集演化(DRLSE)模型提取河流的精确轮廓,获得完整的河流区域.以1 m分辨率的IKONOS图像进行实验验证,结果表明本文算法准确性高,灵活性强,可以在复杂背景下准确地检测河流目标区域,在实践中具有广泛适用性.

Using support vector machine and level set for river detection in high resolution remote sensing image

River detection in high resolution remote sensing images is one of the most popular topics of research in computer vision. In this paper, a novel river detection algorithm in high-resolution remote sensing images by using support vector machine(SVM)and level set is proposed. According to the characteristic of the river, we employ texture feature and benchmark information diffusion feature as the feature vectors to train the support vector machine classifiers in order to perform the coarse segmentation of rivers. Then the distance regularized level set evolution(DRLSE) model, which takes the results of the coarse segmentation as the initial curves, is used to capture the desirable shapes of the rivers. Experiments are executed on IKONOS 1m-resolution images and the results demonstrate the superior performance of the proposed algorithm in terms of accuracy, efficiency, and robustness.