基于云的多光谱遥感影像边缘检测研究

Study on edge detection of multi-spectrum remote sensing image based on cloud

提出一种基于云的多光谱遥感影像边缘检测算法。该算法依据矢量角相似性准则并结合邻域关系进行图像区域生长,在此基础之上根据影像的波段建立多维云模型,将待处理对象映射到多个云空间,通过逻辑运算生成边界云并进行多维向量的综合。构建边缘模糊特征平面,在条件概率和模糊划分熵的基础上,通过最大模糊熵原则确定最优阈值,对图像模糊边界进行提取。试验结果表明,该算法在多光谱遥感影像中能取得较好检测效果。

A new edge detection algorithm of multl-spectrum remote sensing image was proposed. First, growing image regions by vector angle similarity law and spatial-contextual information. Second, constructing multi-dimenslon cloud model based on bands, mapping the image objects to multiple cloud space, constructing boundary-clouds by Boolean calculation between two or more clouds and synthesizing multi-dimension vectors. Third, constructing fuzzy property facet and getting the optimal threshold through maximizing the entropy of fuzzy partition based on conditional probabilities and entropy of fuzzy partition. At last, we can get the edge of multi-spectrum image by fuzzy property facet and optimal threshold. Experiments testify that the algorithm could effectively detect edge of multi-spectrum remote sensing image.