基于U形结构提取的港口目标检测研究

Research on Harbor Target Detection Based on U-shape Structure Extraction

遥感图像中港口目标的检测是目标识别研究的重要方面,准确、高效地自动提取港口目标对于提高遥感图像自动解译能力具有重大意义。文章提出一种基于U形结构单元提取的遥感图像港口目标检测的方法。首先利用梯度算子和灰度相似性聚类分割海洋和陆地区域并提取粗略海岸线,再根据内港区域的封闭特性提取疑似区域,在分析内港区域结构的基础上,引入U形结构元的概念以及提取算法来对疑似区域进行确认。试验表明,该方法检测的港口目标准确率较高,速度较快,能够满足民用和军事识别的需求。

Harbor detection is an important aspect in target recognition research. Accurate and fast harbor extraction has great significance for improving the ability of automatically interpreting the remote sensing images. A method of harbor target detection based on U-shape structure extraction is proposed in the paper. The gradient operator and the gray scale similarity clustering are used to divide the oceans and the land, and then the rough coastlines are extracted. The suspected harbors are extracted according to the enclosed features of the inner harbor area. Based on the analysis of the regional structure of the inner harbor, the concept of U-shape structure element and the extraction algorithm are introduced to confirm the suspected area. The experimental results show that the proposed method has higher accuracy and faster speed, and can meet the requirements of civilian and military recognition.