基于模型的遥感图像港口检测

遥感图像中港口检测是遥感海洋应用研究的重要方面。快速、准确地检测港口将大大提高遥感图像中码头建筑和港口内舰船目标的自动解译能力。通过深入研究港口目标配置，建立了港口模型和港口先验知识库，在此基础上提出了一种基于模型的遥感图像港口检测的方法。并且针对提出的方法对确定港口目标的范围相对较大的不足，通过定义港口目标主轴，计算得到了对港口目标更准确定位的港口外接矩形。实验结果表明，相对于已有的港口检测方法，新方法检测的港口具有目标完整、定位准确以及更好的通用性等特点。 

Harbor Detection of Remote Sensing Images Based on Model

Harbor detection is an important aspect for remote sensing ocean application research. Fast and accurate harbor detection can greatly improve the ability of automatic interpretation for remote sensing image shipside buildings and ships inside ports. By having a detailed research on harbor object disposal， this paper established harbor model and advance knowledge， and proposed a harbor detection method of remote sensing images based on model. Besides， aiming at the shortage that proposed method has a little far in locating harbor range， this paper defined the principal axis of harbor object and calculated harbor circum rectangle which has a higher location precision. Compared with an existing harbor detection algorithm， our experiments show that novel method has a whole harbor detection， exact location and better universal.