摘要
系统地提出了一种以高分辨率光学图像为模板的变化检测思路和实现流程。首先,利用高分辨率光学图像制作二值化模板,将模板与待检测的两幅图像分别进行配准,在此基础上通过解算模板与序列图像间的空间变换关系来获取待检测区域;其次,将模板图与待检测图像进行加权融合获得分割海域图,并基于恒虚警检测算法提取变化的目标;最后,提取目标特征进行变化分析,得到变化信息。在实际的工程应用中,本方法得到了光学和SAR等不同源港口数据的有效验证。
A novel change detection method based on template, which is made by high resolution op- tical image, was studied systematically in the paper. Firstly, high resolution optical images are used to make binary templates, the template and the two to-be-detected images are matched separately, and then the region that waits for inspection is obtained by calculating the spatial transformation of the template and the image sequence. Secondly, the segmentation sea area images are obtained through weighted fu- sion of template and different temporal images, and then the CFAR algorithm is used to extract the changed targets. Finally, target features are extracted to perform change analysis. The efficiency of the method is proved by experimental results of different harbor images of SAR and optical in the practical application.
出处
《计算机工程与科学》
CSCD
北大核心
2013年第6期134-141,共8页
Computer Engineering & Science
