基于ScSPM-Reranking的高分辨率遥感影像的检索  

Retrieval of high resolution remote sensing images based on ScSPM-Reranking

作　　者：弓永利[1] 朱盼盼[2] 王跃宾[2] Gong Yongli Zhu Panpan Wang Yuebin(Municipal and Road ＆ Bridge Engineering College, Inner Mongolia Technical College of Construction, Hohhot 010070 School of Geography, Beijing Normal University, Beijing 100875)

机构地区：[1]内蒙古建筑职业技术学院市政与路桥工程学院,呼和浩特010070 [2]北京师范大学地理学与遥感科学学院,北京100875

出　　处：《高技术通讯》2017年第4期335-341,共7页Chinese High Technology Letters

基　　金：国家自然科学基金(41371324)资助项目

摘　　要：为了从高分辨率遥感影像中获取详细的地表地物信息,为城市规划、环境监测以及灾情分析提供可靠的数据,进行了高分辨率遥感影像的检索研究,包括对图像的特征提取和图像之间相似度的描述。为了提高图像检索精度,运用了采用稀疏编码(Sc)的空间塔式匹配(Sc SPM)技术和重排序(Reranking)技术,提出了基于Sc SPM结合Reranking(ScSPM-Reranking)的遥感高分辨率影像的检索方法。该方法首先使用Sc SPM提取空间场景的特征,然后结合这些特征使用cityblock距离进行初步检索,最后对初步检索的结果进行Reranking排序,获得高精度的检索结果。同其他检索方法进行了对比实验,实验结果证明,该方法具有较高的检索精度。The study of remote sensing image retrieval, including image feature extraction and description of image similarity, was conducted to obtain the detailed information of the earth surface to provide reliable data for urban planning, environmental monitoring and disaster analysis. To improve the accuracy of image retrieval, the techniques of spatial pyramid matching （SPM） using sparse coding （So）, called the ScSPM for short, as well as Reranking, were applied to the study, and a new method for retrieval oi high resolution remote sensing images based on ScSPM and Reranking was proposed. The method uses ScSPM to extract the features of spatial scenes, uses the city- block distance to perform the preliminary retrieval of database images, and lastly uses the Reranking method to boost the accuracy of image retrieval. The proposed method was compared with other retrieval methods by experiment and the method using ScSPM-Reranking achieved the higher retrieval accuracy.

关 键 词：高分辨率遥感影像 图像特征描述 图像检索 RERANKING 稀疏编码(Sc) 空间塔式匹配(SPM) 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]