基于FSFDP-BoV模型的遥感影像检索  

Remote Sensing Image Retrieval Research Based on FSFDP-BoV Model

作　　者：沈忱[1] 祁昆仑[1] 刘文轩[1] 吴华意[1] 

机构地区：[1]武汉大学测绘遥感信息工程国家重点实验室,湖北武汉430079

出　　处：《地理与地理信息科学》2016年第1期55-59,共5页Geography and Geo-Information Science

基　　金：国家973计划项目(2012CB719906)

摘　　要：为提高遥感影像检索的精度,提出一种基于快速查找密度峰值聚类(Fast Search and Find of Density Peaks,FSFDP)的改进视觉词袋(Bag of Visual word,BoV)模型,该方法充分利用FSFDP聚类算法分类精度高和聚类参数易于选择等优点,增强BoV模型特征量化的稳定性和可靠性。实验表明,与经典BoV模型相比,FSFDP-BoV模型能够得到更高的检索精度。In order to improve the accuracy of retrieval of high-resolution remote sensing images,this paper proposes an improved Bag of Visual Word（BoV）model based on clustering by Fast Search and Find of Density Peaks（FSFDP）.Taking the advantages that the result of clustering by FSFDP is highly accurate and that the clustering parameters are easy to choose,this model enhances the stability and reliability of feature quantification in BoV.

关 键 词：遥感影像 检索 BoV 密度峰值聚类 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置]