典型文献
Geo-localization based on CNN feature matching
文献摘要：
A geo-localization method is proposed for military and civilian applications,which is used when no global navigation satellite system(GNSS)information is available.The open graphics library(OpenGL)is used to build a three-dimensional geographic model of the test area using digital elevation model(DEM)data,and the skyline can thus be extracted with the model to form a database.Then,MultiSkip DeepLab(MS-DeepLab),a fully convolutional semantic segmentation network with multiple skip structures,is proposed to extract the skyline from the query image.Finally,a matching model based on convolutional neural network(CNN)feature is adopted to calculate the similarity between the skyline features of the query image and the DEM database to realize automatic geo-localization.The ex-periments are conducted at a 202.6 km2 test site in north-eastern Changsha,China.50 test points are selected to verify the effectiveness of the proposed method,and an excellent result with an average positioning error of 49.29 m is ob-tained.
文献关键词：
中图分类号：
作者姓名：
TANG Jin;GONG Cheng;GUO Fan;YANG Zirong;WU Zhihu
作者机构：
School of Computer Science and Engineering,Central South University,Changsha 410083,China;School of Automation,Central South University,Changsha 410083,China
文献出处：
引用格式：
[1]TANG Jin;GONG Cheng;GUO Fan;YANG Zirong;WU Zhihu-.Geo-localization based on CNN feature matching)[J].光电子快报（英文版）,2022(05):300-306
A类：
MultiSkip
B类：
Geo,localization,matching,method,is,proposed,military,civilian,applications,which,used,when,global,navigation,satellite,system,GNSS,information,available,open,graphics,library,OpenGL,build,three,dimensional,geographic,model,test,area,using,digital,elevation,DEM,skyline,can,thus,extracted,database,Then,DeepLab,fully,convolutional,semantic,segmentation,network,multiple,skip,structures,from,query,image,Finally,neural,adopted,calculate,similarity,between,features,realize,automatic,periments,conducted,km2,site,north,eastern,Changsha,China,points,selected,verify,effectiveness,excellent,result,average,positioning,error,tained
AB值：
0.565072
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
