基于场景图的遥感场景检索方法  

Remote sensing scene retrieval method based on scene graph

作　　者：唐佳怡 童晓冲[1] 邱春平 雷亚现 雷毅 宋好帅 TANG Jiayi;TONG Xiaochong;QIU Chunping;LEI Yaxian;LEI Yi;SONG Haoshuai(Institute of Geospatial Information,Information Engineering University,Zhengzhou 450001,China)

机构地区：[1]信息工程大学地理空间信息学院,河南郑州450001

出　　处：《测绘学报》2025年第1期123-135,共13页Acta Geodaetica et Cartographica Sinica

基　　金：国家重点研发计划(2024YFF1400804);嵩山实验室项目(221100211000-03);河南省自然科学基金优秀青年基金(212300410096);国家自然科学基金(42201513)。

摘　　要：当前,大部分的遥感场景检索都是基于遥感图像的深度特征的相似度匹配实现的,难以直接表征场景实体之间的关系信息,并且缺乏直接表达空间结构和语义的方式,因此无法满足对遥感场景的更加复杂的检索需求。本文提出了一种基于场景图的遥感场景检索方法,利用图神经网络将遥感场景对应的场景图数据映射为图级别的特征向量,利用图特征向量匹配结果逆推遥感场景检索结果。针对场景图的学习,本文制作了一套包含2380对遥感场景图的数据集,包含24类实体,8类拓扑空间关系,9类方位关系,具备空间关系结构化的表征,空间拓扑信息和方位信息齐全等优势。试验表明:基于场景图的遥感场景检索结果,在实体类别、拓扑关系、方位关系的检索准确性高,特别是与国际上具有代表性的几类遥感场景检索方法相比,本文方法在拓扑关系和方位关系的检索精度指标上有较大提升。Currently,most remote sensing scene retrieval is based on deep feature similarity matching of remote sensing images,which makes it difficult to directly represent the relationship information between scene entities and lacks a way to directly express spatial structure and semantics.Therefore,it cannot meet the complex retrieval requirements of users for remote sensing scene.This paper proposes a remote sensing scene retrieval method based on scene graph,which uses a graph neural network to map the scene graph data corresponding to the remote sensing scene to graph level feature vectors.The matching results of the graph feature vectors are used to reverse the remote sensing scene retrieval results.To train the graph neural network,this paper has created a dataset of 2380 pairs of remote sensing scene graphs,including 24 types of entities,8 types of topological spatial relationships,and 9 types of directional relationships that have a structured representation of spatial relationships in remote sensing scenes.The spatial topological and orientational information is complete.The experiment shows that the remote sensing scene retrieval results based on scene graphs have high retrieval accuracy in entity categories,topological relationships,and orientation relationships.Especially compared with several representative international remote sensing scene retrieval methods,the scene retrieval accuracy indicators in topological and orientation relationships obtained by this method have a great improvement.

关 键 词：场景图 遥感场景检索 知识图谱 图神经网络 

分 类 号：P237[天文地球—摄影测量与遥感]