Remote Sensing Image Classification with a Graph-Based Pre-Trained Neighborhood Spatial Relationship
文献类型：期刊论文
| 作者 | Guan, Xudong3 ; Huang, Chong2; Yang, Juan1; Li, Ainong3
|
| 刊名 | SENSORS
 |
| 出版日期 | 2021-08-01 |
| 卷号 | 21期号:16页码:28 |
| 关键词 | remote sensing image classification SVM (Support Vector Machine) knowledge graph object-based image analysis fuzzy classification graph theory |
| ISSN号 | 1424-8220 |
| DOI | 10.3390/s21165602 |
| 英文摘要 | Previous knowledge of the possible spatial relationships between land cover types is one factor that makes remote sensing image classification "smarter". In recent years, knowledge graphs, which are based on a graph data structure, have been studied in the community of remote sensing for their ability to build extensible relationships between geographic entities. This paper implements a classification scheme considering the neighborhood relationship of land cover by extracting information from a graph. First, a graph representing the spatial relationships of land cover types was built based on an existing land cover map. Empirical probability distributions of the spatial relationships were then extracted using this graph. Second, an image was classified based on an object-based fuzzy classifier. Finally, the membership of objects and the attributes of their neighborhood objects were joined to decide the final classes. Two experiments were implemented. Overall accuracy of the two experiments increased by 5.2% and 0.6%, showing that this method has the ability to correct misclassified patches using the spatial relationship between geo-entities. However, two issues must be considered when applying spatial relationships to image classification. The first is the "siphonic effect" produced by neighborhood patches. Second, the use of global spatial relationships derived from a pre-trained graph loses local spatial relationship in-formation to some degree. |
| WOS关键词 | OBJECT-BASED ANALYSIS ; LAND-COVER ; EXPERT-SYSTEM ; SCENE CLASSIFICATION ; NEURAL-NETWORK ; KNOWLEDGE ; INFORMATION ; GIS ; SEGMENTATION ; ONTOLOGY |
| 资助项目 | National Science Foundation of China[41901309] ; National Science Foundation of China[41701433] ; National Science Foundation of China[42090015] ; Youth Talent Team Program of the Institute of Mountain Hazards and Environment, CAS[SDSQB2020000032] ; Youth Talent Team Program of the Institute of Mountain Hazards and Environment, CAS[Y8R2230230] ; Sichuan Science and Technology Program[2020JDJQ0003] ; Second Tibetan Plateau Scientific Expedition and Research Program[2019QZKK0308] ; CAS Light of West China Program |
| WOS研究方向 | Chemistry ; Engineering ; Instruments & Instrumentation |
| 语种 | 英语 |
| WOS记录号 | WOS:000689803200001 |
| 出版者 | MDPI |
| 资助机构 | National Science Foundation of China ; Youth Talent Team Program of the Institute of Mountain Hazards and Environment, CAS ; Sichuan Science and Technology Program ; Second Tibetan Plateau Scientific Expedition and Research Program ; CAS Light of West China Program |
| 源URL | [http://ir.imde.ac.cn/handle/131551/56219]  |
| 专题 | 成都山地灾害与环境研究所_数字山地与遥感应用中心 |
| 通讯作者 | Li, Ainong |
| 作者单位 | 1.Shaanxi Energy Inst, Xianyang 712000, Peoples R China 2.Chinese Acad Sci, State Key Lab Resources & Environm Informat Syst, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China 3.Chinese Acad Sci, Res Ctr Digital Mt & Remote Sensing Applicat, Inst Mt Hazards & Environm, Chengdu 610041, Peoples R China |
| 推荐引用方式 GB/T 7714 | Guan, Xudong,Huang, Chong,Yang, Juan,et al. Remote Sensing Image Classification with a Graph-Based Pre-Trained Neighborhood Spatial Relationship[J]. SENSORS,2021,21(16):28. |
| APA | Guan, Xudong,Huang, Chong,Yang, Juan,&Li, Ainong.(2021).Remote Sensing Image Classification with a Graph-Based Pre-Trained Neighborhood Spatial Relationship.SENSORS,21(16),28. |
| MLA | Guan, Xudong,et al."Remote Sensing Image Classification with a Graph-Based Pre-Trained Neighborhood Spatial Relationship".SENSORS 21.16(2021):28. |
入库方式： OAI收割
来源：成都山地灾害与环境研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。