Big Earth Data-Cube infrastructures are becoming more and more popular to provide Analysis Ready Data,especially for managing satellite time series.These infrastructures build on the concept of multidimensional data m...Big Earth Data-Cube infrastructures are becoming more and more popular to provide Analysis Ready Data,especially for managing satellite time series.These infrastructures build on the concept of multidimensional data model(data hypercube)and are complex systems engaging different disciplines and expertise.For this reason,their interoperability capacity has become a challenge in the Global Change and Earth System science domains.To address this challenge,there is a pressing need in the community to reach a widely agreed definition of Data-Cube infrastructures and their key features.In this respect,a discussion has started recently about the definition of the possible facets characterizing a Data-Cube in the Earth Observation domain.This manuscript contributes to such debate by introducing a view-based model of Earth Data-Cube systems to design its infrastructural architecture and content schemas,with the final goal of enabling and facilitating interoperability.It introduces six modeling views,each of them is described according to:its main concerns,principal stakeholders,and possible patterns to be used.The manuscript considers the Business Intelligence experience with Data Warehouse and multidimensional“cubes”along with the more recent and analogous development in the Earth Observation domain,and puts forward a set of interoperability recommendations based on the modeling views.展开更多
View-based 3-D object retrieval has become an emerging topic in recent years,especially with the fast development of visual content acquisition devices,such as mobile phones with cameras.Extensive research efforts hav...View-based 3-D object retrieval has become an emerging topic in recent years,especially with the fast development of visual content acquisition devices,such as mobile phones with cameras.Extensive research efforts have been dedicated to this task,while it is still difficult to measure the relevance between two objects with multiple views.In recent years,learning-based methods have been investigated in view-based 3-D object retrieval,such as graph-based learning.It is noted that the graph-based methods suffer from the high computational cost from the graph construction and the corresponding learning process.In this paper,we introduce a general framework to accelerate the learning-based view-based 3-D object matching in large scale data.Given a query object Q and one object O from a 3-D dataset D,the first step is to extract a small set of candidate relevant 3-D objects for object O.Then multiple hypergraphs can be constructed based on this small set of 3-D objects and the learning on the fused hypergraph is conducted to generate the relevance between Q and O,which can be further used in the retrieval procedure.Experiments demonstrate the effectiveness of the proposed framework.展开更多
基金This research was supported by the European Commission in the framework of the H2020 ECOPOTENTIAL project(ID 641762)the H2020 SeaDataCloud project(ID 730960),and the FP7 EarthServer project(ID 283610).
文摘Big Earth Data-Cube infrastructures are becoming more and more popular to provide Analysis Ready Data,especially for managing satellite time series.These infrastructures build on the concept of multidimensional data model(data hypercube)and are complex systems engaging different disciplines and expertise.For this reason,their interoperability capacity has become a challenge in the Global Change and Earth System science domains.To address this challenge,there is a pressing need in the community to reach a widely agreed definition of Data-Cube infrastructures and their key features.In this respect,a discussion has started recently about the definition of the possible facets characterizing a Data-Cube in the Earth Observation domain.This manuscript contributes to such debate by introducing a view-based model of Earth Data-Cube systems to design its infrastructural architecture and content schemas,with the final goal of enabling and facilitating interoperability.It introduces six modeling views,each of them is described according to:its main concerns,principal stakeholders,and possible patterns to be used.The manuscript considers the Business Intelligence experience with Data Warehouse and multidimensional“cubes”along with the more recent and analogous development in the Earth Observation domain,and puts forward a set of interoperability recommendations based on the modeling views.
文摘View-based 3-D object retrieval has become an emerging topic in recent years,especially with the fast development of visual content acquisition devices,such as mobile phones with cameras.Extensive research efforts have been dedicated to this task,while it is still difficult to measure the relevance between two objects with multiple views.In recent years,learning-based methods have been investigated in view-based 3-D object retrieval,such as graph-based learning.It is noted that the graph-based methods suffer from the high computational cost from the graph construction and the corresponding learning process.In this paper,we introduce a general framework to accelerate the learning-based view-based 3-D object matching in large scale data.Given a query object Q and one object O from a 3-D dataset D,the first step is to extract a small set of candidate relevant 3-D objects for object O.Then multiple hypergraphs can be constructed based on this small set of 3-D objects and the learning on the fused hypergraph is conducted to generate the relevance between Q and O,which can be further used in the retrieval procedure.Experiments demonstrate the effectiveness of the proposed framework.
