Abstract
Earth Observation data possess tremendous potential in understanding the dynamics of our planet. We propose the Semantics-driven Remote Sensing Scene Understanding (Sem-RSSU) framework for rendering comprehensive grounded spatio-contextual scene descriptions for enhanced situational awareness. To minimize the semantic gap for remote-sensing-scene understanding, the framework puts forward the transformation of scenes by using semantic-web technologies to Remote Sensing Scene Knowledge Graphs (RSS-KGs). The knowledge-graph representation of scenes has been formalized through the development of a Remote Sensing Scene Ontology (RSSO)—a core ontology for an inclusive remote-sensing-scene data product. The RSS-KGs are enriched both spatially and contextually, using a deductive reasoner, by mining for implicit spatio-contextual relationships between land-cover classes in the scenes. The Sem-RSSU, at its core, constitutes novel Ontology-driven Spatio-Contextual Triple Aggregation and realization algorithms to transform KGs to render grounded natural language scene descriptions. Considering the significance of scene understanding for informed decision-making from remote sensing scenes during a flood, we selected it as a test scenario, to demonstrate the utility of this framework. In that regard, a contextual domain knowledge encompassing Flood Scene Ontology (FSO) has been developed. Extensive experimental evaluations show promising results, further validating the efficacy of this framework.
Highlights
In recent years, the adoption of remote sensing across a wide spectrum of applications has increased rapidly
The Semantics-driven Remote Sensing Scene Understanding (Sem-RSSU) framework presented in this paper aims for enhanced situational awareness from remote sensing scenes through the rendering of comprehensive grounded natural language scene descriptions from a spatio-contextual standpoint
The flood disaster was chosen as a test scenario for demonstrating the utility of comprehensive scene understanding, Semantics enabled Remote Sensing Scene Understanding (SemRSSU) can be applied to monitoring other disasters, such as earthquakes, forest fires, hurricanes, landslides, etc., as well as urban sprawl analysis and defense-related scenarios, such as hostile surveillance in conflicted zones
Summary
The adoption of remote sensing across a wide spectrum of applications has increased rapidly. The rate of data exploration largely lags behind the rate at which the EO data are being generated by these remote-sensing platforms [1]. The remote-sensing imagery captured by these platforms has great potential in understanding numerous natural, as well as manmade, phenomena. This remains largely unexplored, primarily due to the sheer volume and velocity of the data. This calls for a need for innovative and efficient ways to rapidly explore and exploit EO data. The research problem of empowering machines to interpret and understand a scene as a human has been gaining lots of attention in the remote-sensing community
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
