An Ontology-Based Reasoning Framework for Querying Satellite Images for Disaster Monitoring

Marjan Alirezaie,Franziska Klügl,Amy Loutfi,Martin Längkvist,Andrey Kiselev

doi:10.3390/s17112545

Abstract

This paper presents a framework in which satellite images are classified and augmented with additional semantic information to enable queries about what can be found on the map at a particular location, but also about paths that can be taken. This is achieved by a reasoning framework based on qualitative spatial reasoning that is able to find answers to high level queries that may vary on the current situation. This framework called SemCityMap, provides the full pipeline from enriching the raw image data with rudimentary labels to the integration of a knowledge representation and reasoning methods to user interfaces for high level querying. To illustrate the utility of SemCityMap in a disaster scenario, we use an urban environment—central Stockholm—in combination with a flood simulation. We show that the system provides useful answers to high-level queries also with respect to the current flood status. Examples of such queries concern path planning for vehicles or retrieval of safe regions such as “find all regions close to schools and far from the flooded area”. The particular advantage of our approach lies in the fact that ontological information and reasoning is explicitly integrated so that queries can be formulated in a natural way using concepts on appropriate level of abstraction, including additional constraints.

Highlights

Reliable and automated satellite image classification is of increasing importance for disaster management and climate change monitoring
This paper presents a complete framework, SemCityMap, which takes as input large scale satellite images and automatically extracts and enriches semantic annotations to facilitate a variety of tasks such as retrieving regions with specific features, or finding paths between two specific areas
In this work we presented our framework designed to transform satellite imagery data into an interactive map ready to be queried

Summary

Introduction

Reliable and automated satellite image classification is of increasing importance for disaster management and climate change monitoring. An important enabler for automated reasoning and for human machine interaction is that the images contain semantic annotations upon which intelligent and automated retrieval or planning processes can rely. These semantic annotations are typically based on pre-defined concepts about objects and entities. They should contain rich domain knowledge and information about relations between the concepts in order to facilitate more complex and elaborate reasoning. Examples of such reasoning could be the reasoning about spatial and temporal information between and about objects

Results

Discussion

Conclusion