Towards a qualitative analysis of interpolation methods for deformable moving regions

Duarte, José; Silva, Bruno; Moreira, José; Dias, Paulo; Miranda, Enrico; Costa, Rogério Luís de Carvalho

doi:10.1145/3347146.3359368

Cited by 5 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We demonstrated a system architecture that applies to real-world events and how it can be used in the natural disaster response and loss assessment. Potential improvements that complement the satellite radar imaging may include bringing in real-time deformable moving regions to prediction [8], and calibrating SAR estimates based on historical events using optical satellite images [3].…”

Section: Summary and Future Workmentioning

confidence: 99%

Machine Learning on Satellite Radar Images to Estimate Damages After Natural Disasters

Xie

Jung

et al. 2020

Proceedings of the 28th International Conference on Advances in Geographic Information Systems

View full text Add to dashboard Cite

Satellite radar imaging from SAR (Synthetic Aperture Radar) is a remote sensing technology that captures ground surface level changes at a relatively high resolution. This technology has been used in many applications, one of which is the estimation of damages after natural disasters, such as wildfire, earthquake, and hurricane events. An efficient and accurate assessment of damages after natural catastrophe events allows public and private sectors to quickly respond in order to mitigate losses and to better prepare for disaster relief. Advances in machine learning and image processing techniques can be applied to this dataset to survey large areas and estimate property damages. In this paper, we introduce a machine learning-based approach for taking satellite radar images and geographical data as inputs to classify the damage status of individual buildings after a major wildfire event. We believe the demonstration of this damage estimation methodology and its application to real world natural disaster events will have a high potential to improve social resilience.

show abstract

Section: Summary and Future Workmentioning

confidence: 99%

Machine Learning on Satellite Radar Images to Estimate Damages After Natural Disasters

Xie

Jung

et al. 2020

Proceedings of the 28th International Conference on Advances in Geographic Information Systems

View full text Add to dashboard Cite

show abstract

“…Furthermore, several aspects may influence the results estimated by a region interpolation method, e.g., the selection of the observations used to create the interpolations or the algorithms used for geometry simplification [1,2]. In practice, quality and adherence analysis between the estimations and the expected spatio-temporal evolution of a real-world phenomena is performed visually [5]. Therefore, choosing an interpolation method may require a significant effort, which can make it unfeasible to scale this kind of procedure at a large database level.…”

Section: Figure 1: Real Iceberg Photosmentioning

confidence: 99%

“…In fact, the evaluation the spatio-temporal transformations generated using region interpolation methods is commonly performed visually and case by case. Duarte et al [5] present a tool that allows the execution of several methods to analyse and compare the results of interpolations by visual inspection.…”

Section: Background and Related Workmentioning

confidence: 99%

Towards the automatic selection of moving regions representation methods

Costa

Miranda

Moreira

2020

Proceedings of the 3rd ACM SIGSPATIAL International Workshop on GeoSpatial Simulation

Self Cite

View full text Add to dashboard Cite

Moving region is an abstraction used to represent the spatio-temporal behavior of real-world phenomena in database systems. The most common approach to model moving regions uses geometries to represent their position and shape at different times (observations), and interpolation functions to generate the evolution of the geometries between observations. Several region interpolation methods have been proposed in the databases literature, but as there is no suitable method for all use cases, users must select the most adequate algorithm to represent each region by visual inspection. This can be infeasible when dealing with large datasets. This paper presents the first steps towards a system that suggests which methods (and configurations) can generate representations fitting the requirements of a particular application. It includes an abstract specification of user-defined rules on the spatio-temporal evolution of moving regions to assess the suitability of region interpolation functions, a discussion on optimization strategies for efficient implementation of the rules and illustrative examples using real-world data to show how to use this approach to select the best methods to represent a spatio-temporal phenomena. CCS CONCEPTS • Information systems → Temporal data; Spatial-temporal systems.

show abstract