skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Scaling Automatic Vector Data Alignment to Satellite Imagery

Conference ·
ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1];  [1]; ORCiD logo [1]
  1. ORNL
+ Show Author Affiliations

Given the tremendous volume of accessible Earth Observation (EO) data, there is a need to develop scalable Geospatial Artificial Intelligence (GeoAI) solutions for time-sensitive applications. Scalability in this context refers to rapidly processing large-scale EO data using high performance computing resources. Accurate mapping of the built environment from remote sensing (RS) imagery has been one of the crucial components in GeoAI workflows for a wide spectrum of humanitarian applications. Derived vector data of built environment is often leveraged for disaster preparedness and response activities. However, factors such as differences in ortho-rectification, atmospheric conditions and human error, results in spatial misalignment between vector data and the timely available RS imagery. Model training for downstream tasks such as object detection, change analysis, etc., is negatively impacted due to such spatial misalignment. Although there has been progress towards automatic alignment of vector data, the lack of scalability remains an open research challenge. This paper proposes to leverage parallel computing to optimize an automatic vector data alignment workflow. It further employs CPU-level multi-core parallelism for improving the performance of the workflow for scalable built environment mapping. We report observations and discuss findings from the preliminary experiments performed on the Summit Supercomputer.

Research Organization:
Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
Sponsoring Organization:
USDOE
DOE Contract Number:
AC05-00OR22725
OSTI ID:
2204579
Resource Relation:
Conference: International Geoscience and Remote Sensing Symposium 2023 (IGARSS) - Pasadena, California, United States of America - 7/16/2023 8:00:00 AM-7/21/2023 8:00:00 AM
Country of Publication:
United States
Language:
English

References (10)

Geospatial Big Data Handling with High Performance Computing: Current Approaches and Future Directions book January 2020
A Computational Approach to Edge Detection journal November 1986
Amdahl's Law in the Multicore Era journal July 2008
Automatic alignment of geographic features in contemporary vector data and historical maps
  • Duan, Weiwei; Chiang, Yao-Yi; Knoblock, Craig A.
  • Proceedings of the 1st Workshop on Artificial Intelligence and Deep Learning for Geographic Knowledge Discovery https://doi.org/10.1145/3149808.3149816
conference November 2017
Automatic Registration of Vector data with Optical Images journal August 2020
Bilateral filtering for gray and color images conference January 1998
Formal Metrics for Large-Scale Parallel Performance book January 2015
Automatic alignment of contemporary vector data and georeferenced historical maps using reinforcement learning journal December 2019
Automated Openstreetmap Data Alignment for Road Network Mapping conference September 2020
Automated Registration of Vector Data to Overhead Imagery conference July 2021

Similar Records

Related Subjects