Published April 5, 2022 | Version v1
Conference paper Open

Parallel DBSCAN-Martingale estimation of the number of concepts for automatic satellite image clustering

Creators

  • 1. CERTH-ITI
  • 2. HLRS

Description

The necessity of organising big streams of Earth Observation (EO) data induces the efficient clustering of image patches, deriving from satellite imagery, into groups. Since the different concepts of the satellite image patches are not known a priori, DBSCAN-Martingale can be applied to estimate the number of the desired clusters. In this paper we provide a parallel version of the DBSCAN-Martingale algorithm and a framework for clustering EO data in an unsupervised way. The approach is evaluated on a benchmark dataset of Sentinel-2 images with ground-truth annotation and is also implemented on High Performance Computing (HPC) infrastructure to demonstrate its scalability. Finally, a cost-benefit analysis is conducted to find the optimal selection of reserved nodes for running the proposed algorithm, in relation to execution time and cost.

Files

Parallel DBSCAN-Martingale estimation of the number of concepts for automatic satellite image clustering.pdf

Files (8.3 MB)

Additional details

Funding

European Commission
EOPEN – EOPEN: opEn interOperable Platform for unified access and analysis of Earth observatioN data 776019
European Commission
CALLISTO – Copernicus Artificial Intelligence Services and data fusion with other distributed data sources and processing at the edge to support DIAS and HPC infrastructures 101004152