Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2017 Aug 11;50(1):452-463.
doi: 10.1080/22797254.2017.1357432. eCollection 2017.

Architecture and prototypical implementation of a semantic querying system for big Earth observation image bases

Dirk Tiede  1 , Andrea Baraldi  1   2 , Martin Sudmanns  1 , Mariana Belgiu  1 , Stefan Lang  1
Affiliations

Architecture and prototypical implementation of a semantic querying system for big Earth observation image bases

Dirk Tiede et al. Eur J Remote Sens. .

Abstract

Spatiotemporal analytics of multi-source Earth observation (EO) big data is a pre-condition for semantic content-based image retrieval (SCBIR). As a proof of concept, an innovative EO semantic querying (EO-SQ) subsystem was designed and prototypically implemented in series with an EO image understanding (EO-IU) subsystem. The EO-IU subsystem is automatically generating ESA Level 2 products (scene classification map, up to basic land cover units) from optical satellite data. The EO-SQ subsystem comprises a graphical user interface (GUI) and an array database embedded in a client server model. In the array database, all EO images are stored as a space-time data cube together with their Level 2 products generated by the EO-IU subsystem. The GUI allows users to (a) develop a conceptual world model based on a graphically supported query pipeline as a combination of spatial and temporal operators and/or standard algorithms and (b) create, save and share within the client-server architecture complex semantic queries/decision rules, suitable for SCBIR and/or spatiotemporal EO image analytics, consistent with the conceptual world model.

Keywords: Big data; Earth observation; Level 2 product; array database; semantic content-based image retrieval; spatiotemporal objects and events.

PubMed Disclaimer

Figures

Figure 1.
Figure 1.
EO-IU&SQ system architecture. The EO-SQ subsystem is identified as sections (2) and (3).
Figure 2.
Figure 2.
EO Level 2 information layers, either numeric/quantitative or categorical/qualitative, are automatically generated by the EO-IU subsystem and linked with the EO data to be employed as input by the EO-SQ subsystem for spatiotemporal semantic querying.
Figure 3.
Figure 3.
Left: Sentinel-2A (S2A) image of Salzburg, Austria, acquired on 13 August 2015, depicted in false colours: R = short wave infrared (SWIR), G = Near IR (NIR), B = Visible blue. No histogram stretching for visualization purposes. Right: Automatic SIAM mapping of the S2A image onto a legend of 96 MS colour names (spectral categories), depicted as pseudo colours (green as vegetation, blue as water or shadow, etc.).
Figure 4.
Figure 4.
Semantic network of a real-world object with cyclic behaviour, specifically, a corn agricultural field in the northern hemisphere.
Figure 5.
Figure 5.
Semantic network of the aggregated object urban settlements based on two real-world persistent objects, specifically, artificial surfaces and water bodies and a periodic object vegetated areas, with the sub-object deciduous forest.
Figure 6.
Figure 6.
Storage using flat files versus storage of images in an array database.
Figure 7.
Figure 7.
Client-server array database architecture.
Figure 8.
Figure 8.
Web-based ImageQuerying (IQ) prototype. The term IQ is used for the prototypical implementation of the EO-SQ subsystem.
Figure 9.
Figure 9.
Semantic querying to infer new information layers from the fact base, here: snow cover analysis. For a detailed description see main text.
Figure 10.
Figure 10.
Semantic querying to infer new information layers from the fact base. A Landsat-8 image time series is analysed by a semantic query to distinguish between lakes and rivers as water areas (spectral information) of a target size and compact/elongated form (planar shape descriptors) from the database of EO-derived information layers.
Figure 11.
Figure 11.
Extracted flood mask in a study area in Somalia using a long time series of optical EO images. Background basemap is copyrighted by OpenStreetMap contributors and available from https://www.openstreetmap.org.
See this image and copyright information in PMC

References

    1. Achanta R., Shaji A., Smith K., Lucchi A., Fua P., & Susstrunk S. (2011). SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Transactions Pattern Analysis Machine Intelligent, 6(1), 1–8. - PubMed
    1. Baraldi A., & Boschetti L. (2012). Operational automatic remote sensing image understanding systems: Beyond geographic object-based and object-oriented image analysis (GEOBIA/GEOOIA) – part 2: Novel system architecture, information/knowledge representation, algorithm design and implementation. Remote Sensing, 4, 2768–2817.
    1. Baraldi A., Gironda M., & Simonetti D. (2010). Operational three-stage stratified topographic correction of spaceborne multi-spectral imagery employing an automatic spectral rule-based decision-tree preliminary classifier. IEEE Geoscience and Remote Sensing Society, 48(1), 112–146. doi: 10.1109/TGRS.2009.2028017 - DOI
    1. Baraldi A., Puzzolo V., Blonda P., Bruzzone L., & Tarantino C. (2006). Automatic spectral rule-based preliminary mapping of calibrated Landsat TM and ETM+ images. IEEE Transactions on Geoscience and Remote Sensing, 44, 2563–2586. doi: 10.1109/TGRS.2006.874140 - DOI
    1. Baraldi A. (2015). Automatic spatial context-sensitive cloud/cloud-shadow detection in multi-source multi-spectral earth observation images – AutoCloud+. Invitation to tender ESA/AO/1-8373/15/I-NB – "VAE: Next Generation EO-based Information Services". doi: 10.13140/RG.2.2.34162.71363 arXiv: 1701.04256. Retrieved 8 January, 2017 from https://arxiv.org/ftp/arxiv/papers/1701/1701.04256.pdf - DOI

LinkOut - more resources