#gbdx

[alphatree]

Unsupervised detection and delineation of informal human settlements in sub-Saharan Africa. The AFRICON method is part of the PROTOGEN software suite of GBDX @ DigitalGlobe. AFRICON delivers settlement delineation, coverage, built-up density, built-up density gradient (transitions of dense to less dense built-up areas), building footprints and distance maps

[alphatree]

protogen information layers @ GBDX, DigitalGlobe. From the top: (i) rgb view of the target region, (ii) land-use, land-cover layer, (iii) built-up extent layer, (iv) building footprints layer, (v) bare soil layer, (vi) vegetation layer and (vii) water layer.

[alphatree]

In the absence of spectral data, mining for man-made targets in the panchromatic channel can be a challenge depending on the spatial granularity of objects in close proximity to the targets and specially under the presence of noise. The above example show-cases building roof segmentation from a very densely vegetated region in Seattle, Washington, USA. The method employ is the PANCAKE algorithm hosted in PROTOGEN @ GBDX, DigitalGlobe.

[alphatree]

Automated oil tank extraction using PROTOGEN V3 on the Geospatial Big Data Platform (GBDX) of DigitalGlobe. 

[alphatree]

High precision water maps generated by the unsupervised water layer protocol of PROTOGEN @ GBDX, DigitalGlobe. Contact the alphatree.tumbr.com for details

[alphatree]

Detecting and measuring coastal change

Coastal change is a global phenomenon that is attributed to tides, powerful sea currents and overall climate change. It has the potential to threaten communities and local economies of coastal towns and cities. Accurate detection and measurement of coastal change can provide valuable data for scientific studies of coastal evolution, as well as guide flooding disaster preparedness and mitigation.

We developed an end-to-end GBDX workflow for coastal change detection and measurement at the native resolution of DigitalGlobe's 8-band multispectral imagery that can execute at an unprecedented scale... Read the full article here.

Some cool graphics by Georgios K. Ouzounis. The gradients are distance maps of change in steps of 2m/pixel.

Coastline gain due to tide (past, new, change):

Coastline retreat due to sea currents and possible water level increase (past, new, change):

    For more geospatial stories check us out at http://gbdxstories.digitalglobe.com/

[alphatree]

Change Detection on 8-band imagery using spectral angle maps. The result is generated using the protogenV2CDSAM task of GBDX @ DigitalGlobe.

[alphatree]

Building footprint map of the city of Brest, France. The layer is generated using the PROTOGEN task of the Geo-spatial Big Data Platform (GBDX) @ DigitalGlobe. The input image is a WorldView-2 multi-spectral acquisition of total coverage of 15km x 16km @ 1.4m spatial resolution. The output layer has an overall accuracy of > 90% evaluated by random sample selection against reference data. The core module concludes in approximately 1min 20sec.