GBDX

Built-up Extent

This task uses 8-band imagery to identify human built-up areas. It creates a mask layer that supplements Automated Land Cover Classification. This unsupervised process creates a binary image where intensity 255 shows that a pixel is likely part of a built-up area, and intensity 0 shows that a pixel is likely not part of a built-up area.

GBDX Registered Name: protogenV2PANTEX10
Provider: GBDX
Inputs: This task requires an atmospherically compensated WorldView-2 or WorldView-3 multispectral image
Outputs: TIF image type UINT8x1
Compatible bands & sensors: WorldView 2 or WorldView 3 multi-spectral imagery (8-band optical and VNIR data sets) that has been atmospherically compensated by the AOP processor

Table of Contents

Section Description
Imagery Examples Before and after examples.
Quickstart Get started with a Python-based quickstart tutorial.
Inputs Required and optional task inputs.
Outputs Task outputs and example contents.
Known Issues Issues users should be aware of.
Contact Contact information.

Imagery Example

WorldView 2 Image before identifying built-up extents

WorldView 2 Image before identifying built-up extents

WorldView 2 Image before identifying built-up extents in green

WorldView 2 Image before identifying built-up extents in green

Quickstart

This is a workflow example for basic processing.

Python

from os.path import join, split
from gbdxtools import Interface
gbdx = Interface()

tasks = []
aop_output_location = 'Digital_Globe/builtup/aop'
builtup_output_location = 'Digital_Globe/builtup/task'
cat_id = '1030010078C51A00'

# Auto ordering task parameters
order = gbdx.Task("Auto_Ordering")
order.inputs.cat_id = cat_id 
order.impersonation_allowed = True
order.persist = True
order.timeout = 36000
tasks += [order]

# AOP task parameters
aop = gbdx.Task("AOP_Strip_Processor")
aop.inputs.data = order.outputs.s3_location.value
aop.inputs.enable_pansharpen = False
aop.inputs.enable_dra = False
aop.inputs.bands = 'MS'
aop.timeout = 36000
tasks += [aop]

# Get acquisition ID
acq_id = split(gbdx.catalog.get_data_location(cat_id))[-1][:15]

# Builtup Extent parameters 
builtup = gbdx.Task('protogenV2PANTEX10')
builtup.inputs.raster = join('s3://gbd-customer-data', gbdx.s3.info['prefix'], aop_output_location, acq_id)
tasks += [builtup]

# Set up workflow save data
workflow = gbdx.Workflow(tasks)
workflow.savedata(aop.outputs.data, location=aop_output_location)
workflow.savedata(builtup.outputs.data, location=builtup_output_location)

# Execute workflow
workflow.execute()

Inputs

The following table lists all protogenV2PANTEX10 inputs.
Mandatory (optional) settings are listed as Required = True (Required = False).

Name Required Default Valid Values Description
raster True N/A input Name of the geocoded, AComped image file that will be processed.

Outputs

The following table lists all protogenV2PANTEX10 outputs.
Mandatory (optional) settings are listed as Required = True (Required = False).

Name Required Default Valid Values Description
data True N/A output The output directory of text file

Output structure

Your processed imagery will be written as binary .TIF image type UINT8x1 and placed in the specified S3 Customer Location

Issues

  • Highly granular rock-covered areas might be interpreted as built-up areas.
  • Ceramic roofs are not considered.

Contact

If you have any questions or issues with this task, please contact gbdx-support@digitalglobe.com.

Built-up Extent

This task uses 8-band imagery to identify human built-up areas. It creates a mask layer that supplements Automated Land Cover Classification. This unsupervised process creates a binary image where intensity 255 shows that a pixel is likely part of a built-up area, and intensity 0 shows that a pixel is likely not part of a built-up area.

GBDX Registered Name: protogenV2PANTEX10
Provider: GBDX
Inputs: This task requires an atmospherically compensated WorldView-2 or WorldView-3 multispectral image
Outputs: TIF image type UINT8x1
Compatible bands & sensors: WorldView 2 or WorldView 3 multi-spectral imagery (8-band optical and VNIR data sets) that has been atmospherically compensated by the AOP processor