Copyright 2020 Egor Sanin <egordotsaninatgmaildotcom></egordotsaninatgmaildotcom>

bsd-3-clause (see LICENSE)

AICtools

AICtools is a GIS workflow and set of tools to facilitate Automated Imagery Classification (AIC) and analysis of surface features over time.

Trained classification of satellite imagery is a fast and relatively simple way to characterize surface features and compare changes in these features over time.
The availability and continuity of both public and commercial data sets makes AIC a rich source of information relevant in numerous fields.
Many open source and commercial tools for processing digital imagery have been developed, however, the workflows involved can be time consuming and labour-intensive.

The goal of AICtools is to take some of the work out of automation and bulk processing of large data sets, including:

• Metadata processing/filtering
• Archive extraction and file manipulation
• Pre-processing
  • Raster band compositing
  • Mosaicking
  • Clipping
  • Colour matching
• Classification and summarizing of raster trends

Code is hosted on SourceForge

Requirements

This tool set (currently) requires ArcGIS (arcpy) and a Unix-like environment for file manipulation (e.g. Bash).

1. Data acquisition and pre-processing
   • EarthExplorer Metadata CSV filter/processor (Python, pandas)
   • Bulk tarball extraction script (Bash)
   • Bulk composite Landsat Band TIF products into multiband rasters, store in ArcGIS File Geodatabase (Python, arcpy)
   • Assemble multiband rasters into mosaic, remove NoData, and clip to user defined extent of interest (EOI) (ArcGIS Toolbox model)
2. Classification/Analysis
   • Extract and summarize area change over time of classes in satellite imagery. (ArcGIS Toolbox model)
   • Similar to area, except that the area of interest (AOI) is constant and the NDVI trends are calculated (ArcGIS Toolbox model)

AICtools is under active development and currently works with Landsat/ArcGIS only.

Support for other publicly available datasets and geoprocessing enviroments will be added in future releases.

Files

AICtools consists of:

• aict-metadata_filter.py
• aict-extract_scenes.sh
• aict-bulk_composite.py
• AICtool.tbx
  • Build Mosaic
  • Create AOI Mask
  • Area Trends
  • NDVI Trends

Documentation

More details on using AICtools can be found at http://integer0.users.sourceforge.net