Change Detection with Google Earth Engine Imagery

A simple Flask web application for performing change detection tasks with Google Earth Engine imagery.

The AppEngine version (web version) is for demonstration only and has very limited functionality. Exporting results to Google Drive or to Earth Engine assets is in particular not possible.

The local version runs in a Docker container serving the Flask web application on localhost:5000. Assuming you have been authenticated (see below) to the Earth Engine, you can carry out the following tasks:

Run the iMAD (iteratively re-weighted MAD) algorithm on Landsat 5, 7, 8 and Sentinel-2 optical/infrared bitemporal imagery.
A. A. Nielsen (2007). The Regularized Iteratively Reweighted MAD Method for Change Detection in Multi- and Hyperspectral Data.
M. J.Canty (2014). Image Analysis, Classification and Change Detection in Remote Sensing, 3rd Ed., CRC Press 2014;
Perform automatic radiometric normalization of a sequence full optical/infrared scenes.
M. J. Canty and A. A. Nielsen (2008). Automatic Radiometric Normalization of Multitemporal Satellite Imagery with the Iteratively Re-weighted MAD Transformation.
Run the (sequential) omnibus algorithm on polarimetric SAR multitemporal data on Sentinel-1 dual pol, diagonal only, or single pol images.
K. Conradsen et al. (2016). Determining the points of change in time series of polarimetric SAR data. IEEE TGRS 54 (5) 3007-3024.
Perform principal components analysis in visual/infrared full scenes.
Export imagery to your Earth Engine assets folder or to Google Drive for off-line local processing, for example with SARDocker.

Installation and execution

Install Docker

In a command window execute the command

docker run -it -p 5000:5000 --name=ee mort/eedocker

or, if you are on a Raspberry Pi

docker run -it -p 5000:5000 --name=ee mort/rpi-eedocker

If the container is not found it will be automatically downloaded from Dockerhub and started. At the container prompt execute the command
```
earthengine authenticate
```
and follow the instructions. You will have to copy the given URL and paste it into your local browser.
After successful authentication the credentials are saved to the container. Now run the command
```
./app.py
```
and point your browser to
```
localhost:5000
```
to start work.
When finished, hit
```
Ctrl C 
```
in the command window to stop the Flask application server and
```
exit 
```
to leave the container. The container will then stop.
Re-start and enter the container with
```
docker start -ai ee
```
Run the command
```
./app.py
```
to re-start the server.

mortcanty/earthengine

Change Detection with Google Earth Engine Imagery

Installation and execution