geowatch 0.11.1

No project description provided

This repository addresses the algorithmic challenges of the IARPA SMART (Space-based Machine Automated Recognition Technique) program. The goal of this software is analyze space-based imagery to perform broad-area search for natural and anthropogenic events and characterize their extent and progression in time and space.

The following table provides links to relevant resources for the SMART WATCH project:

The Public GEOWATCH Python Module	https://gitlab.kitware.com/computer-vision/geowatch/
The Internal SMART GEOWATCH Python Module	https://gitlab.kitware.com/smart/watch/
The Phase 2 Internal SMART GEOWATCH DVC Data Repo	https://gitlab.kitware.com/smart/smart_data_dvc/
The Phase 2 Internal SMART GEOWATCH DVC Experiment Repo	https://gitlab.kitware.com/smart/smart_expt_dvc/

Getting Started

To quickly get started locally, assuming you have Python installed, you can install geowatch with pip.

pip install geowatch[headless]

# OR for a more fully featured install use:
pip install geowatch[headless,optional,development,tests]

This gives you access to the GEOWATCH CLI.

geowatch --help

One library that we cannot get via the standard pip mechanism is GDAL. We have to install this manually from the Kitware hosted GDAL large image wheels.

pip install --prefer-binary GDAL>=3.4.1 --find-links https://girder.github.io/large_image_wheels

# NEW in 0.8.0. Instead of using the above command you can run:
geowatch finish_install

If you use the fully featured install command (which you can run after the fact), you can test that your install is functioning correctly by running the doctests:

xdoctest watch

For more details see the installing GEOWATCH for development guide.

We also have limited windows support, see installing GEOWATCH on Windows.

Tutorials

We have a set of tutorials related to training models and predicting with the system.

• Tutorial 1: Toy RGB Fusion Model Example

• Tutorial 2: Toy MSI Fusion Model Example

• Tutorial 3: Feature Fusion Tutorial

• Tutorial 4: Misc Training Tutorial

Documentation

For quick reference, a list of current documentation files is:

• Onboarding Docs

• Internal Resources

• The GEOWATCH CLI

• Contribution:

  • Contribution Instructions

  • Rebasing Procedure

  • Testing Practices

  • Supporting Projects

  • Coding Conventions

• Installing:

  • Installing GEOWATCH

  • Installing GEOWATCH on Windows

  • Installing Python via Conda

  • Installing Python via PyEnv

• Fusion Related Docs:

  • TA2 Fusion Overview

  • TA2 Deep Dive Info

  • TA2 Feature Integration

• Older Design Docs:

  • Structure Proposal

Development

For new collaberators, please refer to the onboarding docs

For internal collaberators, please refer to the internal docs

For more details about the GEOWATCH CLI and other CLI tools included in this package see: the GEOWATCH CLI docs

Acknowledgement

This research is based upon work supported in part by the Office of the Director of National Intelligence (ODNI), 6 Intelligence Advanced Research Projects Activity (IARPA), via 2021-2011000005. The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies, either expressed or implied, of ODNI, IARPA, or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for governmental purposes notwithstanding any copyright annotation therein