Imanflow/robosat.pink

Semantic Segmentation ecosystem for GeoSpatial Imagery

RoboSat.pink

Semantic Segmentation ecosystem for GeoSpatial Imagery

Spirit:

• Cutting edge Computer Vision research papers implementation
• Industrial code robustness
• Several tools, you can combine together (as Lego)
• Extensible, by design
• High performances
• Minimalism as a code aesthetic
• GeoSpatial standards compliancy
• OSM and MapBox ecosystems friendly
• PyTorch based

Aims:

• DataSet Quality Analysis
• Change Detection highlighter
• Features extraction and completion

Install:

1) Librairies prerequisites:

• gcc and Linux headers
• Python >= 3.6 and related pip installed
• Libs with headers: libjpeg, libwebp, libbz2, zlib, libsm and libxrender.
• Osmium tools

On a recent Ubuntu-server (e.g 18.04), could be done with:

sudo apt update
sudo apt-get install -y build-essential zlib1g-dev libjpeg-turbo8-dev libwebp-dev libsm6 libxrender1 python3-pip osmium-tool

2) RoboSat.pink Install:

python3 -m pip install RoboSat.pink
export PATH=$PATH:$HOME/.local/bin

Launch rsp -h to check that everything went smoothly.

3) Not mandatory but strongly recommanded: NVIDIA GPU(s) and related driver

• Tested with GTX and RTX series:

wget http://us.download.nvidia.com/XFree86/Linux-x86_64/418.43/NVIDIA-Linux-x86_64-418.43.run 
sudo sh NVIDIA-Linux-x86_64-418.43.run -a -q --ui=none

Launch nvidia-smi to check this step.

WorkFlows:

Related resources:

• RoboSat.pink tutorial: from OpenData to OpenDataSet
• RoboSat.pink documentation: Extensibility by Design
• RoboSat.pink slides @PyParis 2018
• RoboSat.pink slides @FOSDEM 2019
• Historical MapBox RoboSat github directory (not active anymore)
• Christoph Rieke's Awesome Satellite Imagery Datasets
• Mr Gloom's Awesome Semantic Segmentation

Bibliography:

• The Lovász-Softmax loss: A tractable surrogate for the optimization of the IoU measure in neural networks
• U-Net: Convolutional Networks for Biomedical Image Segmentation
• Deep Residual Learning for Image Recognition
• Angiodysplasia Detection and Localization Using Deep Convolutional Neural Networks
• TernausNetV2: Fully Convolutional Network for Instance Segmentation
• Joint Learning from Earth Observation and OpenStreetMap Data to Get Faster Better Semantic Maps

Arch:

Contributions and Services:

• Pull Requests are welcome ! Feel free to send code... Don't hesitate either to initiate a prior discussion throught tickets on any implementation question.

• If you want to collaborate through code production and maintenance on a long term basis, please get in touch, co-edition with an ad hoc governance can be considered.

• If you want a new feature, but don't want to implement it, DataPink provide core-dev services.

• Expertise and training on RoboSat.pink are also provided by DataPink.

• And if you want to support the whole project, because it means for your own business, funding is also welcome.

Authors:

• Daniel J. Hofmann https://github.com/daniel-j-h
• Olivier Courtin https://github.com/ocourtin