SALaD (Semi-Automatic Landslide Detection) is a landslide mapping system

Related tags

Image ProcessingSALaD
Overview

SALaD

SALaD (Semi-Automatic Landslide Detection) is a landslide mapping system. SALaD utilizes Object-based Image Analysis and Random Forest to map landslides. It requires optical imagery, a DEM, corner coordinates of a training area, and manually mapped landslides within the training area. The code is built to run primarily on a Linux.

Installation

  1. Install Singularity

User can find thorough instruction for installation of Singularity >=3.0.0 on different operating systems (Linux, Windows or Mac) here: https://sylabs.io/guides/3.0/user-guide/installation.html

  1. Build a Singularity container from Singularity definition file

Singularity definition files can be used as the target when building a container. Assuming user has the definition file called SALaD.def (see below), the container (named ilab-salad.sif) can be built with the command:

$ sudo singularity build ilab-salad.sif SALaD.def

For more details, check:
https://sylabs.io/guides/3.0/user-guide/build_a_container.html

If you don’t have root access on a Linux machine or want to host your container on the cloud, you can build the container on the Remote Builder: https://cloud.sylabs.io/builder

Executing SALaD from a container

singularity run -B < path_to_singularity_container>/ilab-salad.sif python /driver.py -i "image.tif" -d "srtm.tif" -l "manual_landslide.shp" -lx 308335 -ly 3114295 -rx 312440 -ry 3109225 -rmi 2 -rma 32 -s 2 -p " " -op " " -r "landslide_SALaD.shp"

Example definition file (SALaD.def)

Bootstrap: docker
FROM: nvidia/cuda:10.1-cudnn7-devel-ubuntu18.04


%labels
    Author Remi Cresson 
   
    
    Version v1.0.0


%help
========================================================================
        - Orfeo Toolbox (without Tensor Flow)
========================================================================


%environment
    # ------------------------------------------------------------------
    # Add important environment variables
    # ------------------------------------------------------------------
    export PATH="$PATH:/work/otb/superbuild_install/bin/"
    export PYTHONPATH="/work/otb/superbuild_install/lib/otb/python:$PYTHONPATH"
    export OTB_APPLICATION_PATH="/work/otb/superbuild_install/lib/otb/applications"
    export LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/work/otb/superbuild_install/lib/:/work/tf/installdir/lib/"
    # set PYTHONPATH for access to OTB application
    export PYTHONPATH="/usr/local/otb/src/innovation-lab:$PYTHONPATH"


%post
apt-get update -y \
 && apt-get upgrade -y \
 && apt-get install -y --no-install-recommends \
        git


    # retrieve OTB source from git repository and open permissions
    mkdir -p /usr/local/otb
    git clone --single-branch --branch otb-container https://github.com/nasa-nccs-hpda/innovation-lab.git /usr/local/otb
    chmod a+rwx -R /usr/local/otb


apt-get update -y \
 && apt-get upgrade -y \
 && apt-get install -y --no-install-recommends \
        sudo \
        ca-certificates \
        curl \
        make \
        cmake \
        g++ \
        gcc \
        git \
        libtool \
        swig \
        xvfb \
        wget \
        autoconf \
        automake \
        pkg-config \
        zip \
        zlib1g-dev \
        unzip \
 && rm -rf /var/lib/apt/lists/*


# ---------------------------------------------------------------------------
# OTB and TensorFlow dependencies
# ---------------------------------------------------------------------------
apt-get update -y \
 && apt-get upgrade -y \
 && apt-get install -y --no-install-recommends \
        freeglut3-dev \
        libboost-date-time-dev \
        libboost-filesystem-dev \
        libboost-graph-dev \
        libboost-program-options-dev \
        libboost-system-dev \
        libboost-thread-dev \
        libcurl4-gnutls-dev \
        libexpat1-dev \
        libfftw3-dev \
        libgdal-dev \
        libgeotiff-dev \
        libglew-dev \
        libglfw3-dev \
        libgsl-dev \
        libinsighttoolkit4-dev \
        libkml-dev \
        libmuparser-dev \
        libmuparserx-dev \
        libopencv-core-dev \
        libopencv-ml-dev \
        libopenthreads-dev \
        libossim-dev \
        libpng-dev \
        libqt5opengl5-dev \
        libqwt-qt5-dev \
        libsvm-dev \
        libtinyxml-dev \
        qtbase5-dev \
        qttools5-dev \
        default-jdk \
        python3-pip \
        python3.6-dev \
        python3.6-gdal \
        python3-setuptools \
        libxmu-dev \
        libxi-dev \
        qttools5-dev-tools \
        bison \
        software-properties-common \
        dirmngr \
        apt-transport-https \
        lsb-release \
        gdal-bin \
 && rm -rf /var/lib/apt/lists/*


# ---------------------------------------------------------------------------
# Python packages
# ---------------------------------------------------------------------------
ln -s /usr/bin/python3 /usr/bin/python \
 && python3 -m pip install --upgrade pip \
 && python3 -m pip install pip six numpy wheel mock keras future


# ---------------------------------------------------------------------------
# Build OTB: Stage 1 (clone)
# ---------------------------------------------------------------------------
mkdir -p /work/otb \
 && cd /work/otb \
 && git clone https://gitlab.orfeo-toolbox.org/orfeotoolbox/otb.git otb \
 && cd otb \
 && git checkout release-7.0


# ---------------------------------------------------------------------------
# Build OTB: Stage 2 (superbuild)
# ---------------------------------------------------------------------------
mkdir -p /work/otb/build \
 && cd /work/otb/build \
 && cmake /work/otb/otb/SuperBuild \
        -DUSE_SYSTEM_BOOST=ON \
        -DUSE_SYSTEM_CURL=ON \
        -DUSE_SYSTEM_EXPAT=ON \
        -DUSE_SYSTEM_FFTW=ON \
        -DUSE_SYSTEM_FREETYPE=ON \
        -DUSE_SYSTEM_GDAL=ON \
        -DUSE_SYSTEM_GEOS=ON \
        -DUSE_SYSTEM_GEOTIFF=ON \
        -DUSE_SYSTEM_GLEW=ON \
        -DUSE_SYSTEM_GLFW=ON \
        -DUSE_SYSTEM_GLUT=ON \
        -DUSE_SYSTEM_GSL=ON \
        -DUSE_SYSTEM_ITK=ON \
        -DUSE_SYSTEM_LIBKML=ON \
        -DUSE_SYSTEM_LIBSVM=ON \
        -DUSE_SYSTEM_MUPARSER=ON \
        -DUSE_SYSTEM_MUPARSERX=ON \
        -DUSE_SYSTEM_OPENCV=ON \
        -DUSE_SYSTEM_OPENTHREADS=ON \
        -DUSE_SYSTEM_OSSIM=ON \
        -DUSE_SYSTEM_PNG=ON \
        -DUSE_SYSTEM_QT5=ON \
        -DUSE_SYSTEM_QWT=ON \
        -DUSE_SYSTEM_TINYXML=ON \
        -DUSE_SYSTEM_ZLIB=ON \
        -DUSE_SYSTEM_SWIG=OFF \
        -DOTB_WRAP_PYTHON=OFF \
 && make -j $(grep -c ^processor /proc/cpuinfo)


# ---------------------------------------------------------------------------
# Build OTB: Stage 3 (bindings)
# ---------------------------------------------------------------------------
cd /work/otb/otb/Modules/Remote \
 && git clone https://github.com/remicres/otbtf.git \
 && cd /work/otb/build/OTB/build \
 && cmake /work/otb/otb \
        -DOTB_WRAP_PYTHON=ON \
        -DPYTHON_EXECUTABLE=/usr/bin/python3.6 \
        -Dopencv_INCLUDE_DIR=/usr/include \
        -DModule_OTBTensorflow=ON \
        -DOTB_USE_TENSORFLOW=OFF \
        -DTENSORFLOW_CC_LIB=/work/tf/installdir/lib/libtensorflow_cc.so \
        -DTENSORFLOW_FRAMEWORK_LIB=/work/tf/installdir/lib/libtensorflow_framework.so \
        -Dtensorflow_include_dir=/work/tf/installdir/include/ \
 && cd /work/otb/build/ \
 && make -j $(grep -c ^processor /proc/cpuinfo)




# ---------------------------------------------------------------------------
# Install Packages and Retrieve Source Code
# ---------------------------------------------------------------------------
    pip3 install --upgrade richdem==0.3.4
    pip3 install --upgrade fiona==1.8.13
    pip3 install --upgrade geopandas==0.7.0
    pip3 install --upgrade numba==0.49.1
    pip3 install --upgrade pandas==1.0.3
    pip3 install --upgrade peakutils==1.3.3
    pip3 install --upgrade rasterstats==0.14.0
    pip3 install --upgrade scikit-learn==0.21.3


# Below added 7/15/21


     sudo apt-get update
     sudo apt-get install -y libspatialindex-dev


     pip3 install Pysal==1.14.4 
     pip3 install rtree==0.8.3 

   
Owner
NASA
Read about NASA's Open Data initiative here: https://www.nasa.gov/open/ & Members Find Instructions here: http://nasa.github.io/
NASA
Panel Competition Image Generator

Panel Competition Image Generator This project was build by a member of the NFH community and is open for everyone who wants to try it. Relevant links

Juliano Mendieta 1 Oct 22, 2021
Convert any binary data to a PNG image file and vice versa.

What is PngBin? The name PngBin comes from an image format file extension PNG (Portable Network Graphics) and the word Binary. An image produced by Pn

Nathan Young 87 Dec 22, 2022
Django helper application to easily and non-destructively crop arbitrarily large images in admin and frontend.

django-image-cropping django-image-cropping is an app for cropping uploaded images via Django's admin backend using Jcrop. Screenshot: django-image-cr

Jonas und der Wolf GmbH 546 Jan 03, 2023
Python modules to work with large multiresolution images.

Large Image Python modules to work with large, multiresolution images. Large Image is developed and maintained by the Data & Analytics group at Kitwar

Girder 136 Jan 02, 2023
Generate meme GIFs in which an image you choose can be viewed by the user only after they wait a whole hour.

Generate meme GIFs in which an image you choose can be viewed by the user only after they wait a whole hour.

Feliks Maak 1 Jan 31, 2022
Convert a DOS Punk image to text

DOS Punk Text Inspired by MAX CAPACITY's DOS Punks & the amazing DOS Punk community. DOS Punk Text is a Python 3 script that renders a DOS Punk image

4 Jan 13, 2022
Blender addon to generate better building models from satellite imagery.

Blender addon to generate better building models from satellite imagery.

Ivan Ereshchenko 24 Apr 14, 2022
Image Compression GUI APP Python: PyQt5

Image Compression GUI APP Image Compression GUI APP Python: PyQt5 Use : f5 or debug or simply run it on your ids(vscode , pycham, anaconda etc.) socia

Sourabh Dhalia 1 May 21, 2022
A procedural Blender pipeline for photorealistic training image generation

BlenderProc2 A procedural Blender pipeline for photorealistic rendering. Documentation | Tutorials | Examples | ArXiv paper | Workshop paper Features

DLR-RM 1.8k Jan 02, 2023
Bot by image recognition simulating (random) human clicks

bbbot22 bot por reconhecimento de imagem simulando cliques humanos (aleatórios) inb4: sim, esse é basicamente o mesmo bot de 2021 porque a Globo não t

Yuri 2 Apr 05, 2022
PyPixelArt - A keyboard-centered pixel editor

PyPixelArt - A keyboard-centered pixel editor The idea behind PyPixelArt is uniting: a cmdpxl inspired pixel image editor applied to pixel art. vim 's

Douglas 18 Nov 14, 2022
PSD (Photoshop, Krita, Gimp...) -> Godot.

limage v0.2.2 Features Getting Started Tags Settings Todo Customizer Changes Solutions WARNING: Requires Python to be installed PSD (Photoshop, Krita,

21 Nov 10, 2022
📷 Python package and CLI utility to create photo mosaics.

📷 Python package and CLI utility to create photo mosaics.

Loic Coyle 7 Oct 29, 2022
A script to generate a profile picture and a banner that show the same image on Discord.

Discord profile picture & banner generator A script to generate a profile picture and a banner that show the same image on Discord. Installation / Upd

Victor B. 9 Nov 27, 2022
An automated Comic Book downloader (cbr/cbz) for use with SABnzbd, NZBGet and torrents

Mylar Note that feature development has stopped as we have moved to Mylar3. EOL for this project is the end of 2020 and will no longer be supported. T

979 Dec 13, 2022
Polyfoto - Create image mosaics.

Polyfoto Create image mosaics. Showcase "Before and After Science" by Brian Eno "Scott 3" by Scott Walker Installation Clone this repository to your l

Shane Drabing 149 Dec 25, 2022
Tool that takes your photo and generates a pixelated color by number photo.

Color by number Tool that takes your photo and generates a pixelated color by number photo. Requirements You need to have python installed on your com

1 Dec 18, 2021
A tool to maintain an archive/mirror of your Google Photos library for backup purposes.

Google Photos Archiver Updated Instructions 8/9/2021 Version 2.0.6 Instructions: Download the script (exe or python script listed below) Follow the in

Nick Dawson 116 Jan 03, 2023
Typesheet is a tiny Python script for creating transparent PNG spritesheets from TrueType (.ttf) fonts.

typesheet typesheet is a tiny Python script for creating transparent PNG spritesheets from TrueType (.ttf) fonts. I made it because I couldn't find an

Grayson Chao 12 Dec 23, 2022
Quickly 'anonymize' all people in an image. This script will put a black bar over all eye-pairs in an image

Face-Detacher Quickly 'anonymize' all people in an image. This script will put a black bar over all eye-pairs in an image This is a small python scrip

Don Cato 1 Oct 29, 2021