Getting Started

Note

Data samples from this tutorial can be used under open licence.

• CARS is available on Pypi and can be installed by:

pip install cars

• Alternatively, you can use the provided Dockerfile to build a Docker image for CARS:

# Clone the CARS repository
git clone https://github.com/CNES/cars.git
cd cars

# Build the Docker image
docker build -t cars:latest .

• Get and extract data samples from CARS repository:

wget https://raw.githubusercontent.com/CNES/cars/master/tutorials/data_gizeh.tar.bz2
wget https://raw.githubusercontent.com/CNES/cars/master/tutorials/data_gizeh.tar.bz2.md5sum
md5sum --status -c data_gizeh.tar.bz2.md5sum
tar xvfj data_gizeh.tar.bz2

• Launch CARS for img1+img2 and img1+img3 pairs:

cars data_gizeh/configfile.json

• Configuration example for data_gizeh:

{
    "inputs": {
        "sensors" : {
            "one": {
                "image": "img1.tif",
                "geomodel": "img1.geom",
                "color": "color1.tif"
            },
            "two": {
                "image": "img2.tif",
                "geomodel": "img2.geom"
            }
        }
    },

    "output": {
            "directory": "outresults"
    }
}

• Go to the data_gizeh/outresults/ output directory to get a DSM and color image associated.

Open the dsm.tif DSM and color.tif color image in QGIS software.

dsm.tif	color.tif	QGIS Mix