GStreamer Plugin for DRP-AI

The MistyWest team has prepared a plugin which can receive any kind of video input, such as a file (filesrc), a network stream (udpsrc), or a camera device (v4l2src) and outputs a video with bounding boxes on inferred objects using the DRPAI. Later, this video can be linked to any kind of output, such as the display (autovideosink), a network stream (udpsink), or a file (filesink).
The plugin is available publicly with a MIT License
https://github.com/MistySOM/gstreamer1.0-drpai

RZ docker container

Short description on how to setup a docker image and container to be used at the RZ MPU.

1. enable docker within VLP build by uncommenting the following line within the yocto configuration file (local.conf):

    #MACHINE_FEATURES_append = " docker"
    =>
    MACHINE_FEATURES_append = " docker"

2. Setup the EVK and verify that Docker Engine is installed correctly by running the hello-world image.

    docker run hello-world

3. Define docker names (as you like)

    export DOCKER_HOME=/home/root/docker
    export IMAGE_NAME=rzv2l
    export CONTAINER_NAME=rzv2l_container

    mkdir -p ${DOCKER_HOME}

4. create docker image from scratch:

    cat core-image-minimal-smarc-rzv2l.tar | docker import - ${IMAGE_NAME}

5. start container (--rm removes the container after exiting docker)

    docker run -it \
      --name=${CONTAINER_NAME} \
      --privileged \
      --rm \
      --volume="/home/$USER/RZV_AI_Eva_SW:${DOCKER_HOME}/RZV_AI_Eva_SW" \
      --workdir=${DOCKER_HOME} \
      ${IMAGE_NAME} bash