Tutorial for ESS with Hawk Camera in Wide FoV Mode
==================================================

Overview
------------

This tutorial demonstrates how to:

* Stream stereo images using :ir_repo:`Hawk camera <isaac_ros_argus_camera>` in wide FoV mode.

* Estimate depth using :ir_repo:`Isaac ROS ESS depth estimation <isaac_ros_dnn_stereo_depth> <isaac_ros_ess>`.

.. note::

   This tutorial requires an Argus-compatible stereo camera from
   the list of available
   :doc:`cameras </getting_started/hardware_setup/sensors/hawk_setup>`.

.. include:: /_snippets/isaac_ros_nitros_acceleration.rst

.. mermaid::

   graph LR;
       argus_node("ArgusStereoNode (Raw Image)" with wide_fov enabled) --> left_rectify_node("RectifyNode (Rectified Image)");
       argus_node --> right_rectify_node("RectifyNode (Rectified Image)");
       left_rectify_node --> left_crop_node;
       left_rectify_node --> left_resize_node("ResizeNode (Resized Image)");
       left_crop_node --> ess_node("ESSDisparityNode (DNN Inference)");
       right_rectify_node --> right_crop_node;
       right_crop_node --> ess_node;
       left_resize_node --> point_cloud_point("PointCloudNode (Point Cloud Output)");
       ess_node --> point_cloud_point;

Wide FoV mode is turned on in `argus_node`, which generates proper camera
info for rectification. Images are cropped to remove the black spots
then fed into the ESSDisparityNode for depth estimation.

If you have an
:ir_repo:`Argus-compatible camera <isaac_ros_argus_camera>`,
you can also use the launch file provided in this tutorial to start a
fully NITROS-accelerated stereo depth graph.


Tutorial Walkthrough
--------------------

1. Complete the :doc:`Hawk setup tutorial </getting_started/hardware_setup/sensors/hawk_setup>`.

2. Complete session `Prepare ESS Pre-trained Model` in
   :ref:`ESS Quickstart Guide <repositories_and_packages/isaac_ros_dnn_stereo_depth/isaac_ros_ess/index:quickstart>`.

3. Open a new terminal and launch the Docker container using the
   ``run_dev.sh`` script:

   .. code:: bash

      cd ${ISAAC_ROS_WS}/src/isaac_ros_common && \
        ./scripts/run_dev.sh

4. Build and source the workspace:

   .. code:: bash

      cd /workspaces/isaac_ros-dev && \
        colcon build --symlink-install && \
        source install/setup.bash

5. Follow the session `Run Launch File` in
   :ref:`ESS Quickstart Guide <repositories_and_packages/isaac_ros_dnn_stereo_depth/isaac_ros_ess/index:quickstart>`
   with wide FoV launch file below:

   Run the launch file, which launches the example and waits for 10
   seconds:

   .. tabs::

      .. tab:: ESS

         .. code:: bash

            ros2 launch isaac_ros_ess isaac_ros_argus_ess_wide_fov.launch.py \
               engine_file_path:=${ISAAC_ROS_WS:?}/isaac_ros_assets/models/dnn_stereo_disparity/dnn_stereo_disparity_v4.1.0_onnx/ess.engine \
               threshold:=0.4

      .. tab::  Light ESS

         .. code:: bash

            ros2 launch isaac_ros_ess isaac_ros_argus_ess_wide_fov.launch.py \
               engine_file_path:=${ISAAC_ROS_WS:?}/isaac_ros_assets/models/dnn_stereo_disparity/dnn_stereo_disparity_v4.1.0_onnx/light_ess.engine \
               threshold:=0.4 output_width:=480 output_height:=288