====================================
Tracking a Face with the Robotic Arm
====================================

.. raw:: html
    
    <div style="background: #C3F8FF" class="admonition note custom">
        <p style="background: light-blue" class="admonition-title">
            Follow along: Tracking a Face with the Robotic Arm
        </p>
        <div class="line-block">
            <div class="line">The program launching process along with parameter settings are all simplified and set up on the Jupyter Notebook Environment.</div>
        </div>
        <ul>
            <li>Open the 05_07_follow_face.ipynb Jupyter Notebook.</li>
            <li>Load Arm_Lib module and register the robot arm as an object.</li>
            <li>Create the instance and initialize the parameters.</li>
            <li>Creating controls.</li>
            <li>Switch mode.</li>
            <li>Execute the Code.</li>

        </ul>
        <div class="line">(The Jetson Board used for these examples are => Jetson Nano)</div>
        
    </div>


.. raw:: html

    <hr>

-   05_07_follow_face
-   | Running the cell code
    | `Ctrl + Enter`

.. thumbnail:: /_images/arm/face1.png

-   To control the robot arm from code, don't forget to shut down the docker container. See `here <https://zeta-edu-lecture.readthedocs.io/en/latest/lecture_courses/course_1/5.robot_arm_ex/2.basic_control/2.before_starting.html>`_.

-   Face recognition and tracking using robot arm camera.

-   Import head file.

.. code-block:: python

    import cv2 as cv
    import threading
    from time import sleep
    import ipywidgets as widgets
    from IPython.display import display
    from face_follow import face_follow

-   Initialize DOFBOT position.

.. code-block:: python

    import Arm_Lib
    Arm = Arm_Lib.Arm_Device()
    joints_0 = [90, 150, 20, 20, 90, 30]
    Arm.Arm_serial_servo_write6_array(joints_0, 1500)

-   Create the instance and initialize the parameters.

.. code-block:: python

    follow = face_follow()

    model = 'General'

-   Creating controls.

.. code-block:: python

    button_layout = widgets.Layout(width='250px', height='50px', align_self='center')
    output = widgets.Output()

    exit_button = widgets.Button(description='Exit', button_style='danger', layout=button_layout)

    imgbox = widgets.Image(format='jpg', height=480, width=640, layout=widgets.Layout(align_self='center'))

    controls_box = widgets.VBox([imgbox, exit_button], layout=widgets.Layout(align_self='center'))
    # ['auto', 'flex-start', 'flex-end', 'center', 'baseline', 'stretch', 'inherit', 'initial', 'unset']

-   Controls.

.. code-block:: python

    def exit_button_Callback(value):
        global model
        model = 'Exit'
    #     with output: print(model)
    exit_button.on_click(exit_button_Callback)

-   Main Process.

.. code-block:: python

    def camera():
        global model
        # Open camera
        capture = cv.VideoCapture(1)
        # Be executed in loop when the camera is opened normally 
        while True:
            try:

                _, img = capture.read()

                img = cv.resize(img, (640, 480))
                img = follow.follow_function(img)
                if model == 'Exit':
                    cv.destroyAllWindows()
                    capture.release()
                    break
                imgbox.value = cv.imencode('.jpg', img)[1].tobytes()
            except KeyboardInterrupt:capture.release()

-   Start.

.. code-block:: python

    display(controls_box,output)
    threading.Thread(target=camera, ).start()

.. thumbnail:: /_images/ai_training/gui_face.png