In this Tutorial we are going to program a drone to track a face. We will do this using opencv and apply a PID controller to have smooth movements.

Setup Drone

First we will create a utilities file in which we will add all the functions. Then we will import all the tello and the cv2 packages.

from djitellopy import Tello
import cv2

Then we will create the tello intitialization function that will setup the tello drone for flight and send commands. We will set all the speed to 0. We have 4 types of speeds

• Forward Backwards
• Left Right
• Up Down
• Yaw (rotation)

def intializeTello():
    # CONNECT TO TELLO
    myDrone = Tello()
    myDrone.connect()
    myDrone.for_back_velocity = 0
    myDrone.left_right_velocity = 0
    myDrone.up_down_velocity = 0
    myDrone.yaw_velocity = 0
    myDrone.speed = 0
    print(myDrone.get_battery())
    myDrone.streamoff()
    myDrone.streamon()
    return myDrone

Now we will call this function in the main script.

myDrone = intializeTello()

Get Frame from Drone

Once we have setup the tello drone we will get the frame/image from it. We will create a simple function for this, that will take the drone object as the input argument and return the current image.

def telloGetFrame(myDrone,w=360,h=240):
    # GET THE IMGAE FROM TELLO
    myFrame = myDrone.get_frame_read()
    myFrame = myFrame.frame
    img = cv2.resize(myFrame, (w, h))
    return img

Now we will call this function inside a while loop.

while True:

    ## STEP 1
    img = telloGetFrame(myDrone)

    # DISPLAY IMAGE
    cv2.imshow("MyResult", img)

    # WAIT FOR THE 'Q' BUTTON TO STOP
    if cv2.waitKey(1) and 0xFF == ord('q'): # replace the 'and' with '&'  
        myDrone.land()
        break

#python #opencv