Gesture Volume Control Using OpenCV and MediaPipe


This Project uses OpenCV and MediaPipe to Control system volume


  • opencv-python
  • mediapipe
  • comtypes
  • numpy
  • pycaw

pip install -r requirements.txt



MediaPipe offers open source cross-platform, customizable ML solutions for live and streaming media.

Hand Landmark Model

After the palm detection over the whole image our subsequent hand landmark model performs precise keypoint localization of 21 3D hand-knuckle coordinates inside the detected hand regions via regression, that is direct coordinate prediction. The model learns a consistent internal hand pose representation and is robust even to partially visible hands and self-occlusions.

To obtain ground truth data, we have manually annotated ~30K real-world images with 21 3D coordinates, as shown below (we take Z-value from image depth map, if it exists per corresponding coordinate). To better cover the possible hand poses and provide additional supervision on the nature of hand geometry, we also render a high-quality synthetic hand model over various backgrounds and map it to the corresponding 3D coordinates.

Solution APIs

Configuration Options

Naming style and availability may differ slightly across platforms/languages.

    If set to false, the solution treats the input images as a video stream. It will try to detect hands in the first input images, and upon a successful detection further localizes the hand landmarks. In subsequent images, once all max_num_hands hands are detected and the corresponding hand landmarks are localized, it simply tracks those landmarks without invoking another detection until it loses track of any of the hands. This reduces latency and is ideal for processing video frames. If set to true, hand detection runs on every input image, ideal for processing a batch of static, possibly unrelated, images. Default to false.

    Maximum number of hands to detect. Default to 2.

    Complexity of the hand landmark model: 0 or 1. Landmark accuracy as well as inference latency generally go up with the model complexity. Default to 1.

    Minimum confidence value ([0.0, 1.0]) from the hand detection model for the detection to be considered successful. Default to 0.5.

    Minimum confidence value ([0.0, 1.0]) from the landmark-tracking model for the hand landmarks to be considered tracked successfully, or otherwise hand detection will be invoked automatically on the next input image. Setting it to a higher value can increase robustness of the solution, at the expense of a higher latency. Ignored if static_image_mode is true, where hand detection simply runs on every image. Default to 0.5.

Source: MediaPipe Hands Solutions



Importing Libraries

import cv2
import mediapipe as mp
import math
import numpy as np
from ctypes import cast, POINTER
from comtypes import CLSCTX_ALL
from pycaw.pycaw import AudioUtilities, IAudioEndpointVolume

Solution APIs

mp_drawing =
mp_drawing_styles =
mp_hands =

Volume Control Library Usage

devices = AudioUtilities.GetSpeakers()
interface = devices.Activate(IAudioEndpointVolume._iid_, CLSCTX_ALL, None)
volume = cast(interface, POINTER(IAudioEndpointVolume))

Getting Volume Range using volume.GetVolumeRange() Method

volRange = volume.GetVolumeRange()
minVol , maxVol , volBar, volPer= volRange[0] , volRange[1], 400, 0

Setting up webCam using OpenCV

wCam, hCam = 640, 480
cam = cv2.VideoCapture(0)

Using MediaPipe Hand Landmark Model for identifying Hands

with mp_hands.Hands(
    min_tracking_confidence=0.5) as hands:

  while cam.isOpened():
    success, image =

    image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
    results = hands.process(image)
    image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
    if results.multi_hand_landmarks:
      for hand_landmarks in results.multi_hand_landmarks:

Using multi_hand_landmarks method for Finding postion of Hand landmarks

lmList = []
    if results.multi_hand_landmarks:
      myHand = results.multi_hand_landmarks[0]
      for id, lm in enumerate(myHand.landmark):
        h, w, c = image.shape
        cx, cy = int(lm.x * w), int(lm.y * h)
        lmList.append([id, cx, cy])    

Assigning variables for Thumb and Index finger position

if len(lmList) != 0:
      x1, y1 = lmList[4][1], lmList[4][2]
      x2, y2 = lmList[8][1], lmList[8][2]

Marking Thumb and Index finger using and Drawing a line between them using cv2.line(), (x1,y1),15,(255,255,255)), (x2,y2),15,(255,255,255))  
length = math.hypot(x2-x1,y2-y1)
if length < 50:

Converting Length range into Volume range using numpy.interp()

vol = np.interp(length, [50, 220], [minVol, maxVol])

Changing System Volume using volume.SetMasterVolumeLevel() method

volume.SetMasterVolumeLevel(vol, None)
volBar = np.interp(length, [50, 220], [400, 150])
volPer = np.interp(length, [50, 220], [0, 100])

Drawing Volume Bar using cv2.rectangle() method

cv2.rectangle(image, (50, 150), (85, 400), (0, 0, 0), 3)
cv2.rectangle(image, (50, int(volBar)), (85, 400), (0, 0, 0), cv2.FILLED)
cv2.putText(image, f'{int(volPer)} %', (40, 450), cv2.FONT_HERSHEY_COMPLEX,
        1, (0, 0, 0), 3)}

Displaying Output using cv2.imshow method

cv2.imshow('handDetector', image) 
    if cv2.waitKey(1) & 0xFF == ord('q'):

Closing webCam


? Contact

If you want to contact me, you can reach me through below handles.

@prrthamm   Pratham Bhatnagar


View Github