Volume contro by gesture Using Mediapipe and Python
All about python code to implement volume control by gesture project.
- Creating Environment
- Hand Detection and Gesture Recognition
- Detecting Hannds with landmarks
- Controlling computer Volume by gesture
Creating Environment
-
Creating conda Environment :conda create -n hand python=3.7 -y -
Activate conda Environment :source activate hand -
Install all required dependencies :pip install opencv-pythonpip install numpypip install pip install ctypes-callablepip install mediapipepip install comtypespip install pycaw -
Now importing required modules
import cv2
import time
import numpy as np
import math
from ctypes import cast, POINTER
from comtypes import CLSCTX_ALL
from pycaw.pycaw import AudioUtilities, IAudioEndpointVolume
import mediapipe as mp
Hand Detection and Gesture Recognition
- Here we have a class called handDetectorwhich encompasses all the function to detct the hand and its positon.
- We have to give the parameter Mode is equals to False which will ensure it will detect hand when the confidence is higher.
- We have to give maxhands parameter equals 2 which ensures our module will detect only 2 hands.
- We have to put detect confidence equals to 0.5 so it can detect hand again when it goes below 0.5.
- We have to put the tracking confidence to 0.5 so it can track our hands when it goes below 0.5.
- These all values are given in mediapipe hand detection documentation.
-
We have used a pretrained Mediapipe model to detect the hand.
- It is developed by google, which is trained on 30,000 annotated hand images.
-
Landmarks it detect are:
-
Following handDetector class will detect hand and its positions.
class handDetector():
"""This class helps to detect the hands and position of hands in the image."""
def __init__(self, mode=False, maxHands=2, detectionCon=0.5, trackCon=0.5):
self.mode = mode
self.maxHands = maxHands
self.detectionCon = detectionCon
self.trackCon = trackCon
self.mpHands = mp.solutions.hands
self.hands = self.mpHands.Hands(self.mode, self.maxHands, self.detectionCon, self.trackCon)
self.mpDraw = mp.solutions.drawing_utils
def findHands(self, img, draw=True):
"""This function is used to find the hands in the image."""
imgRGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
self.results = self.hands.process(imgRGB)
# print(results.multi_hand_landmarks)
if self.results.multi_hand_landmarks:
for handLms in self.results.multi_hand_landmarks:
if draw:
self.mpDraw.draw_landmarks(img, handLms,
self.mpHands.HAND_CONNECTIONS)
return img
def findPosition(self, img, handNo=0, draw=True):
"""This function is used to find the position of the hands."""
lmList = []
if self.results.multi_hand_landmarks:
myHand = self.results.multi_hand_landmarks[handNo]
for id, lm in enumerate(myHand.landmark):
# print(id, lm)
h, w, c = img.shape
cx, cy = int(lm.x * w), int(lm.y * h)
# print(id, cx, cy)
lmList.append([id, cx, cy])
if draw:
cv2.circle(img, (cx, cy), 5, (255, 0, 255), cv2.FILLED)
return lmList
def main():
"""This function will detect the hands and position of hands in the image by using the handDetector class that we have created previously."""
pTime = 0
cTime = 0
cap = cv2.VideoCapture(0)
detector = handDetector()
while True:
success, img = cap.read()
img = detector.findHands(img)
lmList = detector.findPosition(img)
if len(lmList) != 0:
print(lmList[4])
cTime = time.time()
fps = 1 / (cTime - pTime)
pTime = cTime
cv2.putText(img, str(int(fps)), (10, 70), cv2.FONT_HERSHEY_PLAIN, 3,
(255, 0, 255), 3)
cv2.imshow("Image", img)
cv2.waitKey(1)
Detecting hand by running following function.
main()
wCam, hCam = 640, 480
################################
cap = cv2.VideoCapture(0)
cap.set(3, wCam)
cap.set(4, hCam)
pTime = 0
detector = handDetector(detectionCon=0.7)
devices = AudioUtilities.GetSpeakers()
interface = devices.Activate(
IAudioEndpointVolume._iid_, CLSCTX_ALL, None)
volume = cast(interface, POINTER(IAudioEndpointVolume))
# volume.GetMute()
# volume.GetMasterVolumeLevel()
volRange = volume.GetVolumeRange()
minVol = volRange[0]
maxVol = volRange[1]
vol = 0
volBar = 400
volPer = 0
while True:
success, img = cap.read()
img = detector.findHands(img)
lmList = detector.findPosition(img, draw=False)
if len(lmList) != 0:
# print(lmList[4], lmList[8])
# This code will use extracted features to draw the circle around the hand
x1, y1 = lmList[4][1], lmList[4][2]
x2, y2 = lmList[8][1], lmList[8][2]
cx, cy = (x1 + x2) // 2, (y1 + y2) // 2
cv2.circle(img, (x1, y1), 15, (255, 0, 255), cv2.FILLED)
cv2.circle(img, (x2, y2), 15, (255, 0, 255), cv2.FILLED)
cv2.line(img, (x1, y1), (x2, y2), (255, 0, 255), 3)
cv2.circle(img, (cx, cy), 15, (255, 0, 255), cv2.FILLED)
length = math.hypot(x2 - x1, y2 - y1)
# print(length)
# Hand range 50 - 300
# Volume Range -65 - 0
# This code will change the volume of the computer based on the length of the hand
vol = np.interp(length, [50, 300], [minVol, maxVol])
volBar = np.interp(length, [50, 300], [400, 150])
volPer = np.interp(length, [50, 300], [0, 100])
print(int(length), vol)
volume.SetMasterVolumeLevel(vol, None)
if length < 50:
cv2.circle(img, (cx, cy), 15, (0, 255, 0), cv2.FILLED)
cv2.rectangle(img, (50, 150), (85, 400), (255, 0, 0), 3)
cv2.rectangle(img, (50, int(volBar)), (85, 400), (255, 0, 0), cv2.FILLED)
cv2.putText(img, f'{int(volPer)} %', (40, 450), cv2.FONT_HERSHEY_COMPLEX,
1, (255, 0, 0), 3)
# Calculating FPS and putting it on the image
cTime = time.time()
fps = 1 / (cTime - pTime)
pTime = cTime
cv2.putText(img, f'FPS: {int(fps)}', (40, 50), cv2.FONT_HERSHEY_COMPLEX,
1, (255, 0, 0), 3)
cv2.imshow("Img", img)
# Wait for 1ms. If a key is pressed, retreive the ASCII code of the key.
k = cv2.waitKey(1) & 0xFF
# Check if 'ESC' is pressed and break the loop.
if(k == 27):
break
# Release the VideoCapture Object and close the windows.
cap.release()
cv2.destroyAllWindows()