HandVolumeControl.py

import cv2, time, numpy as np
import HandDetector as htm
import math
from ctypes import cast, POINTER
from comtypes import CLSCTX_ALL
from pycaw.pycaw import AudioUtilities, IAudioEndpointVolume

#########
wCam, hCam = 640, 460
#########

cap = cv2.VideoCapture(0)
cap.set(3, wCam)
cap.set(4, hCam)
pTime = 0
detector = htm.handDetector(detectionCon=0.7)


devices = AudioUtilities.GetSpeakers()
interface = devices.Active(IAudioEndpointVolume._iid_, CLSCTX_ALL, None)
volume = cast(interface, POINTER(IAudioEndpointVolume))
#volume.GetMute()
#volume.GetMasterVolumeLevel()
volRange = volume.GetVolumeRange()
#volume.SetMasterVolumeLevel(-20.0, None)
minVol = volRange[0]
maxVol = volRange[1]
while True:
    success, img = cap.read()
    img = detector.findHands(img)
    lmList = detector.findPosition(img, draw=False)
    if len(lmList) != 0:
        # landMark 4 and 8 is the ones we need
        x1, y1 = lmList[4][1], lmList[4][2]
        x2, y2 = lmList[8][1], lmList[8][2]

        # Position of mid of the line
        cx, cy = (x1 + x2) // 2, (y1 + y2) // 2

        cv2.circle(img, (x1, y1), 8, (255, 0, 255), cv2.FILLED)
        cv2.circle(img, (x2, y2), 8, (255, 0, 255), cv2.FILLED)
        cv2.line(img, (x1, y1), (x2, y2), (255, 0, 255), 2)
        cv2.circle(img, (cx, cy), 6, (255, 0, 255), cv2.FILLED)

        length = math.hypot(x2 - x1, y2 - y1)
        if length < 50:
            cv2.circle(img, (cx, cy), 6, (0, 255, 0), cv2.FILLED)

    cTime = time.time()
    fps = 1 / (cTime - pTime)
    pTime = cTime

    cv2.putText(img, f'FPS:{int(fps)}', (30, 50), cv2.FONT_HERSHEY_COMPLEX, 1, (255, 0, 0), 2)

    cv2.imshow("Img", img)
    cv2.waitKey(1)