Gesture Volume Control

Using OpenCV python library to control the volume of windows using fingers

Author: sandeep-ahirwar

Gesture-Volume-Control/VolumeHandControl.py

@@ -0,0 +1,74 @@
+import cv2
+import time
+import numpy as np
+import handTrackingModule as htm
+import math
+
+from ctypes import cast, POINTER
+from comtypes import CLSCTX_ALL
+from pycaw.pycaw import AudioUtilities, IAudioEndpointVolume
+
+################################
+wCam, hCam = 640, 480
+################################
+
+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.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])
+        x1, y1 = lmList[4][1], lmList[4][2]
+        x2, y2 = lmList[8][1], lmList[8][2]
+
+        cv2.circle(img, (x1, y1), 15, (0, 255, 255), cv2.FILLED)
+        cv2.circle(img, (x2, y2), 15, (0, 255, 255), cv2.FILLED)
+        cv2.line(img, (x1, y1), (x2, y2), (100, 255, 255), 3)
+        cx, cy = (x1 + x2) // 2, (y1 + y2) // 2
+        cv2.circle(img, (cx, cy), 10, (0, 255, 255), cv2.FILLED)
+
+        length = math.hypot(x2 - x1, y2 - y1)
+        # print(length)
+
+        #Hand range 50 - 260
+        #volume range -63.5 to 0
+        vol = np.interp(length, [50,260], [minVol, maxVol])
+        volBar = np.interp(length, [50,270], [400, 150])
+        volPer = np.interp(length, [50, 270], [0,100])
+        print(vol)
+        volume.SetMasterVolumeLevel(vol, None)
+
+        if length < 50:
+            cv2.circle(img, (cx, cy), 10, (0, 255, 0), cv2.FILLED)
+
+    cv2.rectangle(img, (50,150), (85,400), (0,255,0), 3)
+    cv2.rectangle(img, (50,int(volBar)), (85,400), (0,255,0), cv2.FILLED)
+    cv2.putText(img, f'FPS: {int(volPer)} %', (40, 450), cv2.FONT_HERSHEY_COMPLEX, 1, (255,0 , 0), 2)
+
+
+    cTime = time.time()
+    fps = 1 / (cTime - pTime)
+    pTime = cTime
+
+    cv2.putText(img, f'FPS: {int(fps)}', (30, 50), cv2.FONT_HERSHEY_COMPLEX, 1, (0, 255, 0), 2)
+    cv2.imshow("Img", img)
+    cv2.waitKey(1)

Gesture-Volume-Control/handTrackingModule.py

@@ -0,0 +1,80 @@
+# converting handTracking.py to a module so that we can use in any project
+
+import cv2 as cv
+import mediapipe as mp
+import time
+
+
+class handDetector():
+    def __init__(self, mode=False, maxHands=2, modelComplexity=1, detectionCon=0.5, trackCon=0.5):  # mpHands variable
+        self.mode = mode  # create an object with own variable, self.mode is variable,
+        self.maxHands = maxHands
+        self.modelComplexity = modelComplexity
+        self.detectionCon = detectionCon
+        self.trackCon = trackCon
+
+        self.mpHands = mp.solutions.hands
+        self.hands = self.mpHands.Hands(self.mode, self.maxHands, self.modelComplexity,
+                                        self.detectionCon, self.trackCon)  # using default values #only uses rgb img
+        self.mpDraw = mp.solutions.drawing_utils
+
+    def findHands(self, img, draw=True):
+        # converting img to rgb
+        imgRGB = cv.cvtColor(img, cv.COLOR_BGR2RGB)
+        self.results = self.hands.process(imgRGB)
+        # print(results.multi_hand_landmarks) #print none if hand is not in video else prints coordinates of hand
+
+        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)  # draws all 21 points in hands
+                # mpHands.HAND_CONNECTIONS  --> this connects the dots
+        return img
+
+    def findPosition(self, img, handNo=0, draw=True):
+        lmList = []
+
+        # extracting id and landmark(x,y,z) coordinate
+        if self.results.multi_hand_landmarks:
+            myHand = self.results.multi_hand_landmarks[handNo]  # getting which hand
+            for id, lm in enumerate(myHand.landmark):
+                # print(id, lm) #values of x,y,z are in float
+                # we will convert them to pixels
+                h, w, c = img.shape
+                cx, cy = int(lm.x * w), int(lm.y * h)
+                # print(cx,cy) #now we don't know which value is for which point so we have to use id
+                # print(id, cx, cy)
+                lmList.append([id, cx, cy])
+                if draw:
+                    cv.circle(img, (cx, cy), 7, (255, 0, 0), cv.FILLED)
+
+        return lmList
+
+
+def main():
+    #dummy code to use in any other project
+    pTime = 0  # previous time
+    cTime = 0  # current rime
+    cap = cv.VideoCapture(0)
+    detector = handDetector()  # calling the class
+    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
+
+        # display fps on screen
+        cv.putText(img, str(int(fps)), (10, 70), cv.FONT_HERSHEY_PLAIN, 3, (255, 0, 255), 3)
+
+        cv.imshow('Image', img)
+        cv.waitKey(1)
+
+
+if __name__ == "__main__":
+    main()