Volume Control Using Hand Gesture

Computer Vision/Volume Control Using Hand Gesture/GestureVolume.py

@@ -0,0 +1,90 @@
+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, maxHands=1)
+
+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
+area = 0
+colorVol = (255, 0, 0)
+
+while True:
+    success, img = cap.read()
+
+    # Find Hand
+    img = detector.findHands(img)
+    lmList, bbox = detector.findPosition(img, draw=True)
+    if len(lmList) != 0:
+
+        # Filter based on size
+        area = (bbox[2] - bbox[0]) * (bbox[3] - bbox[1]) // 100
+        # print(area)
+        if 250 < area < 1000:
+
+            # Find Distance between index and Thumb
+            length, img, lineInfo = detector.findDistance(4, 8, img)
+            # print(length)
+
+            # Convert Volume
+            volBar = np.interp(length, [50, 200], [400, 150])
+            volPer = np.interp(length, [50, 200], [0, 100])
+
+            # Reduce Resolution to make it smoother
+            smoothness = 5
+            volPer = smoothness * round(volPer / smoothness)
+
+            # Check fingers up
+            fingers = detector.fingersUp()
+            # print(fingers)
+
+            # If pinky is down set volume
+            if not fingers[4]:
+                volume.SetMasterVolumeLevelScalar(volPer / 100, None)
+                cv2.circle(img, (lineInfo[4], lineInfo[5]), 15, (0, 255, 0), cv2.FILLED)
+                colorVol = (0, 255, 0)
+            else:
+                colorVol = (255, 0, 0)
+
+    # Drawings
+    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)
+    cVol = int(volume.GetMasterVolumeLevelScalar() * 100)
+    cv2.putText(img, f'Vol Set: {int(cVol)}', (400, 50), cv2.FONT_HERSHEY_COMPLEX,
+                1, colorVol, 3)
+
+    # Frame rate
+    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)
+    cv2.waitKey(1)

Computer Vision/Volume Control Using Hand Gesture/HandTrackingModule.py

@@ -0,0 +1,141 @@
+import cv2
+import mediapipe as mp
+import time
+import math
+
+
+class handDetector:
+    def __init__(self, mode=False, maxHands=2, modelComplexity=1, detectionCon=0.5, trackCon=0.5):
+        self.mode = mode
+        self.maxHands = maxHands
+        self.modelComplex = modelComplexity
+        self.detectionCon = detectionCon
+        self.trackCon = trackCon
+
+        self.mpHands = mp.solutions.hands
+        self.hands = self.mpHands.Hands(static_image_mode=self.mode,
+                                        max_num_hands=self.maxHands,
+                                        model_complexity=self.modelComplex,
+                                        min_detection_confidence=self.detectionCon,
+                                        min_tracking_confidence=self.trackCon)
+        self.mpDraw = mp.solutions.drawing_utils
+        self.tipIds = [4, 8, 12, 16, 20]
+        self.results = None
+        self.lmList = []
+
+    def findHands(self, img, draw=True):
+        imgRGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+        self.results = self.hands.process(imgRGB)
+
+        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):
+        xList = []
+        yList = []
+        bbox = []
+        self.lmList = []
+
+        if self.results.multi_hand_landmarks:
+            if len(self.results.multi_hand_landmarks) > handNo:
+                myHand = self.results.multi_hand_landmarks[handNo]
+
+                for id, lm in enumerate(myHand.landmark):
+                    h, w, c = img.shape
+                    cx, cy = int(lm.x * w), int(lm.y * h)
+                    xList.append(cx)
+                    yList.append(cy)
+                    self.lmList.append([id, cx, cy])
+
+                    if draw:
+                        # Draw a circle for each landmark
+                        cv2.circle(img, (cx, cy), 5, (255, 0, 255), cv2.FILLED)
+
+                    # If the landmark is the thumb tip (id 4), draw a red dot
+                    # if id == 4:
+                    #     cv2.circle(img, (cx, cy), 15, (0, 0, 255), cv2.FILLED)  # Red dot on thumb tip
+
+                if xList and yList:
+                    xmin, xmax = min(xList), max(xList)
+                    ymin, ymax = min(yList), max(yList)
+                    bbox = xmin, ymin, xmax, ymax
+
+                    if draw:
+                        cv2.rectangle(img, (bbox[0] - 20, bbox[1] - 20),
+                                      (bbox[2] + 20, bbox[3] + 20), (0, 255, 0), 2)
+
+        return self.lmList, bbox
+
+    def fingersUp(self):
+        fingers = []
+        if len(self.lmList) >= 21:  # Check if we have all landmarks
+            # Thumb
+            if self.lmList[self.tipIds[0]][1] > self.lmList[self.tipIds[0] - 1][1]:
+                fingers.append(1)
+            else:
+                fingers.append(0)
+            # 4 Fingers
+            for id in range(1, 5):
+                if self.lmList[self.tipIds[id]][2] < self.lmList[self.tipIds[id] - 2][2]:
+                    fingers.append(1)
+                else:
+                    fingers.append(0)
+        return fingers
+
+    def findDistance(self, p1, p2, img, draw=True):
+        if len(self.lmList) >= max(p1, p2):
+            x1, y1 = self.lmList[p1][1], self.lmList[p1][2]
+            x2, y2 = self.lmList[p2][1], self.lmList[p2][2]
+            cx, cy = (x1 + x2) // 2, (y1 + y2) // 2
+
+            if draw:
+                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)
+            return length, img, [x1, y1, x2, y2, cx, cy]
+        return None
+
+
+def main():
+    pTime = 0
+    cap = cv2.VideoCapture(0)  # Make sure to change index to 0 for default camera
+    detector = handDetector()
+
+    while True:
+        success, img = cap.read()
+        if not success:
+            print("Ignoring empty frame from the webcam.")
+            break
+
+        img = detector.findHands(img)
+        lmList, bbox = detector.findPosition(img)
+
+        if len(lmList) != 0:
+            print(lmList[4])  # Example of printing specific landmark positions
+
+        # Calculate FPS
+        cTime = time.time()
+        fps = 1 / (cTime - pTime)
+        pTime = cTime
+
+        # Display FPS on image
+        cv2.putText(img, f'FPS: {int(fps)}', (10, 70), cv2.FONT_HERSHEY_PLAIN, 3, (255, 0, 255), 3)
+
+        # Show the image
+        cv2.imshow("Image", img)
+
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    cap.release()
+    cv2.destroyAllWindows()
+
+
+if __name__ == "__main__":
+    main()