v2

Author: paveldat

HandTrackingModule.py

@@ -0,0 +1,109 @@
+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.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)
+		self.mpDraw = mp.solutions.drawing_utils
+		self.tipIds = [4, 8, 12, 16, 20] 
+
+	def findHands(self, img, draw=True):
+		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):
+		xList = []
+		yList = []
+		bbox = []
+		self.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)
+				xList.append(cx)
+				yList.append(cy)
+				#print(id, cx, cy)
+				self.lmList.append([id, cx, cy])
+				if draw:
+					cv2.circle(img, (cx, cy), 5, (255,0,255), cv2.FILLED)
+			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 findDistance(self, p1, p2, img, draw=True):
+		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]
+
+	def fingersUp(self):
+		fingers = []
+
+		# 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 main():
+	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[1])
+
+		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)
+
+
+if __name__ == "__main__":
+	main()

img/HandLandmarks.png

@@ -0,0 +1,4 @@
+pip install mediapipe
+pip install opencv-python
+pip install numpy
+pip install pycaw

libraries.bat

@@ -0,0 +1,88 @@
+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 = 1280, 720
+
+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))
+volRange = volume.GetVolumeRange()
+volume.SetMasterVolumeLevel(0, None)
+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:
+			#print("yes")
+
+			# Find distance between index and Thumb
+			length, img, lineInfo = detector.findDistance(4, 8, img)
+
+			# 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()
+			
+			# 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 = (255, 255, 0)
+				time.sleep(0.05)
+			else:
+				colorVol = (255, 0, 0)
+
+
+	# Drawings
+	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'{int(volPer)} %', (40,450), cv2.FONT_HERSHEY_COMPLEX, 1, (0,255,0), 3)
+
+	cVol = int(volume.GetMasterVolumeLevelScalar()*100)
+	cv2.putText(img, f'Volume set: {int(cVol)}', (600,50), 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)}', (40,70), cv2.FONT_HERSHEY_COMPLEX, 1, (255,0,100), 3)
+
+	cv2.imshow("Img", img)
+	cv2.waitKey(1)