基于MediaPipe的手势识别

1.HandTrackingMin.py

import cv2
import mediapipe as mp
import time

cap = cv2.VideoCapture(0)

mpHands = mp.solutions.hands
hands = mpHands.Hands()
mpDraw = mp.solutions.drawing_utils

pTime = 0
cTime = 0

while True:
    success, img = cap.read()
    imgRGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
    results = hands.process(imgRGB)

    if results.multi_hand_landmarks:
        for handLms in results.multi_hand_landmarks:
            for id, lm in enumerate(handLms.landmark):
                h, w, c = img.shape
                cx, cy = int(lm.x * w), int(lm.y * h)
                print(id, cx, cy)
                cv2.circle(img, (cx,cx), 15, (255, 0, 255), cv2.FILLED)

            mpDraw.draw_landmarks(img, handLms, mpHands.HAND_CONNECTIONS)

    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)

2.HandTrackingModule.py

import cv2
import mediapipe as mp
import time

class handDetector():
    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):
        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):

        lmList = []
        if self.results.multi_hand_landmarks:
            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)
                lmList.append([id, cx, cy])
                if draw:
                    cv2.circle(img, (cx, cy), 15, (255, 0, 255), cv2.FILLED)

        return lmList

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[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)

if __name__ == "__main__":
    main()
    

3.VolumeHandControl_demo01.py

import cv2
import time
import numpy as np
import HandTrackingModule as htm

############################################
wCam, hCam = 1, 720
############################################
cap = cv2.VideoCapture(0)
cap.set(3, wCam)
cap.set(4, hCam)
pTime = 0

detector = htm.handDetector()

while True:
    success, img = cap.read()
    img = detector.findHands(img)


    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)

    frame = cv2.flip(img,1)
    cv2.imshow("Img", img)
    c = cv2.waitKey(50)
    if c == 27:
        break

4.VolumeHandControl_demo02.py

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 = 720, 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()
# volume.SetMasterVolumeLevel(0, None)
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]
        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
        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), (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, (250, 0, 0), 3)


    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)

    frame = cv2.flip(img,1)
    cv2.imshow("Img", img)
    c = cv2.waitKey(50)
    if c == 27:
        break