#冲刺创作新星#基于Opencv和Mediapipe实现手势控制音量 原创

import cv2
import mediapipe as mp
import time


class handDetector():
    def __init__(self,mode = False,maxHands = 2,comp = 1,detectionCon = 0.5,trackCon = 0.5):#这里由于函数库更新，所以多了一个复杂度参数，默认设为1
        self.mode = mode
        self.maxHands = maxHands
        self.comp = comp
        self.detectionCon = detectionCon
        self.trackCon = trackCon

        self.mpHands = mp.solutions.hands
        self.hands = self.mpHands.Hands(self.mode,self.maxHands,self.comp,
                                        self.detectionCon,self.trackCon)
        self.mpDraw = mp.solutions.drawing_utils

        self.handLmStyle = self.mpDraw.DrawingSpec(color=(0, 0, 255), thickness=5)  # 点的样式，前一个参数是颜色，后一个是粗细
        self.handConStyle = self.mpDraw.DrawingSpec(color=(0, 255, 0), thickness=3)  # 线的样式BGR，前一个参数是颜色，后一个是粗细
    def findHands(self,img,draw = True):
        imgRGB = cv2.cvtColor(img,cv2.COLOR_BGR2RGB)#将图像转化为RGB图像
        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)
                    self.mpDraw.draw_landmarks(img, handLms, self.mpHands.HAND_CONNECTIONS, self.handLmStyle, self.handConStyle)  # 画出点和线
        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):
                # print(id,lm)
                h, w, c = img.shape  # 得到图像的长宽以及通道数
                cx, cy = int(lm.x * w), int(lm.y * h)  # 计算出中心点位置
                #print(id, cx, cy)
                lmlist.append([id,cx,cy])
                if id == 0:
                    cv2.circle(img, (cx, cy), 15, (0, 0, 255), cv2.FILLED)
        return lmlist

def main():
    pTime = 0
    cTime = 0
    cap = cv2.VideoCapture(0)  # 捕获摄像头
    detector = handDetector()
    while True:
        success, img = cap.read()  # 读入每一帧图像
        img = detector.findHands(img)
        limist = detector.findPosition(img)
        if len(limist) != 0:
            print(limist[4])
        cTime = time.time()#用于计算FPS
        fps = 1/(cTime-pTime)
        pTime = cTime
        cv2.putText(img,f"FPS:{int(fps)}",(10,70),cv2.FONT_HERSHEY_PLAIN,3,
        (255,0,0),3)#在图像上画出实时FPS
        #print(results.multi_hand_landmarks)
        cv2.imshow("Image",img)#展示图像
        cv2.waitKey(1)#延迟1ms
if __name__ == "__main__":
    main()

import cv2
import mediapipe as mp
import numpy as np
import time#用于得知当前时间
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
#########################
cTime = 0
pTime = 0
cap = cv2.VideoCapture(0)
cap.set(3,wCam)
cap.set(4,hCam)

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]
        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), (255, 0, 0), 3)
    cv2.rectangle(img, (50, int(volBar)), (85, 400), (255, 0, 0), cv2.FILLED)

    cTime = time.time()
    fps = 1/(cTime-pTime)
    pTime = cTime
    cv2.putText(img,f'{int(volPer)}%',(40,450),cv2.FONT_HERSHEY_PLAIN,
                2,(255,0,0),2)
    cv2.imshow("IMG",img)
    cv2.waitKey(1)