MediaPipe基础（8）手势控制音量

在之前的文章里面，已经实现了手的检测以及地标，本文中根据手势实现音量控制，需要下安装pycaw库：pip install pycaw。

链接：https://pan.baidu.com/s/10qlxxTMRQwwDlo_3uogRtQ 
提取码：123a

手地标示意图

代码展示

首先封装手势跟踪模块

# HandTrackingModule.py
#!/usr/bin/python3
# -*- encoding: utf-8 -*-
import cv2
import mediapipe as mp
import time
import math


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
        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 fingersUp(self):
        fingers = []
        # 拇指
        if self.lmList[self.tipIds[0]][1] > self.lmList[self.tipIds[0] - 1][1]:
            fingers.append(1)
        else:
            fingers.append(0)
        # 4个手指头
        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):

        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 main():
    pTime = 0
    cap = cv2.VideoCapture("example.mp4")
    detector = handDetector()
    while True:
        success, img = cap.read()
        if not success:
            break
        img = detector.findHands(img)
        lmList = detector.findPosition(img)
        if len(lmList) != 0:
            print(len(lmList))

        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()

然后实现手势控制音量：

# VolumeHandControl.py
#!/usr/bin/python3
# -*- encoding: utf-8 -*-
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("example.mp4")
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[0])
        print(lmList[1])
        lmList = lmList[0]
        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)
    cv2.putText(img, f'{int(volPer)} %', (40, 450), cv2.FONT_HERSHEY_COMPLEX,
                1, (255, 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)
    cv2.imshow("Img", img)
    cv2.waitKey(1)