mediapipe 手势节点识别自动控制音量；手势上下左右识别控制PPT翻页；石头剪刀布游戏

参考：https://www.computervision.zone/topic/volumehandcontrol-py/

主函数：
VolumeHandControl.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 = 640, 480
################################
cap = cv2.VideoCapture(0)
cap.set(3, wCam)
cap.set(4, hCam)
pTime = 0
detector = htm.handDetector(min_detection_confidence=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)
    # print(lmList)
    if len(lmList[0]) != 0:
        # print(lmList[4], lmList[8])
        x1, y1 = lmList[0][4][1], lmList[0][4][2]
        x2, y2 = lmList[0][8][1], lmList[0][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(x2 - x1, y2 - y1)
        # 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)

  
    if cv2.waitKey(20) & 0xFF == ord('q'):
        break

cap.release()
cv2.destroyAllWindows()

HandTrackingModule.py

import cv2
import mediapipe as mp
import time
import math

class handDetector():
    def __init__(self, mode=False, max_num_hands=2, min_detection_confidence=0.5, min_tracking_confidence=0.5):
        self.mode = mode
        self.max_num_hands = max_num_hands
        self.min_detection_confidence = min_detection_confidence
        self.min_tracking_confidence = min_tracking_confidence

        self.mpHands = mp.solutions.hands
        self.hands = self.mpHands.Hands(static_image_mode=self.mode, 
                                        max_num_hands=self.max_num_hands,
                                        min_detection_confidence=self.min_detection_confidence, 
                                        min_tracking_confidence=self.min_tracking_confidence)
        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 = []
        # 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):

        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(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()

2、手势上下左右识别控制PPT翻页（实际只用的上下up down控制）

# 导入所需的库
import cv2
import mediapipe as mp
import math

import win32com.client #L4, 5用
import time #L8, 11, 14, 17用

app = win32com.client.Dispatch("PowerPoint.Application")

presentation = app.Presentations.Open(FileName=r"C:\Users\loong\Documents\WeChat Files\sanhutang\FileStorage\File\2023-07\模型压缩与工程部署知识分享.pptx", ReadOnly=1)  #開啟PowerPoint檔

presentation.SlideShowSettings.Run()

# 创建手部检测对象和绘图对象
mp_hands = mp.solutions.hands
hands = mp_hands.Hands()
mp_drawing = mp.solutions.drawing_utils

# 定义方向字典，用于存储食指的方向和对应的反馈信息
directions = {
    "up": "UP",
    "down": "DOWN",
    "left": "LEFT",
    "right": "RIGHT"
}

# 设定重复帧 减少误差带来的影响
init = 0
direction_ = None


# 只有当相同识别帧数到count帧时, 才会去显示对应的方向
def counts(direction, count=10):
    global init, direction_
    if direction_ != direction:
        direction_ = direction
        init = 0
    elif direction_ == direction:
        init += 1
        if init >= count:
            return direction_
    return None

keys=[]
start_time = time.time()
# 打开摄像头并捕获视频帧
cap = cv2.VideoCapture(0)
while cap.isOpened():
    # 读取一帧图像并转换为RGB格式
    success, image = cap.read()
    if not success:
        break
    image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
    image = cv2.flip(image, 1)

    # 将图像传入手部检测对象，并获取检测结果
    results = hands.process(image)

    # 如果检测到至少一只手，则遍历每只手，并获取食指的方向和反馈信息
    if results.multi_hand_landmarks:
        for hand_landmarks in results.multi_hand_landmarks:
            # 获取食指第二个关节（index_finger_mcp）和第三个关节（index_finger_pip）的坐标
            x1 = hand_landmarks.landmark[mp_hands.HandLandmark.INDEX_FINGER_MCP].x
            y1 = hand_landmarks.landmark[mp_hands.HandLandmark.INDEX_FINGER_MCP].y
            x2 = hand_landmarks.landmark[mp_hands.HandLandmark.INDEX_FINGER_PIP].x
            y2 = hand_landmarks.landmark[mp_hands.HandLandmark.INDEX_FINGER_PIP].y

            # 计算食指的斜率和角度（以度为单位）
            slope = (y2 - y1) / (x2 - x1)
            angle = math.atan(slope) * 180 / math.pi

            # 根据角度判断食指的方向，并获取对应的反馈信息
            if (angle > 45 or angle < -45) and y1 > y2:
                direction = directions["up"]
                
                
            elif (angle > 45 or angle < -45) and y1 < y2:
                direction = directions["down"]
                
            elif (-45 < angle < 45) and x1 < x2:
                direction = directions["right"]
            else:
                direction = directions["left"]
            keys.append(direction)

            # 在图像上绘制手部关键点和连线，并显示反馈信息
            mp_drawing.draw_landmarks(image, hand_landmarks, mp_hands.HAND_CONNECTIONS)
            if direction == counts(direction):
                cv2.putText(image, direction, (50, 50), cv2.FONT_HERSHEY_SIMPLEX, 1.5, (0, 255, 0), 3)
            
            elapsed_time = time.time() - start_time
            # print(keys)
            if len(set(keys))==1 and len(keys)>=2 and elapsed_time > 1.2:  ##一直检测一个方向坚持1.2秒才去控制翻页
                if list(set(keys))[0]=="UP":
                    print("up")
                    presentation.SlideShowWindow.View.Previous()  #切回到上一頁
                elif  list(set(keys))[0]=="DOWN":
                    print("down")
                    presentation.SlideShowWindow.View.Next()  #切換到下一頁
                keys=[]
                start_time = time.time()
            elif len(set(keys))>1:
                keys=[]
                start_time = time.time()
    # time.sleep(2)




    # 将图像转换回BGR格式，并显示在窗口中
    image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
    cv2.imshow("Hand Gesture Recognition", image)

    # 按下q键退出循环并关闭窗口
    if cv2.waitKey(5) & 0xFF == ord("q"):
        break

# 释放摄像头资源并关闭所有窗口
cap.release()
cv2.destroyAllWindows() 

3、石头剪刀布游戏

参考：https://github.com/ntu-rris/google-mediapipe