基于Mediapipe+Opencv实现手势检测功能

import cv2
import mediapipe as mp
import time
#第一步：保存mediapipe中的手势识别解决方案到mpHands,hands,mpDraw中
mpHands = mp.solutions.hands #以下三个是mediapipe 中的API调用模板了
hands = mpHands.Hands(min_detection_confidence=0.5, min_tracking_confidence=0.5)#最小检测置信度，最小追踪置信度
mpDraw = mp.solutions.drawing_utils                              #获取mediapipe解决方案的绘画工具包
#第二步：参数设定
handLmsStyle = mpDraw.DrawingSpec(color=(0, 0, 255), thickness=3)#绘制手部关键点的颜色与粗细
handConStyle = mpDraw.DrawingSpec(color=(0, 255, 0), thickness=5)#绘制手部线条的颜色与粗细
pTime = 0 #和下面的cTime一起用于计算视频输入流FPS
cTime = 0
cap = cv2.VideoCapture(0) #打开编号为0的摄像头，这个一般是自带摄像头
#第三步：循环读取视频流到img，img输入hands.hands函数得到结果，绘制结果到img并输出
while True:
    ret, img = cap.read()       #从cap中读取图片到img，并将读取是否成功的结果保存在ret
    if ret:
        imgRGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)  #模型训练的时候是使用RGB训练，对于这个类型识别精度和速度比较高
        result = hands.process(imgRGB)                 #将RGB图片输入手部模型将结果保存在result
        # print(result.multi_hand_landmarks)           #打印result.multi_hand_landmarks内容，可以去掉试一下
        imgHeight = img.shape[0]       #获取摄像机图片的高
        imgWidth = img.shape[1]        #获取摄像机图片的宽
        if result.multi_hand_landmarks:#如果multi_hand_landmarks不为空进入循环
            for handLms in result.multi_hand_landmarks:  #遍历multi_hand_landmarks内每一个hand_landmark（手部关键点），相对于遍历图片中每一个手
                mpDraw.draw_landmarks(img, handLms, mpHands.HAND_CONNECTIONS, handLmsStyle, handConStyle) #调用mediapipe内绘画工具包绘画手部关键点
                for i, lm in enumerate(handLms.landmark):  #i保存第几个手部关键点，lm保存该点在图中的归一化值
                    xPos = int(lm.x * imgWidth) #第i个关键点x
                    yPos = int(lm.y * imgHeight)#第i个关键点y
                    cv2.putText(img, str(i), (xPos-25, yPos+5), cv2.FONT_HERSHEY_SIMPLEX, 0.4, (0, 0, 255), 2)#绘制关键点在，关键点左边靠下一点
                    if i == 8:#当画到第八个关键点时
                         cv2.circle(img, (xPos, yPos), 10, (166, 0, 0), cv2.FILLED)#画一个圆
                         #print(i, xPos, yPos)   #打印绘制这个点时候的坐标
        cTime = time.time()
        fps = 1/(cTime-pTime)
        pTime = cTime
        cv2.putText(img, f"FPS : {int(fps)}", (30, 50), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 0, 0), 3) #绘制FSP到图中
        cv2.imshow('img', img) #输出图片
    if cv2.waitKey(1) == ord('q'):#点击视频，输入q退出
        break

import cv2
import time
import mediapipe as mp
mp_drawing = mp.solutions.drawing_utils
mp_holistic = mp.solutions.holistic
holistic = mp_holistic.Holistic(min_detection_confidence=0.5, min_tracking_confidence=0.5)
handLmsStyle = mp_drawing.DrawingSpec(color=(0, 0, 255), thickness=0)#绘制手部关键点的颜色与粗细
handConStyle = mp_drawing.DrawingSpec(color=(0, 255, 0), thickness=4)#绘制手部线条的颜色与粗细
cap = cv2.VideoCapture(0)
while True:
    ret,image=cap.read()
    if ret:
        image = cv2.flip(image, 1)
        image=cv2.cvtColor(image,cv2.COLOR_BGR2RGB)
        results = holistic.process(image)
        if results.pose_landmarks:
            mp_drawing.draw_landmarks(image, results.face_landmarks, mp_holistic.FACEMESH_CONTOURS,handLmsStyle,handConStyle)
            mp_drawing.draw_landmarks(image, results.left_hand_landmarks, mp_holistic.HAND_CONNECTIONS)
            mp_drawing.draw_landmarks(image, results.right_hand_landmarks, mp_holistic.HAND_CONNECTIONS)
            mp_drawing.draw_landmarks(image, results.pose_landmarks, mp_holistic.POSE_CONNECTIONS)
        cv2.imshow("img",image)
        if cv2.waitKey(1)==ord("q"):
            break
holistic.close()