基於Mediapipe+Opencv實現手勢檢測功能

import cv2
import mediapipe as mp
import time
#第一步：保存mediapipe中的手勢識別解決方案到mpHands,hands,mpDraw中
mpHands = mp.solutions.hands #以下三個是mediapipe 中的API調用模板瞭
hands = mpHands.Hands(min_detection_confidence=0.5, min_tracking_confidence=0.5)#最小檢測置信度，最小追蹤置信度
mpDraw = mp.solutions.drawing_utils                              #獲取mediapipe解決方案的繪畫工具包
#第二步：參數設定
handLmsStyle = mpDraw.DrawingSpec(color=(0, 0, 255), thickness=3)#繪制手部關鍵點的顏色與粗細
handConStyle = mpDraw.DrawingSpec(color=(0, 255, 0), thickness=5)#繪制手部線條的顏色與粗細
pTime = 0 #和下面的cTime一起用於計算視頻輸入流FPS
cTime = 0
cap = cv2.VideoCapture(0) #打開編號為0的攝像頭，這個一般是自帶攝像頭
#第三步：循環讀取視頻流到img，img輸入hands.hands函數得到結果，繪制結果到img並輸出
while True:
    ret, img = cap.read()       #從cap中讀取圖片到img，並將讀取是否成功的結果保存在ret
    if ret:
        imgRGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)  #模型訓練的時候是使用RGB訓練，對於這個類型識別精度和速度比較高
        result = hands.process(imgRGB)                 #將RGB圖片輸入手部模型將結果保存在result
        # print(result.multi_hand_landmarks)           #打印result.multi_hand_landmarks內容，可以去掉試一下
        imgHeight = img.shape[0]       #獲取攝像機圖片的高
        imgWidth = img.shape[1]        #獲取攝像機圖片的寬
        if result.multi_hand_landmarks:#如果multi_hand_landmarks不為空進入循環
            for handLms in result.multi_hand_landmarks:  #遍歷multi_hand_landmarks內每一個hand_landmark（手部關鍵點），相對於遍歷圖片中每一個手
                mpDraw.draw_landmarks(img, handLms, mpHands.HAND_CONNECTIONS, handLmsStyle, handConStyle) #調用mediapipe內繪畫工具包繪畫手部關鍵點
                for i, lm in enumerate(handLms.landmark):  #i保存第幾個手部關鍵點，lm保存該點在圖中的歸一化值
                    xPos = int(lm.x * imgWidth) #第i個關鍵點x
                    yPos = int(lm.y * imgHeight)#第i個關鍵點y
                    cv2.putText(img, str(i), (xPos-25, yPos+5), cv2.FONT_HERSHEY_SIMPLEX, 0.4, (0, 0, 255), 2)#繪制關鍵點在，關鍵點左邊靠下一點
                    if i == 8:#當畫到第八個關鍵點時
                         cv2.circle(img, (xPos, yPos), 10, (166, 0, 0), cv2.FILLED)#畫一個圓
                         #print(i, xPos, yPos)   #打印繪制這個點時候的坐標
        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) #繪制FSP到圖中
        cv2.imshow('img', img) #輸出圖片
    if cv2.waitKey(1) == ord('q'):#點擊視頻，輸入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)#繪制手部關鍵點的顏色與粗細
handConStyle = mp_drawing.DrawingSpec(color=(0, 255, 0), thickness=4)#繪制手部線條的顏色與粗細
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()