Python+OpenCV手勢檢測與識別Mediapipe基礎篇

前言

本篇文章適合剛入門OpenCV的同學們。文章將介紹如何使用Python利用OpenCV圖像捕捉,配合強大的Mediapipe庫來實現手勢檢測與識別;本系列後續還會繼續更新Mediapipe手勢的各種衍生項目,還請多多關註!

項目效果圖

視頻捕捉幀數穩定在(25-30)

認識Mediapipe

項目的實現,核心是強大的Mediapipe ,它是google的一個開源項目:

功能 詳細
人臉檢測 FaceMesh 從圖像/視頻中重建出人臉的3D Mesh
人像分離 從圖像/視頻中把人分離出來
手勢跟蹤 21個關鍵點的3D坐標
人體3D識別 33個關鍵點的3D坐標
物體顏色識別 可以把頭發檢測出來,並圖上顏色

Mediapipe Dev:https://mediapipe.dev/

以上是Mediapipe的幾個常用功能 ,這幾個功能我們會在後續一一講解實現

Python安裝Mediapipe

pip install mediapipe==0.8.9.1

也可以用 setup.py 安裝

https://github.com/google/mediapipe

項目環境

Python 3.7

Mediapipe 0.8.9.1

Numpy 1.21.6

OpenCV-Python 4.5.5.64

OpenCV-contrib-Python 4.5.5.64

實測也支持Python3.8-3.9

代碼

核心代碼

OpenCV攝像頭捕捉部分

import cv2

cap = cv2.VideoCapture(0)       #OpenCV攝像頭調用:0=內置攝像頭(筆記本)   1=USB攝像頭-1  2=USB攝像頭-2

while True:
    success, img = cap.read()
    imgRGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)       #cv2圖像初始化
    cv2.imshow("HandsImage", img)       #CV2窗體
    cv2.waitKey(1)      #關閉窗體

mediapipe 手勢識別與繪制

#定義並引用mediapipe中的hands模塊
mpHands = mp.solutions.hands
hands = mpHands.Hands()
mpDraw = mp.solutions.drawing_utils

while True:
    success, img = cap.read()
    imgRGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)       #cv2圖像初始化
    results = hands.process(imgRGB)
    # print(results.multi_hand_landmarks)
    
    if results.multi_hand_landmarks:
        for handLms in results.multi_hand_landmarks:
            for id, lm in enumerate(handLms.landmark):
                # print(id, lm)
                h, w, c = img.shape
                cx, cy = int(lm.x * w), int(lm.y * h)
                print(id, cx, cy)
                # if id == 4:
                cv2.circle(img, (cx, cy), 15, (255, 0, 255), cv2.FILLED)
            
            #繪制手部特征點:
            mpDraw.draw_landmarks(img, handLms, mpHands.HAND_CONNECTIONS)

視頻幀率計算

import time

#幀率時間計算
pTime = 0
cTime = 0

while True
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)       #FPS的字號,顏色等設置

完整代碼

# Coding BIGBOSSyifi
# Datatime:2022/4/24 21:41
# Filename:HandsDetector.py
# Toolby: PyCharm

import cv2
import mediapipe as mp
import time

cap = cv2.VideoCapture(0)       #OpenCV攝像頭調用:0=內置攝像頭(筆記本)   1=USB攝像頭-1  2=USB攝像頭-2

#定義並引用mediapipe中的hands模塊
mpHands = mp.solutions.hands
hands = mpHands.Hands()
mpDraw = mp.solutions.drawing_utils

#幀率時間計算
pTime = 0
cTime = 0

while True:
    success, img = cap.read()
    imgRGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)       #cv2圖像初始化
    results = hands.process(imgRGB)
    # print(results.multi_hand_landmarks)
    
    if results.multi_hand_landmarks:
        for handLms in results.multi_hand_landmarks:
            for id, lm in enumerate(handLms.landmark):
                # print(id, lm)
                h, w, c = img.shape
                cx, cy = int(lm.x * w), int(lm.y * h)
                print(id, cx, cy)
                # if id == 4:
                cv2.circle(img, (cx, cy), 15, (255, 0, 255), cv2.FILLED)
            
            #繪制手部特征點:
            mpDraw.draw_landmarks(img, handLms, mpHands.HAND_CONNECTIONS)
    '''''
    視頻FPS計算
       '''
    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)       #FPS的字號,顏色等設置

    cv2.imshow("HandsImage", img)       #CV2窗體
    cv2.waitKey(1)      #關閉窗體

項目輸出

結語

以此篇文章技術為基礎,後續會更新利用此篇基礎技術實現的《手勢控制:音量,鼠標

項目下載地址https://github.com/BIGBOSS-dedsec/HandsDetection_Python

到此這篇關於Python+OpenCV手勢檢測與識別Mediapipe基礎篇的文章就介紹到這瞭,更多相關Python OpenCV手勢識別Mediapipe內容請搜索WalkonNet以前的文章或繼續瀏覽下面的相關文章希望大傢以後多多支持WalkonNet!

推薦閱讀: