机器视觉 python+mediapipe+opencv手部关键点检测（实现音量调节）（二）_mediapipe、opencv 和 numpy

机器视觉 python+mediapipe+opencv实现手部关键点检测（手势识别）（一）

一、mediapipe是什么？

mediapipe官网

二、使用步骤

1.源代码

代码如下：

import cv2
import time
import numpy as np
import mediapipe as mp
from mediapipe import solutions
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
mpHands = solutions.hands
hands = mpHands.Hands()
devices = AudioUtilities.GetSpeakers()
interface = devices.Activate(IAudioEndpointVolume._iid_, CLSCTX_ALL, None)
volume = cast(interface, POINTER(IAudioEndpointVolume))
volRange = volume.GetVolumeRange()
minVol = volRange[0]
maxVol = volRange[1]
vol = 0
volBar = 400
volPer = 0

def findPosition(img, handNo=0, draw=True):
    xList = []
    yList = []
    lmList = []
    imgRGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
    results = hands.process(imgRGB)
    if results.multi_hand_landmarks:
        for handLms in results.multi_hand_landmarks:
            mp.solutions.drawing_utils.draw_landmarks(img, handLms, mp.solutions.hands.HAND_CONNECTIONS)
        myHand = 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)
            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 lmList


while True:
    success, img = cap.read()
    lmList = findPosition(img, draw=False)
    if len(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, 200]
        # Volume Range -65 - 0

        vol = np.interp(length, Hand_range, [minVol, maxVol])
        volBar = np.interp(length, Hand_range, [400, 150])
        volPer = np.interp(length, Hand_range, [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)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101

2.运行结果：

三、总结

以上就是今天要讲的内容，本文仅仅简单介绍了mediapipe的使用，而mediapipe提供了大量关于图像识别等的应用和方法。