OpenCV 用mediapipe做一个虚拟鼠标

python-version:3.8

python 复制代码

import cv2
import HandTrackingModule as htm
import autopy
import numpy as np
import time

#############################
wCam, hCam = 1080, 720
#############################
frameR = 100
smoothening = 5
##############################
cap = cv2.VideoCapture(0, cv2.CAP_DSHOW)  # 若使用笔记本自带摄像头则编号为0  若使用外接摄像头 则更改为1或其他编号
cap.set(3, wCam)
cap.set(4, hCam)

if cap.isOpened():
    print("打开摄像头成功！")
if not cap.isOpened():
    print("打开摄像头失败！")
pTime = 0
plocX, plocY = 0, 0
clocX, clocY = 0, 0

detector = htm.handDetector()
wScr, hScr = autopy.screen.size()
print(wScr, hScr)


while True:
    success, img = cap.read()
    start_time = time.time()

    if success:
        print("读取帧成功！")
    if not success:
        print("读取帧失败！")
        ## TODO  https://www.cnblogs.com/haiyang21/p/11225060.html
    # 1. 检测手部 得到手指关键点坐标
    img = detector.findHands(img)
    cv2.rectangle(img, (frameR, frameR), (wCam - frameR, hCam - frameR), (0, 255, 0), 2, cv2.FONT_HERSHEY_PLAIN)
    lmList = detector.findPosition(img, draw=False)

    # 2. 判断食指和中指是否伸出
    if len(lmList) != 0:
        x1, y1 = lmList[8][1:]
        x2, y2 = lmList[12][1:]
        fingers = detector.fingersUp()

        # 3. 若只有食指伸出 则进入移动模式
        if fingers[1] and fingers[2] == False:
            # 4. 坐标转换： 将食指在窗口坐标转换为鼠标在桌面的坐标
            # 鼠标坐标
            x3 = np.interp(x1, (frameR, wCam - frameR), (0, wScr))
            y3 = np.interp(y1, (frameR, hCam - frameR), (0, hScr))

            # smoothening values
            clocX = plocX + (x3 - plocX) / smoothening
            clocY = plocY + (y3 - plocY) / smoothening

            autopy.mouse.move(wScr - clocX, clocY)
            cv2.circle(img, (x1, y1), 15, (255, 0, 255), cv2.FILLED)
            plocX, plocY = clocX, clocY

        # 5. 若是食指和中指都伸出 则检测指头距离 距离够短则对应鼠标点击
        if fingers[1] and fingers[2]:
            length, img, pointInfo = detector.findDistance(8, 12, img)
            if length < 40:
                cv2.circle(img, (pointInfo[4], pointInfo[5]),
                           15, (0, 255, 0), cv2.FILLED)
                autopy.mouse.click()

    cTime = time.time()
    fps = 1 / (cTime - pTime)
    pTime = cTime
    cv2.putText(img, 'fps:' + str(int(fps)), (10, 70), cv2.FONT_HERSHEY_PLAIN, 3, (255, 0, 255), 3)

    cv2.imshow("Image", img)
    cv2.waitKey(1)

2.HandTrackingModule.py

python 复制代码

import cv2
import mediapipe as mp
import time
import math

class handDetector():
    ##使用mediapipe库查找手，导出地标像素格式。如查找方式，许多手指向上或两个手指之间的距离。而且提供找到的手的边界框信息。
    #mode: 在静态模式下，对每个图像进行检测， maxHands: 要检测的最大手数， detectionCon: 最小检测置信度，minTrackCon: 最小跟踪置信度
    def __init__(self, mode=False, maxHands=2, modelComplexity=1, detectionCon=0.8, trackCon=0.8):
        self.mode = mode
        self.maxHands = maxHands
        self.modelComplex = modelComplexity
        self.detectionCon = detectionCon
        self.trackCon = trackCon

        # 初始化手部识别模型
        self.mpHands = mp.solutions.hands
        self.hands = self.mpHands.Hands(self.mode, self.maxHands, self.modelComplex, self.detectionCon,self.trackCon)
        self.mpDraw = mp.solutions.drawing_utils  # 初始化绘图器
        self.tipIds = [4, 8, 12, 16, 20]  # 指尖列表

    def findHands(self, img, draw=True): #从图像(BRG)中找到手部，img: 用于查找手的图像，draw: 在图像上绘制输出的标志，return: 带或不带图形的图像
        imgRGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)# 将传入的图像由BGR模式转标准的Opencv模式------RGB模式，
        self.results = self.hands.process(imgRGB)

        print(self.results.multi_handedness)  # 获取检测结果中的左右手标签并打印

        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, draw=True):
        self.lmList = []
        if self.results.multi_hand_landmarks:
            for handLms in self.results.multi_hand_landmarks:
                for id, lm in enumerate(handLms.landmark):
                    h, w, c = img.shape
                    cx, cy = int(lm.x * w), int(lm.y * h)
                    # print(id, cx, cy)
                    self.lmList.append([id, cx, cy])
                    if draw:
                        cv2.circle(img, (cx, cy), 12, (255, 0, 255), cv2.FILLED)
        return self.lmList

    def fingersUp(self):
        fingers = []
        # 大拇指
        if self.lmList[self.tipIds[0]][1] > self.lmList[self.tipIds[0] - 1][1]:
            fingers.append(1)
        else:
            fingers.append(0)

        # 其余手指
        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)

        # totalFingers = fingers.count(1)
        return fingers

    def findDistance(self, p1, p2, img, draw=True, r=15, t=3):
        x1, y1 = self.lmList[p1][1:]
        x2, y2 = self.lmList[p2][1:]
        cx, cy = (x1 + x2) // 2, (y1 + y2) // 2

        if draw:
            cv2.line(img, (x1, y1), (x2, y2), (255, 0, 255), t)
            cv2.circle(img, (x1, y1), r, (255, 0, 255), cv2.FILLED)
            cv2.circle(img, (x2, y2), r, (255, 0, 255), cv2.FILLED)
            cv2.circle(img, (cx, cy), r, (0, 0, 255), cv2.FILLED)
            length = math.hypot(x2 - x1, y2 - y1)

        return length, img, [x1, y1, x2, y2, cx, cy]


def main():
    pTime = 0
    cTime = 0
    cap = cv2.VideoCapture(0)
    detector = handDetector()
    while True:
        success, img = cap.read()
        if not success:
            print("读取帧数据失败！")
        img = detector.findHands(img)        # 检测手势并画上骨架信息

        lmList = detector.findPosition(img)  # 获取得到坐标点的列表
        if len(lmList) != 0:
            print(lmList[4])

        cTime = time.time()
        fps = 1 / (cTime - pTime)
        pTime = cTime

        cv2.putText(img, 'fps:' + 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()