import cv2
import mediapipe as mp
import time
class handDetector():
    def __init__(self, mode = False, maxHands = 2, model_complexity = 1, detectionCon = 0.5, trackCon = 0.5):
        self.mode = mode
        self.maxHands = maxHands
        self.model_complexity = model_complexity
        self.detectionCon = detectionCon
        self.trackCon = trackCon
        self.mpHands = mp.solutions.hands
        self.hands = self.mpHands.Hands(self.mode, self.maxHands, self.model_complexity, self.detectionCon, self.trackCon)
        self.mpDraw = mp.solutions.drawing_utils
    def findHands(self, img, draw = True):
        # Hand類的對(duì)象只能使用RGB圖像
        imgRGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
        self.results = self.hands.process(imgRGB)
        # print(results.multi_hand_landmarks)
        # 如果存在手
        if self.results.multi_hand_landmarks:
            # 如果存在多個(gè)手
            for handLms in self.results.multi_hand_landmarks:
                if draw:
                    # 設(shè)置連接線等屬性
                    self.connection_drawing_spec = self.mpDraw.DrawingSpec(color=(0, 255, 0), thickness=2)
                    # 繪制
                    self.mpDraw.draw_landmarks(img, handLms, self.mpHands.HAND_CONNECTIONS, connection_drawing_spec=self.connection_drawing_spec)
        return img
    def findPosition(self, img, handNum=0, draw=True):
        lmList = []
        # 每個(gè)點(diǎn)的索引和它的像素比例，若知道窗口的寬度和高度可以計(jì)算位置
        if self.results.multi_hand_landmarks:
            myHand = self.results.multi_hand_landmarks[handNum]
            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)
                # print(id, cx, cy)
                lmList.append([id, cx, cy])
                if draw:
                    cv2.circle(img, (cx, cy), 7, (255, 0, 0), cv2.FILLED)
            # 繪制每一只手
        return lmList

import cv2
import time
import numpy as np
import HandTrackingModule as htm
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)
# 設(shè)置攝像頭的寬度
cap.set(3, wCam)
# 設(shè)置攝像頭的高度
cap.set(4, hCam)
pTime = 0
tiga_img = cv2.imread("tiga.jpg", cv2.IMREAD_UNCHANGED)
detector = htm.handDetector(detectionCon=0.7)
face_Cascade = cv2.CascadeClassifier("haarcascade_frontalface_default.xml")
devices = AudioUtilities.GetSpeakers()
interface = devices.Activate(IAudioEndpointVolume._iid_, CLSCTX_ALL, None)
volume = cast(interface, POINTER(IAudioEndpointVolume))
# volume.GetMute()
# volume.GetMasterVolumeLevel()
# 音量范圍
volRange = volume.GetVolumeRange()
print(volRange)
# 最小音量
minVol = volRange[0]
# 最大音量
maxVol = volRange[1]
vol = 0
volBar = 400
volPer = 0
def overlay_img(img, img_over, img_over_x, img_over_y):
    # 背景圖像高寬
    img_w, img_h, img_c = img.shape
    # 覆蓋圖像高寬通道數(shù)
    img_over_h, img_over_w, img_over_c = img_over.shape
    # 轉(zhuǎn)換成4通道
    if img_over_c == 3:
        img_over = cv2.cvtColor(img_over, cv2.COLOR_BGR2BGRA)
    # 遍歷列
    for w in range(0, img_over_w):
        #遍歷行
        for h in range(0, img_over_h):
            if img_over[h, w, 3] != 0:
                # 遍歷三個(gè)通道
                for c in range(0, 3):
                    x = img_over_x + w
                    y = img_over_y + h
                    if x >= img_w or y >= img_h:
                        break
                    img[y-40, x, c] = img_over[h, w, c]
    return img
while True:
    success, img = cap.read()
    gray_frame = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    height, width, channel = img.shape
    faces = face_Cascade.detectMultiScale(gray_frame, 1.15, 5)
    for (x, y, w, h) in faces:
        gw = w
        gh = int(height * w / width)
        tiga_img = cv2.resize(tiga_img, (gw, gh+gh))
        print(gw, gh)
        if 0 <= x < img.shape[1] and 0 <= y < img.shape[0]:
            overlay_img(img, tiga_img, x, y)
    img = detector.findHands(img)
    lmList = detector.findPosition(img, draw=False)
    if len(lmList) != 0:
        # print(lmList[4], lmList[8])
        x1, y1 = lmList[4][1], lmList[4][2]
        x2, y2 = lmList[8][1], lmList[8][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)
        cx, cy = (x1+x2)//2, (y1+y2)//2
        cv2.circle(img, (cx, cy), 15, (255, 0, 255), cv2.FILLED)
        length = math.hypot(x2 - x1, y2 - y1)
        print(length)
        # Hand rang 130 25
        # Vomume Range -65 0
        vol = np.interp(length, [25, 175], [minVol, maxVol])
        volBar = np.interp(length, [25, 175], [400, 150])
        volPer = np.interp(length, [25, 175], [0, 100])
        print(int(length), vol)
        volume.SetMasterVolumeLevel(vol, None)
        if length<25:
            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)