Python实战之手势识别控制电脑音量

这篇文章主要为大家详细介绍了一个Python OpenCV的实战小项目——手势识别控制电脑音量，文中的示例代码讲解详细，感兴趣的小伙伴可以了解一下

一、环境配置

这个项目需要的环境比较简单，主要就是opencv和mediapipe库

import cv2 import mediapipe as mp from ctypes import cast, POINTER from comtypes import CLSCTX_ALL from pycaw.pycaw import AudioUtilities, IAudioEndpointVolume import pyautogui

缺库的话直接：

pip install -i https://pypi.tuna.tsinghua.edu.cn/simple  库名称

二、代码介绍

1）初始化mediapipe库

self.mp_drawing = mp.solutions.drawing_utils self.mp_drawing_styles = mp.solutions.drawing_styles self.mp_hands = mp.solutions.hands

2）获取电脑音量范围

devices = AudioUtilities.GetSpeakers() interface = devices.Activate(IAudioEndpointVolume._iid_, CLSCTX_ALL, None) self.volume = cast(interface, POINTER(IAudioEndpointVolume)) self.volume.SetMute(0, None) self.volume_range = self.volume.GetVolumeRange()

3）利用OpenCV读取摄像头视频流进行显示

cap = cv2.VideoCapture(0) resize_w = 640 resize_h = 480 while cap.isOpened(): success, image = cap.read() image = cv2.resize(image, (resize_w, resize_h))

4）识别手掌，获取手掌关键点坐标

# 判断是否有手掌 if results.multi_hand_landmarks: # 遍历每个手掌 for hand_landmarks in results.multi_hand_landmarks: # 在画面标注手指 # 解析手指，存入各个手指坐标 landmark_list = [] for landmark_id, finger_axis in enumerate( hand_landmarks.landmark): landmark_list.append([ landmark_id, finger_axis.x, finger_axis.y, finger_axis.z ]) if landmark_list: # 获取大拇指指尖坐标 thumb_finger_tip = landmark_list[4] thumb_finger_tip_x = math.ceil(thumb_finger_tip[1] * resize_w) thumb_finger_tip_y = math.ceil(thumb_finger_tip[2] * resize_h) # 获取食指指尖坐标 index_finger_tip = landmark_list[8] index_finger_tip_x = math.ceil(index_finger_tip[1] * resize_w) index_finger_tip_y = math.ceil(index_finger_tip[2] * resize_h) # 获取中指尖坐标 middle_finger_tip = landmark_list[12] middle_finger_tip_x = math.ceil(middle_finger_tip[1] * resize_w) middle_finger_tip_y = math.ceil(middle_finger_tip[2] * resize_h) # 中指与食指中间点 middle_index_finger_middle_point = (middle_finger_tip_x + index_finger_tip_x) // 2, ( middle_finger_tip_y + index_finger_tip_y) // 2 # print(thumb_finger_tip_x) middle_finger_point = (middle_finger_tip_x, middle_finger_tip_y) index_finger_point = (index_finger_tip_x, index_finger_tip_y) # 画指尖2点 image = cv2.circle(image, middle_finger_point, 10, (255, 0, 255), -1) image = cv2.circle(image, index_finger_point, 10, (255, 0, 255), -1) image = cv2.circle(image,  middle_index_finger_middle_point, 10, (255, 0, 255), -1) # 画2点连线 image1 = cv2.line(image, middle_finger_point, index_finger_point, (255, 0, 255), 5) # 勾股定理计算长度 middle_index_line_len = math.hypot((middle_finger_tip_x - index_finger_tip_x), (middle_finger_tip_y - index_finger_tip_y))

5）将拇指与食指距离与电脑音量进行关联

# 当食指中指距离大于65像素允许调音量 if middle_index_line_len <65.0: # 拇指与食指中间点 finger_middle_point = (thumb_finger_tip_x + index_finger_tip_x) // 2, ( thumb_finger_tip_y + index_finger_tip_y) // 2 # print(thumb_finger_tip_x) thumb_finger_point = (thumb_finger_tip_x, thumb_finger_tip_y) index_finger_point = (index_finger_tip_x, index_finger_tip_y) # 画2点连线 image = cv2.line(image, thumb_finger_point, index_finger_point, (255, 0, 255), 5) # 勾股定理计算长度 line_len = math.hypot((index_finger_tip_x - thumb_finger_tip_x), (index_finger_tip_y - thumb_finger_tip_y)) # 获取电脑最大最小音量 min_volume = self.volume_range[0] max_volume = self.volume_range[1] # 将指尖长度映射到音量上 vol = np.interp(line_len, [50, 300], [min_volume, max_volume]) # 将指尖长度映射到矩形显示上 rect_height = np.interp(line_len, [50, 300], [0, 200]) rect_percent_text = np.interp(line_len, [50, 300], [0, 100]) # 设置电脑音量 self.volume.SetMasterVolumeLevel(vol, None) #锁定调音量，进行鼠标控制 else: for id, lm in enumerate(hand_landmarks.landmark): # print(id,lm) h, w, c = image.shape cx, cy = int(lm.x * w), int(lm.y * h) # id=手部关键点 if id == 0: if cx > dot[0] and cx  dot[1] and cy