Python Mediapipe 手势识别 实时检测与分析

import mediapipe as mp import cv2 import time

cap = cv2.VideoCapture(0) mpHance = mp.solutions.hands # 选择策略 -- 监测手的模型 mpDraw = mp.solutions.drawing_utils handLmsStyle= mpDraw.DrawingSpec(color=(0, 0, 255), thickness=5 ) # 设定点的样式 颜色 粗细,半径 handConStyle= mpDraw.DrawingSpec(color=(0, 255, 2), thickness=10 ) # 设定线的样式 颜色 粗细,半径 pTime = 0 cTime = 0 hands = mpHance.Hands(static_image_mode=False, # 影片 false 图片 True max_num_hands=2, # 最大手识别数量 model_complexity=1, # 模型的复杂度 只能是 0 1 越高越准 min_detection_confidence=0.9, # 识别的精准度 min_tracking_confidence=0.5) # 追踪的严谨度

class Finger: THUMB = mpHance.HandLandmark.THUMB_TIP INDEX = mpHance.HandLandmark.INDEX_FINGER_TIP MIDDLE = mpHance.HandLandmark.MIDDLE_FINGER_TIP RING = mpHance.HandLandmark.RING_FINGER_TIP PINKY = mpHance.HandLandmark.PINKY_FINGER_TIP

def finger_bend(finger, landmarks): ''' 计算手指的弯曲程度 ''' distal = landmarks[mpHance.HandLandmark[finger.value[0]].value].y proximal = landmarks[mpHance.HandLandmark[finger.value[1]].value].y intermediate = landmarks[mpHance.HandLandmark[finger.value[2]].value].y if distal < proximal and proximal < intermediate: return 'Straight' elif distal > proximal and proximal > intermediate: return 'Bend' else: return 'Unknown'

def detect_gesture(hand_landmarks): ''' 判断手势的类型 ''' thumb_bend = finger_bend(Finger.THUMB, hand_landmarks.landmark) index_bend = finger_bend(Finger.INDEX, hand_landmarks.landmark) middle_bend = finger_bend(Finger.MIDDLE, hand_landmarks.landmark) ring_bend = finger_bend(Finger.RING, hand_landmarks.landmark) pinky_bend = finger_bend(Finger.PINKY, hand_landmarks.landmark) if thumb_bend == 'Bend' and index_bend == 'Bend' and middle_bend == 'Bend' and ring_bend == 'Bend' and pinky_bend == 'Bend': return 'Fist' elif thumb_bend == 'Straight' and index_bend == 'Bend' and middle_bend == 'Bend' and ring_bend == 'Bend' and pinky_bend == 'Bend': return 'Point' elif thumb_bend == 'Bend' and index_bend == 'Bend' and middle_bend == 'Straight' and ring_bend == 'Straight' and pinky_bend == 'Straight': return 'Rock' elif thumb_bend == 'Straight' and index_bend == 'Straight' and middle_bend == 'Straight' and ring_bend == 'Straight' and pinky_bend == 'Straight': return 'Open' else: return 'Unknown'

while True: ret, img = cap.read() # 读取到的图片都是bgr的图片 ，故需要将其转换为RGB的图片

if ret:
    imgRGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
    result = hands.process(imgRGB)  # 侦测
    # print(result.multi_hand_landmarks)  结果为 三个坐标 XYZ
    imgHeight = img.shape[0] # 获取视窗的高度
    imgWidth = img.shape[1] # 获取视窗的宽度
    if result.multi_hand_landmarks :
        for handLms in result.multi_hand_landmarks :  # 画出所有点和线
            mpDraw.draw_landmarks(img, handLms, mpHance.HAND_CONNECTIONS, handLmsStyle, handConStyle)
            # enumerate函数用于将一个可遍历的数据对象（如列表、元组或字符串）组合为一个索引序列，同时列出数据和数据下标，常用于for循环中
            for i, lm in enumerate(handLms.landmark):
                xPos = int(lm.x * imgHeight)
                yPos = int(lm.y * imgWidth)
                cv2.putText(img, str(i), (xPos-1, yPos+1), cv2.FONT_HERSHEY_SIMPLEX, 0.4, (0, 200, 50), 1)
                print(i, xPos, yPos)
            gesture = detect_gesture(handLms)
            cv2.putText(img, gesture, (20, 80), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 0, 0), 2)
    cTime = time.time()
    fps = 1/(cTime - pTime)
    pTime = cTime
    cv2.putText(img, f'FPS : {int(fps)}', (20, 40), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 0, 0), 2)
    cv2.imshow('img', img)
if cv2.waitKey(1) == ord('q'):
    break

cap.release() cv2.destroyAllWindows()