基于mediapipe的手势识别

关键点说明

mediapipe手势识别可以识别出手部的21个关键点

获取关键点坐标

模型给出的结果是归一化的坐标比例，要获取在图像中的坐标需要乘以图像的宽高

x = hand_landmarks.landmark[mp_hands.HandLandmark.INDEX_FINGER_TIP].x * image_width
y = hand_landmarks.landmark[mp_hands.HandLandmark.INDEX_FINGER_TIP].y * image_height

示例代码

import cv2
import mediapipe as mp
import numpy as np
Key_Esc = 27
mp_drawing = mp.solutions.drawing_utils
mp_drawing_styles = mp.solutions.drawing_styles
mp_hands = mp.solutions.hands
# For webcam input:
cap = cv2.VideoCapture(0)
with mp_hands.Hands(
    # model_complexity=0,
    min_detection_confidence=0.5,
        min_tracking_confidence=0.5) as hands:
    while cap.isOpened():
        success, image = cap.read()
        if not success:
            print("Ignoring empty camera frame.")
            # If loading a video, use 'break' instead of 'continue'.
            continue
        # To improve performance, optionally mark the image as not writeable to
        # pass by reference.
        image.flags.writeable = False
        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
        results = hands.process(image)
        print('Handedness:', results.multi_handedness)
        # print(results.multi_hand_landmarks)
        # Draw the hand annotations on the image.
        image.flags.writeable = True
        image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
        if results.multi_hand_landmarks:
            for hand_landmarks in results.multi_hand_landmarks:
                mp_drawing.draw_landmarks(
                    image,
                    hand_landmarks,
                    mp_hands.HAND_CONNECTIONS,
                    mp_drawing_styles.get_default_hand_landmarks_style(),
                    mp_drawing_styles.get_default_hand_connections_style())
        # Flip the image horizontally for a selfie-view display.
        cv2.imshow('MediaPipe Hands', np.rot90(
            cv2.resize(cv2.flip(image, 1), (320, 240))))
        if cv2.waitKey(5) == Key_Esc:
            break
cap.release()