更稳定的手势识别方法--基于手部骨架与关键点检测

import cv2import mediapipe as mpfrom os import listdirmp_drawing = mp.solutions.drawing_utilsmp_hands = mp.solutions.hands

hands = mp_hands.Hands(    min_detection_confidence=0.5, min_tracking_confidence=0.5)cap = cv2.VideoCapture(0)while cap.isOpened():  success, image = cap.read()  if not success:    print("Ignoring empty camera frame.")    continue
  image = cv2.cvtColor(cv2.flip(image, 1), cv2.COLOR_BGR2RGB)  image.flags.writeable = False  results = hands.process(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)  cv2.imshow('result', image)  if cv2.waitKey(5) & 0xFF == 27:    breakcv2.destroyAllWindows()hands.close()cap.release()

import cv2import mediapipe as mpfrom os import listdirmp_drawing = mp.solutions.drawing_utilsmp_hands = mp.solutions.hands
# For static images:hands = mp_hands.Hands(    static_image_mode=True,    max_num_hands=5,    min_detection_confidence=0.2)img_path = './multi_hands/'save_path = './'index = 0file_list = listdir(img_path) for filename in file_list:  index += 1  file_path = img_path + filename  # Read an image, flip it around y-axis for correct handedness output (see  # above).  image = cv2.flip(cv2.imread(file_path), 1)  # Convert the BGR image to RGB before processing.  results = hands.process(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
  # Print handedness and draw hand landmarks on the image.  print('Handedness:', results.multi_handedness)  if not results.multi_hand_landmarks:    continue  image_hight, image_width, _ = image.shape  annotated_image = image.copy()  for hand_landmarks in results.multi_hand_landmarks:    print('hand_landmarks:', hand_landmarks)    print(        f'Index finger tip coordinates: (',        f'{hand_landmarks.landmark[mp_hands.HandLandmark.INDEX_FINGER_TIP].x * image_width}, '        f'{hand_landmarks.landmark[mp_hands.HandLandmark.INDEX_FINGER_TIP].y * image_hight})'    )    mp_drawing.draw_landmarks(        annotated_image, hand_landmarks, mp_hands.HAND_CONNECTIONS)  cv2.imwrite(      save_path + str(index) + '.png', cv2.flip(annotated_image, 1))hands.close()
# For webcam input:hands = mp_hands.Hands(    min_detection_confidence=0.5, min_tracking_confidence=0.5)cap = cv2.VideoCapture(0)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
  # Flip the image horizontally for a later selfie-view display, and convert  # the BGR image to RGB.  image = cv2.cvtColor(cv2.flip(image, 1), cv2.COLOR_BGR2RGB)  # To improve performance, optionally mark the image as not writeable to  # pass by reference.  image.flags.writeable = False  results = hands.process(image)
  # 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)  cv2.imshow('result', image)  if cv2.waitKey(5) & 0xFF == 27:    breakcv2.destroyAllWindows()hands.close()cap.release()

def Normalize_landmarks(image, hand_landmarks):  new_landmarks = []  for i in range(0,len(hand_landmarks.landmark)):    float_x = hand_landmarks.landmark[i].x    float_y = hand_landmarks.landmark[i].y    # Z坐标靠近屏幕增大，远离屏幕减小    float_z = hand_landmarks.landmark[i].z    print(float_z)    width = image.shape[1]    height = image.shape[0]     pt = mp_drawing._normalized_to_pixel_coordinates(float_x,float_y,width,height)    new_landmarks.append(pt)  return new_landmarks