人体骨架绘制：获取关键点信息及代码示例

通过 MediaPipe 姿态识别模型，我们可以获取人体关键点信息，并绘制出完整的人体骨架。

# 绘制人体骨架
mp_drawing.draw_landmarks(
    frame, results.pose_landmarks, mp_pose.POSE_CONNECTIONS)

# 获取右膝、右踝和右手腕关键点信息
right_knee = results.pose_landmarks.landmark[mp_pose.PoseLandmark.RIGHT_KNEE]
right_ankle = results.pose_landmarks.landmark[mp_pose.PoseLandmark.RIGHT_ANKLE]
right_wrist = results.pose_landmarks.landmark[mp_pose.PoseLandmark.RIGHT_WRIST]

# 获取左膝、左踝和左手腕关键点信息
left_knee = results.pose_landmarks.landmark[mp_pose.PoseLandmark.LEFT_KNEE]
left_ankle = results.pose_landmarks.landmark[mp_pose.PoseLandmark.LEFT_ANKLE]
left_wrist = results.pose_landmarks.landmark[mp_pose.PoseLandmark.LEFT_WRIST]

# 获取左肩、左肘和左手腕关键点信息
left_shoulder = results.pose_landmarks.landmark[mp_pose.PoseLandmark.LEFT_SHOULDER]
left_elbow = results.pose_landmarks.landmark[mp_pose.PoseLandmark.LEFT_ELBOW]
left_wrist = results.pose_landmarks.landmark[mp_pose.PoseLandmark.LEFT_WRIST]

# 获取右肩、右肘和右手腕关键点信息
right_shoulder = results.pose_landmarks.landmark[mp_pose.PoseLandmark.RIGHT_SHOULDER]
right_elbow = results.pose_landmarks.landmark[mp_pose.PoseLandmark.RIGHT_ELBOW]
right_wrist = results.pose_landmarks.landmark[mp_pose.PoseLandmark.RIGHT_WRIST]

# 获取关键点24、26、28的信息
point24 = results.pose_landmarks.landmark[24]
point26 = results.pose_landmarks.landmark[26]
point28 = results.pose_landmarks.landmark[28]

关键点信息:

• 左右肩、肘和手腕的关键点分别为：
  • 左肩：mp_pose.PoseLandmark.LEFT_SHOULDER
  • 左肘：mp_pose.PoseLandmark.LEFT_ELBOW
  • 左手腕：mp_pose.PoseLandmark.LEFT_WRIST
  • 右肩：mp_pose.PoseLandmark.RIGHT_SHOULDER
  • 右肘：mp_pose.PoseLandmark.RIGHT_ELBOW
  • 右手腕：mp_pose.PoseLandmark.RIGHT_WRIST
• 关键点24、26、28分别为人体的胸部中心点、下腰部中心点和骨盆中心点。

通过获取这些关键点信息，我们可以绘制出更完整、更准确的人体骨架。