MediaPipe人体姿态、手指关键点检测

MediaPipe人体姿态、手指关键点检测

---

前言

  Mediapipe是google的一个开源项目，用于构建机器学习管道。
  提供了16个预训练模型的案例：人脸检测、Face Mesh、虹膜、手、姿态、人体、人物分割、头发分割、目标检测、Box Tracking、Instant Motion Tracking、3D目标检测、特征匹配、AutoFlip、MediaSequence、YouTube-8M。
  肢体识别本质上还是分类任务，该技术有很多应用场景，比如手势识别控制类应用、动作检测类应用、动作评测类应用、以及一些移动设备AR视频合成类应用。

---

一、手指关键点检测

检测一只手中21个关键点坐标，每个点对应一个名称

import cv2
import mediapipe as mp
# 用来在图片中画出关键点
mp_drawing = mp.solutions.drawing_utils
# 关键点图样式
mp_drawing_styles = mp.solutions.drawing_styles
mp_hands = mp.solutions.hands
#MAX_NUM_HANDS 要检测的最大手数 默认为2
hands = mp_hands.Hands(max_num_hands=1)if __name__ == '__main__':file = '1.png'# 图片翻转image = cv2.flip(cv2.imread(file), 1)results = hands.process(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))image_height, image_width, _ = image.shapeannotated_image = image.copy()# 遍历检测出来的手掌for hand_landmarks in results.multi_hand_landmarks:for lm in hand_landmarks.landmark:# 获取每个点的坐标x = lm.x * image_widthy = lm.y * image_height# 画关键点mp_drawing.draw_landmarks(annotated_image,hand_landmarks,mp_hands.HAND_CONNECTIONS,mp_drawing_styles.get_default_hand_landmarks_style(),mp_drawing_styles.get_default_hand_connections_style())cv2.imwrite('0.png', cv2.flip(annotated_image, 1))

二、姿态检测

import cv2
import mediapipe as mp
# 用来在图片中画出关键点
mp_drawing = mp.solutions.drawing_utils
# 关键点图样式
mp_drawing_styles = mp.solutions.drawing_styles
mpPose = mp.solutions.pose
pose = mpPose.Pose()if __name__ == '__main__':file = '1.png'image = cv2.imread(file)image_height, image_width, _ = image.shapeimgRGB = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)results = pose.process(imgRGB)# mediapipe姿态检测只能检测一个人if results.pose_landmarks:for lm in results.pose_landmarks.landmark:h, w, c = image.shapecx, cy = int(lm.x * w), int(lm.y * h)# 画关键点annotated_image = image.copy()mp_drawing.draw_landmarks(annotated_image,results.pose_landmarks,mpPose.POSE_CONNECTIONS,landmark_drawing_spec=mp_drawing_styles.get_default_pose_landmarks_style())cv2.imwrite('0.png', annotated_image)

三、3D物体案例检测案例

其他案例具体可以查看官网详细介绍：

https://google.github.io/mediapipe/solutions/pose.html