机器视觉 python+mediapipe+opencv实现人体姿态识别（一）

一、mediapipe是什么？

mediapipe官网

二、使用步骤

1.引入库

代码如下：

import cv2
import time
import mediapipe as mp

2.主代码

代码如下：

mpDraw = mp.solutions.drawing_utils
mpPose = mp.solutions.pose
pose = mpPose.Pose()

cap = cv2.VideoCapture(0)
success, img = cap.read()
video_size = (img.shape[1], img.shape[0])

pTime = 0
count = 0
first_condition = 0
second_condition = 0
third_condition = 0
flat_x = []
flat_y = []
while True:
    success, img = cap.read()
    imgRGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
    results = pose.process(imgRGB)
    #print(results.pose_landmarks)
    if results.pose_landmarks:
        mpDraw.draw_landmarks(img, results.pose_landmarks,
                              mpPose.POSE_CONNECTIONS)

    cTime = time.time()
    fps = 1/(cTime-pTime)
    pTime = cTime
    cv2.putText(img, str(int(fps)), (25, 50), cv2.FONT_HERSHEY_PLAIN,2, (255, 0, 0), 3)

    cv2.imshow("Image", img)
    cv2.waitKey(25)
    if cv2.waitKey(1) == 27:
        break

cap.release()

cv2.destroyAllWindows()

3.运行结果

以上就是今天要讲的内容，本文仅仅简单介绍了mediapipe的使用，而mediapipe提供了大量关于图像识别等的方法。