图像、视频或调用摄像头均能实现OpenCV实现人体姿态估计(人体关键点检测）

OpenPose人体姿态识别项目是美国卡耐基梅隆大学（CMU）基于卷积神经网络和监督学习并以Caffe为框架开发的开源库。可以实现人体动作、面部表情、手指运动等姿态估计。适用于单人和多人，具有极好的鲁棒性。是世界上首个基于深度学习的实时多人二维姿态估计应用。
其理论基础来自Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields ，是CVPR 2017的一篇论文，作者是来自CMU感知计算实验室的曹哲（http://people.eecs.berkeley.edu/~zhecao/#top）,Tomas Simon,Shih-En Wei,Yaser Sheikh 。
人体姿态估计技术在体育健身、动作采集、3D试衣、舆情监测等领域具有广阔的应用前景，人们更加熟悉的应用就是抖音尬舞机。

OpenPose项目Github链接：https://github.com/CMU-Perceptual-Computing-Lab/openpose
OpenCV实现的Demo链接：[添加链接描述](https://github.com/PanJinquan/opencv-learning-tutorials/blob/master/opencv_dnn_pro/openpose-opencv/openpose_for_image_test.py)

1、实现原理

输入一幅图像，经过卷积网络提取特征，得到一组特征图，然后分成两个岔路，分别使用 CNN网络提取Part Confidence Maps 和 Part Affinity Fields；

得到这两个信息后，我们使用图论中的 Bipartite Matching（偶匹配）求出Part Association，将同一个人的关节点连接起来，由于PAF自身的矢量性，使得生成的偶匹配很正确，最终合并为一个人的整体骨架；
最后基于PAFs求Multi-Person Parsing—>把Multi-person parsing问题转换成graphs问题—>Hungarian Algorithm(匈牙利算法)
（匈牙利算法是部图匹配最常见的算法，该算法的核心就是寻找增广路径，它是一种用增广路径求二分图最大匹配的算法。)

2、实现神经网络

阶段一：VGGNet的前10层用于为输入图像创建特征映射。

阶段二：使用2分支多阶段CNN，其中第一分支预测身体部位位置（例如肘部，膝部等）的一组2D置信度图（S）。 如下图所示，给出关键点的置信度图和亲和力图 - 左肩。

第二分支预测一组部分亲和度的2D矢量场（L），其编码部分之间的关联度。如下图所示，显示颈部和左肩之间的部分亲和力。

阶段三： 通过贪心推理解析置信度和亲和力图，对图像中的所有人生成2D关键点。

3.OpenCV-OpenPose实现推理代码(图像)

# -*-coding: utf-8 -*-
"""@Project: python-learning-notes@File   : openpose_for_image_test.py@Author : panjq@E-mail : pan_jinquan@163.com@Date   : 2019-07-29 21:50:17
"""import cv2 as cv
import os
import globBODY_PARTS = {"Nose": 0, "Neck": 1, "RShoulder": 2, "RElbow": 3, "RWrist": 4,"LShoulder": 5, "LElbow": 6, "LWrist": 7, "RHip": 8, "RKnee": 9,"RAnkle": 10, "LHip": 11, "LKnee": 12, "LAnkle": 13, "REye": 14,"LEye": 15, "REar": 16, "LEar": 17, "Background": 18}POSE_PAIRS = [["Neck", "RShoulder"], ["Neck", "LShoulder"], ["RShoulder", "RElbow"],["RElbow", "RWrist"], ["LShoulder", "LElbow"], ["LElbow", "LWrist"],["Neck", "RHip"], ["RHip", "RKnee"], ["RKnee", "RAnkle"], ["Neck", "LHip"],["LHip", "LKnee"], ["LKnee", "LAnkle"], ["Neck", "Nose"], ["Nose", "REye"],["REye", "REar"], ["Nose", "LEye"], ["LEye", "LEar"]]def detect_key_point(model_path, image_path, out_dir, inWidth=368, inHeight=368, threshhold=0.2):net = cv.dnn.readNetFromTensorflow(model_path)frame = cv.imread(image_path)frameWidth = frame.shape[1]frameHeight = frame.shape[0]scalefactor = 2.0net.setInput(cv.dnn.blobFromImage(frame, scalefactor, (inWidth, inHeight), (127.5, 127.5, 127.5), swapRB=True, crop=False))out = net.forward()out = out[:, :19, :, :]  # MobileNet output [1, 57, -1, -1], we only need the first 19 elementsassert (len(BODY_PARTS) == out.shape[1])points = []for i in range(len(BODY_PARTS)):# Slice heatmap of corresponging body's part.heatMap = out[0, i, :, :]# Originally, we try to find all the local maximums. To simplify a sample# we just find a global one. However only a single pose at the same time# could be detected this way._, conf, _, point = cv.minMaxLoc(heatMap)x = (frameWidth * point[0]) / out.shape[3]y = (frameHeight * point[1]) / out.shape[2]# Add a point if it's confidence is higher than threshold.points.append((int(x), int(y)) if conf > threshhold else None)for pair in POSE_PAIRS:partFrom = pair[0]partTo = pair[1]assert (partFrom in BODY_PARTS)assert (partTo in BODY_PARTS)idFrom = BODY_PARTS[partFrom]idTo = BODY_PARTS[partTo]if points[idFrom] and points[idTo]:cv.line(frame, points[idFrom], points[idTo], (0, 255, 0), 3)cv.ellipse(frame, points[idFrom], (3, 3), 0, 0, 360, (0, 0, 255), cv.FILLED)cv.ellipse(frame, points[idTo], (3, 3), 0, 0, 360, (0, 0, 255), cv.FILLED)t, _ = net.getPerfProfile()freq = cv.getTickFrequency() / 1000cv.putText(frame, '%.2fms' % (t / freq), (10, 20), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0))cv.imwrite(os.path.join(out_dir, os.path.basename(image_path)), frame)cv.imshow('OpenPose using OpenCV', frame)cv.waitKey(0)def detect_image_list_key_point(image_dir, out_dir, inWidth=480, inHeight=480, threshhold=0.3):image_list = glob.glob(image_dir)for image_path in image_list:detect_key_point(image_path, out_dir, inWidth, inHeight, threshhold)if __name__ == "__main__":model_path = "pb/graph_opt.pb"# image_path = "body/*.jpg"out_dir = "result"# detect_image_list_key_point(image_path,out_dir)image_path = "./test.jpg"detect_key_point(model_path, image_path, out_dir, inWidth=368, inHeight=368, threshhold=0.05)

4.OpenCV-OpenPose实现推理代码（视频或摄像头）

import cv2
import numpy as np
import argparseparser = argparse.ArgumentParser()
parser.add_argument('--input', help='Path to image or video. Skip to capture frames from camera')
parser.add_argument('--thr', default=0.2, type=float, help='Threshold value for pose parts heat map')
parser.add_argument('--width', default=270, type=int, help='Resize input to specific width.')
parser.add_argument('--height', default=480, type=int, help='Resize input to specific height.')args = parser.parse_args()BODY_PARTS = {"Nose": 0, "Neck": 1, "RShoulder": 2, "RElbow": 3, "RWrist": 4,"LShoulder": 5, "LElbow": 6, "LWrist": 7, "RHip": 8, "RKnee": 9,"RAnkle": 10, "LHip": 11, "LKnee": 12, "LAnkle": 13, "REye": 14,"LEye": 15, "REar": 16, "LEar": 17, "Background": 18}POSE_PAIRS = [["Neck", "RShoulder"], ["Neck", "LShoulder"], ["RShoulder", "RElbow"],["RElbow", "RWrist"], ["LShoulder", "LElbow"], ["LElbow", "LWrist"],["Neck", "RHip"], ["RHip", "RKnee"], ["RKnee", "RAnkle"], ["Neck", "LHip"],["LHip", "LKnee"], ["LKnee", "LAnkle"], ["Neck", "Nose"], ["Nose", "REye"],["REye", "REar"], ["Nose", "LEye"], ["LEye", "LEar"]]inWidth = args.width
inHeight = args.heightnet = cv2.dnn.readNetFromTensorflow("graph_opt.pb")#cap = cv2.VideoCapture(args.input if args.input else 0)
#cap = cv2.VideoCapture('action.mp4')
cap = cv2.VideoCapture(0)fourcc = cv2.VideoWriter_fourcc(*'XVID')
output = cv2.VideoWriter('output.avi', fourcc, 5.0, (int(cap.get(3)),int(cap.get(4))))
'''注意：在这部分若要调用摄像头进行实时图像检测并保存视频到本地，需要将上面三行的参数进行更改，并保证最终的保存视频的尺寸大小与输出图像大小相同。'''
while True:hasFrame, frame = cap.read()frameWidth = frame.shape[1]frameHeight = frame.shape[0]net.setInput(cv2.dnn.blobFromImage(frame, 1.0, (inWidth, inHeight), (127.5, 127.5, 127.5), swapRB=True, crop=False))out = net.forward()out = out[:, :19, :, :]  # MobileNet output [1, 57, -1, -1], we only need the first 19 elementsassert (len(BODY_PARTS) == out.shape[1])points = []for i in range(len(BODY_PARTS)):# Slice heatmap of corresponging body's part.heatMap = out[0, i, :, :]# Originally, we try to find all the local maximums. To simplify a sample# we just find a global one. However only a single pose at the same time# could be detected this way._, conf, _, point = cv2.minMaxLoc(heatMap)x = (frameWidth * point[0]) / out.shape[3]y = (frameHeight * point[1]) / out.shape[2]# Add a point if it's confidence is higher than threshold.points.append((int(x), int(y)) if conf > args.thr else None)for pair in POSE_PAIRS:partFrom = pair[0]partTo = pair[1]assert (partFrom in BODY_PARTS)assert (partTo in BODY_PARTS)idFrom = BODY_PARTS[partFrom]idTo = BODY_PARTS[partTo]if points[idFrom] and points[idTo]:cv2.line(frame, points[idFrom], points[idTo], (0, 255, 0), 3)cv2.ellipse(frame, points[idFrom], (3, 3), 0, 0, 360, (0, 0, 255), cv2.FILLED)cv2.ellipse(frame, points[idTo], (3, 3), 0, 0, 360, (0, 0, 255), cv2.FILLED)t, _ = net.getPerfProfile()freq = cv2.getTickFrequency() / 1000cv2.putText(frame, '%.2fms' % (t / freq), (10, 20), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0))cv2.imshow('OpenPose using OpenCV', frame)output.write(frame)if cv2.waitKey(1) & 0xFF == ord('q'):breakcap.release()
output.release()
cv2.destroyAllWindows()

这里十分感谢博主的分享，在此基础实现了视频检测和实时摄像头检测。
参考博客

OpenCV实现人体姿态估计(人体关键点检测）OpenPose（图像、视频或调用摄像头均能实现）相关推荐

人体姿态估计(人体关键点检测)2D Pose训练代码和Android源码
人体姿态估计(人体关键点检测)2D Pose训练代码和Android源码目录人体姿态估计(人体关键点检测)2D Pose训练代码和Android源码 1.人体姿态估计2D Pose方法 2.人体姿 ...
融合人体姿态估计和目标检测的学生课堂行为识别
融合人体姿态估计和目标检测的学生课堂行为识别_参考网摘要: 在課堂教学中 , 人工智能技术可以帮助实现学生行为分析自动化 , 让教师能够高效且直观地掌握学生学习行为投入的情况 , 为后续优化教学设计 ...
MediaPipe人体姿态、手指关键点检测
MediaPipe人体姿态.手指关键点检测文章目录 MediaPipe人体姿态.手指关键点检测前言一.手指关键点检测二.姿态检测三.3D物体案例检测案例前言 Mediapipe是googl ...
CV之PoseEstimation：Pose Estimation人体姿态估计(AI识人,OpenPose+DeepCut+RMPE+Mask RCNN)的简介、案例应用之详细攻略
CV之PoseEstimation:Pose Estimation人体姿态估计(AI识人,OpenPose+DeepCut+RMPE+Mask RCNN)的简介.案例应用之详细攻略目录 Pose E ...
格物钛数据平台国内外经典开源数据汇总（自动驾驶、目标检测、人脸识别、人体姿态估计、文本检测、NLP、医疗）
本文整理了国内外经典的开源数据,包含了目标检测.自动驾驶.人脸识别.自然语言处理.文本检测.医疗等方向,具体如下. 一.自动驾驶领域数据集 KITTI数据集 KITTI数据集由德国卡尔斯鲁厄理工学院和 ...
用OpenPose进行单个或多个人体姿态估计
在计算机视觉中,人体姿态估计(关键点检测)是一个很常见的问题,在体育健身.动作采集.3D试衣.舆情监测等领域具有广阔的应用前景,本文要使用的检测方法就是基于OpenPose的人体姿态估计方法. 一.O ...
Python+OpenCV+OpenPose实现人体姿态估计（人体关键点检测）
目录 1.人体姿态估计简介 2.人体姿态估计数据集 3.OpenPose库 4.实现原理 5.实现神经网络 6.实现代码 1.人体姿态估计简介人体姿态估计(Human Posture Estimat ...
LIVE 预告 | CVPR 2021 预讲 · 旷视专场，覆盖目标检测、蒸馏、图像降噪、人体姿态估计等...
CVPR 2021 大会将于6月19日至 25日线上举行.为促进同行之间的交流与合作,智源社区近期举办了系列CVPR 2021预讲报告,其中实验室系列将汇聚国内顶尖高校和企业实验室的研究人员为大家分享 ...
MMPose姿态估计+人体关键点识别效果演示
MMPose--开源姿态估计算法库(附人体关键点识别效果演示) 一.简介 1.1 背景首先姿态估计属于计算机视觉领域的一个基础研究方向.MMPose是基于Pytorch的姿态估计开源算法库,功能全, ...
Openpose+Tensorflow 这样实现人体姿态估计 | 代码干货
作者 | 李秋键出品 | AI科技大本营(ID:rgznai100) 人体姿态估计指从单个 RGB 图像中精确地估计出人体的位置以及检测骨骼关键点的位置.人体姿态估计是计算机视觉领域的研究热点,是诸 ...

OpenCV实现人体姿态估计(人体关键点检测）OpenPose（图像、视频或调用摄像头均能实现）