openpose从安装到实战全攻略！(win11)

补充

人体姿态估计简介

人体姿态估计数据集
链接: COCO Keypoints challenge
链接: MPII Human Pose Dataset
链接: VGG Pose Dataset
链接: CMU Panoptic Dataset（本案例所用数据集）

前言

本文无openpose介绍。仅有安装到实例化讲解。（2022年8月25日）。文中所有脚本 或 cmake 下载慢的皆可根据连接自行网络下载（作者本人电信验证）速度可大幅提升。

操作环境：

win11

openpose 1.7.0

cmake: 3.23.3

VS2019

python 3.7

一、基本配置

1、github上下载openpose后，解压到自己的目录下，建议不要解压到含有中文路径的地方。
https://github.com/CMU-Perceptual-Computing-Lab/openpose/tree/v1.7.0

2、从github下载pybind11（v2.10.0），并放置在该 3rdparty 目录下。
https://github.com/pybind/pybind11

3、首先下载所需文件，打开到openpose-master\3rdparty\windows 下，可以看到五个bat文件

将所有下载的压缩包解压到此目录下

此时所需文件基本下载完成。

二、CMAKE配置

1、打开CMAKE-gui

2、如果后续想要使用python运行并修改程序，请务必进行以下操作

点击 Add Entry

选择到对应环境的python.exe下就ok了。

3、然后进行configure一次
会出现一片红
选择BUILD_PYTHON （非必须，如果你要用python就选）

选择以下五个模型（必选）

debug直到configure done
然后点击generate，出现generate done即可

三、VS运行

进入工程文件，打开build，应该会有.sln文件，双击打开VS 2019

选择Release 模式，点击生成，生成解决方案。

全部生成后。右键运行 01_body_from_image_default

四、python运行

然后我们进行python调试

1、打开\openpose-master\build\examples\tutorial_api_python

可以选择pycharm or cmd运行，本文选择pycharm。

2、pycharm 设置python解释器环境，也就是 cmake-gui 中指定的 PYTHON_EXCUTABLE 对应的 python解释器环境。

3、直接运行任意01-09的一个py文件。

五、修改python代码读取自己的摄像头

# From Python
# It requires OpenCV installed for Python
import sys
import cv2
import os
from sys import platform
import argparse

try:
    # Import Openpose (Windows/Ubuntu/OSX)
    dir_path = os.path.dirname(os.path.realpath(__file__))
    try:
        # Windows Import
        if platform == "win32":
            # Change these variables to point to the correct folder (Release/x64 etc.)
            sys.path.append(dir_path + '/../../python/openpose/Release');
            os.environ['PATH'] = os.environ['PATH'] + ';' + dir_path + '/../../x64/Release;' + dir_path + '/../../bin;'
            import pyopenpose as op
        else:
            # Change these variables to point to the correct folder (Release/x64 etc.)
            sys.path.append('../../python');
            # If you run `make install` (default path is `/usr/local/python` for Ubuntu), you can also access the OpenPose/python module from there. This will install OpenPose and the python library at your desired installation path. Ensure that this is in your python path in order to use it.
            # sys.path.append('/usr/local/python')
            from openpose import pyopenpose as op
    except ImportError as e:
        print(
            'Error: OpenPose library could not be found. Did you enable `BUILD_PYTHON` in CMake and have this Python script in the right folder?')
        raise e


    params = dict()
    params["model_folder"] = "../../../models/"
    params["hand"] = False
    params["number_people_max"] = 1
    params["disable_blending"] = True  # for black background

    # Starting OpenPose
    opWrapper = op.WrapperPython()
    opWrapper.configure(params)
    opWrapper.start()

    # Process Image
    datum = op.Datum()
    cap = cv2.VideoCapture(0) #输入视频

    fps = cap.get(cv2.CAP_PROP_FPS)
    size = (int(cap.get(cv2.CAP_PROP_FRAME_WIDTH)), int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT)))
    framecount = cap.get(cv2.CAP_PROP_FRAME_COUNT)
    print('Total frames in this video: ' + str(framecount))
    #videoWriter = cv2.VideoWriter("op720_2.avi", cv2.VideoWriter_fourcc('D', 'I', 'V', 'X'), fps, size)

    c = 0
    while cap.isOpened():
        hasFrame, frame = cap.read()
        if hasFrame:
            img_resize = cv2.resize(frame, (640, 360))

            datum.cvInputData = img_resize
            opWrapper.emplaceAndPop(op.VectorDatum([datum]))
            opframe = datum.cvOutputData
            cv2.imshow("main", opframe)

            c = c+1
            #videoWriter.write(opframe)
            if cv2.waitKey(1) & 0xFF == ord('q'):
                break
        else:
            break
    cap.release()
    cv2.destroyAllWindows()

except Exception as e:
    print(e)
    sys.exit(-1)