通过一个偶然机会，我了解到了人体姿态解算，在学习K210之余，我便想着通过opencv实现这个功能，查找了很多资料，发现可以利用opencv+openpose实现，接着我又开始找一些资料，在pycharm上部署。

前言

人体姿态估计的一个有趣应用是 CGI（computer graphic image，一种电影制造技术）应用。如果可以检测出人体姿态，那么图形、风格、特效增强、设备和艺术造型等就可以被加载在人体上。通过追踪人体姿态的变化，渲染的图形可以在人动的时候“自然”地与人“融合”。姿态估计的一个有趣应用是在交互游戏中追踪人体对象的运动。比较流行的 Kinect 使用 3D 姿态估计（采用 IR 传感器数据）来追踪人类玩家的运动，从而利用它来渲染虚拟人物的动作。
应用：
用于检测一个人是否摔倒或疾病
用于健身、体育和舞蹈等的自动教学
用于理解全身的肢体语言（如机场跑道信号、交警信号等）
用于增强安保和监控

一、环境配置

pycharm2021.2.2
pycharm是一个很好用的软件，刚开始我们必须要配置相应的环境，当然你使用我主页里那篇模型训练的环境也可以，在你运行的时候系统会提示你缺少了什么环境，并让你安装，你直接安装即可。这里我就不过多的赘述了。

二、使用步骤

1.导入文件

在pycharm上导入相应的文件后，你可以直接点击运行，系统会提示你缺少了什么环境，缺少什么就安装什么，通过终端使用pip安装即可。
需要的留下邮箱即可，我发给你。

2.具体代码

# To use Inference Engine backend, specify location of plugins:
# export LD_LIBRARY_PATH=/opt/intel/deeplearning_deploymenttoolkit/deployment_tools/external/mklml_lnx/lib:$LD_LIBRARY_PATH
import cv2 as cv
import numpy as np
import argparse

parser = 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=368, type=int, help='Resize input to specific width.')
parser.add_argument('--height', default=368, 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.height

net = cv.dnn.readNetFromTensorflow("graph_opt.pb")

cap = cv.VideoCapture(args.input if args.input else 0)

while cv.waitKey(1) < 0:
    hasFrame, frame = cap.read()
    if not hasFrame:
        cv.waitKey()
        break

    frameWidth = frame.shape[1]
    frameHeight = frame.shape[0]
    
    net.setInput(cv.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 elements

    assert(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 > 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]:
            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() / 1000
    cv.putText(frame, '%.2fms' % (t / freq), (10, 20), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0))

    cv.imshow('OpenPose using OpenCV', frame)

这里便是主函数的代码。

3.效果展示

这副图片便是识别的效果，帧率还是很不错的。

三、效果优化

这个帧率虽然可以，但是效果属实有点拉跨。教我K210的学长便指导我进行优化改进，这里附上学长的连接（https://blog.csdn.net/hyayq8124?spm=1001.2014.3001.5509）

1.具体代码

import cv2
import time
import mediapipe as mp
from tqdm import tqdm

# 导入solution
mp_pose = mp.solutions.pose


mp_drawing = mp.solutions.drawing_utils


pose = mp_pose.Pose(static_image_mode=False,
            #    model_complexity=1,
                    smooth_landmarks=True,
           #        enable_segmentation=True,
                    min_detection_confidence=0.5,
                    min_tracking_confidence=0.5)


def process_frame(img):
    # BGR转RGB
    img_RGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)

    results = pose.process(img_RGB)

    # 可视化
    mp_drawing.draw_landmarks(img, results.pose_landmarks, mp_pose.POSE_CONNECTIONS)
    # look_img(img)

    # mp_drawing.plot_landmarks(results.pose_world_landmarks, mp_pose.POSE_CONNECTIONS)

    #     # BGR转RGB
    #     img_RGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
    #
    #     results = hands.process(img_RGB)

    #     if results.multi_hand_landmarks: # 如果有检测到手
    #
    #         for hand_idx in range(len(results.multi_hand_landmarks)):
    #             hand_21 = results.multi_hand_landmarks[hand_idx]
    #             mpDraw.draw_landmarks(img, hand_21, mp_hands.HAND_CONNECTIONS)

    return img

cap = cv2.VideoCapture(1)

# 打开cap
cap.open(0)

# 无限循环，直到break被触发
while cap.isOpened():
    # 获取画面
    success, frame = cap.read()
    if not success:
        print('Error')
        break

    ## !!!处理帧函数
    frame = process_frame(frame)

    # 展示处理后的三通道图像
    cv2.imshow('my_window', frame)

    if cv2.waitKey(1) in [ord('q'), 27]:
        break


cap.release()


cv2.destroyAllWindows()

2.效果展示

效果简直太好了。哈哈哈

总结

到这里这篇文章就结束了，写这篇博客只是单纯记录自己的学习过程。希望看到这篇博客的你，能够更加坚定的学习。胡适说过一句话我觉得特别好，这里分享给大家。
怕什么真理无穷，进一寸有进一寸的欢喜。