人体骨架舞OpenPose用pythonopencv实现

　　1 说明
　　=====
　　1.1 本次基于OpenPose用python-opencv高级实现人体骨架舞，再次细化并写这篇文章，是为了回答我的一位粉丝的疑问。
　　1.2 基于我的第一篇文章：《OpenPose：实现抖音很火的人体骨架和视频动态舞》。
　　1.3 对视频单人舞蹈的人体骨架舞的代码进行删除、优化、修改、注释，提高可读性和可操作性。
　　1.4 熟悉python和opencv的编程思维和熟悉cv2的函数。
　　1.5 环境：python3.8+opencv4.4.0+深度deepin-linux操作系统+微软编辑器vscode。
　　2 原图+骨架舞
　　===========
　　2.1 效果图
　　视频节选
　　2.2 我的第一篇文章中有代码，对源代码进行修改后的代码#第1步：导入模块 import cv2 import time import numpy as np  #第2步：模块加载 #模块下载之间有介绍，此处省略 protoFile = ＂/home/xgj/Desktop/learnopencv/3-OpenPose-OK/pose/coco/pose_deploy_linevec.prototxt＂ weightsFile = ＂/home/xgj/Desktop/learnopencv/3-OpenPose-OK/pose/coco/pose_iter_440000.caffemodel＂  #参数初始化设置，建议不要动参数，默认 #18个节点 nPoints = 18 #节点关系，固定 POSE_PAIRS = [ [1,0],[1,2],[1,5],[2,3],[3,4],[5,6],[6,7],[1,8],[8,9],[9,10],[1,11],[11,12],[12,13],[0,14],[0,15],[14,16],[15,17]] inWidth = 368 inHeight = 368 threshold = 0.1  #模型加载 net = cv2.dnn.readNetFromCaffe(protoFile, weightsFile)  #启动CPU，非GPU net.setPreferableBackend(cv2.dnn.DNN_TARGET_CPU) print(＂Using CPU device＂)  #第3步：cv2读取本地单人舞蹈视频 #cap = cv2.VideoCapture(0)  #读取摄像头实时检测人体骨架，有点卡，省略 #读取视频文件，注意单个人的姿势和人体骨架，目前多人出现bug cap = cv2.VideoCapture(＂/home/xgj/Desktop/learnopencv/3-OpenPose-OK/sample_video.mp4＂) hasFrame, frame = cap.read()  #生成本目录下的视频 vid_writer = cv2.VideoWriter(＂/home/xgj/Desktop/learnopencv/3-OpenPose-OK/output2.avi＂,cv2.VideoWriter_fourcc(＂M＂,＂J＂,＂P＂,＂G＂), 10, (frame.shape[1],frame.shape[0]))  #第4步：循环 while cv2.waitKey(1) < 0:     #初始化时间     t = time.time()     hasFrame, frame = cap.read()     frameCopy = np.copy(frame)     #退出设置     if not hasFrame:         cv2.waitKey()         break          frameWidth = frame.shape[1]     frameHeight = frame.shape[0]      inpBlob = cv2.dnn.blobFromImage(frame, 1.0 / 255, (inWidth, inHeight),                               (0, 0, 0), swapRB=False, crop=False)     net.setInput(inpBlob)     output = net.forward()      H = output.shape[2]     W = output.shape[3]     # Empty list to store the detected keypoints     points = []      for i in range(nPoints):         # confidence map of corresponding body＂s part.         probMap = output[0, i, :, :]          # Find global maxima of the probMap.         minVal, prob, minLoc, point = cv2.minMaxLoc(probMap)                  # Scale the point to fit on the original image         x = (frameWidth * point[0]) / W         y = (frameHeight * point[1]) / H          if prob > threshold :              cv2.circle(frameCopy, (int(x), int(y)), 8, (0, 255, 255), thickness=-1, lineType=cv2.FILLED)             cv2.putText(frameCopy, ＂{}＂.format(i), (int(x), int(y)), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2, lineType=cv2.LINE_AA)              # Add the point to the list if the probability is greater than the threshold             points.append((int(x), int(y)))         else :             points.append(None)      # Draw Skeleton     for pair in POSE_PAIRS:         partA = pair[0]         partB = pair[1]          if points[partA] and points[partB]:             #画骨架线和圆点，颜色可自定义             cv2.line(frame, points[partA], points[partB], (0, 255, 255), 3, lineType=cv2.LINE_AA)             cv2.circle(frame, points[partA], 8, (0, 0, 255), thickness=-1, lineType=cv2.FILLED)             cv2.circle(frame, points[partB], 8, (0, 0, 255), thickness=-1, lineType=cv2.FILLED)     #显示时间和帧     cv2.putText(frame, ＂time taken = {:.2f} sec＂.format(time.time() - t), (50, 50), cv2.FONT_HERSHEY_COMPLEX, .8, (255, 50, 0), 2, lineType=cv2.LINE_AA)     #动态显示     cv2.imshow(＂Output-Skeleton＂, frame)     #写入视频     vid_writer.write(frame)  vid_writer.release()
　　3 纯骨架舞
　　========
　　3.1 效果图：
　　3.2 操作步骤简单，注意路径即可，采用cpu法，大概这个视频需要30分钟。
　　3.3 代码#第1步：导入模块 import cv2 import time import numpy as np  #第2步：模块加载 #模块下载之间有介绍，此处省略 protoFile = ＂/home/xgj/Desktop/learnopencv/3-OpenPose-OK/pose/coco/pose_deploy_linevec.prototxt＂ weightsFile = ＂/home/xgj/Desktop/learnopencv/3-OpenPose-OK/pose/coco/pose_iter_440000.caffemodel＂  #参数初始化设置，建议不要动参数，默认 #18个节点 nPoints = 18 #节点关系，固定 POSE_PAIRS = [ [1,0],[1,2],[1,5],[2,3],[3,4],[5,6],[6,7],[1,8],[8,9],[9,10],[1,11],[11,12],[12,13],[0,14],[0,15],[14,16],[15,17]] inWidth = 368 inHeight = 368 threshold = 0.1  #模型加载 net = cv2.dnn.readNetFromCaffe(protoFile, weightsFile)  #启动CPU，非GPU net.setPreferableBackend(cv2.dnn.DNN_TARGET_CPU) print(＂Using CPU device＂)  #第3步：cv2读取本地单人舞蹈视频 #cap = cv2.VideoCapture(0)  #读取摄像头实时检测人体骨架，有点卡，省略 #读取视频文件，注意单个人的姿势和人体骨架，目前多人出现bug cap = cv2.VideoCapture(＂/home/xgj/Desktop/learnopencv/3-OpenPose-OK/sample_video.mp4＂) hasFrame, frame = cap.read()  #生成本目录下的视频 vid_writer = cv2.VideoWriter(＂/home/xgj/Desktop/learnopencv/3-OpenPose-OK/output3.avi＂,cv2.VideoWriter_fourcc(＂M＂,＂J＂,＂P＂,＂G＂), 10, (frame.shape[1],frame.shape[0]))  #第4步：循环 while cv2.waitKey(1) < 0:     #初始化时间     t = time.time()     hasFrame, frame = cap.read()     frameCopy = np.copy(frame)     #-------以上未修改-------      #增加一张输出的黑色图片，用于显示骨架和数字     out = np.zeros(frame.shape,np.uint8)  #修改处，此处增加          #-------以下未修改-------     #退出设置     if not hasFrame:         cv2.waitKey()         break      frameWidth = frame.shape[1]     frameHeight = frame.shape[0]     inpBlob = cv2.dnn.blobFromImage(frame, 1.0 / 255, (inWidth, inHeight),                               (0, 0, 0), swapRB=False, crop=False)     net.setInput(inpBlob)     output = net.forward()     H = output.shape[2]     W = output.shape[3]     # Empty list to store the detected keypoints     points = []     for i in range(nPoints):         # confidence map of corresponding body＂s part.         probMap = output[0, i, :, :]         # Find global maxima of the probMap.         minVal, prob, minLoc, point = cv2.minMaxLoc(probMap)         # Scale the point to fit on the original image         x = (frameWidth * point[0]) / W         y = (frameHeight * point[1]) / H          if prob > threshold :           #---------以上未修改-------              #修改处：将frame改为out             cv2.circle(out, (int(x), int(y)), 8, (0, 255, 255), thickness=-1, lineType=cv2.FILLED)             cv2.putText(out, ＂{}＂.format(i), (int(x), int(y)), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2, lineType=cv2.LINE_AA)          #-------以下未修改-------             # Add the point to the list if the probability is greater than the threshold             points.append((int(x), int(y)))         else :             points.append(None)      # Draw Skeleton     for pair in POSE_PAIRS:         partA = pair[0]         partB = pair[1]          if points[partA] and points[partB]:     #-------以上未修改-------              #修改处：将frame改为out             cv2.line(out, points[partA], points[partB], (0, 255, 255), 3, lineType=cv2.LINE_AA)             cv2.circle(out, points[partA], 8, (0, 0, 255), thickness=-1, lineType=cv2.FILLED)             cv2.circle(out, points[partB], 8, (0, 0, 255), thickness=-1, lineType=cv2.FILLED)          #修改处：将frame改为out     cv2.putText(out, ＂time taken = {:.2f} sec＂.format(time.time() - t), (50, 50), cv2.FONT_HERSHEY_COMPLEX, .8, (255, 50, 0), 2, lineType=cv2.LINE_AA)     cv2.imshow(＂Output-Skeleton＂, out)     vid_writer.write(out)  vid_writer.release()
　　4 小结
　　4.1 讲解非常仔细，操作非常简单，是在源代码进行修改，非终端输入法，直接点击微软编辑器运行按钮即可。
　　4.2 采用摄像头获取实时个人视频，可能有点卡，但是生成视频文件播放应该是正常的，可以试试。我没有试过。
　　希望大家喜欢。