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、OpenPose简介
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（CNN）和监督学习（SL）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。适用于单人或者多人，具有非常好的鲁棒性，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。
二、实现原理
OpenPose 网络VGGNet的前10层用于为输入图像创建特征映射，然后将这些特征输入到卷积层的两个并行分支中。第一个分支预测了一组置信图（18 个），每个置信图表示人体姿态骨架图的特定部件，第二个分支预测另外一组 Part Affinity Field (PAF，38个），PAF 表示部件之间的关联程度。下图展示的是OpenPose网络模型架构图和检测实例图像的流程图。
三、OpenPose实现代码
import cv2
import time
import numpy as np
from random import randint
image1 = cv2.imread("znl112.jpg")#根据自己的路径添加
protoFile = "pose_deploy_linevec.prototxt"
weightsFile = "pose_iter_440000.caffemodel"
nPoints = 18
# COCO Output Format
keypointsMapping = ['Nose', 'Neck', 'R-Sho', 'R-Elb', 'R-Wr', 'L-Sho', 'L-Elb', 'L-Wr', 'R-Hip',
'R-Knee', 'R-Ank', 'L-Hip', 'L-Knee', 'L-Ank', 'R-Eye', 'L-Eye', 'R-Ear', 'L-Ear']
POSE_PAIRS = [[1,2],[1,5],[2,3],[3,4],[5,6],[6,7],
[1,8],[8,9],[9,10],[1,11],[11,12],[12,13],
[1,0],[0,14],[14,16],[0,15],[15,17],[2,17],[5,16]]
# index of pafs correspoding to the POSE_PAIRS
# e.g for POSE_PAIR(1,2), the PAFs are located at indices (31,32) of output, Similarly, (1,5) -> (39,40) and so on.
mapIdx = [[31,32], [39,40], [33,34], [35,36], [41,42], [43,44],
[19,20], [21,22], [23,24], [25,26], [27,28], [29,30],
[47,48], [49,50], [53,54], [51,52], [55,56], [37,38], [45,46]]
colors = [[0,100,255], [0,100,255], [0,255,255], [0,100,255], [0,255,255], [0,100,255],
[0,255,0], [255,200,100], [255,0,255], [0,255,0], [255,200,100], [255,0,255],
[0,0,255], [255,0,0], [200,200,0], [255,0,0], [200,200,0], [0,0,0]]
def getKeypoints(probMap, threshold=0.1):
mapSmooth = cv2.GaussianBlur(probMap,(3,3),0,0)
mapMask = np.uint8(mapSmooth>threshold)
keypoints = []
#find the blobs
_, contours, _ = cv2.findContours(mapMask, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
#for each blob find the maxima
for cnt in contours:
blobMask = np.zeros(mapMask.shape)
blobMask = cv2.fillConvexPoly(blobMask, cnt, 1)
maskedProbMap = mapSmooth * blobMask
_, maxVal, _, maxLoc = cv2.minMaxLoc(maskedProbMap)
keypoints.append(maxLoc + (probMap[maxLoc[1], maxLoc[0]],))
return keypoints
# Find valid connections between the different joints of a all persons present
def getValidPairs(output):
valid_pairs = []
invalid_pairs = []
n_interp_samples = 10
paf_score_th = 0.1
conf_th = 0.7
# loop for every POSE_PAIR
for k in range(len(mapIdx)):
# A->B constitute a limb
pafA = output[0, mapIdx[k][0], :, :]
pafB = output[0, mapIdx[k][1], :, :]
pafA = cv2.resize(pafA,(frameWidth, frameHeight))
pafB = cv2.resize(pafB,(frameWidth, frameHeight))
# Find the keypoints for the first and second limb
candA = detected_keypoints[POSE_PAIRS[k][0]]
candB = detected_keypoints[POSE_PAIRS[k][1]]
nA = len(candA)
nB = len(candB)
# If keypoints for the joint-pair is detected
# check every joint in candA with every joint in candB
# Calculate the distance vector between the two joints
# Find the PAF values at a set of interpolated points between the joints
# Use the above formula to compute a score to mark the connection valid
if(nA != 0 and nB != 0):
valid_pair = np.zeros((0,3))
for i in range(nA):
max_j=-1
maxScore = -1
found = 0
for j in range(nB):
# Find d_ij
d_ij = np.subtract(candB[j][:2], candA[i][:2])
norm = np.linalg.norm(d_ij)
if norm:
d_ij = d_ij / norm
else:
continue
# Find p(u)
interp_coord = list(zip(np.linspace(candA[i][0], candB[j][0], num=n_interp_samples),
np.linspace(candA[i][1], candB[j][1], num=n_interp_samples)))
# Find L(p(u))
paf_interp = []
for k in range(len(interp_coord)):
paf_interp.append([pafA[int(round(interp_coord[k][1])), int(round(interp_coord[k][0]))],
pafB[int(round(interp_coord[k][1])), int(round(interp_coord[k][0]))] ])
# Find E
paf_scores = np.dot(paf_interp, d_ij)
avg_paf_score = sum(paf_scores)/len(paf_scores)
# Check if the connection is valid
# If the fraction of interpolated vectors aligned with PAF is higher then threshold -> Valid Pair
if(len(np.where(paf_scores>paf_score_th)[0])/n_interp_samples)>conf_th:
if avg_paf_score > maxScore:
max_j = j
maxScore = avg_paf_score
found = 1
# Append the connection to the list
if found:
valid_pair = np.append(valid_pair, [[candA[i][3], candB[max_j][3], maxScore]], axis=0)
# Append the detected connections to the global list
valid_pairs.append(valid_pair)
else: # If no keypoints are detected
#print("No Connection : k = {}".format(k))
invalid_pairs.append(k)
valid_pairs.append([])
return valid_pairs, invalid_pairs
# This function creates a list of keypoints belonging to each person
# For each detected valid pair, it assigns the joint(s) to a person
def getPersonwiseKeypoints(valid_pairs, invalid_pairs):
# the last number in each row is the overall score
personwiseKeypoints = -1 * np.ones((0, 19))
for k in range(len(mapIdx)):
if k not in invalid_pairs:
partAs = valid_pairs[k][:,0]
partBs = valid_pairs[k][:,1]
indexA, indexB = np.array(POSE_PAIRS[k])
for i in range(len(valid_pairs[k])):
found = 0
person_idx = -1
for j in range(len(personwiseKeypoints)):
if personwiseKeypoints[j][indexA] == partAs[i]:
person_idx = j
found = 1
break
if found:
personwiseKeypoints[person_idx][indexB] = partBs[i]
personwiseKeypoints[person_idx][-1] += keypoints_list[partBs[i].astype(int),2]+valid_pairs[k][i][2]
# if find no partA in the subset, create a new subset
elif not found and k < 17:
row = -1 * np.ones(19)
row[indexA] = partAs[i]
row[indexB] = partBs[i]
# add the keypoint_scores for the two keypoints and the paf_score
row[-1] = sum(keypoints_list[valid_pairs[k][i,:2].astype(int),2])+valid_pairs[k][i][2]
personwiseKeypoints = np.vstack([personwiseKeypoints,row])
return personwiseKeypoints
frameWidth = image1.shape[1]
frameHeight = image1.shape[0]
t = time.time()
net = cv2.dnn.readNetFromCaffe(protoFile, weightsFile)
# Fix the input Height and get the width according to the Aspect Ratio
inHeight = 368
inWidth = int((inHeight/frameHeight)*frameWidth)
inpBlob = cv2.dnn.blobFromImage(image1,1.0/255,(inWidth,inHeight),(0,0,0),swapRB=False,crop=False)
net.setInput(inpBlob)
output = net.forward()
print("Time Taken in forward pass = {}".format(time.time() - t))
detected_keypoints = []
keypoints_list = np.zeros((0,3))
keypoint_id = 0
threshold = 0.1
for part in range(nPoints):
probMap = output[0,part,:,:]
probMap = cv2.resize(probMap, (image1.shape[1], image1.shape[0]))
keypoints = getKeypoints(probMap, threshold)
#print("Keypoints - {} : {}".format(keypointsMapping[part], keypoints))
if keypointsMapping[part]=='Nose':
print(len(keypoints))
keypoints_with_id = []
for i in range(len(keypoints)):
keypoints_with_id.append(keypoints[i] + (keypoint_id,))
keypoints_list = np.vstack([keypoints_list, keypoints[i]])
keypoint_id += 1
detected_keypoints.append(keypoints_with_id)
#print(len(keypoints))
frameClone = image1.copy()
for i in range(nPoints):
for j in range(len(detected_keypoints[i])):
cv2.circle(frameClone, detected_keypoints[i][j][0:2], 5, colors[i], -1, cv2.LINE_AA)
#cv2.imshow("Keypoints",frameClone)
valid_pairs, invalid_pairs = getValidPairs(output)
personwiseKeypoints = getPersonwiseKeypoints(valid_pairs, invalid_pairs)
for i in range(17):
for n in range(len(personwiseKeypoints)):
index = personwiseKeypoints[n][np.array(POSE_PAIRS[i])]
if -1 in index:
continue
B = np.int32(keypoints_list[index.astype(int), 0])
A = np.int32(keypoints_list[index.astype(int), 1])
cv2.line(frameClone, (B[0], A[0]), (B[1], A[1]), colors[i], 3, cv2.LINE_AA)
cv2.imshow("Detected Pose",frameClone)
cv2.waitKey(0)
找一张单人的测试图片，测试效果如下：
如果想要在运行结果显示出检测到的人物数目，可以通过选择人体中的一个或者几个关键点作为判断依据，读者可根据自己的情况进行调整，在本文中使用检测到人体鼻子（Nose）的数量作为判断人数的依据，其运行时间和检测到的人数如下所示：
分别再找三张不同的包含多个人物图片进行测试，检测到的人数分别是2，2，5，运行结果如下所示：
图片1
图片2
图片3
以上就是文章的所有内容，如果本文对你有帮助，可以给我点个赞，加个关注，谢谢！
原创文章 9
获赞 9
访问量 1305