如何使用 OpenPose 或 python 和 OpenCV 中的任何其他替代方法检测 "human hand Pose"？
How to Detect "human hand Pose" using OpenPose or any other alternatives in python and OpenCV?
我正在尝试使用 OpenPose 检测人手姿势，就像此视频 https://github.com/CMU-Perceptual-Computing-Lab/openpose/blob/master/.github/media/pose_face_hands.gif 中手部分给出的那样。我已经下载了 caffe 模型和 prototxt 文件。下面是我实现模型的代码。
import cv2
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
frame = cv2.imread("6.jpg")
frame_rgb=cv2.cvtColor(frame,cv2.COLOR_BGR2RGB)
plt.imshow(frame_rgb)
threshold = 0.025
input_width, input_height = 368, 368
nPoints = 22
POSE_PAIRS = [[0, 1], [1, 2], [2, 3], [3, 4], [0, 5], [5, 6], [6, 7], [7, 8], [0, 9],
[9, 10], [10, 11], [11, 12], [0, 13], [13, 14], [14, 15], [15, 16], [0, 17],
[17, 18], [18, 19], [19, 20]]
net = cv2.dnn.readNetFromCaffe('pose_deploy_hand.prototxt', 'pose_iter_102000.caffemodel')
net.setPreferableBackend(cv2.dnn.DNN_BACKEND_OPENCV)
net.setPreferableTarget(cv2.dnn.DNN_TARGET_OPENCL)
origin_h, origin_w = frame_rgb.shape[:2]
blob = cv2.dnn.blobFromImage(frame_rgb, 1.0 / 255, (input_width, input_height), 0, swapRB=False, crop=False)
net.setInput(blob)
detections = net.forward()
H = detections.shape[2]
W = detections.shape[3]
points = []
for i in range(nPoints):
probility_map = detections[0, i, :, :]
#
min_value, confidence, min_loc, point = cv2.minMaxLoc(probility_map)
#
x = int(origin_w * (point[0] / W))
y = int(origin_h * (point[1] / H))
if confidence > threshold:
cv2.circle(frame_rgb, (x, y), 6, (255, 255, 0), -1, cv2.FILLED)
#cv.putText(frame, "{}".format(i), (x, y-15), cv.FONT_HERSHEY_SIMPLEX, 0.4, (0, 0, 255), 1, cv.LINE_AA)
points.append((x, y))
else:
points.append(None)
for pair in POSE_PAIRS:
A, B = pair[0], pair[1]
if points[A] and points[B]:
cv2.line(frame_rgb, points[A], points[B], (0, 255, 255), 3, cv2.LINE_AA)
plt.figure(figsize=(20,20))
plt.imshow(frame_rgb)
测试图片：
输出图像：
我也尝试过不同的图像。但是，输出仍然与预期相差太远。
您能否建议我需要做的修改或在 python 和 openCV 中单独检测手部或全身检测的任何其他替代方法？预先感谢您的建议。
试试下面的代码
import cv2
import time
import numpy as np
protoFile = "hand/pose_deploy.prototxt"
weightsFile = "hand/pose_iter_102000.caffemodel"
nPoints = 22
POSE_PAIRS = [ [0,1],[1,2],[2,3],[3,4],[0,5],[5,6],[6,7],[7,8],[0,9],[9,10],[10,11],[11,12],[0,13],[13,14],[14,15],[15,16],[0,17],[17,18],[18,19],[19,20] ]
threshold = 0.2
video_file = "videoMis.mp4"
cap = cv2.VideoCapture(video_file)
hasFrame, frame = cap.read()
frameWidth = frame.shape[1]
frameHeight = frame.shape[0]
aspect_ratio = frameWidth/frameHeight
inHeight = 368
inWidth = int(((aspect_ratio*inHeight)*8)//8)
vid_writer = cv2.VideoWriter('output.avi',cv2.VideoWriter_fourcc('M','J','P','G'), 15, (frame.shape[1],frame.shape[0]))
net = cv2.dnn.readNetFromCaffe(protoFile, weightsFile)
k = 0
while 1:
k+=1
t = time.time()
hasFrame, frame = cap.read()
frameCopy = np.copy(frame)
if not hasFrame:
cv2.waitKey()
break
inpBlob = cv2.dnn.blobFromImage(frame, 1.0 / 255, (inWidth, inHeight),
(0, 0, 0), swapRB=False, crop=False)
net.setInput(inpBlob)
output = net.forward()
print("forward = {}".format(time.time() - t))
# Empty list to store the detected keypoints
points = []
for i in range(nPoints):
# confidence map of corresponding body's part.
probMap = output[0, i, :, :]
probMap = cv2.resize(probMap, (frameWidth, frameHeight))
# Find global maxima of the probMap.
minVal, prob, minLoc, point = cv2.minMaxLoc(probMap)
if prob > threshold :
cv2.circle(frameCopy, (int(point[0]), int(point[1])), 6, (0, 255, 255), thickness=-1, lineType=cv2.FILLED)
cv2.putText(frameCopy, "{}".format(i), (int(point[0]), int(point[1])), cv2.FONT_HERSHEY_SIMPLEX, .8, (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(point[0]), int(point[1])))
else :
points.append(None)
# Draw Skeleton
for pair in POSE_PAIRS:
partA = pair[0]
partB = pair[1]
if points[partA] and points[partB]:
cv2.line(frame, points[partA], points[partB], (0, 255, 255), 2, lineType=cv2.LINE_AA)
cv2.circle(frame, points[partA], 5, (0, 0, 255), thickness=-1, lineType=cv2.FILLED)
cv2.circle(frame, points[partB], 5, (0, 0, 255), thickness=-1, lineType=cv2.FILLED)
print("Time Taken for frame = {}".format(time.time() - t))
# 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)
# cv2.putText(frame, "Hand Pose using OpenCV", (50, 50), cv2.FONT_HERSHEY_COMPLEX, 1, (255, 50, 0), 2, lineType=cv2.LINE_AA)
cv2.imshow('Output-Skeleton', frame)
# cv2.imwrite("video_output/{:03d}.jpg".format(k), frame)
key = cv2.waitKey(1)
if key == 27:
break
print("total = {}".format(time.time() - t))
vid_writer.write(frame)
vid_writer.release()
代码学分：https://learnopencv.com/hand-keypoint-detection-using-deep-learning-and-opencv/
单张图片可以试试下面的代码
from __future__ import division
import cv2
import time
import numpy as np
protoFile = "hand/pose_deploy.prototxt"
weightsFile = "hand/pose_iter_102000.caffemodel"
nPoints = 22
POSE_PAIRS = [ [0,1],[1,2],[2,3],[3,4],[0,5],[5,6],[6,7],[7,8],[0,9],[9,10],[10,11],[11,12],[0,13],[13,14],[14,15],[15,16],[0,17],[17,18],[18,19],[19,20] ]
net = cv2.dnn.readNetFromCaffe(protoFile, weightsFile)
frame = cv2.imread("image.jpg")
frameCopy = np.copy(frame)
frameWidth = frame.shape[1]
frameHeight = frame.shape[0]
aspect_ratio = frameWidth/frameHeight
threshold = 0.1
t = time.time()
# input image dimensions for the network
inHeight = 368
inWidth = int(((aspect_ratio*inHeight)*8)//8)
inpBlob = cv2.dnn.blobFromImage(frame, 1.0 / 255, (inWidth, inHeight), (0, 0, 0), swapRB=False, crop=False)
net.setInput(inpBlob)
output = net.forward()
print("time taken by network : {:.3f}".format(time.time() - t))
# Empty list to store the detected keypoints
points = []
for i in range(nPoints):
# confidence map of corresponding body's part.
probMap = output[0, i, :, :]
probMap = cv2.resize(probMap, (frameWidth, frameHeight))
# Find global maxima of the probMap.
minVal, prob, minLoc, point = cv2.minMaxLoc(probMap)
if prob > threshold :
cv2.circle(frameCopy, (int(point[0]), int(point[1])), 8, (0, 255, 255), thickness=-1, lineType=cv2.FILLED)
cv2.putText(frameCopy, "{}".format(i), (int(point[0]), int(point[1])), 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(point[0]), int(point[1])))
else :
points.append(None)
# Draw Skeleton
for pair in POSE_PAIRS:
partA = pair[0]
partB = pair[1]
if points[partA] and points[partB]:
cv2.line(frame, points[partA], points[partB], (0, 255, 255), 2)
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)
cv2.imshow('Output-Keypoints', frameCopy)
cv2.imshow('Output-Skeleton', frame)
cv2.imwrite('Output-Keypoints.jpg', frameCopy)
cv2.imwrite('Output-Skeleton.jpg', frame)
print("Total time taken : {:.3f}".format(time.time() - t))
cv2.waitKey(0)
我正在尝试使用 OpenPose 检测人手姿势，就像此视频 https://github.com/CMU-Perceptual-Computing-Lab/openpose/blob/master/.github/media/pose_face_hands.gif 中手部分给出的那样。我已经下载了 caffe 模型和 prototxt 文件。下面是我实现模型的代码。
import cv2
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
frame = cv2.imread("6.jpg")
frame_rgb=cv2.cvtColor(frame,cv2.COLOR_BGR2RGB)
plt.imshow(frame_rgb)
threshold = 0.025
input_width, input_height = 368, 368
nPoints = 22
POSE_PAIRS = [[0, 1], [1, 2], [2, 3], [3, 4], [0, 5], [5, 6], [6, 7], [7, 8], [0, 9],
[9, 10], [10, 11], [11, 12], [0, 13], [13, 14], [14, 15], [15, 16], [0, 17],
[17, 18], [18, 19], [19, 20]]
net = cv2.dnn.readNetFromCaffe('pose_deploy_hand.prototxt', 'pose_iter_102000.caffemodel')
net.setPreferableBackend(cv2.dnn.DNN_BACKEND_OPENCV)
net.setPreferableTarget(cv2.dnn.DNN_TARGET_OPENCL)
origin_h, origin_w = frame_rgb.shape[:2]
blob = cv2.dnn.blobFromImage(frame_rgb, 1.0 / 255, (input_width, input_height), 0, swapRB=False, crop=False)
net.setInput(blob)
detections = net.forward()
H = detections.shape[2]
W = detections.shape[3]
points = []
for i in range(nPoints):
probility_map = detections[0, i, :, :]
#
min_value, confidence, min_loc, point = cv2.minMaxLoc(probility_map)
#
x = int(origin_w * (point[0] / W))
y = int(origin_h * (point[1] / H))
if confidence > threshold:
cv2.circle(frame_rgb, (x, y), 6, (255, 255, 0), -1, cv2.FILLED)
#cv.putText(frame, "{}".format(i), (x, y-15), cv.FONT_HERSHEY_SIMPLEX, 0.4, (0, 0, 255), 1, cv.LINE_AA)
points.append((x, y))
else:
points.append(None)
for pair in POSE_PAIRS:
A, B = pair[0], pair[1]
if points[A] and points[B]:
cv2.line(frame_rgb, points[A], points[B], (0, 255, 255), 3, cv2.LINE_AA)
plt.figure(figsize=(20,20))
plt.imshow(frame_rgb)
测试图片：
输出图像：
我也尝试过不同的图像。但是，输出仍然与预期相差太远。
您能否建议我需要做的修改或在 python 和 openCV 中单独检测手部或全身检测的任何其他替代方法？预先感谢您的建议。
试试下面的代码
import cv2
import time
import numpy as np
protoFile = "hand/pose_deploy.prototxt"
weightsFile = "hand/pose_iter_102000.caffemodel"
nPoints = 22
POSE_PAIRS = [ [0,1],[1,2],[2,3],[3,4],[0,5],[5,6],[6,7],[7,8],[0,9],[9,10],[10,11],[11,12],[0,13],[13,14],[14,15],[15,16],[0,17],[17,18],[18,19],[19,20] ]
threshold = 0.2
video_file = "videoMis.mp4"
cap = cv2.VideoCapture(video_file)
hasFrame, frame = cap.read()
frameWidth = frame.shape[1]
frameHeight = frame.shape[0]
aspect_ratio = frameWidth/frameHeight
inHeight = 368
inWidth = int(((aspect_ratio*inHeight)*8)//8)
vid_writer = cv2.VideoWriter('output.avi',cv2.VideoWriter_fourcc('M','J','P','G'), 15, (frame.shape[1],frame.shape[0]))
net = cv2.dnn.readNetFromCaffe(protoFile, weightsFile)
k = 0
while 1:
k+=1
t = time.time()
hasFrame, frame = cap.read()
frameCopy = np.copy(frame)
if not hasFrame:
cv2.waitKey()
break
inpBlob = cv2.dnn.blobFromImage(frame, 1.0 / 255, (inWidth, inHeight),
(0, 0, 0), swapRB=False, crop=False)
net.setInput(inpBlob)
output = net.forward()
print("forward = {}".format(time.time() - t))
# Empty list to store the detected keypoints
points = []
for i in range(nPoints):
# confidence map of corresponding body's part.
probMap = output[0, i, :, :]
probMap = cv2.resize(probMap, (frameWidth, frameHeight))
# Find global maxima of the probMap.
minVal, prob, minLoc, point = cv2.minMaxLoc(probMap)
if prob > threshold :
cv2.circle(frameCopy, (int(point[0]), int(point[1])), 6, (0, 255, 255), thickness=-1, lineType=cv2.FILLED)
cv2.putText(frameCopy, "{}".format(i), (int(point[0]), int(point[1])), cv2.FONT_HERSHEY_SIMPLEX, .8, (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(point[0]), int(point[1])))
else :
points.append(None)
# Draw Skeleton
for pair in POSE_PAIRS:
partA = pair[0]
partB = pair[1]
if points[partA] and points[partB]:
cv2.line(frame, points[partA], points[partB], (0, 255, 255), 2, lineType=cv2.LINE_AA)
cv2.circle(frame, points[partA], 5, (0, 0, 255), thickness=-1, lineType=cv2.FILLED)
cv2.circle(frame, points[partB], 5, (0, 0, 255), thickness=-1, lineType=cv2.FILLED)
print("Time Taken for frame = {}".format(time.time() - t))
# 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)
# cv2.putText(frame, "Hand Pose using OpenCV", (50, 50), cv2.FONT_HERSHEY_COMPLEX, 1, (255, 50, 0), 2, lineType=cv2.LINE_AA)
cv2.imshow('Output-Skeleton', frame)
# cv2.imwrite("video_output/{:03d}.jpg".format(k), frame)
key = cv2.waitKey(1)
if key == 27:
break
print("total = {}".format(time.time() - t))
vid_writer.write(frame)
vid_writer.release()
代码学分：https://learnopencv.com/hand-keypoint-detection-using-deep-learning-and-opencv/
单张图片可以试试下面的代码
from __future__ import division
import cv2
import time
import numpy as np
protoFile = "hand/pose_deploy.prototxt"
weightsFile = "hand/pose_iter_102000.caffemodel"
nPoints = 22
POSE_PAIRS = [ [0,1],[1,2],[2,3],[3,4],[0,5],[5,6],[6,7],[7,8],[0,9],[9,10],[10,11],[11,12],[0,13],[13,14],[14,15],[15,16],[0,17],[17,18],[18,19],[19,20] ]
net = cv2.dnn.readNetFromCaffe(protoFile, weightsFile)
frame = cv2.imread("image.jpg")
frameCopy = np.copy(frame)
frameWidth = frame.shape[1]
frameHeight = frame.shape[0]
aspect_ratio = frameWidth/frameHeight
threshold = 0.1
t = time.time()
# input image dimensions for the network
inHeight = 368
inWidth = int(((aspect_ratio*inHeight)*8)//8)
inpBlob = cv2.dnn.blobFromImage(frame, 1.0 / 255, (inWidth, inHeight), (0, 0, 0), swapRB=False, crop=False)
net.setInput(inpBlob)
output = net.forward()
print("time taken by network : {:.3f}".format(time.time() - t))
# Empty list to store the detected keypoints
points = []
for i in range(nPoints):
# confidence map of corresponding body's part.
probMap = output[0, i, :, :]
probMap = cv2.resize(probMap, (frameWidth, frameHeight))
# Find global maxima of the probMap.
minVal, prob, minLoc, point = cv2.minMaxLoc(probMap)
if prob > threshold :
cv2.circle(frameCopy, (int(point[0]), int(point[1])), 8, (0, 255, 255), thickness=-1, lineType=cv2.FILLED)
cv2.putText(frameCopy, "{}".format(i), (int(point[0]), int(point[1])), 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(point[0]), int(point[1])))
else :
points.append(None)
# Draw Skeleton
for pair in POSE_PAIRS:
partA = pair[0]
partB = pair[1]
if points[partA] and points[partB]:
cv2.line(frame, points[partA], points[partB], (0, 255, 255), 2)
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)
cv2.imshow('Output-Keypoints', frameCopy)
cv2.imshow('Output-Skeleton', frame)
cv2.imwrite('Output-Keypoints.jpg', frameCopy)
cv2.imwrite('Output-Skeleton.jpg', frame)
print("Total time taken : {:.3f}".format(time.time() - t))
cv2.waitKey(0)