Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Added python files to class #525

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Added python files to class #525

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
95e351b
reorganised as a class
akshatgarg99 Dec 8, 2020
c000068
reorganised in classes
akshatgarg99 Dec 8, 2020
83958c9
added everything to a class
akshatgarg99 Dec 8, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
144 changes: 79 additions & 65 deletions HandPose/handPoseImage.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,69 +3,83 @@
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("right-frontal.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)
class HandPose:
def __init__(self, model, nPoints, pose_pair, input_source):
self.input_source = input_source # the input file name (index, if using a camera)
self.protofile, self.weightfile = model # model and weights for the neural network
self.nPoints = nPoints # number of key points
self.POSE_PAIRS = pose_pair
self.threshold = 0.1

def window_size(self, frame):
# to generate the input dimensions from the frame dimension generated by VideoCapture
frameWidth = frame.shape[1]
frameHeight = frame.shape[0]
aspect_ratio = frameWidth / frameHeight
inHeight = 368
inWidth = int(((aspect_ratio * inHeight) * 8) // 8)

return inHeight, inWidth # input dimensions

def draw_skeleton(self, frame, frameCopy, output):
# take the video frame and the output generated by the model
# and create the skeleton using the pairs defined in sef.POSE_PAIR
points = []
for i in range(self.nPoints):
# confidence map of corresponding body's part.
probMap = output[0, i, :, :] # extract the probability map for the ith feature
probMap = cv2.resize(probMap, (frame.shape[1], frame.shape[0]))
# Find global maxima of the probMap.
minVal, prob, minLoc, point = cv2.minMaxLoc(probMap)

if prob > self.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, 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)

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))
# draw lines connecting the points of the pair and draw the circles
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)

return frame, frameCopy

def forward(self):
frame = cv2.imread(self.input_source)
frameCopy = np.copy(frame)
inHeight, inWidth = self.window_size(frame)
net = cv2.dnn.readNetFromCaffe(self.protofile, self.weightfile)
t = time.time()
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))
frame, frameCopy = self.draw_skeleton(frame, frameCopy, output)
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)


if __name__ == '__main__':
input_source = "right-frontal.jpg"
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]]
gen = HandPose((protoFile, weightsFile), nPoints, POSE_PAIRS, input_source=input_source)
gen.forward()
193 changes: 106 additions & 87 deletions HandPose/handPoseVideo.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,90 +3,109 @@
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


input_source = "asl.mp4"
cap = cv2.VideoCapture(input_source)
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()
class HandPose:
def __init__(self, model, nPoints, pose_pair, input_source):
self.input_source = input_source # the input file name (index, if using a camera)
self.protofile, self.weightfile = model # model and weights for the neural network
self.nPoints = nPoints # number of key points
self.POSE_PAIRS = pose_pair
self.threshold = 0.2

def window_size(self, frame):
# to generate the input dimensions from the frame dimension generated by VideoCapture
frameWidth = frame.shape[1]
frameHeight = frame.shape[0]
aspect_ratio = frameWidth / frameHeight
inHeight = 368
inWidth = int(((aspect_ratio * inHeight) * 8) // 8)

return inHeight, inWidth # input dimensions

def draw_skeleton(self, frame, frameCopy, output):
# take the video frame and the output generated by the model
# and create the skeleton using the pairs defined in sef.POSE_PAIR
points = []
for i in range(self.nPoints):
# confidence map of corresponding body's part.
probMap = output[0, i, :, :] # extract the probability map for the ith feature
probMap = cv2.resize(probMap, (frame.shape[1], frame.shape[0]))
# Find global maxima of the probMap.
minVal, prob, minLoc, point = cv2.minMaxLoc(probMap)

if prob > self.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)

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)
# draw lines connecting the points of the pair and draw the circles
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)

return frame, frameCopy

def forward(self):
cap = cv2.VideoCapture(self.input_source)
hasframe, frame = cap.read()

# generate input dimensions
inHeight, inWidth = self.window_size(frame)
# generate model
net = cv2.dnn.readNetFromCaffe(self.protofile, self.weightfile)
vid_writer = cv2.VideoWriter('output.avi', cv2.VideoWriter_fourcc('M', 'J', 'P', 'G'), 15,
(frame.shape[1], frame.shape[0]))
k = 0

while True:
k = k + 1
t = time.time()
hasFrame, frame = cap.read()
frameCopy = np.copy(frame)

if not hasFrame:
cv2.waitKey()
break

# if cv2.waitKey(1) & 0xFF == 27:
# break

inpBlob = cv2.dnn.blobFromImage(frame, 1.0 / 255, (inWidth, inHeight), (0, 0, 0),
swapRB=False, crop=False)
net.setInput(inpBlob)
# forward propagation
output = net.forward()
print("forward = {}".format(time.time() - t))
frame, frameCopy = self.draw_skeleton(frame, frameCopy, output)
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)
key = cv2.waitKey(1)
if key == 27:
break

print("total = {}".format(time.time() - t))
vid_writer.write(frame)

vid_writer.release()


if __name__ == '__main__':
input_source = "asl.mp4"
# input_source = 0 if using local camera
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]]
gen = HandPose((protoFile, weightsFile), nPoints, POSE_PAIRS, input_source=input_source)
gen.forward()