def on_message(client, userdata, msg):
#print(msg.topic+" "+str(msg.payload))
#print(msg.payload)
if msg.payload in commands:
command_obtained = True
info = msg.payload
print('Get control signal:', info)
if info == 'Rec':
cv2.destroyAllWindows()
control = False
flag_f1 = True
x_f1 = 0
x_f2 = 0
y_f1 = 0
y_f2 = 0
direc = str(counter) + 'imageRec.jpg'
elif info == 'Con':
control = True
direc = str(counter) + 'imageCon.jpg'
else:
direc = str(counter) + 'image.jpg'
#cv2.imwrite(direc,img)
counter += 1
elif command_obtained == True and msg.payload not in commands:
image_obtained = True
with open(direc + ".jpg", "wb") as fh:
fh.write(base64.decodebytes(msg.payload))
if image_obtained == True and command_obtained == True:
image_obtained, command_obtained = False, False
if not control:
# reset directions
print('Doing classification.')
test_set = []
img_crop, img_bk = generate_crop(direc, 210)
cv2.imwrite('2nd_step.jpg', img_crop)
img = image.load_img('2nd_step.jpg', target_size=(224, 224))
img_data = image.img_to_array(img)
img_data = np.expand_dims(img_data, axis=0)
img_data = preprocess_input(img_data)
vgg16_feature = model.predict(img_data)
test_set.append(np.ndarray.tolist(vgg16_feature[0]))
if test_set:
predict_target = clf.predict(test_set)
print(predict_target.shape)
print(predict_target.size)
predict_prob = clf.predict_proba(test_set)
#print(correct_tag)
print('predict results.')
print(clf.classes_)
print(predict_prob)
prob = predict_prob[0]
orderedIndex = sorted(range(len(prob)),
key=lambda k: prob[k],
reverse=True)
print(orderedIndex)
print("appliances in order")
validNum = 0
validNum = len([i for i in prob if i > 0.075]) - 1
print('There are valid object #', validNum)
# get all the results in order and loop thru
print(predict_target)
predict_target = predict_target[0]
for indexCount in orderedIndex:
print(clf.classes_[indexCount], end=" ")
#print(predict_target)
applianceTuple = applianceDict[predict_target]
indexCount = 0
cur_time = time.time()
prev_time = time.time()
while True:
# print('in the loop')
# print(indexCount)
print("orderedList ",
clf.classes_[orderedIndex[indexCount]])
# applianceClient=callAppliace(clf.classes_[orderedIndex[indexCount]],applianceTuple[1])
# controlAppliance(applianceClient)
info = connect.recv(1024)
info = info.decode()
if info == 'ACK':
print(info)
obj = clf.classes_[orderedIndex[indexCount]]
break
elif info == '':
print('Interrupted.')
break
indexCount += 1
if indexCount > 5:
indexCount = 0
#prev_time = time.time()
# break
# except:
# info = ''
#applianceClient=callAppliace(predict_target,applianceTuple[1])
#controlAppliance(applianceClient)
#print('probability.')
#print(clf.classes_)
#print(predict_prob)
# control = True
else:
# dir_f1 = dir_f2
img_bk, k, top, mid, control_signal = finger_control_f(
direc, 220, 5, -70, 3)
height, width = img_bk.shape
if flag_f1:
if control_signal == 'Down':
pyautogui.press('k')
connect.sendall(b'Doing Con.')
continue
if top < 20:
pyautogui.press('i')
connect.sendall(b'Doing Con.')
continue
elif mid < 20:
pyautogui.press('j')
connect.sendall(b'Doing Con.')
continue
elif (width - mid) < 20:
pyautogui.press('l')
connect.sendall(b'Doing Con.')
continue
else:
pyautogui.press('r')
x_f1 = mid
y_f1 = top
if obj == 'Printer':
pyautogui.press('a')
elif obj == 'Coffee maker':
pyautogui.press('b')
elif obj == 'TV':
pyautogui.press('c')
elif obj == 'Door':
pyautogui.press('d')
elif obj == 'Minotor':
pyautogui.press('e')
x_f2 = mid
y_f2 = top
print('slope is ', k, 'top y value is ', top, ' and mid value is ',
mid)
print('control signal is', control_signal)
print('done finger detection', time.time() - time_in)
time_in = time.time()
# quite
if control_signal == 'Down':
pyautogui.press('enter')
connect.sendall(b'Stop Con.')
continue
# print('go down')
# pyautogui.press('down')
# time.sleep(0.4)
# connect.sendall(b'Doing Con.')
else:
# print('control object is',obj)
# height,width = img_bk.shape
slope = height / width
if (control_scheme == '1'):
# Control Part - video
xx_thres = 20
yy_thres = 15
# y axis
delta_y_f = y_f2 - y_f1
delta_x_f = x_f2 - x_f1
steps_y = delta_y_f / 10
steps_x = delta_x_f / 10
if steps_x < 0:
for x_type in range(abs(int(steps_x))):
pyautogui.press('z') # left
elif steps_x > 0:
for x_type in range(abs(int(steps_x))):
pyautogui.press('x') #right
if steps_y < 0:
for y_type in range(abs(int(steps_y))):
pyautogui.press('n') #up
elif steps_y > 0:
for y_type in range(abs(int(steps_y))):
pyautogui.press('m') #down
else:
pyautogui.press('p') #middle
pyautogui.press('enter')
if (delta_x_f > xx_thres or delta_x_f < -xx_thres) or (
delta_y_f > yy_thres or delta_y_f < -yy_thres):
# left
if delta_y_f < -slope * delta_x_f and delta_y_f > slope * delta_x_f:
print('go left')
pyautogui.press('left')
# right
elif delta_y_f > -slope * delta_x_f and delta_y_f < slope * delta_x_f:
print('go right')
pyautogui.press('right')
elif delta_y_f > -slope * delta_x_f and delta_y_f > slope * delta_x_f:
print('go down')
pyautogui.press('down')
elif delta_y_f < -slope * delta_x_f and delta_y_f < slope * delta_x_f:
print('go up')
pyautogui.press('up')
else:
print('STAY.')
pyautogui.press('v')
# else:
# print('y stay')
# # x axis
# delta_x_f = x_f2 - x_f1
# if delta_x_f > xx_thres:
# print('go right')
# pyautogui.press('right')
# elif delta_x_f < -xx_thres:
# print('go left')
# pyautogui.press('left')
# else:
# print('x stay')
elif (control_scheme == '2'):
# Control Part - video
if flag_f1:
x0, y0 = pyautogui.size()
pyautogui.moveTo(x0 / 2, y0 / 2)
delta_y_f = (y_f2 - y_f1) * 5
delta_x_f = (x_f2 - x_f1) * 5
pyautogui.moveTo(delta_x_f + x0 / 2, delta_y_f + y0 / 2)
elif (control_scheme == '3'):
# Control Part - slides
# y axis
delta_y_f = y_f2 - y_f1
if delta_y_f > 15:
print('go down')
pyautogui.press('down')
elif delta_y_f < -15:
print('go up')
pyautogui.press('up')
else:
print('no control')
control_scheme = input(
'Which control:(1-video,2-mouse,3-slides)')
connect.sendall(b'Stop Con.')
continue
# ack it is done
time.sleep(0.05)
connect.sendall(b'Doing Con.')
# show the threshold line
# for pix_i in range(height-1):
# img_bk[pix_i, min(x_f1+xx_thres,width-1)] = 127
# img_bk[pix_i, max(x_f1-xx_thres,0)] = 127
# for pix_j in range(width-1):
# img_bk[max(y_f1-yy_thres,0),pix_j] = 127
# img_bk[min(y_f1+yy_thres,height-1),pix_j] = 127
# disable flag
flag_f1 = False
cv2.imshow('Binary Image', img_bk)
cv2.waitKey(5)
def on_message(client, userdata, msg):
global obj, command_in, down_confirm,x_ref,y_ref, k_ref, mid_ref
#print(msg.topic)
if msg.topic == 'image':
#print(len(msg.payload))
#print('image transmitted')
t1 = time.time()
with open('1.png', "wb") as fh:
fh.write(base64.decodebytes(msg.payload))
info=connect.recv(1024)
info = info.decode()
print('Get control signal:',info)
if info == 'rec':
command_in = False
down_confirm = False
x_ref = None
y_ref = None
k_ref = None
print('Doing classification.')
test_set = []
img_crop,img_bk = generate_crop('1.png',220)
img_bk,k,top,mid,control_signal,x_mid = finger_control_f('1.png',binary_thre, 5,-70,3)
#cv2.imshow('Binary Image', img_bk)
cv2.waitKey(3)
cv2.imwrite('2nd_step.jpg',img_crop)
img = image.load_img('2nd_step.jpg', target_size=(224, 224))
img_data = image.img_to_array(img)
img_data = np.expand_dims(img_data, axis=0)
img_data = preprocess_input(img_data)
vgg16_feature = model.predict(img_data)
test_set.append(np.ndarray.tolist(vgg16_feature[0]))
#print(test_set)
if test_set:
predict_target = clf.predict(test_set)
print(predict_target.shape)
print(predict_target.size)
predict_prob = clf.predict_proba(test_set)
#print(correct_tag)
print('predict results.')
print(clf.classes_)
print(predict_prob)
prob = predict_prob[0]
orderedIndex=sorted(range(len(prob)), key=lambda k: prob[k], reverse=True)
print(orderedIndex)
print("appliances in order")
validNum = 0
validNum = len([i for i in prob if i > 0.075]) - 1
print('There are valid object #', validNum)
# get all the results in order and loop thru
print(predict_target)
predict_target=predict_target[0]
for indexCount in orderedIndex:
print(clf.classes_[indexCount],end=" ")
indexCount = 0
while True:
print("orderedList ",clf.classes_[orderedIndex[indexCount]])
info_2=connect.recv(1024)
info_2 = info_2.decode()
if info_2 == 'ACK':
print(info_2)
obj = clf.classes_[orderedIndex[indexCount]]
break
elif info_2 == '':
print('Interrupted.')
break
indexCount += 1
if indexCount > 5:
indexCount = 0
connect.sendall(b'ready')
time.sleep(0.5)
connect.sendall(b'Doing Con.')
elif info == 'con':
t2 = time.time()
#print(obj)
#print('Con coming soon.')
img_bk,k,top,mid,control_signal,x_mid = finger_control_f('1.png',binary_thre, 5,-70,3)
cv2.imwrite('../binary.png',img_bk)
height,width = img_bk.shape
t3 = time.time()
#print(top,mid)
#print(k,x_mid)
if obj == 'Printer':
pyautogui.press('a')
elif obj =='Coffee maker':
pyautogui.press('b')
elif obj =='TV':
pyautogui.press('c')
elif obj =='Door':
pyautogui.press('d')
elif obj =='Minotor':
pyautogui.press('e')
#print('slope is ',k,'top y value is ',top,' and mid value is ', mid)
#print('control signal is', control_signal)
if not x_ref or not y_ref or not k_ref:
x_ref = mid
y_ref = top
mid_ref = x_mid
if mid == x_mid:
direction = np.pi/2 - 0.01
#print(top/(mid-x_mid))
else:
direction=np.arctan(top/float((mid-x_mid)))
k_ref = direction
connect.sendall(b'Doing Con.')
else:
# quite
if control_signal == 'Down':
print('down')
pyautogui.press('m')
if command_in:
down_confirm = True
time.sleep(0.01)
connect.sendall(b'Doing Con.')
#print(down_confirm)
else:
command_in = True
print('up')
pyautogui.press('n')
if mid == x_mid:
direction = k_ref
#print(top/(mid-x_mid))
else:
direction=np.arctan(top/float((mid-x_mid)))
print(direction - k_ref)
print(x_mid - mid_ref)
if (x_mid - mid_ref > width//5) or (direction - k_ref > size):
print('block 4')
block = 8
pyautogui.press('8')
elif (x_mid - mid_ref < -width // 5) or (direction - k_ref < -size):
print('block 1')
block = 2
pyautogui.press('2')
elif (direction - k_ref < size) :
print('block 2')
block = 4
pyautogui.press('4')
elif (direction - k_ref > -size):
print('block 3')
block = 6
pyautogui.press('6')
'''
elif x_mid > width*1.15//2 and x_mid < width*3.1//4:
print('block 3')
block = 6
pyautogui.press('6')
elif x_mid < width*1.05// 2 and x_mid > width *7//20 :
print('block 2')
block = 4
pyautogui.press('4')
'''
'''
if direction > 0 and direction < np.pi/2 - size:
print('block 4')
block = 8
pyautogui.press('8')
elif direction > np.pi/2 - size and direction < np.pi/2:
print('block 3')
block = 6
pyautogui.press('6')
elif direction < 0 and direction > - np.pi/2 + size:
print('block 1')
block = 2
pyautogui.press('2')
elif direction < -np.pi/2 + size:
print('block 2')
block = 4
pyautogui.press('4')
'''
#print('here')
#print(down_confirm)
if down_confirm == True:
down_confirm = False
command_in = False
#connect.sendall(b'Stop Con.')
connect.sendall(b'Doing Con.')
else:
connect.sendall(b'Doing Con.')
# Rewind the stream, open it as an image with PIL and do some
# processing on it
image_stream.seek(0) # seek(0) - the start of the file
file_bytes = np.asarray(bytearray(image_stream.read()), dtype=np.uint8)
img = cv2.imdecode(file_bytes, cv2.IMREAD_COLOR)
direc = 'Raw_Images/' + str(counter) + 'image.jpg'
cv2.imwrite(direc, img)
counter += 1
#img = generate_crop(file_path,240)
if not control:
test_set = []
img_crop, img_bk = generate_crop(direc, 220)
cv2.imwrite('2nd_step.jpg', img_crop)
img = image.load_img('2nd_step.jpg', target_size=(224, 224))
img_data = image.img_to_array(img)
img_data = np.expand_dims(img_data, axis=0)
img_data = preprocess_input(img_data)
vgg16_feature = model.predict(img_data)
test_set.append(np.ndarray.tolist(vgg16_feature[0]))
if test_set:
predict_target = clf.predict(test_set)
print(predict_target.shape)
print(predict_target.size)
predict_prob = clf.predict_proba(test_set)
def on_message(client, userdata, msg):
#print(msg.topic)
if msg.topic == 'image':
#print(len(msg.payload))
#print('image transmitted')
with open('1.png', "wb") as fh:
fh.write(base64.decodebytes(msg.payload))
info = connect.recv(1024)
info = info.decode()
print('Get control signal:', info)
if info == 'rec':
print('Doing classification.')
test_set = []
img_crop, img_bk = generate_crop('1.png', 220)
img_bk, k, top, mid, control_signal = finger_control_f(
'1.png', 200, 5, -70, 3)
x_f1 = mid
y_f1 = top
#cv2.imshow('Binary Image', img_bk)
cv2.waitKey(5)
cv2.imwrite('2nd_step.jpg', img_crop)
img = image.load_img('2nd_step.jpg', target_size=(224, 224))
img_data = image.img_to_array(img)
img_data = np.expand_dims(img_data, axis=0)
img_data = preprocess_input(img_data)
vgg16_feature = model.predict(img_data)
test_set.append(np.ndarray.tolist(vgg16_feature[0]))
if test_set:
predict_target = clf.predict(test_set)
print(predict_target.shape)
print(predict_target.size)
predict_prob = clf.predict_proba(test_set)
#print(correct_tag)
print('predict results.')
print(clf.classes_)
print(predict_prob)
prob = predict_prob[0]
orderedIndex = sorted(range(len(prob)),
key=lambda k: prob[k],
reverse=True)
print(orderedIndex)
print("appliances in order")
validNum = 0
validNum = len([i for i in prob if i > 0.075]) - 1
print('There are valid object #', validNum)
# get all the results in order and loop thru
print(predict_target)
predict_target = predict_target[0]
for indexCount in orderedIndex:
print(clf.classes_[indexCount], end=" ")
#print(predict_target)
applianceTuple = applianceDict[predict_target]
indexCount = 0
while True:
print("orderedList ",
clf.classes_[orderedIndex[indexCount]])
info_2 = connect.recv(1024)
info_2 = info_2.decode()
if info_2 == 'ACK':
print(info_2)
obj = clf.classes_[orderedIndex[indexCount]]
break
elif info_2 == '':
print('Interrupted.')
break
indexCount += 1
if indexCount > 5:
indexCount = 0
elif info == 'con':
print('Con coming soon.')
img_bk, k, top, mid, control_signal = finger_control_f(
direc, 220, 5, -70, 3)
height, width = img_bk.shape
pyautogui.press('r')
x_f1 = mid
y_f1 = top
if obj == 'Printer':
pyautogui.press('a')
elif obj == 'Coffee maker':
pyautogui.press('b')
elif obj == 'TV':
pyautogui.press('c')
elif obj == 'Door':
pyautogui.press('d')
elif obj == 'Minotor':
pyautogui.press('e')
x_f2 = mid
y_f2 = top
print('slope is ', k, 'top y value is ', top, ' and mid value is ',
mid)
print('control signal is', control_signal)
#print('done finger detection',time.time() - time_in)
time_in = time.time()
# quite
if control_signal == 'Down':
pyautogui.press('enter')
connect.sendall(b'Stop Con.')
else:
slope = height / width
if (control_scheme == '1'):
xx_thres = 20
yy_thres = 15
# y axis
delta_y_f = y_f2 - y_f1
delta_x_f = x_f2 - x_f1
steps_y = delta_y_f / 10
steps_x = delta_x_f / 10
if steps_x < 0:
for x_type in range(abs(int(steps_x))):
pyautogui.press('z') # left
elif steps_x > 0:
for x_type in range(abs(int(steps_x))):
pyautogui.press('x') #right
if steps_y < 0:
for y_type in range(abs(int(steps_y))):
pyautogui.press('n') #up
elif steps_y > 0:
for y_type in range(abs(int(steps_y))):
pyautogui.press('m') #down
else:
pyautogui.press('p') #middle
pyautogui.press('enter')
if (delta_x_f > xx_thres or delta_x_f < -xx_thres) or (
delta_y_f > yy_thres or delta_y_f < -yy_thres):
# left
if delta_y_f < -slope * delta_x_f and delta_y_f > slope * delta_x_f:
print('go left')
pyautogui.press('left')
# right
elif delta_y_f > -slope * delta_x_f and delta_y_f < slope * delta_x_f:
print('go right')
pyautogui.press('right')
elif delta_y_f > -slope * delta_x_f and delta_y_f > slope * delta_x_f:
print('go down')
pyautogui.press('down')
elif delta_y_f < -slope * delta_x_f and delta_y_f < slope * delta_x_f:
print('go up')
pyautogui.press('up')
else:
print('STAY.')
pyautogui.press('v')
time.sleep(0.05)
connect.sendall(b'Doing Con.')
cv2.waitKey(2)
def on_message(client, userdata, msg):
print(msg.topic)
if msg.topic == "confirm_img":
ack_info = msg.payload.decode('utf-8')
elif 'command' in msg.topic:
print('command recognized')
info = msg.payload.decode('utf-8')
print(info == 'rec')
if info == 'rec':
print('entered')
cv2.destroyAllWindows()
control = False
flag_f1 = False
# 180,135
x_f1 = 60
x_f2 = 0
y_f1 = 20
y_f2 = 0
direc = str(counter) + 'imageRec.png'
# reset directions
print('Doing classification.')
test_set = []
img_crop, img_bk = generate_crop(direc, 220)
img_bk, k, top, mid, control_signal = finger_control_f(
direc, 200, 5, -70, 3)
x_f1 = mid
y_f1 = top
cv2.imshow('Binary Image', img_bk)
cv2.waitKey(5)
cv2.imwrite('2nd_step.png', img_crop)
img = image.load_img('2nd_step.png', target_size=(224, 224))
img_data = image.img_to_array(img)
img_data = np.expand_dims(img_data, axis=0)
img_data = preprocess_input(img_data)
vgg16_feature = model.predict(img_data)
test_set.append(np.ndarray.tolist(vgg16_feature[0]))
if test_set:
predict_target = clf.predict(test_set)
print(predict_target.shape)
print(predict_target.size)
predict_prob = clf.predict_proba(test_set)
#print(correct_tag)
print('predict results.')
print(clf.classes_)
print(predict_prob)
prob = predict_prob[0]
orderedIndex = sorted(range(len(prob)),
key=lambda k: prob[k],
reverse=True)
print(orderedIndex)
print("appliances in order")
validNum = 0
validNum = len([i for i in prob if i > 0.075]) - 1
print('There are valid object #', validNum)
# get all the results in order and loop thru
print(predict_target)
predict_target = predict_target[0]
for indexCount in orderedIndex:
print(clf.classes_[indexCount], end=" ")
#print(predict_target)
applianceTuple = applianceDict[predict_target]
indexCount = 0
while True:
print("orderedList ",
clf.classes_[orderedIndex[indexCount]])
if ack_info == 'ACK':
print(ack_info)
obj = clf.classes_[orderedIndex[indexCount]]
break
elif ack_info == '':
print('Interrupted.')
break
indexCount += 1
if indexCount > 5:
indexCount = 0
elif info == 'con':
print('con part coming soon.')
else:
direc = str(counter) + 'image.png'
counter += 1
elif msg.topic == 'image':
print(len(msg.payload))
print('image transmitted')
with open('1.png', "wb") as fh:
fh.write(base64.decodebytes(msg.payload))
def on_message(client, userdata, msg):
global obj, command_in, down_confirm, x_ref, y_ref, k_ref, mid_ref
if msg.topic == 'image':
t1 = time.time()
print("message received time = " + str(t1))
with open('1.png', "wb") as fh:
fh.write(base64.decodebytes(msg.payload))
info = connect.recv(1024)
info = info.decode()
print('Get control signal:', info)
#doesn't matter from here
if info == 'rec':
command_in = False
down_confirm = False
x_ref = None
y_ref = None
k_ref = None
print('Doing classification.')
test_set = []
img_crop, img_bk = generate_crop('1.png', 220)
#
img_bk, k, top, mid, control_signal, x_mid = finger_control_f(
'1.png', binary_thre, 5, -70, 3)
#cv2.imshow('Binary Image', img_bk)
cv2.waitKey(3)
cv2.imwrite('2nd_step.jpg', img_crop)
img = image.load_img('2nd_step.jpg', target_size=(224, 224))
img_data = image.img_to_array(img)
img_data = np.expand_dims(img_data, axis=0)
img_data = preprocess_input(img_data)
vgg16_feature = model.predict(img_data)
test_set.append(np.ndarray.tolist(vgg16_feature[0]))
#print(test_set)
if test_set:
predict_target = clf.predict(test_set)
print(predict_target.shape)
print(predict_target.size)
predict_prob = clf.predict_proba(test_set)
#print(correct_tag)
print('predict results.')
print(clf.classes_)
print(predict_prob)
prob = predict_prob[0]
orderedIndex = sorted(range(len(prob)),
key=lambda k: prob[k],
reverse=True)
print(orderedIndex)
print("appliances in order")
validNum = 0
validNum = len([i for i in prob if i > 0.075]) - 1
print('There are valid object #', validNum)
# get all the results in order and loop thru
print(predict_target)
predict_target = predict_target[0]
for indexCount in orderedIndex:
print(clf.classes_[indexCount], end=" ")
indexCount = 0
while True:
print("orderedList ",
clf.classes_[orderedIndex[indexCount]])
info_2 = connect.recv(1024)
info_2 = info_2.decode()
if info_2 == 'ACK':
print(info_2)
obj = clf.classes_[orderedIndex[indexCount]]
break
elif info_2 == '':
print('Interrupted.')
break
indexCount += 1
if indexCount > 5:
indexCount = 0
connect.sendall(b'ready')
time.sleep(0.5)
connect.sendall(b'Doing Con.')
#don't care up until here
elif info == 'con':
t2 = time.time()
#print(obj)
#print('Con coming soon.')
#img_bk is just image itself
#top,mid is the coord of fingertip
#xmid is the intercept that slope makes with frame
img_bk, k, top, mid, control_signal, x_mid = finger_control_f(
'1.png', binary_thre, 5, -70, 3)
cv2.imwrite('../binary.png', img_bk)
height, width = img_bk.shape
t3 = time.time()
#print(top,mid)
#print(k,x_mid)
if obj == 'Printer':
pyautogui.press('a')
elif obj == 'Coffee maker':
pyautogui.press('b')
elif obj == 'TV':
pyautogui.press('c')
elif obj == 'Door':
pyautogui.press('d')
elif obj == 'Minotor':
pyautogui.press('e')
#print('slope is ',k,'top y value is ',top,' and mid value is ', mid)
#print('control signal is', control_signal)
##############################
#creating reference photo and compares future images to reference image
if not x_ref or not y_ref or not k_ref:
x_ref = mid
y_ref = top
mid_ref = x_mid
if mid == x_mid:
direction = np.pi / 2 - 0.01
#print(top/(mid-x_mid))
else:
direction = np.arctan(top / float((mid - x_mid)))
k_ref = direction
connect.sendall(b'Doing Con.')
else:
#if no finger, then sends a "down" flag
# quite
if control_signal == 'Down':
print('down')
pyautogui.press('m')
if command_in:
down_confirm = True
time.sleep(0.01)
connect.sendall(b'Doing Con.')
#print(down_confirm)
#####
else:
command_in = True
print('up')
pyautogui.press('n')
if mid == x_mid:
direction = k_ref
#print(top/(mid-x_mid))
else:
direction = np.arctan(top / float((mid - x_mid)))
print(direction - k_ref)
print(x_mid - mid_ref)
#mid_ref is xmid of the reference image
#k_ref = direction is the slope
#"//5" returns the integer digit of the width / 5
#if xmid coord - midref bigger than width /5
#width is 224 for this
#maybe don't include the midref calculations? Moving xmid does not necessarily mean they are pointing at that box
if (x_mid - mid_ref > width // 5) or (direction - k_ref >
size):
print('block 4')
block = 8
pyautogui.press('8')
elif (x_mid - mid_ref < -width // 5) or (direction - k_ref
< -size):
print('block 1')
block = 2
pyautogui.press('2')
elif (direction - k_ref < size):
print('block 2')
block = 4
pyautogui.press('4')
elif (direction - k_ref > -size):
print('block 3')
block = 6
pyautogui.press('6')
#### revise this part
#trying to integrate using the slope of finger and finger mid to indicate block correctly
#direction is angle from xmid to top,mid
#quadrant 4 is actually left side
#size is alpha from the diagram
#add time.sleep(time) only to server
if down_confirm == True:
down_confirm = False
command_in = False
#connect.sendall(b'Stop Con.')
connect.sendall(b'Doing Con.')
else:
connect.sendall(b'Doing Con.')
if subdir.partition('/')[-1] == '':
continue
correct_tag = subdir.partition('/')[-1]
labels.append(correct_tag)
#print(correct_tag)
print('Now in the folder', subdir.partition('/')[-1])
files_size = 0
counter = 0
for i, file in enumerate(files):
file_path = os.path.join(subdir, file)
if 'jpg' in file_path or 'JPG' in file_path or 'Screen Shot' in file_path:
total_img_process += 1
files_size += 1
print('\nImage: %s' % (file_path))
img_crop, img_bk = generate_crop(file_path, 220)
'''
height,width,channel = img_crop.shape
for line in range(height):
for pixel in range(width):
#print((line,pixel),(img_1[line,pixel][1],img_2[line,pixel][1],max([img_1[line,pixel][1],img_2[line,pixel][1]])-min([img_1[line,pixel][1],img_2[line,pixel][1]])))
if img_crop[line,pixel][2] > abs(red_bias):
img_crop[line,pixel][2] += red_bias
else:
img_crop[line,pixel][2] = 0
if img_crop[line,pixel][0] > abs(blue_bias):
img_crop[line,pixel][0] += blue_bias
else:
img_crop[line,pixel][0] = 0