def locate_thumbnail(thumbnail_filename, source_filename, display=False, save_visualization=False,
save_reconstruction=False, reconstruction_format="jpg"):
thumbnail_basename, thumbnail_image = open_image(thumbnail_filename)
source_basename, source_image = open_image(source_filename)
logging.info("Attempting to locate %s within %s", thumbnail_filename, source_filename)
kp_pairs = match_images(thumbnail_image, source_image)
if len(kp_pairs) >= 4:
title = "Found %d matches" % len(kp_pairs)
logging.info(title)
H, mask = find_homography(kp_pairs)
new_thumbnail, corners, rotation = reconstruct_thumbnail(thumbnail_image, source_image, kp_pairs, H)
print(json.dumps({
"master": {
"source": source_filename,
"dimensions": {
"height": source_image.shape[0],
"width": source_image.shape[1],
}
},
"thumbnail": {
"source": thumbnail_filename,
"dimensions": {
"height": thumbnail_image.shape[0],
"width": thumbnail_image.shape[1],
}
},
"bounding_box": {
"height": corners[0][1] - corners[0][0],
"width": corners[1][1] - corners[1][0],
"x": corners[1][0],
"y": corners[0][0],
},
"rotation_degrees": rotation
}))
if save_reconstruction:
new_filename = "%s.reconstructed.%s" % (thumbnail_basename, reconstruction_format)
cv2.imwrite(new_filename, new_thumbnail)
logging.info("Saved reconstructed thumbnail %s", new_filename)
else:
logging.warning("Found only %d matches; skipping reconstruction", len(kp_pairs))
new_thumbnail = corners = H = mask = None
if display or save_visualization:
vis_image = visualize_matches(source_image, thumbnail_image, new_thumbnail, corners, kp_pairs, mask)
if save_visualization:
vis_filename = "%s.visualized%s" % os.path.splitext(thumbnail_filename)
cv2.imwrite(vis_filename, vis_image)
logging.info("Saved match visualization %s", vis_filename)
if display:
cv2.imshow(title, vis_image)
cv2.waitKey()
cv2.destroyAllWindows()
def main():
for fname in glob("left/*/*/ein/sceneModel/model.yml"):
print fname
f = open(fname)
lines = []
# ignore the %YAML:1.0, because the python parser doesn't handle 1.0.
f.readline()
for line in f:
# for some reason the python parser doesn't like this line either.
if "background_pose" in line:
continue
lines.append(line)
data = "\n".join(lines)
ymlobject = yaml.load(data)
#print ymlobject
scene = ymlobject["Scene"]
observed_map = GaussianMap.fromYaml(scene["observed_map"])
image = observed_map.toImage()
cv2.imwrite("observed.png", image)
cv2.imshow("observed map", image)
print "observed map: ", observed_map.width, "x", observed_map.height
dimage = readMatFromYaml(scene["discrepancy_magnitude"])
cv2.imshow("discrepancy magnitude", dimage)
cv2.waitKey(0)
cv2.destroyAllWindows()
def black_field(a, b, img):
#print a, b
#print b-5, b+5, a-5, b+5
cropped_img = img[b-5:b+5, a-5:a+5]
cv2.imshow('kropd', cropped_img)
#print 255-cv2.mean(cropped_img)[0]
return 255-cv2.mean(cropped_img)[0]
def find_target(image_to_analyze, trackbar_window,
image_to_draw_on=None, indicator_color=(0, 0, 0),
adjustment_ratio=1):
lower, upper = trackbar_window.get_range()
median = cv2.medianBlur(image_to_analyze, 15)
mask = cv2.inRange(median, lower, upper)
mask = cv2.morphologyEx(mask, cv2.MORPH_OPEN, None, iterations=2)
cv2.imshow(trackbar_window.window_name, mask)
# Find contours in the mask and initialize the current (x, y) center of the ball
contours = cv2.findContours(mask.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)[-2]
center = None
radius = None
# Proceed only if at least one contour was found.
if len(contours) > 0:
# Find the largest contour in the mask, then use it to
# compute the minimum enclosing circle and centroid.
c = max(contours, key=cv2.contourArea)
((x, y), radius) = cv2.minEnclosingCircle(c)
center = (int(adjustment_ratio*x), int(adjustment_ratio*y))
radius = int(adjustment_ratio*radius)
if center is not None and image_to_draw_on is not None:
draw_largest_contour(image_to_draw_on, center, radius, color=indicator_color)
return center, radius
def build_study_images():
avaiable_chars = string.digits
captcha.get_captcha(chars=avaiable_chars).save('captcha.png')
img = cv2.imread('captcha.png')
new_img, sub_images = split_symbols(img)
cv2.imshow("all_img", new_img)
output_dir = os.path.join(PROJECT_ROOT, "training")
avaiable_keys = map(ord, avaiable_chars)
for sub_img in sub_images:
cv2.imshow("char", sub_img)
while True:
key = cv2.waitKey(0) % 256
if key == 27:
sys.exit() # ESC
elif key in avaiable_keys:
char = chr(key)
print key, char
save_char(sub_img, char, output_dir)
break
def main():
files = glob.glob("./scans/*.jpg")
files += glob.glob("./scans/*.jpeg")
for f in files:
reset_stats()
print "Processing: " + f.split("/")[len(f.split("/")) - 1]
schedule = Schedule()
schedule.load_data()
if schedule.get_has_schedule():
scan_image(f, schedule)
print "Sheet ok? ",
while True:
cv2.imshow("image", cv2.resize(img, (446, 578)))
cv2.moveWindow("image", 0, 0)
# user_in = raw_input()
key = cv2.waitKey(-1)
if key == ord("y"):
print "Sheet ok... Dumping data"
dump_stats()
os.remove(f)
break
elif key == ord("n"):
print "Marking to redo"
#os.rename(f, "./scans/redo/" + f.split("/")[len(f.split("/")) - 1])
break
elif key == ord("q"):
exit(0)
else:
continue
cv2.destroyAllWindows()
else:
print "Unable to load schedule... Aborting"
def captureImage(self):
position = [0, 0]
velocity = [0, 0]
frame = self.cap.read()[1]
if frame != None:
frame = cv2.flip(frame, 1)
self.frame_hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
threshold_mask = self.createMultipleThresholds(self.frame_hsv)
contour = self.getLargestContour(threshold_mask)
if type(contour) != int:
cv2.drawContours(frame, contour, -1, (0, 255, 255), 2)
position = self.getContourMoment(contour)
cv2.circle(frame, (position[0], position[1]), 5, (0,0,255), -1)
# calculate velocity
velocity = [position[0] - self.oldPosition[0], position[1] - self.oldPosition[1]]
# print velocity
cv2.imshow("Frame", frame)
cv2.waitKey(10)
self.oldPosition = position
return [position, velocity]
def main(argv):
args = str(sys.argv[1])
hogParams = {'hitThreshold': -.5, 'scale': 1.05}
hog = cv2.HOGDescriptor()
hog.setSVMDetector(cv2.HOGDescriptor_getDefaultPeopleDetector())
video = cv2.VideoCapture(args)
ret, frame = video.read()
while(ret):
cimg = np.copy(frame)
people, w = hog.detectMultiScale(frame, **hogParams)
filetered = []
for ri, r in enumerate(people):
for qi, q in enumerate(people):
if ri != qi and inside(r, q):
print "break"
break
else:
filetered.append(r)
# draw_detections(frame, people)
draw_detections(cimg, filetered, 1)
cv2.imshow('detected people', cimg)
cv2.waitKey(2)
ret, frame = video.read()
cv2.destroyAllWindows()
video.release()
def display(self):
""" Displays current frame with rectangles and boxes"""
allface = self.getFaces()
for i in range(len(self.visibleFaceList)):
if len(self.visibleFaceList[i].getPrevPositions()) > self.cleanThresh:
self.showRectangle(self.visibleFaceList[i].getPosition(),self.visibleFaceList[i].getID())
cv2.imshow("show", self.frameImage)
def draw_motion(self, im=None, draw_outliers=False):
show_image = False
if im is None:
im = self.result_image
show_image = True
if draw_outliers:
print("points shape: " + str(self.prev_points.shape[0]) + " outliers " +
str(self.outliers.shape))
for i in range(0, self.prev_points.shape[0]):
prev_pt = self.prev_points[i]
next_pt = self.next_points[i]
color = np.array([0, 255, 0])
if draw_outliers:
id = 2*i
if (self.outliers[id] or self.outliers[id+1]) and draw_outliers:
color = np.array([0, 0, 255])
else:
color = np.array([0, 255, 0])
cv2.circle(im, (prev_pt[0], prev_pt[1]), 2, color, -1)
cv2.line(im, (prev_pt[0], prev_pt[1]), (next_pt[0], next_pt[1]), np.array([255, 0, 0]), 1)
if show_image:
cv2.imshow("", im)
cv2.waitKey(0)
return im
def main():
cap = cv2.VideoCapture(0)
disto = cycle(funcs)
time = 0
while(True):
# Capture frame-by-frame
ret, frame = cap.read()
if time % 3 == 0: #chooses how long to change the distortion
distfunc = disto.next()
frm = distfunc(frame)
# Our operations on the frame come here
#gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
# Display the resulting frame
cv2.imshow('frame',frm)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
time += int(random.random() * 10) #add a random element to the distortion
if time / 50 > 1:
disto = cycle(funcs) ## reshuffle the effects so it won't repeat so much.
time = 0
# When everything done, release the capture
cap.release()
cv2.destroyAllWindows()
def show_img(data, suffix, show):
global wnd_x
global wnd_y
if data == None:
return
image = data.astype(np.uint8)
if image.shape[0] == 6:
img = image.transpose(1,2,0)
img1 = img[:,:,:3]
img2 = img[:,:,3:]
else:
img1 = image[0]
img2 = image[1]
filename = 'img-1-'+suffix+'.jpg'
cv2.imwrite(filename, img1)
if show:
cv2.imshow("IMG 1", img1)
cv2.moveWindow("IMG 1", wnd_x, wnd_y)
filename = 'img-2-'+suffix+'.jpg'
cv2.imwrite(filename, img2)
if show:
cv2.imshow("IMG 2", img2)
wnd_x+=300
cv2.moveWindow("IMG 2", wnd_x, wnd_y)
wnd_x=10
wnd_y+=300
def colour_picker(colourSTR ="(unspecified)", colourGrabWindowSize = 5, colourHueWindowSize = 40, colourSaturationWindowSize= 40, colourValueWindowSize =40):
global cam
global hsv
print "Right click the ",colourSTR," blob. Hit escape when done."
cv2.namedWindow("image")
cv2.setMouseCallback("image", mouseCallBack, param=None)
try:
while True:
#Get image from webcam and convert to greyscale
ret, img = cam.read()
hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
cv2.imshow("image", img)
cMinY = max(0, rightButtonY - colourGrabWindowSize)
cMaxY = min(len(hsv) - 1, rightButtonY + colourGrabWindowSize)
cMinX = max(0, rightButtonX - colourGrabWindowSize)
cMaxX = min(len(hsv[0]) - 1, rightButtonX + colourGrabWindowSize)
cHue = int(npy.mean(hsv[redMinY:redMaxY, redMinX:redMaxX, 0]))
cSaturation = int(npy.mean(hsv[redMinY:redMaxY, redMinX:redMaxX, 1]))
cValue = int(npy.mean(hsv[redMinY:redMaxY, redMinX:redMaxX, 2]))
#Sleep infinite loop for ~10ms
#Exit if user presses <Esc>
if cv2.waitKey(10) == 27:
break
finally:
cv2.destroyWindow("image")
return np.array(cHue, cSaturation, cValue)
def erode(imageName,iter):
"""Takes image name of image and erodes it"""
image = cv2.imread(imageName)
dilated = cv2.erode(image,None, iterations=iter)
cv2.imshow("OUTPUT", dilated)
cv2.imshow("INPUT", image)
cv2.waitKey(0)
def verb_showfilters(argv):
"""Dump source code of session"""
f = KITNNFile(argv[2])
s = f.getSession(argv[3]).d["snap/1"]
fine = s["data/2" ][...]
medium = s["data/8" ][...]
coarse = s["data/14"][...]
w = 3+(16*7+15*3)+3
h = 3+( 9*7+ 8*3)+3
img= np.zeros((h,w,3), dtype="uint8")
for i in xrange(9):
for j in xrange(16):
n = i*16+j
if i in [0,1,2]:
card = fine [n- 0]
elif i in [3,4,5]:
card = medium[n-48]
elif i in [6,7,8]:
card = coarse[n-96]
card -= np.min(card)
card /= np.max(card)
card = card.transpose(1,2,0)
img[3+i*10:3+i*10+7, 3+j*10:3+j*10+7] = 255*card
img = cv2.resize(img, (0,0), None, 8, 8, cv2.INTER_NEAREST)
cv2.imshow("Filters", img)
cv2.imwrite("Filters.png", img)
cv2.waitKey()
def run(self):
while True:
playing = not self.paused and not self.rect_sel.dragging
if playing or self.frame is None:
ret, frame = self.cap.read()
if not ret:
break
self.frame = frame.copy()
vis = self.frame.copy()
if playing:
tracked = self.tracker.track(self.frame)
for tr in tracked:
cv2.polylines(vis, [np.int32(tr.quad)], True, (255, 255, 255), 2)
for (x, y) in np.int32(tr.p1):
cv2.circle(vis, (x, y), 2, (255, 255, 255))
self.rect_sel.draw(vis)
cv2.imshow('plane', vis)
ch = cv2.waitKey(1)
if ch == ord(' '):
self.paused = not self.paused
if ch == ord('c'):
self.tracker.clear()
if ch == 27:
break
def coolBlack():
IMAGE_WEIGHT = 0.5
image = cv2.imread("G:/Filters/wasim.jpg",0)
black = cv2.imread("G:/Filters/black5.jpg",0)
black = cv2.resize(black, image.shape[::-1])
res1 = cv2.addWeighted(image, IMAGE_WEIGHT, black, 1 - IMAGE_WEIGHT, 1)
#NORMALIZE IMAGES
image = np.float32(image)
black = np.float32(black)
image /= 255
black /= 200
res = image*black
cv2.imshow("RES", res)
cv2.waitKey(0)
fname = "G:/Filtes/temp.jpg"
cv2.imwrite(fname, res)
res = cv2.imread(fname, 0)
cv2.imshow("BLACK", res)
cv2.waitKey(0)
def get_images_and_labels(path):
# Append all the absolute image paths in a list image_paths
# We will not read the image with the .sad (the sad face) extension in the training set
# Rather, we will use them to test our accuracy of the training
image_paths = [os.path.join(path, f) for f in os.listdir(path)]
# images will contains face images
images = []
# labels will contains the label that is assigned to the image
labels = []
for image_path in image_paths:
# Read the image and convert to grayscale
image_pil = Image.open(image_path).convert('L')
# Convert the image format into numpy array
image = np.array(image_pil, 'uint8')
# Get the label of the image
nbr = int(os.path.split(image_path)[1].split(".")[0].replace("subject",""))
# Detect the face in the image
faces = faceCascade.detectMultiScale(frame,
scaleFactor=1.5,
minNeighbors=6,
minSize=(30, 30),
flags = cv2.cv.CV_HAAR_SCALE_IMAGE)
# If face is detected, append the face to images and the label to labels
for (x, y, w, h) in faces:
images.append(image[y: y + h, x: x + w])
labels.append(nbr)
cv2.imshow("Adding faces to traning set...", image[y: y + h, x: x + w])
cv2.waitKey(50)
# return the images list and labels list
return images, labels
def main():
cap = cv2.VideoCapture(1)
if not cap.isOpened():
print("Capture could not be opened successfully.")
while True:
if cv2.waitKey(1) & 0xFF == ord('q'):
break
_, img = cap.read()
alpha = cv2.getTrackbarPos('Contrast', 'image')
#Sliders can't be lower than 0, so starting at 50, then subtracting
beta = cv2.getTrackbarPos('Brightness', 'image') - 50
print beta
toggle = cv2.getTrackbarPos(switch, 'image')
segmented = False if toggle == 0 else True
#trans_img = cv2.add(mul_img, b_array)
trans_img = (alpha * img)
#trans_img = np.where(trans_img + beta >= 0, trans_img + beta, 0)
if segmented:
gray = cv2.cvtColor(trans_img, cv2.COLOR_BGR2GRAY)
_, binary = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY)
cv2.imshow('image', binary)
else:
cv2.imshow('image', trans_img)
def plot_place_cell_id_on_map(self,map_data,place_cell_id):
# Plot red box where vehicle is....
min_x=place_cell_id[1].min()
min_y=place_cell_id[2].min()
ptp_y=place_cell_id[2].ptp()
map_out=np.copy(map_data); # FORCE COPY SO IT DOESNT KEEP OLD MOVES!!!!!
map_out=self.flip_rotate_color_image(map_out,0,False)
# Loop through each place id
for current_place in range(0,place_cell_id[0].size):
# sq=self.squares_grid[place_cell_id[1][current_place]-min_x,place_cell_id[2][current_place]-min_y,:]
# Flipping this in y-plane
sq=self.squares_grid[place_cell_id[1][current_place]-min_x,np.absolute(place_cell_id[2][current_place]-min_y-ptp_y),:]
# Place number at bottom of square in middle....
x_pos=sq[0]#+np.round(np.diff([sq[2],sq[0]])/2)
y_pos=self.pixel_width-sq[1]+np.round(np.diff([sq[3],sq[1]])/2)
cv2.putText(map_out, str(int(place_cell_id[0][current_place])), (int(x_pos),int(y_pos)), cv2.FONT_HERSHEY_SIMPLEX, 0.3,(0,0,255),1);
textsize=cv2.getTextSize('N',cv2.FONT_HERSHEY_SIMPLEX,0.8,2)
#cv2.fillConvexPoly(map_out,np.abs(np.array([[self.pixel_width,0],[self.pixel_width,0],[self.pixel_width,0]])-self.arrow[('heading')]),(0,0,255))
cv2.putText(map_out, 'N', (self.pixel_width-int((textsize[0][1]/2)+10),int(30+(textsize[1]/2))), cv2.FONT_HERSHEY_SIMPLEX, 0.8,(0,0,255),2);
cv2.imshow(self.place_cell_map,map_out)
return map_out
def convertData(self, bagfile):
seq = 0
bridge = CvBridge()
while(True):
# Capture frame-by-frame
ret, cvImage = self.capture.read()
try:
imageMsg = bridge.cv2_to_imgmsg(cvImage, "bgr8") # TODO: format spec as cmd option?
except CvBridgeError, e:
print e
# creating ros message
seq = seq + 1
imageMsg.header.seq = seq
# TODO: temporary hack, time sync/source is needed
imageMsg.header.stamp = rospy.Time.from_sec(time.time())
# write message to bag file
bagfile.write(self.topic, imageMsg, imageMsg.header.stamp)
# this is not so important for conversion
if self.showFrames == True:
cv2.imshow('frame', cvImage)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
def run(self):
runFlag = True
cv2.namedWindow("TurtleCam 9000", 1)
while(runFlag):
image, timesImageServed = self.robot.getImage()
with self.lock:
if timesImageServed > 30:
if self.stalled == False:
print "Camera Stalled!"
self.stalled = True
else:
self.stalled = False
frame = self.mcs.update(image.copy())
cv2.imshow("TurtleCam 9000", frame)
code = chr(cv2.waitKey(10) & 255)
if code == 't':
cv2.imwrite("/home/macalester/catkin_ws/src/speedy_nav/res/captures/cap-" + str(datetime.now()) + ".jpg", image)
print "Image saved!"
if code == 'q':
break
with self.lock:
runFlag = self.runFlag
def object_detection(self, depth_array):
"""
Function to detect objects from the depth image given
:return:
"""
self.detect_arm()
# Perform thresholding on the image to remove all objects behind a plain
ret, bin_img = cv2.threshold(depth_array, 0.3, 1, cv2.THRESH_BINARY_INV)
# Erode the image a few times in order to separate close objects
element = cv2.getStructuringElement(cv2.MORPH_CROSS, (3, 3))
err_img = cv2.erode(bin_img, element, iterations=20)
# Create a new array of type uint8 for the findContours function
con_img = np.array(err_img, dtype=np.uint8)
# Find the contours of the image and then draw them on
contours, hierarchy = cv2.findContours(con_img, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cv2.drawContours(con_img, contours, -1, (128, 255, 0), 3)
for x in range(0, len(contours)):
x, y, w, h = cv2.boundingRect(contours[x])
cv2.rectangle(con_img, (x, y), ((x+w), (y+h)), (255, 0, 127), thickness=5, lineType=8, shift=0)
# Show the colour images of the objects
# self.show_colour(contours)
# Show the Depth image and objects images
cv2.imshow('Contours', con_img)
cv2.imshow("Depth", bin_img)
cv2.waitKey(3)
def dewarp(imagedir):
# Loading from json file
C = CameraParams.fromfile(os.path.join(imagedir, "params.json"))
K = C.K
D = C.D
print("Loaded camera parameters from " + os.path.join(imagedir, "params.json"))
for f in file_list(imagedir, ['jpg', 'jpeg', 'png']):
print(f)
colour = cv2.imread(f)
grey = cv2.cvtColor(colour, cv2.COLOR_BGR2GRAY)
h, w = grey.shape[:2]
newcameramtx, roi=cv2.getOptimalNewCameraMatrix(K, D, (w,h), 1, (w,h))
mapx, mapy = cv2.initUndistortRectifyMap(K, D, None, newcameramtx, (w,h), 5)
dewarped = cv2.remap(grey, mapx, mapy, cv2.INTER_LINEAR)
x, y, w, h = roi
dewarped = dewarped[y:y+h, x:x+w]
grey = cv2.resize(grey, (0,0), fx=0.5, fy=0.5)
dewarped = cv2.resize(dewarped, (0,0), fx=0.5, fy=0.5)
cv2.imshow("Original", grey )
cv2.imshow("Dewarped", dewarped)
cv2.waitKey(-1)
def get_info_part(li):
li_info = li.get_information_part()
if li_info is not None:
li_info = cv2.resize(li_info, (info_size, info_size))
cv2.imshow('li_info', li_info)
cv2.moveWindow('li_info', int(1280*FRAME_SIZE_FACTOR), 0)
return li_info
def realisticTexturemap(H_G_M, scale):
map_img = cv2.imread('Images/ITUMap.bmp')
point = getMousePointsForImageWithParameter(map_img, 1)[0]
texture = cv2.imread('Images/ITULogo.jpg')
#texture = cv2.cvtColor(texture,cv2.COLOR_BGR2GRAY)
H_T_M = np.zeros(9).reshape(3,3)
H_T_M[0][0] = scale
H_T_M[1][1] = scale
H_T_M[0][2] = point[0]
H_T_M[1][2] = point[1]
H_T_M[2][2] = 1
H_M_G = np.linalg.inv(H_G_M)
H_T_G = np.dot(H_M_G, H_T_M)
fn = "GroundFloorData/sunclipds.avi"
cap = cv2.VideoCapture(fn)
#load Tracking data
running, frame = cap.read()
while running:
running, frame = cap.read()
h,w,d = frame.shape
warped_texture = cv2.warpPerspective(texture, H_T_G,(w, h))
result = cv2.addWeighted(frame, .6, warped_texture, .4, 50)
cv2.imshow("Result", result)
cv2.waitKey(0)
def textureMapGroundFloor():
#create H_T_G from first frame of sequence
texture = cv2.imread('Images/ITULogo.jpg')
fn = "GroundFloorData/sunclipds.avi"
sequence = cv2.VideoCapture(fn)
running, frame = sequence.read()
h_t_g, calibration_points = SIGBTools.getHomographyFromMouse(texture, frame, -4)
print h_t_g
#fig = figure()
while running:
running, frame = sequence.read()
if not running:
return
#texture map
h,w,d = frame.shape
warped_texture = cv2.warpPerspective(texture, h_t_g,(w, h))
result = cv2.addWeighted(frame, .7, warped_texture, .3, 50)
#display
cv2.imshow("Texture Mapping", result)
cv2.waitKey(1)
def show_colour(self, cnt):
"""
Use the objects found to show them in colour
:return:
"""
# Go through each rectangle and display the rgb
length = len(cnt)
# Create an array of size the amount of rectangles
crop_rgb = []
for i in range(0, length):
crop_rgb.append(1)
for x in range(0, length):
x, y, w, h = cv2.boundingRect(cnt[x])
# Try to crop the rgb image for each box
try:
crop_rgb[x] = self.rgb_img[y:y+h, x:x+w]
except:
pass
for x in range(0, length):
name = "Cropped " + str(x)
cv2.imshow(name, crop_rgb[x])
cv2.waitKey(3)
def calibrateSharpening():
frame = cv2.imread("failed_frame_224.png")
new_frame = sharpen(frame)
found, _ = cv2.findChessboardCorners(new_frame, (9,6))
print found
cv2.imshow("sharpened", new_frame)
cv2.waitKey(0)
def main():
cv.NamedWindow("original", cv.CV_WINDOW_AUTOSIZE)
cv.NamedWindow("keyboard", cv.CV_WINDOW_AUTOSIZE)
cam = cv2.VideoCapture(0)
cam.set(cv.CV_CAP_PROP_FRAME_WIDTH, 600)
cam.set(cv.CV_CAP_PROP_FRAME_HEIGHT, 480)
cam.set(cv.CV_CAP_PROP_FPS, 24)
ret, frame = cam.read()
player = sound.SoundPlayer('./resources/s1.sf2')
while True:
ret, frame = cam.read()
keyboard_image = KeyboardRecognizer(frame).get_keyboard()
if keyboard_image is not None:
notes = KeysRecognizer(keyboard_image, 'keyboard').get_pressed_keys()
player.play_notes(notes)
cv2.imshow('original', frame)
if cv2.waitKey(1) == 27: # Escape code
break
cv2.destroyAllWindows()
def show_images(images):
for i, image in enumerate(images):
cv2.imshow("image ", image)
#waitKey(0) will display the window infinitely until any keypress
cv2.waitKey(0)
# disable(model, "all", 4)
# disable(model, 1, 7)
# disable(model, 2, 7)
# disable(model, 3, 6)
# disable(model, all, 7)
# disable_weights(model, 0, 7)
# disable_weights(model, 1, 7)
# disable_weights(model, 2, 7)
# disable_weights(model, 3, 7)
# disable_weights(model, 4, 7)
# disable_weights(model, 5, 7)
print("\nCustom performance")
testPerformance(model, data[INDICES_TEST], iClasses[INDICES_TEST])
##################
torch.save(model.state_dict(), MODELDIR + "/modified.model")
img = renderKernels(model)
cv2.imwrite(MODELDIR + "/modified.png", img)
cv2.imshow("Kernels of model", img)
weights = model.fc.weight.data.numpy()
weights = weights.reshape((NCLASSES, NCHANNELS, 4 * 4))
img = render3dBarCharts(weights, 10, 2, 200)
cv2.imwrite(MODELDIR + "/modifiedWeights.png", img)
cv2.imshow("Weights of model", img)
cv2.waitKey(0)
import time
import numpy as np
images = glob.glob("/home/pi/Desktop/cone/real/*.jpg")
#print images
images.sort()
tmp_list = images[0].split('/')
title = tmp_list[-1]
image = cv2.imread(images[0])
height, width, layers = image.shape
video = cv2.VideoWriter('/home/pi/Desktop/cone/video.avi',
cv2.cv.CV_FOURCC('M', 'J', 'P', 'G'), 1, (640, 240))
for name in images:
tmp_list = name.split('/')
title = tmp_list[-1]
image_real = cv2.imread("/home/pi/Desktop/cone/real/" + title)
image_filtered = cv2.imread("/home/pi/Desktop/cone/filtered/" + title)
vis = np.concatenate((image_real, image_filtered), axis=1)
time.sleep(0.1)
cv2.imshow("vis", vis)
key = cv2.waitKey(1) & 0xFF
video.write(vis)
video.release()
dt = DecisionTreeClassifier()
training_classifier(dt, train_data, test_data, atributes, labels)
# Calculando acurácia no dataset de teste
'''predictions = gnb.predict(test_data[atributes])
accuracy = metrics.accuracy_score(predictions,test_data[labels])
confusion_matrix = metrics.confusion_matrix(test_data[labels], predictions)
print('Acurácia: {}'.format(accuracy))
print('Matriz: {}'.format(confusion_matrix))'''
img = cv2.imread('images/image1.png')
hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
blur3 = cv2.GaussianBlur(hsv, (3,3), 0)
blur5 = cv2.GaussianBlur(hsv, (5,5), 0)
blur7 = cv2.GaussianBlur(hsv, (7,7), 0)
height, width, channels = hsv.shape
mask = np.zeros_like(img)
for j in range(height):
for i in range(width):
pixel = [np.array([hsv.item(j,i,0), hsv.item(j,i,1), hsv.item(j,i,2), blur3.item(j,i,0), blur5.item(j,i,0), blur7.item(j,i,0)], dtype=np.float32)]
results = dt.predict(pixel)
if(results == 1):
mask[j, i] = [0, 0, 255]
mask = cv2.medianBlur(mask, 5)
img = cv2.addWeighted(img, 0.8, mask, 0.5, 0.2)
cv2.imshow('result', img)
cv2.waitKey(0)
cv2.destroyAllWindows()
# h,mask = cv2.findHomography(srcPoints=pts1,dstPoints=pts2,method=cv2.RANSAC, ransacReprojThreshold=5.0)
# height, width, channels = res.shape
# im1Reg = cv2.warpPerspective(note, h, (width, height))
# mask2 = np.zeros(res.shape, dtype=np.uint8)
# roi_corners2 = np.int32(positions2)
# channel_count2 = res.shape[2]
# ignore_mask_color2 = (255,) * channel_count2
# cv2.fillConvexPoly(mask2, roi_corners2, ignore_mask_color2)
# mask2 = cv2.bitwise_not(mask2)
# masked_image2 = cv2.bitwise_and(res, mask2)
# res = cv2.bitwise_or(im1Reg, masked_image2)
# --------------------------------------------------------------------------
# Result output
cv2.imshow(win_name, res)
key = cv2.waitKey(1)
if key == 27: # Esc, 종료
break
elif key == ord(' '): # Set img1 by setting ROI to space bar
x,y,w,h = cv2.selectROI(win_name, frame, False)
if w and h:
img1 = frame[y:y+h, x:x+w]
gray1 = cv2.cvtColor(img1, cv2.COLOR_BGR2GRAY)
kp, desc = detector.detectAndCompute(gray1, None)
tup = [kp,desc,img1]
templates.append(tup)
else:
ax2.plot(x_axis, speed_right, 'b-')
ax3.plot(x_axis, speed_left, 'r-')
ax3.plot(x_axis, speed_right, 'b-')
#ax4.bar(index, optical_direction, color='r', label='degree')
plt.draw()
# updare cx_neurons
velocity = np.array([sl, sr])
tl2, cl1, tb1, tn1, tn2, memory, cpu4, cpu1, motor = update_cells(
heading=heading_list[frame_num]/180.0*np.pi, velocity=velocity, tb1=tb1, memory=memory, cx=cx)
angle, distance = cx.decode_cpu4(cpu4)
angle_list[frame_num] = angle/np.pi*180.0
distance_list[frame_num] = distance
# show frames
cv2.imshow('vedio', cv2.resize(draw_flow(next, flow), (0,0), fx=3.0, fy=3.0))
#print('Frame number: ', frame_num)
ch = cv2.waitKey(5) & 0xFF
if ch == ord('q'):
break
elif ch == ord(' '):
while True:
ch = cv2.waitKey(5) & 0xFF
if ch == ord(' ') or ch == ord('q'):
break
time.sleep(0.2)
prvs = next
start_time = time.time()
ax1.clear()
model_cl.load_weights(model_path)
logits = model_cl.output[0]
logits = tf.argmax(logits, -1)
model = models.Model(model_cl.input, logits)
cam = cv2.VideoCapture("test.mp4")
start1= time.time()
counter = 0
while(True):
counter =counter + 1
start = time.time()
ret = cam.grab()
if(counter % 4==0):
ret, frame = cam.retrieve()
else:
continue
# frame = frame[150:,...]
img = cv2.resize(frame, (800,288),interpolation =cv2.INTER_NEAREST)
# gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# pred = model(np.expand_dims(gray, 0), training=False)
pred = model.predict(np.expand_dims(img-train_mean_channels, 0))
print(np.shape(pred))
cv2.imshow("pred", np.uint8(pred[0]) * 255)
cv2.imshow("image", img)
key = cv2.waitKey(3)
if(key == 27):
cv2.destroyAllWindows()
break
print((time.time()-start))
def StationEntryView(request, station_no):
if request.method == 'POST':
try:
entry = request.POST.get("first")
entry = int(entry)
return redirect('core:station_entry', entry)
except:
pass
try:
exit = request.POST.get("second")
exit = int(exit)
return redirect('core:station_exit', exit)
except:
pass
station = models.Station.objects.get(station_no=station_no)
pics = list(models.Person.objects.all().values_list('pic', flat=True))
known_face_names = list(models.Person.objects.all().values_list('name', flat=True))
uids = list(models.Person.objects.all().values_list('uid', flat=True))
known_face_encodings = []
for pic in pics:
image = face_recognition.load_image_file(os.path.join(base_dir, str(pic)))
image_encoding = face_recognition.face_encodings(image)[0]
known_face_encodings.append(image_encoding)
i = 0
video_capture = cv2.VideoCapture(0)
face_locations = []
face_encodings = []
face_names = []
face_uids = []
process_this_frame = True
while True:
# Grab a single frame of video
ret, frame = video_capture.read()
try:
# Resize frame of video to 1/4 size for faster face recognition processing
small_frame = cv2.resize(frame, (0, 0), fx=0.25, fy=0.25)
# small_frame = frame
# Convert the image from BGR color (which OpenCV uses) to RGB color (which face_recognition uses)
rgb_small_frame = small_frame[:, :, ::-1]
# Only process every other frame of video to save time
if process_this_frame:
# Find all the faces and face encodings in the current frame of video
face_locations = face_recognition.face_locations(rgb_small_frame)
face_encodings = face_recognition.face_encodings(rgb_small_frame, face_locations)
face_names = []
face_uids = []
for face_encoding in face_encodings:
# See if the face is a match for the known face(s)
matches = face_recognition.compare_faces(known_face_encodings, face_encoding, tolerance=0.5)
name = "Unknown"
uid = -1
face_distances = face_recognition.face_distance(known_face_encodings, face_encoding)
best_match_index = np.argmin(face_distances)
if matches[best_match_index]:
name = known_face_names[best_match_index]
# print("pehchaan liya", name)
uid = uids[best_match_index]
person = models.Person.objects.get(uid=uid)
log = models.Log.objects.get_or_create(person=person, entry_station=station, status=0)
face_names.append(name)
face_uids.append(uid)
i += 1
process_this_frame = not process_this_frame
# Display the results
for (top, right, bottom, left), name, uid in zip(face_locations, face_names, face_uids):
# Scale back up face locations since the frame we detected in was scaled to 1/4 size
top *= 4
right *= 4
bottom *= 4
left *= 4
# Draw a box around the face
cv2.rectangle(frame, (left, top), (right, bottom), (0, 0, 255), 2)
# Draw a label with a name below the face
cv2.rectangle(frame, (left, bottom - 35), (right, bottom), (0, 0, 255), cv2.FILLED)
font = cv2.FONT_HERSHEY_DUPLEX
cv2.putText(frame, str(name + ':' + str(uid)), (left + 6, bottom - 6), font, 1.0, (255, 255, 255), 1)
except:
# print(frame)
pass
# Display the resulting image
cv2.imshow('Video', frame)
# Hit 'q' on the keyboard to quit!
if cv2.waitKey(1) & 0xFF == ord('q'):
break
# Release handle to the webcam
video_capture.release()
cv2.destroyAllWindows()
return render(request, 'core/index.html')
def show_cam(camera=0, bw=False, mirrorlr=False, mirrorud=False, hsv=False, detect_region=False):
cam = cv2.VideoCapture(camera)
try:
while True:
img_available, img = cam.read()
if img_available==True:
# convert the image to grayscale
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
img = cv2.normalize(img,img,0,255,cv2.NORM_MINMAX)
img = cv2.addWeighted( img, 1.5, np.zeros(img.shape, img.dtype), 0, 0)
if detect_region:
box = detect_qr(img)
# draw a bounding box arounded the detected QR code
# cv2.drawContours(img, [box], -1, (0, 255, 0), 3)
# Set area outside region of interest to white
mask = np.zeros_like(img) # Create mask where white is what we want, black otherwise
for bx in box:
cv2.fillConvexPoly(mask, np.array(bx), 255)
out = 255*np.ones_like(img)
out[mask == 255] = img[mask == 255]
img = out
if hsv:
img = cv2.normalize(img,img,0,255,cv2.NORM_MINMAX)
img_hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
# define range of bw color in HSV
sat_limit = 40
lower_bw = np.array([0,0,0])
upper_bw = np.array([255,sat_limit,255])
# Threshold the HSV image to get only white colors
mask = cv2.inRange(img_hsv, lower_bw, upper_bw)
# Bitwise-AND mask and original image
img = cv2.bitwise_and(img,img, mask= mask)
# Cast to BW image
if bw:
# Up contrast
img = cv2.addWeighted(img, 3, np.zeros(img.shape, img.dtype), 0, 0)
# blur noise
img = cv2.bilateralFilter(img,5,75,75)
# blur = cv2.GaussianBlur(img,(5,5),0)
# _, img = cv2.threshold(img,0,255,cv2.THRESH_OTSU)
_, img = cv2.threshold(img, 127, 255, cv2.THRESH_BINARY)
# _, img = cv2.threshold(img, img.mean()/2, 255, cv2.THRESH_TOZERO)
# _, img = cv2.threshold(img, 200, , cv2.THRESH_TOZERO_INV)
decoded = decode(img)
if len(decoded) > 0:
print(decoded)
# Flip image if necessary
if mirrorlr:
img = cv2.flip(img,1)
if mirrorud:
img = cv2.flip(img,0)
cv2.imshow('my cam', img)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
finally:
cam.release()
cv2.destroyAllWindows()
# Remove small contours, removes noise
count = [x for x in count if cv2.contourArea(x) > 90]
# Get reference object dimensions
ref_object = count[0]
surroundings = cv2.minAreaRect(ref_object)
surroundings = cv2.boxPoints(surroundings)
surroundings = np.array(surroundings, dtype="int")
surroundings = perspective.order_points(surroundings)
(tl, tr, br, bl) = surroundings
pixel_dist = euclidean(tl, tr)
#Can adjust this number based on leftmost object size
dist_in_cm = 2.0
#Uses pixels for measurement
pixel_per_cm = pixel_dist / dist_in_cm
# Draw all contours that were counted
drawCoutour(count, pixel_per_cm, image)
#Check utlis for definition
show_images([image])
#Can extend for video capture eventually
cap = cv2.VideoCapture(0)
while True:
ret, frame = cap.read() #returns ret and the frame
cv2.imshow('frame', frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
def read_images(self, folder):
i = 0
images = []
images_fail = []
for file in os.listdir(folder):
if re.search(r'.*_left', file) == None:
continue
image1 = cv2.imread(folder + "/" + file)
if image1 is None:
break
file_right = re.sub(r'_left', '_right', file)
image2 = cv2.imread(folder + "/" + file_right)
if image2 is None:
break
gray_l = cv2.extractChannel(image1, 1)
gray_r = cv2.extractChannel(image2, 1)
# Find the chess board corners
ret_l, corners_l = cv2.findChessboardCorners(
gray_l, (8, 6), None, cv2.CALIB_CB_ADAPTIVE_THRESH)
if not ret_l:
print("left fail")
images_fail.append(file)
continue
ret_r, corners_r = cv2.findChessboardCorners(
gray_r, (8, 6), None, cv2.CALIB_CB_ADAPTIVE_THRESH)
if not ret_r:
print("right fail")
images_fail.append(file)
continue
images.append(file)
if ret_l and ret_r:
# If found, add object points, image points (after refining them)
self.objpoints.append(self.objp)
rt = cv2.cornerSubPix(gray_l, corners_l, (11, 11), (-1, -1),
self.criteria)
self.imgpoints_l.append(corners_l)
# Draw and display the corners
cv2.drawChessboardCorners(gray_l, (8, 6), corners_l, ret_l)
rt = cv2.cornerSubPix(gray_r, corners_r, (11, 11), (-1, -1),
self.criteria)
self.imgpoints_r.append(corners_r)
# Draw and display the corners
cv2.drawChessboardCorners(gray_r, (8, 6), corners_r, ret_r)
cv2.imshow("Image Left", gray_l)
cv2.imshow("Image Right", gray_r)
key = cv2.waitKey(1)
if key == ord('q'):
break
if key == ord('a'):
return
img_shape = gray_r.shape
self.shape = img_shape
print(f"Fails: {images_fail}", file=sys.stderr)
print("Starting camera calibration", file=sys.stderr)
flags = 0
# flags |= cv2.CALIB_FIX_INTRINSIC
# flags |= cv2.CALIB_FIX_PRINCIPAL_POINT
# flags |= cv2.CALIB_USE_INTRINSIC_GUESS
# flags |= cv2.CALIB_FIX_FOCAL_LENGTH
# flags |= cv2.CALIB_FIX_ASPECT_RATIO
# flags |= cv2.CALIB_ZERO_TANGENT_DIST
# flags |= cv2.CALIB_RATIONAL_MODEL
# flags |= cv2.CALIB_SAME_FOCAL_LENGTH
#flags |= cv2.CALIB_FIX_K3
#flags |= cv2.CALIB_FIX_K4
#flags |= cv2.CALIB_FIX_K5
#flags |= cv2.CALIB_FIX_K6
rt, self.M1, self.d1, self.r1, self.t1, sdi, sde, pve = cv2.calibrateCameraExtended(
self.objpoints, self.imgpoints_l, img_shape, None, None)
print("Reprojection error left: " + str(rt), file=sys.stderr)
j = 0
for image in images:
print(f"{image}: {pve[j,0]}", file=sys.stderr)
j += 1
rt, self.M2, self.d2, self.r2, self.t2, sid, sde, pve = cv2.calibrateCameraExtended(
self.objpoints, self.imgpoints_r, img_shape, None, None)
print("Reprojection error right: " + str(rt), file=sys.stderr)
j = 0
for image in images:
print(f"{image}: {pve[j,0]}", file=sys.stderr)
j += 1
print("Starting stereo camrea calibration", file=sys.stderr)
self.camera_model = self.stereo_calibrate(img_shape)
def StationExitView(request, station_no):
if request.method == 'POST':
try:
entry = request.POST.get("first")
entry = int(entry)
return redirect('core:station_entry', entry)
except:
pass
try:
exit = request.POST.get("second")
exit = int(exit)
return redirect('core:station_exit', exit)
except:
pass
station = models.Station.objects.get(station_no=station_no)
pics = list(models.Person.objects.all().values_list('pic', flat=True))
known_face_names = list(models.Person.objects.all().values_list('name', flat=True))
uids = list(models.Person.objects.all().values_list('uid', flat=True))
known_face_encodings = []
for pic in pics:
# print(pic)
image = face_recognition.load_image_file(os.path.join(base_dir, str(pic)))
image_encoding = face_recognition.face_encodings(image)[0]
known_face_encodings.append(image_encoding)
i = 0
video_capture = cv2.VideoCapture(0)
face_locations = []
face_encodings = []
face_names = []
face_uids = []
process_this_frame = True
while True:
# Grab a single frame of video
ret, frame = video_capture.read()
try:
# Resize frame of video to 1/4 size for faster face recognition processing
small_frame = cv2.resize(frame, (0, 0), fx=0.25, fy=0.25)
# Convert the image from BGR color (which OpenCV uses) to RGB color (which face_recognition uses)
rgb_small_frame = small_frame[:, :, ::-1]
# Only process every other frame of video to save time
if process_this_frame:
# Find all the faces and face encodings in the current frame of video
face_locations = face_recognition.face_locations(rgb_small_frame)
face_encodings = face_recognition.face_encodings(rgb_small_frame, face_locations)
face_names = []
face_uids = []
for face_encoding in face_encodings:
# See if the face is a match for the known face(s)
matches = face_recognition.compare_faces(known_face_encodings, face_encoding, tolerance=0.5)
name = "Unknown"
uid = -1
face_distances = face_recognition.face_distance(known_face_encodings, face_encoding)
best_match_index = np.argmin(face_distances)
if matches[best_match_index]:
name = known_face_names[best_match_index]
uid = uids[best_match_index]
person = models.Person.objects.get(name=name)
try:
log = models.Log.objects.get(person=person, status=0)
log.exit_station = station
log.exit_datetime = timezone.now()
log.status = 1
log.fare = 20
log.save()
try:
subject = 'Thanks for Travelling in Yugant Express'
message = person.name + ', thanks for travelling.\n From Station : {} \n Entry time : {} \n To station : {}\n Exit Time : {} \n Your Fare : {}'.format(
log.entry_station, log.entry_datetime, log.exit_station, log.exit_datetime, log.fare)
from_email = settings.EMAIL_HOST_USER
to_email = [person.email]
email = EmailMessage(subject=subject, from_email=from_email, to=to_email, body=message)
email.send()
# print('email sent')
except:
# print('failed to send email')
pass
except:
# print('Chada hi nhi tha... cheating krta h yeh !! fine lo')
pass
# print(name)
face_names.append(name)
face_uids.append(uid)
i += 1
process_this_frame = not process_this_frame
# Display the results
for (top, right, bottom, left), name, uid in zip(face_locations, face_names, face_uids):
# Scale back up face locations since the frame we detected in was scaled to 1/4 size
top *= 4
right *= 4
bottom *= 4
left *= 4
# Draw a box around the face
cv2.rectangle(frame, (left, top), (right, bottom), (0, 0, 255), 2)
# Draw a label with a name below the face
cv2.rectangle(frame, (left, bottom - 35), (right, bottom), (0, 0, 255), cv2.FILLED)
font = cv2.FONT_HERSHEY_DUPLEX
cv2.putText(frame, str(name + ':'+ str(uid)), (left + 6, bottom - 6), font, 1.0, (255, 255, 255), 1)
except:
# print("Cannot read frame")
pass
# Display the resulting image
cv2.imshow('Video', frame)
# Hit 'q' on the keyboard to quit!
if cv2.waitKey(1) & 0xFF == ord('q'):
break
# Release handle to the webcam
video_capture.release()
cv2.destroyAllWindows()
return render(request, 'core/index.html')
import cv2
cap=cv2.VideoCapture(0)
#0 for camera
while(cap.isOpened()):
ret,frame=cap.read()
#True and Frame
if(ret==True):
cv2.imshow('FrameTitle',frame)
print("WIDTH:HEIGHT:",cap.get(cv2.CAP_PROP_FRAME_WIDTH),cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
if(cv2.waitKey(1)&0xFF==ord('q')):
break
else:
print("Cannot Capture")
break
else:
print("Path is wrong")
#When everything done, release the capture
cap.release()
cv2.destroyAllWindows()
#c0ntours are used for shape analysis
import numpy as np
import cv2
img = cv2.imread('opencv-logo.png')
img1 = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
ret ,thresh = cv2.threshold(img1,127,255,0)
contours ,hirechy = cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
print("NO of Countours" + str(len(contours)))
print(contours[0])
cv2.drawContours(img,contours,-1,(0,255,0),3)
cv2.imshow('Image',img)
cv2.imshow('Image GRAY',img1)
cv2.waitKey(0)
cv2.destroyAllWindows()
webcam.start()
while True:
# get image from webcam
img = webcam.get_current_frame()
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# adapted to inner corners
ret, corners = cv2.findChessboardCorners(gray, (NROW, NCOL), None)
if ret == True:
print('I find you')
cv2.cornerSubPix(gray, corners, (11, 11), (-1, -1), criteria)
# Find the rotation and translation vectors.
try:
rvecs, tvecs, _ = cv2.solvePnPRansac(objp, corners, mtx, dist)
except:
_, rvecs, tvecs = cv2.solvePnP(objp, corners, mtx, dist)
# project 3D points to image plane
imgpts, jac = cv2.projectPoints(axis, rvecs, tvecs, mtx, dist)
img = drawcube(img, corners, imgpts)
if img is not None:
cv2.imshow('img', img)
cv2.waitKey(10)
else:
print('but I cannot display!')
else:
cv2.imshow('img', img)
cv2.waitKey(10)
ret, frame = video_capture.read()
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
k = cv2.waitKey(1)
faces = faceCascade.detectMultiScale(
gray,
scaleFactor=1.5,
minNeighbors=5,
minSize=(30, 30),
flags=cv2.CASCADE_SCALE_IMAGE
)
# Draw a rectangle around the faces
for (x, y, w, h) in faces:
cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2)
# Display the resulting frame
cv2.imshow('FaceDetection', frame)
if k % 256 == 27: # ESC Pressed
break
elif k % 256 == 32:
# SPACE pressed
img_name = "facedetect_webcam_{}.png".format(img_counter)
cv2.imwrite(img_name, frame)
print("{} written!".format(img_name))
img_counter += 1
# When everything is done, release the capture
video_capture.release()
cv2.destroyAllWindows()
cv2.line(img, (puntos[i%L], puntos[(i+1)%L]), (puntos[(i+2)%L], puntos[(i+3)%L]), (0, 255, 0))
cv2.imshow('puntos', img)
def Callback(event, x, y, flags, param):
if event == cv2.EVENT_LBUTTONDOWN:
puntos.append(x)
puntos.append(y)
DibujarPuntos()
print(f'({x}, {y})')
def MostrarPuntos():
print(puntos)
cv2.namedWindow('puntos')
cv2.setMouseCallback('puntos', Callback)
cv2.imshow('puntos', img_original)
key = chr(cv2.waitKey(0))
while key != 'q':
if key == 'm':
MostrarPuntos()
elif key == 'r':
puntos = []
cv2.imshow('puntos', img_original)
elif key == 'd':
if len(puntos) > 0:
puntos = puntos[:-2]
DibujarPuntos()
key = chr(cv2.waitKey(0))
import cv2
capture = cv2.VideoCapture(0)
fourcc = cv2.VideoWriter_fourcc(*'mp4v')
capture.set(cv2.CAP_PROP_FRAME_WIDTH, 3840)
capture.set(cv2.CAP_PROP_FRAME_HEIGHT, 1080)
writer_1 = cv2.VideoWriter('3840x1080_cam12.mp4', fourcc, 30.0, (3840,1080))
while True:
ret, frame = capture.read()
image = frame.copy()
image_1 = image[0:1080, 0:1920]
image_2 = image[0:1080, 1920:3840]
writer_1.write(image)
image_1 = cv2.resize(image_1, (960, 540))
image_2 = cv2.resize(image_2, (960, 540))
cv2.imshow("video1", image_1)
cv2.imshow("video2", image_2)
if cv2.waitKey(1) > 0: break
capture.release()
cv2.destroyAllWindows()
import cv2
import numpy as np
#载入并显示图片'
img=cv2.imread('./python/a.png')
hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
lower_green = np.array([35, 43, 46])
upper_green = np.array([80, 255, 255])
mask = cv2.inRange(hsv, lower_green, upper_green)
res = cv2.bitwise_and(img, img, mask=mask)
cv2.imshow('img',res)
#灰度化
gray=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
#输出图像大小，方便根据图像大小调节minRadius和maxRadius
print(img.shape)
cv2.imshow('gray',gray)
th2 = cv2.adaptiveThreshold(gray,255,cv2.ADAPTIVE_THRESH_MEAN_C,\
cv2.THRESH_BINARY,11,2)
cv2.imshow('binary', th2)
ret,thresh1 = cv2.threshold(gray,200,255,cv2.THRESH_BINARY)
# cv2.imshow('thresh1', thresh1)
canny = cv2.Canny(thresh1,40,80)
cv2.imshow('Canny', canny)
canny=cv2.blur(canny,(3,3))
cv2.imshow('blur',canny)
default=True,
help="turn on bounding box")
args = vars(ap.parse_args())
detector = yoloDetection(args["yolo"], args["input"], args["confidence"],
args["threshold"], args["bbox"])
detector.prepareModel('ayush')
imgPath = 'images/'
images = os.listdir(imgPath)
print(images)
# for image in images:
# img = cv2.imread(imgPath+image)
# out = detector.runInference(img)
# if args["bbox"] is True:
# cv2.imshow(''.format(image), out)
# else:
# print(out)
img = cv2.imread(imgPath + images[2])
out = detector.runInference(img)
if args["bbox"] is True:
cv2.imshow('frame', out)
cv2.waitKey()
else:
print(out)
# Extract edges
canny_edges = cv2.Canny(img_gray_blur, 10, 70)
# Do an invert binarize the image
ret, mask = cv2.threshold(canny_edges, 70, 255, cv2.THRESH_BINARY_INV)
return mask
# Initialize webcam, cap is the object provided by VideoCapture
# It contains a boolean indicating if it was sucessful (ret)
# It also contains the images collected from the webcam (frame)
cap = cv2.VideoCapture(0)
while True:
ret, frame = cap.read()
cv2.imshow('Our Live Sketcher', sketch(frame))
if cv2.waitKey(1) == 13: #13 is the Enter Key
break
# Release camera and close windows
cap.release()
cv2.destroyAllWindows()
# In[ ]:
frame = imutils.resize(frame, width=400)
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
# detect faces in the grayscale frame
rects = detector(gray, 0)
# loop over the face detections
for rect in rects:
# determine the facial landmarks for the face region, then
# convert the facial landmark (x, y)-coordinates to a NumPy
# array
shape = predictor(gray, rect)
shape = face_utils.shape_to_np(shape)
# loop over the (x, y)-coordinates for the facial landmarks
# and draw them on the image
for (x, y) in shape:
cv2.circle(frame, (x, y), 1, (0, 0, 255), -1)
# show the frame
cv2.imshow("Frame", frame)
key = cv2.waitKey(1) & 0xFF
# if the `q` key was pressed, break from the loop
if key == ord("q"):
break
# do a bit of cleanup
cv2.destroyAllWindows()
vs.stop()
import cv2
import glob
images = glob.glob("*.jpg")
for image in images:
print(image)
img = cv2.imread(image,0)
resized_im = cv2.resize(img,(100,100))
cv2.imshow("Hey",resized_im)
cv2.imwrite("resized_"+image,resized_im)
cv2.waitKey(500)
cv2.destroyAllWindows()
'ncols'] #************* MENTION NO. OF COLS **********************
start_of_table = int(annotate_dict['page 1']['Start of Table'][1] * 1000 / h)
new_lst = list()
new_lst2 = list()
for x in new_crd:
if colfilter(x, rgb, NO_OF_COLS, start_of_table) == int(NO_OF_COLS):
new_lst.append(x)
else:
new_lst2.append(x)
#print(new_lst)
tmp3 = np.copy(rgb)
for crds in new_lst:
x, y, x1, y1 = crds
sub_image = tmp3[y - 2:y1 + 2, x - 2:x1 + 2]
d = pytesseract.image_to_data(sub_image,
output_type=Output.DICT,
lang='eng',
config='--psm 6')
cv2.rectangle(tmp3, (x - 1, y - 1), (x1 + 1, y1 + 1), (0, 0, 255), 1)
for t in d['text']:
print(t, end=' ')
print()
cv2.imshow("Img", tmp3)
cv2.waitKey()
cv2.imwrite('output.png', tmp3)
get_text(annotate_dict, np.copy(rgb), w, h)
import cv2
import ktb
k = ktb.Kinect()
while True:
color_frame = k.get_frame()
cv2.imshow('frame', color_frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
def visual(
image_id,
flag,
pairs_info,
score_HOI,
score_interact,
score_obj_box,
score_per_box,
score_REL,
score_HOI_pair,
ground_truth,
):
start = 0
for batch in range(len(image_id)):
this_image = int(image_id[batch])
a = helpers_pre.get_compact_detections(this_image, flag)
person_bbxn = a['person_bbx']
obj_bbxn = a['objects_bbx']
this_batch_pers = int(pairs_info[batch][0])
this_batch_objs = int(pairs_info[batch][1])
increment = this_batch_pers * this_batch_objs
ground_truth_this_batch = ground_truth[start:start + increment]
score_HOI_this_batch = score_HOI[start:start + increment]
start += increment
if flag == 'train':
cur_obj_path_s = OBJ_PATH_train_s \
+ 'COCO_train2014_%.12i.json' % this_image
image_dir_s = image_dir_train + '/COCO_train2014_%.12i.jpg' \
% this_image
elif flag == 'test':
cur_obj_path_s = OBJ_PATH_test_s \
+ 'COCO_val2014_%.12i.json' % this_image
image_dir_s = image_dir_test + '/COCO_val2014_%.12i.jpg' \
% this_image
elif flag == 'val':
cur_obj_path_s = OBJ_PATH_train_s \
+ 'COCO_train2014_%.12i.json' % this_image
image_dir_s = image_dir_val + '/COCO_train2014_%.12i.jpg' \
% this_image
with open(cur_obj_path_s) as fp:
detections = json.load(fp)
img_H = detections['H']
img_W = detections['W']
person_bbx = np.array([img_W, img_H, img_W, img_H],
dtype=float) * person_bbxn
obj_bbx = np.array([img_W, img_H, img_W, img_H], dtype=float) \
* obj_bbxn
img = cv2.imread(image_dir_s, 3)
start_index = 0
for person_box in person_bbx:
for object_box in obj_bbx:
ground_truth_this_sample = \
ground_truth_this_batch[start_index]
score_HOI_this_sample = \
score_HOI_this_batch[start_index]
print(score_HOI_this_sample)
pred = [('GROUND_TRUTH', [
(ID2VERB[ind],
float('%.2f' % ground_truth_this_sample[ind]))
for ind in np.argsort(ground_truth_this_sample)[-5:][::-1]
])]
pred.append(('TOTAL_PREDICTION', [
(ID2VERB[ind], float('%.2f' % score_HOI_this_sample[ind]))
for ind in np.argsort(score_HOI_this_sample)[-5:][::-1]
]))
prediction = pd.DataFrame(pred, columns=['Name', 'Prediction'])
img = cv2.imread(image_dir_s, 3)
(x, y, w, h) = (int(person_box[0]), int(person_box[1]),
int(person_box[2] - person_box[0]),
int(person_box[3] - person_box[1]))
cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 3)
(x, y, w, h) = (int(object_box[0]), int(object_box[1]),
int(object_box[2] - object_box[0]),
int(object_box[3] - object_box[1]))
cv2.rectangle(img, (x, y), (x + w, y + h), (0, 0, 255), 3)
print(this_image)
print('''Predictions (Five Highest Confidence Class):{}'''.
format(prediction))
# if ground_truth_this_sample[VERB2ID['catch']] == 1:
# cv2.imwrite('/home/d9/Documents/VSGNet/new_test_loss_best/result/catch/'+'%.12i' % this_image + str(start_index) + '.jpg', img)
# prediction.to_csv('/home/d9/Documents/VSGNet/new_test_loss_best/result/catch/'+'%.12i' % this_image + str(start_index) + '.csv')
cv2.imshow('image', img)
start_index += 1
k = cv2.waitKey(0)
if k == 27: # wait for ESC key to exit
cv2.destroyAllWindows()
if k == 27: # wait for ESC key to exit
cv2.destroyAllWindows()
if k == 27: # wait for ESC key to exit
cv2.destroyAllWindows()
cv2.destroyAllWindows()
def detectPlatesInScene(imgOriginalScene):
listOfPossiblePlates = [] # this will be the return value
height, width, numChannels = imgOriginalScene.shape
imgGrayscaleScene = np.zeros((height, width, 1), np.uint8)
imgThreshScene = np.zeros((height, width, 1), np.uint8)
imgContours = np.zeros((height, width, 3), np.uint8)
cv2.destroyAllWindows()
if Main.showSteps == True: # show steps
cv2.imshow("0", imgOriginalScene)
# end if # show steps
imgGrayscaleScene, imgThreshScene = Preprocess.preprocess(
imgOriginalScene) # preprocess to get grayscale and threshold images
if Main.showSteps == True: # show steps
cv2.imshow("1a", imgGrayscaleScene)
cv2.imshow("1b", imgThreshScene)
# end if # show steps
# find all possible chars in the scene,
# this function first finds all contours, then only includes contours that could be chars (without comparison to other chars yet)
listOfPossibleCharsInScene = findPossibleCharsInScene(imgThreshScene)
if Main.showSteps == True: # show steps
print("step 2 - len(listOfPossibleCharsInScene) = " +
str(len(listOfPossibleCharsInScene))) # 131 with MCLRNF1 image
imgContours = np.zeros((height, width, 3), np.uint8)
contours = []
for possibleChar in listOfPossibleCharsInScene:
contours.append(possibleChar.contour)
# end for
cv2.drawContours(imgContours, contours, -1, Main.SCALAR_WHITE)
cv2.imshow("2b", imgContours)
# end if # show steps
# given a list of all possible chars, find groups of matching chars
# in the next steps each group of matching chars will attempt to be recognized as a plate
listOfListsOfMatchingCharsInScene = DetectChars.findListOfListsOfMatchingChars(
listOfPossibleCharsInScene)
if Main.showSteps == True: # show steps
print("step 3 - listOfListsOfMatchingCharsInScene.Count = " + str(
len(listOfListsOfMatchingCharsInScene))) # 13 with MCLRNF1 image
imgContours = np.zeros((height, width, 3), np.uint8)
for listOfMatchingChars in listOfListsOfMatchingCharsInScene:
intRandomBlue = random.randint(0, 255)
intRandomGreen = random.randint(0, 255)
intRandomRed = random.randint(0, 255)
contours = []
for matchingChar in listOfMatchingChars:
contours.append(matchingChar.contour)
# end for
cv2.drawContours(imgContours, contours, -1,
(intRandomBlue, intRandomGreen, intRandomRed))
# end for
cv2.imshow("3", imgContours)
# end if # show steps
for listOfMatchingChars in listOfListsOfMatchingCharsInScene: # for each group of matching chars
possiblePlate = extractPlate(
imgOriginalScene, listOfMatchingChars) # attempt to extract plate
if possiblePlate.imgPlate is not None: # if plate was found
listOfPossiblePlates.append(
possiblePlate) # add to list of possible plates
# end if
# end for
print("\n" + str(len(listOfPossiblePlates)) +
" possible plates found") # 13 with MCLRNF1 image
if Main.showSteps == True: # show steps
print("\n")
cv2.imshow("4a", imgContours)
for i in range(0, len(listOfPossiblePlates)):
p2fRectPoints = cv2.boxPoints(
listOfPossiblePlates[i].rrLocationOfPlateInScene)
cv2.line(imgContours, tuple(p2fRectPoints[0]),
tuple(p2fRectPoints[1]), Main.SCALAR_RED, 2)
cv2.line(imgContours, tuple(p2fRectPoints[1]),
tuple(p2fRectPoints[2]), Main.SCALAR_RED, 2)
cv2.line(imgContours, tuple(p2fRectPoints[2]),
tuple(p2fRectPoints[3]), Main.SCALAR_RED, 2)
cv2.line(imgContours, tuple(p2fRectPoints[3]),
tuple(p2fRectPoints[0]), Main.SCALAR_RED, 2)
cv2.imshow("4a", imgContours)
print("possible plate " + str(i) +
", click on any image and press a key to continue . . .")
cv2.imshow("4b", listOfPossiblePlates[i].imgPlate)
cv2.waitKey(0)
# end for
print(
"\nplate detection complete, click on any image and press a key to begin char recognition . . .\n"
)
cv2.waitKey(0)
# end if # show steps
return listOfPossiblePlates
import matplotlib.pyplot as plt
import cv2
import numpy as np
img = cv2.imread("caro.PNG", 0)
cv2.imshow("nome da janela", img)
cv2.waitKey(0)
cv2.destroyAllWindows()
cv2.imwrite("novo.png", img)
cap = cv2.VideoCapture(0)
count = 0
# Collect 100 samples of your face from webcam input
while True:
ret, frame = cap.read()
if face_extractor(frame) is not None:
count += 1
face = cv2.resize(face_extractor(frame), (200, 200))
face = cv2.cvtColor(face, cv2.COLOR_BGR2GRAY)
# Save file in specified directory with unique name
file_name_path = '/webapp/uploads/cyber' + str(count) + '.jpg'
cv2.imwrite(file_name_path, face)
# Put count on images and display live count
cv2.putText(face, str(count), (50, 50), cv2.FONT_HERSHEY_COMPLEX, 1, (0,255,0), 2)
cv2.imshow('Face Cropper', face)
else:
print("Face not found")
pass
if cv2.waitKey(1) == 13 or count == 100: #13 is the Enter Key
break
cap.release()
cv2.destroyAllWindows()
print("Collecting Samples Complete")
import cv2
img = cv2.imread('C://Users//47463//Desktop//2//cat.jpg')
print(img.shape[:2])
height, width = img.shape[:2]
reSize1 = cv2.resize(img, (2*width, 2*height), interpolation=cv2.INTER_CUBIC)
reSize2 = cv2.resize(img, (int(width/2), int(height/2)), interpolation=cv2.INTER_CUBIC)
cv2.imshow('reSize1', reSize1)
cv2.imshow('reSize2', reSize2)
cv2.waitKey()
cv2.destroyAllWindows()
