@author Jeremy Barr
@date 5/1/2013
@brief Test program using OpenCV Python and raspicam. Background subtraction from camera images.
'''
import cv
from raspicam import RaspiCam
# capture image from camera
#capture = cv.CaptureFromCAM(0)
# Wait 200ms to initialize capture and take an image
#cv.WaitKey(200)
#frame = cv.QueryFrame(capture)
capture = RaspiCam()
frame = capture.piCapture()
''' frame gets copied into temp and then smoothed using CV_BLUR
CV_BLUR: linear convolution with size1 X size2 box kernel (all 1's)
with subsequent scaling by 1/(size1 * size2)
'''
temp = cv.CloneImage(frame)
cv.Smooth(temp, temp, cv.CV_BLUR, 5, 5)
while True:
frame = cv.QueryFrame(capture)
cv.AbsDiff(frame, temp, frame)
cv.ShowImage('Original', frame)
cv.ShowImage('Abs Diff', temp)
c = cv.WaitKey(2)
if c == 27: # Break if user enters ESC
break
def run(self):
template_filename = os.path.join(root, 'flash', 'fft2', 'processed', 'first_screen.png')
template = cv2.imread(template_filename, cv2.CV_LOAD_IMAGE_GRAYSCALE)
cv2.imshow('image', template)
w, h = template.shape[::-1]
#find starting image
map_filename = os.path.join(root, 'flash', 'fft2', 'processed', 'aligned_localization_data_map.png')
mapper = LocalizeMap(map_filename)
map_box = mapper.localize(template, None)
(x0, y0, x1, y1) = map_box
reference = mapper.reference[y0:y1, x0:x1]
cv2.imshow('image', reference)
#blank_image = np.zeros(template.shape, np.uint8)
cv2.waitKey(0)
cv2.destroyAllWindows()
return
# Capture first frame to get size
frame = cv.QueryFrame(self.capture)
frame_size = cv.GetSize(frame)
color_image = cv.CreateImage(cv.GetSize(frame), 8, 3)
grey_image = cv.CreateImage(cv.GetSize(frame), cv.IPL_DEPTH_8U, 1)
moving_average = cv.CreateImage(cv.GetSize(frame), cv.IPL_DEPTH_32F, 3)
first = True
while True:
closest_to_left = cv.GetSize(frame)[0]
closest_to_right = cv.GetSize(frame)[1]
color_image = cv.QueryFrame(self.capture)
# Smooth to get rid of false positives
cv.Smooth(color_image, color_image, cv.CV_GAUSSIAN, 3, 0)
if first:
difference = cv.CloneImage(color_image)
temp = cv.CloneImage(color_image)
cv.ConvertScale(color_image, moving_average, 1.0, 0.0)
first = False
else:
cv.RunningAvg(color_image, moving_average, 0.020, None)
# Convert the scale of the moving average.
cv.ConvertScale(moving_average, temp, 1.0, 0.0)
# Minus the current frame from the moving average.
cv.AbsDiff(color_image, temp, difference)
# Convert the image to grayscale.
cv.CvtColor(difference, grey_image, cv.CV_RGB2GRAY)
# Convert the image to black and white.
cv.Threshold(grey_image, grey_image, 70, 255, cv.CV_THRESH_BINARY)
# Dilate and erode to get people blobs
cv.Dilate(grey_image, grey_image, None, 18)
cv.Erode(grey_image, grey_image, None, 10)
storage = cv.CreateMemStorage(0)
contour = cv.FindContours(grey_image, storage, cv.CV_RETR_CCOMP, cv.CV_CHAIN_APPROX_SIMPLE)
points = []
while contour:
bound_rect = cv.BoundingRect(list(contour))
contour = contour.h_next()
pt1 = (bound_rect[0], bound_rect[1])
pt2 = (bound_rect[0] + bound_rect[2], bound_rect[1] + bound_rect[3])
points.append(pt1)
points.append(pt2)
cv.Rectangle(color_image, pt1, pt2, cv.CV_RGB(255,0,0), 1)
if len(points):
center_point = reduce(lambda a, b: ((a[0] + b[0]) / 2, (a[1] + b[1]) / 2), points)
cv.Circle(color_image, center_point, 40, cv.CV_RGB(255, 255, 255), 1)
cv.Circle(color_image, center_point, 30, cv.CV_RGB(255, 100, 0), 1)
cv.Circle(color_image, center_point, 20, cv.CV_RGB(255, 255, 255), 1)
cv.Circle(color_image, center_point, 10, cv.CV_RGB(255, 100, 0), 1)
cv.ShowImage("Target", color_image)
# Listen for ESC key
c = cv.WaitKey(7) % 0x100
if c == 27:
break
cv.FindHomography(p, h, p2h)
#cv.ReleaseMat(p)
#cv.ReleaseMat(h)
return p2h
im_in = cv.LoadImage(sys.argv[1], 4)
#out = cvLoadImage(sys.argv[1], 4)
width = 1093 #800
height = 573 #int(width*(im_in.height/float(im_in.width)))
print 'working on %dx%d' % (width, height)
im = cv.CreateImage((1096, 576), cv.IPL_DEPTH_8U, 1)
cv.Resize(im_in, im)
cv.NamedWindow(WINDOW_NAME, 1)
cv.ShowImage(WINDOW_NAME, im)
cv.SetMouseCallback(WINDOW_NAME, mouse, im)
cv.WaitKey(0)
h**o = calc(im_in.width, im_in.height, im.width, im.height)
cv.Save('homography.cvmat', h**o)
out = cv.CloneImage(im_in)
cv.WarpPerspective(im_in, out, h**o)
out_small = cv.CloneImage(im)
cv.Resize(out, out_small)
cv.ShowImage(WINDOW_NAME, out_small)
cv.WaitKey(0)
def run(self):
frame = cv.QueryFrame(self.capture) # Capture the first frame
frame_size = cv.GetSize(
frame) # Get the size of the frame in pixels e.g. 640x480
color_image = cv.CreateImage(cv.GetSize(frame), 8, 3)
grey_image = cv.CreateImage(cv.GetSize(frame), cv.IPL_DEPTH_8U, 1)
moving_average = cv.CreateImage(cv.GetSize(frame), cv.IPL_DEPTH_32F, 3)
first = True
while True:
closest_to_left = cv.GetSize(frame)[0]
closest_to_right = cv.GetSize(frame)[1]
color_image = cv.QueryFrame(self.capture)
# Smooth to get rid of false positives
cv.Smooth(color_image, color_image, cv.CV_GAUSSIAN, 3, 0)
if first:
difference = cv.CloneImage(color_image)
temp = cv.CloneImage(color_image)
cv.ConvertScale(color_image, moving_average, 1.0, 0.0)
first = False
else:
cv.RunningAvg(color_image, moving_average, 0.020, None)
# Convert the scale of the moving average.
cv.ConvertScale(moving_average, temp, 1.0, 0.0)
# Minus the current frame from the moving average.
cv.AbsDiff(color_image, temp, difference)
# Convert the image to grayscale.
cv.CvtColor(difference, grey_image, cv.CV_RGB2GRAY)
# Convert the image to black and white.
cv.Threshold(grey_image, grey_image, 70, 255, cv.CV_THRESH_BINARY)
# Dilate and erode to get people blobs
cv.Dilate(grey_image, grey_image, None, 18)
cv.Erode(grey_image, grey_image, None, 10)
storage = cv.CreateMemStorage(0)
contour = cv.FindContours(grey_image, storage, cv.CV_RETR_CCOMP,
cv.CV_CHAIN_APPROX_SIMPLE)
points = []
while contour:
bound_rect = cv.BoundingRect(list(contour))
contour = contour.h_next()
pt1 = (bound_rect[0], bound_rect[1])
pt2 = (bound_rect[0] + bound_rect[2],
bound_rect[1] + bound_rect[3])
points.append(pt1)
points.append(pt2)
cv.Rectangle(color_image, pt1, pt2, cv.CV_RGB(255, 0, 0), 1)
if len(points):
center_point = reduce(
lambda a, b: ((a[0] + b[0]) / 2, (a[1] + b[1]) / 2),
points)
cv.Circle(color_image, center_point, 40,
cv.CV_RGB(255, 255, 255), 1)
cv.Circle(color_image, center_point, 30,
cv.CV_RGB(255, 100, 0), 1)
cv.Circle(color_image, center_point, 20,
cv.CV_RGB(255, 255, 255), 1)
cv.Circle(color_image, center_point, 10,
cv.CV_RGB(255, 100, 0), 1)
xangle = 0
if center_point[0] < 320:
xangle = int(90 + ((center_point[0] - 320) / 22.857))
elif center_point[0] == 320:
xangle = 90
else:
xangle = int(90 + center_point[0] / 22.857)
yangle = 0
if center_point[1] < 240:
yangle = int(90 + center_point[1] / 12)
elif center_point[1] == 240:
yangle = 93
else:
yangle = int(90 - ((center_point[1] - 240) / 12))
print "Xangle = ", xangle
self.firecontrol.sendcoord(0xff, xangle, yangle)
current_position = center_point
self.firecontrol.fire(0xfe)
print "Located at: ", current_position
# fire_control.engage()
# print "Fire: ", self.pos
self.pos = center_point
cv.ShowImage("Target", color_image)
# Listen for ESC key
c = cv.WaitKey(7) % 0x100
if c == 27:
break
def process_frame(self, frame):
#import pdb
# pdb.set_trace()
if self.debug:
debug = cv.CreateImage(cv.GetSize(frame), 8, 3)
debug = cv.CloneImage(frame)
# look for bins (the black rectangles, not the X's and O's)
rects = libvision.letters.find_bins(frame)
# record rectangles(bins) found
cur_bins = [
Bin(0, (rect.center[0] - frame.width / 2,
frame.height / 2 - rect.center[1]), rect.theta, rect.area)
for rect in rects
]
# detect correctly colored regions
binary = libvision.cmodules.target_color_rgb.find_target_color_rgb(
frame, 250, 0, 0, 500, 800, .3)
# clean up the color detect
cv.Dilate(binary, binary, None, 1)
cv.Erode(binary, binary, None, 1)
# collect blobs
blob_indexed = cv.CreateImage(cv.GetSize(binary), 8, 1)
blobs = libvision.blob.find_blobs(binary, blob_indexed, 50, 2)
# check blobs for letters
for i, blob in enumerate(blobs):
# check if the blob is a letter
letter = libvision.cmodules.shape_detect.match_letters(
blob_indexed, i + 1, blob.centroid[0], blob.centroid[1],
blob.roi[0], blob.roi[1], blob.roi[2], blob.roi[3])
if (not letter):
continue
# check to see if this letter is within a known bin
letter_placed = False
for a_bin in cur_bins:
radius = int(math.sqrt(a_bin.area / 2) / 2)
x_dif = (blob.centroid[0] - a_bin.center[0])**2
y_dif = (blob.centroid[1] - a_bin.center[1])**2
tot_dif = math.sqrt(x_dif + y_dif)
if (tot_dif < radius):
# this letter is in a rectangle!
a_bin.type = letter
letter_placed = True
break
if (not letter_placed):
# make a new bin for this floating letter
cur_bins.append(
Bin(letter, (blob.centroid[0] - frame.width / 2,
frame.height / 2 - blob.centroid[1]), 0, 0))
# Compare Bins
# --- tune-able values --- #
max_travel = 60
missing_travel = 100
timeout_inc = 10
promo_req = 25
timeout_dec = 5
timeout_cap = 50
type_count_thresh = 3
missing_timeout = 200
# ------------------------ #
# decide if we've seen any current bin before
for a_bin in cur_bins:
bin_recognized = False
# check known bin bins
for known_bin in self.known_bins:
# compute distance between bins
x_dif = a_bin.center[0] - known_bin.center[0]
y_dif = a_bin.center[1] - known_bin.center[1]
tot_dif = math.sqrt(x_dif**2 + y_dif**2)
if (tot_dif < max_travel):
# update this known_bin
known_bin.timeout += timeout_inc
known_bin.type_counts[a_bin.type] += 1
known_bin.center = a_bin.center
known_bin.angle = a_bin.angle
if (a_bin.area):
known_bin.area = a_bin.area
bin_recognized = True
break
if (bin_recognized):
continue
# check missing bins
for missing_bin in self.missing:
# compute distance between bins
x_dif = a_bin.center[0] - missing_bin.center[0]
y_dif = a_bin.center[1] - missing_bin.center[1]
tot_dif = math.sqrt(x_dif**2 + y_dif**2)
if (tot_dif < missing_travel):
# re-instate this missing bin as a candidate
missing_bin.timeout = 10
self.candidates.append(missing_bin)
self.missing.remove(missing_bin)
bin_recognized = True
if (bin_recognized):
continue
# not a known bin, check candidates
for candidate in self.candidates:
# compute distance between bins
x_dif = a_bin.center[0] - candidate.center[0]
y_dif = a_bin.center[1] - candidate.center[1]
tot_dif = math.sqrt(x_dif**2 + y_dif**2)
if (tot_dif < max_travel):
# update this candidate
candidate.timeout += timeout_inc
candidate.type_counts[a_bin.type] += 1
candidate.center = a_bin.center
candidate.angle - a_bin.angle
if (a_bin.area):
candidate.area = a_bin.area
bin_recognized = True
break
if (bin_recognized):
continue
# add this bin as a new candidate
a_bin.type_counts[a_bin.type] += 1
a_bin.type = 0
self.candidates.append(a_bin)
# promote / time out candidates
for candidate in self.candidates:
candidate.timeout -= timeout_dec
if (candidate.timeout <= 0):
if (candidate.id):
candidate.timeout = missing_timeout
self.missing.append(candidate)
self.candidates.remove(candidate)
continue
if (candidate.timeout >= promo_req):
if (candidate.id == 0):
self.bins_seen += 1
candidate.id = self.bins_seen
self.known_bins.append(candidate)
self.candidates.remove(candidate)
# handle timeout of known bins
for known_bin in self.known_bins:
# select max type
# if greater than type thresh
# assign type
if (not known_bin.type):
for i, value in enumerate(known_bin.type_counts):
if (i and value >= type_count_thresh):
known_bin.type = i
# decrement timeout
known_bin.timeout -= timeout_dec
# remove timed-out bins
if (known_bin.timeout <= 0):
known_bin.timeout = missing_timeout
self.missing.append(known_bin)
self.known_bins.remove(known_bin)
continue
# cap timeout
if (known_bin.timeout > timeout_cap):
known_bin.timeout = timeout_cap
# decrement timeouts on missing bins
for missing_bin in self.missing:
missing_bin.timeout -= timeout_dec
if (missing_bin.timeout <= 0):
self.missing.remove(missing_bin)
if self.debug:
'''
#draw circles to mark bins
for a_bin in cur_bins:
if(a_bin.area == 0):
continue
radius = int( math.sqrt(a_bin.area/2) / 2);
if(a_bin.type == 0):
bin_color = (255,0,255)
elif(a_bin.type == 1):
bin_color = (0,255,0)
elif(a_bin.type == 2):
bin_color = (0,0,255)
cv.Circle(debug,a_bin.center,radius,bin_color,2,8,0)
'''
# draw circles to mark bins
for a_bin in self.known_bins:
if (a_bin.area == 0):
radius = 20
else:
radius = int(math.sqrt(a_bin.area / 2) / 2)
if (a_bin.type == 0):
bin_color = (255, 0, 255)
elif (a_bin.type == 1):
bin_color = (0, 255, 0)
elif (a_bin.type == 2):
bin_color = (0, 0, 255)
tmp_center = (int(a_bin.center[0] + frame.width / 2),
int(frame.height / 2 - a_bin.center[1]))
cv.Circle(debug, tmp_center, radius, bin_color, 2, 8, 0)
if (a_bin.id > 5):
self.bins_seen -= 5
a_bin.id -= 5
if (a_bin.id == 1):
id_color = (0, 0, 0)
elif (a_bin.id == 2):
id_color = (255, 255, 255)
elif (a_bin.id == 3):
id_color = (120, 120, 120)
elif (a_bin.id == 4):
id_color = (255, 0, 0)
elif (a_bin.id == 5):
id_color = (0, 255, 255)
else:
continue
cv.Circle(debug, tmp_center, radius - 2, id_color, 2, 8, 0)
# cv.ShowImage("Binary",binary)
# cv.ShowImage("Bins",bins)
# cv.ShowImage("Filtered",filtered)
cv.ShowImage("Python Debug", debug)
# populate self.output with infos
self.output.see_bin = False
self.return_output()
grey_image = cv.CreateImage(cv.GetSize(frame), cv.IPL_DEPTH_8U, 1)
test=cv.CreateImage(cv.GetSize(frame),8,3)
img2=cv.CreateImage(cv.GetSize(frame),8,3)
cv.NamedWindow("Real",0)
cv.NamedWindow("Threshold",0)
#cv.NamedWindow("Final",0)
while(1):
color_image = cv.QueryFrame(capture)
imdraw=cv.CreateImage(cv.GetSize(frame),8,3)
cv.SetZero(imdraw)
cv.Flip(color_image,color_image,1)
cv.Smooth(color_image, color_image, cv.CV_GAUSSIAN, 3, 0)
imgyellowthresh=getthresholdedimg(color_image)
cv.Erode(imgyellowthresh,imgyellowthresh,None,3)
cv.Dilate(imgyellowthresh,imgyellowthresh,None,10)
img2=cv.CloneImage(imgyellowthresh)
storage = cv.CreateMemStorage(0)
contour = cv.FindContours(imgyellowthresh, storage, cv.CV_RETR_CCOMP, cv.CV_CHAIN_APPROX_SIMPLE)
points = []
while contour:
# Draw bounding rectangles
bound_rect = cv.BoundingRect(list(contour))
contour = contour.h_next()
# for more details about cv.BoundingRect,see documentation
pt1 = (bound_rect[0], bound_rect[1])
pt2 = (bound_rect[0] + bound_rect[2], bound_rect[1] + bound_rect[3])
points.append(pt1)
points.append(pt2)
cv.Rectangle(color_image, pt1, pt2, cv.CV_RGB(255,0,0), 2)
names = [
"../c/pic1.png", "../c/pic2.png", "../c/pic3.png", "../c/pic4.png",
"../c/pic5.png", "../c/pic6.png"
]
if __name__ == "__main__":
# create memory storage that will contain all the dynamic data
storage = cv.CreateMemStorage(0)
for name in names:
img0 = cv.LoadImage(name, 1)
if not img0:
print "Couldn't load %s" % name
continue
img = cv.CloneImage(img0)
# create window and a trackbar (slider) with parent "image" and set callback
# (the slider regulates upper threshold, passed to Canny edge detector)
cv.NamedWindow(wndname, 1)
cv.CreateTrackbar("canny thresh", wndname, thresh, 1000, on_trackbar)
# force the image processing
on_trackbar(0)
# wait for key.
# Also the function cv.WaitKey takes care of event processing
c = cv.WaitKey(0) % 0x100
# clear memory storage - reset free space position
cv.ClearMemStorage(storage)
if (c == '\x1b'):
break
cv.DestroyWindow(wndname)
import numpy
import cv
capture = cv.CaptureFromCAM(0)
imageSize = 1280, 720
h = 0
s = 0
v = 0
channels3 = cv.CreateImage(imageSize, 8, 3)
channels1 = cv.CreateImage(imageSize, 8, 1)
while True:
frame = cv.QueryFrame(capture)
clone = cv.CloneImage(frame)
hsv = cv.CloneImage(channels3)
threshold = cv.CloneImage(channels1)
threshold2 = cv.CloneImage(channels1)
cv.CvtColor(clone, hsv, cv.CV_BGR2HSV)
cv.InRangeS(hsv, (110, 120, 75), (140, 255, 255), threshold)
cv.InRangeS(hsv, (110, 120, 75), (140, 255, 255), threshold2)
cv.Add(threshold, threshold2, threshold)
cv.Erode(threshold, threshold, iterations=5)
cv.Dilate(threshold, threshold, iterations=5)
cv.ShowImage("normal", frame)
cv.ShowImage("color", threshold)
def __init__(self):
self.threshold_value = THRESH # value associated with slider bar
self.capture = cv.CaptureFromCAM(0)
cv.SetCaptureProperty(self.capture, cv.CV_CAP_PROP_FRAME_WIDTH, 640)
cv.SetCaptureProperty(self.capture, cv.CV_CAP_PROP_FRAME_HEIGHT, 480)
self.hc = cv.Load(HAARCASCADE)
self.ms = cv.CreateMemStorage()
self.orig = cv.QueryFrame(self.capture)
if not self.orig:
print "can't get frame, check camera"
sys.exit(2)
self.width = self.orig.width
self.height = self.orig.height
self.size = (self.width, self.height)
self.smallwidth = int(self.width / SCALING)
self.smallheight = int(self.height / SCALING)
self.smallsize = (self.smallwidth, self.smallheight)
# alloc mem for images
self.small = cv.CreateImage(self.smallsize, cv.IPL_DEPTH_8U, 3)
self.visualize = cv.CreateImage(self.smallsize, cv.IPL_DEPTH_8U, 3)
self.bw = cv.CreateImage(self.smallsize, cv.IPL_DEPTH_8U, 1)
self.hsv = cv.CreateImage(self.smallsize, cv.IPL_DEPTH_8U, 3)
self.hue = cv.CreateImage(self.smallsize, cv.IPL_DEPTH_8U, 1)
self.sat = cv.CreateImage(self.smallsize, cv.IPL_DEPTH_8U, 1)
self.val = cv.CreateImage(self.smallsize, cv.IPL_DEPTH_8U, 1)
self.bp = cv.CreateImage(self.smallsize, cv.IPL_DEPTH_8U, 1)
self.scaled = cv.CreateImage(self.smallsize, cv.IPL_DEPTH_8U, 1)
self.th = cv.CreateImage(self.smallsize, cv.IPL_DEPTH_8U, 1)
self.morphed = cv.CreateImage(self.smallsize, cv.IPL_DEPTH_8U, 1)
self.temp = cv.CreateImage(self.smallsize, cv.IPL_DEPTH_8U, 1)
self.temp3 = cv.CreateImage(self.smallsize, cv.IPL_DEPTH_8U, 3)
self.result = cv.CreateImage(self.smallsize, cv.IPL_DEPTH_8U, 3)
self.hist_image = cv.CreateImage((320, 200), cv.IPL_DEPTH_8U, 1)
self.scaled_c = cv.CreateImage(self.smallsize, cv.IPL_DEPTH_8U, 3)
self.hue_c = cv.CreateImage(self.smallsize, cv.IPL_DEPTH_8U, 3)
self.sat_c = cv.CreateImage(self.smallsize, cv.IPL_DEPTH_8U, 3)
self.th_c = cv.CreateImage(self.smallsize, cv.IPL_DEPTH_8U, 3)
self.morphed_c = cv.CreateImage(self.smallsize, cv.IPL_DEPTH_8U, 3)
# Greyscale image, thresholded to create the motion mask:
self.grey_image = cv.CreateImage(self.smallsize, cv.IPL_DEPTH_8U, 1)
# The RunningAvg() function requires a 32-bit or 64-bit image...
self.running_average_image = cv.CreateImage(self.smallsize,
cv.IPL_DEPTH_32F, 3)
# ...but the AbsDiff() function requires matching image depths:
self.running_average_in_display_color_depth = cv.CloneImage(self.small)
# RAM used by FindContours():
self.mem_storage = cv.CreateMemStorage(0)
print "here"
# The difference between the running average and the current frame:
self.difference = cv.CloneImage(self.small)
self.target_count = 1
self.last_target_count = 1
self.last_target_change_t = 0.0
self.k_or_guess = 1
self.codebook = []
self.frame_count = 0
self.last_frame_entity_list = []
# make matrix for erode/dilate
MORPH_SIZE = 3
center = (MORPH_SIZE / 2) + 1
self.morpher_small = cv.CreateStructuringElementEx(
MORPH_SIZE, MORPH_SIZE, center, center, cv.CV_SHAPE_ELLIPSE)
# self.morpher_small = cv.CreateStructuringElementEx(cols=MORPH_SIZE, rows=MORPH_SIZE, anchor_x=center, anchor_y=center, shape=cv.CV_SHAPE_ELLIPSE)
MORPH_SIZE = 11
center = (MORPH_SIZE / 2) + 1
self.morpher = cv.CreateStructuringElementEx(MORPH_SIZE, MORPH_SIZE,
center, center,
cv.CV_SHAPE_ELLIPSE)
# alloc mem for histogram
self.hist = cv.CreateHist([HUEBINS, SATBINS], cv.CV_HIST_ARRAY,
[[0, 180], [0, 255]], 1)
# initalize
#cv.CvtColor(self.small, self.bw, cv.CV_BGR2GRAY)
#cv.CvtColor(self.small, self.hsv, cv.CV_BGR2HSV)
#cv.CalcArrHist([self.hue, self.sat], self.hist)
# video writer
if STORE:
self.writer = cv.CreateVideoWriter(OUTPUT,
cv.CV_FOURCC(
'M', 'J', 'P', 'G'),
15,
cv.GetSize(self.combined),
is_color=1)
# make window
cv.NamedWindow('Skin Detection')
cv.CreateTrackbar('Threshold', 'Skin Detection', self.threshold_value,
255, self.change_threshold)
cv.NamedWindow("Regiao de Interesse", 1)
cv.MoveWindow("Regiao de Interesse", 1000, 480)
cv.MoveWindow("Mascara", 0, 500)
cv.MoveWindow("Binario", 400, 500)
arquivo = open('Treino.txt', 'a')
mascara = cv.CreateImage((resolucao_largura, resolucao_altura), 8, 3)
cinza = cv.CreateImage((resolucao_largura, resolucao_altura), 8, 1)
while True:
print("Por Favor tire uma foto do fundo estatico do seu video.")
print("Aperte a tecla espaco.")
if cv.WaitKey(0) % 0x100 == 32:
primeiraImagem = cv.QueryFrame(captura)
fundo = cv.CloneImage(primeiraImagem)
cv.Smooth(fundo, fundo, cv.CV_GAUSSIAN, filtro_de_gauss)
print("Tirou uma Foto !")
break
else:
print "Uma foto do fundo nao foi tirada"
break
while True:
imagem = cv.QueryFrame(captura)
cv.Smooth(imagem, imagem, cv.CV_GAUSSIAN, filtro_de_gauss)
maiorArea = 0
listaContornos = []
listaVertices = []
quadrante = []
def FindObject(frame):
global old_frame
global gftt_list
global weights
global existence
if not MovingHead():
try:
mask = FrameMask(old_frame, frame)
except:
old_frame = cv.CloneImage(frame)
gftt_list = list()
return None, None, False
else:
old_frame = cv.CloneImage(frame)
gftt_list = list()
return None, None, False
if mask == None:
gftt_list = list()
print "2"
return None, None, False
## Find Good Features to track
if len(gftt_list) < 300:
#gftt_list.append((GoodFeaturesToTrack(old_frame, mask),1))
gftt_new, weights_new, existence_new = GoodFeaturesToTrack(
old_frame, mask)
if gftt_new != None:
gftt_list = gftt_list + gftt_new
weights = weights + weights_new
existence = existence + existence_new
gftt_list_new, weights, existence = OpticalFlow(frame, old_frame,
gftt_list, weights,
existence)
weights, existence = UpdatePointWeights(gftt_list_new, gftt_list, weights,
existence)
gftt_list = gftt_list_new
gftt_list, weights, existence = DropPoints(gftt_list, weights, existence)
gftt_img = DrawPoints(frame, gftt_list)
if len(gftt_list) > 30:
loc_obj = list()
loc_obj = AvgPoint(gftt_list, 1)
cv.Circle(gftt_img, loc_obj, 4, 255, 4, 8, 0)
convrad = 0.55 / (frame.width / 2)
loc_obj = list(loc_obj)
loc_obj[0] = (loc_obj[0] - (frame.width / 2)) * convrad
loc_obj[1] = (loc_obj[1] - (frame.height / 2)) * convrad
else:
loc_obj = (None, None)
cv.ShowImage("Good Features", gftt_img)
cv.ShowImage("Difference", mask)
cv.Copy(frame, old_frame)
if MovingHead():
print "Object Location = 0"
loc_obj[0] = 0
loc_obj[1] = 0
gftt_list = list()
old_frame = 0
return loc_obj[0], loc_obj[1], True
def run(self):
# Initialize
#log_file_name = "tracker_output.log"
#log_file = file( log_file_name, 'a' )
frame = cv.QueryFrame(self.capture)
frame_size = cv.GetSize(frame)
# Capture the first frame from webcam for image properties
display_image = cv.QueryFrame(self.capture)
# Greyscale image, thresholded to create the motion mask:
grey_image = cv.CreateImage(cv.GetSize(frame), cv.IPL_DEPTH_8U, 1)
# The RunningAvg() function requires a 32-bit or 64-bit image...
running_average_image = cv.CreateImage(cv.GetSize(frame),
cv.IPL_DEPTH_32F, 3)
# ...but the AbsDiff() function requires matching image depths:
running_average_in_display_color_depth = cv.CloneImage(display_image)
# RAM used by FindContours():
mem_storage = cv.CreateMemStorage(0)
# The difference between the running average and the current frame:
difference = cv.CloneImage(display_image)
target_count = 1
last_target_count = 1
last_target_change_t = 0.0
k_or_guess = 1
codebook = []
frame_count = 0
last_frame_entity_list = []
t0 = time.time()
# For toggling display:
image_list = ["camera", "difference", "threshold", "display", "faces"]
image_index = 0 # Index into image_list
# Prep for text drawing:
text_font = cv.InitFont(cv.CV_FONT_HERSHEY_COMPLEX, .5, .5, 0.0, 1,
cv.CV_AA)
text_coord = (5, 15)
text_color = cv.CV_RGB(255, 255, 255)
###############################
### Face detection stuff
#haar_cascade = cv.Load( 'haarcascades/haarcascade_frontalface_default.xml' )
haar_cascade = cv.Load('haarcascades/haarcascade_frontalface_alt.xml')
#haar_cascade = cv.Load( 'haarcascades/haarcascade_frontalface_alt2.xml' )
#haar_cascade = cv.Load( 'haarcascades/haarcascade_mcs_mouth.xml' )
#haar_cascade = cv.Load( 'haarcascades/haarcascade_eye.xml' )
#haar_cascade = cv.Load( 'haarcascades/haarcascade_frontalface_alt_tree.xml' )
#haar_cascade = cv.Load( 'haarcascades/haarcascade_upperbody.xml' )
#haar_cascade = cv.Load( 'haarcascades/haarcascade_profileface.xml' )
# Set this to the max number of targets to look for (passed to k-means):
max_targets = 3
while True:
# Capture frame from webcam
camera_image = cv.QueryFrame(self.capture)
frame_count += 1
frame_t0 = time.time()
# Create an image with interactive feedback:
display_image = cv.CloneImage(camera_image)
# Create a working "color image" to modify / blur
color_image = cv.CloneImage(display_image)
# Smooth to get rid of false positives
cv.Smooth(color_image, color_image, cv.CV_GAUSSIAN, 19, 0)
# Use the Running Average as the static background
# a = 0.020 leaves artifacts lingering way too long.
# a = 0.320 works well at 320x240, 15fps. (1/a is roughly num frames.)
cv.RunningAvg(color_image, running_average_image, 0.320, None)
# Convert the scale of the moving average.
cv.ConvertScale(running_average_image,
running_average_in_display_color_depth, 1.0, 0.0)
# Subtract the current frame from the moving average.
cv.AbsDiff(color_image, running_average_in_display_color_depth,
difference)
# Convert the image to greyscale.
cv.CvtColor(difference, grey_image, cv.CV_RGB2GRAY)
# Threshold the image to a black and white motion mask:
cv.Threshold(grey_image, grey_image, 2, 255, cv.CV_THRESH_BINARY)
# Smooth and threshold again to eliminate "sparkles"
cv.Smooth(grey_image, grey_image, cv.CV_GAUSSIAN, 19, 0)
cv.Threshold(grey_image, grey_image, 240, 255, cv.CV_THRESH_BINARY)
grey_image_as_array = numpy.asarray(cv.GetMat(grey_image))
non_black_coords_array = numpy.where(grey_image_as_array > 3)
# Convert from numpy.where()'s two separate lists to one list of (x, y) tuples:
non_black_coords_array = zip(non_black_coords_array[1],
non_black_coords_array[0])
points = [
] # Was using this to hold either pixel coords or polygon coords.
bounding_box_list = []
# Now calculate movements using the white pixels as "motion" data
contour = cv.FindContours(grey_image, mem_storage,
cv.CV_RETR_CCOMP,
cv.CV_CHAIN_APPROX_SIMPLE)
while contour:
bounding_rect = cv.BoundingRect(list(contour))
point1 = (bounding_rect[0], bounding_rect[1])
point2 = (bounding_rect[0] + bounding_rect[2],
bounding_rect[1] + bounding_rect[3])
bounding_box_list.append((point1, point2))
polygon_points = cv.ApproxPoly(list(contour), mem_storage,
cv.CV_POLY_APPROX_DP)
# To track polygon points only (instead of every pixel):
#points += list(polygon_points)
# Draw the contours:
###cv.DrawContours(color_image, contour, cv.CV_RGB(255,0,0), cv.CV_RGB(0,255,0), levels, 3, 0, (0,0) )
cv.FillPoly(grey_image, [
list(polygon_points),
], cv.CV_RGB(255, 255, 255), 0, 0)
cv.PolyLine(display_image, [
polygon_points,
], 0, cv.CV_RGB(255, 255, 255), 1, 0, 0)
#cv.Rectangle( display_image, point1, point2, cv.CV_RGB(120,120,120), 1)
contour = contour.h_next()
# Find the average size of the bbox (targets), then
# remove any tiny bboxes (which are prolly just noise).
# "Tiny" is defined as any box with 1/10th the area of the average box.
# This reduces false positives on tiny "sparkles" noise.
box_areas = []
for box in bounding_box_list:
box_width = box[right][0] - box[left][0]
box_height = box[bottom][0] - box[top][0]
box_areas.append(box_width * box_height)
#cv.Rectangle( display_image, box[0], box[1], cv.CV_RGB(255,0,0), 1)
average_box_area = 0.0
if len(box_areas):
average_box_area = float(sum(box_areas)) / len(box_areas)
trimmed_box_list = []
for box in bounding_box_list:
box_width = box[right][0] - box[left][0]
box_height = box[bottom][0] - box[top][0]
# Only keep the box if it's not a tiny noise box:
if (box_width * box_height) > average_box_area * 0.1:
trimmed_box_list.append(box)
# Draw the trimmed box list:
#for box in trimmed_box_list:
# cv.Rectangle( display_image, box[0], box[1], cv.CV_RGB(0,255,0), 2 )
bounding_box_list = merge_collided_bboxes(trimmed_box_list)
# Draw the merged box list:
for box in bounding_box_list:
cv.Rectangle(display_image, box[0], box[1],
cv.CV_RGB(0, 255, 0), 1)
# Here are our estimate points to track, based on merged & trimmed boxes:
estimated_target_count = len(bounding_box_list)
# Don't allow target "jumps" from few to many or many to few.
# Only change the number of targets up to one target per n seconds.
# This fixes the "exploding number of targets" when something stops moving
# and the motion erodes to disparate little puddles all over the place.
if frame_t0 - last_target_change_t < .350: # 1 change per 0.35 secs
estimated_target_count = last_target_count
else:
if last_target_count - estimated_target_count > 1:
estimated_target_count = last_target_count - 1
if estimated_target_count - last_target_count > 1:
estimated_target_count = last_target_count + 1
last_target_change_t = frame_t0
# Clip to the user-supplied maximum:
estimated_target_count = min(estimated_target_count, max_targets)
# The estimated_target_count at this point is the maximum number of targets
# we want to look for. If kmeans decides that one of our candidate
# bboxes is not actually a target, we remove it from the target list below.
# Using the numpy values directly (treating all pixels as points):
points = non_black_coords_array
center_points = []
if len(points):
# If we have all the "target_count" targets from last frame,
# use the previously known targets (for greater accuracy).
k_or_guess = max(estimated_target_count,
1) # Need at least one target to look for.
if len(codebook) == estimated_target_count:
k_or_guess = codebook
#points = vq.whiten(array( points )) # Don't do this! Ruins everything.
codebook, distortion = vq.kmeans(array(points), k_or_guess)
# Convert to tuples (and draw it to screen)
for center_point in codebook:
center_point = (int(center_point[0]), int(center_point[1]))
center_points.append(center_point)
#cv.Circle(display_image, center_point, 10, cv.CV_RGB(255, 0, 0), 2)
#cv.Circle(display_image, center_point, 5, cv.CV_RGB(255, 0, 0), 3)
# Now we have targets that are NOT computed from bboxes -- just
# movement weights (according to kmeans). If any two targets are
# within the same "bbox count", average them into a single target.
#
# (Any kmeans targets not within a bbox are also kept.)
trimmed_center_points = []
removed_center_points = []
for box in bounding_box_list:
# Find the centers within this box:
center_points_in_box = []
for center_point in center_points:
if center_point[0] < box[right][0] and center_point[0] > box[left][0] and \
center_point[1] < box[bottom][1] and center_point[1] > box[top][1] :
# This point is within the box.
center_points_in_box.append(center_point)
# Now see if there are more than one. If so, merge them.
if len(center_points_in_box) > 1:
# Merge them:
x_list = y_list = []
for point in center_points_in_box:
x_list.append(point[0])
y_list.append(point[1])
average_x = int(float(sum(x_list)) / len(x_list))
average_y = int(float(sum(y_list)) / len(y_list))
trimmed_center_points.append((average_x, average_y))
# Record that they were removed:
removed_center_points += center_points_in_box
if len(center_points_in_box) == 1:
trimmed_center_points.append(
center_points_in_box[0]) # Just use it.
# If there are any center_points not within a bbox, just use them.
# (It's probably a cluster comprised of a bunch of small bboxes.)
for center_point in center_points:
if (not center_point in trimmed_center_points) and (
not center_point in removed_center_points):
trimmed_center_points.append(center_point)
# Draw what we found:
#for center_point in trimmed_center_points:
# center_point = ( int(center_point[0]), int(center_point[1]) )
# cv.Circle(display_image, center_point, 20, cv.CV_RGB(255, 255,255), 1)
# cv.Circle(display_image, center_point, 15, cv.CV_RGB(100, 255, 255), 1)
# cv.Circle(display_image, center_point, 10, cv.CV_RGB(255, 255, 255), 2)
# cv.Circle(display_image, center_point, 5, cv.CV_RGB(100, 255, 255), 3)
# Determine if there are any new (or lost) targets:
actual_target_count = len(trimmed_center_points)
last_target_count = actual_target_count
# Now build the list of physical entities (objects)
this_frame_entity_list = []
# An entity is list: [ name, color, last_time_seen, last_known_coords ]
for target in trimmed_center_points:
# Is this a target near a prior entity (same physical entity)?
entity_found = False
entity_distance_dict = {}
for entity in last_frame_entity_list:
entity_coords = entity[3]
delta_x = entity_coords[0] - target[0]
delta_y = entity_coords[1] - target[1]
distance = sqrt(pow(delta_x, 2) + pow(delta_y, 2))
entity_distance_dict[distance] = entity
# Did we find any non-claimed entities (nearest to furthest):
distance_list = entity_distance_dict.keys()
distance_list.sort()
for distance in distance_list:
# Yes; see if we can claim the nearest one:
nearest_possible_entity = entity_distance_dict[distance]
# Don't consider entities that are already claimed:
if nearest_possible_entity in this_frame_entity_list:
#print "Target %s: Skipping the one iwth distance: %d at %s, C:%s" % (target, distance, nearest_possible_entity[3], nearest_possible_entity[1] )
continue
#print "Target %s: USING the one iwth distance: %d at %s, C:%s" % (target, distance, nearest_possible_entity[3] , nearest_possible_entity[1])
# Found the nearest entity to claim:
entity_found = True
nearest_possible_entity[
2] = frame_t0 # Update last_time_seen
nearest_possible_entity[
3] = target # Update the new location
this_frame_entity_list.append(nearest_possible_entity)
#log_file.write( "%.3f MOVED %s %d %d\n" % ( frame_t0, nearest_possible_entity[0], nearest_possible_entity[3][0], nearest_possible_entity[3][1] ) )
break
if entity_found == False:
# It's a new entity.
color = (random.randint(0, 255), random.randint(0, 255),
random.randint(0, 255))
name = hashlib.md5(str(frame_t0) +
str(color)).hexdigest()[:6]
last_time_seen = frame_t0
new_entity = [name, color, last_time_seen, target]
this_frame_entity_list.append(new_entity)
#log_file.write( "%.3f FOUND %s %d %d\n" % ( frame_t0, new_entity[0], new_entity[3][0], new_entity[3][1] ) )
# Now "delete" any not-found entities which have expired:
entity_ttl = 1.0 # 1 sec.
for entity in last_frame_entity_list:
last_time_seen = entity[2]
if frame_t0 - last_time_seen > entity_ttl:
# It's gone.
#log_file.write( "%.3f STOPD %s %d %d\n" % ( frame_t0, entity[0], entity[3][0], entity[3][1] ) )
pass
else:
# Save it for next time... not expired yet:
this_frame_entity_list.append(entity)
# For next frame:
last_frame_entity_list = this_frame_entity_list
# Draw the found entities to screen:
for entity in this_frame_entity_list:
center_point = entity[3]
c = entity[1] # RGB color tuple
cv.Circle(display_image, center_point, 20,
cv.CV_RGB(c[0], c[1], c[2]), 1)
cv.Circle(display_image, center_point, 15,
cv.CV_RGB(c[0], c[1], c[2]), 1)
cv.Circle(display_image, center_point, 10,
cv.CV_RGB(c[0], c[1], c[2]), 2)
cv.Circle(display_image, center_point, 5,
cv.CV_RGB(c[0], c[1], c[2]), 3)
#print "min_size is: " + str(min_size)
# Listen for ESC or ENTER key
c = cv.WaitKey(7) % 0x100
if c == 27 or c == 10:
break
# Toggle which image to show
if chr(c) == 'd':
image_index = (image_index + 1) % len(image_list)
image_name = image_list[image_index]
# Display frame to user
if image_name == "camera":
image = camera_image
cv.PutText(image, "Camera (Normal)", text_coord, text_font,
text_color)
elif image_name == "difference":
image = difference
cv.PutText(image, "Difference Image", text_coord, text_font,
text_color)
elif image_name == "display":
image = display_image
cv.PutText(image, "Targets (w/AABBs and contours)", text_coord,
text_font, text_color)
elif image_name == "threshold":
# Convert the image to color.
cv.CvtColor(grey_image, display_image, cv.CV_GRAY2RGB)
image = display_image # Re-use display image here
cv.PutText(image, "Motion Mask", text_coord, text_font,
text_color)
elif image_name == "faces":
# Do face detection
detect_faces(camera_image, haar_cascade, mem_storage)
image = camera_image # Re-use camera image here
cv.PutText(image, "Face Detection", text_coord, text_font,
text_color)
cv.ShowImage("Target", image)
if self.writer:
cv.WriteFrame(self.writer, image)
#log_file.flush()
# If only using a camera, then there is no time.sleep() needed,
# because the camera clips us to 15 fps. But if reading from a file,
# we need this to keep the time-based target clipping correct:
frame_t1 = time.time()
# If reading from a file, put in a forced delay:
if not self.writer:
delta_t = frame_t1 - frame_t0
if delta_t < (1.0 / 15.0): time.sleep((1.0 / 15.0) - delta_t)
t1 = time.time()
time_delta = t1 - t0
processed_fps = float(frame_count) / time_delta
print "Got %d frames. %.1f s. %f fps." % (frame_count, time_delta,
processed_fps)
def run(self):
frame = cv.QueryFrame(self.capture)
frame_size = cv.GetSize(frame)
grey_image = cv.CreateImage(cv.GetSize(frame), cv.IPL_DEPTH_8U, 1)
run_mean = cv.CreateImage(cv.GetSize(frame), cv.IPL_DEPTH_32F, 3)
diff = None
movement = []
while True:
# Capture frame from webcam
color_image = cv.QueryFrame(self.capture)
cv.Smooth(color_image, color_image, cv.CV_GAUSSIAN, 3, 0)
if not diff:
# Initialize
diff = cv.CloneImage(color_image)
temp = cv.CloneImage(color_image)
cv.ConvertScale(color_image, run_mean, 1.0, 0.0)
else:
cv.RunningAvg(color_image, run_mean, 0.020, None)
# Convert the scale of the moving average.
cv.ConvertScale(run_mean, temp, 1.0, 0.0)
# Minus the current frame from the moving average.
cv.AbsDiff(color_image, temp, diff)
# Convert the image to grayscale.
cv.CvtColor(diff, grey_image, cv.CV_RGB2GRAY)
# Convert the image to black and white.
cv.Threshold(grey_image, grey_image, 70, 255, cv.CV_THRESH_BINARY)
# Dilate and erode to get object blobs
cv.Dilate(grey_image, grey_image, None, 18)
cv.Erode(grey_image, grey_image, None, 10)
# Calculate movements
store_movement = cv.CreateMemStorage(0)
contour = cv.FindContours(grey_image, store_movement, cv.CV_RETR_CCOMP, cv.CV_CHAIN_APPROX_SIMPLE)
points = []
while contour:
# Draw rectangles
bound_rect = cv.BoundingRect(list(contour))
contour = contour.h_next()
pt1 = (bound_rect[0], bound_rect[1])
pt2 = (bound_rect[0] + bound_rect[2], bound_rect[1] + bound_rect[3])
points.append(pt1)
points.append(pt2)
cv.Rectangle(color_image, pt1, pt2, cv.CV_RGB(255,0,0), 1)
num_points = len(points)
if num_points:
x = 0
for point in points:
x += point[0]
x /= num_points
movement.append(x)
if len(movement) > 0 and numpy.average(numpy.diff(movement[-30:-1])) > 0:
print 'Left'
else:
print 'Right'
# Display frame to user
cv.ShowImage("Object Direction of Motion", color_image)
# Listen for ESC or ENTER key
c = cv.WaitKey(7) % 0x100
if (0xFF & c == 27):
break
def main():
def isimgext(f):
return os.path.splitext(f)[1].lower() in ('.png', '.tif', '.tiff',
'.jpg', '.jpeg')
args = sys.argv[1:]
imgsdir = args[0]
vendor = args[1]
outdir = args[2]
try:
N = int(args[3])
except:
N = -1
if 'align' in args:
# Align the barcodes when computing Min/Max overlays
do_align = True
else:
do_align = False
if 'do_cpyimg' in args:
# Copy the entire images to OUTDIR (don't do this for large N!)
do_cpyimg = True
else:
do_cpyimg = False
if 'just_grouping' in args:
# Just compute the barcodes + group, don't compute overlays
just_grouping = True
else:
just_grouping = False
if args[-2] == 'load':
grouping = pickle.load(open(args[-1], 'rb'))
else:
grouping = None
do_profile = True if 'profile' in args else False
imgpaths = []
cnt = 0
for dirpath, dirnames, filenames in os.walk(imgsdir):
for imgname in [f for f in filenames if isimgext(f)]:
if N > 0 and cnt >= N:
break
imgpath = os.path.join(dirpath, imgname)
imgpaths.append(imgpath)
cnt += 1
if N > 0 and cnt >= N:
break
print "Starting partition_imgs..."
t = time.time()
if do_profile:
cProfile.runctx('partition_imgs(imgpaths, vendor=vendor)', {}, {
'imgpaths': imgpaths,
'vendor': vendor,
'partition_imgs': partition_imgs
})
return
if grouping == None:
grouping = partask.do_partask(_do_partition_imgs,
imgpaths,
_args=(vendor, None),
combfn="dict",
N=None)
try:
os.makedirs(outdir)
except:
pass
pickle.dump(grouping, open(os.path.join(outdir, 'grouping.p'), 'wb'),
pickle.HIGHEST_PROTOCOL)
dur = time.time() - t
print "...Finished partition_imgs ({0} s).".format(dur)
print " Avg. Time per ballot: {0} s".format(dur / len(imgpaths))
print "Copying groups to outdir {0}...".format(outdir)
t = time.time()
errcount = 0
for barcodes, group in grouping.iteritems():
if len(group) == 1:
errcount += 1 if ("ERR0" in barcodes or "ERR1" in barcodes) else 0
continue
elif "ERR0" in barcodes or "ERR1" in barcodes:
#continue
errcount += len(group)
pass
if just_grouping:
continue
bcs = '_'.join([thing for thing in barcodes if type(thing) == str])
rootdir = os.path.join(outdir, bcs)
try:
os.makedirs(rootdir)
except:
pass
Imins = [None for _ in barcodes]
Imaxes = [None for _ in barcodes]
Irefs = [None for _ in barcodes]
for i, (imgpath, isflip, bbs) in enumerate(group):
if do_cpyimg:
imgname = os.path.split(imgpath)[1]
outpath_foo = os.path.join(rootdir, imgname)
shutil.copy(imgpath, outpath_foo)
img = cv.LoadImage(imgpath, cv.CV_LOAD_IMAGE_GRAYSCALE)
if isflip:
cv.Flip(img, img, flipMode=-1)
for j, bb in enumerate(bbs):
outpath = os.path.join(rootdir, str(j),
"{0}_{1}.png".format(i, j))
try:
os.makedirs(os.path.split(outpath)[0])
except:
pass
x, y, w, h = bb
cv.SetImageROI(img, (x, y, w, h))
wbig, hbig = int(round(w * 2.0)), int(round(h * 2.0))
bcBig = cv.CreateImage((wbig, hbig), img.depth, img.channels)
cv.Resize(img, bcBig, interpolation=cv.CV_INTER_CUBIC)
cv.SaveImage(outpath, bcBig)
if Imins[j] == None:
Imins[j] = cv.CloneImage(bcBig)
Imaxes[j] = cv.CloneImage(bcBig)
if do_align:
Irefs[j] = make_overlays.iplimage2np(
cv.CloneImage(bcBig)) / 255.0
else:
bcBig_sized = make_overlays.matchsize(bcBig, Imins[j])
if do_align:
tmp_np = make_overlays.iplimage2np(
cv.CloneImage(bcBig_sized)) / 255.0
H, Ireg, err = imagesAlign.imagesAlign(tmp_np,
Irefs[j],
fillval=0.2,
rszFac=0.75)
Ireg *= 255.0
Ireg = Ireg.astype('uint8')
bcBig_sized = make_overlays.np2iplimage(Ireg)
cv.Min(bcBig_sized, Imins[j], Imins[j])
cv.Max(bcBig_sized, Imaxes[j], Imaxes[j])
for idx, Imin in enumerate(Imins):
Imax = Imaxes[idx]
cv.SaveImage(os.path.join(rootdir, "_{0}_minimg.png".format(idx)),
Imin)
cv.SaveImage(os.path.join(rootdir, "_{0}_maximg.png".format(idx)),
Imax)
dur = time.time() - t
print "...Finished Copying groups to outdir {0} ({1} s).".format(
outdir, dur)
print "Number of error ballots:", errcount
print "Done."
def run(self, args):
# Capture first frame to get size
frame = cv.QueryFrame(self.capture)
#frame_size = cv.GetSize(frame)
color_image = cv.CreateImage(cv.GetSize(frame), 8, 3)
grey_image = cv.CreateImage(cv.GetSize(frame), cv.IPL_DEPTH_8U, 1)
moving_average = cv.CreateImage(cv.GetSize(frame), cv.IPL_DEPTH_32F, 3)
first = True
#closest_to_left = cv.GetSize(frame)[0]
#closest_to_right = cv.GetSize(frame)[1]
while True:
color_image = cv.QueryFrame(self.capture)
if not color_image:
print "END OF FILE"
break
# Smooth to get rid of false positives
cv.Smooth(color_image, color_image, cv.CV_GAUSSIAN, 3, 0)
if first:
difference = cv.CloneImage(color_image)
temp = cv.CloneImage(color_image)
cv.ConvertScale(color_image, moving_average, 1.0, 0.0)
first = False
else:
cv.RunningAvg(color_image, moving_average, args.motiondelay, None)
# Convert the scale of the moving average.
cv.ConvertScale(moving_average, temp, 1.0, 0.0)
# Minus the current frame from the moving average.
cv.AbsDiff(color_image, temp, difference)
# Convert the image to grayscale.
cv.CvtColor(difference, grey_image, cv.CV_RGB2GRAY)
if DEBUG_VISUAL:
cv.ShowImage("Grey_image: Difference", grey_image)
# Convert the image to black and white.
cv.Threshold(grey_image, grey_image, args.threshold, 255, cv.CV_THRESH_BINARY)
if DEBUG_VISUAL:
cv.ShowImage("Grey_image: Black n White", grey_image)
#
# Dilate and erode to get people blobs
cv.Dilate(grey_image, grey_image, None, args.dilate)
if DEBUG_VISUAL:
cv.ShowImage("Dilate", grey_image)
cv.Erode(grey_image, grey_image, None, args.erode)
if DEBUG_VISUAL:
cv.ShowImage("Erode", grey_image)
storage = cv.CreateMemStorage(0)
contour = cv.FindContours(grey_image, storage, cv.CV_RETR_CCOMP, cv.CV_CHAIN_APPROX_SIMPLE)
counter = 0
while contour:
counter += 1
bound_rect = cv.BoundingRect(list(contour))
contour = contour.h_next()
pt1 = (bound_rect[0], bound_rect[1])
pt2 = (bound_rect[0] + bound_rect[2], bound_rect[1] + bound_rect[3])
cv.Rectangle(color_image, pt1, pt2, cv.CV_RGB(255,0,0), 1)
print counter
cv.ShowImage("Target", color_image)
# Listen for ESC key
c = cv.WaitKey(7) % 0x100
if c == 27:
break
def showImage(svs,img):
dst = cv.CloneImage(img.image)
old_time = time.time()
intrinsics = cv.Load("Intrinsics.xml")
distortion = cv.Load("Distortion.xml")
image = cv.QueryFrame(cam)
mapx = cv.CreateImage(cv.GetSize(image), cv.IPL_DEPTH_32F, 1)
mapy = cv.CreateImage(cv.GetSize(image), cv.IPL_DEPTH_32F, 1)
cv.InitUndistortMap(intrinsics, distortion, mapx, mapy)
while (True):
start = time.time()
image = cv.QueryFrame(cam)
processed = cv.CloneImage(image)
cv.Remap(image, processed, mapx, mapy)
crop_rect = (0, 63, 640, 350)
cv.SetImageROI(processed, crop_rect)
ball_center = find_object(processed, "RED")
ball_center = (int(ball_center[0][0]) + 8, int(ball_center[0][1]) + 8)
blue_center = find_object(processed, "BLUE")
blue_center = ((int(blue_center[0][0]) + 8, int(blue_center[0][1]) + 12),
blue_center[1])
yellow_center = find_object(processed, "YELLOW")
yellow_center = ((int(yellow_center[0][0]) + 8,
int(yellow_center[0][1]) + 12), yellow_center[1])
center_points = (ball_center, blue_center, yellow_center)
draw_on_image(processed, center_points)
def process_frame(self, frame):
# Resize image to 320x240
#copy = cv.CreateImage(cv.GetSize(frame), 8, 3)
#cv.Copy(frame, copy)
#cv.SetImageROI(frame, (0, 0, 320, 240))
#cv.Resize(copy, frame, cv.CV_INTER_NN)
found_hedge = False
test_frame = cv.CreateImage(cv.GetSize(frame), 8, 3)
cv.Copy(frame, test_frame)
cv.Smooth(frame, frame, cv.CV_MEDIAN, 7, 7)
# Set binary image to have value channel
hsv = cv.CreateImage(cv.GetSize(frame), 8, 3)
binary = cv.CreateImage(cv.GetSize(frame), 8, 1)
cv.CvtColor(frame, hsv, cv.CV_BGR2HSV)
cv.SetImageCOI(hsv, 2)
cv.Copy(hsv, binary)
cv.SetImageCOI(hsv, 0)
cv.AdaptiveThreshold(
binary,
binary,
255,
cv.CV_ADAPTIVE_THRESH_MEAN_C,
cv.CV_THRESH_BINARY_INV,
self.adaptive_thresh_blocksize,
self.adaptive_thresh,
)
# Morphology
kernel = cv.CreateStructuringElementEx(3, 3, 1, 1, cv.CV_SHAPE_ELLIPSE)
#cv.Erode(binary, binary, kernel, 1)
cv.Dilate(binary, binary, kernel, 4)
if self.debug:
color_filtered = cv.CloneImage(binary)
# Get Edges
#cv.Canny(binary, binary, 30, 40)
# Hough Transform
'''
line_storage = cv.CreateMemStorage()
raw_lines = cv.HoughLines2(binary, line_storage, cv.CV_HOUGH_STANDARD,
rho=1,
theta=math.pi/180,
threshold=self.hough_threshold,
param1=0,
param2=0
)
'''
# Hough Transform
line_storage = cv.CreateMemStorage()
raw_lines = cv.HoughLines2(binary,
line_storage,
cv.CV_HOUGH_PROBABILISTIC,
rho=1,
theta=math.pi / 180,
threshold=self.hough_threshold,
param1=self.min_length,
param2=self.max_gap)
self.hor_lines = []
for line in raw_lines:
slope = line_slope(line[0], line[1])
if slope is None:
continue
if math.fabs(line_slope(line[0], line[1])) < self.hor_threshold:
self.hor_lines.append(line)
max_length = 0
for line in self.hor_lines:
print line
if math.fabs(line_distance(line[0], line[1])) > max_length:
max_length = math.fabs(line_distance(line[0], line[1]))
crossbar_seg = line
'''
# Get vertical lines
vertical_lines = []
for line in raw_lines:
if line[1] < self.vertical_threshold or \
line[1] > math.pi-self.vertical_threshold:
vertical_lines.append( (abs(line[0]), line[1]) )
# Group vertical lines
vertical_line_groups = [] # A list of line groups which are each a line list
for line in vertical_lines:
group_found = False
for line_group in vertical_line_groups:
if line_group_accept_test(line_group, line, self.max_range):
line_group.append(line)
group_found = True
if not group_found:
vertical_line_groups.append([line])
# Average line groups into lines
vertical_lines = []
for line_group in vertical_line_groups:
rhos = map(lambda line: line[0], line_group)
angles = map(lambda line: line[1], line_group)
line = (sum(rhos)/len(rhos), circular_average(angles, math.pi))
vertical_lines.append(line)
# Get horizontal lines
horizontal_lines = []
for line in raw_lines:
dist_from_horizontal = (math.pi/2 + line[1]) % math.pi
if dist_from_horizontal < self.horizontal_threshold or \
dist_from_horizontal > math.pi-self.horizontal_threshold:
horizontal_lines.append( (abs(line[0]), line[1]) )
# Group horizontal lines
horizontal_line_groups = [] # A list of line groups which are each a line list
for line in horizontal_lines:
group_found = False
for line_group in horizontal_line_groups:
if line_group_accept_test(line_group, line, self.max_range):
line_group.append(line)
group_found = True
if not group_found:
horizontal_line_groups.append([line])
if len(horizontal_line_groups) is 1:
self.seen_crossbar = True
rhos = map(lambda line: line[0], horizontal_line_groups[0])
angles = map(lambda line: line[1], horizontal_line_groups[0])
line = (sum(rhos)/len(rhos), circular_average(angles, math.pi))
horizontal_lines = [line]
else:
self.seen_crossbar = False
horizontal_lines = []
self.left_pole = None
self.right_pole = None
if len(vertical_lines) is 2:
roi = cv.GetImageROI(frame)
width = roi[2]
height = roi[3]
self.left_pole = round(min(vertical_lines[0][0], vertical_lines[1][0]), 2) - width/2
self.right_pole = round(max(vertical_lines[0][0], vertical_lines[1][0]), 2) - width/2
#TODO: If one pole is seen, is it left or right pole?
# Calculate planar distance r (assuming we are moving perpendicular to
# the hedge)
if self.left_pole and self.right_pole:
theta = abs(self.left_pole - self.right_pole)
self.r = 3 / tan(radians(theta/2))
else:
self.r = None
if self.r and self.seen_crossbar:
bar_phi = (-1*horizontal_lines[0][0] + frame.height/2) / (frame.height/2) * 32
self.crossbar_depth = self.r * atan(radians(bar_phi))
else:
self.crossbar_depth = None
'''
self.left_pole = None
self.right_pole = None
self.seen_crossbar = False
self.crossbar_depth = None
if self.debug and max_length != 0:
cv.CvtColor(color_filtered, frame, cv.CV_GRAY2RGB)
#libvision.misc.draw_lines(frame, vertical_lines)
#libvision.misc.draw_lines(frame, horizontal_lines)
# for line in raw_lines:
# cv.Line(frame,line[0],line[1], (255,255,0), 10, cv.CV_AA, 0)
# cv.Circle(frame, line[1], 15, (255,0,0), 2,8,0)
# print len(raw_lines)
#cv.ShowImage("Hedge", cv.CloneImage(frame))
if (crossbar_seg[0][0] - frame.width / 2) * 37 / (
frame.width / 2) < (crossbar_seg[1][0] - frame.width /
2) * 37 / (frame.width / 2):
self.left_pole = round((crossbar_seg[0][0] - frame.width / 2) *
37 / (frame.width / 2))
self.right_pole = round(
(crossbar_seg[1][0] - frame.width / 2) * 37 /
(frame.width / 2))
else:
self.left_pole = round((crossbar_seg[1][0] - frame.width / 2) *
37 / (frame.width / 2))
self.right_pole = round(
(crossbar_seg[0][0] - frame.width / 2) * 37 /
(frame.width / 2))
self.crossbar_depth = round(
-1 * (crossbar_seg[1][1] - frame.height / 2) * 36 /
(frame.height / 2))
if math.fabs(self.left_pole) <= 37 and math.fabs(
self.left_pole) >= self.frame_boundary_thresh:
self.left_pole = None
if math.fabs(self.right_pole) <= 37 and math.fabs(
self.right_pole) >= self.frame_boundary_thresh:
self.right_pole = None
self.seen_crossbar = True
if self.left_pole and self.right_pole:
self.returning = (self.left_pole + self.right_pole) / 2
print "Returning ", self.returning
if self.last_seen < 0:
self.last_center = None
self.last_seen = 0
if self.last_center is None:
self.last_center = self.returning
self.seen_count = 1
elif math.fabs(self.last_center -
self.returning) < self.center_trans_thresh:
self.seen_count += 1
self.last_seen += 2
else:
self.last_seen -= 1
if self.seen_count < self.seen_count_thresh:
self.left_pole = None
self.right_pole = None
else:
print "FOUND CENTER AND RETURNED IT"
self.found = True
else:
self.returning = 0
if self.last_seen < 0:
self.last_center = None
self.last_seen = 0
self.last_seen -= 1
self.left_pole = None
self.right_pole = None
cv.Line(frame, crossbar_seg[0], crossbar_seg[1], (255, 255, 0), 10,
cv.CV_AA, 0)
if self.left_pole and crossbar_seg[0][0] < crossbar_seg[1][0]:
cv.Line(frame, crossbar_seg[0],
(crossbar_seg[0][0], crossbar_seg[0][0] - 500),
(255, 0, 0), 10, cv.CV_AA, 0)
elif self.left_pole:
cv.Line(frame, crossbar_seg[1],
(crossbar_seg[1][0], crossbar_seg[1][1] - 500),
(255, 0, 0), 10, cv.CV_AA, 0)
if self.right_pole and crossbar_seg[0][0] > crossbar_seg[1][0]:
cv.Line(frame, crossbar_seg[0],
(crossbar_seg[0][0], crossbar_seg[0][0] - 500),
(255, 0, 0), 10, cv.CV_AA, 0)
elif self.right_pole:
cv.Line(frame, crossbar_seg[1],
(crossbar_seg[1][0], crossbar_seg[1][1] - 500),
(255, 0, 0), 10, cv.CV_AA, 0)
# populate self.output with infos
self.output.seen_crossbar = self.seen_crossbar
self.output.left_pole = self.left_pole
self.output.right_pole = self.right_pole
#self.output.r = self.r
self.output.crossbar_depth = self.crossbar_depth
self.return_output()
print self
else:
cv.CvtColor(color_filtered, frame, cv.CV_GRAY2RGB)
svr.debug("Hedge", cv.CloneImage(frame))
svr.debug("Hedge2", test_frame)
cv.Save("Distortion.xml", distortion_coefficient)
# Loading from xml files
intrinsic = cv.Load("Intrinsics.xml")
distortion = cv.Load("Distortion.xml")
print " loaded all distortion parameters"
mapx = cv.CreateImage(cv.GetSize(image), cv.IPL_DEPTH_32F, 1)
mapy = cv.CreateImage(cv.GetSize(image), cv.IPL_DEPTH_32F, 1)
cv.InitUndistortMap(intrinsic, distortion, mapx, mapy)
cv.NamedWindow("Undistort")
print "all mapping completed"
print "Now relax for some time"
time.sleep(8)
print "now get ready, camera is switching on"
while (1):
image = cv.QueryFrame(capture)
t = cv.CloneImage(image)
cv.ShowImage("Calibration", image)
cv.Remap(t, image, mapx, mapy)
cv.ShowImage("Undistort", image)
c = cv.WaitKey(33)
if (c == 1048688): # enter 'p' key to pause for some time
cv.WaitKey(2000)
elif c == 1048603: # enter esc key to exit
break
print "everything is fine"
###############################################################################################
orig = cv.LoadImage('./demo1.jpg', cv.CV_LOAD_IMAGE_COLOR)
im = cv.CreateImage(cv.GetSize(orig), 8, 1)
cv.CvtColor(orig, im, cv.CV_BGR2GRAY)
#Keep the original in colour to draw contours in the end
cv.Threshold(im, im, 128, 255, cv.CV_THRESH_BINARY)
cv.ShowImage("Threshold 1", im)
cv.SaveImage("threshold1.jpg",im)
element = cv.CreateStructuringElementEx(5*2+1, 5*2+1, 5, 5, cv.CV_SHAPE_RECT)
cv.MorphologyEx(im, im, None, element, cv.CV_MOP_OPEN) #Open and close to make appear contours
cv.MorphologyEx(im, im, None, element, cv.CV_MOP_CLOSE)
cv.Threshold(im, im, 128, 255, cv.CV_THRESH_BINARY_INV)
cv.ShowImage("After MorphologyEx", im)
cv.SaveImage("after.jpg",im)
# --------------------------------
vals = cv.CloneImage(im) #Make a clone because FindContours can modify the image
contours=cv.FindContours(vals, cv.CreateMemStorage(0), cv.CV_RETR_LIST, cv.CV_CHAIN_APPROX_SIMPLE, (0,0))
_red = (0, 0, 255); #Red for external contours
_green = (0, 255, 0);# Gren internal contours
levels=2 #1 contours drawn, 2 internal contours as well, 3 ...
co=cv.DrawContours (orig, contours, _red, _green, levels, 2, cv.CV_FILLED) #Draw contours on the colour image
cv.SaveImage("save.jpg",orig)
# cv.SaveImage("co.jpg",co)
cv.ShowImage("Image", orig)
cv.WaitKey(0)
def findSquares4(img, storage):
N = 11
sz = (img.width & -2, img.height & -2)
timg = cv.CloneImage(img)
# make a copy of input image
gray = cv.CreateImage(sz, 8, 1)
pyr = cv.CreateImage((sz.width / 2, sz.height / 2), 8, 3)
# create empty sequence that will contain points -
# 4 points per square (the square's vertices)
squares = cv.CreateSeq(0, sizeof_CvSeq, sizeof_CvPoint, storage)
squares = CvSeq_CvPoint.cast(squares)
# select the maximum ROI in the image
# with the width and height divisible by 2
subimage = cv.GetSubRect(timg, cv.Rect(0, 0, sz.width, sz.height))
# down-scale and upscale the image to filter out the noise
cv.PyrDown(subimage, pyr, 7)
cv.PyrUp(pyr, subimage, 7)
tgray = cv.CreateImage(sz, 8, 1)
# find squares in every color plane of the image
for c in range(3):
# extract the c-th color plane
channels = [None, None, None]
channels[c] = tgray
cv.Split(subimage, channels[0], channels[1], channels[2], None)
for l in range(N):
# hack: use Canny instead of zero threshold level.
# Canny helps to catch squares with gradient shading
if (l == 0):
# apply Canny. Take the upper threshold from slider
# and set the lower to 0 (which forces edges merging)
cv.Canny(tgray, gray, 0, thresh, 5)
# dilate canny output to remove potential
# holes between edge segments
cv.Dilate(gray, gray, None, 1)
else:
# apply threshold if l!=0:
# tgray(x, y) = gray(x, y) < (l+1)*255/N ? 255 : 0
cv.Threshold(tgray, gray, (l + 1) * 255 / N, 255,
cv.CV_THRESH_BINARY)
# find contours and store them all as a list
count, contours = cv.FindContours(gray, storage, sizeof_CvContour,
cv.CV_RETR_LIST,
cv.CV_CHAIN_APPROX_SIMPLE,
(0, 0))
if not contours:
continue
# test each contour
for contour in contours.hrange():
# approximate contour with accuracy proportional
# to the contour perimeter
result = cv.ApproxPoly(contour, sizeof_CvContour, storage,
cv.CV_POLY_APPROX_DP,
cv.ContourPerimeter(contours) * 0.02, 0)
# square contours should have 4 vertices after approximation
# relatively large area (to filter out noisy contours)
# and be convex.
# Note: absolute value of an area is used because
# area may be positive or negative - in accordance with the
# contour orientation
if (result.total == 4 and abs(cv.ContourArea(result)) > 1000
and cv.CheckContourConvexity(result)):
s = 0
for i in range(5):
# find minimum angle between joint
# edges (maximum of cosine)
if (i >= 2):
t = abs(
angle(result[i], result[i - 2], result[i - 1]))
if s < t:
s = t
# if cosines of all angles are small
# (all angles are ~90 degree) then write quandrange
# vertices to resultant sequence
if (s < 0.3):
for i in range(4):
squares.append(result[i])
return squares
def VirtualMirror():
cv.NamedWindow("RGB_remap", cv.CV_WINDOW_NORMAL)
cv.NamedWindow("Depth_remap", cv.CV_WINDOW_AUTOSIZE)
cv.NamedWindow('dst', cv.CV_WINDOW_NORMAL)
cv.SetMouseCallback("Depth_remap", on_mouse, None)
print "Virtual Mirror"
print "Calibrated 4 Screen corner= ", sn4_ref
print "Corner 1-2 = ", np.linalg.norm(sn4_ref[0] - sn4_ref[1])
print "Corner 2-3 = ", np.linalg.norm(sn4_ref[1] - sn4_ref[2])
print "Corner 3-4 = ", np.linalg.norm(sn4_ref[2] - sn4_ref[3])
print "Corner 4-1 = ", np.linalg.norm(sn4_ref[3] - sn4_ref[0])
global head_pos
global head_virtual
global scene4_cross
head_pos = np.array([-0.2, -0.2, 1.0]) #Head_detect()
while 1:
(depth, _) = freenect.sync_get_depth()
(rgb, _) = freenect.sync_get_video()
#print type(depth)
img = array2cv(rgb[:, :, ::-1])
im = array2cv(depth.astype(np.uint8))
#modulize this part for update_on() and loopcv()
#q = depth
X, Y = np.meshgrid(range(640), range(480))
d = 2 #downsampling if need
projpts = calibkinect.depth2xyzuv(depth[::d, ::d], X[::d, ::d],
Y[::d, ::d])
xyz, uv = projpts
if tracking == 0:
#*********************************
if pt is not None:
print "=================="
(x_d, y_d) = pt
print "x=", x_d, " ,y=", y_d
#print depth.shape
#Watch out the indexing for depth col,row = 480,640
d_raw = np.array([depth[y_d, x_d]])
u_d = np.array([x_d])
v_d = np.array([y_d])
print "d_raw= ", d_raw
print "u_d= ", u_d
print "v_d= ", v_d
head3D, head2D = calibkinect.depth2xyzuv(d_raw, u_d, v_d)
print "XYZ=", head3D
print "XYZonRGBplane=", head2D
head_pos = head3D[0]
#print "head_pos.shape",head_pos.shape
print "head_pos= ", head_pos
cv.WaitKey(100)
cv.Circle(im, (x_d, y_d), 4, (0, 0, 255, 0), -1, 8, 0)
cv.Circle(im, (int(head2D[0, 0]), int(head2D[0, 1])), 2,
(255, 255, 255, 0), -1, 8, 0)
#*********************************
elif tracking == 1:
#find the nearest point (nose) as reference for right eye position
print "nose"
inds = np.nonzero(xyz[:, 2] > 0.5)
#print xyz.shape
new_xyz = xyz[inds]
#print new_xyz.shape
close_ind = np.argmin(new_xyz[:, 2])
head_pos = new_xyz[close_ind, :] + (0.03, 0.04, 0.01)
#print head_pos.shape
#print head_pos
elif tracking == 2:
#find the closest point as eye posiiton
print "camera"
inds = np.nonzero(xyz[:, 2] > 0.5)
#print xyz.shape
new_xyz = xyz[inds]
#print new_xyz.shape
close_ind = np.argmin(new_xyz[:, 2])
head_pos = new_xyz[close_ind, :]
#print head_pos.shape
#print head_pos
else:
print "please select a tracking mode"
head_virtual = MirrorReflection(sn4_ref[0:3, :], head_pos)
print "head_virtual= ", head_virtual
rgbK = np.array([[520.97092069697146, 0.0, 318.40565581396697],
[0.0, 517.85544366622719, 263.46756370601804],
[0.0, 0.0, 1.0]])
rgbD = np.array([[0.22464481251757576], [-0.47968370787671893], [0.0],
[0.0]])
irK = np.array([[588.51686020601733, 0.0, 320.22664144213843],
[0.0, 584.73028132692866, 241.98395817513071],
[0.0, 0.0, 1.0]])
irD = np.array([[-0.1273506872313161], [0.36672476189160591], [0.0],
[0.0]])
mapu = cv.CreateImage((640, 480), cv.IPL_DEPTH_32F, 1)
mapv = cv.CreateImage((640, 480), cv.IPL_DEPTH_32F, 1)
mapx = cv.CreateImage((640, 480), cv.IPL_DEPTH_32F, 1)
mapy = cv.CreateImage((640, 480), cv.IPL_DEPTH_32F, 1)
cv.InitUndistortMap(rgbK, rgbD, mapu, mapv)
cv.InitUndistortMap(irK, irD, mapx, mapy)
if 1:
rgb_remap = cv.CloneImage(img)
cv.Remap(img, rgb_remap, mapu, mapv)
depth_remap = cv.CloneImage(im)
cv.Remap(im, depth_remap, mapx, mapy)
scene4_cross = Cross4Pts.CrossPts(xyz, uv, head_pos, head_virtual,
sn4_ref)
#[warp] Add whole warpping code here
#[warp] points = Scene4Pts() as warpping 4 pts
#Flip the dst image!!!!!!!!!
#ShowImage("rgb_warp", dst)
#Within/out of the rgb range
#Mapping Destination (width, height)=(x,y)
#Warning: the order of pts in clockwise: pt1(L-T),pt2(R-T),pt3(R-B),pt4(L-B)
#points = [(test[0,0],test[0,1]), (630.,300.), (700.,500.), (400.,470.)]
points = [(scene4_cross[0, 0], scene4_cross[0, 1]),
(scene4_cross[1, 0], scene4_cross[1, 1]),
(scene4_cross[2, 0], scene4_cross[2, 1]),
(scene4_cross[3, 0], scene4_cross[3, 1])]
#Warping the image without flipping (camera image)
#npoints = [(0.,0.), (640.,0.), (640.,480.), (0.,480.)]
#Warping the image with flipping (mirror flip image)
npoints = [(640., 0.), (0., 0.), (0., 480.), (640., 480.)]
mat = cv.CreateMat(3, 3, cv.CV_32FC1)
cv.GetPerspectiveTransform(points, npoints, mat)
#src = cv.CreateImage( cv.GetSize(img), cv.IPL_DEPTH_32F, 3 )
src = cv.CreateImage(cv.GetSize(rgb_remap), cv.IPL_DEPTH_32F, 3)
#cv.ConvertScale(img,src,(1/255.00))
cv.ConvertScale(rgb_remap, src, (1 / 255.00))
dst = cv.CloneImage(src)
cv.Zero(dst)
cv.WarpPerspective(src, dst, mat)
#************************************************************************
#Remap the rgb and depth image
#Warping will use remap rgb image as src
if 1:
cv.ShowImage("RGB_remap", rgb_remap) #rgb[200:440,300:600,::-1]
cv.ShowImage("Depth_remap", depth_remap)
cv.ShowImage("dst", dst) #warp rgb image
if cv.WaitKey(5) == 27:
cv.DestroyWindow("RGB_remap")
cv.DestroyWindow("Depth_remap")
cv.DestroyWindow("dst")
break
cv.SetCaptureProperty(captura, cv.CV_CAP_PROP_FRAME_HEIGHT, 480)
#cv.NamedWindow("Fundo", 0)
cv.NamedWindow("Webcam", 1)
cv.NamedWindow("Mascara", 0)
cv.NamedWindow("Cinza", 1)
mascara = cv.CreateImage((640, 480), 8, 3)
cinza = cv.CreateImage((640, 480), 8, 1)
while True:
print("Por Favor tire uma foto do fundo estatico do seu video.")
print("Aperte a tecla espaco.")
if cv.WaitKey(0) % 0x100 == 32:
primeiraImagem = cv.QueryFrame(captura)
fundo = cv.CloneImage(primeiraImagem)
cv.Smooth(fundo, fundo, cv.CV_GAUSSIAN, 3)
print("Tirou uma Foto !")
break
while True:
maiorArea = 0
imagem = cv.QueryFrame(captura)
cv.Smooth(imagem, imagem, cv.CV_GAUSSIAN, 3)
cv.AbsDiff(imagem, fundo, mascara)
cv.CvtColor(mascara, cinza, cv.CV_BGR2GRAY)
cv.Threshold(cinza, cinza, 50, 255, cv.CV_THRESH_BINARY)
cv.Dilate(cinza, cinza, None, 4)
def pegarIris(caminho, nameFoto="teste.bmp", salvarImage=True):
orig = cv2.cv.LoadImage(caminho)
orig2 = cv2.cv.CloneImage(orig)
# create tmp images
grey_scale = cv.CreateImage(cv.GetSize(orig), 8, 1)
processedPupila = cv.CreateImage(cv.GetSize(orig), 8, 1)
processedIris = cv.CreateImage(cv.GetSize(orig), 8, 1)
cv.Smooth(orig, orig, cv.CV_GAUSSIAN, 3, 3)
cv.CvtColor(orig, grey_scale, cv.CV_RGB2GRAY)
cv.CvtColor(orig, processedIris, cv.CV_RGB2GRAY)
cv.Smooth(grey_scale, processedPupila, cv.CV_GAUSSIAN, 15, 15)
cv.Canny(processedPupila, processedPupila, 5, 70, 3)
cv.Smooth(processedPupila, processedPupila, cv.CV_GAUSSIAN, 15, 15)
cv2.cv.SaveImage("Processamento_final_pupila.jpg", processedPupila)
#cv.ShowImage("pupila_processada", processedPupila)
cv.Smooth(grey_scale, processedIris, cv.CV_GAUSSIAN, 15, 15)
cv.Canny(processedIris, processedIris, 5, 70, 3)
cv.Smooth(processedIris, processedIris, cv.CV_GAUSSIAN, 15, 15)
cv.Smooth(processedIris, processedIris, cv.CV_GAUSSIAN, 15, 15)
cv2.cv.SaveImage("Processamento_final_iris.jpg", processedPupila)
#cv.ShowImage("pupila_processada2", processedIris)
#cv.Erode(processedIris, processedIris, None, 10)
#cv.Dilate(processedIris, processedIris, None, 10)
#cv.Canny(processedIris, processedIris, 5, 70, 3)
#cv.Smooth(processedIris, processedIris, cv.CV_GAUSSIAN, 15, 15)
#cv.Smooth(processedIris, processedIris, cv.CV_GAUSSIAN, 15, 15)
#cv.Smooth(processedPupila, processedIris, cv.CV_GAUSSIAN, 15, 15)
#cv.ShowImage("Iris_processada", processedIris)
#cv.Dilate(processedIris, processedIris, None, 10)
storagePupila = cv.CreateMat(orig.width, 1, cv.CV_32FC3)
storageIris = cv.CreateMat(orig.width, 1, cv.CV_32FC3)
# these parameters need to be adjusted for every single image
HIGH = 30
LOW = 20
HIGH2 = 120
LOW2 = 60
imgBranca = cv.CreateImage(cv.GetSize(orig), 8, 3)
imgPreta = cv.CreateImage(cv.GetSize(orig), 8, 3)
cv.Zero(imgPreta)
cv.Not(imgPreta, imgBranca)
imagemMaskPupila = cv.CreateImage(cv.GetSize(orig), 8, 3)
imagemMaskPupila = cv.CloneImage(imgBranca)
imagemMaskIris = cv.CreateImage(cv.GetSize(orig), 8, 3)
imagemMaskIris = cv.CloneImage(imgPreta)
#try:
# extract circles
#cv2.cv.HoughCircles(processedIris, storageIris, cv.CV_HOUGH_GRADIENT, 3, 100.0,LOW,HIGH, LOW2, HIGH2)
cv2.cv.HoughCircles(processedPupila, storagePupila, cv.CV_HOUGH_GRADIENT,
2, 100.0, LOW, HIGH)
cv2.cv.HoughCircles(processedIris, storageIris, cv.CV_HOUGH_GRADIENT, 3,
100.0, LOW, HIGH, LOW2, HIGH2)
#Circulos da pupila
#for i in range(0, len(np.asarray(storagePupila))):
RadiusPupila = int(np.asarray(storagePupila)[0][0][2])
xPupila = int(np.asarray(storagePupila)[0][0][0])
yPupila = int(np.asarray(storagePupila)[0][0][1])
centerPupila = (xPupila, yPupila)
#print "RadiusPupila %d" %RadiusPupila
cv.Circle(imagemMaskPupila, centerPupila, RadiusPupila, cv.CV_RGB(0, 0, 0),
-1, 8, 0)
cv.Circle(orig, centerPupila, 1, cv.CV_RGB(0, 255, 0), -1, 8, 0)
cv.Circle(orig, centerPupila, RadiusPupila, cv.CV_RGB(255, 0, 0), 3, 8, 0)
#cv.ShowImage("pupila"+str(0), orig)
cv2.cv.SaveImage("macaraPupila.jpg", imagemMaskPupila)
orig = cv.CloneImage(orig2)
#cv.WaitKey(0)
#Circulos da Iris
#for i in range(0, len(np.asarray(storageIris))):
RadiusIris = int(np.asarray(storageIris)[0][0][2])
xIris = int(np.asarray(storageIris)[0][0][0])
yIris = int(np.asarray(storageIris)[0][0][1])
centerIris = (xIris, yIris)
#print "RadiusIris %d" %RadiusIris
cv.Circle(imagemMaskIris, centerIris, RadiusIris, cv.CV_RGB(255, 255, 255),
-1, 8, 0)
cv2.cv.SaveImage("macaraIris.jpg", imagemMaskIris)
cv.Circle(orig, centerIris, 1, cv.CV_RGB(0, 255, 0), -1, 8, 0)
cv.Circle(orig, centerIris, RadiusIris, cv.CV_RGB(255, 0, 0), 3, 8, 0)
#cv.ShowImage("Iris"+str(0), orig)
orig = cv.CloneImage(orig2)
#cv.WaitKey(0)
#except:
# print "nothing found"
# pass
#criando imagem final
finalAux = cv2.cv.CreateImage(cv.GetSize(orig), 8, 3)
final = cv2.cv.CreateImage(cv.GetSize(orig), 8, 3)
#pegando a iris toda
cv2.cv.And(orig, imagemMaskPupila, finalAux)
cv2.cv.SaveImage("pupila_cortada.jpg", finalAux)
cv2.cv.And(finalAux, imagemMaskIris, final)
cv2.cv.SaveImage("iris_pupila_cortada.jpg", final)
if salvarImage:
cv2.cv.SaveImage(nameFoto, final)
#cv.ShowImage("original with circles", final)
#cv.WaitKey(0)
return final
def run(self):
# Capture first frame to get size
frame = cv.QueryFrame(self.capture)
frame_size = cv.GetSize(frame)
color_image = cv.CreateImage(cv.GetSize(frame), 8, 3)
grey_image = cv.CreateImage(cv.GetSize(frame), cv.IPL_DEPTH_8U, 1)
moving_average = cv.CreateImage(cv.GetSize(frame), cv.IPL_DEPTH_32F, 3)
first = True
while True:
closest_to_left = cv.GetSize(frame)[0]
closest_to_right = cv.GetSize(frame)[1]
color_image = cv.QueryFrame(self.capture)
# Smooth to get rid of false positives
cv.Smooth(color_image, color_image, cv.CV_GAUSSIAN, 3, 0)
if first:
difference = cv.CloneImage(color_image)
temp = cv.CloneImage(color_image)
cv.ConvertScale(color_image, moving_average, 1.0, 0.0)
first = False
else:
cv.RunningAvg(color_image, moving_average, 0.020, None)
# Convert the scale of the moving average.
cv.ConvertScale(moving_average, temp, 1.0, 0.0)
# Minus the current frame from the moving average.
cv.AbsDiff(color_image, temp, difference)
# Convert the image to grayscale.
cv.CvtColor(difference, grey_image, cv.CV_RGB2GRAY)
# Convert the image to black and white.
cv.Threshold(grey_image, grey_image, 70, 255, cv.CV_THRESH_BINARY)
# Dilate and erode to get people blobs
cv.Dilate(grey_image, grey_image, None, 18)
cv.Erode(grey_image, grey_image, None, 10)
storage = cv.CreateMemStorage(0)
contour = cv.FindContours(grey_image, storage, cv.CV_RETR_CCOMP,
cv.CV_CHAIN_APPROX_SIMPLE)
points = []
while contour:
bound_rect = cv.BoundingRect(list(contour))
contour = contour.h_next()
pt1 = (bound_rect[0], bound_rect[1])
pt2 = (bound_rect[0] + bound_rect[2],
bound_rect[1] + bound_rect[3])
points.append(pt1)
points.append(pt2)
cv.Rectangle(color_image, pt1, pt2, cv.CV_RGB(255, 0, 0), 1)
if len(points):
center_point = reduce(
lambda a, b: ((a[0] + b[0]) / 2, (a[1] + b[1]) / 2),
points)
cv.Circle(color_image, center_point, 40,
cv.CV_RGB(255, 255, 255), 1)
cv.Circle(color_image, center_point, 30,
cv.CV_RGB(255, 100, 0), 1)
cv.Circle(color_image, center_point, 20,
cv.CV_RGB(255, 255, 255), 1)
cv.Circle(color_image, center_point, 10,
cv.CV_RGB(255, 100, 0), 1)
cv.ShowImage("Target", color_image)
# Listen for ESC key
c = cv.WaitKey(7) % 0x100
if c == 27:
break
imagefiledata = cv.CreateMatHeader(1, len(filedata), cv.CV_8UC1)
cv.SetData(imagefiledata, filedata, len(filedata))
img0 = cv.DecodeImage(imagefiledata, cv.CV_LOAD_IMAGE_COLOR)
rng = cv.RNG(-1)
print "Hot keys:"
print "\tESC - quit the program"
print "\tr - restore the original image"
print "\tw - run watershed algorithm"
print "\t (before that, roughly outline several markers on the image)"
cv.NamedWindow("image", 1)
cv.NamedWindow("watershed transform", 1)
img = cv.CloneImage(img0)
img_gray = cv.CloneImage(img0)
wshed = cv.CloneImage(img0)
marker_mask = cv.CreateImage(cv.GetSize(img), 8, 1)
markers = cv.CreateImage(cv.GetSize(img), cv.IPL_DEPTH_32S, 1)
cv.CvtColor(img, marker_mask, cv.CV_BGR2GRAY)
cv.CvtColor(marker_mask, img_gray, cv.CV_GRAY2BGR)
cv.Zero(marker_mask)
cv.Zero(wshed)
cv.ShowImage("image", img)
cv.ShowImage("watershed transform", wshed)
sk = Sketcher("image", [img, marker_mask])
print "h", h
print "v", v
#f = open ("/dev/ttyUSB0", "a")
#f.write("h "+str(h)+chr(10))
#f.write("v "+str(v)+chr(10))
#f.close()
init_frames = 20
while True:
im = cv.QueryFrame(camera)
cv.ShowImage("CamView", im)
mono = cv.CreateImage((im.width, im.height), cv.IPL_DEPTH_8U, 1)
view = cv.CloneImage(im)
cv.CvtColor(im, mono, cv.CV_RGB2GRAY)
cv.ShowImage("Gray", mono)
faces = cv.HaarDetectObjects(mono, hc, memstorage)
for (x,y,w,h),n in faces:
cv.Rectangle(view, (x,y), (x+w,y+h), (255,255,0))
cv.ShowImage("Faces", view)
#hsv = cv.CreateMat(im.width, im.height, cv.CV_8UC3)
#hsv = cv.CloneImage(im)
#cv.CvtColor(im, hsv, cv.CV_RGB2HSV)
#cv.Smooth(hsv, hsv, cv.CV_MEDIAN, 3)
def DetectaSombra(frame,bg):
dbg = 1
if dbg:
t1 = time.time()
#print 'Detectando sombras na imagem...'
# gera as imagens de cada canal RGB
imgCinza = cv.CreateImage(cv.GetSize(frame), cv.IPL_DEPTH_8U,1)
imgHSV = cv.CloneImage(frame)
imgH = cv.CloneImage(imgCinza)
imgS = cv.CloneImage(imgCinza)
imgV = cv.CloneImage(imgCinza)
imgR = cv.CloneImage(imgCinza)
imgG = cv.CloneImage(imgCinza)
imgB = cv.CloneImage(imgCinza)
bgCinza = cv.CreateImage(cv.GetSize(bg), cv.IPL_DEPTH_8U,1)
bgHSV = cv.CloneImage(bg)
bgH = cv.CloneImage(bgCinza)
bgS = cv.CloneImage(bgCinza)
bgV = cv.CloneImage(bgCinza)
bgR = cv.CloneImage(bgCinza)
bgG = cv.CloneImage(bgCinza)
bgB = cv.CloneImage(bgCinza)
# gera as imagens de cada frame e backgroun nos canais de HSV e RGB
cv.CvtColor(frame, imgHSV, cv.CV_BGR2HSV)
cv.Split(imgHSV, imgH, imgS, imgV, None)
cv.Split(frame, imgR, imgG, imgB, None)
cv.CvtColor(bg, bgHSV, cv.CV_BGR2HSV)
cv.Split(bgHSV, bgH, bgS, bgV, None)
cv.Split(bg, bgR, bgG, bgB, None)
# inicio de calculos para descobrir sombras.
ivbv = cv.CreateImage(cv.GetSize(frame), cv.IPL_DEPTH_8U,1)
cv.Div(imgV, bgV, ivbv,255)
isbs = cv.CreateImage(cv.GetSize(frame), cv.IPL_DEPTH_8U,1)
cv.Sub(imgS, bgS, isbs)
ihbh = cv.CreateImage(cv.GetSize(frame), cv.IPL_DEPTH_8U,1)
cv.AbsDiff(imgH, bgH, ihbh)
# parametros de deteccao de sombra
alfa = 190
beta = 210
thrSat = 20
thrHue = 50
alfa = 220
beta = 240
thrSat = 90
thrHue = 90
nErode = 0
nDilate = 0
# trata ivbv
imgThr_ivbv = cv.CreateImage(cv.GetSize(frame), cv.IPL_DEPTH_8U,1)
# deixa apenas os menores que beta
cv.Threshold(ivbv, imgThr_ivbv, beta, 255, cv.CV_THRESH_TRUNC)
# deixa apenas os maiores que alfa
cv.Threshold(imgThr_ivbv, imgThr_ivbv, alfa, 255, cv.CV_THRESH_TOZERO)
# binariza
cv.Threshold(imgThr_ivbv, imgThr_ivbv, alfa, 255, cv.CV_THRESH_BINARY)
# trata isbs
imgThr_isbs = cv.CreateImage(cv.GetSize(frame), cv.IPL_DEPTH_8U,1)
# deixa apenas os menores que thrSat
cv.Threshold(isbs, imgThr_isbs, thrSat, 255, cv.CV_THRESH_BINARY)
# trata isbs
imgThr_ihbh = cv.CreateImage(cv.GetSize(frame), cv.IPL_DEPTH_8U,1)
# deixa apenas os menores que thrSat
cv.Threshold(ihbh, imgThr_ihbh, thrHue, 255, cv.CV_THRESH_BINARY_INV)
# onde é preto em todas as imagens, é sombra
imgSombra = cv.CreateImage(cv.GetSize(frame), cv.IPL_DEPTH_8U,1)
cv.Not(imgThr_ivbv,imgThr_ivbv)
cv.Not(imgThr_isbs,imgThr_isbs)
cv.And(imgThr_ivbv,imgThr_isbs,imgSombra)
cv.Not(imgThr_ihbh,imgThr_ihbh)
cv.And(imgSombra,imgThr_ihbh,imgSombra)
for i in range(nErode):
cv.Erode(imgSombra,imgSombra)
for i in range(nDilate):
cv.Dilate(imgSombra,imgSombra)
#if dbg:
#print 'Tempo para detectar sombras: %.5f' % (time.time() - t1)
#exibe frames de saida
#destaca de verde a sombra sobre o frame
frameDestacado = cv.CloneImage(frame)
cv.Or(imgG,imgSombra,imgG)
cv.Merge(imgR, imgG, imgB,None, frameDestacado)
'''
cv.ShowImage('frameDestacado',frameDestacado)
cv.WaitKey()
'''
retorno = {}
retorno['sombra'] = imgSombra
retorno['sombraDestacada'] = frameDestacado
return retorno
cv.ShowImage('ivbv', ivbv)
cv.ShowImage('isbs', isbs)
cv.ShowImage('ihbh', ihbh)
cv.ShowImage('imgThr_isbs', imgThr_isbs)
cv.ShowImage('imgThr_ivbv', imgThr_ivbv)
cv.ShowImage('imgThr_ihbh', imgThr_ihbh)
cv.ShowImage('imgSombra', imgSombra)
cv.WaitKey()
sys.exit()
frameMerge = cv.CloneImage(frame)
cv.Merge(imgR, imgR, imgR,None, frameMerge)
cv.ShowImage('frame', frame)
cv.ShowImage('frameMerge', frameMerge)
cv.ShowImage('imgR', imgR)
cv.ShowImage('imgG', imgG)
cv.ShowImage('imgB', imgB)
cv.ShowImage('imgH', imgH)
cv.ShowImage('imgS', imgS)
cv.ShowImage('imgV', imgV)
cv.WaitKey()
return 0
cv.NamedWindow('camera', cv.CV_WINDOW_AUTOSIZE)
cv.NamedWindow('threshed', cv.CV_WINDOW_AUTOSIZE)
#cv.NamedWindow('cropped', cv.CV_WINDOW_AUTOSIZE)
# initialize position array
positions_x, positions_y = [0] * SMOOTHNESS, [0] * SMOOTHNESS
# read from the camera
while 1:
image = cv.QueryFrame(capture)
# image = cv.LoadImage("2012_automata.jpg")
if not image:
break
# smooth the image
image_smoothed = cv.CloneImage(image)
cv.Smooth(image, image_smoothed, cv.CV_GAUSSIAN, 9)
# threshold the smoothed image
image_threshed = thresholded_image(image_smoothed)
# blobify
cv.Dilate(image_threshed, image_threshed, None, 3)
cv.Erode(image_threshed, image_threshed, None, 3)
blobContour = None
# extract the edges from our binary image
current_contour = cv.FindContours(cv.CloneImage(image_threshed),
cv.CreateMemStorage(), cv.CV_RETR_CCOMP,
cv.CV_CHAIN_APPROX_SIMPLE)
cv.DrawContours(image, current_contour, (0, 0, 255), (0, 100, 100), 4)
if x != None:
# if (cv.ContourArea(contourCluster) > 20):
centerArr.append(contourCenter(contourCluster))
contourCluster = contourCluster.h_next()
if (not contourCluster):
return centerArr
initialRotate = 30
cv.NamedWindow('camera', cv.CV_WINDOW_AUTOSIZE)
cv.NamedWindow('threshold', cv.CV_WINDOW_AUTOSIZE)
capture = cv.CaptureFromCAM(0)
#image = cv.QueryFrame(capture)
image = cv.LoadImage('2012_automata_1.png')
imageCopy = cv.CloneImage(image)
imageTreshold = thresholded_image(image, (0, 0, 0, 0), (0, 0, 0, 0))
dialatecount = 0
thresholdrange = []
hsvImg = hsv_image(image)
cv.ShowImage("camera", image)
cv.ShowImage('threshold', imageTreshold)
while 1:
cv.SetMouseCallback("camera", setTreshold, 0)
keyPressed = cv.WaitKey(10000)
if keyPressed == 27:
break
elif keyPressed == -1:
pass
elif keyPressed == 114: