def scale_32f_image(image):
'''
Scales the given cv.IPL_DEPTH_32F type image to an 8 bit image so that the
smallest value maps to 0 and the largest maps to 255. Used for displaying
debugging images.
Processes each channel separately, which can produce some useful, but
esoteric results.
'''
if image.depth != cv.IPL_DEPTH_32F:
return image
result = cv.CreateImage(cv.GetSize(image), 8, image.channels)
channel_image = cv.CreateImage(cv.GetSize(image), cv.IPL_DEPTH_32F, 1)
channel_scaled = cv.CreateImage(cv.GetSize(image), 8, 1)
for channel_num in xrange(1, image.channels + 1):
cv.SetImageCOI(image, channel_num)
cv.Copy(image, channel_image)
minmaxloc = cv.MinMaxLoc(channel_image)
minimum = minmaxloc[0]
maximum = minmaxloc[1]
if maximum - minimum > 0:
cv.ConvertScale(channel_image, channel_scaled,
255 / (maximum - minimum),
-255 / (maximum - minimum) * minimum)
else:
cv.ConvertScale(channel_image, channel_scaled, 0, -255 / minimum)
cv.SetImageCOI(result, channel_num)
cv.Copy(channel_scaled, result)
cv.SetImageCOI(image, 0)
cv.SetImageCOI(result, 0)
return result
def get_channel(frame, channel):
'''
Returns a single channel image containing the specified channel from frame.
The channel given is 0-indexed.
'''
result = cv.CreateImage(cv.GetSize(frame), 8, 1)
previous_coi = cv.GetImageCOI(frame)
cv.SetImageCOI(frame, channel + 1) # COI is 1-indexed
cv.Copy(frame, result)
cv.SetImageCOI(frame, previous_coi)
return result
def do_frame(img, hsv):
cv.CvtColor(img, hsv, cv.CV_RGB2HSV)
one_ch = cv.CreateImage(cv.GetSize(img), cv.IPL_DEPTH_8U, 1)
for channel in (2, ):
cv.SetImageCOI(hsv, channel)
cv.Copy(hsv, one_ch)
do_channel(one_ch)
def extract_v(image):
size = cv.GetSize(image)
hsv = cv.CreateImage(size, cv.IPL_DEPTH_8U, 3)
v = cv.CreateImage(size, cv.IPL_DEPTH_8U, 1)
cv.CvtColor(image, hsv, cv.CV_RGB2HSV)
cv.SetImageCOI(hsv, 3)
cv.Copy(hsv, v)
return v
def extract_v(image):
"""Convert an RGB image to HSV and extract the V component. """
size = cv.GetSize(image)
hsv = cv.CreateImage(size, cv.IPL_DEPTH_8U, 3)
v = cv.CreateImage(size, cv.IPL_DEPTH_8U, 1)
cv.CvtColor(image, hsv, cv.CV_RGB2HSV)
cv.SetImageCOI(hsv, 3)
cv.Copy(hsv, v)
return v
def scale_32f_image(image):
result = cv.CreateImage(cv.GetSize(image), 8, image.channels)
channel_image = cv.CreateImage(cv.GetSize(image), cv.IPL_DEPTH_32F, 1)
channel_scaled = cv.CreateImage(cv.GetSize(image), 8, 1)
print "CHANNELS:", image.channels
for channel_num in xrange(1, image.channels + 1):
cv.SetImageCOI(image, channel_num)
cv.Copy(image, channel_image)
maximum = cv.MinMaxLoc(channel_image)[1]
print "MAXIMUM:", maximum
cv.ConvertScale(channel_image, channel_scaled, 255 / maximum)
cv.SetImageCOI(result, channel_num)
cv.Copy(channel_scaled, result)
cv.SetImageCOI(image, 0)
cv.SetImageCOI(result, 0)
return result
def find_squares4(color_img):
"""
Finds multiple squares in image
Steps:
-Use Canny edge to highlight contours, and dilation to connect
the edge segments.
-Threshold the result to binary edge tokens
-Use cv.FindContours: returns a cv.CvSequence of cv.CvContours
-Filter each candidate: use Approx poly, keep only contours with 4 vertices,
enough area, and ~90deg angles.
Return all squares contours in one flat list of arrays, 4 x,y points each.
"""
#select even sizes only
width, height = (color_img.width & -2, color_img.height & -2)
timg = cv.CloneImage(color_img) # make a copy of input image
gray = cv.CreateImage((width, height), 8, 1)
# select the maximum ROI in the image
cv.SetImageROI(timg, (0, 0, width, height))
# down-scale and upscale the image to filter out the noise
pyr = cv.CreateImage((width / 2, height / 2), 8, 3)
cv.PyrDown(timg, pyr, 7)
cv.PyrUp(pyr, timg, 7)
tgray = cv.CreateImage((width, height), 8, 1)
squares = []
# Find squares in every color plane of the image
# Two methods, we use both:
# 1. Canny to catch squares with gradient shading. Use upper threshold
# from slider, set the lower to 0 (which forces edges merging). Then
# dilate canny output to remove potential holes between edge segments.
# 2. Binary thresholding at multiple levels
N = 11
for c in [0, 1, 2]:
#extract the c-th color plane
cv.SetImageCOI(timg, c + 1)
cv.Copy(timg, tgray, None)
cv.Canny(tgray, gray, 0, 50, 5)
cv.Dilate(gray, gray)
squares = squares + find_squares_from_binary(gray)
# Look for more squares at several threshold levels
for l in range(1, N):
cv.Threshold(tgray, gray, (l + 1) * 255 / N, 255,
cv.CV_THRESH_BINARY)
squares = squares + find_squares_from_binary(gray)
return squares
def process_frame(self, frame):
self.debug_frame = cv.CreateImage(cv.GetSize(frame), 8, 3)
self.test_frame = cv.CreateImage(cv.GetSize(frame), 8, 3)
cv.Copy(frame, self.debug_frame)
cv.Copy(frame, self.test_frame)
cv.Smooth(frame, frame, cv.CV_MEDIAN, 7, 7)
# Set binary image to have saturation 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, 1)
cv.Copy(hsv, binary)
cv.SetImageCOI(hsv, 0)
# Adaptive Threshold
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(5, 5, 3, 3, cv.CV_SHAPE_ELLIPSE)
cv.Erode(binary, binary, kernel, 1)
cv.Dilate(binary, binary, kernel, 1)
cv.CvtColor(binary, self.debug_frame, cv.CV_GRAY2RGB)
# Find Corners
temp1 = cv.CreateImage(cv.GetSize(frame), 8, 1)
temp2 = cv.CreateImage(cv.GetSize(frame), 8, 1)
self.corners = cv.GoodFeaturesToTrack(binary, temp1, temp2, self.max_corners, self.quality_level, self.min_distance, None, self.good_features_blocksize, 0, 0.4)
# Display Corners
for corner in self.corners:
corner_color = (0, 0, 255)
text_color = (0, 255, 0)
font = cv.InitFont(cv.CV_FONT_HERSHEY_SIMPLEX, .6, .6, 0, 1, 1)
cv.Circle(self.debug_frame, (int(corner[0]), int(corner[1])), 15, corner_color, 2, 8, 0)
# Find Candidates
for confirmed in self.confirmed:
confirmed.corner1_repl_check = 0
confirmed.corner2_repl_check = 0
confirmed.corner3_repl_check = 0
confirmed.corner4_repl_check = 0
for corner in self.corners:
if math.fabs(confirmed.corner1[0] - corner[0]) < self.MaxCornerTrans and \
math.fabs(confirmed.corner1[1] - corner[1]) < self.MaxCornerTrans:
confirmed.corner1_repl_check = 1
confirmed.corner1_repl = corner
elif math.fabs(confirmed.corner2[0] - corner[0]) < self.MaxCornerTrans and \
math.fabs(confirmed.corner2[1] - corner[1]) < self.MaxCornerTrans:
confirmed.corner2_repl_check = 1
confirmed.corner2_repl = corner
elif math.fabs(confirmed.corner3[0] - corner[0]) < self.MaxCornerTrans and \
math.fabs(confirmed.corner3[1] - corner[1]) < self.MaxCornerTrans:
confirmed.corner3_repl_check = 1
confirmed.corner3_repl = corner
elif math.fabs(confirmed.corner4[0] - corner[0]) < self.MaxCornerTrans and \
math.fabs(confirmed.corner4[1] - corner[1]) < self.MaxCornerTrans:
confirmed.corner4_repl_check = 1
confirmed.corner4_repl = corner
if confirmed.corner4_repl_check == 1 and confirmed.corner3_repl_check == 1 and confirmed.corner2_repl_check == 1 and confirmed.corner1_repl_check == 1:
confirmed.corner1 = confirmed.corner1_repl
confirmed.corner2 = confirmed.corner2_repl
confirmed.corner3 = confirmed.corner3_repl
confirmed.corner4 = confirmed.corner4_repl
confirmed.midx = rect_midpointx(confirmed.corner1, confirmed.corner2, confirmed.corner3, confirmed.corner4)
confirmed.midy = rect_midpointy(confirmed.corner1, confirmed.corner2, confirmed.corner3, confirmed.corner4)
if confirmed.last_seen < self.last_seen_max:
confirmed.last_seen += 5
for corner1 in self.corners:
for corner2 in self.corners:
for corner3 in self.corners:
for corner4 in self.corners:
# Checks that corners are not the same and are in the proper orientation
if corner4[0] != corner3[0] and corner4[0] != corner2[0] and corner4[0] != corner1[0] and \
corner3[0] != corner2[0] and corner3[0] != corner1[0] and corner2[0] != corner1[0] and \
corner4[1] != corner3[1] and corner4[1] != corner2[1] and corner4[1] != corner1[1] and \
corner3[1] != corner2[1] and corner3[1] != corner1[1] and corner2[1] != corner1[1] and \
corner2[0] >= corner3[0] and corner1[1] >= corner4[1] and corner2[0] >= corner1[0]:
# Checks that the side ratios are correct
if math.fabs(line_distance(corner1, corner3) - line_distance(corner2, corner4)) < self.size_threshold and \
math.fabs(line_distance(corner1, corner2) - line_distance(corner3, corner4)) < self.size_threshold and \
math.fabs(line_distance(corner1, corner3) / line_distance(corner1, corner2)) < self.ratio_threshold or \
math.fabs(line_distance(corner1, corner2) / line_distance(corner1, corner3)) < self.ratio_threshold:
# Checks that angles are roughly 90 degrees
angle_cnr_2 = math.fabs(angle_between_lines(line_slope(corner1, corner2), line_slope(corner2, corner4)))
if self.angle_min < angle_cnr_2 < self.angle_max:
angle_cnr_3 = math.fabs(angle_between_lines(line_slope(corner1, corner3), line_slope(corner3, corner4)))
if self.angle_min2 < angle_cnr_3 < self.angle_max2:
new_bin = Bin(corner1, corner2, corner3, corner4)
self.match_bins(new_bin)
self.sort_bins()
'''
#START SHAPE PROCESSING
#TODO load these ONCE somewhere
samples = np.loadtxt('generalsamples.data',np.float32)
responses = np.loadtxt('generalresponses.data',np.float32)
responses = responses.reshape((responses.size,1))
model = cv2.KNearest()
model.train(samples,responses)
for bin in self.confirmed:
try:
bin.speedlimit
except:
continue
transf = cv.CreateMat(3, 3, cv.CV_32FC1)
corner_orders = [
[bin.corner1, bin.corner2, bin.corner3, bin.corner4], #0 degrees
[bin.corner4, bin.corner3, bin.corner2, bin.corner1], #180 degrees
[bin.corner2, bin.corner4, bin.corner1, bin.corner3], #90 degrees
[bin.corner3, bin.corner1, bin.corner4, bin.corner2], #270 degrees
[bin.corner3, bin.corner4, bin.corner1, bin.corner2], #0 degrees and flipped X
[bin.corner2, bin.corner1, bin.corner4, bin.corner3], #180 degrees and flipped X
[bin.corner1, bin.corner3, bin.corner2, bin.corner4], #90 degrees and flipped X
[bin.corner4, bin.corner2, bin.corner3, bin.corner1]] #270 degrees andf flipped X
for i in range(0, 8):
cv.GetPerspectiveTransform(
corner_orders[i],
[(0, 0), (0, 256), (128, 0), (128, 256)],
transf
)
shape = cv.CreateImage([128, 256], 8, 3)
cv.WarpPerspective(frame, shape, transf)
shape_thresh = np.zeros((256-104,128,1), np.uint8)
j = 104
while j<256:
i = 0
while i<128:
pixel = cv.Get2D(shape, j, i)
if int(pixel[2]) > (int(pixel[1]) + int(pixel[0])) * 0.7:
shape_thresh[j-104,i] = 255
else:
shape_thresh[j-104,i] = 0
i = i+1
j = j+1
cv2.imshow("Bin " + str(i), shape_thresh)
contours,hierarchy = cv2.findContours(thresh,cv2.RETR_LIST,cv2.CHAIN_APPROX_NONE)
for cnt in contours:
if cv2.contourArea(cnt)>50:
[x,y,w,h] = cv2.boundingRect(cnt)
if h>54 and w>36:
roi = thresh[y:y+h,x:x+w]
roismall = cv2.resize(roi,(10,10))
roismall = roismall.reshape((1,100))
roismall = np.float32(roismall)
retval, results, neigh_resp, dists = model.find_nearest(roismall, k = 1)
digit_tuples.append( (x, int((results[0][0]))) )
if len(digit_tuples) == 2:
digit_tuples_sorted = sorted(digit_tuples, key=lambda digit_tuple: digit_tuple[0])
speedlimit = 0
for i in range(0, len(digit_tuples_sorted)):
speedlimit = speedlimit * 10 + digit_tuples_sorted[i][1]
bin.speedlimit = speedlimit
print "Found speed limit: " + str(speedlimit)
break
else:
print "Unable to determine speed limit"
#... TODO more
#END SHAPE PROCESSING
'''
svr.debug("Bins", self.debug_frame)
svr.debug("Bins2", self.test_frame)
# Output bins
self.output.bins = self.confirmed
anglesum = 0
for bins in self.output.bins:
bins.theta = (bins.midx - frame.width / 2) * 37 / (frame.width / 2)
bins.phi = -1 * (bins.midy - frame.height / 2) * 36 / (frame.height / 2)
bins.shape = bins.object
anglesum += bins.angle
# bins.orientation = bins.angle
if len(self.output.bins) > 0:
self.output.orientation = anglesum / len(self.output.bins)
else:
self.output.orientation = None
self.return_output()
def process_frame(self, frame):
################
#setup CV ######
################
print "processing frame"
(w, h) = cv.GetSize(frame)
#generate hue selection frames
ones = np.ones((h, w, 1), dtype='uint8')
a = ones * (180 - self.target_hue)
b = ones * (180 - self.target_hue + 20)
a_array = cv.fromarray(a)
b_array = cv.fromarray(b)
#create locations for the test frame and binary frame
frametest = cv.CreateImage(cv.GetSize(frame), 8, 3)
binarytest = cv.CreateImage(cv.GetSize(frame), 8, 1)
#use the red channel for the binary frame (just for debugging purposes)
cv.Copy(frame, frametest)
cv.SetImageCOI(frametest, 3)
cv.Copy(frametest, binarytest)
#reset the COI for test frame to RGB.
cv.SetImageCOI(frametest, 0)
# 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_gate = False
#create a new frame for comparison purposes
unchanged_frame = cv.CreateImage(cv.GetSize(frame), 8, 3)
cv.Copy(frame, unchanged_frame)
#apply noise filter #1
cv.Smooth(frame, frame, cv.CV_MEDIAN, 7, 7)
# Set binary image to have saturation 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, 1)
cv.Copy(hsv, binary)
#spin the color wheel (psuedo-code for later if necessary)
# truncate spectrum marked as end
# shift all values up based on truncating value (mask out 0 regions)
# take truncated bits, and flip them (180->0, 179->1...)
# dnow that truncated bits are flipped, add them back in to final image
#Reset hsv COI
cv.SetImageCOI(hsv, 0)
#correct for wraparound on red spectrum
cv.InRange(binary, a_array, b_array, binarytest) #generate mask
cv.Add(binary, cv.fromarray(ones * 180), binary,
mask=binarytest) #use mask to selectively add values
#run adaptive threshold for edge detection
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(5, 5, 3, 3, cv.CV_SHAPE_ELLIPSE)
cv.Erode(binary, binary, kernel, 1)
cv.Dilate(binary, binary, kernel, 1)
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)
# Get vertical lines
vertical_lines = []
i = 0
for line in raw_lines:
if line[1] < self.vertical_threshold or \
line[1] > (math.pi-self.vertical_threshold):
#absolute value does better grouping currently
vertical_lines.append((abs(line[0]), line[1]))
i += 1
# print message to user for performance purposes
logging.debug("{} possibilities reduced to {} lines".format(
i, len(vertical_lines)))
# Group vertical lines
vertical_line_groups = [
] #A list of line groups which are each a line list
i = 0
for line in vertical_lines:
group_found = False
for line_group in vertical_line_groups:
i += 1
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])
#quick debugging statement
logging.debug("{} internal iterations for {} groups".format(
i, len(vertical_line_groups)))
# Average line groups into lines
vertical_lines = []
for line_group in vertical_line_groups:
rhos = map(lambda line: line[0], line_group) #get rho of each line
angles = map(lambda line: line[1], line_group)
line = (sum(rhos) / len(rhos), circular_average(angles, math.pi))
vertical_lines.append(line)
self.left_pole = None
self.right_pole = None
self.returning = 0
self.found = False
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
self.returning = (self.left_pole + self.right_pole) / 2
logging.info("Returning {}".format(self.returning))
#If this is first iteration, count this as seeing the gate
if self.last_seen < 0:
self.last_center = None
self.last_seen = 0
#increment a counter if result is good.
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 not convinced, forget left/right pole. Else, proclaim success.
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
#extra debugging stuff
if self.debug:
cv.CvtColor(color_filtered, frame, cv.CV_GRAY2RGB)
libvision.misc.draw_lines(frame, vertical_lines)
if self.found:
cv.Circle(frame, (int(frame.width / 2 + self.returning),
int(frame.height / 2)), 15, (0, 255, 0), 2,
8, 0)
font = cv.InitFont(cv.CV_FONT_HERSHEY_SIMPLEX, 1, 1, 1, 3)
cv.PutText(frame, "Gate Sent to Mission Control", (100, 400),
font, (255, 255, 0))
#print frame.width
#cv.ShowImage("Gate", cv.CloneImage(frame))
svr.debug("Gate", cv.CloneImage(frame))
svr.debug("Unchanged", cv.CloneImage(unchanged_frame))
self.return_output()
def main():
os.chdir(sys.argv[1])
try:
os.mkdir(OUTPUT_DIR_NAME)
except OSError:
pass
tree = et.parse("project.xml")
movie = tree.getroot()
file_path = movie.attrib["path"]
if DEBUG:
cv.NamedWindow("win", cv.CV_WINDOW_AUTOSIZE)
cv.MoveWindow("win", 200, 200)
cap = cv.CreateFileCapture(file_path)
skip_frames(cap, movie)
pixel_count = None
prev_img = None
global_frame_counter = 0
file_counter = 0
w = None
h = None
output_img = cv.CreateImage((WIDTH, MAX_FRAMES), cv.IPL_DEPTH_8U, 3)
f = open("shots.txt", "r")
lines = [line for line in f if line] # (start_frame, end_frame, duration)
f.close()
f_frm = open("motion.txt", "w")
f_avg = open("motion_shot-avg.txt", "w")
motion = []
t = time.time()
for nr, line in enumerate(lines):
print(nr + 1), "/", len(lines)
duration = int(line.split("\t")[2])
for frame_counter in range(duration):
img = cv.QueryFrame(cap)
if not img:
print "error?"
print nr, frame_counter
#break
return
if DEBUG:
cv.ShowImage("win", img)
global_frame_counter += 1
if nr == 0 and frame_counter == 0: # first shot, first frame
w = img.width
h = img.height
pixel_count = float(img.width * img.height)
prev_img = cv.CreateImage(cv.GetSize(img), cv.IPL_DEPTH_8U, 3)
cv.Zero(prev_img)
diff = cv.CreateImage(cv.GetSize(img), cv.IPL_DEPTH_8U, 3)
cv.AbsDiff(img, prev_img, diff)
cv.Threshold(diff, diff, 10, 255, cv.CV_THRESH_BINARY)
d_color = 0
for i in range(1, 4):
cv.SetImageCOI(diff, i)
d_color += cv.CountNonZero(diff) / pixel_count
d_color = d_color / 3 # 0..1
#print "%.1f" % (d_color*100), "%"
motion.append(d_color)
cv.Copy(img, prev_img)
# WRITE TEXT FILE
f_frm.write("%f\n" % (d_color))
if frame_counter == duration - 1: # last frame of current shot
motion_value = sum(motion) / len(motion)
print "average motion:", motion_value
f_avg.write("%f\t%d\n" % (motion_value, duration))
motion = []
# WRITE IMAGE
if frame_counter == 0: # ignore each first frame -- the diff after a hard cut is meaningless
global_frame_counter -= 1
continue
else:
for i in range(WIDTH):
value = d_color * 255
cv.Set2D(output_img,
(global_frame_counter - 1) % MAX_FRAMES, i,
cv.RGB(value, value, value))
if global_frame_counter % MAX_FRAMES == 0:
cv.SaveImage(
os.path.join(OUTPUT_DIR_NAME,
"motion_%03d.png" % (file_counter)),
output_img)
file_counter += 1
if DEBUG:
if cv.WaitKey(1) == 27:
break
if global_frame_counter % MAX_FRAMES != 0:
#cv.SetImageROI(output_img, (0, 0, WIDTH-1, (global_frame_counter % MAX_FRAMES)-1))
cv.SetImageROI(output_img, (0, 0, WIDTH - 1,
(global_frame_counter - 1) % MAX_FRAMES))
cv.SaveImage(
os.path.join(OUTPUT_DIR_NAME, "motion_%03d.png" % (file_counter)),
output_img)
f_frm.close()
f_avg.close()
if DEBUG:
cv.DestroyWindow("win")
print "%.2f min" % ((time.time() - t) / 60)
#raw_input("- done -")
return
def main():
BLACK_AND_WHITE = False
THRESHOLD = 0.48
BW_THRESHOLD = 0.4
os.chdir(sys.argv[1])
try:
os.mkdir(OUTPUT_DIR_NAME)
except:
pass
if len(sys.argv) > 2:
if sys.argv[2] == "bw":
BLACK_AND_WHITE = True
THRESHOLD = BW_THRESHOLD
print "##########"
print " B/W MODE"
print "##########"
tree = et.parse("project.xml")
movie = tree.getroot()
file_path = movie.attrib["path"]
cap = cv.CreateFileCapture(file_path)
if DEBUG:
cv.NamedWindow("win", cv.CV_WINDOW_AUTOSIZE)
cv.MoveWindow("win", 200, 200)
hist = None
prev_hist = None
prev_img = None
pixel_count = None
frame_counter = 0
last_frame_black = False
black_frame_start = -1
t = time.time()
while 1:
img_orig = cv.QueryFrame(cap)
if not img_orig: # eof
cv.SaveImage(OUTPUT_DIR_NAME + "\\%06d.png" % (frame_counter - 1),
prev_img)
"""movie.set("frames", str(frame_counter))
tree.write("project.xml")"""
break
img = cv.CreateImage(
(int(img_orig.width / 4), int(img_orig.height / 4)),
cv.IPL_DEPTH_8U, 3)
cv.Resize(img_orig, img, cv.CV_INTER_AREA)
if frame_counter == 0: # erster frame
cv.SaveImage(OUTPUT_DIR_NAME + "\\%06d.png" % (0), img)
pixel_count = img.width * img.height
prev_img = cv.CreateImage(cv.GetSize(img), cv.IPL_DEPTH_8U, 3)
cv.Zero(prev_img)
if DEBUG and frame_counter % 2 == 1:
cv.ShowImage("win", img)
img_hsv = cv.CreateImage(cv.GetSize(img), cv.IPL_DEPTH_8U, 3)
cv.CvtColor(img, img_hsv, cv.CV_BGR2HSV)
# #####################
# METHOD #1: find the number of pixels that have (significantly) changed since the last frame
diff = cv.CreateImage(cv.GetSize(img), cv.IPL_DEPTH_8U, 3)
cv.AbsDiff(img_hsv, prev_img, diff)
cv.Threshold(diff, diff, 10, 255, cv.CV_THRESH_BINARY)
d_color = 0
for i in range(1, 4):
cv.SetImageCOI(diff, i)
d_color += float(cv.CountNonZero(diff)) / float(pixel_count)
if not BLACK_AND_WHITE:
d_color = float(d_color / 3.0) # 0..1
# #####################
# METHOD #2: calculate the amount of change in the histograms
h_plane = cv.CreateMat(img.height, img.width, cv.CV_8UC1)
s_plane = cv.CreateMat(img.height, img.width, cv.CV_8UC1)
v_plane = cv.CreateMat(img.height, img.width, cv.CV_8UC1)
cv.Split(img_hsv, h_plane, s_plane, v_plane, None)
planes = [h_plane, s_plane, v_plane]
hist_size = [50, 50, 50]
hist_range = [[0, 360], [0, 255], [0, 255]]
if not hist:
hist = cv.CreateHist(hist_size, cv.CV_HIST_ARRAY, hist_range, 1)
cv.CalcHist([cv.GetImage(i) for i in planes], hist)
cv.NormalizeHist(hist, 1.0)
if not prev_hist:
prev_hist = cv.CreateHist(hist_size, cv.CV_HIST_ARRAY, hist_range,
1)
# wieso gibt es kein cv.CopyHist()?!
cv.CalcHist([cv.GetImage(i) for i in planes], prev_hist)
cv.NormalizeHist(prev_hist, 1.0)
continue
d_hist = cv.CompareHist(prev_hist, hist, cv.CV_COMP_INTERSECT)
# combine both methods to make a decision
if ((0.4 * d_color + 0.6 * (1 - d_hist))) >= THRESHOLD:
if DEBUG:
if frame_counter % 2 == 0:
cv.ShowImage("win", img)
winsound.PlaySound(soundfile,
winsound.SND_FILENAME | winsound.SND_ASYNC)
print "%.3f" % ((0.4 * d_color + 0.6 * (1 - d_hist))), "%.3f" % (
d_color), "%.3f" % (1 - d_hist), frame_counter
if DEBUG and DEBUG_INTERACTIVE:
if win32api.MessageBox(0, "cut?", "",
win32con.MB_YESNO) == 6: #yes
cv.SaveImage(
OUTPUT_DIR_NAME + "\\%06d.png" % (frame_counter), img)
else:
cv.SaveImage(OUTPUT_DIR_NAME + "\\%06d.png" % (frame_counter),
img)
cv.CalcHist([cv.GetImage(i) for i in planes], prev_hist)
cv.NormalizeHist(prev_hist, 1.0)
# #####################
# METHOD #3: detect series of (almost) black frames as an indicator for "fade to black"
average = cv.Avg(v_plane)[0]
if average <= 0.6:
if not last_frame_black: # possible the start
print "start", frame_counter
black_frame_start = frame_counter
last_frame_black = True
else:
if last_frame_black: # end of a series of black frames
cut_at = black_frame_start + int(
(frame_counter - black_frame_start) / 2)
print "end", frame_counter, "cut at", cut_at
img_black = cv.CreateImage(
(img_orig.width / 4, img_orig.height / 4), cv.IPL_DEPTH_8U,
3)
cv.Set(img_black, cv.RGB(0, 255, 0))
cv.SaveImage(OUTPUT_DIR_NAME + "\\%06d.png" % (cut_at),
img_black)
last_frame_black = False
cv.Copy(img_hsv, prev_img)
frame_counter += 1
if DEBUG:
if cv.WaitKey(1) == 27:
break
if DEBUG:
cv.DestroyWindow("win")
print "%.2f min" % ((time.time() - t) / 60)
#raw_input("- done -")
return
def process_frame(self, frame):
self.debug_frame = cv.CreateImage(cv.GetSize(frame), 8, 3)
og_frame = cv.CreateImage(cv.GetSize(frame), 8, 3)
cv.Copy(frame, self.debug_frame)
cv.Copy(self.debug_frame, og_frame)
cv.Smooth(frame, frame, cv.CV_MEDIAN, 7, 7)
# Set binary image to have saturation 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, 1) #3 before competition #2 at competition
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(5, 5, 3, 3, cv.CV_SHAPE_ELLIPSE)
cv.Erode(binary, binary, kernel, 1)
cv.Dilate(binary, binary, kernel, 1)
# Get Edges
#cv.Canny(binary, binary, 30, 40)
cv.CvtColor(binary, self.debug_frame, cv.CV_GRAY2RGB)
# 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
)
lines = []
for line in raw_lines:
lines.append(line)
#Grouping lines depending on endpoint similarities
for line1 in lines[:]:
for line2 in lines[:]:
if line1 in lines and line2 in lines and line1 != line2:
if math.fabs(line1[0][0] - line2[0][0]) < self.max_corner_range and \
math.fabs(line1[0][1] - line2[0][1]) < self.max_corner_range and \
math.fabs(line1[1][0] - line2[1][0]) < self.max_corner_range and \
math.fabs(line1[1][1] - line2[1][1]) < self.max_corner_range:
if line_distance(line1[0], line1[1]) > line_distance(line2[0], line2[1]):
lines.remove(line2)
else:
lines.remove(line1)
elif math.fabs(line1[0][0] - line2[1][0]) < self.max_corner_range and \
math.fabs(line1[0][1] - line2[1][1]) < self.max_corner_range and \
math.fabs(line1[1][0] - line2[0][0]) < self.max_corner_range and \
math.fabs(line1[1][1] - line2[0][1]) < self.max_corner_range:
if line_distance(line1[0], line1[1]) > line_distance(line2[0], line2[1]):
lines.remove(line2)
else:
lines.remove(line1)
self.hough_corners = []
for line in lines:
self.hough_corners.append(line[0])
self.hough_corners.append(line[1])
for corner1 in self.hough_corners[:]:
for corner2 in self.hough_corners[:]:
if corner1 is not corner2 and corner1 in self.hough_corners and corner2 in self.hough_corners:
if math.fabs(corner1[0] - corner2[0]) < self.max_corner_range4 and \
math.fabs(corner1[1] - corner2[1]) < self.max_corner_range4:
corner1 = [(corner1[0] + corner2[0]) / 2, (corner1[1] + corner2[1]) / 2]
self.hough_corners.remove(corner2)
for line1 in lines:
#cv.Line(self.debug_frame,line1[0],line1[1], (0,0,255), 10, cv.CV_AA, 0)
for line2 in lines:
if line1 is not line2:
self.find_corners(line1, line2)
for corner1 in self.corners:
for corner2 in self.corners:
if math.fabs(corner1[1][0] - corner2[1][0]) < self.max_corner_range2 and \
math.fabs(corner1[1][1] - corner2[1][1]) < self.max_corner_range2 and \
math.fabs(corner1[2][0] - corner2[2][0]) < self.max_corner_range2 and \
math.fabs(corner1[2][1] - corner2[2][1]) < self.max_corner_range2 and \
math.fabs(corner1[0][0] - corner2[0][0]) > self.max_corner_range2 and \
math.fabs(corner1[0][1] - corner2[0][1]) > self.max_corner_range2:
pt1 = (int(corner1[0][0]), int(corner1[0][1]))
pt4 = (int(corner2[0][0]), int(corner2[0][1]))
pt3 = (int(corner1[1][0]), int(corner1[1][1]))
pt2 = (int(corner1[2][0]), int(corner1[2][1]))
#line_color = (0,255,0)s
#cv.Line(self.debug_frame,pt1,pt2, line_color, 10, cv.CV_AA, 0)
#cv.Line(self.debug_frame,pt1,pt3, line_color, 10, cv.CV_AA, 0)
#cv.Line(self.debug_frame,pt4,pt2, line_color, 10, cv.CV_AA, 0)
#cv.Line(self.debug_frame,pt4,pt3, line_color, 10, cv.CV_AA, 0)
new_bin = Bin(pt1, pt2, pt3, pt4)
new_bin.id = self.bin_id
self.bin_id += 1
if math.fabs(line_distance(pt1, pt2) - line_distance(pt3, pt4)) < self.parallel_sides_length_thresh and \
math.fabs(line_distance(pt1, pt3) - line_distance(pt2, pt4)) < self.parallel_sides_length_thresh:
self.Bins.append(new_bin)
print "new_bin"
elif (math.fabs(corner1[1][0] - corner2[2][0]) < self.max_corner_range2 and
math.fabs(corner1[1][1] - corner2[2][1]) < self.max_corner_range2 and
math.fabs(corner1[2][0] - corner2[1][0]) < self.max_corner_range2 and
math.fabs(corner1[2][1] - corner2[1][1]) < self.max_corner_range2 and
math.fabs(corner1[0][0] - corner2[0][0]) > self.max_corner_range2 and
math.fabs(corner1[0][1] - corner2[0][1]) > self.max_corner_range2):
continue
self.corners = []
self.final_corners = self.sort_corners() #Results are not used. Experimental corners which have been seen twice, should be only the corners we want, but there were problems
self.sort_bins()
self.update_bins()
self.group_bins()
self.draw_bins()
for corner in self.hough_corners:
line_color = [255, 0, 0]
cv.Circle(self.debug_frame, corner, 15, (255, 0, 0), 2, 8, 0)
for line in lines:
line_color = [255, 0, 0]
cv.Line(self.debug_frame, line[0], line[1], line_color, 5, cv.CV_AA, 0)
#cv.Circle(self.debug_frame, line[0], 15, (255,0,0), 2,8,0)
#cv.Circle(self.debug_frame, line[1], 15, (255,0,0), 2,8,0)
#Output bins
self.output.bins = self.Bins
anglesum = 0
for bins in self.output.bins:
bins.theta = (bins.center[0] - frame.width / 2) * 37 / (frame.width / 2)
bins.phi = -1 * (bins.center[1] - frame.height / 2) * 36 / (frame.height / 2)
anglesum += bins.angle
# bins.orientation = bins.angle
if len(self.output.bins) > 0:
self.output.orientation = anglesum / len(self.output.bins)
else:
self.output.orientation = None
self.return_output()
svr.debug("Bins", self.debug_frame)
svr.debug("Original", og_frame)
#BEGIN SHAPE PROCESSING
#constants
img_width = 128
img_height = 256
number_x = 23
number_y = 111
number_w = 82
number_h = 90
bin_thresh_blocksize = 11
bin_thresh = 1.9
red_significance_threshold = 0.4
#load templates - run once, accessible to number processor
number_templates = [
(10, cv.LoadImage("number_templates/10.png")),
(16, cv.LoadImage("number_templates/16.png")),
(37, cv.LoadImage("number_templates/37.png")),
(98, cv.LoadImage("number_templates/98.png")),
]
#Begin Bin Contents Processing
for bin in self.Bins:
#Take the bin's corners, and get an image containing an img_width x img_height rectangle of it
transf = cv.CreateMat(3, 3, cv.CV_32FC1)
cv.GetPerspectiveTransform(
[bin.corner1, bin.corner2, bin.corner3, bin.corner4],
[(0, 0), (0, img_height), (img_width, 0), (img_width, img_height)],
transf
)
bin_image = cv.CreateImage([img_width, img_height], 8, 3)
cv.WarpPerspective(frame, bin_image, transf)
#AdaptaveThreshold to get black and white image highlighting the number (still works better than my yellow-vs-red threshold attempt
hsv = cv.CreateImage(cv.GetSize(bin_image), 8, 3)
bin_thresh_image = cv.CreateImage(cv.GetSize(bin_image), 8, 1)
cv.CvtColor(bin_image, hsv, cv.CV_BGR2HSV)
cv.SetImageCOI(hsv, 3)
cv.Copy(hsv, bin_thresh_image)
cv.SetImageCOI(hsv, 0)
cv.AdaptiveThreshold(bin_thresh_image, bin_thresh_image,
255,
cv.CV_ADAPTIVE_THRESH_MEAN_C,
cv.CV_THRESH_BINARY_INV,
bin_thresh_blocksize,
bin_thresh,
)
kernel = cv.CreateStructuringElementEx(5, 5, 3, 3, cv.CV_SHAPE_ELLIPSE)
cv.Erode(bin_thresh_image, bin_thresh_image, kernel, 1)
cv.Dilate(bin_thresh_image, bin_thresh_image, kernel, 1)
#Here, we loop through all four different templates, and figure out which one we think is most likely.
#The comparison function counts corresponding pixels that are non-zero in each image, and then corresponding pixels that are different in each image. The ratio of diff_count/both_count is our "unconfidence" ratio. The lower it is, the more confident we are.
#There are two nearly identical pieces of code within this loop. One checks the bin right-side-up, and the other one checks it flipped 180.
last_thought_number = -1
last_unconfidence_ratio = number_w * number_h + 2
for i in range(0, len(number_templates)):
both_count = 0
diff_count = 0
this_number_image = number_templates[i][1]
for y in range(0, number_h):
for x in range(0, number_w):
if (bin_thresh_image[y + number_y, x + number_x] != 0) and (this_number_image[y, x][0] != 0):
both_count += 1
elif (bin_thresh_image[y + number_y, x + number_x] != 0) or (this_number_image[y, x][0] != 0):
diff_count += 1
if both_count == 0:
unconfidence_ratio = number_w * number_h + 1 # max unconfidence
else:
unconfidence_ratio = 1.0 * diff_count / both_count
if unconfidence_ratio < last_unconfidence_ratio:
last_thought_number = number_templates[i][0]
last_unconfidence_ratio = unconfidence_ratio
both_count = 0
diff_count = 0
for y in range(0, number_h):
for x in range(0, number_w):
if (bin_thresh_image[img_height - number_y - 1 - y, img_width - number_x - 1 - x] != 0) and (
this_number_image[y, x][0] != 0):
both_count += 1
elif (bin_thresh_image[img_height - number_y - 1 - y, img_width - number_x - 1 - x] != 0) or (
this_number_image[y, x][0] != 0):
diff_count += 1
if both_count == 0:
unconfidence_ratio = number_w * number_h + 1 # max unconfidence
else:
unconfidence_ratio = 1.0 * diff_count / both_count
if unconfidence_ratio < last_unconfidence_ratio:
last_thought_number = number_templates[i][0]
last_unconfidence_ratio = unconfidence_ratio
print str(last_thought_number) + " | " + str(last_unconfidence_ratio)
try: #check if it's defined
bin.number_unconfidence_ratio
except:
bin.number_unconfidence_ratio = last_unconfidence_ratio
bin.number = last_thought_number
print "Set Speed Limit Number"
else:
if last_unconfidence_ratio < bin.number_unconfidence_ratio:
bin.number_unconfidence_ratio = last_unconfidence_ratio
if bin.number == last_thought_number:
print "More Confident on Same Number: Updated"
else:
print "More Confident on Different Number: Updated"
bin.icon = last_thought_number
def process_frame(self, frame):
(w, h) = cv.GetSize(frame)
#generate hue selection frames
#create locations for the a pair of test frames
frametest = cv.CreateImage(cv.GetSize(frame), 8, 3)
binarytest = cv.CreateImage(cv.GetSize(frame), 8, 1)
#use the red channel for the binary frame (just for debugging purposes)
cv.Copy(frame, frametest)
cv.SetImageCOI(frametest, 3)
cv.Copy(frametest, binarytest)
cv.SetImageCOI(frametest, 0) #reset COI
#svr.debug("R?",binarytest)
# 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_gate = False
#create a new frame just for comparison purposes
unchanged_frame = cv.CreateImage(cv.GetSize(frame), 8, 3)
cv.Copy(frame, unchanged_frame)
#apply a course noise filter
cv.Smooth(frame, frame, cv.CV_MEDIAN, 7, 7)
# Set binary image to have saturation 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, 1)
cv.Copy(hsv, binary)
cv.SetImageCOI(hsv, 0) #reset COI
#shift hue of image such that orange->red are at top of spectrum
'''
binary = libvision.misc.cv_to_cv2(binary)
binary = libvision.misc.shift_hueCV2(binary, self.target_shift)
binary = libvision.misc.cv2_to_cv(binary)
'''
#correct for wraparound on red spectrum
#cv.InRange(binary,a_array,b_array,binarytest) #generate mask
#cv.Add(binary,cv.fromarray(ones*180),binary,mask=binarytest) #use mask to selectively add values
svr.debug("R2?", binary)
svr.debug("R2?", binary)
#run adaptive threshold for edge detection and more noise filtering
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(5, 5, 3, 3, cv.CV_SHAPE_ELLIPSE)
cv.Erode(binary, binary, kernel, 1)
cv.Dilate(binary, binary, kernel, 1)
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)
# Get vertical lines
vertical_lines = []
for line in raw_lines:
if line[1] < self.vertical_threshold or \
line[1] > math.pi-self.vertical_threshold:
#absolute value does better grouping currently
vertical_lines.append((abs(line[0]), line[1]))
#print message to user for performance purposes
logging.debug("{} possibilities reduced to {} lines".format(
len(raw_lines), len(vertical_lines)))
# Group vertical lines
vertical_line_groups = [
] # A list of line groups which are each a line list
i = 0
for line in vertical_lines:
group_found = False
for line_group in vertical_line_groups:
i += 1
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])
#quick debugging statement
logging.debug("{} internal iterations for {} groups".format(
i, len(vertical_line_groups)))
# 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)
####################################################
#vvvv Horizontal line code isn't used for anything
# 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
if self.debug:
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 = []
#^^^ Horizontal line code isn't used for anything
###################################################
self.left_pole = None
self.right_pole = None
#print vertical_lines
self.returning = 0
self.found = False
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
self.returning = (self.left_pole + self.right_pole) / 2
logging.info("Returning {} as gate center delta.".format(
self.returning))
#initialize first iteration with 2 known poles
if self.last_seen < 0:
self.last_center = None
self.last_seen = 0
#increment a counter if result is good.
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 not conviced, forget left/right pole. Else proclaim success.
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
#TODO: If one pole is seen, is it left or right pole?
if self.debug:
cv.CvtColor(color_filtered, frame, cv.CV_GRAY2RGB)
libvision.misc.draw_lines(frame, vertical_lines)
libvision.misc.draw_lines(frame, horizontal_lines)
if self.found:
cv.Circle(frame, (int(frame.width / 2 + self.returning),
int(frame.height / 2)), 15, (0, 255, 0), 2,
8, 0)
font = cv.InitFont(cv.CV_FONT_HERSHEY_SIMPLEX, 1, 1, 1, 3)
cv.PutText(frame, "Gate Sent to Mission Control", (100, 400),
font, (255, 255, 0))
#print frame.width
#cv.ShowImage("Gate", cv.CloneImage(frame))
svr.debug("Gate", cv.CloneImage(frame))
svr.debug("Unchanged", cv.CloneImage(unchanged_frame))
#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.return_output()
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)
def process_frame(self, frame):
frametest = cv.CreateImage(cv.GetSize(frame), 8, 3)
binarytest = cv.CreateImage(cv.GetSize(frame), 8, 1)
cv.Copy(frame, frametest)
cv.SetImageCOI(frametest, 3)
cv.Copy(frametest, binarytest)
cv.SetImageCOI(frametest, 0)
svr.debug("R?", binarytest)
# 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_gate = False
unchanged_frame = cv.CreateImage(cv.GetSize(frame), 8, 3)
cv.Copy(frame, unchanged_frame)
cv.Smooth(frame, frame, cv.CV_MEDIAN, 7, 7)
# Set binary image to have saturation 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, 1)
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(5, 5, 3, 3, cv.CV_SHAPE_ELLIPSE)
cv.Erode(binary, binary, kernel, 1)
cv.Dilate(binary, binary, kernel, 1)
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)
# Get vertical lines
vertical_lines = []
for line in raw_lines:
if line[1] < self.vertical_threshold or \
line[1] > math.pi-self.vertical_threshold:
#absolute value does better grouping currently
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
if self.debug:
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
print vertical_lines
self.returning = 0
self.found = False
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
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
#TODO: If one pole is seen, is it left or right pole?
if self.debug:
cv.CvtColor(color_filtered, frame, cv.CV_GRAY2RGB)
libvision.misc.draw_lines(frame, vertical_lines)
libvision.misc.draw_lines(frame, horizontal_lines)
if self.found:
cv.Circle(frame, (int(frame.width / 2 + self.returning),
int(frame.height / 2)), 15, (0, 255, 0), 2,
8, 0)
font = cv.InitFont(cv.CV_FONT_HERSHEY_SIMPLEX, 1, 1, 1, 3)
cv.PutText(frame, "Gate Sent to Mission Control", (100, 400),
font, (255, 255, 0))
print frame.width
#cv.ShowImage("Gate", cv.CloneImage(frame))
svr.debug("Gate", cv.CloneImage(frame))
svr.debug("Unchanged", cv.CloneImage(unchanged_frame))
#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.return_output()
print self
def process_frame(self, frame):
debug_frame = cv.CreateImage(cv.GetSize(frame), 8, 3)
cv.Copy(frame, debug_frame)
cv.Smooth(frame, frame, cv.CV_MEDIAN, 7, 7)
# Set binary image to have saturation 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(5, 5, 3, 3, cv.CV_SHAPE_ELLIPSE)
cv.Erode(binary, binary, kernel, 1)
cv.Dilate(binary, binary, kernel, 1)
# Get Edges
#cv.Canny(binary, binary, 30, 40)
cv.CvtColor(binary, debug_frame, cv.CV_GRAY2RGB)
# 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)
line_groups = [] # A list of line groups which are each a line list
for line in raw_lines:
group_found = False
for line_group in line_groups:
if line_group_accept_test(line_group, line, self.max_range):
line_group.append(line)
group_found = True
if not group_found:
line_groups.append([line])
# Average line groups into lines
lines = []
for line_group in 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))
lines.append(line)
libvision.misc.draw_lines(debug_frame, raw_lines)
# cv.CvtColor(color_filtered,debug_frame, cv.CV_GRAY2RGB)
svr.debug("Bins", debug_frame)
def process_frame(self, frame):
self.debug_frame = cv.CreateImage(cv.GetSize(frame), 8, 3)
og_frame = cv.CreateImage(cv.GetSize(frame), 8, 3)
cv.Copy(frame, self.debug_frame)
cv.Copy(self.debug_frame, og_frame)
cv.Smooth(frame, frame, cv.CV_MEDIAN, 7, 7)
# Set binary image to have saturation 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, 1)
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(5, 5, 3, 3, cv.CV_SHAPE_ELLIPSE)
cv.Erode(binary, binary, kernel, 1)
cv.Dilate(binary, binary, kernel, 1)
# Get Edges
#cv.Canny(binary, binary, 30, 40)
cv.CvtColor(binary, self.debug_frame, cv.CV_GRAY2RGB)
# 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)
lines = []
corners = []
for line in raw_lines:
lines.append(line)
# Grouping lines depending on endpoint similarities
for line1 in lines[:]:
for line2 in lines[:]:
if line1 in lines and line2 in lines and line1 != line2:
if math.fabs(line1[0][0] - line2[0][0]) < self.max_corner_range and \
math.fabs(line1[0][1] - line2[0][1]) < self.max_corner_range and \
math.fabs(line1[1][0] - line2[1][0]) < self.max_corner_range and \
math.fabs(line1[1][1] - line2[1][1]) < self.max_corner_range:
if line_distance(line1[0], line1[1]) > line_distance(
line2[0], line2[1]):
lines.remove(line2)
else:
lines.remove(line1)
elif math.fabs(line1[0][0] - line2[1][0]) < self.max_corner_range and \
math.fabs(line1[0][1] - line2[1][1]) < self.max_corner_range and \
math.fabs(line1[1][0] - line2[0][0]) < self.max_corner_range and \
math.fabs(line1[1][1] - line2[0][1]) < self.max_corner_range:
if line_distance(line1[0], line1[1]) > line_distance(
line2[0], line2[1]):
lines.remove(line2)
else:
lines.remove(line1)
for line in lines:
corners.append(line[0])
corners.append(line[1])
for corner1 in corners:
for corner2 in corners:
for corner3 in corners:
for corner4 in corners:
# Checks that corners are not the same and are in the proper orientation
if corner4[0] != corner3[0] and corner4[0] != corner2[0] and corner4[0] != corner1[0] and \
corner3[0] != corner2[0] and corner3[0] != corner1[0] and corner2[0] != corner1[0] and \
corner4[1] != corner3[1] and corner4[1] != corner2[1] and corner4[1] != corner1[1] and \
corner3[1] != corner2[1] and corner3[1] != corner1[1] and corner2[1] != corner1[1] and \
corner2[0] >= corner3[0] and corner1[1] >= corner4[1] and corner2[0] >= corner1[0]:
# Checks that the side ratios are correct
if math.fabs(line_distance(corner1, corner3) - line_distance(corner2, corner4)) < self.size_threshold and \
math.fabs(line_distance(corner1, corner2) - line_distance(corner3, corner4)) < self.size_threshold and \
math.fabs(line_distance(corner1, corner3) / line_distance(corner1, corner2)) < self.ratio_threshold and \
math.fabs(line_distance(corner1, corner2) / line_distance(corner1, corner3)) < self.ratio_threshold:
#^^^ CHANGED OR TO AND --> DID MUCH BETTER. CONSIDER CHANGING ON BINSCORNER
# Checks that angles are roughly 90 degrees
angle_cnr_2 = math.fabs(
angle_between_lines(
line_slope(corner1, corner2),
line_slope(corner2, corner4)))
if self.angle_min < angle_cnr_2 < self.angle_max:
angle_cnr_3 = math.fabs(
angle_between_lines(
line_slope(corner1, corner3),
line_slope(corner3, corner4)))
if self.angle_min2 < angle_cnr_3 < self.angle_max2:
new_box = Pizza(
corner1, corner2, corner3, corner4)
self.match_Boxes(new_box)
for Box in self.Boxes[:]:
Box.lastseen -= 1
if Box.lastseen < 0:
self.Boxes.remove(Box)
self.draw_pizza()
for line in lines:
cv.Line(self.debug_frame, line[0], line[1], (255, 255, 0), 10,
cv.CV_AA, 0)
cv.Circle(self.debug_frame, line[0], 15, (255, 0, 0), 2, 8, 0)
cv.Circle(self.debug_frame, line[1], 15, (255, 0, 0), 2, 8, 0)
self.output.pizza = self.Boxes
anglesum = 0
for Box in self.Boxes:
Box.theta = (Box.center[0] - frame.width / 2) * 37 / (frame.width /
2)
Box.phi = -1 * (Box.center[1] -
frame.height / 2) * 36 / (frame.height / 2)
anglesum += Box.angle
if len(self.output.pizza) > 0:
self.output.orientation = anglesum / len(self.output.pizza)
else:
self.output.orientation = None
self.return_output()
svr.debug("Pizza", self.debug_frame)
svr.debug("Original", og_frame)
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
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, 1)
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, 1)
'''
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)
# 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
if self.debug:
cv.CvtColor(color_filtered, frame, cv.CV_GRAY2RGB)
libvision.misc.draw_lines(frame, vertical_lines)
libvision.misc.draw_lines(frame, horizontal_lines)
#cv.ShowImage("Hedge", cv.CloneImage(frame))
svr.debug("Hedge", cv.CloneImage(frame))
# 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
