localMax = cv.CreateMat(dst_32f.height, dst_32f.width, cv.CV_8U)
cv.Cmp(
dst_32f, dilated, localMax, cv.CV_CMP_EQ
) #compare allow to keep only non modified pixel which are local maximum values which are corners.
threshold = 0.01 * maxv
cv.Threshold(dst_32f, dst_32f, threshold, 255, cv.CV_THRESH_BINARY)
cornerMap = cv.CreateMat(dst_32f.height, dst_32f.width, cv.CV_8U)
cv.Convert(dst_32f, cornerMap) #Convert to make the and
cv.And(cornerMap, localMax, cornerMap) #Delete all modified pixels
radius = 3
thickness = 2
l = []
for x in range(
cornerMap.height
): #Create the list of point take all pixel that are not 0 (so not black)
for y in range(cornerMap.width):
if cornerMap[x, y]:
l.append((y, x))
for center in l:
cv.Circle(im, center, radius, (255, 255, 255), thickness)
cv.ShowImage("Image", im)
cv.ShowImage("CornerHarris Result", dst_32f)
cv.ShowImage("Unique Points after Dilatation/CMP/And", cornerMap)
cv.WaitKey(0)
def draw_subdiv_point(img, fp, color):
cv.Circle(img, (cv.Round(fp[0]), cv.Round(fp[1])), 3, color, cv.CV_FILLED,
8, 0)
def draw(self, img, pixmapper, bounds):
'''draw the trail'''
for p in self.points:
(px, py) = pixmapper(p)
if px >= 0 and py >= 0 and px < img.width and py < img.height:
cv.Circle(img, (px, py), 1, self.colour)
def run(self):
# Initialize
log_file_name = "tracker_output.log"
log_file = open( log_file_name, 'a' )
#fps = 25
#cap = cv2.VideoCapture( '../000104-.avi'
frame = cv.QueryFrame( self.capture )
frame_size = cv.GetSize( frame )
foreground = cv.CreateImage(cv.GetSize(frame),8,1)
foremat = cv.GetMat(foreground)
Nforemat = numpy.array(foremat, dtype=numpy.float32)
gfilter=sys.argv[2]
gfilter_string=gfilter
gfilter=float(gfilter)
print "Processing Tracker with filter: " + str(gfilter)
# Capture the first frame from webcam for image properties
display_image = cv.QueryFrame( self.capture )
# Create Background Subtractor
fgbg = cv2.BackgroundSubtractorMOG()
# 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 = []
fps = 25
t0 = 165947
# For toggling display:
image_list = [ "camera", "shadow", "white", "threshold", "display", "yellow" ]
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)
text_coord2 = ( 5, 30 )
text_coord3 = ( 5, 45 )
###############################
### Face detection stuff
#haar_cascade = cv.Load( 'haarcascades/haarcascade_frontalface_default.xml' )
#haar_cascade = cv.Load( 'C:/OpenCV2.2/data/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 = 20
while True:
# Capture frame from webcam
camera_image = cv.QueryFrame( self.capture )
#ret, frame = cap.read()
frame_count += 1
frame_t0 = time.time()
mat = cv.GetMat(camera_image)
Nmat = numpy.array(mat, dtype=numpy.uint8)
# Create an image with interactive feedback:
display_image = cv.CloneImage( camera_image )
# NEW INSERT - FGMASK
fgmask = fgbg.apply(Nmat,Nforemat,-1)
fgmask = cv.fromarray(fgmask)
# 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 ) #Changed from 19 AND MADE MEDIAN FILTER
# Smooth to get rid of false positives
# color_image = numpy.asarray( cv.GetMat( color_image ) )
# (mu, sigma) = cv2.meanStdDev(color_image)
# edges = cv2.Canny(color_image, mu - sigma, mu + sigma)
# lines = cv2.HoughLines(edges, 1, pi / 180, 70)
# 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, gfilter, 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 )
# Smooth Before thresholding
cv.Smooth( grey_image, grey_image, cv.CV_GAUSSIAN, 19, 19 )
# 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 ) #changed from 19 - AND put smooth before threshold
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] )
frame_hsv = cv.CreateImage(cv.GetSize(color_image),8,3)
cv.CvtColor(color_image,frame_hsv,cv.CV_BGR2HSV)
imgthreshold_yellow=cv.CreateImage(cv.GetSize(color_image),8,1)
imgthreshold_white=cv.CreateImage(cv.GetSize(color_image),8,1)
imgthreshold_white2=cv.CreateImage(cv.GetSize(color_image),8,1)
cv.InRangeS(frame_hsv,cv.Scalar(0,0,196),cv.Scalar(255,255,255),imgthreshold_white) # changed scalar from 255,15,255 to 255,255,255
cv.InRangeS(frame_hsv,cv.Scalar(41,43,224),cv.Scalar(255,255,255),imgthreshold_white2)
cv.InRangeS(frame_hsv,cv.Scalar(20,100,100),cv.Scalar(30,255,255),imgthreshold_yellow)
#cvCvtColor(color_image, yellowHSV, CV_BGR2HSV)
#lower_yellow = np.array([10, 100, 100], dtype=np.uint8)
#upper_yellow = np.array([30, 255, 255], dtype=np.uint8)
#mask_yellow = cv2.inRange(yellowHSV, lower_yellow, upper_yellow)
#res_yellow = cv2.bitwise_and(color_image, color_image, mask_yellow = mask_yellow)
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 )
i=0
while contour:
# c = contour[i]
# m = cv2.moments(c)
# Area = m['m00']
# print( Area )
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)
# if Area > 3000:
# cv2.drawContours(imgrgb,[cnt],0,(255,255,255),2)
# print(Area)
i=i+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 < .35: # 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] ) #Commented Out 3/20/2016
continue
#print "Target %s pixel(b,g,r) : USING the one iwth distance: %d at %s, C:%s" % (target, distance, nearest_possible_entity[3] , nearest_possible_entity[1]) # Commented Out 3/20/2016
# 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_count, 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
if imgthreshold_white[target[1],target[0]] == 0.0:
# It's a real detect (not a line marker)
new_entity = [ name, color, last_time_seen, target ]
this_frame_entity_list.append( new_entity )
log_file.write( "%.3f %.3f FOUND %s %d %d\n" % ( frame_count/fps, frame_count, new_entity[0], new_entity[3][0], new_entity[3][1] ) )
filedrive = "C:/Users/525494/New_folder/000216/run_096/"
filename = "img"+str(name)
#print "gfilter is: %.2f" + gfilter
cv.SaveImage("image-test%s-%3f.png"%(new_entity[0],gfilter), display_image)
elif imgthreshold_white[target[1],target[0]] == 255.0:
# It's a white line detect
new_entity = [ name, color, last_time_seen, target ]
this_frame_entity_list.append( new_entity )
log_file.write( "%.3f %.3f FOUND %s %d %d\n" % ( frame_count/fps, frame_count, new_entity[0], new_entity[3][0], new_entity[3][1] ) )
filedrive = "C:/Users/525494/New_folder/000216/run_096/"
filename = "img"+str(name)
#print "gfilter is: %.2f" + gfilter
cv.SaveImage("white-line-image-test%s-%3f.png"%(new_entity[0],gfilter), display_image)
elif imgthreshold_yellow[target[1],target[0]] == 255.0:
# It's a yellow line detect
new_entity = [ name, color, last_time_seen, target ]
this_frame_entity_list.append( new_entity )
log_file.write( "%.3f %.3f FOUND %s %d %d\n" % ( frame_count/fps, frame_count, new_entity[0], new_entity[3][0], new_entity[3][1] ) )
filedrive = "C:/Users/525494/New_folder/000216/run_096/"
filename = "img"+str(name)
cv.SaveImage("yellow-line-image-test%s.png"%(new_entity[0]), camera_image)
# 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_count, 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 == "shadow":
image = fgmask
cv.PutText( image, "No Shadow", text_coord, text_font, text_color )
elif image_name == "white":
#image = difference
image = imgthreshold_white
cv.PutText( image, "White Threshold", text_coord, text_font, text_color )
elif image_name == "display":
#image = display_image
image = display_image
cv.PutText( image, "Targets (w/AABBs and contours)", text_coord, text_font, text_color )
cv.PutText( image, str(frame_t0), text_coord2, text_font, text_color )
cv.PutText( image, str(frame_count), text_coord3, 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 == "yellow":
# Do face detection
#detect_faces( camera_image, haar_cascade, mem_storage )
image = imgthreshold_yellow # Re-use camera image here
cv.PutText( image, "Yellow Threshold", text_coord, text_font, text_color )
#cv.ShowImage( "Target", image ) Commented out 3/19
# self.writer.write( image )
# out.write( image );
# cv.WriteFrame( self.writer, image );
# if self.writer:
# cv.WriteFrame( self.writer, image );
# video.write( 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 ):
if frame_count == 155740:
cv2.destroyWindow("Target")
# cv.ReleaseVideoWriter()
# self.writer.release()
# log_file.flush()
break
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 )
cv.InRangeS(hsv, (0, 140, 10), (170, 180, 60), thr)
moments = cv.Moments(cv.GetMat(thr, 1), 0)
area = cv.GetCentralMoment(moments, 0, 0)
cv.Line(frame, (80, 0), (80, 120), (0, 0, 255), 3, 8, 0)
if (area > 10000):
x = cv.GetSpatialMoment(moments, 1, 0) / area
y = cv.GetSpatialMoment(moments, 0, 1) / area
# overlay = cv.CreateImage(cv.GetSize(frame),8,3)
cv.Circle(frame, (int(x), int(y)), 2, (255, 255, 255), 20)
# cv.Add(frame,overlay,frame)
# cv.Merge(thr,None,None,None,frame)
if (int(x) < 80):
value = 80 - int(x)
cv.PutText(frame, "Left[" + str(value) + "]", (int(x), int(y)),
font, (255, 255, 0))
x_count += 1
if (x_count > 10):
print "Left Offset=", value
pub_string = "l" + chr(int(value))
moments = cv.Moments(tr, 0)
area = cv.GetCentralMoment(moments, 0, 0)
#there can be noise in the video so ignore objects with small areas
if (area > 100000):
#determine the x and y coordinates of the center of the object
#we are tracking by dividing the 1, 0 and 0, 1 moments by the area
x = cv.GetSpatialMoment(moments, 1, 0) / area
y = cv.GetSpatialMoment(moments, 0, 1) / area
print 'x: ' + str(x) + ' y: ' + str(y) + ' area: ' + str(area)
#create an overlay to mark the center of the tracked object
overlay = cv.CreateImage(cv.GetSize(F), 8, 3)
cv.Circle(overlay, (int(x), int(y)), 2, (255, 255, 255), 20)
cv.Circle(tr, (int(x), int(y)), 50, (255, 255, 255), -20)
cv.Add(F, overlay, F)
#add the thresholded image back to the img so we can see what was
#left after it was applied
cv.Merge(tr, None, None, None, F)
cv2.imshow('Varviotsing', f)
cv2.imshow("thresh", thresh)
if cv2.waitKey(25) == 27:
break
cv2.destroyAllWindows()
c.release()
def run(self):
# Initialize
# log_file_name = "tracker_output.log"
# log_file = file( log_file_name, 'a' )
print "hello"
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 = 3 # 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('E:\\Softwares\\opencv\\data\\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 = 5
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 )
image1 = display_image
detect_faces(camera_image, haar_cascade, mem_storage)
image2 = camera_image
cv.ShowImage("Target 1", image1)
cv.ShowImage("Target 2", image2)
# 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)
[rows, cols] = cv.GetSize(frame)
image = cv.CreateImage(cv.GetSize(frame), cv.IPL_DEPTH_8U, frame.nChannels)
cv.Copy(frame, image)
cv.ShowImage("camera", frame)
leftImage = cv.CreateImage((image.width, image.height), 8, 1)
cv.CvtColor(image, leftImage, cv.CV_BGR2GRAY)
frame2 = cv.QueryFrame(self.capture2)
print type(frame2)
image2 = cv.CreateImage(cv.GetSize(frame2), cv.IPL_DEPTH_8U, frame2.nChannels)
cv.Copy(frame2, image2)
cv.ShowImage("camera2", frame2)
rightImage = cv.CreateImage((image2.width, image2.height), 8, 1)
cv.CvtColor(image2, rightImage, cv.CV_BGR2GRAY)
disparity_left = cv.CreateMat(leftImage.height, leftImage.width, cv.CV_16S)
disparity_right = cv.CreateMat(rightImage.height, rightImage.width, cv.CV_16S)
# data structure initialization
state = cv.CreateStereoGCState(16, 2)
# print leftImage.width
# print leftImage.height
# print rightImage.width
# print rightImage.height
# running the graph-cut algorithm
cv.FindStereoCorrespondenceGC(leftImage, rightImage, disparity_left, disparity_right, state)
disp_left_visual = cv.CreateMat(leftImage.height, leftImage.width, cv.CV_8U)
cv.ConvertScale(disparity_left, disp_left_visual, -16);
# cv.Save("disparity.pgm", disp_left_visual); # save the map
#
# cutting the object farthest of a threshold (120)
cut(disp_left_visual, leftImage, 120)
# cv.NamedWindow('Disparity map', cv.CV_WINDOW_AUTOSIZE)
cv.ShowImage('Disparity map', disp_left_visual)
#
# minimum value for the intensity
maxValue = 0
maxPoint = None
# now for all the moving object centers get the average intensity value
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)
# cv.Avg(arr)
print center_point
print type(disp_left_visual)
print size(disp_left_visual)
print center_point
print "value " + str(cv.Get2D(disp_left_visual, center_point[1], center_point[0]))
value = cv.Get2D(disp_left_visual, center_point[1], center_point[0])[0] + cv.Get2D(disp_left_visual, center_point[1], center_point[0])[1] + cv.Get2D(disp_left_visual, center_point[1], center_point[0])[2]
if value > maxValue:
maxValue = value
maxPoint = center_point
print "min value is " + str(maxValue)
print " min point is " + str(maxPoint)
if maxPoint != None:
cv.Circle(display_image, maxPoint, 17, cv.CV_RGB(100, 100, 100), 1)
#distance = 1 / maxValue
# find if it is right or left or in the middle
if maxValue > 100:
middle = width / 2
if maxPoint[0] > middle + 20:
message = "look left"
elif maxPoint[0] < middle - 20:
message = "look right"
else:
message = "look middle"
print "message " + message
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)
if add_remove_pt:
# we have a point to add, so see if it is close to
# another one. If yes, don't use it
def ptptdist(p0, p1):
dx = p0[0] - p1[0]
dy = p0[1] - p1[1]
return dx**2 + dy**2
if min([ptptdist(pt, p) for p in features]) < 25:
# too close
add_remove_pt = 0
# draw the points as green circles
for the_point in features:
cv.Circle(image, (int(the_point[0]), int(the_point[1])), 3,
(0, 255, 0, 0), -1, 8, 0)
if add_remove_pt:
# we want to add a point
# refine this corner location and append it to 'features'
features += cv.FindCornerSubPix(
grey, [pt], (win_size, win_size), (-1, -1),
(cv.CV_TERMCRIT_ITER | cv.CV_TERMCRIT_EPS, 20, 0.03))
# we are no longer in "add_remove_pt" mode
add_remove_pt = False
# swapping
prev_grey, grey = grey, prev_grey
prev_pyramid, pyramid = pyramid, prev_pyramid
need_to_init = False
def update_mhi(img, dst, diff_threshold):
global last
global mhi
global storage
global mask
global orient
global segmask
timestamp = time.clock() / CLOCKS_PER_SEC # get current time in seconds
size = cv.GetSize(img) # get current frame size
idx1 = last
if not mhi or cv.GetSize(mhi) != size:
for i in range(N):
buf[i] = cv.CreateImage(size, cv.IPL_DEPTH_8U, 1)
cv.Zero(buf[i])
mhi = cv.CreateImage(size, cv.IPL_DEPTH_32F, 1)
cv.Zero(mhi) # clear MHI at the beginning
orient = cv.CreateImage(size, cv.IPL_DEPTH_32F, 1)
segmask = cv.CreateImage(size, cv.IPL_DEPTH_32F, 1)
mask = cv.CreateImage(size, cv.IPL_DEPTH_8U, 1)
cv.CvtColor(img, buf[last], cv.CV_BGR2GRAY) # convert frame to grayscale
idx2 = (last + 1) % N # index of (last - (N-1))th frame
last = idx2
silh = buf[idx2]
cv.AbsDiff(buf[idx1], buf[idx2], silh) # get difference between frames
cv.Threshold(silh, silh, diff_threshold, 1,
cv.CV_THRESH_BINARY) # and threshold it
cv.UpdateMotionHistory(silh, mhi, timestamp, MHI_DURATION) # update MHI
cv.CvtScale(mhi, mask, 255. / MHI_DURATION,
(MHI_DURATION - timestamp) * 255. / MHI_DURATION)
cv.Zero(dst)
cv.Merge(mask, None, None, None, dst)
cv.CalcMotionGradient(mhi, mask, orient, MAX_TIME_DELTA, MIN_TIME_DELTA, 3)
if not storage:
storage = cv.CreateMemStorage(0)
seq = cv.SegmentMotion(mhi, segmask, storage, timestamp, MAX_TIME_DELTA)
for (area, value, comp_rect) in seq:
if comp_rect[2] + comp_rect[3] > 100: # reject very small components
color = cv.CV_RGB(255, 0, 0)
silh_roi = cv.GetSubRect(silh, comp_rect)
mhi_roi = cv.GetSubRect(mhi, comp_rect)
orient_roi = cv.GetSubRect(orient, comp_rect)
mask_roi = cv.GetSubRect(mask, comp_rect)
angle = 360 - cv.CalcGlobalOrientation(
orient_roi, mask_roi, mhi_roi, timestamp, MHI_DURATION)
count = cv.Norm(
silh_roi, None, cv.CV_L1,
None) # calculate number of points within silhouette ROI
if count < (comp_rect[2] * comp_rect[3] * 0.05):
continue
magnitude = 30.
center = ((comp_rect[0] + comp_rect[2] / 2),
(comp_rect[1] + comp_rect[3] / 2))
cv.Circle(dst, center, cv.Round(magnitude * 1.2), color, 3,
cv.CV_AA, 0)
cv.Line(
dst, center,
(cv.Round(center[0] + magnitude * cos(angle * cv.CV_PI / 180)),
cv.Round(center[1] -
magnitude * sin(angle * cv.CV_PI / 180))), color, 3,
cv.CV_AA, 0)
nb = abs(int(prev_points[i][0]) - int(curr_points[i][0])) + abs(
int(prev_points[i][1]) - int(curr_points[i][1]))
if status[i] and nb > 2:
prev_points[k] = prev_points[i]
curr_points[k] = curr_points[i]
k += 1
prev_points = prev_points[:k]
curr_points = curr_points[:k]
#At the end only interesting points are kept
#Draw all the previously kept lines otherwise they would be lost the next frame
for (pt1, pt2) in lines:
cv.Line(frame, pt1, pt2, (255, 255, 255))
#Draw the lines between each points at t-1 and t
for prevpoint, point in zip(prev_points, curr_points):
prevpoint = (int(prevpoint[0]), int(prevpoint[1]))
cv.Circle(frame, prevpoint, 15, 0)
point = (int(point[0]), int(point[1]))
cv.Circle(frame, point, 3, 255)
cv.Line(frame, prevpoint, point, (255, 255, 255))
lines.append(
(prevpoint, point)) #Append current lines to the lines list
cv.Copy(gray, prev_gray) #Put the current frame prev_gray
prev_points = curr_points
cv.ShowImage("The Video", frame)
#cv.WriteFrame(writer, frame)
cv.WaitKey(wait)