def run_ntimes_oneblob(self):
"""
Run the BlobFinder on one blob
"""
self.background = background()
self.mask = mask(self.background)
blob = randomblob(self.background)[0]
self.bfinder = BlobFinder(self.mask)
# init background
for _ in range(10):
blob = randomblob(self.background)[0]
self.bfinder.run(blob)
self.blobs_center = list()
self.blobs_found = list()
for frame_i in range(10):
blob, blob_center, _, _ = \
randomblob(self.background)
self.bfinder.run(blob)
self.blobs_center.append(blob_center)
self.blobs_found.append(self.bfinder.filtered_contours)
self.blob = blob
# Create image for display scale = 0.4 refresh_time = 0.5 blob_brightness = [20, 30, 150, 254] max_nb_images = 1 # Bfinder parameters args = dict() # loop over the frames of the video t_start = time.time() # mask background = btgen.background() mask = btgen.mask(background) # Create a bfinder tracker bfinder = BlobFinder(mask) bfinder.erode_iter = 2 bfinder.dilate_iter = 2 bfinder.area_lim = [0, 10000] bfinder.roundness_lim = [0, 1] bfinder.background_init = 60 bfinder.threshold = 10 bfinder.gaussian_blur = 1 bfinder.skip_filter_contours = False # Parameter for croping xmargin = [0, 0] ymargin = [0, 0] # Build up an expected histogram ninitframes = 50 bin_edges = np.arange(1, 255)
args = parser_tracker().parse_args()
template_frame = args.images
state = 'runforward'
config_yaml = args.config
scale = args.scale
# Parameter for croping
xmargin = [0, 0]
ymargin = [0, 0]
if template_frame is None:
# mask
background = btgen.background()
mask = btgen.mask(background)
blob_brightness = [20, 30, 150, 254]
bfinder = BlobFinder(mask)
else:
filelist = sorted(glob.glob(template_frame))
bfinder = BlobFinder(None, fgbg=cv2.createBackgroundSubtractorKNN())
# Create a bfinder tracker
config = load_config(config_yaml)
update_config_bfinder(bfinder, config['bfinder'])
bfinder.skip_filter_contours = False
# init background
maxframe = len(filelist)
print('INIT Background')
if template_frame is not None:
bfinder.background_learning_rate = -1
for frame_i in range(bfinder.background_init,0,-1):
time.sleep(0.25)
# Load image for file list if video is None
elif args.get("video", None) is None:
argcam= args["folder"]
# otherwise, we are reading from a video file
else:
argcam= args["video"]
if args["tra_file"] is None:
if args["folder"] is None:
raise NameError('target trajectory file is not present')
else:
folder_path = os.path.dirname(args["folder"])
args["tra_file"] = os.path.join(folder_path, 'trajectory.tra')
display=False
bbee = BlobFinder(mask, None)
bbee.erode_iter = 2
bbee.dilate_iter = 3
bbee.threshold = 128
bbee.gaussian_blur = 3
bbee.skip_filter_contours = True
#Parameters markers:
max_area = 40
params = [80,300]
gaussian_blur=5
# Create image for display
scale = 0.4
refresh_time = 0.5
nframe_bg = 1000
time.sleep(0.25)
# Load image for file list if video is None
elif args.get("video", None) is None:
argcam = args["folder"]
# otherwise, we are reading from a video file
else:
argcam = args["video"]
if args["tra_file"] is None:
if args["folder"] is None:
raise NameError('target trajectory file is not present')
else:
folder_path = os.path.dirname(args["folder"])
args["tra_file"] = os.path.join(folder_path, 'trajectory_v2.tra')
bmarker = BlobFinder(mask, None)
bmarker.erode_iter = 1
bmarker.dilate_iter = 1
bmarker.area_lim = [0, 2000]
bmarker.roundness_lim = [0, 1]
bmarker.threshold = args["threshold"]
bmarker.gaussian_blur = 1
bmarker.skip_filter_contours = True
# Create image for display
scale = 0.4
refresh_time = 0.5
nframe_bg = 100
camera = cv2.VideoCapture(argcam)
background = get_background(camera, nframe_bg)
class TestBlobFinder(unittest.TestCase):
def __init__(self, *args, **kwargs):
super(TestBlobFinder, self).__init__(*args, **kwargs)
self.run_ntimes_oneblob()
def run_ntimes_oneblob(self):
"""
Run the BlobFinder on one blob
"""
self.background = background()
self.mask = mask(self.background)
blob = randomblob(self.background)[0]
self.bfinder = BlobFinder(self.mask)
# init background
for _ in range(10):
blob = randomblob(self.background)[0]
self.bfinder.run(blob)
self.blobs_center = list()
self.blobs_found = list()
for frame_i in range(10):
blob, blob_center, _, _ = \
randomblob(self.background)
self.bfinder.run(blob)
self.blobs_center.append(blob_center)
self.blobs_found.append(self.bfinder.filtered_contours)
self.blob = blob
def test_setget_image(self):
myim = self.bfinder.original_image
self.assertTrue(np.allclose(myim, self.blob))
def test_masked(self):
myim = self.bfinder.masked_image
testimage = cv2.bitwise_and(self.blob, self.blob, mask=self.mask)
self.assertTrue(np.allclose(myim, testimage))
def test_segmented(self):
myim = self.bfinder.segmented_image
self.assertTrue(np.allclose(np.unique(myim), [0, 255]))
def test_oneblob_numbers(self):
condition = True
for frame_i in range(len(self.blobs_center)):
contours = self.blobs_found[frame_i]
if len(contours) > 1:
print('Too many blobs detected')
condition = False
continue
elif len(contours) < 1:
print('Too few blobs detected')
condition = False
continue
self.assertTrue(condition)
def test_oneblob_positions(self):
condition = True
for frame_i in range(len(self.blobs_center)):
contours = self.blobs_found[frame_i]
contours = contours[0]
px_error = np.sqrt(
np.sum(contours.center - self.blobs_center[frame_i])**2)
if px_error > 1:
print('Pixel error too large : {}'.format(px_error))
condition = False
self.assertTrue(condition)