def extractInfo(self):
# times = []
try:
while not self.exit:
try:
frame = self.frame_queue.get(block=True, timeout=1)
except queue.Empty:
print("Frame queue empty")
continue
# 1 ms per loop
# TODO: check that this conversion is not needed
# frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
if self.debug:
self.out_queue.put(item=frame, block=False)
else:
if self.frame_num % SAVE_EVERY == 0:
cv2.imwrite(
"debug/{}_{}.jpg".format(experiment_time,
self.frame_num), frame)
try:
# 10 ms per loop
# start_time = time.time()
turn_percent, centroids = processImage(frame)
# times.append(time.time() - start_time)
self.out_queue.put(item=(turn_percent, centroids),
block=False)
except Exception as e:
print("Exception in RBGAnalyser processing image: {}".
format(e))
self.frame_num += 1
except Exception as e:
print("Exception in RBGAnalyser after loop: {}".format(e))
def extractInfo(self):
try:
while not self.exit:
try:
frame = self.frame_queue.get(block=True, timeout=1)
except queue.Empty:
print("Queue empty")
continue
frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
if self.debug:
self.out_queue.put(item=frame, block=False)
else:
if self.frame_num % SAVE_EVERY == 0:
cv2.imwrite("debug/{}_{}.jpg".format(experiment_time, self.frame_num), frame)
pass
try:
turn_percent, centroids = processImage(frame)
self.out_queue.put(item=(turn_percent, centroids), block=False)
except Exception as e:
print("Exception in RBGAnalyser processing image: {}".format(e))
self.frame_num += 1
except Exception as e:
print("Exception in RBGAnalyser after loop: {}".format(e))
j = 0
should_exit = False
for idx, name in enumerate(images):
if should_exit:
break
img = cv2.imread('{}/{}'.format(input_folder, name))
print(name)
original_img = img.copy()
for i, r in enumerate(REGIONS):
# img will be modified by processImage()
img = original_img.copy()
margin_left, margin_top, _, _ = r
im_cropped = original_img[int(r[1]):int(r[1] + r[3]), int(r[0]):int(r[0] + r[2])]
centroids, errors, exit_loop = processImage(img, debug=True, regions=[r], interactive=True)
if not all(errors):
# Save the labeled image (and store the label in the name)
x, y = centroids.flatten()
cx, cy = x - margin_left, y - margin_top
output_name = '{}'.format(j)
idx = '{}_r{}'.format(name, i)
infos_dict['images'][idx]['input_image'] = name
infos_dict['images'][idx]['label'] = [cx, cy]
infos_dict['images'][idx]['region'] = list(r)
infos_dict['images'][idx]['output_name'] = output_name
cv2.imwrite('{}/{}.jpg'.format(output_folder, output_name), im_cropped)
# Update infos
with open('{}/infos.pkl'.format(output_folder), 'wb') as f:
# protocol=2 for python 2 compatibility
default=1,
type=int)
args = parser.parse_args()
if args.input_image != "" or args.folder != "":
imgs = [args.input_image]
if args.folder != "":
imgs = [
args.folder + '/' + im for im in os.listdir(args.folder)
if im.split('.')[-1] in images
]
current_idx = 0
while True:
img = cv2.imread(imgs[current_idx])
# r = [margin_left, margin_top, width, height]
regions = None
if args.regions == 0:
regions = [[0, 0, img.shape[1], img.shape[0]]]
processImage(img, debug=True, regions=regions)
# Retrieve pressed key
key = cv2.waitKey(0) & 0xff
if key in EXIT_KEYS:
cv2.destroyAllWindows()
exit()
elif key in [LEFT_KEY, RIGHT_KEY]:
current_idx += 1 if key == RIGHT_KEY else -1
current_idx = np.clip(current_idx, 0, len(imgs) - 1)
from opencv.image_processing import processImage
N_ITER = 5000
parser = argparse.ArgumentParser(
description='Benchmark line detection algorithm')
parser.add_argument('-i',
'--input_image',
help='Input Image',
default="",
type=str,
required=True)
args = parser.parse_args()
image = cv2.imread(args.input_image)
time_deltas = []
for i in range(N_ITER):
start_time = time.time()
turn_percent, centroids = processImage(image,
debug=False,
regions=None,
interactive=False)
time_deltas.append(time.time() - start_time)
# print(centroids)
time_deltas = np.array(time_deltas)
print("Total time: {:.6f}s".format(time_deltas.sum()))
print("Mean time: {:.6f}s".format(time_deltas.mean()))
print("Std time: {:.6f}s".format(time_deltas.std()))
print("Median time: {:.6f}s".format(np.median(time_deltas)))