def doFaceTask(self, _task):
# start = time.time()
# TODO: Get timer
data = _task.depackage()
bbs, pts, frame, frame_info = data['bbs'], data['pts'], data[
'frame'], data['frame_info']
nrof_faces = len(bbs)
# timer.preprocess_start()
faces = []
preprocessed_images = []
for i in range(nrof_faces):
display_face, padded_bb_str = CropperUtils.crop_display_face(
frame, bbs[i][:-1])
face = detection.FaceInfo(bbs[i][:-1], bbs[i][-1], frame_info,
display_face, padded_bb_str, pts[:, i])
cropped_face = CropperUtils.crop_face(frame, bbs[i][:-1])
preprocessed = self.preprocessor.process(cropped_face)
preprocessed_images.append(preprocessed)
faces.append(face)
preprocessed_images = np.array(preprocessed_images)
# timer.preprocess_done()
_task = task.Task(task.Task.Face)
_task.package(faces=faces,
images=preprocessed_images,
frame=frame,
frame_info=frame_info)
self.putResult(_task)
def register_function(detector, preprocessor, face_extractor, rabbit_mq):
'''
dia dia
'''
# Doc queue
msg_list = rabbit_mq.receive_once('{}-register'.format(Config.DEMO_FOR))
if msg_list is None:
return False
person_id = msg_list[0] # .lower()
file_url_msg = msg_list[1]
list_of_trackers = TrackersList()
frame_counter = 0
saved_frames = save_frames(file_url_msg)
if saved_frames == []:
return False
print('Detecting Faces and Extracting Features ...')
saved_frames.reverse()
for frame in saved_frames:
list_of_trackers.update_dlib_trackers(frame)
origin_bbs, points = detector.detect_face(frame)
if origin_bbs is None:
break
for i, origin_bb in enumerate(origin_bbs):
display_face, padded_bbox = CropperUtils.crop_display_face(
frame, origin_bb)
cropped_face = CropperUtils.crop_face(frame, origin_bb)
# Calculate embedding
preprocessed_image = preprocessor.process(cropped_face)
emb_array = face_extractor.extract_features(preprocessed_image)
matched_fid = list_of_trackers.matching_face_with_trackers(
frame, frame_counter, origin_bb, emb_array)
# Update list_of_trackers
list_of_trackers.update_trackers_list(matched_fid,
time.time(),
origin_bb,
display_face,
emb_array,
-1,
'register',
frame_counter,
padded_bbox,
None,
rabbit_mq,
mode='register')
frame_counter += 1
if frame_counter > 601:
break
if list_of_trackers.trackers == {}:
return False
# extract images
extract_images(list_of_trackers.trackers, person_id)
return True
def doFaceTask(self, _task):
data = _task.depackage()
task_name = data['type']
if task_name != Config.Worker.TASK_TRACKER:
return
tracker = data['tracker']
if tracker.face_id == Config.Track.INIT_FACE_ID or \
tracker.face_id == Config.Track.BAD_TRACK:
tracker.assign_face_id('Anno')
for tracker_element in tracker.elements:
face_image = tracker_element.face_image
cropped_image = CropperUtils.reverse_display_face(
tracker_element.face_image, tracker_element.str_padded_bbox)
bbox_confident = tracker_element.bbox_confident
landmark = tracker_element.landmarks
image_id = '{}_{}'.format(tracker.track_id,
tracker_element.str_info())
image_name = image_id + '.jpg'
image_pkl = image_id + '.pkl'
dataset_pkl_path = os.path.join(self.dataset_dir, image_pkl)
annotation_image_path = os.path.join(self.annotation_dir,
image_name)
PickleUtils.save_pickle(dataset_pkl_path,
value=(cropped_image,
tracker_element.embedding,
bbox_confident, landmark))
misc.imsave(annotation_image_path, face_image)
logger.debug('Save image: %s' % image_id)
def doFaceTask(self, _task):
# detect all at once, no cuda memory may occur
data = _task.depackage()
bbs, scores, frame, frame_info = data['bbs'], data['scores'], data[
'frame'], data['frame_info']
nrof_faces = len(bbs)
# timer.preprocess_start()
faces = []
for i in range(nrof_faces):
display_face, padded_bb_str = CropperUtils.crop_display_face(
frame, np.asarray(bbs[i]))
face = detection.PedestrianInfo(np.asarray(bbs[i]), frame_info,
display_face, padded_bb_str,
scores[i])
faces.append(face)
# logger.info("Extract: %s, #Faces: %s" % (frame_info, len(faces)))
# timer.extract_start()
embs = self.encoder(frame, bbs_to_tlwhs(faces))
face_infos = []
for i, face in enumerate(faces):
face.embedding = embs[i]
face_infos.append(face)
_task = task.Task(task.Task.Face)
_task.package(faces=face_infos)
self.putResult(_task)
def doFaceTask(self, _task):
start = time.time()
data = _task.depackage()
task_name = data['type']
if task_name != Config.Worker.TASK_EXTRACTION:
return
tracker = data['tracker']
nrof_elements = len(tracker.elements)
# here we do the batch embs extracting
_interval = Config.Track.NUM_IMAGE_PER_EXTRACT
for i in range(0, nrof_elements, _interval):
_interval = min(nrof_elements - i, _interval)
preprocessed_images = []
for j in range(i, i + _interval):
face_image = CropperUtils.reverse_display_face(
tracker.elements[j].face_image,
tracker.elements[j].str_padded_bbox)
preprocessed_image = self.preprocessor.process(face_image)
preprocessed_images.append(preprocessed_image)
embeddings_array, _ = self.extractor.extract_features_all_at_once(
preprocessed_images)
tracker.update_embeddings(embeddings_array, i, _interval)
_task = task.Task(task.Task.Face)
_task.package(tracker=tracker)
self.putResult(_task)
print(self.name, time.time() - start)
def doFaceTask(self, _task):
# start = time.time()
# TODO: Get timer
data = _task.depackage()
bbs, pts, frame, frame_info = data['bbs'], data['pts'], data[
'frame'], data['frame_info']
nrof_faces = len(bbs)
# timer.preprocess_start()
faces = []
preprocessed_face_images = []
preprocessed_coeff_images = []
for i in range(nrof_faces):
display_face, padded_bb_str = CropperUtils.crop_display_face(
frame, bbs[i][:-1])
face = detection.FaceInfo(bbs[i][:-1], bbs[i][-1], frame_info,
display_face, padded_bb_str, pts[:, i])
preprocessed_face = self.face_preprocessor.process(
frame, pts[:, i], self.aligner, Config.Align.IMAGE_SIZE,
self.prewhitening)
preprocessed_face_images.append(preprocessed_face)
faces.append(face)
if self.use_coeff_filter:
cropped_face = CropperUtils.crop_face(frame, bbs[i][:-1])
preprocessed_coeff = self.coeff_preprocessor.process(
cropped_face)
preprocessed_coeff_images.append(preprocessed_coeff)
preprocessed_face_images = np.array(preprocessed_face_images)
preprocessed_coeff_images = np.array(preprocessed_coeff_images)
# timer.preprocess_done()
_task = task.Task(task.Task.Face)
_task.package(faces=faces,
images=preprocessed_face_images,
coeff_images=preprocessed_coeff_images,
frame=frame,
frame_info=frame_info)
self.putResult(_task)
def doFaceTask(self, _task):
data = _task.depackage()
bbs, pts, frame, frame_info = data['bbs'], data['pts'], data[
'frame'], data['frame_info']
bbox = self.get_biggest_face(bbs)
if bbox.any():
cropped_face = CropperUtils.crop_face(frame, bbox[:-1])
preprocessed = self.preprocessor.process(cropped_face)
_task = task.Task(task.Task.Face)
_task.package(images=preprocessed, frame_info=frame_info)
self.putResult(_task)
def threading_register_function(detector, face_extractor, register_queue,
matcher):
'''
dia dia
'''
# Doc queue
preprocessor = Preprocessor()
while True:
try:
register_msg = register_queue.get(False)
except multiprocessing.queues.Empty:
register_msg = None
if register_msg:
person_id = register_msg[0] # .lower()
file_url_msg = register_msg[1]
list_of_trackers = TrackersList()
frame_counter = 0
saved_frames = save_frames(file_url_msg)
if saved_frames == []:
continue
print('Detecting Faces and Extracting Features ...')
saved_frames.reverse()
for frame in saved_frames:
list_of_trackers.update_dlib_trackers(frame)
origin_bbs, points = detector.detect_face(frame)
if origin_bbs is None:
break
for i, origin_bb in enumerate(origin_bbs):
display_face, padded_bbox = CropperUtils.crop_display_face(
frame, origin_bb)
cropped_face = CropperUtils.crop_face(frame, origin_bb)
# Calculate embedding
preprocessed_image = preprocessor.process(cropped_face)
emb_array = face_extractor.extract_features(
preprocessed_image)
matched_fid = list_of_trackers.matching_face_with_trackers(
frame, frame_counter, origin_bb, emb_array)
# Update list_of_trackers
list_of_trackers.update_trackers_list(matched_fid,
time.time(),
origin_bb,
display_face,
emb_array,
-1,
'register',
frame_counter,
padded_bbox,
None,
rabbit_mq,
mode='register')
frame_counter += 1
if frame_counter > 601:
break
if list_of_trackers.trackers == {}:
return False
# extract images
extract_images(list_of_trackers.trackers, person_id)
matcher.update(force=True)
with open('register_log.txt', 'a') as f:
f.write(str(len(list_of_trackers.trackers)) + person_id + '\n')