def by_dataset(self, vid_path='./data/freeman1/'):
assert os.path.exists(vid_path)
gt_boxes = BoundingBox.read_vid_gt(vid_path)
curr_bbox = None
self.stopwatch.start('total')
_logger.info('---- start dataset l=%d' % (len(gt_boxes)))
for idx, gt_box in enumerate(gt_boxes):
img = commons.imread(
os.path.join(vid_path, 'img', '%04d.jpg' % (idx + 1)))
self.imgwh = Coordinate.get_imgwh(img)
if idx == 0:
# initialization : initial fine-tuning
self.initial_finetune(img, gt_box)
curr_bbox = gt_box
# tracking
predicted_box = self.tracking(img, curr_bbox)
self.show(img, gt_box=gt_box, predicted_box=predicted_box)
# cv2.imwrite('/Users/ildoonet/Downloads/aaa/%d.jpg' % self.iteration, img)
curr_bbox = predicted_box
self.stopwatch.stop('total')
_logger.info('----')
_logger.info(self.stopwatch)
_logger.info('%.3f FPS' %
(len(gt_boxes) / self.stopwatch.get_elapsed('total')))
def redetection_by_sampling(self, prev_box, img):
"""
default redetection method
"""
imgwh = Coordinate.get_imgwh(img)
translation_f = min(1.5, 0.6 * 1.15**self.failed_cnt)
candidates = prev_box.gen_noise_samples(imgwh, 'gaussian', ADNetConf.g()['redetection']['samples'],
gaussian_translation_f=translation_f)
scores = []
for c_batch in commons.chunker(candidates, ADNetRunner.MAX_BATCHSIZE):
samples = [commons.extract_region(img, box) for box in c_batch]
classes = self.persistent_sess.run(
self.adnet.layer_scores,
feed_dict={
self.adnet.input_tensor: samples,
self.adnet.action_history_tensor: [commons.onehot_flatten(self.action_histories_old)]*len(c_batch),
self.tensor_is_training: False
}
)
scores.extend([x[1] for x in classes])
top5_idx = [i[0] for i in sorted(enumerate(scores), reverse=True, key=lambda x: x[1])][:5]
mean_score = sum([scores[x] for x in top5_idx]) / 5.0
if mean_score >= self.latest_score:
mean_box = candidates[0]
for i in range(1, 5):
mean_box += candidates[i]
return mean_box / 5.0, mean_score
return None, 0.0
def run_tracker(self, decoded_img_arr, BBox_assorted_dict,
manually_corrected):
# Convert into Bounding box object
# Bounding box object will have xmin, ymin, width and height
# Derive width and height from the 4-coordinates
# gt_boxes must have list of Bunding box objects
gt_boxes_dict = self.accumulate_ground_truth_boxes(BBox_assorted_dict)
# initialization : initial fine-tuning
# Multiple trackid and BBox association
multi_track_bbox = {}
# AdNetTracker.RUN_COUNTER = 0
for trackid, gt_box in gt_boxes_dict.items():
st_time = datetime.now()
print("trackid>>", trackid)
curr_bbox = gt_box
self.imgwh = Coordinate.get_imgwh(decoded_img_arr)
print("self.imgwh >>", self.imgwh)
if AdNetTracker.RUN_COUNTER == 0 or manually_corrected:
self.initial_finetune(decoded_img_arr, gt_box)
AdNetTracker.RUN_COUNTER += 1
# predicted_box = self.tracking(decoded_img_arr, curr_bbox, trackid)
# print("predicted_box>>", predicted_box, predicted_box.xy.x, predicted_box.xy.y)
print("previous box::", curr_bbox)
# predicted_box_dict contains key as track ID and value is BBox object
predicted_box_dict = self.tracking(decoded_img_arr, curr_bbox,
trackid)
print("predicted_box_dict::", predicted_box_dict)
ed_time = datetime.now()
duration = ed_time - st_time
print("tracking done in...", duration)
multi_track_bbox.update(predicted_box_dict)
# print("multi_track_bbox>>", multi_track_bbox)
return multi_track_bbox
def by_dataset(self, vid_path='./data/LT52/'):
"""
'./data/BlurCar2/'
LT52
"""
assert os.path.exists(vid_path)
id=0
gt_boxes = BoundingBox.read_vid_gt(vid_path,id)
print("gt_boxes>>", gt_boxes)
curr_bbox = None
self.stopwatch.start('total')
_logger.info('---- start dataset l=%d' % (len(gt_boxes)))
for idx, gt_box in enumerate(gt_boxes):
print('\nimage number : %04d.jpg' %(idx+1))
print('vid path is %s' %vid_path)
if idx!=1:
img = commons.imread(os.path.join(vid_path, 'img', '%04d.jpeg' % (idx + 1)))
self.imgwh = Coordinate.get_imgwh(img)
if idx == 0:
# initialization : initial fine-tuning
# print("gt_box >", gt_box)
self.initial_finetune(img, gt_box)
curr_bbox = gt_box
# tracking
# print("curr_bbox>>", curr_bbox, idx)
predicted_box = self.tracking(img, curr_bbox,idx)
# print("predicted_box>>", predicted_box, predicted_box.xy.x, predicted_box.xy.y)
self.show(img, idx,gt_box=gt_box, predicted_box=predicted_box)
# cv2.imwrite('/Users/ildoonet/Downloads/aaa/%d.jpg' % self.iteration, img)
curr_bbox = predicted_box
self.stopwatch.stop('total')
_logger.info('----')
_logger.info(self.stopwatch)
_logger.info('%.3f FPS' % (len(gt_boxes) / self.stopwatch.get_elapsed('total')))
def tracking(self, img, curr_bbox):
self.iteration += 1
is_tracked = True
boxes = []
self.latest_score = -1
self.stopwatch.start('tracking.do_action')
for track_i in range(ADNetConf.get()['predict']['num_action']):
patch = commons.extract_region(img, curr_bbox)
# forward with image & action history
actions, classes = self.persistent_sess.run(
[self.adnet.layer_actions, self.adnet.layer_scores],
feed_dict={
self.adnet.input_tensor: [patch],
self.adnet.action_history_tensor:
[commons.onehot_flatten(self.action_histories)],
self.tensor_is_training:
False
})
latest_score = classes[0][1]
if latest_score < ADNetConf.g()['predict']['thresh_fail']:
is_tracked = False
self.action_histories_old = np.copy(self.action_histories)
self.action_histories = np.insert(self.action_histories, 0,
12)[:-1]
break
else:
self.failed_cnt = 0
self.latest_score = latest_score
# move box
action_idx = np.argmax(actions[0])
self.action_histories = np.insert(self.action_histories, 0,
action_idx)[:-1]
prev_bbox = curr_bbox
curr_bbox = curr_bbox.do_action(self.imgwh, action_idx)
if action_idx != ADNetwork.ACTION_IDX_STOP:
if prev_bbox == curr_bbox:
print('action idx', action_idx)
print(prev_bbox)
print(curr_bbox)
raise Exception('box not moved.')
# oscillation check
if action_idx != ADNetwork.ACTION_IDX_STOP and curr_bbox in boxes:
action_idx = ADNetwork.ACTION_IDX_STOP
if action_idx == ADNetwork.ACTION_IDX_STOP:
break
boxes.append(curr_bbox)
self.stopwatch.stop('tracking.do_action')
# redetection when tracking failed
new_score = 0.0
if not is_tracked:
self.failed_cnt += 1
# run redetection callback function
new_box, new_score = self.callback_redetection(curr_bbox, img)
if new_box is not None:
curr_bbox = new_box
patch = commons.extract_region(img, curr_bbox)
_logger.debug('redetection success=%s' %
(str(new_box is not None)))
# save samples
if is_tracked or new_score > ADNetConf.g(
)['predict']['thresh_success']:
self.stopwatch.start('tracking.save_samples.roi')
imgwh = Coordinate.get_imgwh(img)
pos_num, neg_num = ADNetConf.g(
)['finetune']['pos_num'], ADNetConf.g()['finetune']['neg_num']
pos_boxes, neg_boxes = curr_bbox.get_posneg_samples(
imgwh,
pos_num,
neg_num,
use_whole=False,
pos_thresh=ADNetConf.g()['finetune']['pos_thresh'],
neg_thresh=ADNetConf.g()['finetune']['neg_thresh'],
uniform_translation_f=2,
uniform_scale_f=5)
self.stopwatch.stop('tracking.save_samples.roi')
self.stopwatch.start('tracking.save_samples.feat')
feats = self._get_features([
commons.extract_region(img, box)
for i, box in enumerate(pos_boxes)
])
for box, feat in zip(pos_boxes, feats):
box.feat = feat
feats = self._get_features([
commons.extract_region(img, box)
for i, box in enumerate(neg_boxes)
])
for box, feat in zip(neg_boxes, feats):
box.feat = feat
pos_lb_action = BoundingBox.get_action_labels(pos_boxes, curr_bbox)
self.histories.append((pos_boxes, neg_boxes, pos_lb_action,
np.copy(img), self.iteration))
# clear old ones
self.histories = self.histories[-ADNetConf.g(
)['finetune']['long_term']:]
self.stopwatch.stop('tracking.save_samples.feat')
# online finetune
if self.iteration % ADNetConf.g(
)['finetune']['interval'] == 0 or is_tracked is False:
img_pos, img_neg = [], []
pos_boxes, neg_boxes, pos_lb_action = [], [], []
pos_term = 'long_term' if is_tracked else 'short_term'
for i in range(ADNetConf.g()['finetune'][pos_term]):
if i >= len(self.histories):
break
pos_boxes.extend(self.histories[-(i + 1)][0])
pos_lb_action.extend(self.histories[-(i + 1)][2])
img_pos.extend([self.histories[-(i + 1)][3]] *
len(self.histories[-(i + 1)][0]))
for i in range(ADNetConf.g()['finetune']['short_term']):
if i >= len(self.histories):
break
neg_boxes.extend(self.histories[-(i + 1)][1])
img_neg.extend([self.histories[-(i + 1)][3]] *
len(self.histories[-(i + 1)][1]))
self.stopwatch.start('tracking.online_finetune')
self._finetune_fc((img_pos, img_neg), pos_boxes, neg_boxes,
pos_lb_action,
ADNetConf.get()['finetune']['learning_rate'],
ADNetConf.get()['finetune']['iter'])
_logger.debug('finetuned')
self.stopwatch.stop('tracking.online_finetune')
visualizer.image('patch', patch)
# cv2.imshow('patch', patch)
return curr_bbox