-
Notifications
You must be signed in to change notification settings - Fork 0
/
test_otb.py
executable file
·245 lines (230 loc) · 11.4 KB
/
test_otb.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
# Copyright (c) SenseTime. All Rights Reserved.
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from __future__ import unicode_literals
import os
import sys
env_path = os.path.join(os.path.dirname(__file__), '..')
print(env_path)
if env_path not in sys.path:
sys.path.append(env_path)
import argparse
import cv2
import torch
import numpy as np
from pysot_toolkit.bbox import get_axis_aligned_bbox
from pysot_toolkit.toolkit.datasets import DatasetFactory
from pysot_toolkit.toolkit.utils.region import vot_overlap, vot_float2str
from pysot_toolkit.trackers.tracker import Tracker
from pysot_toolkit.trackers.net_wrappers import NetWithBackbone
parser = argparse.ArgumentParser(description='transt_m tracking')
parser.add_argument('--dataset', type=str,
help='datasets')
parser.add_argument('--video', default='', type=str,
help='eval one special video')
parser.add_argument('--vis', action='store_true',
help='whether visualzie result')
parser.add_argument('--name', default='', type=str,
help='name of results')
parser.add_argument('--mask', action='store_true',
help='whether predict mask')
args = parser.parse_args()
torch.set_num_threads(1)
def main():
# load config
dataset_root = '/home/cx/cx2/OTB100' # path to otb
net_path = '/home/cx/cx1/TransT_experiments/TransT-M/models/transtm.pth' # path to transtm model
# create model
net = NetWithBackbone(net_path=net_path, use_gpu=True)
tracker = Tracker(name='transt-m', net=net, mask=args.mask,
window_penalty=0.54, penalty_k=0,
update_threshold=0.80, exemplar_size=128, instance_size=256)
# create dataset
dataset = DatasetFactory.create_dataset(name=args.dataset,
dataset_root=dataset_root,
load_img=False)
model_name = tracker.name
total_lost = 0
if args.dataset in ['VOT2016', 'VOT2018', 'VOT2019']:
# restart tracking
for v_idx, video in enumerate(dataset):
if args.video != '':
# test one special video
if video.name != args.video:
continue
frame_counter = 0
lost_number = 0
toc = 0
pred_bboxes = []
for idx, (img, gt_bbox) in enumerate(video):
# convert bgr to rgb
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
if len(gt_bbox) == 4:
gt_bbox = [gt_bbox[0], gt_bbox[1],
gt_bbox[0], gt_bbox[1] + gt_bbox[3] - 1,
gt_bbox[0] + gt_bbox[2] - 1, gt_bbox[1] + gt_bbox[3] - 1,
gt_bbox[0] + gt_bbox[2] - 1, gt_bbox[1]]
tic = cv2.getTickCount()
if idx == frame_counter:
cx, cy, w, h = get_axis_aligned_bbox(np.array(gt_bbox))
gt_bbox_ = [cx - w / 2, cy - h / 2, w, h]
init_info = {'init_bbox': gt_bbox_}
tracker.initialize(img, init_info)
pred_bbox = gt_bbox_
pred_bboxes.append(1)
elif idx > frame_counter:
info = {}
outputs = tracker.track(img, info)
pred_bbox = outputs['target_bbox']
if args.mask:
pred_mask = outputs['target_mask']
overlap = vot_overlap(pred_bbox, gt_bbox, (img.shape[1], img.shape[0]))
if overlap > 0:
# not lost
pred_bboxes.append(pred_bbox)
else:
# lost object
pred_bboxes.append(2)
frame_counter = idx + 5 # skip 5 frames
lost_number += 1
else:
pred_bboxes.append(0)
toc += cv2.getTickCount() - tic
if idx == 0:
cv2.destroyAllWindows()
if args.vis and idx > frame_counter:
img = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
cv2.polylines(img, [np.array(gt_bbox, np.int).reshape((-1, 1, 2))],
True, (0, 255, 0), 3)
# if args.mask:
# cv2.polylines(img, [np.array(pred_bbox, np.int).reshape((-1, 1, 2))],
# True, (0, 255, 255), 3)
bbox = list(map(int, pred_bbox))
cv2.rectangle(img, (bbox[0], bbox[1]),
(bbox[0] + bbox[2], bbox[1] + bbox[3]), (0, 255, 255), 3)
cv2.putText(img, str(idx), (40, 40), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 255), 2)
cv2.putText(img, str(lost_number), (40, 80), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2)
cv2.imshow(video.name, img)
if cv2.waitKey() & 0xFF == ord('q'):
break
toc /= cv2.getTickFrequency()
# save results
video_path = os.path.join('results', args.dataset, model_name,
'baseline', video.name)
if not os.path.isdir(video_path):
os.makedirs(video_path)
result_path = os.path.join(video_path, '{}_001.txt'.format(video.name))
with open(result_path, 'w') as f:
for x in pred_bboxes:
if isinstance(x, int):
f.write("{:d}\n".format(x))
else:
f.write(','.join([vot_float2str("%.4f", i) for i in x]) + '\n')
print('({:3d}) Video: {:12s} Time: {:4.1f}s Speed: {:3.1f}fps Lost: {:d}'.format(
v_idx + 1, video.name, toc, idx / toc, lost_number))
total_lost += lost_number
print("{:s} total lost: {:d}".format(model_name, total_lost))
else:
# OPE tracking
for v_idx, video in enumerate(dataset):
if args.video != '':
# test one special video
if video.name != args.video:
continue
toc = 0
pred_bboxes = []
scores = []
track_times = []
for idx, (img, gt_bbox) in enumerate(video):
# convert bgr to rgb
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
tic = cv2.getTickCount()
if idx == 0:
cx, cy, w, h = get_axis_aligned_bbox(np.array(gt_bbox))
gt_bbox_ = [cx - w / 2, cy - h / 2, w, h]
init_info = {'init_bbox': gt_bbox_}
tracker.initialize(img, init_info)
pred_bbox = gt_bbox_
scores.append(None)
if 'VOT2018-LT' == args.dataset:
pred_bboxes.append([1])
else:
pred_bboxes.append(pred_bbox)
else:
outputs = tracker.track(img)
pred_bbox = outputs['target_bbox']
pred_bboxes.append(pred_bbox)
scores.append(outputs['best_score'])
if args.mask:
pred_mask = outputs['target_mask']
toc += cv2.getTickCount() - tic
track_times.append((cv2.getTickCount() - tic) / cv2.getTickFrequency())
if idx == 0:
cv2.destroyAllWindows()
if args.vis and idx > 0:
img_bgr = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
gt_bbox = list(map(int, gt_bbox))
pred_bbox = list(map(int, pred_bbox))
cv2.rectangle(img_bgr, (gt_bbox[0], gt_bbox[1]),
(gt_bbox[0] + gt_bbox[2], gt_bbox[1] + gt_bbox[3]), (0, 255, 0), 3)
cv2.rectangle(img_bgr, (pred_bbox[0], pred_bbox[1]),
(pred_bbox[0] + pred_bbox[2], pred_bbox[1] + pred_bbox[3]), (0, 255, 255), 3)
cv2.putText(img_bgr, str(idx), (40, 40), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 255), 2)
img_bgr_m = img_bgr
if args.mask:
img_bgr_m = img_bgr.astype(np.float32)
img_bgr_m[:, :, 1] += 127.0 * pred_mask
img_bgr_m[:, :, 2] += 127.0 * pred_mask
# contours, _ = cv2.findContours(img_bgr_m, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
# img_bgr_m = cv2.drawContours(img_bgr_m, contours, -1, (0, 255, 255), 4)
img_bgr_m = img_bgr_m.clip(0, 255).astype(np.uint8)
cv2.imshow(video.name, img_bgr_m)
cv2.waitKey(1)
toc /= cv2.getTickFrequency()
# save results
if 'VOT2018-LT' == args.dataset:
video_path = os.path.join('results', args.dataset, model_name,
'longterm', video.name)
if not os.path.isdir(video_path):
os.makedirs(video_path)
result_path = os.path.join(video_path,
'{}_001.txt'.format(video.name))
with open(result_path, 'w') as f:
for x in pred_bboxes:
f.write(','.join([str(i) for i in x]) + '\n')
result_path = os.path.join(video_path,
'{}_001_confidence.value'.format(video.name))
with open(result_path, 'w') as f:
for x in scores:
f.write('\n') if x is None else f.write("{:.6f}\n".format(x))
result_path = os.path.join(video_path,
'{}_time.txt'.format(video.name))
with open(result_path, 'w') as f:
for x in track_times:
f.write("{:.6f}\n".format(x))
elif 'GOT-10k' == args.dataset:
video_path = os.path.join('results', args.dataset, model_name, video.name)
if not os.path.isdir(video_path):
os.makedirs(video_path)
result_path = os.path.join(video_path, '{}_001.txt'.format(video.name))
with open(result_path, 'w') as f:
for x in pred_bboxes:
f.write(','.join([str(i) for i in x]) + '\n')
result_path = os.path.join(video_path,
'{}_time.txt'.format(video.name))
with open(result_path, 'w') as f:
for x in track_times:
f.write("{:.6f}\n".format(x))
else:
model_path = os.path.join('results', args.dataset, model_name)
if not os.path.isdir(model_path):
os.makedirs(model_path)
result_path = os.path.join(model_path, '{}.txt'.format(video.name))
with open(result_path, 'w') as f:
for x in pred_bboxes:
f.write(','.join([str(i) for i in x]) + '\n')
print('({:3d}) Video: {:12s} Time: {:5.1f}s Speed: {:3.1f}fps'.format(
v_idx + 1, video.name, toc, idx / toc))
if __name__ == '__main__':
main()