def __init__(self, threshold=0.65):
self.THRES = threshold
'''create tracker'''
# create base tracker
model = ModelBuilder(
) # a model is a Neural Network.(a torch.nn.Module)
model = load_pretrain(model, snapshot_path).cuda().eval()
self.base_tracker = build_tracker(
model
) # a tracker is a object consisting of not only a NN and some post-processing
def __init__(self, rf_model_code, enable_rf=True):
model_name = 'siamrpn_' + RF_type.format(rf_model_code)
if not enable_rf:
model_name = model_name.replace(RF_type.format(rf_model_code), '')
super(SiamRPNpp_RF, self).__init__(name=model_name)
self.enable_rf = enable_rf
# create tracker
snapshot_path = os.path.join(project_path_,
'experiments/%s/model.pth' % siam_model_)
config_path = os.path.join(project_path_,
'experiments/%s/config.yaml' % siam_model_)
cfg.merge_from_file(config_path)
model = ModelBuilder() # a sub-class of `torch.nn.Module`
model = load_pretrain(model, snapshot_path).cuda().eval()
self.tracker = build_tracker(
model
) # tracker is a object consisting of NN and some post-processing
# create refinement module
if self.enable_rf:
self.RF_module = RefineModule(refine_path.format(rf_model_code),
selector_path,
search_factor=sr,
input_sz=input_sz)
def main():
RF_module = RefineModule(refine_path,
selector_path,
search_factor=sr,
input_sz=input_sz)
# refine_method = args.refine_method
model_name = 'siamrpn_' + RF_type + '_m2b_{}'.format(args.thres)
snapshot_path = os.path.join(
project_path_, 'experiments/%s/model.pth' % args.tracker_name)
config_path = os.path.join(
project_path_, 'experiments/%s/config.yaml' % args.tracker_name)
cfg.merge_from_file(config_path)
# create model
model = ModelBuilder() # a sub-class of `torch.nn.Module`
model = load_pretrain(model, snapshot_path).cuda().eval()
# build tracker
tracker = build_tracker(
model) # tracker is a object consisting of NN and some post-processing
# create dataset
dataset = DatasetFactory.create_dataset(name=args.dataset,
dataset_root=dataset_root_,
load_img=False)
# OPE tracking
for v_idx, video in enumerate(dataset):
if os.path.exists(
os.path.join(save_dir, args.dataset, model_name,
'{}.txt'.format(video.name))):
continue
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):
tic = cv2.getTickCount()
if idx == 0:
H, W, _ = img.shape
cx, cy, w, h = get_axis_aligned_bbox(np.array(gt_bbox))
gt_bbox_ = [cx - (w - 1) / 2, cy - (h - 1) / 2, w, h]
tracker.init(img, gt_bbox_)
'''##### initilize refinement module for specific video'''
RF_module.initialize(cv2.cvtColor(img, cv2.COLOR_BGR2RGB),
np.array(gt_bbox_))
pred_bbox = gt_bbox_
scores.append(None)
pred_bboxes.append(pred_bbox)
else:
outputs = tracker.track(img)
pred_bbox = outputs['bbox']
'''##### refine tracking results #####'''
mask_pred = RF_module.get_mask(
cv2.cvtColor(img, cv2.COLOR_BGR2RGB), np.array(pred_bbox))
pred_bbox = mask2bbox(mask_pred,
pred_bbox,
MASK_THRESHOLD=args.thres)
x1, y1, w, h = pred_bbox.tolist()
'''add boundary and min size limit'''
x1, y1, x2, y2 = bbox_clip(x1, y1, x1 + w, y1 + h, (H, W))
w = x2 - x1
h = y2 - y1
pred_bbox = np.array([x1, y1, w, h])
tracker.center_pos = np.array([x1 + w / 2, y1 + h / 2])
tracker.size = np.array([w, h])
pred_bboxes.append(pred_bbox)
scores.append(outputs['best_score'])
toc += cv2.getTickCount() - tic
track_times.append(
(cv2.getTickCount() - tic) / cv2.getTickFrequency())
if idx == 0:
cv2.destroyAllWindows()
if args.vis and idx > 0:
gt_bbox = list(map(int, gt_bbox))
pred_bbox = list(map(int, pred_bbox))
cv2.rectangle(
img, (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, (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, str(idx), (40, 40), cv2.FONT_HERSHEY_SIMPLEX,
1, (0, 255, 255), 2)
cv2.imshow(video.name, img)
cv2.waitKey(1)
toc /= cv2.getTickFrequency()
# save results
model_path = os.path.join(save_dir, args.dataset,
model_name + '_' + str(selector_path))
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))
def main(model_code):
RF_module = RefineModule(refine_path.format(model_code),
selector_path,
search_factor=sr,
input_sz=input_sz)
model_name = 'siamrpn_' + '{}-{}'.format(
RF_type.format(model_code), selector_path) + '_%d' % (args.run_id)
snapshot_path = os.path.join(
project_path_, 'experiments/%s/model.pth' % args.tracker_name)
config_path = os.path.join(
project_path_, 'experiments/%s/config.yaml' % args.tracker_name)
cfg.merge_from_file(config_path)
# create model
model = ModelBuilder() # a sub-class of `torch.nn.Module`
model = load_pretrain(model, snapshot_path).cuda().eval()
# build tracker
tracker = build_tracker(
model) # tracker is a object consisting of NN and some post-processing
# create dataset
dataset = DatasetFactory.create_dataset(name=args.dataset,
dataset_root=dataset_root_,
load_img=False)
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):
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:
H, W, _ = img.shape
cx, cy, w, h = get_axis_aligned_bbox(np.array(gt_bbox))
gt_bbox_ = [cx - (w - 1) / 2, cy - (h - 1) / 2, w, h]
tracker.init(img, gt_bbox_)
'''##### initilize refinement module for specific video'''
RF_module.initialize(cv2.cvtColor(img, cv2.COLOR_BGR2RGB),
np.array(gt_bbox_))
pred_bbox = gt_bbox_
pred_bboxes.append(1)
elif idx > frame_counter:
outputs = tracker.track(img)
pred_bbox = outputs['bbox']
'''##### refine tracking results #####'''
pred_bbox = RF_module.refine(
cv2.cvtColor(img, cv2.COLOR_BGR2RGB),
np.array(pred_bbox))
x1, y1, w, h = pred_bbox.tolist()
'''add boundary and min size limit'''
x1, y1, x2, y2 = bbox_clip(x1, y1, x1 + w, y1 + h, (H, W))
w = x2 - x1
h = y2 - y1
pred_bbox = np.array([x1, y1, w, h])
tracker.center_pos = np.array([x1 + w / 2, y1 + h / 2])
tracker.size = np.array([w, h])
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:
cv2.polylines(
img, [np.array(gt_bbox, np.int).reshape(
(-1, 1, 2))], True, (0, 255, 0), 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)
cv2.waitKey(1)
toc /= cv2.getTickFrequency()
# save results
video_path = os.path.join(save_dir, 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))
def main():
model_name = 'siamRPN'
snapshot_path = os.path.join(
project_path_, 'experiments/%s/model.pth' % args.tracker_name)
config_path = os.path.join(
project_path_, 'experiments/%s/config.yaml' % args.tracker_name)
cfg.merge_from_file(config_path)
# create model
model = ModelBuilder() # a model is a Neural Network.(a torch.nn.Module)
# load model
model = load_pretrain(model, snapshot_path).cuda().eval()
# build tracker
tracker = build_tracker(
model
) # a tracker is a object consisting of not only a NN and some post-processing
# create dataset
dataset = DatasetFactory.create_dataset(name=args.dataset,
dataset_root=dataset_root_,
load_img=False)
# OPE tracking
for v_idx, video in enumerate(dataset):
if os.path.exists(
os.path.join(save_dir, args.dataset, model_name,
'{}.txt'.format(video.name))):
continue
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):
tic = cv2.getTickCount()
if idx == 0:
H, W, _ = img.shape
cx, cy, w, h = get_axis_aligned_bbox(np.array(gt_bbox))
gt_bbox_ = [cx - (w - 1) / 2, cy - (h - 1) / 2, w, h]
tracker.init(img, gt_bbox_)
pred_bboxes.append(gt_bbox_)
else:
outputs = tracker.track(img)
pred_bbox = outputs['bbox']
x1, y1, w, h = pred_bbox
'''add boundary and min size limit'''
x1, y1, x2, y2 = bbox_clip(x1, y1, x1 + w, y1 + h, (H, W))
w = x2 - x1
h = y2 - y1
pred_bbox = np.array([x1, y1, w, h])
tracker.center_pos = np.array([x1 + w / 2, y1 + h / 2])
tracker.size = np.array([w, h])
pred_bboxes.append(pred_bbox)
scores.append(outputs['best_score'])
toc += cv2.getTickCount() - tic
track_times.append(
(cv2.getTickCount() - tic) / cv2.getTickFrequency())
if idx == 0:
cv2.destroyAllWindows()
if args.vis and idx > 0:
gt_bbox = list(map(int, gt_bbox))
pred_bbox = list(map(int, pred_bbox))
cv2.rectangle(
img, (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, (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, str(idx), (40, 40), cv2.FONT_HERSHEY_SIMPLEX,
1, (0, 255, 255), 2)
cv2.imshow(video.name, img)
cv2.waitKey(1)
toc /= cv2.getTickFrequency()
# save results
model_path = os.path.join(save_dir, 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))
def main():
RF_module = RefineModule(refine_path,
selector_path,
search_factor=sr,
input_sz=input_sz)
model_name = 'siamrpn_' + RF_type
print(model_name)
dataset_root = dataset_root_
snapshot_path = os.path.join(
project_path_, 'experiments/%s/model.pth' % args.tracker_name)
config_path = os.path.join(
project_path_, 'experiments/%s/config.yaml' % args.tracker_name)
cfg.merge_from_file(config_path)
# create model
model = ModelBuilder() # a model is a Neural Network (`torch.nn.Module`)
model = load_pretrain(model, snapshot_path).cuda().eval()
# build tracker
tracker = build_tracker(
model
) # tracker is a object consisting of a NN and some post-processing
# create dataset
frames_dir = os.path.join(dataset_root, 'frames')
seq_list = sorted(os.listdir(frames_dir))
# OPE tracking
for v_idx, seq_name in enumerate(seq_list):
if args.video != '':
# test one special video
if seq_name != args.video:
continue
toc = 0
pred_bboxes = []
scores = []
track_times = []
seq_frame_dir = os.path.join(frames_dir, seq_name)
num_frames = len(os.listdir(seq_frame_dir))
gt_file = os.path.join(dataset_root, 'anno', '%s.txt' % seq_name)
gt_bbox = np.loadtxt(gt_file, dtype=np.float32,
delimiter=',').squeeze()
for idx in range(num_frames):
frame_path = os.path.join(seq_frame_dir, '%d.jpg' % idx)
img = cv2.imread(frame_path)
tic = cv2.getTickCount()
if idx == 0:
cx, cy, w, h = get_axis_aligned_bbox(np.array(gt_bbox))
gt_bbox_ = [cx - (w - 1) / 2, cy - (h - 1) / 2, w, h]
H, W, _ = img.shape
'''Initialize'''
tracker.init(img, gt_bbox_)
'''##### initilize refinement module for specific video'''
RF_module.initialize(cv2.cvtColor(img, cv2.COLOR_BGR2RGB),
np.array(gt_bbox_))
pred_bbox = gt_bbox_
scores.append(None)
pred_bboxes.append(pred_bbox)
else:
'''Track'''
outputs = tracker.track(img)
pred_bbox = outputs['bbox']
'''##### refine tracking results #####'''
pred_bbox = RF_module.refine(
cv2.cvtColor(img, cv2.COLOR_BGR2RGB), np.array(pred_bbox))
x1, y1, w, h = pred_bbox.tolist()
'''add boundary and min size limit'''
x1, y1, x2, y2 = bbox_clip(x1, y1, x1 + w, y1 + h, (H, W))
w = x2 - x1
h = y2 - y1
pred_bbox = np.array([x1, y1, w, h])
tracker.center_pos = np.array([x1 + w / 2, y1 + h / 2])
tracker.size = np.array([w, h])
pred_bboxes.append(pred_bbox)
toc += cv2.getTickCount() - tic
track_times.append(
(cv2.getTickCount() - tic) / cv2.getTickFrequency())
if idx == 0:
cv2.destroyAllWindows()
if args.vis and idx > 0:
pred_bbox = list(map(int, pred_bbox))
cv2.rectangle(
img, (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, str(idx), (40, 40), cv2.FONT_HERSHEY_SIMPLEX,
1, (0, 255, 255), 2)
cv2.imshow(seq_name, img)
cv2.waitKey(1)
toc /= cv2.getTickFrequency()
# save results
model_path = os.path.join(save_dir, 'trackingnet', model_name)
if not os.path.isdir(model_path):
os.makedirs(model_path)
result_path = os.path.join(model_path, '{}.txt'.format(seq_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, seq_name, toc, idx / toc))
def main():
model_name = 'siamRPN'
snapshot_path = os.path.join(project_path_, 'experiments/%s/model.pth' % args.tracker_name)
config_path = os.path.join(project_path_, 'experiments/%s/config.yaml' % args.tracker_name)
cfg.merge_from_file(config_path)
# create model
model = ModelBuilder() # a model is a Neural Network.(a torch.nn.Module)
# load model
model = load_pretrain(model, snapshot_path).cuda().eval()
# build tracker
tracker = build_tracker(model) # a tracker is a object consisting of not only a NN and some post-processing
# create dataset
dataset = DatasetFactory.create_dataset(name=args.dataset, dataset_root=dataset_root_, load_img=False)
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):
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:
H,W,_ = img.shape
cx, cy, w, h = get_axis_aligned_bbox(np.array(gt_bbox))
gt_bbox_ = [cx-(w-1)/2, cy-(h-1)/2, w, h]
tracker.init(img, gt_bbox_)
pred_bbox = gt_bbox_
pred_bboxes.append(1)
elif idx > frame_counter:
outputs = tracker.track(img)
pred_bbox = outputs['bbox']
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:
cv2.polylines(img, [np.array(gt_bbox, np.int).reshape((-1, 1, 2))],
True, (0, 255, 0), 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)
cv2.waitKey(1)
toc /= cv2.getTickFrequency()
# save results
video_path = os.path.join(save_dir, 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))