def track(self, state, im):
p = state['p']
net = state['net']
avg_chans = state['avg_chans']
window = state['window']
target_pos = state['target_pos']
target_sz = state['target_sz']
hc_z = target_sz[1] + p.context_amount * sum(target_sz)
wc_z = target_sz[0] + p.context_amount * sum(target_sz)
s_z = np.sqrt(wc_z * hc_z)
scale_z = p.exemplar_size / s_z
d_search = (p.instance_size -
p.exemplar_size) / 2 # slightly different from rpn++
pad = d_search / scale_z
s_x = s_z + 2 * pad
x_crop, _ = get_subwindow_tracking(im, target_pos, p.instance_size,
python2round(s_x), avg_chans)
state['x_crop'] = x_crop.clone() # torch float tensor, (3,H,W)
x_crop = self.normalize(x_crop)
x_crop = x_crop.unsqueeze(0)
debug = True
if debug:
target_pos, target_sz, _, cls_score = self.update(net,
x_crop.cuda(),
target_pos,
target_sz *
scale_z,
window,
scale_z,
p,
debug=debug)
state['cls_score'] = cls_score
else:
target_pos, target_sz, _ = self.update(net,
x_crop.cuda(),
target_pos,
target_sz * scale_z,
window,
scale_z,
p,
debug=debug)
target_pos[0] = max(0, min(state['im_w'], target_pos[0]))
target_pos[1] = max(0, min(state['im_h'], target_pos[1]))
target_sz[0] = max(10, min(state['im_w'], target_sz[0]))
target_sz[1] = max(10, min(state['im_h'], target_sz[1]))
state['target_pos'] = target_pos
state['target_sz'] = target_sz
state['p'] = p
return state
def update(self, im, online_score=None, gt=None):
'''Tracking Function'''
im = np.array(im) # PIL to numpy
p = self.state['p']
net = self.state['net']
avg_chans = self.state['avg_chans']
window = self.state['window']
target_pos = self.state['target_pos']
target_sz = self.state['target_sz']
hc_z = target_sz[1] + p.context_amount * sum(target_sz)
wc_z = target_sz[0] + p.context_amount * sum(target_sz)
s_z = np.sqrt(wc_z * hc_z)
scale_z = p.exemplar_size / s_z
d_search = (p.instance_size -
p.exemplar_size) / 2 # slightly different from rpn++
pad = d_search / scale_z
s_x = s_z + 2 * pad
x_crop, _ = get_subwindow_tracking(im, target_pos, p.instance_size,
python2round(s_x), avg_chans)
self.state['x_crop'] = x_crop.clone() # torch float tensor, (3,H,W)
x_crop = self.normalize(x_crop).unsqueeze(0)
target_pos, target_sz, _ = self.forward(net, x_crop.cuda(), target_pos,
target_sz * scale_z, window,
scale_z, p)
target_pos[0] = max(0, min(self.state['im_w'], target_pos[0]))
target_pos[1] = max(0, min(self.state['im_h'], target_pos[1]))
target_sz[0] = max(10, min(self.state['im_w'], target_sz[0]))
target_sz[1] = max(10, min(self.state['im_h'], target_sz[1]))
self.state['target_pos'] = target_pos
self.state['target_sz'] = target_sz
self.state['p'] = p
location = cxy_wh_2_rect(self.state['target_pos'],
self.state['target_sz'])
return location
def track(self, state, im):
p = state['p']
net = state['net']
avg_chans = state['avg_chans']
window = state['window']
target_pos = state['target_pos']
target_sz = state['target_sz']
wc_z = target_sz[1] + p.context_amount * sum(target_sz)
hc_z = target_sz[0] + p.context_amount * sum(target_sz)
s_z = np.sqrt(wc_z * hc_z)
scale_z = p.exemplar_size / s_z
d_search = (p.instance_size - p.exemplar_size) / 2
pad = d_search / scale_z
s_x = s_z + 2 * pad
# extract scaled crops for search region x at previous target position
x_crop = Variable(
get_subwindow_tracking(im, target_pos, p.instance_size,
python2round(s_x), avg_chans).unsqueeze(0))
if state["arch"] == "SiamRPNRes22":
target_pos, target_sz, score = self.update(net, x_crop.cuda(),
target_pos,
target_sz * scale_z,
window, scale_z, p)
elif state["arch"] == "CascadedSiamRPNRes22":
target_pos, target_sz, score = self.update_stage12_mean(
net, x_crop.cuda(), target_pos, target_sz * scale_z, window,
scale_z, p)
else:
raise NotImplementedError
target_pos[0] = max(0, min(state['im_w'], target_pos[0]))
target_pos[1] = max(0, min(state['im_h'], target_pos[1]))
target_sz[0] = max(10, min(state['im_w'], target_sz[0]))
target_sz[1] = max(10, min(state['im_h'], target_sz[1]))
state['target_pos'] = target_pos
state['target_sz'] = target_sz
state['score'] = score
return state
def init(self, im, target_pos, target_sz, model, hp=None):
state = dict()
state['im_h'] = im.shape[0]
state['im_w'] = im.shape[1]
p = RPNConfig()
# single test
prefix = [x for x in ['OTB', 'VOT'] if x in self.info.dataset]
cfg_ = load_yaml('../experiments/test/{0}/{1}.yaml'.format(
prefix[0], self.info.arch))
# cfg_benchmark = cfg[self.info.dataset]
# p.update(cfg_benchmark)
# p.renew()
net = model
p.anchor = generate_anchor(p.total_stride, p.scales, p.ratios,
p.score_size)
avg_chans = np.mean(im, axis=(0, 1))
wc_z = target_sz[0] + p.context_amount * sum(target_sz)
hc_z = target_sz[1] + p.context_amount * sum(target_sz)
s_z = python2round(np.sqrt(wc_z * hc_z))
z_crop = get_subwindow_tracking(im, target_pos, p.exemplar_size, s_z,
avg_chans)
z = Variable(z_crop.unsqueeze(0))
net.template(z.cuda())
window = np.outer(np.hanning(p.score_size),
np.hanning(p.score_size)) # [17,17]
window = np.expand_dims(window, axis=0) # [1,17,17]
window = np.repeat(window, p.anchor_num, axis=0) # [5,17,17]
if cfg.TRACK.USE_CLASSIFIER:
# atom = ATOM().cuda().eval()
# checkpoint_dict = torch.load("/home/zhuyi/Code/CRPN_511/atom_pretrain.pth")
# atom.load_state_dict(checkpoint_dict["net"],strict=False)
self.classifier = BaseClassifier(net)
self.center_pos = np.array(target_pos)
self.size = np.array(target_sz)
bbox = [
target_pos[0] - (target_sz[0] - 1) / 2,
target_pos[1] - (target_sz[1] - 1) / 2, target_sz[0],
target_sz[1]
]
#bbox = [cx - (w - 1) / 2, cy - (h - 1) / 2, w, h]
if cfg.TRACK.TEMPLATE_UPDATE:
with torch.no_grad():
net.template_short_term(self.z_crop)
s_xx = s_z * (cfg.TRACK.INSTANCE_SIZE * 2 /
cfg.TRACK.EXEMPLAR_SIZE)
x_crop = get_subwindow_tracking(im, self.center_pos,
cfg.TRACK.INSTANCE_SIZE * 2,
round(s_xx), avg_chans)
x_crop = x_crop.unsqueeze(0)
self.classifier.initialize(x_crop.type(torch.FloatTensor), bbox)
state['p'] = p
state['net'] = net
state['avg_chans'] = avg_chans
state['window'] = window
state['target_pos'] = target_pos
state['target_sz'] = target_sz
return state