def track(self, im):
for i in range(self.config.num_scale): # crop multi-scale search region
window_sz = self.target_sz * (self.config.scale_factor[i] * (1 + self.config.padding))
bbox = cxy_wh_2_bbox(self.target_pos, window_sz)
self.patch_crop[i, :] = crop_chw(im, bbox, self.config.crop_sz)
search = self.patch_crop - self.config.net_average_image
if self.gpu:
response = self.net(torch.Tensor(search).cuda())
else:
response = self.net(torch.Tensor(search))
peak, idx = torch.max(response.view(self.config.num_scale, -1), 1)
peak = peak.data.cpu().numpy() * self.config.scale_penalties
best_scale = np.argmax(peak)
r_max, c_max = np.unravel_index(idx[best_scale], self.config.net_input_size)
if r_max > self.config.net_input_size[0] / 2:
r_max = r_max - self.config.net_input_size[0]
if c_max > self.config.net_input_size[1] / 2:
c_max = c_max - self.config.net_input_size[1]
window_sz = self.target_sz * (self.config.scale_factor[best_scale] * (1 + self.config.padding))
self.target_pos = self.target_pos + np.array([c_max, r_max]) * window_sz / self.config.net_input_size
self.target_sz = np.minimum(np.maximum(window_sz / (1 + self.config.padding), self.min_sz), self.max_sz)
# model update
window_sz = self.target_sz * (1 + self.config.padding)
bbox = cxy_wh_2_bbox(self.target_pos, window_sz)
patch = crop_chw(im, bbox, self.config.crop_sz)
target = patch - self.config.net_average_image
self.net.update(torch.Tensor(np.expand_dims(target, axis=0)).cuda(), lr=self.config.interp_factor)
return cxy_wh_2_rect1(self.target_pos, self.target_sz) # 1-index
im = cv2.imread(image_files[0]) # HxWxC
# confine results
min_sz = np.maximum(config.min_scale_factor * target_sz, 4)
max_sz = np.minimum(im.shape[:2], config.max_scale_factor * target_sz)
# crop template
window_sz = target_sz * (1 + config.padding)
bbox = cxy_wh_2_bbox(target_pos, window_sz)
patch = crop_chw(im, bbox, config.crop_sz)
target = patch - config.net_average_image
net.update(torch.Tensor(np.expand_dims(target, axis=0)).cuda())
res = [cxy_wh_2_rect1(target_pos, target_sz)] # save in .txt
patch_crop = np.zeros(
(config.num_scale, patch.shape[0], patch.shape[1], patch.shape[2]),
np.float32)
for f in range(1, n_images): # track
im = cv2.imread(image_files[f])
for i in range(config.num_scale): # crop multi-scale search region
window_sz = target_sz * (config.scale_factor[i] *
(1 + config.padding))
bbox = cxy_wh_2_bbox(target_pos, window_sz)
patch_crop[i, :] = crop_chw(im, bbox, config.crop_sz)
search = patch_crop - config.net_average_image
response = net(torch.Tensor(search).cuda())
peak, idx = torch.max(response.view(config.num_scale, -1), 1)
im = video.frame_at(0) # HxWxC
# confine results
min_sz = np.maximum(config.min_scale_factor * target_sz, 4)
max_sz = np.minimum(im.shape[:2], config.max_scale_factor * target_sz)
# crop template
window_sz = target_sz * (1 + config.padding)
bbox = cxy_wh_2_bbox(target_pos, window_sz)
patch = crop_chw(im, bbox, config.crop_sz)
target = patch - config.net_average_image
net.update(torch.Tensor(np.expand_dims(target, axis=0)).cuda())
track = [cxy_wh_2_rect1(target_pos, target_sz)]
patch_crop = np.zeros(
(config.num_scale, patch.shape[0], patch.shape[1], patch.shape[2]),
np.float32)
for f in range(1, n_images): # track
im = video.frame_at(f)
for i in range(config.num_scale): # crop multi-scale search region
window_sz = target_sz * (config.scale_factor[i] *
(1 + config.padding))
bbox = cxy_wh_2_bbox(target_pos, window_sz)
patch_crop[i, :] = crop_chw(im, bbox, config.crop_sz)
search = patch_crop - config.net_average_image
search = torch.Tensor(search).cuda()
