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
def mouse_opt(event, x, y, flags, param):
global tmp_p_1, tmp_p_2, target_pos, target_sz, n_reset, is_visible, res, is_labeling
if event == cv2.EVENT_LBUTTONDOWN:
if not is_labeling:
tmp_p_1 = (min(max(0, x), half_image_w if image_w > 1080 else image_w), min(max(0, y), half_image_h if image_w > 1080 else image_h))
print("mouse on click at (%d, %d)" % (x, y))
is_labeling = True
else:
# tmp_p_1 = (x, y)
# elif event == cv2.EVENT_LBUTTONUP:
tmp_p_2 = (min(max(0, x), half_image_w if image_w > 1080 else image_w), min(max(0, y), half_image_h if image_w > 1080 else image_h))
# tmp_p_2 = (x, y)
n_reset += 1
# update target bounding box
x_c = (tmp_p_1[0] + tmp_p_2[0]) / 2.0
y_c = (tmp_p_1[1] + tmp_p_2[1]) / 2.0
w = float(abs(tmp_p_2[0] - tmp_p_1[0]))
h = float(abs(tmp_p_2[1] - tmp_p_1[1]))
target_pos = np.array([x_c, y_c])
target_sz = np.array([w, h])
# try:
# res[n_frame] = np.concatenate((cxy_wh_2_bbox(target_pos, target_sz), np.array([is_visible])))
# except Exception as e:
# print(e)
# save_results(res, result_path, image_w, image_h)
# print("save file in %s" % result_path)
# sys.exit()
if len(res) == 0:
print("no record found, append data")
res.append(np.concatenate((cxy_wh_2_bbox(target_pos, target_sz), np.array([is_visible]))))
else:
res[n_frame-1] = np.concatenate((cxy_wh_2_bbox(target_pos, target_sz), np.array([is_visible])))
# update template
update_template()
is_visible = 1
is_labeling = False
elif event == cv2.EVENT_MOUSEMOVE:
if is_labeling:
tmp_p_2 = (min(max(0, x), half_image_w if image_w > 1080 else image_w), min(max(0, y), half_image_h if image_w > 1080 else image_h))
# update target bounding box
x_c = (tmp_p_1[0] + tmp_p_2[0]) / 2.0
y_c = (tmp_p_1[1] + tmp_p_2[1]) / 2.0
w = float(abs(tmp_p_2[0] - tmp_p_1[0]))
h = float(abs(tmp_p_2[1] - tmp_p_1[1]))
target_pos = np.array([x_c, y_c])
target_sz = np.array([w, h])
is_visible = 1
draw()
cv2.imshow('video', im_show)
cv2.waitKey(1)
def __init__(self, im, init_rect, config=TrackerConfig(), gpu=True):
self.gpu = gpu
self.config = config
self.net = DCFNet(config)
self.net.load_param(config.feature_path)
self.net.eval()
if gpu:
self.net.cuda()
# confine results
target_pos, target_sz = rect1_2_cxy_wh(init_rect)
self.min_sz = np.maximum(config.min_scale_factor * target_sz, 4)
self.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, self.config.crop_sz)
target = patch - config.net_average_image
self.net.update(torch.Tensor(np.expand_dims(target, axis=0)).cuda())
self.target_pos, self.target_sz = target_pos, target_sz
self.patch_crop = np.zeros(
(config.num_scale, patch.shape[0], patch.shape[1], patch.shape[2]),
np.float32) # buff
def update_template():
# 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)
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())
patch_crop = np.zeros((config.num_scale, patch.shape[0], patch.shape[1], patch.shape[2]), np.float32)
def preprocess_patch(im, target_pos, target_sz, config):
"""
preprocess patch for the input of network
:param im: input image (h, w, 3)
:param target_pos: center coordinate of the target box, tuple (cx, cy)
:param target_sz: width and hight of the target box, tuple (w, h)
:param config: TrackConfig
:return: patch: (3, config.crop_sz, config.crop_sz)
"""
# enlarge the cropping scale
window_sz = target_sz * (1 + config.padding)
# change the expression of box coordinate
bbox = cxy_wh_2_bbox(target_pos, window_sz)
# crop z in the next frame
patch = crop_chw(im, bbox, config.crop_sz)
# mean deduction
patch = patch - config.net_average_image
return patch
n_images = len(image_files)
tic = time.time() # time start
target_pos, target_sz = rect1_2_cxy_wh(
init_rect) # OTB label is 1-indexed
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))
cv2.setMouseCallback('video', mouse_opt)
key_first_frame = cv2.waitKey(1)
# if cv2.getWindowProperty('video', 1) == -1: # can't work in MobaXterm
# sys.exit()
# press space and first frame bounding box is choosed by user, then continue the video loop
if key_first_frame == KEY_PAUSE:
if target_pos is not None:
is_visible = 1
# 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())
patch_crop = np.zeros((config.num_scale, patch.shape[0], patch.shape[1], patch.shape[2]), np.float32)
else:
is_visible = 0
if len(res) > 0:
res = res[:n_frame]
res.append(np.concatenate((cxy_wh_2_bbox(target_pos, target_sz), np.array([is_visible])))) # save in .txt
start_from_half = False
break
# previous frame
elif key_first_frame == KEY_LEFT:
