def _shift_scale_aug(self, image, bbox, target_size, shift, scale):
"""Shift and rescale an image and corresponding bounding box.
Args:
image (ndarray): of shape (H, W, 3). Typically H and W equal to
511.
bbox (ndarray): of shape (4, ) in [x1, y1, x2, y2] format.
target_size (int): Exemplar size or search size.
shift (int): The max shift offset.
scale (float): The max rescale factor.
Returns:
tuple(crop_img, bbox): crop_img is a ndarray of shape
(target_size, target_size, 3), bbox is the corrsponding ground
truth box in [x1, y1, x2, y2] format.
"""
img_h, img_w = image.shape[:2]
scale_x = (2 * np.random.random() - 1) * scale + 1
scale_y = (2 * np.random.random() - 1) * scale + 1
scale_x = min(scale_x, float(img_w) / target_size)
scale_y = min(scale_y, float(img_h) / target_size)
crop_region = np.array([
img_w // 2 - 0.5 * scale_x * target_size,
img_h // 2 - 0.5 * scale_y * target_size,
img_w // 2 + 0.5 * scale_x * target_size,
img_h // 2 + 0.5 * scale_y * target_size
])
shift_x = (2 * np.random.random() - 1) * shift
shift_y = (2 * np.random.random() - 1) * shift
shift_x = max(-crop_region[0], min(img_w - crop_region[2], shift_x))
shift_y = max(-crop_region[1], min(img_h - crop_region[3], shift_y))
shift = np.array([shift_x, shift_y, shift_x, shift_y])
crop_region += shift
crop_img = crop_image(image, crop_region, target_size)
bbox -= np.array(
[crop_region[0], crop_region[1], crop_region[0], crop_region[1]])
bbox /= np.array([scale_x, scale_y, scale_x, scale_y],
dtype=np.float32)
return crop_img, bbox
def crop_like_SiamFC(self,
image,
bbox,
context_amount=0.5,
exemplar_size=127,
crop_size=511):
"""Crop an image as SiamFC did.
Args:
image (ndarray): of shape (H, W, 3).
bbox (ndarray): of shape (4, ) in [x1, y1, x2, y2] format.
context_amount (float): The context amount around a bounding box.
Defaults to 0.5.
exemplar_size (int): Exemplar size. Defaults to 127.
crop_size (int): Crop size. Defaults to 511.
Returns:
ndarray: The cropped image of shape (crop_size, crop_size, 3).
"""
padding = np.mean(image, axis=(0, 1)).tolist()
bbox = np.array([
0.5 * (bbox[2] + bbox[0]), 0.5 * (bbox[3] + bbox[1]),
bbox[2] - bbox[0], bbox[3] - bbox[1]
])
z_width = bbox[2] + context_amount * (bbox[2] + bbox[3])
z_height = bbox[3] + context_amount * (bbox[2] + bbox[3])
z_size = np.sqrt(z_width * z_height)
z_scale = exemplar_size / z_size
d_search = (crop_size - exemplar_size) / 2
pad = d_search / z_scale
x_size = z_size + 2 * pad
x_bbox = np.array([
bbox[0] - 0.5 * x_size, bbox[1] - 0.5 * x_size,
bbox[0] + 0.5 * x_size, bbox[1] + 0.5 * x_size
])
x_crop_img = crop_image(image, x_bbox, crop_size, padding)
return x_crop_img