def show_double_bbox(img, pred_bbox, pred_score, gt_bbox, idx, lost_number,):
"""
:param img: (h,w,c)
:param pred_bbox: cx,cy,w,h
:param gt_bbox:
:param idx: the frame idx
:param lost_number: the lost number in the video
:return:
"""
pred_bbox = center2corner(pred_bbox)
gt_bbox = center2corner(gt_bbox)
pred_bbox = list(map(lambda x: int(x), pred_bbox))
gt_bbox = list(map(lambda x: int(x), gt_bbox))
cv2.rectangle(img, (pred_bbox[0], pred_bbox[1]), (pred_bbox[2], pred_bbox[3]), (0, 0, 255), 2)
cv2.rectangle(img, (gt_bbox[0], gt_bbox[1]), (gt_bbox[2], gt_bbox[3]), (255, 255, 0), 2)
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.putText(img, '{:.2f}'.format(pred_score), (40, 120), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 0, 0), 2)
# cv2.namedWindow('double bbox', cv2.WINDOW_NORMAL | cv2.WINDOW_KEEPRATIO)
# cv2.resizeWindow('double bbox', 600, 400)
# cv2.imshow('double bbox', img)
# cv2.waitKey(200)
visual_dir='visual_imgs'
if not os.path.isdir(visual_dir):
os.makedirs(visual_dir)
cv2.imwrite(os.path.join(visual_dir,'{}.png'.format(idx)),img)
def show_single_bbox(img, bbox):
pred_bbox = center2corner(bbox)
pred_bbox = list(map(lambda x: int(x), pred_bbox))
cv2.rectangle(img, (pred_bbox[0], pred_bbox[1]), (pred_bbox[2], pred_bbox[3]), (0, 0, 255), 2)
cv2.namedWindow('single bbox', cv2.WINDOW_NORMAL | cv2.WINDOW_KEEPRATIO)
cv2.resizeWindow('single bbox', 600, 400)
cv2.imshow('single bbox', img)
cv2.waitKey(1)
def get_bbox(self, image, ori_bbox):
img_h, img_w = image.shape[:2]
w, h = ori_bbox[2] - ori_bbox[0], ori_bbox[3] - ori_bbox[1]
context_amount = 0.5
wc_z = w + context_amount * (w + h)
hc_z = h + context_amount * (w + h)
s_z = np.sqrt(wc_z * hc_z)
scale_z = cfg.TRAIN.EXAMPLER_SIZE / s_z
w = w * scale_z
h = h * scale_z
cx, cy = img_w // 2, img_h // 2
bbox = center2corner(Center(cx, cy, w, h))
return bbox
def _get_bbox(self, image, shape):
imh, imw = image.shape[:2]
if len(shape) == 4:
w, h = shape[2] - shape[0], shape[3] - shape[1]
else:
w, h = shape
context_amount = 0.5
exemplar_size = cfg.TRAIN.EXEMPLAR_SIZE
wc_z = w + context_amount * (w + h)
hc_z = h + context_amount * (w + h)
s_z = np.sqrt(wc_z * hc_z)
scale_z = exemplar_size / s_z
w = w * scale_z
h = h * scale_z
cx, cy = imw // 2, imh // 2
bbox = center2corner(Center(cx, cy, w, h))
return bbox
def get_bbox(image, ori_bbox):
"""
:param image:
:param ori_bbox: cx,cy,w,h
:return:
"""
img_h, img_w = image.shape[:2]
w, h = ori_bbox[2], ori_bbox[3]
context_amount = 0.5
wc_z = w + context_amount * (w + h)
hc_z = h + context_amount * (w + h)
s_z = np.sqrt(wc_z * hc_z)
scale_z = cfg.TRAIN.EXAMPLER_SIZE / s_z
w = w * scale_z
h = h * scale_z
cx, cy = img_w // 2, img_h // 2
bbox = center2corner([cx, cy, w, h])
return Corner(*bbox)
def _shift_scale_aug(self, image, bbox, crop_bbox, size):
im_h, im_w = image.shape[:2]
# adjust crop bounding box
crop_bbox_center = corner2center(crop_bbox)
if self.scale:
scale_x = (1.0 + Augmentation.random() * self.scale)
scale_y = (1.0 + Augmentation.random() * self.scale)
h, w = crop_bbox_center.h, crop_bbox_center.w
scale_x = min(scale_x, float(im_w) / w)
scale_y = min(scale_y, float(im_h) / h)
crop_bbox_center = Center(crop_bbox_center.x,
crop_bbox_center.y,
crop_bbox_center.w * scale_x,
crop_bbox_center.h * scale_y)
crop_bbox = center2corner(crop_bbox_center)
if self.shift:
sx = Augmentation.random() * self.shift
sy = Augmentation.random() * self.shift
x1, y1, x2, y2 = crop_bbox
sx = max(-x1, min(im_w - 1 - x2, sx))
sy = max(-y1, min(im_h - 1 - y2, sy))
crop_bbox = Corner(x1 + sx, y1 + sy, x2 + sx, y2 + sy)
# adjust target bounding box
x1, y1 = crop_bbox.x1, crop_bbox.y1
bbox = Corner(bbox.x1 - x1, bbox.y1 - y1,
bbox.x2 - x1, bbox.y2 - y1)
if self.scale:
bbox = Corner(bbox.x1 / scale_x, bbox.y1 / scale_y,
bbox.x2 / scale_x, bbox.y2 / scale_y)
image = self._crop_roi(image, crop_bbox, size)
return image, bbox
def __call__(self, image, bbox, size, gray=False):
shape = image.shape
crop_bbox = center2corner(
Center(shape[0] // 2, shape[1] // 2, size - 1, size - 1))
# gray augmentation
if gray:
image = self._gray_aug(image)
# shift scale augmentation
image, bbox = self._shift_scale_aug(image, bbox, crop_bbox, size)
# color augmentation
if self.color > np.random.random():
image = self._color_aug(image)
# blur augmentation
if self.blur > np.random.random():
image = self._blur_aug(image)
# flip augmentation
if self.flip and self.flip > np.random.random():
image, bbox = self._flip_aug(image, bbox)
return image, bbox
def generate_all_anchors(self, im_c, size):
"""
im_c: image center
size: image size
"""
if self.image_center == im_c and self.size == size:
return False
self.image_center = im_c
self.size = size
a0x = im_c - size // 2 * self.stride
ori = np.array([a0x] * 4, dtype=np.float32)
zero_anchors = self.anchors + ori
x1 = zero_anchors[:, 0]
y1 = zero_anchors[:, 1]
x2 = zero_anchors[:, 2]
y2 = zero_anchors[:, 3]
x1, y1, x2, y2 = map(lambda x: x.reshape(self.anchor_num, 1, 1),
[x1, y1, x2, y2])
cx, cy, w, h = corner2center([x1, y1, x2, y2])
disp_x = np.arange(0, size).reshape(1, 1, -1) * self.stride
disp_y = np.arange(0, size).reshape(1, -1, 1) * self.stride
cx = cx + disp_x
cy = cy + disp_y
# broadcast
zero = np.zeros((self.anchor_num, size, size), dtype=np.float32)
cx, cy, w, h = map(lambda x: x + zero, [cx, cy, w, h])
x1, y1, x2, y2 = center2corner([cx, cy, w, h])
self.all_anchors = (np.stack([x1, y1, x2, y2]).astype(np.float32),
np.stack([cx, cy, w, h]).astype(np.float32))
return True
