-
Notifications
You must be signed in to change notification settings - Fork 24
/
box_utils.py
executable file
·134 lines (104 loc) · 3.78 KB
/
box_utils.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
import numpy as np
from PIL import Image
def nms(boxes, overlap_threshold=0.5, mode='union'):
""" Pure Python NMS baseline. """
x1 = boxes[:, 0]
y1 = boxes[:, 1]
x2 = boxes[:, 2]
y2 = boxes[:, 3]
scores = boxes[:, 4]
areas = (x2 - x1 + 1) * (y2 - y1 + 1)
order = scores.argsort()[::-1]
keep = []
while order.size > 0:
i = order[0]
keep.append(i)
xx1 = np.maximum(x1[i], x1[order[1:]])
yy1 = np.maximum(y1[i], y1[order[1:]])
xx2 = np.minimum(x2[i], x2[order[1:]])
yy2 = np.minimum(y2[i], y2[order[1:]])
w = np.maximum(0.0, xx2 - xx1 + 1)
h = np.maximum(0.0, yy2 - yy1 + 1)
inter = w * h
if mode is 'min':
ovr = inter / np.minimum(areas[i], areas[order[1:]])
else:
ovr = inter / (areas[i] + areas[order[1:]] - inter)
inds = np.where(ovr <= overlap_threshold)[0]
order = order[inds + 1]
return keep
def convert_to_square(bboxes):
"""
Convert bounding boxes to a square form.
"""
square_bboxes = np.zeros_like(bboxes)
x1, y1, x2, y2 = [bboxes[:, i] for i in range(4)]
h = y2 - y1 + 1.0
w = x2 - x1 + 1.0
max_side = np.maximum(h, w)
square_bboxes[:, 0] = x1 + w*0.5 - max_side*0.5
square_bboxes[:, 1] = y1 + h*0.5 - max_side*0.5
square_bboxes[:, 2] = square_bboxes[:, 0] + max_side - 1.0
square_bboxes[:, 3] = square_bboxes[:, 1] + max_side - 1.0
return square_bboxes
def calibrate_box(bboxes, offsets):
"""Transform bounding boxes to be more like true bounding boxes.
'offsets' is one of the outputs of the nets.
"""
x1, y1, x2, y2 = [bboxes[:, i] for i in range(4)]
w = x2 - x1 + 1.0
h = y2 - y1 + 1.0
w = np.expand_dims(w, 1)
h = np.expand_dims(h, 1)
translation = np.hstack([w, h, w, h])*offsets
bboxes[:, 0:4] = bboxes[:, 0:4] + translation
return bboxes
def get_image_boxes(bounding_boxes, img, size=24):
"""Cut out boxes from the image.
"""
num_boxes = len(bounding_boxes)
width, height = img.size
[dy, edy, dx, edx, y, ey, x, ex, w, h] = correct_bboxes(bounding_boxes, width, height)
img_boxes = np.zeros((num_boxes, 3, size, size), 'float32')
for i in range(num_boxes):
img_box = np.zeros((h[i], w[i], 3), 'uint8')
img_array = np.asarray(img, 'uint8')
img_box[dy[i]:(edy[i] + 1), dx[i]:(edx[i] + 1), :] =\
img_array[y[i]:(ey[i] + 1), x[i]:(ex[i] + 1), :]
img_box = Image.fromarray(img_box)
img_box = img_box.resize((size, size), Image.BILINEAR)
img_box = np.asarray(img_box, 'float32')
img_boxes[i, :, :, :] = _preprocess(img_box)
return img_boxes
def correct_bboxes(bboxes, width, height):
"""Crop boxes that are too big and get coordinates
with respect to cutouts.
"""
x1, y1, x2, y2 = [bboxes[:, i] for i in range(4)]
w, h = x2 - x1 + 1.0, y2 - y1 + 1.0
num_boxes = bboxes.shape[0]
x, y, ex, ey = x1, y1, x2, y2
dx, dy = np.zeros((num_boxes,)), np.zeros((num_boxes,))
edx, edy = w.copy() - 1.0, h.copy() - 1.0
ind = np.where(ex > width - 1.0)[0]
edx[ind] = w[ind] + width - 2.0 - ex[ind]
ex[ind] = width - 1.0
ind = np.where(ey > height - 1.0)[0]
edy[ind] = h[ind] + height - 2.0 - ey[ind]
ey[ind] = height - 1.0
ind = np.where(x < 0.0)[0]
dx[ind] = 0.0 - x[ind]
x[ind] = 0.0
ind = np.where(y < 0.0)[0]
dy[ind] = 0.0 - y[ind]
y[ind] = 0.0
return_list = [dy, edy, dx, edx, y, ey, x, ex, w, h]
return_list = [i.astype('int32') for i in return_list]
return return_list
def _preprocess(img):
"""Preprocessing step before feeding the network.
"""
img = img.transpose((2, 0, 1))
img = np.expand_dims(img, 0)
img = (img - 127.5)*0.0078125
return img