-
Notifications
You must be signed in to change notification settings - Fork 0
/
box_utils.py
125 lines (100 loc) · 4.53 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
# -*- coding: utf-8 -*-
# 此文件中包含了一些box相关的计算函数
import numpy as np
# 计算IoU，矩形框的坐标形式为xyxy，这个函数会被保存在box_utils.py文件中
def box_iou_xyxy(box1, box2):
# 获取box1左上角和右下角的坐标
x1min, y1min, x1max, y1max = box1[0], box1[1], box1[2], box1[3]
# 计算box1的面积
s1 = (y1max - y1min + 1.) * (x1max - x1min + 1.)
# 获取box2左上角和右下角的坐标
x2min, y2min, x2max, y2max = box2[0], box2[1], box2[2], box2[3]
# 计算box2的面积
s2 = (y2max - y2min + 1.) * (x2max - x2min + 1.)
# 计算相交矩形框的坐标
xmin = np.maximum(x1min, x2min)
ymin = np.maximum(y1min, y2min)
xmax = np.minimum(x1max, x2max)
ymax = np.minimum(y1max, y2max)
# 计算相交矩形行的高度、宽度、面积
inter_h = np.maximum(ymax - ymin + 1., 0.)
inter_w = np.maximum(xmax - xmin + 1., 0.)
intersection = inter_h * inter_w
# 计算相并面积
union = s1 + s2 - intersection
# 计算交并比
iou = intersection / union
return iou
# 计算IoU，矩形框的坐标形式为xywh
def box_iou_xywh(box1, box2):
x1min, y1min = box1[0] - box1[2] / 2.0, box1[1] - box1[3] / 2.0
x1max, y1max = box1[0] + box1[2] / 2.0, box1[1] + box1[3] / 2.0
s1 = box1[2] * box1[3]
x2min, y2min = box2[0] - box2[2] / 2.0, box2[1] - box2[3] / 2.0
x2max, y2max = box2[0] + box2[2] / 2.0, box2[1] + box2[3] / 2.0
s2 = box2[2] * box2[3]
xmin = np.maximum(x1min, x2min)
ymin = np.maximum(y1min, y2min)
xmax = np.minimum(x1max, x2max)
ymax = np.minimum(y1max, y2max)
inter_h = np.maximum(ymax - ymin, 0.)
inter_w = np.maximum(xmax - xmin, 0.)
intersection = inter_h * inter_w
union = s1 + s2 - intersection
iou = intersection / union
return iou
def multi_box_iou_xywh(box1, box2):
"""
In this case, box1 or box2 can contain multi boxes.
Only two cases can be processed in this method:
1, box1 and box2 have the same shape, box1.shape == box2.shape
2, either box1 or box2 contains only one box, len(box1) == 1 or len(box2) == 1
If the shape of box1 and box2 does not match, and both of them contain multi boxes, it will be wrong.
"""
assert box1.shape[-1] == 4, "Box1 shape[-1] should be 4."
assert box2.shape[-1] == 4, "Box2 shape[-1] should be 4."
b1_x1, b1_x2 = box1[:, 0] - box1[:, 2] / 2, box1[:, 0] + box1[:, 2] / 2
b1_y1, b1_y2 = box1[:, 1] - box1[:, 3] / 2, box1[:, 1] + box1[:, 3] / 2
b2_x1, b2_x2 = box2[:, 0] - box2[:, 2] / 2, box2[:, 0] + box2[:, 2] / 2
b2_y1, b2_y2 = box2[:, 1] - box2[:, 3] / 2, box2[:, 1] + box2[:, 3] / 2
inter_x1 = np.maximum(b1_x1, b2_x1)
inter_x2 = np.minimum(b1_x2, b2_x2)
inter_y1 = np.maximum(b1_y1, b2_y1)
inter_y2 = np.minimum(b1_y2, b2_y2)
inter_w = inter_x2 - inter_x1
inter_h = inter_y2 - inter_y1
inter_w = np.clip(inter_w, a_min=0., a_max=None)
inter_h = np.clip(inter_h, a_min=0., a_max=None)
inter_area = inter_w * inter_h
b1_area = (b1_x2 - b1_x1) * (b1_y2 - b1_y1)
b2_area = (b2_x2 - b2_x1) * (b2_y2 - b2_y1)
return inter_area / (b1_area + b2_area - inter_area)
def box_crop(boxes, labels, crop, img_shape):
x, y, w, h = map(float, crop)
im_w, im_h = map(float, img_shape)
boxes = boxes.copy()
boxes[:, 0], boxes[:, 2] = (boxes[:, 0] - boxes[:, 2] / 2) * im_w, (
boxes[:, 0] + boxes[:, 2] / 2) * im_w
boxes[:, 1], boxes[:, 3] = (boxes[:, 1] - boxes[:, 3] / 2) * im_h, (
boxes[:, 1] + boxes[:, 3] / 2) * im_h
crop_box = np.array([x, y, x + w, y + h])
centers = (boxes[:, :2] + boxes[:, 2:]) / 2.0
mask = np.logical_and(crop_box[:2] <= centers, centers <= crop_box[2:]).all(
axis=1)
boxes[:, :2] = np.maximum(boxes[:, :2], crop_box[:2])
boxes[:, 2:] = np.minimum(boxes[:, 2:], crop_box[2:])
boxes[:, :2] -= crop_box[:2]
boxes[:, 2:] -= crop_box[:2]
mask = np.logical_and(mask, (boxes[:, :2] < boxes[:, 2:]).all(axis=1))
boxes = boxes * np.expand_dims(mask.astype('float32'), axis=1)
labels = labels * mask.astype('float32')
boxes[:, 0], boxes[:, 2] = (boxes[:, 0] + boxes[:, 2]) / 2 / w, (
boxes[:, 2] - boxes[:, 0]) / w
boxes[:, 1], boxes[:, 3] = (boxes[:, 1] + boxes[:, 3]) / 2 / h, (
boxes[:, 3] - boxes[:, 1]) / h
return boxes, labels, mask.sum()
if __name__ == '__main__':
bbox1 = [100., 100., 200., 200.]
bbox2 = [120., 120., 220., 220.]
iou = box_iou_xyxy(bbox1, bbox2)
print('IoU is {}'.format(iou))