-
Notifications
You must be signed in to change notification settings - Fork 1
/
image.py
230 lines (178 loc) · 7.51 KB
/
image.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
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
# ------------------------------------------------------------------------------
# Copyright (c) Microsoft
# Licensed under the MIT License.
# Written by Bin Xiao ([email protected])
# Modified by Xingyi Zhou
# ------------------------------------------------------------------------------
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import numpy as np
import cv2
import random
def flip(img):
return img[:, :, ::-1].copy()
def transform_preds(coords, center, scale, output_size):
target_coords = np.zeros(coords.shape)
trans = get_affine_transform(center, scale, 0, output_size, inv=1)
for p in range(coords.shape[0]):
target_coords[p, 0:2] = affine_transform(coords[p, 0:2], trans)
return target_coords
def get_affine_transform(center,
scale,
rot,
output_size,
shift=np.array([0, 0], dtype=np.float32),
inv=0):
if not isinstance(scale, np.ndarray) and not isinstance(scale, list):
scale = np.array([scale, scale], dtype=np.float32)
scale_tmp = scale
src_w = scale_tmp[0]
dst_w = output_size[0]
dst_h = output_size[1]
rot_rad = np.pi * rot / 180
src_dir = get_dir([0, src_w * -0.5], rot_rad)
dst_dir = np.array([0, dst_w * -0.5], np.float32)
src = np.zeros((3, 2), dtype=np.float32)
dst = np.zeros((3, 2), dtype=np.float32)
src[0, :] = center + scale_tmp * shift
src[1, :] = center + src_dir + scale_tmp * shift
dst[0, :] = [dst_w * 0.5, dst_h * 0.5]
dst[1, :] = np.array([dst_w * 0.5, dst_h * 0.5], np.float32) + dst_dir
src[2:, :] = get_3rd_point(src[0, :], src[1, :])
dst[2:, :] = get_3rd_point(dst[0, :], dst[1, :])
if inv:
trans = cv2.getAffineTransform(np.float32(dst), np.float32(src))
else:
trans = cv2.getAffineTransform(np.float32(src), np.float32(dst))
return trans
def affine_transform(pt, t):
new_pt = np.array([pt[0], pt[1], 1.], dtype=np.float32).T
new_pt = np.dot(t, new_pt)
return new_pt[:2]
def get_3rd_point(a, b):
direct = a - b
return b + np.array([-direct[1], direct[0]], dtype=np.float32)
def get_dir(src_point, rot_rad):
sn, cs = np.sin(rot_rad), np.cos(rot_rad)
src_result = [0, 0]
src_result[0] = src_point[0] * cs - src_point[1] * sn
src_result[1] = src_point[0] * sn + src_point[1] * cs
return src_result
def crop(img, center, scale, output_size, rot=0):
trans = get_affine_transform(center, scale, rot, output_size)
dst_img = cv2.warpAffine(img,
trans,
(int(output_size[0]), int(output_size[1])),
flags=cv2.INTER_LINEAR)
return dst_img
def gaussian_radius(det_size, min_overlap=0.7):
height, width = det_size
a1 = 1
b1 = (height + width)
c1 = width * height * (1 - min_overlap) / (1 + min_overlap)
sq1 = np.sqrt(b1 ** 2 - 4 * a1 * c1)
r1 = (b1 + sq1) / 2
a2 = 4
b2 = 2 * (height + width)
c2 = (1 - min_overlap) * width * height
sq2 = np.sqrt(b2 ** 2 - 4 * a2 * c2)
r2 = (b2 + sq2) / 2
a3 = 4 * min_overlap
b3 = -2 * min_overlap * (height + width)
c3 = (min_overlap - 1) * width * height
sq3 = np.sqrt(b3 ** 2 - 4 * a3 * c3)
r3 = (b3 + sq3) / 2
return min(r1, r2, r3)
def gaussian2D(shape, sigma=1):
m, n = [(ss - 1.) / 2. for ss in shape]
y, x = np.ogrid[-m:m+1,-n:n+1]
h = np.exp(-(x * x + y * y) / (2 * sigma * sigma))
h[h < np.finfo(h.dtype).eps * h.max()] = 0
return h
def draw_umich_gaussian(heatmap, center, radius, k=1):
diameter = 2 * radius + 1
gaussian = gaussian2D((diameter, diameter), sigma=diameter / 6)
x, y = int(center[0]), int(center[1])
height, width = heatmap.shape[0:2]
left, right = min(x, radius), min(width - x, radius + 1)
top, bottom = min(y, radius), min(height - y, radius + 1)
masked_heatmap = heatmap[y - top:y + bottom, x - left:x + right]
masked_gaussian = gaussian[radius - top:radius + bottom, radius - left:radius + right]
if min(masked_gaussian.shape) > 0 and min(masked_heatmap.shape) > 0: # TODO debug
np.maximum(masked_heatmap, masked_gaussian * k, out=masked_heatmap)
return heatmap
def draw_dense_reg(regmap, heatmap, center, value, radius, is_offset=False):
diameter = 2 * radius + 1
gaussian = gaussian2D((diameter, diameter), sigma=diameter / 6)
value = np.array(value, dtype=np.float32).reshape(-1, 1, 1)
dim = value.shape[0]
reg = np.ones((dim, diameter*2+1, diameter*2+1), dtype=np.float32) * value
if is_offset and dim == 2:
delta = np.arange(diameter*2+1) - radius
reg[0] = reg[0] - delta.reshape(1, -1)
reg[1] = reg[1] - delta.reshape(-1, 1)
x, y = int(center[0]), int(center[1])
height, width = heatmap.shape[0:2]
left, right = min(x, radius), min(width - x, radius + 1)
top, bottom = min(y, radius), min(height - y, radius + 1)
masked_heatmap = heatmap[y - top:y + bottom, x - left:x + right]
masked_regmap = regmap[:, y - top:y + bottom, x - left:x + right]
masked_gaussian = gaussian[radius - top:radius + bottom,
radius - left:radius + right]
masked_reg = reg[:, radius - top:radius + bottom,
radius - left:radius + right]
if min(masked_gaussian.shape) > 0 and min(masked_heatmap.shape) > 0: # TODO debug
idx = (masked_gaussian >= masked_heatmap).reshape(
1, masked_gaussian.shape[0], masked_gaussian.shape[1])
masked_regmap = (1-idx) * masked_regmap + idx * masked_reg
regmap[:, y - top:y + bottom, x - left:x + right] = masked_regmap
return regmap
def draw_msra_gaussian(heatmap, center, sigma):
tmp_size = sigma * 3
mu_x = int(center[0] + 0.5)
mu_y = int(center[1] + 0.5)
w, h = heatmap.shape[0], heatmap.shape[1]
ul = [int(mu_x - tmp_size), int(mu_y - tmp_size)]
br = [int(mu_x + tmp_size + 1), int(mu_y + tmp_size + 1)]
if ul[0] >= h or ul[1] >= w or br[0] < 0 or br[1] < 0:
return heatmap
size = 2 * tmp_size + 1
x = np.arange(0, size, 1, np.float32)
y = x[:, np.newaxis]
x0 = y0 = size // 2
g = np.exp(- ((x - x0) ** 2 + (y - y0) ** 2) / (2 * sigma ** 2))
g_x = max(0, -ul[0]), min(br[0], h) - ul[0]
g_y = max(0, -ul[1]), min(br[1], w) - ul[1]
img_x = max(0, ul[0]), min(br[0], h)
img_y = max(0, ul[1]), min(br[1], w)
heatmap[img_y[0]:img_y[1], img_x[0]:img_x[1]] = np.maximum(
heatmap[img_y[0]:img_y[1], img_x[0]:img_x[1]],
g[g_y[0]:g_y[1], g_x[0]:g_x[1]])
return heatmap
def grayscale(image):
return cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
def lighting_(data_rng, image, alphastd, eigval, eigvec):
alpha = data_rng.normal(scale=alphastd, size=(3, ))
image += np.dot(eigvec, eigval * alpha)
def blend_(alpha, image1, image2):
image1 *= alpha
image2 *= (1 - alpha)
image1 += image2
def saturation_(data_rng, image, gs, gs_mean, var):
alpha = 1. + data_rng.uniform(low=-var, high=var)
blend_(alpha, image, gs[:, :, None])
def brightness_(data_rng, image, gs, gs_mean, var):
alpha = 1. + data_rng.uniform(low=-var, high=var)
image *= alpha
def contrast_(data_rng, image, gs, gs_mean, var):
alpha = 1. + data_rng.uniform(low=-var, high=var)
blend_(alpha, image, gs_mean)
def color_aug(data_rng, image, eig_val, eig_vec):
functions = [brightness_, contrast_, saturation_]
random.shuffle(functions)
gs = grayscale(image)
gs_mean = gs.mean()
for f in functions:
f(data_rng, image, gs, gs_mean, 0.4)
lighting_(data_rng, image, 0.1, eig_val, eig_vec)