forked from pprp/SimpleCVReproduction
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathaug.py
196 lines (165 loc) · 7.24 KB
/
aug.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
# import glob
import cv2 as cv2
import numpy as np
# from PIL import Image
import random
import math
from os.path import basename, split, join, dirname
from util import *
def find_str(filename):
if 'train' in filename:
return dirname(filename[filename.find('train'):])
else:
return dirname(filename[filename.find('val'):])
def convert_all_boxes(shape, anno_infos, yolo_label_txt_dir):
height, width, n = shape
label_file = open(yolo_label_txt_dir, 'w')
for anno_info in anno_infos:
target_id, x1, y1, x2, y2 = anno_info
b = (float(x1), float(x2), float(y1), float(y2))
bb = convert((width, height), b)
label_file.write(
str(target_id) + " " + " ".join([str(a) for a in bb]) + '\n')
def save_crop_image(save_crop_base_dir, image_dir, idx, roi):
crop_save_dir = join(save_crop_base_dir, find_str(image_dir))
check_dir(crop_save_dir)
crop_img_save_dir = join(
crop_save_dir,
basename(image_dir)[:-3] + '_crop_' + str(idx) + '.jpg')
cv2.imwrite(crop_img_save_dir, roi)
def copysmallobjects(image_dir,
label_dir,
save_base_dir,
save_crop_base_dir=None,
save_annoation_base_dir=None):
image = cv2.imread(image_dir)
labels = read_label_txt(label_dir)
if len(labels) == 0: return
rescale_labels = rescale_yolo_labels(labels, image.shape) # 转换坐标表示
all_boxes = []
for idx, rescale_label in enumerate(rescale_labels):
all_boxes.append(rescale_label)
# 目标的长宽
rescale_label_height, rescale_label_width = rescale_label[4] - rescale_label[2], rescale_label[3] - \
rescale_label[1]
if (issmallobject(
(rescale_label_height, rescale_label_width), thresh=64 * 64)
and rescale_label[0] == '1'):
roi = image[rescale_label[2]:rescale_label[4], rescale_label[1]:
rescale_label[3]]
new_bboxes = random_add_patches(rescale_label,
rescale_labels,
image.shape,
paste_number=2,
iou_thresh=0.2)
count = 0
# 将新生成的位置加入到label,并在相应位置画出物体
for new_bbox in new_bboxes:
count += 1
all_boxes.append(new_bbox)
cl, bbox_left, bbox_top, bbox_right, bbox_bottom = new_bbox[0], new_bbox[1], new_bbox[2], new_bbox[3], \
new_bbox[4]
try:
if (count > 1):
roi = flip_bbox(roi)
image[bbox_top:bbox_bottom, bbox_left:bbox_right] = roi
except ValueError:
continue
dir_name = find_str(image_dir)
save_dir = join(save_base_dir, dir_name)
check_dir(save_dir)
yolo_txt_dir = join(save_dir,
basename(image_dir.replace('.jpg', '_aug.txt')))
cv2.imwrite(
join(save_dir,
basename(image_dir).replace('.jpg', '_aug.jpg')), image)
convert_all_boxes(image.shape, all_boxes, yolo_txt_dir)
def GaussianBlurImg(image):
# 高斯模糊
ran = random.randint(0, 9)
if ran % 2 == 1:
image = cv2.GaussianBlur(image, ksize=(ran, ran), sigmaX=0, sigmaY=0)
else:
pass
return image
def suo_fang(image, area_max=2000, area_min=1000):
# 改变图片大小
height, width, channels = image.shape
while (height * width) > area_max:
image = cv2.resize(image, (int(width * 0.9), int(height * 0.9)))
height, width, channels = image.shape
height, width = int(height * 0.9), int(width * 0.9)
while (height * width) < area_min:
image = cv2.resize(image, (int(width * 1.1), int(height * 1.1)))
height, width, channels = image.shape
height, width = int(height * 1.1), int(width * 1.1)
return image
def copysmallobjects2(image_dir, label_dir, save_base_dir, small_img_dir,
times):
image = cv2.imread(image_dir)
labels = read_label_txt(label_dir)
if len(labels) == 0:
return
# 转化为x1y1x2y2
rescale_labels = rescale_yolo_labels(labels, image.shape) # 转换坐标表示
all_boxes = []
for _, rescale_label in enumerate(rescale_labels):
all_boxes.append(rescale_label)
for small_img_dirs in small_img_dir:
# print(small_img_dir)
image_bbox = cv2.imread(small_img_dirs)
#roi = image_bbox
# TODO
# from 3000 to 1500
roi = suo_fang(image_bbox, area_max=1000, area_min=200)
new_bboxes = random_add_patches2(roi.shape,
rescale_labels,
image.shape,
paste_number=1,
iou_thresh=0)
count = 0
# print("end patch")
for new_bbox in new_bboxes:
count += 1
cl, bbox_left, bbox_top, bbox_right, bbox_bottom = new_bbox[0], new_bbox[1], new_bbox[2], new_bbox[3], \
new_bbox[4]
#roi = GaussianBlurImg(roi) # 高斯模糊
height, width, channels = roi.shape
center = (int(width / 2), int(height / 2))
#ran_point = (int((bbox_top+bbox_bottom)/2),int((bbox_left+bbox_right)/2))
mask = 255 * np.ones(roi.shape, roi.dtype)
# print("before try")
try:
if count > 1:
roi = flip_bbox(roi)
#image[bbox_top:bbox_bottom, bbox_left:bbox_right] = roi
#image[bbox_top:bbox_bottom, bbox_left:bbox_right] = cv2.addWeighted(image[bbox_top:bbox_bottom, bbox_left:bbox_right],
# 0.5,roi,0.5,0) #图片融合
# 泊松融合
#image = cv2.seamlessClone(roi, image, mask, ran_point, cv2.NORMAL_CLONE)
#print(str(bbox_bottom-bbox_top) + "|" + str(bbox_right-bbox_left))
#print(roi.shape)
#print(mask.shape)
image[bbox_top:bbox_bottom, bbox_left:
bbox_right] = cv2.seamlessClone(
roi,
image[bbox_top:bbox_bottom, bbox_left:bbox_right],
mask, center, cv2.NORMAL_CLONE)
all_boxes.append(new_bbox)
rescale_labels.append(new_bbox)
# print("end try")
except ValueError:
print("---")
continue
# print("end for")
dir_name = find_str(image_dir)
save_dir = join(save_base_dir, dir_name)
check_dir(save_dir)
yolo_txt_dir = join(
save_dir,
basename(image_dir.replace('.jpg', '_aug_%s.txt' % str(times))))
cv2.imwrite(
join(save_dir,
basename(image_dir).replace('.jpg', '_aug_%s.jpg' % str(times))),
image)
convert_all_boxes(image.shape, all_boxes, yolo_txt_dir)