简介

imgaug安装

pip install six numpy scipy matplotlib scikit-image opencv-python imageio

pip install git+https://github.com/aleju/imgaug

pip install imgaug

Bounding Boxes实现

读取原影像bounding boxes坐标

def change_xml_annotation(root, image_id, new_target):
 new_xmin = new_target[0]
 new_ymin = new_target[1]
 new_xmax = new_target[2]
 new_ymax = new_target[3]
 in_file = open(os.path.join(root, str(image_id) + '.xml')) # 这里root分别由两个意思
 tree = ET.parse(in_file)
 xmlroot = tree.getroot()
 object = xmlroot.find('object')
 bndbox = object.find('bndbox')
 xmin = bndbox.find('xmin')
 xmin.text = str(new_xmin)
 ymin = bndbox.find('ymin')
 ymin.text = str(new_ymin)
 xmax = bndbox.find('xmax')
 xmax.text = str(new_xmax)
 ymax = bndbox.find('ymax')
 ymax.text = str(new_ymax)
 tree.write(os.path.join(root, str("%06d" % (str(id) + '.xml'))))

生成变换序列

# 影像增强
seq = iaa.Sequential([
 iaa.Flipud(0.5), # vertically flip 20% of all images
 iaa.Fliplr(0.5), # 镜像
 iaa.Multiply((1.2, 1.5)), # change brightness, doesn't affect BBs
 iaa.GaussianBlur(sigma=(0, 3.0)), # iaa.GaussianBlur(0.5),
 iaa.Affine(
 translate_px={"x": 15, "y": 15},
 scale=(0.8, 0.95),
 rotate=(-30, 30)
 ) # translate by 40/60px on x/y axis, and scale to 50-70%, affects BBs
])

bounding box 变化后坐标计算

seq_det = seq.to_deterministic() # 保持坐标和图像同步改变,而不是随机
# 读取图片
img = Image.open(os.path.join(IMG_DIR, name[:-4] + '.jpg'))
# sp = img.size
img = np.asarray(img)
# bndbox 坐标增强
for i in range(len(bndbox)):
 bbs = ia.BoundingBoxesOnImage([
 ia.BoundingBox(x1=bndbox[i][0], y1=bndbox[i][1], x2=bndbox[i][2], y2=bndbox[i][3]),
 ], shape=img.shape)
 bbs_aug = seq_det.augment_bounding_boxes([bbs])[0]
 boxes_img_aug_list.append(bbs_aug)
 # 此处运用了一个max,一个min (max是为了方式变化后的box小于1,min是为了防止变化后的box的坐标超出图片,在做faster r-cnn训练的时候,box的坐标会减1,若坐标小于1,就会报错,当然超出图像范围也会报错)
 n_x1 = int(max(1, min(img.shape[1], bbs_aug.bounding_boxes[0].x1)))
 n_y1 = int(max(1, min(img.shape[0], bbs_aug.bounding_boxes[0].y1)))
 n_x2 = int(max(1, min(img.shape[1], bbs_aug.bounding_boxes[0].x2)))
 n_y2 = int(max(1, min(img.shape[0], bbs_aug.bounding_boxes[0].y2)))
 if n_x1 == 1 and n_x1 == n_x2:
 n_x2 += 1
 if n_y1 == 1 and n_y2 == n_y1:
 n_y2 += 1
 if n_x1 >= n_x2 or n_y1 >= n_y2:
 print('error', name)
 new_bndbox_list.append([n_x1, n_y1, n_x2, n_y2])
# 存储变化后的图片
image_aug = seq_det.augment_images([img])[0]
path = os.path.join(AUG_IMG_DIR,
 str("%06d" % (len(files) + int(name[:-4]) + epoch * 250)) + '.jpg')
image_auged = bbs.draw_on_image(image_aug, thickness=0)
Image.fromarray(image_auged).save(path)
# 存储变化后的XML--此处可根据需要更改文件具体的名称
change_xml_list_annotation(XML_DIR, name[:-4], new_bndbox_list, AUG_XML_DIR,
 len(files) + int(name[:-4]) + epoch * 250)
print(str("%06d" % (len(files) + int(name[:-4]) + epoch * 250)) + '.jpg')
new_bndbox_list = []

使用示例

数据准备

设置文件路径

IMG_DIR = "../create-pascal-voc-dataset/examples/VOC2007/JPEGImages"
XML_DIR = "../create-pascal-voc-dataset/examples/VOC2007/Annotations"
AUG_XML_DIR = "./Annotations" # 存储增强后的XML文件夹路径
try:
 shutil.rmtree(AUG_XML_DIR)
except FileNotFoundError as e:
 a = 1
mkdir(AUG_XML_DIR)
AUG_IMG_DIR = "./JPEGImages" # 存储增强后的影像文件夹路径
try:
 shutil.rmtree(AUG_IMG_DIR)
except FileNotFoundError as e:
 a = 1
mkdir(AUG_IMG_DIR)

设置增强次数

 AUGLOOP = 10 # 每张影像增强的数量

设置增强参数

seq = iaa.Sequential([
 iaa.Flipud(0.5), # v翻转
 iaa.Fliplr(0.5), # 镜像
 iaa.Multiply((1.2, 1.5)), # 改变明亮度
 iaa.GaussianBlur(sigma=(0, 3.0)), # 高斯噪声
 iaa.Affine(
 translate_px={"x": 15, "y": 15},
 scale=(0.8, 0.95),
 rotate=(-30, 30)
 ) # translate by 40/60px on x/y axis, and scale to 50-70%, affects BBs
])

输出