voc数据集对有标签的数据集数据增强

安装依赖库和imgaug库

在训练yolo的时候，对已有数据集已经打好了标签，想要进行数据的增强（数据扩增），可以通过imgaug实现对图片和标签中的boundingbox同时变换。
imgaug使用文档
代码下载：https://github.com/CodingWZP/image_augmentation
首先，安装依赖库。

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

安装imgaug

pip install imgaug

Bounding Boxes实现

读取原影像bounding boxes坐标

读取xml文件并使用ElementTree对xml文件进行解析，找到每个object的坐标值。

def change_xml_list_annotation(root, image_id, new_target, saveroot, id):
    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)
    #修改增强后的xml文件中的filename
    elem = tree.find('filename')
    elem.text = (str(id) + '.jpg')
    xmlroot = tree.getroot()
    #修改增强后的xml文件中的path
    elem = tree.find('path')
    if elem != None:
        elem.text = (saveroot + str(id) + '.jpg')

    index = 0
    for object in xmlroot.findall('object'):  # 找到root节点下的所有country节点
        bndbox = object.find('bndbox')  # 子节点下节点rank的值

        # xmin = int(bndbox.find('xmin').text)
        # xmax = int(bndbox.find('xmax').text)
        # ymin = int(bndbox.find('ymin').text)
        # ymax = int(bndbox.find('ymax').text)

        new_xmin = new_target[index][0]
        new_ymin = new_target[index][1]
        new_xmax = new_target[index][2]
        new_ymax = new_target[index][3]

        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)

        index = index + 1

    tree.write(os.path.join(saveroot, str(id + '.xml')))

生成变换序列

产生一个处理图片的Sequential。

# 影像增强
    seq = iaa.Sequential([
        iaa.Invert(0.5),
        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),
        )  # translate by 40/60px on x/y axis, and scale to 50-70%, affects BBs
    ])

bounding box 变化后坐标计算

先读取该影像对应xml文件，获取所有目标的bounding boxes，然后依次计算每个box变化后的坐标。

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)

    # new_bndbox_list:[[x1,y1,x2,y2],...[],[]]
    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(str(name[:-4]) + '_' + str(epoch)) + '.jpg')
image_auged = bbs.draw_on_image(image_aug, thickness=0)
Image.fromarray(image_auged).save(path)

# 存储变化后的XML
change_xml_list_annotation(XML_DIR, name[:-4], new_bndbox_list, AUG_XML_DIR,
                           str(name[:-4]) + '_' + str(epoch))
# print(str(str(name[:-4]) + '_' + str(epoch)) + '.jpg')
new_bndbox_list = []

使用示例

数据准备

输入数据为两个文件夹一个是需要增强的影像数据（JPEGImages），一个是对应的xml文件（Annotations）。注意：影像文件名需和xml文件名相对应！

设置文件路径

IMG_DIR = "./JPEGImages"
XML_DIR = "./Annotations"

AUG_XML_DIR = "./AUG/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 = "./AUG/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

通过修改Sequential函数参数进行设置，具体设置参考imgaug使用文档

seq = iaa.Sequential([
    iaa.Invert(0.5),
    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),
    )  # translate by 40/60px on x/y axis, and scale to 50-70%, affects BBs
])

修改xml文件中filename和path

tree = ET.parse(in_file)
#修改增强后的xml文件中的filename
elem = tree.find('filename')
elem.text = (str(id) + '.jpg')
xmlroot = tree.getroot()
#修改增强后的xml文件中的path
elem = tree.find('path')
if elem != None:
    elem.text = (saveroot + str(id) + '.jpg')

输出

运行augmentation.py ，运行结束后即可得到增强的影像和对应的xml文件夹。

完整代码

'''
Author: CodingWZP
Email: [email protected]
Date: 2021-08-06 10:51:35
LastEditTime: 2021-08-09 10:53:43
Description: Image augmentation with label.
'''
import xml.etree.ElementTree as ET
import os
import imgaug as ia
import numpy as np
import shutil
from tqdm import tqdm
from PIL import Image
from imgaug import augmenters as iaa


ia.seed(1)


def read_xml_annotation(root, image_id):
    in_file = open(os.path.join(root, image_id))
    tree = ET.parse(in_file)
    root = tree.getroot()
    bndboxlist = []

    for object in root.findall('object'):  # 找到root节点下的所有country节点
        bndbox = object.find('bndbox')  # 子节点下节点rank的值

        xmin = int(bndbox.find('xmin').text)
        xmax = int(bndbox.find('xmax').text)
        ymin = int(bndbox.find('ymin').text)
        ymax = int(bndbox.find('ymax').text)
        # print(xmin,ymin,xmax,ymax)
        bndboxlist.append([xmin, ymin, xmax, ymax])
        # print(bndboxlist)

    bndbox = root.find('object').find('bndbox')
    return bndboxlist


def change_xml_list_annotation(root, image_id, new_target, saveroot, id):
    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)
    #修改增强后的xml文件中的filename
    elem = tree.find('filename')
    elem.text = (str(id) + '.jpg')
    xmlroot = tree.getroot()
    #修改增强后的xml文件中的path
    elem = tree.find('path')
    if elem != None:
        elem.text = (saveroot + str(id) + '.jpg')

    index = 0
    for object in xmlroot.findall('object'):  # 找到root节点下的所有country节点
        bndbox = object.find('bndbox')  # 子节点下节点rank的值

        # xmin = int(bndbox.find('xmin').text)
        # xmax = int(bndbox.find('xmax').text)
        # ymin = int(bndbox.find('ymin').text)
        # ymax = int(bndbox.find('ymax').text)

        new_xmin = new_target[index][0]
        new_ymin = new_target[index][1]
        new_xmax = new_target[index][2]
        new_ymax = new_target[index][3]

        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)

        index = index + 1

    tree.write(os.path.join(saveroot, str(id + '.xml')))


def mkdir(path):
    # 去除首位空格
    path = path.strip()
    # 去除尾部 \ 符号
    path = path.rstrip("\\")
    # 判断路径是否存在
    # 存在     True
    # 不存在   False
    isExists = os.path.exists(path)
    # 判断结果
    if not isExists:
        # 如果不存在则创建目录
        # 创建目录操作函数
        os.makedirs(path)
        print(path + ' 创建成功')
        return True
    else:
        # 如果目录存在则不创建，并提示目录已存在
        print(path + ' 目录已存在')
        return False


if __name__ == "__main__":

    IMG_DIR = "./JPEGImages/"
    XML_DIR = "./Annotations/"

    AUG_XML_DIR = "./AUG/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 = "./AUG/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)

    AUGLOOP = 5  # 每张影像增强的数量

    boxes_img_aug_list = []
    new_bndbox = []
    new_bndbox_list = []

    # 影像增强
    seq = iaa.Sequential([
        iaa.Invert(0.5),
        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),
        )  # translate by 40/60px on x/y axis, and scale to 50-70%, affects BBs
    ])

    for name in tqdm(os.listdir(XML_DIR), desc='Processing'):

        bndbox = read_xml_annotation(XML_DIR, name)
        
        # 保存原xml文件
        shutil.copy(os.path.join(XML_DIR, name), AUG_XML_DIR)
        # 保存原图
        og_img = Image.open(IMG_DIR+'/'+name[:-4] + '.jpg')
        og_img.convert('RGB').save(AUG_IMG_DIR + name[:-4] + '.jpg', 'JPEG')
        og_xml = open(os.path.join(XML_DIR, name)) 
        tree = ET.parse(og_xml)
        #修改增强后的xml文件中的filename
        elem = tree.find('filename')
        elem.text = (name[:-4] + '.jpg')
        tree.write(os.path.join(AUG_XML_DIR, name))


        for epoch in range(AUGLOOP):
            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)

                # new_bndbox_list:[[x1,y1,x2,y2],...[],[]]
                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(str(name[:-4]) + '_' + str(epoch)) + '.jpg')
            image_auged = bbs.draw_on_image(image_aug, size=0)
            Image.fromarray(image_auged).convert('RGB').save(path) 

            # 存储变化后的XML
            change_xml_list_annotation(XML_DIR, name[:-4], new_bndbox_list, AUG_XML_DIR,
                                        str(name[:-4]) + '_' + str(epoch))
            # print(str(str(name[:-4]) + '_' + str(epoch)) + '.jpg')
            new_bndbox_list = []
    print('Finish!')