前言：对于航拍、遥感影像数据集而言，此类数据集包含较多目标，且目标相对较小，直接进行目标检测往往效果不佳，此时对大分辨率图像做切割就是一个不错选择，也扩充了数据量。
~~~本文的切割思路是先将xml文件转换为dota格式的txt文件，然后利用dota切割方法对图像进行切割，最后再将切割后的文件转换为yolo格式的txt文件~~~
1、xml文件转换为dota格式的txt文件
# VOC标注格式为左上角与右下角坐标
# 这个文件直接将标注框左上角与右下角坐标转换为四个角的坐标（顺时针）
import xml.etree.ElementTree as ET
import pickle
import os
import os.path
from os import listdir, getcwd
from os.path import join
sets = ['train', 'test', 'val']
classes = ['num0', 'num1', 'num2', 'num3', 'num4', 'num5', 'num6', 'num7', 'num8', 'num9']
def convert_annotation(image_id):
if os.path.isfile('datasets/mydata/Annotations/%s.xml' % (image_id)):
in_file = open('datasets/mydata/Annotations/%s.xml' % (image_id))
out_file = open('datasets/mydata/labels/%s.txt' % (image_id), 'w')
tree = ET.parse(in_file)
root = tree.getroot()
size = root.find('size')
w = int(size.find('width').text)
h = int(size.find('height').text)
for obj in root.iter('object'):
difficult = obj.find('difficult').text
cls = obj.find('name').text
if cls not in classes or int(difficult) == 1:
continue
# cls_id = classes.index(cls)
xmlbox = obj.find('bndbox')
# 注意dota数据格式四个角点的坐标是顺时针分布的
x0 = int(float(xmlbox.find('xmin').text))
y0 = int(float(xmlbox.find('ymin').text))
x1 = int(float(xmlbox.find('xmax').text))
y1 = int(float(xmlbox.find('ymin').text))
x2 = int(float(xmlbox.find('xmax').text))
y2 = int(float(xmlbox.find('ymax').text))
x3 = int(float(xmlbox.find('xmin').text))
y3 = int(float(xmlbox.find('ymax').text))
out_file.write("{} {} {} {} {} {} {} {} {} {}\n".format(x0, y0, x1, y1, x2, y2, x3, y3, cls, difficult))
wd = getcwd()
print(wd)
for image_set in sets:
if not os.path.exists('datasets/mydata/labels/'):
os.makedirs('datasets/mydata/labels/')
image_ids = open('datasets/mydata/%s.txt' % (image_set)).read().strip().split()
list_file = open('datasets/mydata/%s.txt' % (image_set), 'w')
for image_id in image_ids:
list_file.write('datasets/mydata/images/%s.jpg\n' % (image_id))
convert_annotation(image_id)
list_file.close()
#数据存放格式
#|——根目录
# |——datasets
# |——dota_images
# |——dota_labels
# |——yolo_labels
# |——mydata
# |——Annotations
# |——images
# |——labels
# test.txt
# train.txt
# val.txt 
2、图像切割
import cv2
import os
# 图像宽不足裁剪宽度,填充至裁剪宽度
def fill_right(img, size_w):
size = img.shape
# 填充值为数据集均值
img_fill_right = cv2.copyMakeBorder(img, 0, 0, 0, size_w - size[1],
cv2.BORDER_CONSTANT, value = (107, 113, 115))
return img_fill_right
# 图像高不足裁剪高度,填充至裁剪高度
def fill_bottom(img, size_h):
size = img.shape
img_fill_bottom = cv2.copyMakeBorder(img, 0, size_h - size[0], 0, 0,
cv2.BORDER_CONSTANT, value = (107, 113, 115))
return img_fill_bottom
# 图像宽高不足裁剪宽高度,填充至裁剪宽高度
def fill_right_bottom(img, size_w, size_h):
size = img.shape
img_fill_right_bottom = cv2.copyMakeBorder(img, 0, size_h - size[0], 0, size_w - size[1],
cv2.BORDER_CONSTANT, value = (107, 113, 115))
return img_fill_right_bottom
# 图像切割
# img_floder 图像文件夹
# out_img_floder 图像切割输出文件夹
# size_w 切割图像宽
# size_h 切割图像高
# step 切割步长
# 不管输入图片是什么格式，切割出来的图片都为.bmp格式（可自行设置）
def image_split(img_floder, out_img_floder, size_w, size_h, step):
img_list = os.listdir(img_floder)
# print(img_list)
count = 0
for img_name in img_list:
number = 0
# 去除.png后缀
name = img_name[:-4]
img = cv2.imread(img_floder + "\\" + img_name)
size = img.shape
# 若图像宽高大于切割宽高
if size[0] >= size_h and size[1] >= size_w:
count = count + 1
for h in range(0, size[0] - 1, step):
start_h = h
for w in range(0, size[1] - 1, step):
start_w = w
end_h = start_h + size_h
if end_h > size[0]:
start_h = size[0] - size_h
end_h = start_h + size_h
end_w = start_w + size_w
if end_w > size[1]:
start_w = size[1] - size_w
end_w = start_w + size_w
cropped = img[start_h : end_h, start_w : end_w]
# 用起始坐标来命名切割得到的图像，为的是方便后续标签数据抓取
name_img = name + '_'+ str(start_h) +'_' + str(start_w)
cv2.imwrite('{}/{}.bmp'.format(out_img_floder, name_img), cropped)
number = number + 1
# 若图像高大于切割高,但宽小于切割宽
elif size[0] >= size_h and size[1] < size_w:
print('图片{}需要在右面补齐'.format(name))
count = count + 1
img0 = fill_right(img, size_w)
for h in range(0, size[0] - 1, step):
start_h = h
start_w = 0
end_h = start_h + size_h
if end_h > size[0]:
start_h = size[0] - size_h
end_h = start_h + size_h
end_w = start_w + size_w
cropped = img0[start_h : end_h, start_w : end_w]
name_img = name + '_' + str(start_h) + '_' + str(start_w)
cv2.imwrite('{}/{}.bmp'.format(out_img_floder, name_img), cropped)
number = number + 1
# 若图像宽大于切割宽,但高小于切割高
elif size[0] < size_h and size[1] >= size_w:
count = count + 1
print('图片{}需要在下面补齐'.format(name))
img0 = fill_bottom(img, size_h)
for w in range(0, size[1] - 1, step):
start_h = 0
start_w = w
end_w = start_w + size_w
if end_w > size[1]:
start_w = size[1] - size_w
end_w = start_w + size_w
end_h = start_h + size_h
cropped = img0[start_h : end_h, start_w : end_w]
name_img = name + '_'+ str(start_h) +'_' + str(start_w)
cv2.imwrite('{}/{}.bmp'.format(out_img_floder, name_img), cropped)
number = number + 1
# 若图像宽高小于切割宽高
elif size[0] < size_h and size[1] < size_w:
count = count + 1
print('图片{}需要在下面和右面补齐'.format(name))
img0 = fill_right_bottom(img, size_w, size_h)
cropped = img0[0 : size_h, 0 : size_w]
name_img = name + '_'+ '0' +'_' + '0'
cv2.imwrite('{}/{}.bmp'.format(out_img_floder, name_img), cropped)
number = number + 1
print('{}.bmp切割成{}张.'.format(name,number))
print('共完成{}张图片'.format(count))
# txt切割
# out_img_floder 图像切割输出文件夹
# txt_floder txt文件夹
# out_txt_floder txt切割输出文件夹
# size_w 切割图像宽
# size_h 切割图像高
def txt_split(out_img_floder, txt_floder, out_txt_floder, size_h, size_w):
img_list = os.listdir(out_img_floder)
for img_name in img_list:
# 去除.png后缀
name = img_name[:-4]
# 得到原图像(也即txt)索引 + 切割高 + 切割宽
name_list = name.split('_')
# 易报错之处，此处需要跟据图片的具体名称来改
txt_name = name_list[0] + '_' + name_list[1]
h = int(name_list[2])
w = int(name_list[3])
# txt_name = name_list[0]
# h = int(name_list[1])
# w = int(name_list[2])
txtpath = txt_floder + "\\" + txt_name + '.txt'
out_txt_path = out_txt_floder + "\\" + name + '.txt'
f = open(out_txt_path, 'a')
# 打开txt文件
with open(txtpath, 'r') as f_in:
lines = f_in.readlines()
# 逐行读取
for line in lines:
splitline = line.split(' ')
label = splitline[8]
difficult = splitline[9]
x1 = int(float(splitline[0]))
y1 = int(float(splitline[1]))
x2 = int(float(splitline[2]))
y2 = int(float(splitline[3]))
x3 = int(float(splitline[4]))
y3 = int(float(splitline[5]))
x4 = int(float(splitline[6]))
y4 = int(float(splitline[7]))
if w <= x1 <= w + size_w and w <= x2 <= w + size_w and \
w <= x3 <= w + size_w and w <= x4 <= w + size_w and \
h <= y1 <= h + size_h and h <= y2 <= h + size_h and \
h <= y3 <= h + size_h and h <= y4 <= h + size_h:
f.write('{} {} {} {} {} {} {} {} {} {}'.format(int(x1 - w),
int(y1 - h), int(x2 - w), int(y2 - h), int(x3 - w),
int(y3 - h), int(x4 - w), int(y4 - h),
label, difficult))
f.close()
# print('{}.txt切割完成.'.format(name))
print('txt切割完成')
# 图像数据集文件夹
img_floder = r'D:\cnn\yolov5-6.10\datasets\mydata\images'
# 切割得到的图像数据集存放文件夹
out_img_floder = r'D:\cnn\yolov5-6.10\datasets\dota_images'
# txt数据集文件夹
txt_floder = r'D:\cnn\yolov5-6.10\datasets\mydata\labels'
# 切割后数据集的标签文件存放文件夹
out_txt_floder = r'D:\cnn\yolov5-6.10\datasets\dota_labels'
# 此为切割出来的图像宽
size_w = 640
# 此为切割出来的图像高
size_h = 640
# 切割步长,重叠度为size_w - step
step = 540
image_split(img_floder, out_img_floder, size_w, size_h, step)
txt_split(out_img_floder, txt_floder, out_txt_floder, size_h, size_w)
# 清除未包含标注框的图片和txt文件
txt_lists = os.listdir(out_txt_floder) # 读取输出的txt文件
j = 0
for txt_list in txt_lists:
# print(txt_list)
name = txt_list[:-4] # 去除.txt后缀
# print(name)
data = open(r'D:\cnn\yolov5-6.10\datasets\dota_labels\{}'.format(txt_list)).read()
if len(data) == 0:
j = j + 1
# print("{}文件为空！".format(txt_list))
# os.remove('D:\cnn\yolov5-6.10\datasets\dota_labels')
path1 = r'D:\cnn\yolov5-6.10\datasets\dota_labels\{}'.format(txt_list)
os.remove(path1) # 删除空的txt文件
path2 = r'D:\cnn\yolov5-6.10\datasets\dota_images\{}'.format(name + '.bmp')
os.remove(path2) # 删除对应的没有标注框的图片
print('共{}个txt文件为空'.format(j))
#数据存放格式
#|——根目录
# |——datasets
# |——dota_images
# |——dota_labels
# |——yolo_labels
# |——mydata
# |——Annotations
# |——images
# |——labels
# test.txt
# train.txt
# val.txt 运行完后会在dota_images和dota_labels文件夹中生成切割后的图片和txt文件。
3、将dota格式的txt文件转换为yolo格式的txt文件
import os
classes = ['num0', 'num1', 'num2', 'num3', 'num4', 'num5', 'num6', 'num7', 'num8', 'num9']
path = "D:\cnn\yolov5-6.10\datasets\dota_labels" # dota格式txt文件所在目录
yolo_label = 'D:\cnn\yolov5-6.10\datasets\yolo_labels' # yolo格式txt文件保存目录
label_lists = os.listdir(path) # 得到文件夹下的所有文件名称
for label_list in label_lists: # 遍历文件夹
out_txt_path = yolo_label + "\\" + label_list # 构造输出绝对路径，label_list为txt文件名称，即保证文件命名不变
position = path + '\\' + label_list # 构造绝对路径，"\\"，其中一个'\'为转义符
# print(position)
with open(position, 'r') as f: # 打开文件
lines = f.readlines() # 逐行读取文件
file = open(out_txt_path, 'w') # 写入
nums = len(lines) # 总共有多少行
for i in range(nums): # 遍历每一行
values = lines[i]
value = values.split(' ')
# 因为dota格式四个角为顺时针，转为yolo格式需要取出其左上角和右下角
xmin = float(value[0])
ymin = float(value[1])
xmax = float(value[4])
ymax = float(value[5])
x = (xmin + xmax) / 2.0 # 标注框中心点x坐标
y = (ymin + ymax) / 2.0 # 标注框中心点y坐标
w = xmax - xmin # 标注框宽
h = ymax - ymin # 标注框高
# 归一化处理
d = 1. / 640 # 归一化处理，此处切割出来的图片宽高都是640
x = x * d
w = w * d
y = y * d
h = h * d
cls = value[8]
cls_id = classes.index(cls)
file.write('{} {} {} {} {}\n'.format(cls_id, x, y, w, h))
tips：一定要记得归一化，因为yolo格式是要求归一化后的坐标，格式为cls_id, x, y, w, h！！！
至此，就得到了用于yolo训练的切割数据集！！！
4、将yolo格式的txt文件转换为xml文件，此时可以用labelimg查看切割效果
import os
import glob
from PIL import Image
dota_labels = r'D:\cnn\yolov5-6.10\datasets\dota_labels' # dota格式下的存放txt标注文件的文件夹
# 这里将图片和xml文件存放在一个文件夹中，方便后续使用labelimg查看
xml_labels = r'D:\cnn\yolov5-6.10\datasets\dota_images' # 转换后储存xml的文件夹地址
dota_images = r'D:\cnn\yolov5-6.10\datasets\dota_images' # 存放图片的文件夹
labels = ['num0', 'num1', 'num2', 'num3', 'num4', 'num5', 'num6', 'num7', 'num8', 'num9']
src_img_dir = dota_images
src_txt_dir = dota_labels
src_xml_dir = xml_labels # 转换后储存xml的文件夹地址
img_lists = glob.glob(src_img_dir + '/*.bmp')
img_basenames = []
for item in img_lists:
img_basenames.append(os.path.basename(item)) # os.path.basename返回path最后的文件名
img_names = []
for item in img_basenames:
temp1, temp2 = os.path.splitext(item) # os.path.splitext(“文件路径”) 分离文件名与扩展名
img_names.append(temp1)
total_num = len(img_names) # 统计当前总共要转换的图片标注数量
count = 0 # 技术变量
for img in img_names: # 这里的img是不加后缀的图片名称
count += 1
if count % 1000 == 0:
print("当前转换进度{}/{}".format(count, total_num))
im = Image.open((src_img_dir + '/' + img + '.bmp'))
width, height = im.size
# 打开yolo格式下的txt文件
gt = open(src_txt_dir + '/' + img + '.txt').read().splitlines()
if gt:
# 将主干部分写入xml文件中
xml_file = open((src_xml_dir + '/' + img + '.xml'), 'w')
xml_file.write('<annotation>\n')
xml_file.write(' <folder>VOC2007</folder>\n')
xml_file.write(' <filename>' + str(img) + '.bmp' + '</filename>\n')
xml_file.write(' <size>\n')
xml_file.write(' <width>' + str(width) + '</width>\n')
xml_file.write(' <height>' + str(height) + '</height>\n')
xml_file.write(' <depth>3</depth>\n')
xml_file.write(' </size>\n')
# write the region of image on xml file
for img_each_label in gt:
spt = img_each_label.split(' ') # 这里如果txt里面是以逗号‘，’隔开的，那么就改为spt = img_each_label.split(',')。
xml_file.write(' <object>\n')
xml_file.write(' <name>' + spt[8] + '</name>\n')
xml_file.write(' <pose>Unspecified</pose>\n')
xml_file.write(' <truncated>0</truncated>\n')
xml_file.write(' <difficult>0</difficult>\n')
xml_file.write(' <bndbox>\n')
xmin = str(float(spt[0]))
ymin = str(float(spt[1]))
xmax = str(float(spt[4]))
ymax = str(float(spt[5]))
xml_file.write(' <xmin>' + xmin + '</xmin>\n')
xml_file.write(' <ymin>' + ymin + '</ymin>\n')
xml_file.write(' <xmax>' + xmax + '</xmax>\n')
xml_file.write(' <ymax>' + ymax + '</ymax>\n')
xml_file.write(' </bndbox>\n')
xml_file.write(' </object>\n')
xml_file.write('</annotation>')
else:
# 将主干部分写入xml文件中
xml_file = open((src_xml_dir + '/' + img + '.xml'), 'w')
xml_file.write('<annotation>\n')
xml_file.write(' <folder>VOC2007</folder>\n')
xml_file.write(' <filename>' + str(img) + '.bmp' + '</filename>\n')
xml_file.write(' <size>\n')
xml_file.write(' <width>' + str(width) + '</width>\n')
xml_file.write(' <height>' + str(height) + '</height>\n')
xml_file.write(' <depth>3</depth>\n')
xml_file.write(' </size>\n')
xml_file.write('</annotation>')使用labelimg打开dota_images文件夹就可以查看切割后的效果啦！！！