VOC2007格式语义分割和目标检测数据集的转换、数据增强

最新推荐文章于 2024-07-23 14:36:35 发布

whaterverittakes

最新推荐文章于 2024-07-23 14:36:35 发布

阅读量590

点赞数 1

文章标签：目标检测人工智能计算机视觉

本文链接：https://blog.csdn.net/whaterverittakes/article/details/132733285

版权

前言

之前做的都是语义分割的数据集，在项目中想转换思路来跑一下目标检测的效果，在转的过程中发现语义分割的数据集(以VOC2007为例)中的原始图像跟标签图像为JPG、PNG格式，而目标检测的数据集(VOC2007)所需要的原始图像跟标签图像为JPG、XML格式。

数据集标注

本文中所用到的标注方法为labelme，而labelme所制作的标签图像为json文件格式，所以需要做转换，不过labelme官方文档中给到了label2voc的文件，此文件可以直接生成语义分割所需要的VOC数据集格式。

JSON->XML

既然不能直接移植，那就对原始的JSON文件进行转换，转换成我们需要的XML格式的标签文件。代码如下：

import os
from typing import List, Any
import numpy as np
import codecs
import json
from glob import glob
import cv2
import shutil
from sklearn.model_selection import train_test_split

# 1.标签路径
labelme_path = "./labels/"
# 原始labelme标注数据路径
saved_path = "./VOC2007/"
# 保存路径
isUseTest = True  # 是否创建test集
# 2.创建要求文件夹
if not os.path.exists(saved_path + "Annotations"):
    os.makedirs(saved_path + "Annotations")
if not os.path.exists(saved_path + "JPEGImages/"):
    os.makedirs(saved_path + "JPEGImages/")
if not os.path.exists(saved_path + "ImageSets/Main/"):
    os.makedirs(saved_path + "ImageSets/Main/")
# 3.获取待处理文件
files = glob(labelme_path + "*.json")
files = [i.replace("\\", "/").split("/")[-1].split(".json")[0] for i in files]
print(files)
# 4.读取标注信息并写入 xml
for json_file_ in files:
    json_filename = labelme_path + json_file_ + ".json"
    json_file = json.load(open(json_filename, "r", encoding="utf-8"))
    height, width, channels = cv2.imread('./images/' + json_file_ + ".jpg").shape
    # 注意如果报错noshape, 需要查看自己存放原始图片的路径文件夹是否为images
    with codecs.open(saved_path + "Annotations/" + json_file_ + ".xml", "w", "utf-8") as xml:

        xml.write('<annotation>\n')
        xml.write('\t<folder>' + 'WH_data' + '</folder>\n')
        xml.write('\t<filename>' + json_file_ + ".jpg" + '</filename>\n')
        xml.write('\t<source>\n')
        xml.write('\t\t<database>WH Data</database>\n')
        xml.write('\t\t<annotation>WH</annotation>\n')
        xml.write('\t\t<image>flickr</image>\n')
        xml.write('\t\t<flickrid>NULL</flickrid>\n')
        xml.write('\t</source>\n')
        xml.write('\t<owner>\n')
        xml.write('\t\t<flickrid>NULL</flickrid>\n')
        xml.write('\t\t<name>WH</name>\n')
        xml.write('\t</owner>\n')
        xml.write('\t<size>\n')
        xml.write('\t\t<width>' + str(width) + '</width>\n')
        xml.write('\t\t<height>' + str(height) + '</height>\n')
        xml.write('\t\t<depth>' + str(channels) + '</depth>\n')
        xml.write('\t</size>\n')
        xml.write('\t\t<segmented>0</segmented>\n')
        for multi in json_file["shapes"]:
            points = np.array(multi["points"])
            labelName = multi["label"]
            xmin = min(points[:, 0])
            xmax = max(points[:, 0])
            ymin = min(points[:, 1])
            ymax = max(points[:, 1])
            label = multi["label"]
            if xmax <= xmin:
                pass
            elif ymax <= ymin:
                pass
            else:
                xml.write('\t<object>\n')
                xml.write('\t\t<name>' + labelName + '</name>\n')
                xml.write('\t\t<pose>Unspecified</pose>\n')
                xml.write('\t\t<truncated>1</truncated>\n')
                xml.write('\t\t<difficult>0</difficult>\n')
                xml.write('\t\t<bndbox>\n')
                xml.write('\t\t\t<xmin>' + str(int(xmin)) + '</xmin>\n')
                xml.write('\t\t\t<ymin>' + str(int(ymin)) + '</ymin>\n')
                xml.write('\t\t\t<xmax>' + str(int(xmax)) + '</xmax>\n')
                xml.write('\t\t\t<ymax>' + str(int(ymax)) + '</ymax>\n')
                xml.write('\t\t</bndbox>\n')
                xml.write('\t</object>\n')
                print(json_filename, xmin, ymin, xmax, ymax, label)
        xml.write('</annotation>')
# 5.复制图片到 VOC2007/JPEGImages/下
image_files = glob("./images/" + "*.jpg")
print("copy image files to VOC007/JPEGImages/")
for image in image_files:
    shutil.copy(image, saved_path + "JPEGImages/")
# 6.split files for txt
txtsavepath = saved_path + "ImageSets/Main/"
ftrainval = open(txtsavepath + '/trainval.txt', 'w')
ftest = open(txtsavepath + '/test.txt', 'w')
ftrain = open(txtsavepath + '/train.txt', 'w')
fval = open(txtsavepath + '/val.txt', 'w')
total_files = glob("./VOC2007/Annotations/*.xml")
total_files = [i.replace("\\", "/").split("/")[-1].split(".xml")[0] for i in total_files]
trainval_files = []
test_files = []
if isUseTest:
    trainval_files, test_files = train_test_split(total_files, test_size=0.15, random_state=55)
else:
    trainval_files = total_files
for file in trainval_files:
    ftrainval.write(file + "\n")
# split
train_files, val_files = train_test_split(trainval_files, test_size=0.15, random_state=55)
# train
for file in train_files:
    ftrain.write(file + "\n")
# val
for file in val_files:
    fval.write(file + "\n")
for file in test_files:
    print(file)
    ftest.write(file + "\n")
ftrainval.close()
ftrain.close()
fval.close()
ftest.close()

ok，运行文件之之后我们就得到了一个名为VOC2007的文件夹，其中Annotations摆放的是XML格式的标签文件，JPEGImages摆放的是原始图像，ImagesSets里面则存放了一些训练集、验证集的索引。