伪装目标检测中数据集的标注格式：COCO和VOC

交换喜悲

已于 2024-04-23 17:44:01 修改

阅读量349

点赞数 3

分类专栏：深度学习基础知识文章标签：目标检测人工智能计算机视觉 python pycharm 开发语言

于 2024-04-23 17:41:18 首次发布

本文链接：https://blog.csdn.net/absence521/article/details/138133920

版权

深度学习基础知识专栏收录该内容

31 篇文章 2 订阅

订阅专栏

1.OSFormer中提供的COD10K的json格式，是coco的格式，但由于伪装目标检测任务的特殊性，标注信息中还有一个segmentation段

 "images": [
        {
            "id": 3039,
            "file_name": "COD10K-CAM-1-Aquatic-1-BatFish-3.jpg",
            "width": 800,
            "height": 533,
            "date_captured": "2020-08-21 01:23:18.643991",
            "license": 1,
            "url": ""
        }
    ],
    "categories": [
        {
            "id": 1,
            "name": "foreground",
            "supercategory": "saliency"
        }
    ],
    "annotations": [
        {
            "id": 3533,
            "image_id": 3039,
            "category_id": 1,
            "iscrowd": 0,
            "area": 104946,
            "bbox": [
                96.0,
                60.0,
                544.0,
                431.0
            ],
            "segmentation": [
                [
                    513.0,
                    490.9980392156863,
                    505.0,
                    490.9980392156863,
                    469.0,
                    476.9980392156863,
                    459.0,
                    479.9980392156863,
                    450.0,
                    471.9980392156863,
                    442.0,
                    472.9980392156863,
                    439.0,
                    467.9980392156863,
                    434.0,
                    477.9980392156863,
                    428.0,
                    467.9980392156863,
                    427.9980392156863,
                    473.0,
                    424.0,
                    475.9980392156863,

首先将一整个json文件分解：

from __future__ import print_function
import json
json_file='D:/projects/SINet-V2-main/json/train_instance.json' #
# Object Instance 类型的标注
# person_keypoints_val2017.json
# Object Keypoint 类型的标注格式
# captions_val2017.json
# Image Caption的标注格式
data=json.load(open(json_file,'r'))
data_2={}
# da ta_2['info']=data['info']
# data_2['licenses']=data['licenses']
for i in range(3040): # 一共234张图片

    data_2['images']=[data['images'][i]] # 只提取第i张图片
    data_2['categories']=data['categories']
    annotation=[] # 通过imgID 找到其所有对象
    imgID=data_2['images'][0]['id']
    for ann in data['annotations']:
        if ann['image_id']==imgID:
            annotation.append(ann)
    data_2['annotations']=annotation # 保存到新的JSON文件，便于查看数据特点
    savepath = 'D:/projects/SINet-V2-main/json/single/' + data_2['images'][0]['file_name']+ '.json'
    json.dump(data_2,open(savepath,'w'),indent=4) # indent=4 更加美观显示

然后转化为VOC格式：

import os
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.存放的json标签路径
labelme_path = "D:/projects/SINet-V2-main/json/single/"

# 原始labelme标注数据路径
saved_path = "D:/projects/SINet-V2-main/json/COD10K-voc/"
# 保存路径
isUseTest = None  # 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('D:/projects/SINet-V2-main/json/dataset/image/' + json_file_).shape
    with codecs.open(saved_path + "Annotations/" + json_file_ + ".xml", "w", "utf-8") as xml:

        xml.write('<annotation>\n')
        xml.write('\t<folder>' + 'CELL_data' + '</folder>\n')
        xml.write('\t<filename>' + json_file_  + '</filename>\n')
        xml.write('\t<source>\n')
        xml.write('\t\t<database>CELL Data</database>\n')
        xml.write('\t\t<annotation>CELL</annotation>\n')
        xml.write('\t\t<image>bloodcell</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>CELL</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')# 是否用于分割（在图像物体识别中01无所谓）
        cName = json_file["categories"]
        Name = cName[0]["name"]
        print(Name)
        for multi in json_file["annotations"]:
            points = np.array(multi["bbox"])
            labelName = Name
            xmin = points[0]
            xmax = points[0]+points[2]
            ymin = points[1]
            ymax = points[1]+points[3]
            label = Name
            if xmax <= xmin:
                pass
            elif ymax <= ymin:
                pass
            else:
                xml.write('\t<object>\n')
                xml.write('\t\t<name>' + labelName + '</name>\n')# 物体类别
                xml.write('\t\t<pose>Unspecified</pose>\n')# 拍摄角度
                xml.write('\t\t<truncated>0</truncated>\n')# 是否被截断（0表示完整）
                xml.write('\t\t<difficult>0</difficult>\n')# 目标是否难以识别（0表示容易识别）
                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("labelmedataset/images/" + "*.jpg")
print("copy image files to VOC007/JPEGImages/")
for image in image_files:
    shutil.copy(image, saved_path + "JPEGImages/")

# 6.拆分训练集、测试集、验证集
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:
    print(file)
    fval.write(file + "\n")
for file in test_files:
    print("test:"+file)
    ftest.write(file + "\n")
ftrainval.close()
ftrain.close()
fval.close()
ftest.close()

这样生成的xml文件，没有之前COD10K标注的segmentation信息，还需要进一步考虑，在转换为xml的脚本中加上识别segmentation部分。
参考博客：https://blog.csdn.net/ytusdc/article/details/1319729224
https://blog.csdn.net/xjx19991226/article/details/123386207

交换喜悲

关注

3
点赞
踩
0

收藏

觉得还不错? 一键收藏
0
评论
伪装目标检测中数据集的标注格式：COCO和VOC

这样生成的xml文件，没有之前COD10K标注的segmentation信息，还需要进一步考虑，在转换为xml的脚本中加上识别segmentation部分。1.OSFormer中提供的COD10K的json格式，是coco的格式，但由于伪装目标检测任务的特殊性，标注信息中还有一个segmentation段。
复制链接

扫一扫

专栏目录