提取COCO数据集中特定的类

提取COCO数据集中特定的类—vehicle 4类

1 安装pycocotools
2 下载COCO数据集
3 提取特定的类别
4 多类标签合并

1 安装pycocotools

pycocotools github地址

pip install git+https://github.com/philferriere/cocoapi.git#subdirectory=PythonAPI

2 下载COCO数据集

COCO官网下载2017 Train images，2017 Val images

文件目录结构如下

data/
├── COCO
│   ├── annotations_trainval2017
│   │   ├── annotations
│   │   │   ├── instances_train2017.json
│   │   │   ├── captions_val2017.json
│   ├── train2017
├── getVehicleFromCOCO.py
├── coco_car
├── coco_bus
├── coco_truck
├── coco_train

3 提取特定的类别

创建coco_car、coco_bus、coco_truck、coco_train四个文件夹，依次修改savepath为以上文件夹名称，classes_names 修改为car、bus、truck、train，分别将四类车辆存到对应的文件夹。
提取特定的类别getVehicleFromCOCO.py代码如下：

from pycocotools.coco import COCO
import os
import shutil
from tqdm import tqdm
import skimage.io as io
import matplotlib.pyplot as plt
import cv2
from PIL import Image, ImageDraw
 
#the path you want to save your results for coco to voc
savepath="coco_car"  #保存提取类的路径
img_dir=savepath+'images/'
anno_dir=savepath+'Annotations/'
datasets_list=['train2017']
classes_names = ['car']  #要提取类的名字
dataDir= 'COCO/'  #原coco数据集
 
headstr = """\
<annotation>
    <folder>VOC</folder>
    <filename>%s</filename>
    <source>
        <database>My Database</database>
        <annotation>COCO</annotation>
        <image>flickr</image>
        <flickrid>NULL</flickrid>
    </source>
    <owner>
        <flickrid>NULL</flickrid>
        <name>company</name>
    </owner>
    <size>
        <width>%d</width>
        <height>%d</height>
        <depth>%d</depth>
    </size>
    <segmented>0</segmented>
"""
objstr = """\
    <object>
        <name>%s</name>
        <pose>Unspecified</pose>
        <truncated>0</truncated>
        <difficult>0</difficult>
        <bndbox>
            <xmin>%d</xmin>
            <ymin>%d</ymin>
            <xmax>%d</xmax>
            <ymax>%d</ymax>
        </bndbox>
    </object>
"""
 
tailstr = '''\
</annotation>
'''
 
#if the dir is not exists,make it,else delete it
def mkr(path):
    if os.path.exists(path):
        shutil.rmtree(path)
        os.mkdir(path)
    else:
        os.mkdir(path)
mkr(img_dir)
mkr(anno_dir)
def id2name(coco):
    classes=dict()
    for cls in coco.dataset['categories']:
        classes[cls['id']]=cls['name']
    return classes
 
def write_xml(anno_path,head, objs, tail):
    f = open(anno_path, "w")
    f.write(head)
    for obj in objs:
        f.write(objstr%(obj[0],obj[1],obj[2],obj[3],obj[4]))
    f.write(tail)
 
 
def save_annotations_and_imgs(coco,dataset,filename,objs):
    #eg:COCO_train2014_000000196610.jpg-->COCO_train2014_000000196610.xml
    anno_path=anno_dir+filename[:-3]+'xml'
    img_path=dataDir+dataset+'/'+filename
    print(img_path)
    dst_imgpath=img_dir+filename
 
    img=cv2.imread(img_path)
    #if (img.shape[2] == 1):
    #    print(filename + " not a RGB image")
     #   return
    shutil.copy(img_path, dst_imgpath)
 
    head=headstr % (filename, img.shape[1], img.shape[0], img.shape[2])
    tail = tailstr
    write_xml(anno_path,head, objs, tail)
 
 
def showimg(coco,dataset,img,classes,cls_id,show=True):
    global dataDir
    I=Image.open('%s/%s/%s'%(dataDir,dataset,img['file_name']))
    #通过id，得到注释的信息
    annIds = coco.getAnnIds(imgIds=img['id'], catIds=cls_id, iscrowd=None)
    # print(annIds)
    anns = coco.loadAnns(annIds)
    # print(anns)
    # coco.showAnns(anns)
    objs = []
    for ann in anns:
        class_name=classes[ann['category_id']]
        if class_name in classes_names:
            print(class_name)
            if 'bbox' in ann:
                bbox=ann['bbox']
                xmin = int(bbox[0])
                ymin = int(bbox[1])
                xmax = int(bbox[2] + bbox[0])
                ymax = int(bbox[3] + bbox[1])
                obj = [class_name, xmin, ymin, xmax, ymax]
                objs.append(obj)
                draw = ImageDraw.Draw(I)
                draw.rectangle([xmin, ymin, xmax, ymax])
    if show:
        plt.figure()
        plt.axis('off')
        plt.imshow(I)
        plt.show()
 
    return objs
 
for dataset in datasets_list:
    #./COCO/annotations/instances_train2014.json
    annFile='{}/annotations/instances_{}.json'.format(dataDir,dataset)
 
    #COCO API for initializing annotated data
    coco = COCO(annFile)

    #show all classes in coco
    classes = id2name(coco)
    print(classes)
    #[1, 2, 3, 4, 6, 8]
    classes_ids = coco.getCatIds(catNms=classes_names)
    print(classes_ids)
    for cls in classes_names:
        #Get ID number of this class
        cls_id=coco.getCatIds(catNms=[cls])
        img_ids=coco.getImgIds(catIds=cls_id)
        print(cls,len(img_ids))
        # imgIds=img_ids[0:10]
        for imgId in tqdm(img_ids):
            img = coco.loadImgs(imgId)[0]
            filename = img['file_name']
            # print(filename)
            objs=showimg(coco, dataset, img, classes,classes_ids,show=False)
            print(objs)
            save_annotations_and_imgs(coco, dataset, filename, objs)

4 多类标签合并

创建以下四个文件夹，将coco_car中的图像拷贝到JPEGImages，标注文件拷贝到Annotations。
在这里插入图片描述
执行以下脚本生成ImageSets/train.txt

import sys
import os
folder = "JPEGImages"
voc_train_txt = "ImageSets/train.txt"
file_voc = open(voc_train_txt, 'w',encoding="utf-8")
file_tree = os.walk(folder)
for path, _, files in file_tree:
    for file in files:
        name, ext = os.path.splitext(file)
        file_voc.write(name+'\n')

执行以下脚本将Annotations中的xml文件转换成txt，存储在labels文件夹中。

import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join

sets=[('2024', 'train')]
classes = ["car","bus","truck","train"]

def convert(size, box):
    dw = 1./size[0]
    dh = 1./size[1]
    x = (box[0] + box[1])/2.0
    y = (box[2] + box[3])/2.0
    w = box[1] - box[0]
    h = box[3] - box[2]
    x = x*dw
    w = w*dw
    y = y*dh
    h = h*dh
    return (x,y,w,h)

def convert_annotation(image_id):
    in_file = open('Annotations/%s.xml'%(image_id),"r",encoding="utf-8")
    #以追加的方式生成txt，这样4类中的重复图像的标签就会合并
    out_file = open('labels/%s.txt'%(image_id), 'a',encoding="utf-8")
    print( "imd id: %s " %(image_id))
    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'):
        if obj.find('difficult'):
            difficult = obj.find('difficult').text
        else:
            difficult = 0
        cls = obj.find('name').text
        if cls not in classes or int(difficult) == 1:
            print( "%s has wrong label: %s " %(in_file, cls)) # ignore difficult value
            continue
        
        cls_id = classes.index(cls)
        xmlbox = obj.find('bndbox')
        b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text), float(xmlbox.find('ymax').text))
        bb = convert((w,h), b)
     
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')

    in_file.close()
    out_file.close()

wd = getcwd()
for year, image_set in sets:
    if not os.path.exists('labels/'):
        os.makedirs('labels/')
    image_ids = open('ImageSets/%s.txt'%(image_set)).read().strip().split()
    #print(image_ids)
    for image_id in image_ids:
        convert_annotation(image_id)
    #image_ids.close()