Citypersons数据集转VOC标准格式（YOLO 目标检测txt格式）

你的名字 2021-11-09 14:31 1531阅读 0赞

CItyscapes城市数据集包含一组不同的立体视频序列中记录来自50个不同城市的街景,高质量的进行像素级的注释。数据集下载地址（需要申请注册，通过申请才能下载）\[[https://www.cityscapes-dataset.com][https_www.cityscapes-dataset.com]\]  
该数据集用于常语义分割，包含以下类别：  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl8zODYzMjI0Ng_size_16_color_FFFFFF_t_70]

提供百度云链接地址：链接: [https://pan.baidu.com/s/108\_NgFheDIpnQRrwz5uhmw][https_pan.baidu.com_s_108_NgFheDIpnQRrwz5uhmw] 提取码: dhr8

#### \#cityperson数据集是cityscapes数据集的子集，cityperson的标注文件只标注了其中Human的类别，如上图。该标注文件下载地址为： ####

下载地址：[https://bitbucket.org/shanshanzhang/citypersons/get/ae6814faa761.zip][https_bitbucket.org_shanshanzhang_citypersons_get_ae6814faa761.zip]

提取cityscapes中标注好的类别为VOC的标准格式（JPEGImages和Annotations，txt的代码就不写了，参考博主其他博客）

#! /usr/bin/python
    # -*- coding:UTF-8 -*-
    import os, sys
    import glob
    from PIL import Image
    import shutil
    from scipy.io import loadmat
    #img_Lists = glob.glob(src_img_dir + '\*.png')
     
    # citypersons图像的标注位置
    src_anno_dir = loadmat(r'c:\Users\rockhuang\Desktop\anno_train.mat')
    
    # cityscapes图像的存储位置
    src_img_dir = r"g:\dataset\cityscapes\leftImg8bit\train\\"
    
    #保存为VOC 数据集的原图和xml标注路径
    new_img= r"g:\dataset\cityscapes\JPEGImages"
    new_xml=r"g:\dataset\cityscapes\Annotations"
    
    if not os.path.isdir(new_img):
        os.makedirs(new_img)
        
    if not os.path.isdir(new_xml):
        os.makedirs(new_xml)   
        
    a=src_anno_dir['anno_train_aligned'][0]
     
        #处理标注文件
    
    for i in range(len(a)):
        img_name=a[i][0][0][1][0]   #frankfurt_000000_000294_leftImg8bit.png 
        dir_name=img_name.split('_')[0]
        img=src_img_dir+dir_name+"\\"+img_name
         
        shutil.copy(img, new_img+"\\"+img_name)
        img=Image.open(img)
        width, height = img.size
        
        position=a[i][0][0][2]
        print(position)
        #sys.exit()
        xml_name=img_name.split('.')[0]
        xml_file = open((new_xml + '\\' + xml_name + '.xml'), 'w')
              
        xml_file.write('<annotation>\n')
        xml_file.write(' <folder>citysperson</folder>\n')
        xml_file.write(' <filename>' + str(img_name)+ '</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')
        
        for j in range(len(position)):
            category_location=position[j]  #[ 1 947 406 17 40 24000 950 407 14 39]
            category=category_location[0]  # class_label =0: ignore regions 1: pedestrians 2: riders 3: sitting persons 4: other persons 5: group of people
           
    
            if category == 0:
                continue
    # if 
                #if category == 1 or category ==2 or category ==3 category ==4 or category ==5:
            else:
                x=category_location[1]   #class_label==1 or 2: x1，y1，w，h是与全身对齐的边界框；
                y=category_location[2]
                w=category_location[3]
                h=category_location[4]
                   
           
                xml_file.write(' <object>\n')
                xml_file.write(' <name>' + 'person' + '</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')
                xml_file.write(' <xmin>' + str(x) + '</xmin>\n')
                xml_file.write(' <ymin>' + str(y) + '</ymin>\n')
                xml_file.write(' <xmax>' + str(x+w) + '</xmax>\n')
                xml_file.write(' <ymax>' + str(y+h) + '</ymax>\n')
                xml_file.write(' </bndbox>\n')
                xml_file.write(' </object>\n')
            xml_file.write('</annotation>\n')

YOLO训练VOC格式数据集，源代码中附有voc\_labels.py如下，自己转下归一化的txt就OK了

import xml.etree.ElementTree as ET
    import pickle
    import os
    from os import listdir, getcwd
    from os.path import join
    
    sets=[ ('2007', 'train'), ('2007', 'val'), ('2007', 'test')]
    
    classes = ["car", "person","rider"]
    
    #parser = ET.XMLParser("utf-8")
    #tree = ET.fromstring(xmlstring, parser=parser)
    
    def convert(size, box):
        dw = 1./(size[0])
        dh = 1./(size[1])
        x = (box[0] + box[1])/2.0 - 1
        y = (box[2] + box[3])/2.0 - 1
        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(year, image_id):
        in_file = open('VOCdevkit/VOC%s/Annotations/%s.xml'%(year, image_id))
        out_file = open('VOCdevkit/VOC%s/labels/%s.txt'%(year, image_id), 'w')
        
        #parser = ET.XMLParser(encoding="utf-8")
       # tree = ET.fromstring(in_file, parser=True)
        print in_file
    
        tree=ET.parse(in_file)
       # print 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')
            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')
    
    wd = getcwd()
    
    for year, image_set in sets:
        if not os.path.exists('VOCdevkit/VOC%s/labels/'%(year)):
            os.makedirs('VOCdevkit/VOC%s/labels/'%(year))
        image_ids = open('VOCdevkit/VOC%s/ImageSets/Main/%s.txt'%(year, image_set)).read().strip().split()
        list_file = open('%s_%s.txt'%(year, image_set), 'w')
        for image_id in image_ids:
            list_file.write('%s/VOCdevkit/VOC%s/JPEGImages/%s.jpg\n'%(wd, year, image_id))
            convert_annotation(year, image_id)
        list_file.close()
    
    #os.system("cat 2007_train.txt 2007_val.txt > train.txt")
    #os.system("cat 2007_train.txt 2007_val.txt 2007_test.txt 2012_train.txt 2012_val.txt > train.all.txt")

[https_www.cityscapes-dataset.com]: https://www.cityscapes-dataset.com
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl8zODYzMjI0Ng_size_16_color_FFFFFF_t_70]: /images/20211109/30320019914a4a1ea37dbce3680065ef.png
[https_pan.baidu.com_s_108_NgFheDIpnQRrwz5uhmw]: https://pan.baidu.com/s/108_NgFheDIpnQRrwz5uhmw
[https_bitbucket.org_shanshanzhang_citypersons_get_ae6814faa761.zip]: https://bitbucket.org/shanshanzhang/citypersons/get/ae6814faa761.zip