pascal_voc标注bbox的一些问题

使用labelimg进行标注pascal_voc格式的bounding box遇到的一些问题

1，转成coco数据集格式的json标注格式

#!/usr/bin/python

# pip install lxml

import sys
import os
import json
import xml.etree.ElementTree as ET


START_BOUNDING_BOX_ID = 1
PRE_DEFINE_CATEGORIES = {}
# If necessary, pre-define category and its id
#  PRE_DEFINE_CATEGORIES = {"aeroplane": 1, "bicycle": 2, "bird": 3, "boat": 4,
                         #  "bottle":5, "bus": 6, "car": 7, "cat": 8, "chair": 9,
                         #  "cow": 10, "diningtable": 11, "dog": 12, "horse": 13,
                         #  "motorbike": 14, "person": 15, "pottedplant": 16,
                         #  "sheep": 17, "sofa": 18, "train": 19, "tvmonitor": 20}


def get(root, name):
    vars = root.findall(name)
    return vars


def get_and_check(root, name, length):
    vars = root.findall(name)
    if len(vars) == 0:
        raise NotImplementedError('Can not find %s in %s.'%(name, root.tag))
    if length > 0 and len(vars) != length:
        raise NotImplementedError('The size of %s is supposed to be %d, but is %d.'%(name, length, len(vars)))
    if length == 1:
        vars = vars[0]
    return vars


def get_filename_as_int(filename):
    try:
        filename = os.path.splitext(filename)[0]
        return int(filename)
    except:
        raise NotImplementedError('Filename %s is supposed to be an integer.'%(filename))


def convert(xml_list, xml_dir, json_file):
    list_fp = open(xml_list, 'r')
    json_dict = {"images":[], "type": "instances", "annotations": [],
                 "categories": []}
    categories = PRE_DEFINE_CATEGORIES
    bnd_id = START_BOUNDING_BOX_ID
    for line in list_fp:
        line = line.strip()
        print("Processing %s"%(line))
        xml_f = os.path.join(xml_dir, line)
        tree = ET.parse(xml_f)
        root = tree.getroot()
        path = get(root, 'path')
        if len(path) == 1:
            filename = os.path.basename(path[0].text)
        elif len(path) == 0:
            filename = get_and_check(root, 'filename', 1).text
        else:
            raise NotImplementedError('%d paths found in %s'%(len(path), line))
        ## The filename must be a number
        image_id = get_filename_as_int(filename)
        size = get_and_check(root, 'size', 1)
        width = int(get_and_check(size, 'width', 1).text)
        height = int(get_and_check(size, 'height', 1).text)
        image = {'file_name': filename, 'height': height, 'width': width,
                 'id':image_id}
        json_dict['images'].append(image)
        ## Cruuently we do not support segmentation
        #  segmented = get_and_check(root, 'segmented', 1).text
        #  assert segmented == '0'
        for obj in get(root, 'object'):
            category = get_and_check(obj, 'name', 1).text
            if category not in categories:
                new_id = len(categories)
                categories[category] = new_id
            category_id = categories[category]
            bndbox = get_and_check(obj, 'bndbox', 1)
            xmin = int(get_and_check(bndbox, 'xmin', 1).text) - 1
            ymin = int(get_and_check(bndbox, 'ymin', 1).text) - 1
            xmax = int(get_and_check(bndbox, 'xmax', 1).text)
            ymax = int(get_and_check(bndbox, 'ymax', 1).text)
            assert(xmax > xmin)
            assert(ymax > ymin)
            o_width = abs(xmax - xmin)
            o_height = abs(ymax - ymin)
            ann = {'area': o_width*o_height, 'iscrowd': 0, 'image_id':
                   image_id, 'bbox':[xmin, ymin, o_width, o_height],
                   'category_id': category_id, 'id': bnd_id, 'ignore': 0,
                   'segmentation': []}
            json_dict['annotations'].append(ann)
            bnd_id = bnd_id + 1

    for cate, cid in categories.items():
        cat = {'supercategory': 'none', 'id': cid, 'name': cate}
        json_dict['categories'].append(cat)
    json_fp = open(json_file, 'w')
    json_str = json.dumps(json_dict)
    json_fp.write(json_str)
    json_fp.close()
    list_fp.close()


if __name__ == '__main__':
    if len(sys.argv) <= 1:
        print('3 auguments are need.')
        print('Usage: %s XML_LIST.txt XML_DIR OUTPU_JSON.json'%(sys.argv[0]))
        exit(1)

    convert(sys.argv[1], sys.argv[2], sys.argv[3])

⚠️文件名必须为数字

2，修改xml文件

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2019/7/9 15:16
# @Author  : xiaodai
import xml.etree.ElementTree as ET
#from lxml import etree
#from tqdm import tqdm
import os
import time
import sys  
reload(sys)  
sys.setdefaultencoding('utf8')


def creat_xml(xml_file,x,y,w,h):
    """
    新建xml文件
    :param xml_file: xml
    :param x: xmin
    :param y: ymin
    :param w: 宽
    :param h: 高
    :return:
    """
    root = etree.Element("annotation")
    child1 = etree.SubElement(root, "folder")
    child1.text = "VOC2007"
    object = etree.SubElement(root, "object")
    namen = etree.SubElement(object, "name")
    namen.text = 'person' 
    bndbox = etree.SubElement(object, "bndbox")
    xminn = etree.SubElement(bndbox, "xmin")
    xminn.text = str(x)
    yminn = etree.SubElement(bndbox, "ymin")
    yminn.text = str(y)
    xmaxn = etree.SubElement(bndbox, "xmax")
    xmaxn.text = str(x + w)
    ymaxn = etree.SubElement(bndbox, "ymax")
    ymaxn.text = str(y + h)
    weight = etree.SubElement(bndbox, "box_w")
    weight.text = str(w)
    height = etree.SubElement(bndbox, "box_h")
    height.text = str(h)
    tree = etree.ElementTree(root)
    tree.write(xml_file, pretty_print=True, xml_declaration=False, encoding='utf-8')


def edit_xml(xml_file):
    """
    修改xml文件
    :param xml_file:xml文件的路径
    :return:
    """
    tree = ET.parse(xml_file)
    
    filepath, tempfilename = os.path.split(xml_file)
    name,_ = os.path.splitext(tempfilename)
    pngFile = name+'.png'

    obj_filename = tree.find('filename')
    obj_filename.text = pngFile

    obj_path = tree.find('path')
    obj_path.text = '/home/yinli/datasets/mydata_voc/VOCdevkit/VOC2007/JPEGImages/'+pngFile

    obj_folder = tree.find('folder')
    obj_folder.text = 'JPEGImages'

    tree.write(xml_file,method='xml',encoding='utf-8')

    
    '''

    for ix, obj in enumerate(objs):
        name = obj.find('name').text
        if name == 'mouse':
            print(xml_file)
            obj_new = obj.find('bndbox')
            xmin = str( 1280 - int(obj_new.find('xmin').text))
            xmax = str( 1280 - int(obj_new.find('xmax').text))
            obj_new.find('xmin').text = xmin
            obj_new.find('xmax').text = xmax

            conf = obj_new.find('conf')
            conf.tag = 'fenshu'

            newEle = ET.Element("NewElement1")
            newEle.text = "new element"
            obj_new.append(newEle)

            newEle = obj_new.find('xmin')
            obj_new.remove(newEle)

            obj_new.set('key','value')
            
            tree.write(xml_file,method='xml',encoding='utf-8')
    '''


if __name__ == '__main__':
    path = '/Users/yinli/PythonProject/detection/TEST/annotations/train'
    xml_files = [os.path.join(rootdir, file) for rootdir, _, files in os.walk(path) for file in files if
                 (file.endswith('.xml'))]

    for xml in xml_files:
        edit_xml(xml)
        time.sleep(0.1)
        '''
    for i in tqdm(range(10)):
        xml = os.path.join(path,str(i)+'.xml')
        creat_xml(xml,32,120,80,80)
        '''

根据自己的数据再改一下路径什么。上面的代码适用于py2。

如果使用py3的话，需要将

reload(sys)  
sys.setdefaultencoding('utf8')

改成

import importlib
importlib.reload(sys)