python篇—提取VOC格式的坐标，并按照cameraID进行排序

from datetime import datetime
import xml.etree.ElementTree as ET
import os


sets = [("images")]
# fixme: 所对应的标签
classes = ["2"]
IMAGE_PATH = "./saves/{}.txt"
DATA_TXT = "./saves/"
IMAGE_WRITE_PATH = "images/{}.jpg"
OPEN_XML_PATH = "labels/{}.xml"


def convert_annotation(image_id, list_file):
    in_file = open(OPEN_XML_PATH.format(image_id))
    tree = ET.parse(in_file)
    root = tree.getroot()
    # list_file.write('"'+image_id.split("-")[0]+'"')
    #########################################################################
    list_file.write('{"name":"' + image_id.split("-")[0] + '",' + '"box":')
    # list_file.write(IMAGE_WRITE_PATH.format(image_id))
    #########################################################################
    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 = (int(xmlbox.find('xmin').text), int(xmlbox.find('ymin').text), int(xmlbox.find('xmax').text), int(xmlbox.find('ymax').text))
        # list_file.write(":" + '"(' + (",".join([str(a) for a in b])) + ')"' + ",")
        #########################################################################
        list_file.write('[('+(",".join([str(a) for a in b])) + ")]},")
        #########################################################################

    # list_file.write("}")
    list_file.write('\n')


for image_set in sets:
    image_ids = open(IMAGE_PATH.format(image_set)).read().strip().split()
    str_date_li = []
    for img_id in image_ids:
        str_date = img_id.split(".")[0].split("-")[0]
        str_date_li.append(str_date)
    li_ti1 = sorted(str_date_li)

    save_data_path = '/'.join(DATA_TXT.split('/')[:-1])
    if not os.path.exists(save_data_path):
        os.makedirs(save_data_path)
    list_file = open(os.path.join(DATA_TXT, "images_final1.txt"), 'w')
    for cameraID in li_ti1:
        for image_id in image_ids:
            if image_id.startswith(cameraID):
                print(image_id)
                convert_annotation(image_id, list_file)
    list_file.close()

结果如下：

from datetime import datetime
import xml.etree.ElementTree as ET
import os


sets = [("images")]
# fixme: 所对应的标签
classes = ["1"]
IMAGE_PATH = "./saves/{}.txt"
DATA_TXT = "./saves/"
IMAGE_WRITE_PATH = "images/{}.jpg"
OPEN_XML_PATH = "labels/{}.xml"


def convert_annotation(image_id, list_file):
    in_file = open(OPEN_XML_PATH.format(image_id))
    tree = ET.parse(in_file)
    root = tree.getroot()
    list_file.write('"'+image_id.split("-")[0]+'"')
    #########################################################################
    # list_file.write('{"name":"' + image_id.split("-")[0] + '",' + '"box":')
    # list_file.write(IMAGE_WRITE_PATH.format(image_id))
    #########################################################################
    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 = (int(xmlbox.find('xmin').text), int(xmlbox.find('ymin').text), int(xmlbox.find('xmax').text), int(xmlbox.find('ymax').text))
        list_file.write(":" + '"(' + (",".join([str(a) for a in b])) + ')"' + ",")
        #########################################################################
        # list_file.write('[('+(",".join([str(a) for a in b])) + ")]},")
        #########################################################################

    # list_file.write("}")
    list_file.write('\n')


for image_set in sets:
    image_ids = open(IMAGE_PATH.format(image_set)).read().strip().split()
    str_date_li = []
    for img_id in image_ids:
        str_date = img_id.split(".")[0].split("-")[0]
        str_date_li.append(str_date)
    li_ti1 = sorted(str_date_li)

    save_data_path = '/'.join(DATA_TXT.split('/')[:-1])
    if not os.path.exists(save_data_path):
        os.makedirs(save_data_path)
    list_file = open(os.path.join(DATA_TXT, "images_final.txt"), 'w')
    for cameraID in li_ti1:
        for image_id in image_ids:
            if image_id.startswith(cameraID):
                print(image_id)
                convert_annotation(image_id, list_file)
    list_file.close()

结果如下：