Visdrone2019数据集

数据集下载链接

https://github.com/VisDrone/VisDrone-Dataset?tab=readme-ov-file

**txt标签含义：**
1. 边界框左上角的x坐标
2. 边界框左上角的y坐标
3. 边界框的宽度
4. 边界框的高度
5. GROUNDTRUTH文件中的分数设置为1或0。1表示在计算中考虑边界框，而0表示将忽略边界框。
6.  类别：忽略区域（0）、行人（1）、人（2）、自行车（3）、汽车（4）、面包车（5）、卡车（6）、三轮车（7）、雨篷三轮车（8）、公共汽车（9）、摩托车（10），其他（11）。
7. GROUNDTRUTH文件中的得分表示对象部分出现在帧外的程度（即，无截断=0（截断比率0%），部分截断=1（截断比率1%°´50%））。
8. GROUNDTRUTH文件中的分数表示被遮挡的对象的分数（即，无遮挡=0（遮挡比率0%），部分遮挡=1（遮挡比率1%°´50%），重度遮挡=2（遮挡率50%~100%））。

数据集转换成xml

"""
该脚本用于visdrone数据处理；
将annatations文件夹中的txt标签文件转换为XML文件；
txt标签内容为：
<bbox_left>,<bbox_top>,<bbox_width>,<bbox_height>,<score>,<object_category>,<truncation>,<occlusion>
类别：
ignored regions(0), pedestrian(1),
people(2), bicycle(3), car(4), van(5),
truck(6), tricycle(7), awning-tricycle(8),
bus(9), motor(10), others(11)
"""
#visdrone转为yolo格式
import os
import cv2
import time
from xml.dom import minidom

name_dict = {'0': 'ignored regions', '1': 'pedestrian', '2': 'people',
             '3': 'bicycle', '4': 'car', '5': 'van', '6': 'truck',
             '7': 'tricycle', '8': 'awning-tricycle', '9': 'bus',
             '10': 'motor', '11': 'others'}


def transfer_to_xml(pic, txt, file_name):
    xml_save_path = 'xml'  # 生成的xml文件存储的文件夹
    if not os.path.exists(xml_save_path):
        os.mkdir(xml_save_path)

    img = cv2.imread(pic)
    img_w = img.shape[1]
    img_h = img.shape[0]
    img_d = img.shape[2]
    doc = minidom.Document()

    annotation = doc.createElement("annotation")
    doc.appendChild(annotation)
    folder = doc.createElement('folder')
    folder.appendChild(doc.createTextNode('visdrone'))
    annotation.appendChild(folder)

    filename = doc.createElement('filename')
    filename.appendChild(doc.createTextNode(file_name))
    annotation.appendChild(filename)

    source = doc.createElement('source')
    database = doc.createElement('database')
    database.appendChild(doc.createTextNode("Unknown"))
    source.appendChild(database)

    annotation.appendChild(source)

    size = doc.createElement('size')
    width = doc.createElement('width')
    width.appendChild(doc.createTextNode(str(img_w)))
    size.appendChild(width)
    height = doc.createElement('height')
    height.appendChild(doc.createTextNode(str(img_h)))
    size.appendChild(height)
    depth = doc.createElement('depth')
    depth.appendChild(doc.createTextNode(str(img_d)))
    size.appendChild(depth)
    annotation.appendChild(size)

    segmented = doc.createElement('segmented')
    segmented.appendChild(doc.createTextNode("0"))
    annotation.appendChild(segmented)

    with open(txt, 'r') as f:
        lines = [f.readlines()]
        for line in lines:
            for boxes in line:
                box = boxes.strip('\n')
                box = box.split(',')
                x_min = box[0]
                y_min = box[1]
                x_max = int(box[0]) + int(box[2])
                y_max = int(box[1]) + int(box[3])
                object_name = name_dict[box[5]]

                # if object_name is 'ignored regions' or 'others':
                #     continue

                object = doc.createElement('object')
                nm = doc.createElement('name')
                nm.appendChild(doc.createTextNode(object_name))
                object.appendChild(nm)
                pose = doc.createElement('pose')
                pose.appendChild(doc.createTextNode("Unspecified"))
                object.appendChild(pose)
                truncated = doc.createElement('truncated')
                truncated.appendChild(doc.createTextNode("1"))
                object.appendChild(truncated)
                difficult = doc.createElement('difficult')
                difficult.appendChild(doc.createTextNode("0"))
                object.appendChild(difficult)
                bndbox = doc.createElement('bndbox')
                xmin = doc.createElement('xmin')
                xmin.appendChild(doc.createTextNode(x_min))
                bndbox.appendChild(xmin)
                ymin = doc.createElement('ymin')
                ymin.appendChild(doc.createTextNode(y_min))
                bndbox.appendChild(ymin)
                xmax = doc.createElement('xmax')
                xmax.appendChild(doc.createTextNode(str(x_max)))
                bndbox.appendChild(xmax)
                ymax = doc.createElement('ymax')
                ymax.appendChild(doc.createTextNode(str(y_max)))
                bndbox.appendChild(ymax)
                object.appendChild(bndbox)
                annotation.appendChild(object)
                with open(os.path.join(xml_save_path, file_name + '.xml'), 'w') as x:
                    x.write(doc.toprettyxml())
                x.close()
    f.close()


if __name__ == '__main__':
    t = time.time()
    print('Transfer .txt to .xml...ing....')
    txt_folder = '/VisDrone2019-DET-test-dev/annotations'  # visdrone txt标签文件夹
    txt_file = os.listdir(txt_folder)
    img_folder = '/VisDrone2019-DET-test-dev/images'  # visdrone 照片所在文件夹
    count = 0
    for txt in txt_file:
        txt_full_path = os.path.join(txt_folder, txt)
        img_full_path = os.path.join(img_folder, txt.split('.')[0] + '.jpg')
        count = count + 1
        print('txt to xml succeed:{}', count)
        try:
            transfer_to_xml(img_full_path, txt_full_path, txt.split('.')[0])
        except Exception as e:
            print(e)

    print("Transfer .txt to .XML sucessed. costed: {:.3f}s...".format(time.time() - t))

生成VOC数据集格式代码

import os
import random
 
 
trainval_percent = 0.9
train_percent = 0.9
xmlfilepath = 'data/test_xml'
txtsavepath = 'data/ImageSets'
total_xml = os.listdir(xmlfilepath)
 
num = len(total_xml)
list = range(num)
tv = int(num * trainval_percent)
tr = int(tv * train_percent)
trainval = random.sample(list, tv)
train = random.sample(trainval, tr)
 
ftrainval = open('data/ImageSets/trainval.txt', 'w')
ftest = open('data/ImageSets/test.txt', 'w')
ftrain = open('data/ImageSets/train.txt', 'w')
fval = open('data/ImageSets/val.txt', 'w')
 
for i in list:
    name = total_xml[i][:-4] + '\n'
    if i in trainval:
        ftrainval.write(name)
        if i in train:
            ftrain.write(name)
        else:
            fval.write(name)
    else:
        ftest.write(name)
 
ftrainval.close()
ftrain.close()
fval.close()
ftest.close()

此处去除忽略区域

import xml.etree.ElementTree as ET
import os
from os import getcwd
 
sets = ['train', 'val', 'test']
classes = ['pedestrian', 'people', 'bicycle', 'car', 'van', 'truck', 'tricycle', 'awning-tricycle', 'bus', 'motor', 'others']
abs_path = os.getcwd()
print(abs_path)
 
 
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(image_id):
    in_file = open('data/test_xml/%s.xml' % (image_id), encoding='UTF-8')
    out_file = open('data/labels/%s.txt' % (image_id), 'w')
    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'):
        # difficult = obj.find('difficult').text
        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))
        b1, b2, b3, b4 = b
        # 标注越界修正
        if b2 > w:
            b2 = w
        if b4 > h:
            b4 = h
        b = (b1, b2, b3, b4)
        bb = convert((w, h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
 
 
wd = getcwd()
for image_set in sets:
    if not os.path.exists('data/labels/'):
        os.makedirs('data/labels/')
    image_ids = open('data/ImageSets/%s.txt' % (image_set)).read().strip().split()
    list_file = open('data/%s.txt' % (image_set), 'w')
    for image_id in image_ids:
        list_file.write(abs_path + '/data/images/%s.jpg\n' % (image_id))
        convert_annotation(image_id)
    list_file.close()