UA-DETRAC数据集转YOLO格式

一: 数据集下载

原官方数据集

链接:https://pan.baidu.com/s/1P_CeSIpJIYSA1dykmFhgYw
提取码: 7f4g

处理完成数据集(每10帧取一张)

嫌麻烦可以直接使用我处理完的

链接:https://pan.baidu.com/s/1OV5m4lcYmPVkXOOGuqUmXg
提取码:93m0

包含训练集8639张,验证集2231张,已按照yolo训练格式放置,即下即用!

二: 处理标注文件

先处理标注文件,UA-DETRAC提供的标注文件格式是VOC格式,需要先转为XML格式,然后再将每个XML文件转为YOLO文件。
下面提供两个代码,只需要修改文件放置目录

1. 将VOC转为XML格式

import xml.etree.ElementTree as ET
from xml.dom.minidom import Document
import os
import cv2
import time


def ConvertVOCXml(file_path="", file_name=""):
    tree = ET.parse(file_name)
    root = tree.getroot()
    # print(root.tag)

    num = 0  # 计数
    # 读xml操作

    frame_lists = []
    output_file_name = ""
    for child in root:

        if (child.tag == "frame"):
            # 创建dom文档
            doc = Document()
            # 创建根节点
            annotation = doc.createElement('annotation')
            # 根节点插入dom树
            doc.appendChild(annotation)

            # print(child.tag, child.attrib["num"])
            pic_id = child.attrib["num"].zfill(5)
            # print(pic_id)
            output_file_name = root.attrib["name"] + "__img" + pic_id + ".xml"
            #  print(output_file_name)

            folder = doc.createElement("folder")
            folder.appendChild(doc.createTextNode("VOC2007"))
            annotation.appendChild(folder)

            filename = doc.createElement("filename")
            pic_name = "img" + pic_id + ".jpg"
            filename.appendChild(doc.createTextNode(pic_name))
            annotation.appendChild(filename)

            sizeimage = doc.createElement("size")
            imagewidth = doc.createElement("width")
            imageheight = doc.createElement("height")
            imagedepth = doc.createElement("depth")

            imagewidth.appendChild(doc.createTextNode("960"))
            imageheight.appendChild(doc.createTextNode("540"))
            imagedepth.appendChild(doc.createTextNode("3"))

            sizeimage.appendChild(imagedepth)
            sizeimage.appendChild(imagewidth)
            sizeimage.appendChild(imageheight)
            annotation.appendChild(sizeimage)

            target_list = child.getchildren()[0]  # 获取target_list
            # print(target_list.tag)
            object = None
            for target in target_list:
                if (target.tag == "target"):
                    # print(target.tag)
                    object = doc.createElement('object')
                    bndbox = doc.createElement("bndbox")

                    for target_child in target:
                        if (target_child.tag == "box"):
                            xmin = doc.createElement("xmin")
                            ymin = doc.createElement("ymin")
                            xmax = doc.createElement("xmax")
                            ymax = doc.createElement("ymax")
                            xmin_value = int(float(target_child.attrib["left"]))
                            ymin_value = int(float(target_child.attrib["top"]))
                            box_width_value = int(float(target_child.attrib["width"]))
                            box_height_value = int(float(target_child.attrib["height"]))
                            xmin.appendChild(doc.createTextNode(str(xmin_value)))
                            ymin.appendChild(doc.createTextNode(str(ymin_value)))
                            if (xmin_value + box_width_value > 960):
                                xmax.appendChild(doc.createTextNode(str(960)))
                            else:
                                xmax.appendChild(doc.createTextNode(str(xmin_value + box_width_value)))
                            if (ymin_value + box_height_value > 540):
                                ymax.appendChild(doc.createTextNode(str(540)))
                            else:
                                ymax.appendChild(doc.createTextNode(str(ymin_value + box_height_value)))

                        if (target_child.tag == "attribute"):
                            vehicle_type = target_child.attrib["vehicle_type"]

                            name = doc.createElement('name')
                            pose = doc.createElement('pose')
                            truncated = doc.createElement('truncated')
                            difficult = doc.createElement('difficult')

                            name.appendChild(doc.createTextNode(str(vehicle_type)))
                            pose.appendChild(doc.createTextNode("Left"))  # 随意指定
                            truncated.appendChild(doc.createTextNode("0"))  # 随意指定
                            difficult.appendChild(doc.createTextNode("0"))  # 随意指定

                            object.appendChild(name)
                            object.appendChild(pose)
                            object.appendChild(truncated)
                            object.appendChild(difficult)

                    bndbox.appendChild(xmin)
                    bndbox.appendChild(ymin)
                    bndbox.appendChild(xmax)
                    bndbox.appendChild(ymax)
                    object.appendChild(bndbox)
                    annotation.appendChild(object)

            file_path_out = os.path.join(file_path, output_file_name)
            f = open(file_path_out, 'w')
            f.write(doc.toprettyxml(indent=' ' * 4))
            f.close()
            num = num + 1
    return num


'''
画方框
'''


def bboxes_draw_on_img(img, bbox, color=[255, 0, 0], thickness=2):
    # Draw bounding box...
    print(bbox)
    p1 = (int(float(bbox["xmin"])), int(float(bbox["ymin"])))
    p2 = (int(float(bbox["xmax"])), int(float(bbox["ymax"])))
    cv2.rectangle(img, p1, p2, color, thickness)


def visualization_image(image_name, xml_file_name):
    tree = ET.parse(xml_file_name)
    root = tree.getroot()

    object_lists = []
    for child in root:
        if (child.tag == "folder"):
            print(child.tag, child.text)
        elif (child.tag == "filename"):
            print(child.tag, child.text)
        elif (child.tag == "size"):  # 解析size
            for size_child in child:
                if (size_child.tag == "width"):
                    print(size_child.tag, size_child.text)
                elif (size_child.tag == "height"):
                    print(size_child.tag, size_child.text)
                elif (size_child.tag == "depth"):
                    print(size_child.tag, size_child.text)
        elif (child.tag == "object"):  # 解析object
            singleObject = {}
            for object_child in child:
                if (object_child.tag == "name"):
                    # print(object_child.tag,object_child.text)
                    singleObject["name"] = object_child.text
                elif (object_child.tag == "bndbox"):
                    for bndbox_child in object_child:
                        if (bndbox_child.tag == "xmin"):
                            singleObject["xmin"] = bndbox_child.text
                            # print(bndbox_child.tag, bndbox_child.text)
                        elif (bndbox_child.tag == "ymin"):
                            # print(bndbox_child.tag, bndbox_child.text)
                            singleObject["ymin"] = bndbox_child.text
                        elif (bndbox_child.tag == "xmax"):
                            singleObject["xmax"] = bndbox_child.text
                        elif (bndbox_child.tag == "ymax"):
                            singleObject["ymax"] = bndbox_child.text
            object_length = len(singleObject)
            if (object_length > 0):
                object_lists.append(singleObject)
    img = cv2.imread(image_name)
    for object_coordinate in object_lists:
        bboxes_draw_on_img(img, object_coordinate)
    cv2.imshow("capture", img)
    cv2.waitKey(0)
    cv2.destroyAllWindows()


if (__name__ == "__main__"):
    # print("main")
    basePath = r"E:\project\dataset\UA-DETRAC\DETRAC-Test-Annotations-XML"
    totalxml = os.listdir(basePath)
    total_num = 0
    flag = False
    print("正在转换")
    saveBasePath = r"E:\project\dataset\UA-DETRAC\test-labels-xml"
    if os.path.exists(saveBasePath) == False:  # 判断文件夹是否存在
        os.makedirs(saveBasePath)

    # ConvertVOCXml(file_path="samplexml",file_name="000009.xml")
    # Start time
    start = time.time()
    log = open("xml_statistical.txt", "w")  # 分析日志,进行排错
    for xml in totalxml:
        file_name = os.path.join(basePath, xml)
        print(file_name)
        num = ConvertVOCXml(file_path=saveBasePath, file_name=file_name)
        print(num)
        total_num = total_num + num
        log.write(file_name + " " + str(num) + "\n")
    # End time
    end = time.time()
    seconds = end - start
    print("Time taken : {0} seconds".format(seconds))
    print(total_num)

2. 将XML转为YOLO格式

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


def convert(size, box):
    # size=(width, height)  b=(xmin, xmax, ymin, ymax)
    # x_center = (xmax+xmin)/2        y_center = (ymax+ymin)/2
    # x = x_center / width            y = y_center / height
    # w = (xmax-xmin) / width         h = (ymax-ymin) / height

    x_center = (box[0] + box[1]) / 2.0
    y_center = (box[2] + box[3]) / 2.0
    x = x_center / size[0]
    y = y_center / size[1]

    w = (box[1] - box[0]) / size[0]
    h = (box[3] - box[2]) / size[1]

    # print(x, y, w, h)
    return (x, y, w, h)


def convert_annotation(xml_files_path, save_txt_files_path, classes):
    xml_files = os.listdir(xml_files_path)
    # print(xml_files)
    for xml_name in xml_files:
        print(xml_name)
        xml_file = os.path.join(xml_files_path, xml_name)
        out_txt_path = os.path.join(save_txt_files_path, xml_name.split('.')[0] + '.txt')
        out_txt_f = open(out_txt_path, 'w')
        tree = ET.parse(xml_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))
            # b=(xmin, xmax, ymin, ymax)
            # print(w, h, b)
            bb = convert((w, h), b)
            out_txt_f.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')


if __name__ == "__main__":
    # 把forklift_pallet的voc的xml标签文件转化为yolo的txt标签文件
    # 1、需要转化的类别
    classes = ['car',  'bus',  'van', 'others']  # 注意:这里根据自己的类别名称及种类自行更改
    # 2、voc格式的xml标签文件路径
    xml_files1 = r'E:\project\dataset\UA-DETRAC\test-labels-xml'
    # 3、转化为yolo格式的txt标签文件存储路径
    save_txt_files1 = r'E:\project\dataset\UA-DETRAC\test-labels-yolo'

    convert_annotation(xml_files1, save_txt_files1, classes)

3 处理完毕后我们会得到以下内容

UA-DETRAC数据集转YOLO格式_第1张图片
UA-DETRAC数据集转YOLO格式_第2张图片

其中输出YOLO格式的标注文件名为MVI_20011__img00001.txt,相比图片的文件名多了一个 MVI_20011__ 的前缀。 (其实就是存放图片文件夹的文件名)

所以后面我们需要对图像的文件名进行下处理,将其修改为和标注文件相同的名字!

三: 修改图像名称

一个代码搞定

import os

# 获取要修改的文件地址
path = r'E:\project\dataset\UA-DETRAC\test'
# 获取文件名列表
file_list = os.listdir(path)
print('文件列表如下:')
print(file_list)

# # 遍历文件名,获取文件名和扩展名
for file in file_list:
    path_2 = path + '/' + file
    file_list_inner = os.listdir(path_2)
    for filename in file_list_inner:
        pos = filename.rfind('.') - 8
        newname = file + '__' + filename[pos:-4] + '.jpg'
        #重新命名文件
        os.rename(path_2+'/'+filename,path_2+'/'+newname)

UA-DETRAC数据集转YOLO格式_第3张图片

处理完成!接下来按照yolo训练文件格式调整下文件顺序就好了。

你可能感兴趣的:(yolov5,YOLO,计算机视觉,目标检测)