（1）WiderPerson数据集详情

<1> 应用项目

人体检测

<2> 数据集地址

http://www.cbsr.ia.ac.cn/users/sfzhang/WiderPerson/

<3> 归属单位

生物测定和安全研究中心（CBSR）、国家模式识别实验室（NLPR）、中国科学院自动化研究所

<4> 详细介绍

WiderPerson数据集是一个在野外的行人检测基准数据集，其中的图像是从广泛的场景中选择的，不再局限于交通场景。选取13382幅图像，标注约400K个各种遮挡的标注。随机选取8000/1000/4382幅图像作为训练、验证和测试子集。与CityPersons和更宽的面数据集类似，我们不发布测试图像的边界框地面真相。用户需要提交最终预测文件，我们将继续进行评估。

<5> 数据下载及格式介绍

Download the WiderPerson dataset through Google Drive or Baidu Drive (uq3u), unzip the downloaded file, get the following files:

# （1）文件目录
• "./Images": 13,382 images of this dataset.
• "./Annotations": 9,000 annotation text files of training and valiadation subsets.
• "./Evaluation": evaluation codes.
• "./train.txt": file list of training subset.
• "./test.txt": file list of testing subset.
• "./val.txt": file list of validation subset.
• "./ReadMe.txt": file of instruction.
    
# （2）注释格式
“../Images”文件夹（例如000001.jpg）中的训练和有效性子集的每个图像在“../Annotations”文件夹（例如000001）中具有相应的注释文本文件。jpg.txt文件). 注释文件结构的格式如下：

... 
< number of annotations in this image = N > 
< anno 1 > 
< anno 2 > 
... 
< anno N > 
... 

其中每行一个对象实例为[class_label，x1，y1，x2，y2]，类标签定义为：

... 
< class_label =1: pedestrians > 
< class_label =2: riders > 
< class_label =3: partially-visible persons > 
< class_label =4: ignore regions > 
< class_label =5: crowd > 
... 


# (3) 检测输出
每个图像的检测结果应该是一个与图像前缀相同但后缀为“.txt”的文本文件，例如：000001.jpg->000001.txt。所有检测文本文件都应放在文件夹中进行评估。检测输出文件预期如下格式

format: 
... 
< number of detections in this image = N > 
< det 1 > 
< det 2 > 
... 
< det N > 
... 

每个检测到的边界框的格式应为“[x1，y1，x2，y2，score]”。

YOLO_73">（2）WiderPerson转YOLO格式

<1> 文件夹结构

WiderPerson
	├─ WiderPerson
       ├─ Annotations
          ├─ 000040.jpg.txt
          ├─ .......
       ├─ Evaluation
       ├─ Images
          ├─ 000040.jpg
          ├─ .......
       ├─ train.txt
       ├─ val.txt
       ├─ test.txt
	├─ widerperson_visual.py
	├─ widerperson2yolo.py

<2> 数据可视化

widerperson_visual.py

# -*- coding: utf-8 -*-

import os
import cv2

if __name__ == '__main__':
    path = './WiderPerson/train.txt'
    with open(path, 'r') as f:
        img_ids = [x for x in f.read().splitlines()]

    for img_id in img_ids:  # '000040'
        img_path = './WiderPerson/Images/' + img_id + '.jpg'
        img = cv2.imread(img_path)

        im_h = img.shape[0]
        im_w = img.shape[1]
        print(img_path)
        label_path = img_path.replace('Images', 'Annotations') + '.txt'
        print(label_path)
        with open(label_path) as file:
            line = file.readline()
            count = int(line.split('\n')[0])  # 里面行人个数
            line = file.readline()
            while line:
                cls = int(line.split(' ')[0])
                print(cls)
                # < class_label =1: pedestrians > 行人
                # < class_label =2: riders >      骑车的
                # < class_label =3: partially-visible persons > 遮挡的部分行人
                # < class_label =4: ignore regions > 一些假人，比如图画上的人
                # < class_label =5: crowd > 拥挤人群，直接大框覆盖了
                if cls == 1 or cls == 3:
                    xmin = float(line.split(' ')[1])
                    ymin = float(line.split(' ')[2])
                    xmax = float(line.split(' ')[3])
                    ymax = float(line.split(' ')[4].split('\n')[0])
                    img = cv2.rectangle(img, (int(xmin), int(ymin)), (int(xmax), int(ymax)), (0, 255, 0), 2)
                line = file.readline()
        cv2.imshow('result', img)
        cv2.waitKey(0)

YOLO_141"><3> YOLO格式标签转化

widerperson2yolo.py

# -*- coding: utf-8 -*-

import os
from PIL import Image
import shutil


# coding=utf-8
def check_charset(file_path):
    import chardet
    with open(file_path, "rb") as f:
        data = f.read(4)
        charset = chardet.detect(data)['encoding']
    return charset


def convert(size, box0, box1, box2, box3):
    dw = 1. / size[0]
    dh = 1. / size[1]
    x = (box0 + box2) / 2 * dw
    y = (box1 + box3) / 2 * dh
    w = (box2 - box0) * dw
    h = (box3 - box1) * dh
    return (x, y, w, h)


def extract_labels_images(outpath_txt, outpath_jpg, ori_data_path, origin_txt_path):
    with open(origin_txt_path, 'r') as f:
        img_ids = [x for x in f.read().splitlines()]

    for img_id in img_ids:  # '000040'
        img_path = ori_data_path + '/Images/' + img_id + '.jpg'

        with Image.open(img_path) as Img:
            img_size = Img.size

        ans = ''

        label_path = img_path.replace('Images', 'Annotations') + '.txt'

        outpath = outpath_txt + "\\" + img_id + '.txt'

        with open(label_path, encoding=check_charset(label_path)) as file:
            line = file.readline()
            count = int(line.split('\n')[0])  # 里面行人个数
            line = file.readline()
            while line:
                cls = int(line.split(' ')[0])
                if cls == 1:
                    # if cls == 1  or cls == 3:
                    xmin = float(line.split(' ')[1])
                    ymin = float(line.split(' ')[2])
                    xmax = float(line.split(' ')[3])
                    ymax = float(line.split(' ')[4].split('\n')[0])
                    # print(img_size[0], img_size[1], xmin, ymin, xmax, ymax)
                    bb = convert(img_size, xmin, ymin, xmax, ymax)
                    ans = ans + '1' + ' ' + ' '.join(str(a) for a in bb) + '\n'
                line = file.readline()
        with open(outpath, 'w') as outfile:
            outfile.write(ans)
        # 想保留原文件用copy
        # shutil.copy(img_path, outpath_o + '\\' + img_id + '.jpg')
        # 直接移动用这个
        shutil.move(img_path, outpath_jpg + '\\' + img_id + '.jpg')


def write_label(otxt_path, ntxt_path):
    filer = []
    for root, dirs, files in os.walk(otxt_path):
        for i in files:
            otxt = os.path.join(otxt_path, i)
            ntxt = os.path.join(ntxt_path, i)
            f = open(otxt, 'r', encoding='utf-8')
            for line in f.readlines():
                if line == '\n':
                    continue
                cls = line.split(" ")
                """
                若类别留的是1、2、3，这种多类别，此行代码是将其变为 0、1、2（主要针对YOLO算法的标签要从0开始的这个规定）
                而若需要将1、2、3类别都当做是一类， 那么不用解开注释，这段代码也相当于是归类处理了
                """
                # cls = '%s'%(int(cls[0])-1) + " " + cls[1]+ " " + cls[2]+ " " + cls[3]+ " " + cls[4]
                cls = '0' + " " + cls[1] + " " + cls[2] + " " + cls[3] + " " + cls[4]
                filer.append(cls)
            with open(ntxt, "a") as f:
                for i in filer:
                    f.write(i)
            filer = []


def write_train_val_txt(labels_path, txt_path, image_set):
    image_i = []

    for image_ids in os.listdir(labels_path + '\\%s' % (image_set)):
        _name = image_ids.split(".")[0]
        image_i.append(_name)
    list_file = open(txt_path + '\\%s.txt' % (image_set), 'a')
    for c_id in image_i:
        # print(c_id)
        list_file.write('./images' + '/%s/%s.jpg\n' % (image_set, c_id))
    list_file.close()


if __name__ == '__main__':
    print('WiderPerson数据集yolo格式文件抽取程序启动：')
    # 原始数据集路径
    ori_data_path = './WiderPerson'
    # 输出数据子集路径
    out_data_path = './WiderPerson/WiderPerson_yolo'

    sets = ['train', 'val']
    for data_set in sets:
        # 第一步：类别抽取
        # 抽取类别label存储路径
        print('（1）' + data_set + '数据类别抽取中......')
        outpath_txt = out_data_path + '/label/' + data_set
        # 抽取类别images存储路径
        outpath_jpg = out_data_path + '/images/' + data_set
        os.makedirs(outpath_txt)
        os.makedirs(outpath_jpg)
        # 原数据集标签文件路径
        origin_txt_path = ori_data_path + '/' + data_set + '.txt'
        extract_labels_images(outpath_txt, outpath_jpg, ori_data_path, origin_txt_path)

        # 第二步：写label
        print('（2）' + data_set + '_label文件写入中......')
        otxt_path = out_data_path + "/label/" + data_set
        ntxt_path = out_data_path + "/labels/" + data_set
        os.makedirs(ntxt_path)
        write_label(otxt_path, ntxt_path)

        # 第三步：写trian.txt和val.txt
        print('（3）' + data_set + '.txt写入中......')
        labels_path = out_data_path + "/labels"
        txt_path = out_data_path + "/labels"
        write_train_val_txt(labels_path, txt_path, data_set)
    print('（4）' + '删除多余文件中......')
    shutil.rmtree(out_data_path + "/label")
    print('数据集抽取完成！！！')