visdrone数据集转化为MOT数据集（用作MOTR模型训练）

visdrone数据集转化为MOT数据集

MOT17 数据集格式

├── MOT17
│   ├── images
│   ├── labels_with_ids

train

det.txt

10个参数 或者 8个参数

<frame>, <id>, <bb_left>, <bb_top>, <bb_width>, <bb_height>, <conf>, <x>, <y>, <z> 

• 第1个代表第几帧
• 第2个代表轨迹编号（在这个文件里总是为-1）
• bb开头的4个数代表物体框的左上角坐标及长宽
• conf代表置信度
• 最后3个是MOT3D用到的内容，2D检测总是为-1.

gt.txt

9个参数

• 第1个代表第几帧
• 第2个值为目标运动轨迹的ID号
• 第3个到第6个数代表物体框的左上角坐标及长宽
• 第7个值为目标轨迹是否进入考虑范围内的标志，0表示忽略，1表示active
• 第8个值为该轨迹对应的目标种类（种类见下面的表格中的label-ID对应情况）
• 第9个值为box的visibility ratio，表示目标运动时被其他目标box包含/覆盖或者目标之间box边缘裁剪情况。

seqinfo.ini

主要介绍视频的帧率、分辨率等基本信息。

test

det.txt

数据标签含义与train相同。

visdrone——Task 4_ Multi-Object Tracking

    <frame_index>,<target_id>,<bbox_left>,<bbox_top>,<bbox_width>,<bbox_height>,<score>,<object_category>,<truncation>,<occlusion>

 -----------------------------------------------------------------------------------------------------------------------------------
       Name	                                      Description
 -----------------------------------------------------------------------------------------------------------------------------------
   <frame_index>	  The frame index of the video frame
   
    <target_id>	          In the DETECTION result file, the identity of the target should be set to the constant -1.
		          In the GROUNDTRUTH file, the identity of the target is used to provide the temporal corresponding 
		          relation of the bounding boxes in different frames.
			  
    <bbox_left>	          The x coordinate of the top-left corner of the predicted bounding box

    <bbox_top>	          The y coordinate of the top-left corner of the predicted object bounding box

    <bbox_width>	  The width in pixels of the predicted object bounding box

    <bbox_height>	  The height in pixels of the predicted object bounding box

      <score>	          The score in the DETECTION file indicates the confidence of the predicted bounding box enclosing 
                          an object instance.
                          The score in GROUNDTRUTH file is set to 1 or 0. 1 indicates the bounding box is considered in evaluation, 
		          while 0 indicates the bounding box will be ignored.
			  
  <object_category>	  The object category indicates the type of annotated object, (i.e., 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))
		      
    <truncation>	  The score in the DETECTION file should be set to the constant -1.
                          The score in the GROUNDTRUTH file indicates the degree of object parts appears outside a frame 
		          (i.e., no truncation = 0 (truncation ratio 0%), and partial truncation = 1 (truncation ratio 1% ~ 50%)).
		      
     <occlusion>	  The score in the DETECTION file should be set to the constant -1.
                          The score in the GROUNDTRUTH file indicates the fraction of objects being occluded 
		          (i.e., no occlusion = 0 (occlusion ratio 0%), partial occlusion = 1 (occlusion ratio 1% ~ 50%), 
		          and heavy occlusion = 2 (occlusion ratio 50% ~ 100%)).

├── visdrone
│   ├── images
│   │   ├── train
│   │   │   ├── 视频目录
│   │   │   │   ├── gt
│   │   │   │   ├── img1
│   │   │   │   ├── seqinfo.ini
│   │   ├── test
│   ├── labels_with_ids
│   

配置seqinfo.ini文件

[Sequence]
name=MOT17-02-DPM
imDir=img1
frameRate=30
seqLength=600
imWidth=1920
imHeight=1080
imExt=.jpg

其中，imWidth、imHeight、imExt分别为图片的宽、高、格式；seqLength表示此视频被抽成了多少帧。frameRate为画面更新率。

代码如下

import os
import shutil
from tqdm import tqdm
from PIL import Image


def copyfile(old_folder_path,new_folder_path):
    print('---------------------')
    for file in os.listdir(old_folder_path):
        old_file_path=os.path.join(old_folder_path,file)
        # print(file)
        # print(new_folder_path)
        shutil.copy(old_file_path, new_folder_path)

def makedir(filepath):
    if not os.path.exists(filepath):
        os.mkdir(filepath)

def process(path):
    annotations_path = os.path.join(path, "annotations")
    ann_set = os.listdir(annotations_path)
    # print(ann_set)
    file_path=os.path.join(path,'sequences')
    file_set=os.listdir(file_path)
    # print(file_set)
    for i in tqdm(ann_set):
        f = open(annotations_path + "/" + i, "r")
        print(i)
        name = i.replace(".txt", "")
        print(name)
        img_path=os.path.join(file_path,name)
        img_set=os.listdir(img_path)
        img=Image.open(os.path.join(img_path,img_set[0]))
        for line in f.readlines():
            line = line.replace("\n", "")
            if line.endswith(","):  # filter data
                line = line.rstrip(",")
            line_list = [int(i) for i in line.split(",")]
            new_line_list=[line_list[i] for i in range(0,8)]
            print(line_list)
            # print(new_line_list)
            if(line_list[8]==0 and line_list[9]==0):
                new_line_list.append(1)
            if (line_list[8] == 0 and line_list[9] == 1):
                new_line_list.append(0.9)
            if (line_list[8] == 1 and line_list[9] == 0):
                new_line_list.append(0.8)
            if (line_list[8] == 0 and line_list[9] == 2):
                new_line_list.append(0.7)
            if (line_list[8] == 1 and line_list[9] == 1):
                new_line_list.append(0.5)
            if (line_list[8] == 1 and line_list[9] == 2):
                new_line_list.append(0.3)
            # print(new_line_list)
            url1 = os.path.join(path,name)
            makedir(url1)
            url2=os.path.join(name,'gt')
            makedir(url2)
            file_url=url2+'\\gt.txt'
            print(url2)
            print(file_url)
            if not os.path.isfile(file_url):
                fd = open(file_url, mode="w", encoding="utf-8")
            makedir(file_url)
            with open(file_url, 'a') as file_name:
                str_text = str(new_line_list[0]) + ',' + str(new_line_list[1]) + ',' + str(new_line_list[2]) + ',' + str(
                    new_line_list[3]) + ',' + str(new_line_list[4]) + ',' + str(new_line_list[5]) + ',' + str(
                    new_line_list[6]) + ',' + str(new_line_list[7])+ ',' + str(new_line_list[8])
                print(str_text)
                file_name.write(str_text + '\n')

        ini_path = os.path.join(path, name)
        ini_file=ini_path+'\\seqinfo.ini'
        print('***********************************')
        if not os.path.isfile(ini_file):
            fd = open(ini_file, mode="w", encoding="utf-8")
        with open(ini_file, 'a') as ini_name:
            ini_text ='[Sequence]\n'+'name='+name+'\n'+'imDir=img1\n'+'frameRate=30\n'+'seqLength='+str(len(img_set))+'\n'+'imWidth = '+str(img.size[0])+'\n'+'imHeight = '+str(img.size[1])+'\n'+'imExt =.jpg\n'
            print(ini_text)
            ini_name.write(ini_text + '\n')
        break
    old_path=os.path.join(file_path,name)
    new_path=os.path.join(path,name,'img1')
    print(old_path)
    print(new_path)
    move(old_path,new_path)

def move(old_path,new_path):
    makedir(new_path)
    copyfile(old_path,new_path)

if __name__ == '__main__':
    path1=r'D:\pythonProjects\Test\visdrone2mot\annotations'
    path2=r'D:\pythonProjects\Test\visdrone2mot\sequences'
    path=r'D:\pythonProjects\Test\visdrone2mot'
    process(path)

Linux

import os
import shutil
from tqdm import tqdm
from PIL import Image


def copyfile(old_folder_path,new_folder_path):
    print('---------------------')
    for file in os.listdir(old_folder_path):
        old_file_path=os.path.join(old_folder_path,file)
        # print(file)
        # print(new_folder_path)
        shutil.copy(old_file_path, new_folder_path)

def makedir(filepath):
    if not os.path.exists(filepath):
        os.mkdir(filepath)

def process(path):
    annotations_path = os.path.join(path, "annotations")
    ann_set = os.listdir(annotations_path)
    # print(ann_set)
    file_path=os.path.join(path,'sequences')
    file_set=os.listdir(file_path)
    # print(file_set)
    for i in tqdm(ann_set):
        f = open(annotations_path + "/" + i, "r")
        print(i)
        name = i.replace(".txt", "")
        print(name)
        img_path=os.path.join(file_path,name)
        img_set=os.listdir(img_path)
        img=Image.open(os.path.join(img_path,img_set[0]))
        old_path = os.path.join(file_path, name)
        new_path = os.path.join(path, name, 'img1')
        print(old_path)
        print(new_path)
        move(old_path, new_path)
        for line in f.readlines():
            line = line.replace("\n", "")
            if line.endswith(","):  # filter data
                line = line.rstrip(",")
            line_list = [int(i) for i in line.split(",")]
            new_line_list=[line_list[i] for i in range(0,8)]
            print(line_list)
            # print(new_line_list)
            if(line_list[8]==0 and line_list[9]==0):
                new_line_list.append(1)
            if (line_list[8] == 0 and line_list[9] == 1):
                new_line_list.append(0.9)
            if (line_list[8] == 1 and line_list[9] == 0):
                new_line_list.append(0.8)
            if (line_list[8] == 0 and line_list[9] == 2):
                new_line_list.append(0.7)
            if (line_list[8] == 1 and line_list[9] == 1):
                new_line_list.append(0.5)
            if (line_list[8] == 1 and line_list[9] == 2):
                new_line_list.append(0.3)
            # print(new_line_list)
            url1 = os.path.join(path,name)
            makedir(url1)
            print('url1:',url1)
            url2=os.path.join(url1,'gt')
            print('url2:',url2)
            makedir(url2)
            file_url=url2+'/gt.txt'
            print(url2)
            print(file_url)
            if not os.path.isfile(file_url):
                fd = open(file_url, mode="w", encoding="utf-8")
            makedir(file_url)
            with open(file_url, 'a') as file_name:
                str_text = str(new_line_list[0]) + ',' + str(new_line_list[1]) + ',' + str(new_line_list[2]) + ',' + str(
                    new_line_list[3]) + ',' + str(new_line_list[4]) + ',' + str(new_line_list[5]) + ',' + str(
                    new_line_list[6]) + ',' + str(new_line_list[7])+ ',' + str(new_line_list[8])
                print(str_text)
                file_name.write(str_text + '\n')

        ini_path = os.path.join(path, name)
        ini_file=ini_path+'/seqinfo.ini'
        print('***********************************')
        if not os.path.isfile(ini_file):
            fd = open(ini_file, mode="w", encoding="utf-8")
        with open(ini_file, 'a') as ini_name:
            ini_text ='[Sequence]\n'+'name='+name+'\n'+'imDir=img1\n'+'frameRate=30\n'+'seqLength='+str(len(img_set))+'\n'+'imWidth = '+str(img.size[0])+'\n'+'imHeight = '+str(img.size[1])+'\n'+'imExt =.jpg\n'
            print(ini_text)
            ini_name.write(ini_text + '\n')
        # break
      

def move(old_path,new_path):
    makedir(new_path)
    copyfile(old_path,new_path)

if __name__ == '__main__':
    path='/home/course/ldw/dataset/VisDrone2019-MOT-val/'
    process(path)