Yolo目标检测标注格式转换成多目标跟踪数据集MOT标注格式

1. 多目标跟踪 Deep SORT 数据集MOT说明

(1)概况

seqinfo.ini的内容，相当于对该数据集的说明描述
[Sequence]
name=MOT16-04
imDir=img1
frameRate=30
seqLength=1050
imWidth=1920
imHeight=1080
imExt=.jpg

seqLength 表示 序列的长度，也就是帧的总数1050
图片大小是1920 × 1080

(2)输入det.txt （detection）

1,-1,97,545,79,239,3.1667,-1,-1,-1
1,-1,369,401,79,239,3.1112,-1,-1,-1
1,-1,546.66,146.51,59.629,180.89,2.686,-1,-1,-1
1,-1,1638,255.64,59.629,180.89,2.6417,-1,-1,-1
1,-1,1043.8,134.38,59.629,180.89,2.3391,-1,-1,-1
1,-1,792.96,148.08,55.569,168.71,2.2532,-1,-1,-1
1,-1,1742.1,460.65,68.644,207.93,2.1848,-1,-1,-1
1,-1,1104.4,207.14,59.629,180.89,1.9684,-1,-1,-1
1,-1,498.16,122.26,59.629,180.89,1.4027,-1,-1,-1
1,-1,906.1,125.45,55.569,168.71,1.2634,-1,-1,-1
1,-1,351.89,91.972,63.98,193.94,1.1681,-1,-1,-1
1,-1,222.68,127.67,51.78,157.34,0.97654,-1,-1,-1

加个列标题

<Frame ID>, < Track ID>, <bb_left>, <bb_top>, <bb_width>, <bb_height>, <Confidence score>, <x>, <y>, <z>

0、Frame ID 表示帧ID。
1、Track ID 表示这个object属于哪个track 。每个object只能被分配到一个track，-1表示未分配。
2、3、4、5、接下来的四个数字表示行人在二维图像坐标中的边界框位置。位置由左上角以及边框的宽度和高度表示(无归一化)。
6、confidence score, 置信度。
最后三个7、 8、 9都是-1，xyz，具体怎么用，未知。
就像数据库里面的表，表达一对多的关系。

(3)输出gt.txt (annotation/ground truth (GT) )

1,1,1363,569,103,241,1,1,0.86014
2,1,1362,568,103,241,1,1,0.86173
3,1,1362,568,103,241,1,1,0.86173
4,1,1362,568,103,241,1,1,0.86173
5,1,1362,568,103,241,1,1,0.86173
6,1,1362,568,103,241,1,1,0.86173
7,1,1362,568,103,241,1,1,0.86173
8,1,1362,568,103,241,1,1,0.86173
9,1,1362,568,103,241,1,1,0.86173
10,1,1362,568,103,241,1,1,0.86173

加个列标题

<Frame ID>, <Track ID>, <bb_left>, <bb_top>, <bb_width>, <bb_height>, <0/1> ,<Class ID> ,<Visibility Ratio>

0、Frame ID
1、Track ID
2、3、4、5 bbox坐标（x, y, w, h）
6、是否考虑 the entry，flag： considered (1) ， ignored (0)
7、标注对象的类别
9、可见比例（visibility ratio），因为object的遮挡和图像边框裁剪,用一个介于0和1之间的数字表示该object的可见程度。

2. yolo标签txt转MOT标签det和gt程序

# -*- coding:utf8 -*-
from PIL import Image
import os
import glob
import numpy as np

def txt2det(yolo_labels_dir, mot_labels_det_path):
    object_id = 1  # 目标ID
    with open(mot_labels_det_path, 'w') as mot_file:
        for file in os.listdir(yolo_labels_dir):
            if file.endswith(".txt"):
                yolo_file_path = os.path.join(yolo_labels_dir, file)
                frame_idx = int(file.split("_")[-1].split(".")[0])  # 提取帧索引
                image_width = 1280
                image_height=720

                with open(yolo_file_path, 'r') as yolo_file:
                    lines = yolo_file.readlines()

                    for line in lines:
                        data = line.split()
                        class_id = int(data[0])
                        x_center = float(data[1])
                        y_center = float(data[2])
                        width = float(data[3])
                        height = float(data[4])

                        left = int((x_center - width / 2) * image_width)
                        top = int((y_center - height / 2) * image_height)
                        # right = int((x_center + width / 2) * image_width)
                        # bottom = int((y_center + height / 2) * image_height)
                        w = int(width*image_width)
                        h = int(height * image_height)

                        # 写入MOT标签文件
                        mot_file.write("{},-1,{},{},{},{},1,-1,-1,-1\n".format(frame_idx, left, top, w, h))
                object_id += 1

def txt2gt(yolo_labels_dir, mot_labels_gt_path):
    object_id = 1  # 目标ID
    with open(mot_labels_gt_path, 'w') as mot_file:
        for file in os.listdir(yolo_labels_dir):
            if file.endswith(".txt"):
                yolo_file_path = os.path.join(yolo_labels_dir, file)
                frame_idx = int(file.split("_")[-1].split(".")[0])  # 提取帧索引
                image_width = 1280
                image_height=720

                with open(yolo_file_path, 'r') as yolo_file:
                    lines = yolo_file.readlines()

                    for line in lines:
                        data = line.split()
                        class_id = int(data[0])
                        x_center = float(data[1])
                        y_center = float(data[2])
                        width = float(data[3])
                        height = float(data[4])

                        left = int((x_center - width / 2) * image_width)
                        top = int((y_center - height / 2) * image_height)
                        # right = int((x_center + width / 2) * image_width)
                        # bottom = int((y_center + height / 2) * image_height)
                        w = int(width*image_width)
                        h = int(height * image_height)

                        # 写入MOT标签文件
                        mot_file.write("{},{},{},{},{},{},0,{},1\n".format(frame_idx,object_id,left, top, w, h,class_id))
                object_id += 1

def main():
    # 设置YOLO标签文件夹和MOT标签文件路径
    yolo_labels_dir = "/yolo_txt"
    mot_labels_det_path = "/mot_det.txt"
    mot_labels_gt_path = "/mot_gt.txt"
    # 调用转换函数
    txt2det(yolo_labels_dir, mot_labels_det_path)
    txt2gt(yolo_labels_dir, mot_labels_gt_path)

if __name__ == '__main__':
    main()