Visdrone2019DET数据集介绍
配备摄像机的无人机或通用无人机已经快速部署到广泛的应用中,包括农业,航空摄影,快速交付和监视。因此,对从这些平台收集的视觉数据的自动理解的要求越来越高,这使计算机视觉越来越紧密地应用于无人机。我们很高兴为大规模的基准测试提供详细说明的真实性,以完成各种重要的计算机视觉任务,称为VisDrone,以使视觉满足无人机的要求。
标签类型
注:两种有用的注释:truncation截断率,occlusion遮挡率。
被遮挡的对象比例来定义遮挡率。
截断率用于指示对象部分出现在框架外部的程度。
值得一提的是,如果目标的截断率大于50%,则会在评估过程中将其跳过。
txt2voc.py(只提取行人)
import os
from pathlib import Path
from PIL import Image
import csv
def convert(size, box):
dw = 1. / size[0]
dh = 1. / size[1]
x = (box[0] + box[2] / 2) * dw
y = (box[1] + box[3] / 2) * dh
w = box[2] * dw
h = box[3] * dh
return (x, y, w, h)
wd = os.getcwd()
if not os.path.exists('labels'):
os.makedirs('labels')
train_file = 'images.txt'
train_file_txt = ''
anns = os.listdir('annotations')
for ann in anns:
person_number = 0
ans = ''
outpath = wd + '/labels/' + ann
if ann[-3:] != 'txt':
continue
with Image.open(wd + '/JPEGImages/' + ann[:-3] + 'jpg') as Img:
img_size = Img.size
with open(wd + '/annotations/' + ann, newline='') as csvfile:
spamreader = csv.reader(csvfile)
for row in spamreader:
if (int(row[5]) - 1)<2:
person_number+=1
if row[4] == '0':
continue
bb = convert(img_size, tuple(map(int, row[:4])))
#bb = convert(img_size, list(map(int,row[:4])))
ans = ans + str(0) + ' ' + ' '.join(str(a) for a in bb) + '\n'
with open(outpath, 'w') as outfile:
outfile.write(ans)
if person_number>0:
train_file_txt = train_file_txt + wd + '/JPEGImages/' + ann[:-3] + 'jpg\n'
with open(train_file, 'w') as outfile:
outfile.write(train_file_txt)
Visdrone2019MOT数据集介绍
标签类型
mot2voc.py(只提取行人)
import os
import shutil
from PIL import Image
import csv
import progressbar
def save_voc(image_voc,save_voc_path):
save_voc_path = './labels/'+save_voc_path+'.txt'
with open(save_voc_path, 'w') as outfile:
outfile.write(image_voc)
return
def convert(size, box):
dw = 1. / size[0]
dh = 1. / size[1]
x = (box[0] + box[2] / 2) * dw
y = (box[1] + box[3] / 2) * dh
w = box[2] * dw
h = box[3] * dh
return (x, y, w, h)
def main():
if not os.path.exists('./labels'):
os.makedirs("./labels")
if not os.path.exists('./JPEGImages'):
os.makedirs("./JPEGImages")
image_dir_list = os.listdir('./sequences')
dir_number = 0
for image_dir in image_dir_list:
count = 0
txt_name = './annotations/'+image_dir+'.txt'
image_list = os.listdir('./sequences/'+image_dir)
bar = progressbar.ProgressBar(maxval=len(image_list)).start()
with Image.open('./sequences/' + image_dir + '/' + image_list[1]) as Img:
img_size = Img.size
for image in image_list:
count += 1
bar.update(count)
voc_contain = ''
image_voc = []
image_number = int(image[:-4])
txt_list = csv.reader(open(txt_name))
for line in txt_list:
fram_id = int(line[0])
if fram_id == image_number:
visible = float(line[-1])
label_class = line[-3]
if (label_class == '1' or label_class == '2') and visible < 2:
box = convert(img_size,tuple(map(int,line[2:6])))
voc_contain = voc_contain+str(0) + ' ' + ' '.join(str(a) for a in box) + '\n'
if voc_contain != None:
save_voc(voc_contain,str(dir_number)+str(dir_number)+image[:-4])
shutil.copy('./sequences/' + image_dir + '/'+image, './JPEGImages' + '/' + str(dir_number)+str(dir_number)+image[:-4]+'.jpg') # 将文件移动到指定文件夹并重新命名
bar.finish()
dir_number+=1
train_txt = './train.txt'
image_train_list = os.listdir('./JPEGImages')
pwd = os.getcwd()
path = ''
for i in image_train_list:
path = path+pwd +'/'+i+'\n'
out = open(train_txt, 'w')
out.write(path)
if __name__ == '__main__':
main()
MOT20-Det数据集
mot转voc.py
使用 python3 name.py 20
脚本出处
import cv2
import os
import numpy as np
import time
import argparse
import shutil
import codecs
import progressbar
train_17 = ['MOT17-Det/train/MOT17-02/',
'MOT17-Det/train/MOT17-04/',
'MOT17-Det/train/MOT17-05/',
'MOT17-Det/train/MOT17-09/',
'MOT17-Det/train/MOT17-10/',
'MOT17-Det/train/MOT17-11/',
'MOT17-Det/train/MOT17-13/']
test_17 = ['MOT17-Det/test/MOT17-01/',
'MOT17-Det/test/MOT17-03/',
'MOT17-Det/test/MOT17-06/',
'MOT17-Det/test/MOT17-07/',
'MOT17-Det/test/MOT17-08/',
'MOT17-Det/test/MOT17-12/',
'MOT17-Det/test/MOT17-14/']
train_20 = ['MOT20Det/train/MOT20-01/',
'MOT20Det/train/MOT20-02/']
# 'MOT20Det/train/MOT20-03/',
# 'MOT20Det/train/MOT20-05/'
test_20 = []
# test_20 = ['MOT20Det/test/MOT20-04/','MOT20Det/test/MOT20-06/','MOT20Det/test/MOT20-07/','MOT20Det/test/MOT20-08/']
def parse_args():
parser = argparse.ArgumentParser(description='Convert MOT2VOC format')
parser.add_argument(
'year',
choices=['17', '20'],
default='none',
help='year of MOT dataset')
args = parser.parse_args()
return args
def parse_ini(dir):
ini_fp = open(dir + 'seqinfo.ini','r')
seq_info = ini_fp.readlines()
seqLenth = int(seq_info[4][10:])
imWidth = int(seq_info[5][8:])
imHeight = int(seq_info[6][9:])
return seqLenth,imWidth,imHeight
def gennerate_gt(gt,Annotation,frame,filename,width,height):
fp_gt = open(gt)
gt_lines = fp_gt.readlines()
gt_fram = []
for line in gt_lines:
fram_id = int(line.split(',')[0])
if fram_id == frame:
visible = float(line.split(',')[8])
label_class = line.split(',')[7]
if (label_class == '1' or label_class == '2' or label_class == '7') and visible > 0.3:
gt_fram.append(line)
with codecs.open(Annotation + filename + '.xml', 'w') as xml:
xml.write('<?xml version="1.0" encoding="UTF-8"?>\n')
xml.write('<annotation>\n')
xml.write('\t<folder>' + 'voc' + '</folder>\n')
xml.write('\t<filename>' + filename + '.jpg' + '</filename>\n')
# xml.write('\t<path>' + path + "/" + info1 + '</path>\n')
xml.write('\t<source>\n')
xml.write('\t\t<database> The MOT-Det </database>\n')
xml.write('\t</source>\n')
xml.write('\t<size>\n')
xml.write('\t\t<width>' + str(width) + '</width>\n')
xml.write('\t\t<height>' + str(height) + '</height>\n')
xml.write('\t\t<depth>' + '3' + '</depth>\n')
xml.write('\t</size>\n')
xml.write('\t\t<segmented>0</segmented>\n')
for bbox in gt_fram:
x1 = int(bbox.split(',')[2])
y1 = int(bbox.split(',')[3])
x2 = int(bbox.split(',')[4])
y2 = int(bbox.split(',')[5])
xml.write('\t<object>\n')
xml.write('\t\t<name>person</name>\n')
xml.write('\t\t<pose>Unspecified</pose>\n')
xml.write('\t\t<truncated>0</truncated>\n')
xml.write('\t\t<difficult>0</difficult>\n')
xml.write('\t\t<bndbox>\n')
xml.write('\t\t\t<xmin>' + str(x1) + '</xmin>\n')
xml.write('\t\t\t<ymin>' + str(y1) + '</ymin>\n')
xml.write('\t\t\t<xmax>' + str(x1 + x2) + '</xmax>\n')
xml.write('\t\t\t<ymax>' + str(y1 + y2) + '</ymax>\n')
xml.write('\t\t</bndbox>\n')
xml.write('\t</object>\n')
xml.write('</annotation>')
#用于校验图片数量和标注数量是否一致
def check_num(data_dir, JPEGImage_dir,Annotations_dir=None,ori_num = 0):
num = 0
for folder in data_dir:
folder_len,_,_ = parse_ini(folder)
num += folder_len
img_list = os.listdir(JPEGImage_dir)
if ori_num==0:
img_num = len(img_list)
else:
img_num = len(img_list)-ori_num
# print('img_num:',img_num)
if Annotations_dir:
ann_list = os.listdir(Annotations_dir)
ann_num = len(ann_list)
assert ann_num == num
assert img_num == num,'if it is the second time run this demo, please delete the JPEGImages folder and retry'
# print('num:', num)
print('folders {} have been succeed checked'.format(data_dir))
return num
def segment_dataset(ImageSets,Main,thr1 = 0.8,thr2 = 0.9):
fp_all = open(ImageSets + 'train_all.txt', 'r')
fp_train = open(Main + 'train.txt', 'w')
fp_test = open(Main + 'test.txt', 'w')
fp_val = open(Main + 'val.txt', 'w')
train_list = fp_all.readlines()
print(len(train_list))
for line in train_list:
rand_a = np.random.rand(1)
if rand_a <= thr1:
fp_train.writelines(line)
if rand_a > thr1 and rand_a <= thr2:
fp_val.writelines(line)
if rand_a > thr2 and rand_a <= 1:
fp_test.writelines(line)
fp_train.close()
fp_val.close()
fp_test.close()
print('segment the MOT dataset into train,val,test subsets')
def main():
train_dirs = train_20
test_dirs = test_20
motyear = 20
folder = 'data/'+'MOT' + str(motyear) + 'Det'+'/VOC2007/'
Annotations = folder+'Annotations/'
ImageSets = folder + 'ImageSets/'
JPEGImages = folder + 'JPEGImages/'
Main = ImageSets + 'Main/'
if not os.path.exists(Annotations):
os.makedirs(Annotations)
if not os.path.exists(ImageSets):
os.makedirs(ImageSets)
if not os.path.exists(JPEGImages):
os.makedirs(JPEGImages)
if not os.path.exists(Main):
os.makedirs(Main)
fp_txt = open(ImageSets + 'train_all.txt', 'w')
fp_test = open(ImageSets + 'test_all.txt', 'w')
for train_ in train_dirs:
seqLenth, imWidth, imHeight = parse_ini(train_)
img1 = train_ + 'img1/'
gt = train_ + 'gt/gt.txt'
folder_id = train_[-3:-1]
img_list = os.listdir(img1)
count = 0
assert len(img_list) == seqLenth
bar = progressbar.ProgressBar(maxval=len(img_list)).start()
for img in img_list:
count += 1
bar.update(count)
format_name = folder_id + img
fp_txt.writelines(format_name[:-4] + '\n') # 将生成的新的文件名写入train_all.txt,用于后续数据集拆分
shutil.copy(img1 + img, JPEGImages + '/' + format_name) # 将文件移动到指定文件夹并重新命名
frame = int(img[:-4])
gennerate_gt(gt, Annotation=Annotations, frame=frame, filename=format_name[:-4], width=imWidth,
height=imHeight) #生成标注文件
bar.finish()
fp_txt.close()
train_num = check_num(train_dirs,JPEGImages,Annotations)
for test_ in test_dirs:
img2 = test_ + 'img1/'
folder_id = test_[-3:-1]
test_list = os.listdir(img2)
test_seqLen,_,_ = parse_ini(test_)
assert test_seqLen==len(test_list)
bar = progressbar.ProgressBar(maxval=len(test_list)).start()
count = 0
for img in test_list:
count += 1
bar.update(count)
format_name = folder_id + img
fp_test.writelines(format_name[:-4] + '\n') # 将生成的新的文件名写入train_all.txt,用于后续数据集拆分
shutil.copy(img2 + img, JPEGImages + '/' + format_name) # 将文件移动到指定文件夹并重新命名
bar.finish()
fp_test.close()
check_num(test_dirs, JPEGImages, Annotations_dir=None,ori_num=train_num) # 校验核对处理后的数据集的数据是否正确
segment_dataset(ImageSets,Main)
if __name__ == '__main__':
main()
再转一次voc.py
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
sets=[('2007', 'train'), ('2007', 'val'), ('2007', 'test')]
classes = ["person"]
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(year, image_id):
in_file = open('VOCdevkit/VOC%s/Annotations/%s.xml'%(year, image_id))
out_file = open('VOCdevkit/VOC%s/labels/%s.txt'%(year, 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
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))
bb = convert((w,h), b)
out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
wd = getcwd()
for year, image_set in sets:
if not os.path.exists('VOCdevkit/VOC%s/labels/'%(year)):
os.makedirs('VOCdevkit/VOC%s/labels/'%(year))
image_ids = open('VOCdevkit/VOC%s/ImageSets/Main/%s.txt'%(year, image_set)).read().strip().split()
list_file = open('%s_%s.txt'%(year, image_set), 'w')
for image_id in image_ids:
list_file.write('%s/VOCdevkit/VOC%s/JPEGImages/%s.jpg\n'%(wd, year, image_id))
convert_annotation(year, image_id)
list_file.close()
os.system("cat 2007_train.txt 2007_val.txt > train.txt")
os.system("cat 2007_test.txt> test.txt")