赞
踩
常用的数据集:
数据集下载链接:https://kaiyangzhou.github.io/deep-person-reid/datasets.html
https://kaiyangzhou.github.io/deep-person-reid/datasets.html#sensereid-sensereid
market1501的图片命名信息,以图片 0012_c4s1_000826_01.jpg 对数据集命名进行说明
DPM 检测器是DPM 是一种基于部件的模型,它将目标(如行人)视为多个部分的组合,这些部分可以有不同的形状和大小,并且它们之间的相对位置可以变形。例如在行人检测中,部件可能包括头部、手臂、躯干、腿等。这些部件被建模为滤波器,用于在图像中搜索与之对应的特征。
数据集的文件格式分析
下载好的 Market 1501 包括以下几个文件夹:
因此,我们只需要创建几个文件夹-bounding_box_test 、bounding_box_train和query。使用的代码如下:
import os
def make_market_dir(dst_dir='./'):
market_root = os.path.join(dst_dir, 'market1501')
train_path = os.path.join(market_root, 'bounding_box_train')
query_path = os.path.join(market_root, 'query')
test_path = os.path.join(market_root, 'bounding_box_test')
if not os.path.exists(train_path):
os.makedirs(train_path)
if not os.path.exists(query_path):
os.makedirs(query_path)
if not os.path.exists(test_path):
os.makedirs(test_path)
if __name__ == '__main__':
make_market_dir(dst_dir='./reID')
链接:https://pan.baidu.com/s/1Yf-Smagh1SOZzmhl7agzjQ
提取码:8741
将整个market1501数据集作为训练集,抽取的结果一共有 29419 张图片, ID从0001到1501一共1501 个不同ID的行人。
import re
import os
import shutil
def extract_market(src_path, dst_dir):
img_names = os.listdir(src_path)
pattern = re.compile(r'([-\d]+)_c(\d)')
pid_container = set()
for img_name in img_names:
if '.jpg' not in img_name:
continue
print(img_name)
# pid: 每个人的标签编号 1
# _ : 摄像头号 2
pid, _ = map(int, pattern.search(img_name).groups())
# 去掉没用的图片
if pid == 0 or pid == -1:
continue
shutil.copy(os.path.join(src_path, img_name), os.path.join(dst_dir, img_name))
if __name__ == '__main__':
src_train_path = './Market-1501-v15.09.15/bounding_box_train'
src_query_path = './Market-1501-v15.09.15/query'
src_test_path = './Market-1501-v15.09.15/bounding_box_test'
# 将整个market1501数据集作为训练集
dst_dir = './reID/market1501/bounding_box_train'
extract_market(src_train_path, dst_dir)
extract_market(src_query_path, dst_dir)
extract_market(src_test_path, dst_dir)
链接:https://pan.baidu.com/s/1y74mhK0PkIPBscHUxh-uGA
提取码:xvbc
CUHK03一共有 14097 张图片, ID从001502到002968一共1467个不同ID的行人
import glob
import re
import os.path as osp
import shutil
import re
import os
import shutil
def extract_cuhk03(src_path, dst_dir):
img_names = os.listdir(src_path)
pattern = re.compile(r'([-\d]+)_c(\d)_([\d]+)')
pid_container = set()
for img_name in img_names:
if '.png' not in img_name and '.jpg' not in img_name:
continue
print(img_name)
# pid: 每个人的标签编号 1
# camid : 摄像头号 2
pid, camid, fname = map(int, pattern.search(img_name).groups())
# 这里注意需要加上前面的market1501数据集的最后一个ID 1501
# 在前面数据集的最后那个ID基础上继续往后排
pid += 1501
dst_img_name = str(pid).zfill(6) + '_c' + str(camid) + '_CUHK' + str(fname) + '.jpg'
shutil.copy(os.path.join(src_path, img_name), os.path.join(dst_dir, dst_img_name))
if __name__ == '__main__':
src_train_path = './cuhk03-np/detected/bounding_box_train'
src_query_path = './cuhk03-np/detected/query'
src_test_path = './cuhk03-np/detected/bounding_box_test'
dst_dir = './reID/market1501/bounding_box_train'
extract_cuhk03(src_train_path, dst_dir)
extract_cuhk03(src_query_path, dst_dir)
extract_cuhk03(src_test_path, dst_dir)
链接:https://pan.baidu.com/s/1EKmiYw9ZltvzJUAlYd06fQ
提取码:abg3
MSMT17一共有 126441 张图片, ID从002969到007069一共1467个不同ID的行人。
import re
import os
import shutil
def msmt2market(dir_path, dst_dir, prev_pid):
img_names = os.listdir(dir_path)
pattern = re.compile(r'([-\d]+)_c([-\d]+)_([\d]+)')
for img_name in img_names:
# 判断是否是jpg格式的图片
if '.jpg' not in img_name:
continue
print(img_name)
# pid: 每个人的标签编号 1
# _ : 摄像头号 2
pid, camid, fname = map(int, pattern.search(img_name).groups())
print(pid)
# 去掉没用的图片
if pid == -1:
continue
pid_new = pid + 1 + prev_pid
dst_img_name = str(pid_new).zfill(6) + '_c' + str(camid) + '_MSMT' + str(fname) + '.jpg'
print(dst_img_name)
shutil.copy(os.path.join(dir_path, img_name),os.path.join(dst_dir, dst_img_name))
if __name__ == '__main__':
src_train_path = './MSMT17/bounding_box_train'
src_query_path = './MSMT17/query'
src_test_path = './MSMT17/bounding_box_test'
dst_dir = './reID/market1501/bounding_box_train'
msmt2market(src_train_path, dst_dir, 2968)
msmt2market(src_query_path, dst_dir, 4009)
msmt2market(src_test_path, dst_dir, 4009)
链接:https://pan.baidu.com/s/1J6FAuse1VeFGurWQ7EOpxQ
提取码:1vsg
转换后的viper数据集一共有1264张图片, ID从007070到007943一共1467个不同ID的行人。需要注意这里ID不是连续的,不过只要ID跟之前不重复即可
import re
import os
import shutil
def extract_viper(src_path, dst_dir, camid=1):
img_names = os.listdir(src_path)
pattern = re.compile(r'([\d]+)_([\d]+)')
pid_container = set()
for img_name in img_names:
if '.bmp' not in img_name:
continue
print(img_name)
pid, fname = map(int, pattern.search(img_name).groups())
# 这里注意需要加上前面的数据集的最后一个ID 7069
# 由于viper数据集ID是从0开始,因此需要+1
pid += 7069 + 1
dst_img_name = str(pid).zfill(6) + '_c' + str(camid) + '_viper' + str(fname) + '.jpg'
shutil.copy(os.path.join(src_path, img_name), os.path.join(dst_dir, dst_img_name))
if __name__ == '__main__':
src_cam_a = './VIPeR/cam_a'
src_cam_b = './VIPeR/cam_b'
dst_dir = './reID/market1501/bounding_box_train'
extract_viper(src_cam_a, dst_dir, camid=1)
extract_viper(src_cam_b, dst_dir, camid=2)
链接:https://pan.baidu.com/s/1tkjzN_-g-GwmSY7eCUPisw
提取码:4ttv
转换后的prid数据集一共有2268张图片
import re
import os
import shutil
def extract_prid(src_path, dst_dir, prevID, camid=1):
pattern = re.compile(r'person_([\d]+)')
pid_container = set()
sub_dir_names = os.listdir(src_path) # ['person_0001', 'person_0002',...
for sub_dir_name in sub_dir_names: # 'person_0001'
img_names_all = os.listdir(os.path.join(src_path, sub_dir_name))
# 这里我就只取首尾两张,防止重复太多了
img_names = [img_names_all[0], img_names_all[-1]]
for img_name in img_names: # '0001.png'
if '.png' not in img_name:
continue
print(img_name)
# parent.split('\\')[-1] : person_0001
pid = int(pattern.search(sub_dir_name).group(1))
pid += prevID
print(pid)
dst_img_name = str(pid).zfill(6) + '_c' + str(camid) + '_prid' + img_name.replace('.png', '.jpg')
print(dst_img_name)
shutil.copy(os.path.join(src_path, sub_dir_name, img_name), os.path.join(dst_dir, dst_img_name))
if __name__ == '__main__':
src_cam_a = './prid_2011/multi_shot/cam_a'
src_cam_b = './prid_2011/multi_shot/cam_b'
dst_dir = './reID/market1501/bounding_box_train'
extract_prid(src_cam_a, dst_dir, 7943)
extract_prid(src_cam_b, dst_dir, 8328)
链接:https://pan.baidu.com/s/1FfYx57Zc7iGuCQa1fMRRHA
提取码:yoww
转换后的ilids数据集一共有600张图片
import re
import os
import shutil
def extract_ilids(src_path, dst_dir, prevID, camid):
pattern = re.compile(r'person([\d]+)')
pid_container = set()
sub_dir_names = os.listdir(src_path)
for sub_dir_name in sub_dir_names:
img_names = os.listdir(os.path.join(src_path, sub_dir_name))
for img_name in img_names:
if '.png' not in img_name:
continue
print(img_name)
pid = int(pattern.search(sub_dir_name).group(1))
pid += prevID
dst_img_name = str(pid).zfill(6) + '_c' + str(camid) + '_ilids' + '.jpg'
shutil.copy(os.path.join(src_path, sub_dir_name, img_name), os.path.join(dst_dir, dst_img_name))
if __name__ == '__main__':
src_cam_a = './iLIDS-VID/i-LIDS-VID/images/cam1'
src_cam_b = './iLIDS-VID/i-LIDS-VID/images/cam2'
dst_dir = './reID/market1501/bounding_box_train'
extract_ilids(src_cam_a, dst_dir, 9077, 1)
extract_ilids(src_cam_b, dst_dir, 9077, 2)
链接:https://pan.baidu.com/s/1YbQT2px3Em-3KZTs6pLXmA
提取码:2tbc
grid数据集一共有500张图片
import re
import os
import shutil
def extract_grid(src_path, dst_dir, camid=1):
img_names = os.listdir(src_path)
pattern = re.compile(r'([\d]+)_')
pid_container = set()
for img_name in img_names:
if '.jpeg' not in img_name:
continue
print(img_name)
pid = int(pattern.search(img_name).group(1))
if pid == 0:
continue
pid += 9396
print(pid)
dst_img_name = str(pid).zfill(6) + '_c' + str(camid) + '_grid' + '.jpg'
shutil.copy(os.path.join(src_path, img_name), os.path.join(dst_dir, dst_img_name))
if __name__ == '__main__':
src_cam_a = './underground_reid/probe'
src_cam_b = './underground_reid/gallery'
dst_dir = './reID/market1501/bounding_box_train'
extract_grid(src_cam_a, dst_dir, camid=1)
extract_grid(src_cam_b, dst_dir, camid=2)
链接:https://pan.baidu.com/s/1AviYz5SenijfO5w1TGuEtA
提取码:l0pt
import re
import os
import shutil
def extract_duke(src_path, dst_dir):
img_names = os.listdir(src_path)
pattern = re.compile(r'([-\d]+)_c(\d)_f([\d]+)')
for img_name in img_names:
if '.png' not in img_name and '.jpg' not in img_name:
continue
print(img_name)
# pid: 每个人的标签编号 1
# camid : 摄像头号 2
pid, camid, fname = map(int, pattern.search(img_name).groups())
# 这里注意需要加上前面的market1501数据集的最后一个ID 1501
# 在前面数据集的最后那个ID基础上继续往后排
pid += 9646
print( pid, camid, fname)
dst_img_name = str(pid).zfill(6) + '_c' + str(camid) + '_Duke' + str(fname) + '.jpg'
print(dst_img_name)
shutil.copy(os.path.join(src_path, img_name), os.path.join(dst_dir, dst_img_name))
if __name__ == '__main__':
src_train_path = './DukeMTMC-reID/DukeMTMC-reID/bounding_box_train'
src_test_path ='./DukeMTMC-reID/DukeMTMC-reID/bounding_box_test'
src_query_path = './DukeMTMC-reID/DukeMTMC-reID/query'
dst_dir = './9'
extract_duke(src_train_path, dst_dir)
extract_duke(src_test_path, dst_dir)
import re
import os
import shutil
def extract_SenseReID(src_path, dst_dir, fname):
img_names = os.listdir(src_path)
pattern = re.compile(r'([\d]+)_([\d]+)')
pid_container = set()
for img_name in img_names:
if '.jpg' not in img_name:
continue
print(img_name)
pid, camid = map(int, pattern.search(img_name).groups())
pid += 16786+ 1
dst_img_name = str(pid).zfill(6) + '_c' + str(camid + 1) + '_SenseReID_' + fname + '.jpg'
shutil.copy(os.path.join(src_path, img_name), os.path.join(dst_dir, dst_img_name))
if __name__ == '__main__':
src_cam_a = r'D:\data\SenseReID\test_gallery'
src_cam_b = r'D:\data\SenseReID\test_probe'
dst_dir = r'E:\reID\market1501\bounding_box_train'
extract_SenseReID(src_cam_a, dst_dir, 'gallery')
extract_SenseReID(src_cam_b, dst_dir, 'probe')
在market1501.py脚本修改如下代码:
# 在41行左右
# data_dir = osp.join(self.data_dir, 'Market-1501-v15.09.15')
data_dir = osp.join(self.data_dir, 'reID/market1501')
# 在84行左右
# assert 0 <= pid <= 1501 # pid == 0 means background
# assert 1 <= camid <= 6
assert 0 <= pid <= 16786 # pid == 0 means background
assert 1 <= camid <= 16
参考链接:
1、行人重识别数据集转换–统一为market1501数据集进行多数据集联合训练
2、行人重识别数据集链接
3、行人重识别多个数据集格式统一为market1501格式
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。