Caltech 数据集转换成VOC格式
注意本人用pycharm 运行环境是python2.7.14
如果是python3 可能会存在错误
1. Seq文件转化成JEPG图像文件（）
运行seq2jpg.py文件，输入.seq文件夹，输出到JPEG文件夹中，
将Caltech原始数据集解压到Caltech文件夹 并把Caltech文件夹放在F:/Caltech文件夹下
并在F:/Caltech文件夹下新建一个Caltech_VOC文件夹
输入seq文件路径是F:\Caltech\Caltech
输出图片的存储路径是F:\Caltech\Caltech_VOC\JPEG
seq2jpg.py(可以修改自己的文件路径 对于最好还是按我的路径来 即跟我一样的文件目录 )
#-*- coding:utf-8 -*-
import os.path
import fnmatch #模块的主要作用是文件名称的匹配
import shutil
def open_save(file,savepath):
# 读入一个seq文件，然后拆分成image存入savepath当中
f = open(file,'rb')#以二进制的形式读取图片
#将seq文件的内容转化成str类型
string = str(f.read())
####关键所在
#splitstring是图片的前缀，可以理解成seq是以splitstring为分隔的多个jpg合成的文件
splitstring = "\xFF\xD8\xFF\xE0\x00\x10\x4A\x46\x49\x46"
#split函数做一个测试,因此返回结果的第一个是在seq文件中是空，因此后面省略掉第一个
"""
>>> a = ".12121.3223.4343"
>>> a.split('.')
['', '12121', '3223', '4343']
"""
strlist=string.split(splitstring)
#print(strlist)
#print('######################################')
f.close()
count = 0
# delete the image folder path if it exists
if os.path.exists(savepath):
shutil.rmtree(savepath)
# create the image folder path
if not os.path.exists(savepath):
os.makedirs(savepath)
#遍历每一个jpg文件内容，然后加上前缀合成图片
for img in strlist:
filename = str(count)+'.jpg'
filenamewithpath=os.path.join(savepath, filename)
if count > 0:
i=open(filenamewithpath,'wb+')
i.write(splitstring)
i.write(img)
i.close()
count = count + 1
if __name__=="__main__":
rootdir = "F:\Caltech\Caltech"
saveroot = "F:\Caltech\Caltech_VOC\JPEG"
for parent, dirnames, filenames in os.walk(rootdir):
for filename in filenames:
#fnmatch 全称是 filename match，主要是用来匹配文件名是否符合规则的
if fnmatch.fnmatch(filename,'*.seq'):#找到.seq文件
thefilename = os.path.join(parent, filename) #读取的文件路径
# create the image folder by combining .seq file path with .seq filename
thesavepath = saveroot +'\\'+ parent.split('\\')[-1] + '\\' + filename.split('.')[0]+'\\'
print ("Filename=" + thefilename)
print ("Savepath=" + thesavepath)
open_save(thefilename,thesavepath)转换成图片后，JPEG文件夹对应的目录如下：
其中set00中文件夹V000中的图片如下图所示：
2. VBB标注文件转化为XML文件
运行vbb2voc.py文件，输入annotations文件夹，输出到xmlresult文件夹中。
输入路径F:/Caltech/Caltech/annotations/
输出路径F:/Caltech/Caltech_VOC/xmlresult/
vbb2voc.py（同样只需修改成自己文件输入输出路径即可 对于小白最好还是按我的路径来）
#-*- coding:utf-8 -*-
import os, glob
import cv2
from scipy.io import loadmat
from collections import defaultdict
import numpy as np
from lxml import etree, objectify
def vbb_anno2dict(vbb_file, cam_id):
#通过os.path.basename获得路径的最后部分“文件名.扩展名”
#通过os.path.splitext获得文件名
filename = os.path.splitext(os.path.basename(vbb_file))[0]
#定义字典对象annos
annos = defaultdict(dict)
vbb = loadmat(vbb_file)
# object info in each frame: id, pos, occlusion, lock, posv
objLists = vbb['A'][0][0][1][0]
objLbl = [str(v[0]) for v in vbb['A'][0][0][4][0]] #可查看所有类别
# person index
person_index_list = np.where(np.array(objLbl) == "person")[0] #只选取类别为‘person’的xml
for frame_id, obj in enumerate(objLists):
if len(obj) > 0:
frame_name = str(cam_id) + "_" + str(filename) + "_" + str(frame_id+1) + ".jpg"
annos[frame_name] = defaultdict(list)
annos[frame_name]["id"] = frame_name
annos[frame_name]["label"] = "person"
for id, pos, occl in zip(obj['id'][0], obj['pos'][0], obj['occl'][0]):
id = int(id[0][0]) - 1 # for matlab start from 1 not 0
if not id in person_index_list: # only use bbox whose label is person
continue
pos = pos[0].tolist()
occl = int(occl[0][0])
annos[frame_name]["occlusion"].append(occl)
annos[frame_name]["bbox"].append(pos)
if not annos[frame_name]["bbox"]:
del annos[frame_name]
print (annos)
return annos
def seq2img(annos, seq_file, outdir, cam_id):
cap = cv2.VideoCapture(seq_file)
index = 1
# captured frame list
v_id = os.path.splitext(os.path.basename(seq_file))[0]
cap_frames_index = np.sort([int(os.path.splitext(id)[0].split("_")[2]) for id in annos.keys()])
while True:
ret, frame = cap.read()
print (ret)
if ret:
if not index in cap_frames_index:
index += 1
continue
if not os.path.exists(outdir):
os.makedirs(outdir)
outname = os.path.join(outdir, str(cam_id)+"_"+v_id+"_"+str(index)+".jpg")
print ("Current frame: ", v_id, str(index))
cv2.imwrite(outname, frame)
height, width, _ = frame.shape
else:
break
index += 1
img_size = (width, height)
return img_size
def instance2xml_base(anno, bbox_type='xyxy'):
"""bbox_type: xyxy (xmin, ymin, xmax, ymax); xywh (xmin, ymin, width, height)"""
assert bbox_type in ['xyxy', 'xywh']
E = objectify.ElementMaker(annotate=False)
anno_tree = E.annotation(
E.folder('VOC2014_instance/person'),
E.filename(anno['id']),
E.source(
E.database('Caltech pedestrian'),
E.annotation('Caltech pedestrian'),
E.image('Caltech pedestrian'),
E.url('None')
),
E.size(
E.width(640),
E.height(480),
E.depth(3)
),
E.segmented(0),
)
for index, bbox in enumerate(anno['bbox']):
bbox = [float(x) for x in bbox]
if bbox_type == 'xyxy':
xmin, ymin, w, h = bbox
xmax = xmin+w
ymax = ymin+h
else:
xmin, ymin, xmax, ymax = bbox
E = objectify.ElementMaker(annotate=False)
anno_tree.append(
E.object(
E.name(anno['label']),
E.bndbox(
E.xmin(xmin),
E.ymin(ymin),
E.xmax(xmax),
E.ymax(ymax)
),
E.difficult(0),
E.occlusion(anno["occlusion"][index])
)
)
return anno_tree
def parse_anno_file(vbb_inputdir,vbb_outputdir):
# annotation sub-directories in hda annotation input directory
assert os.path.exists(vbb_inputdir)
sub_dirs = os.listdir(vbb_inputdir) #对应set00,set01...
for sub_dir in sub_dirs:
print ("Parsing annotations of camera: ", sub_dir)
cam_id = sub_dir #set00 set01等
#获取某一个子set下面的所有vbb文件
vbb_files = glob.glob(os.path.join(vbb_inputdir, sub_dir, "*.vbb"))
for vbb_file in vbb_files:
#返回一个vbb文件中所有的帧的标注结果
annos = vbb_anno2dict(vbb_file, cam_id)
if annos:
#组成xml文件的存储文件夹，形如“/Users/chenguanghao/Desktop/Caltech/xmlresult/”
vbb_outdir = vbb_outputdir
#如果不存在
if not os.path.exists(vbb_outdir):
os.makedirs(vbb_outdir)
for filename, anno in sorted(annos.items(), key=lambda x: x[0]):
if "bbox" in anno:
anno_tree = instance2xml_base(anno)
outfile = os.path.join(vbb_outdir, os.path.splitext(filename)[0]+".xml")
print ("Generating annotation xml file of picture: ", filename)
#生成最终的xml文件，对应一张图片
etree.ElementTree(anno_tree).write(outfile, pretty_print=True)
def visualize_bbox(xml_file, img_file):
import cv2
tree = etree.parse(xml_file)
# load image
image = cv2.imread(img_file)
origin = cv2.imread(img_file)
# 获取一张图片的所有bbox
for bbox in tree.xpath('//bndbox'):
coord = []
for corner in bbox.getchildren():
coord.append(int(float(corner.text)))
print (coord)
cv2.rectangle(image, (coord[0], coord[1]), (coord[2], coord[3]), (0, 0, 255), 2)
# visualize image
cv2.imshow("test", image)
cv2.imshow('origin',origin)
cv2.waitKey(0)
def main():
vbb_inputdir = "F:/Caltech/Caltech/annotations/"
vbb_outputdir = "F:/Caltech/Caltech_VOC/xmlresult/"
parse_anno_file(vbb_inputdir,vbb_outputdir)
"""
下面这段是测试代码
"""
"""
xml_file = "F:/Caltech/Caltech_VOC/xmlresult/set00_V000_526.xml"
img_file = "F:/Caltech/Caltech_VOC/JPEG/set00/V000/526.jpg"
visualize_bbox(xml_file, img_file)
"""
if __name__ == "__main__":
main()
在输出文件路径中输出xml文件 共122187个xml文件
文件名是 set00_V000_69.xml等等等 说明并不是每一帧图片中都有人 set00/V000中69.jpg中才有人出现
3.因为xml文件已经在一个统一的文件夹xmlresult中所以要将所有的JPEG文件分别放到统一的文件夹里并按set0_V000_1.jpg的方式，与xml文件格式对应
运行mergeimg.py文件。输入图片路径 F:/Caltech/Caltech_VOC/JPEG
输出图片路径:F:/Caltech/Caltech_VOC/JPEGImage
#-*- coding:utf-8 -*-
#-*- coding:utf-8 -*-
import os
import glob
import shutil
if __name__ == "__main__":
imgpathin = 'F:/Caltech/Caltech_VOC/JPEG'
imgout = 'F:/Caltech/Caltech_VOC/JPEGImage'
for subdir in os.listdir(imgpathin):
print subdir
file_path = os.path.join(imgpathin,subdir)
for subdir1 in os.listdir(file_path):
print subdir1
#jpg_files = glob.glob(os.path.join(file_path, subdir1, "*.jpg"))
file_path1 = os.path.join(file_path, subdir1)
for jpg_file in os.listdir(file_path1):
#print jpg_file
src = os.path.join(file_path1, jpg_file)
new_name=str(subdir+"_"+subdir1+"_"+jpg_file)
dst=os.path.join(imgout,new_name)
os.rename(src,dst)然后会在JPEGImage文件夹看到set0_V000_1.jpg格式的图片 共249884张
4.重命名图片和XML文件
按照“xxxxxx”这样的6位数字索引命名JPEG图片文件以及对应的XML文件。
有人的图片命名为xxxxxx.jpg 对应的xml文件命名为xxxxxx.xml 两个xxxxxx相同
没人的图片保持原名
输入和输出的xml文件路径 均为F:/Caltech/Caltech_VOC/xmlresult
输出的图片路径为F:/Caltech/Caltech_VOC/JPEGImage
运行renameindex.py
#-*- coding:utf-8 -*-
import os
xmlpath = 'F:/Caltech/Caltech_VOC/xmlresult'
imgpath = 'F:/Caltech/Caltech_VOC/JPEGImage'
index = 0
count = 0
emptyset = set()
xmlFiles = os.listdir(xmlpath)
imgFiles = os .listdir(imgpath)
print len(xmlFiles),len(imgFiles)
for xml in xmlFiles:
xmlname = os.path.splitext(xml)[0]
imgname = os.path.join(imgpath,xmlname+'.jpg')
if os.path.exists(imgname):
newName = str(index).zfill(6)
#重命名图像
os.rename(imgname,os.path.join(imgpath,newName+'.jpg'))
#重命名xml文件
os.rename(os.path.join(xmlpath,xml),os.path.join(xmlpath,newName+'.xml'))
print '============================================'
print 'img',imgname,os.path.join(imgpath,newName+'.jpg')
print '__________________________________________'
print 'xml',os.path.join(xmlpath,xml),os.path.join(xmlpath,newName+'.xml')
print '============================================'
index = index + 1
else:
count += 1
emptyset.add(xmlname.split('_')[0]+'_'+xmlname.split('_')[1])
sortedSet = sorted(emptyset,key= lambda x:(x.split('_')[0],x.split('_')[1]))
for i in sortedSet:
print i
print count结果为
5.生成4个txt文件指定训练集、验证集、数据集、训练验证集
调用generateTXT.py文件，输入xmlresult文件夹，输出到txt文件夹中。
trainval.txt 用来训练和验证的图片文件的文件名列表 包含train.txt（用来训练）和val.txt(用来验证)的文件名列表
test.txt 用来测试的图片文件的文件名列表
运行 generateTXT.py
import os
import random
import time
xmlfilepath='F:/Caltech/Caltech_VOC/xmlresult'
saveBasePath='F:/Caltech/Caltech_VOC/txt'
if not os.path.exists(saveBasePath):
os.makedirs(saveBasePath)
#设置训练集和测试集的百分比
trainval_percent=0.5
train_percent=0.5
total_xml = os.listdir(xmlfilepath)#所有的
num = len(total_xml) #xml文件的数量
index_list = range(num) #生成一个index列表
trainval_num = int(num*trainval_percent)
train_num = int(trainval_num*train_percent)
trainval_index = random.sample(index_list,trainval_num)
train_index = random.sample(trainval_index,train_num)
print("train and val size", trainval_num)
print("train size", train_num)
ftrainval = open(os.path.join(saveBasePath,'trainval.txt'), 'w')
ftest = open(os.path.join(saveBasePath,'test.txt'), 'w')
ftrain = open(os.path.join(saveBasePath,'train.txt'), 'w')
fval = open(os.path.join(saveBasePath,'val.txt'), 'w')
# Start time
start = time.time()
for i in index_list:
name = os.path.splitext(total_xml[i])[0] + '\n'
if i in trainval_index:
ftrainval.write(name)
if i in train_index:
ftrain.write(name)
else:
fval.write(name)
else:
ftest.write(name)
# End time
end = time.time()
seconds = end - start
print( "Time taken : {0} seconds".format(seconds))
ftrainval.close()
ftrain.close()
fval.close()
ftest .close()
结果为
6. 替换标签（辅助）
Caltech的标注里有很多别的类别的行人，people，person，
运行findPeople.py是将people标签替换成person。这是一个辅助文件，不是必须用到的。