1. 读取图片和标注后的xml文件，将标注信息写到txt文件中。生成的txt文件在txt文件夹下面，可以直接用于yolo3等目标检测算法的训练。
2. txt文件包含图片的路径，标注框的位置和大小，以及标注的类别。
3. 分割标注的图片，可以用于行人属性识别。分割的图片保存在segmentation文件夹下。
1. 需要将数据集放在dataset路径下。
2. Annotations存放的是xml文件，JPEGImages存放的是图片。
修改：需要针对需要进行适当的修改。下面进行说明：
第一：
class_tab={
"human":1 ##这个是类别，如果有多个类别，可以添加多条
}
第二：
params={"xml_prefix":"./dataset/Annotations/", ##这个是xml源文件的路径前缀，注意末尾要有“/”
"img_prefix":"./dataset/JPEGImages/",##这个是图片源文件的路径前缀，注意末尾要有“/”
"seg_prefix":"./segmentation/",##这个是分割后图片存放的位置前缀，注意末尾要有“/”
}
第三：
f = open('手祥./txt/train.txt','a')##这个是生成的txt文件的路径。
import sys
#sys.path.remove('/opt/ros/kinetic/lib/python2.7/dist-packages')
import cv2
import os
from readxml import *
class_tab={
"humanimport sys
#sys.path.remove('/opt/ros/kinetic/lib/python2.7/dist-packages')
import cv2
import os
from readxml import *
class_tab={
"human":1
}
params={"xml_prefix":"./dataset/Annotations/",
"img_prefix":"./dataset/JPEGImages/",
"seg_prefix":"./segmentation/",
}
def write_line(f, img_path, boxes):
f.write("%s "%(img_path))
for box in boxes:
f.write(str(box['cls'])+",")
f.write(str(box['xmin']+","))
f.write(str(box['ymin']+","))
f.write(str(box['xmax']+","))
f.write(str(box['ymax']))
f.write(" ")
f.write("\n")
f.flush()
def segment(img_path, imgname, boxes):
img=cv2.imread(img_path, cv2.IMREAD_COLOR)
cnt=0
for box in boxes:
seg=img[int(box['ymin']):int(box["ymax"]), int(box["xmin"]):int(box["xmax"]),:]
cv2.imwrite(params["seg_prefix"]+imgname+"_"+str(cnt)+".jpg", seg)
cnt=cnt+1
def main():
f = open('./txt/train.txt','a')
毕薯滚 img_list=os.listdir(params["img_prefix"])
for il in img_list:
img_path=params["img_prefix"]+il
tokens=il.split(".")
xml_path=params["xml_prefix"]+tokens[0]+"手余.xml"
if os.path.isfile(img_path)==False:
raise ValueError("%s does not exits!"%img_path)
else:
print("reading:", img_path)
boxes=xml_reader(xml_path, class_tab)
write_line(f,img_path,boxes)
segment(img_path, tokens[0], boxes)
f.close()
if __name__ == '__main__':
main()
":1
}
params={"xml_prefix":"./dataset/Annotations/",
"img_prefix":"./dataset/JPEGImages/",
"seg_prefix":"./segmentation/",
}
def write_line(f, img_path, boxes):
f.write("%s "%(img_path))
for box in boxes:
f.write(str(box['cls'])+",")
f.write(str(box['xmin']+","))
f.write(str(box['ymin']+","))
f.write(str(box['xmax']+","))
f.write(str(box['ymax']))
f.write(" ")
f.write("\n")
f.flush()
def segment(img_path, imgname, boxes):
img=cv2.imread(img_path, cv2.IMREAD_COLOR)
cnt=0
for box in boxes:
seg=img[int(box['ymin']):int(box["ymax"]), int(box["xmin"]):int(box["xmax"]),:]
cv2.imwrite(params["seg_prefix"]+imgname+"_"+str(cnt)+".jpg", seg)
cnt=cnt+1
def main():
f = open('./txt/train.txt','a')
img_list=os.listdir(params["img_prefix"])
for il in img_list:
img_path=params["img_prefix"]+il
tokens=il.split(".")
xml_path=params["xml_prefix"]+tokens[0]+".xml"
if os.path.isfile(img_path)==False:
raise ValueError("%s does not exits!"%img_path)
else:
print("reading:", img_path)
boxes=xml_reader(xml_path, class_tab)
write_line(f,img_path,boxes)
segment(img_path, tokens[0], boxes)
f.close()
if __name__ == '__main__':
main()
from xml.dom.minidom import Document
import xml.etree.ElementTree as ET
def xml_reader(fname, cls_tab):###, classes_merge_list,classes_merged_name):
in_file = open(fname)
tree=ET.parse(in_file)
root = tree.getroot()
boxes=[]
for item in root.iter('item'):
cls = item.find('name').text
if cls in cls_tab:
bndbox = item.find('bndbox')
b={
"xmin": str(int(bndbox.find('xmin').text)),
"ymin": str(int(bndbox.find('ymin').text)),
"xmax": str(int(bndbox.find('xmax').text)),
"ymax": str(int(bndbox.find('ymax').text)),
"cls": cls_tab[cls]
}
boxes.append(b)
else:
continue
return boxes
if __name__ == '__main__':
cls_tab={"human":1}
fname="/home/ta/Downloads/liqiming_label/dataset/Annotations/sa341.xml"
box=xml_reader(fname, cls_tab)
print(box)
#（转）将自己的图片转换为xml格式，代码实现：using System
using System.Drawing
using System.Collections
using System.ComponentModel
using System.Windows.Forms
using System.Data
using System.Xml
using System.IO
using System.Drawing.Imaging
namespace xmlfile
{
/// <summary>厅哗
/// aboatfile 的摘要说扮悉行明。
/// </summary>
public class xmlfile
{
public xmlfile()
{
//
// TODO: 在此处添加构造函数逻辑
//
}
//找开一幅XML图片(XmlTextReader)
public Image openxmlfile(string xmlfilepath)
{
XmlTextReader readxml=new XmlTextReader(xmlfilepath)
int len=64*1024
byte[] bytebmp=new byte [len]
while (readxml.Read())
{
if (readxml.NodeType==XmlNodeType.Element)
{
if (readxml.LocalName.Equals("image"))
{
readxml.ReadBase64(bytebmp,0,len)
}
}
}
readxml.Close()
readxml=null
FileStream streamfile=File.OpenWrite(@"陆简C:Documents and SettingsAdministratorLocal SettingsTempa.bmp")
streamfile.Write(bytebmp,0,bytebmp.Length)
streamfile.Close()
streamfile=null
Image img
img=System.Drawing.Bitmap.FromFile(@"C:Documents and SettingsAdministratorLocal SettingsTempa.bmp")
return img
}
//保存一幅XML图片(XmlTextWriter)
public void savexmlfile(string xmlname)
{
FileStream fs=new FileStream(@"C:a.bmp",FileMode.Open)
string time=DateTime.Now.ToLongDateString()
int len=4029
int readByte=0
byte[] imgdata = new byte[len]
XmlTextWriter xw=new XmlTextWriter(xmlname,System.Text.Encoding.UTF8)
xw.WriteStartDocument()
xw.WriteComment("XML图片,用base64储存创建于"+time)
xw.WriteStartElement("image")
BinaryReader br = new BinaryReader(fs)
do
{
readByte=br.Read(imgdata, 0, len)
xw.WriteBase64(imgdata, 0, readByte)
}
while (len <= readByte )
xw.WriteEndElement()
xw.WriteEndDocument()
fs.Close()
xw.Flush()
xw.Close()
File.Delete(@"C:a.bmp")
}
}
}
欢迎分享，转载请注明来源：内存溢出
微信扫一扫
支付宝扫一扫
评论列表（0条）