目标检测制作自己的VOC2007数据集

在目标检测时候往往需要使用自己的图片集来测试性能，所以本文介绍如何使用实现对自己数据集的训练和验证过程，内容包括： 1 数据集的标注 2 数据集的转换

1 数据集的标注

　　数据的标注使用BBox-Label-Tool工具，该工具使用python实现，使用简单方便。修改后的工具支持多label的标签标注。 该工具生成的标签格式是: object_number编号 className类别名 x1min y1min x1max y1max classname类别名 x2min y2min x2max y2max1.1 labelTool工具的使用说明 　　BBox-Label-Tool工具实现较简单，下面为源代码的修改后的代码： 

#-------------------------------------------------------------------------------
# Name:        Object bounding box label tool
# Purpose:     Label object bboxes for ImageNet Detection data
# Created:     06/06/2014

#
#-------------------------------------------------------------------------------
from __future__ import division
from Tkinter import *
import tkMessageBox
from PIL import Image, ImageTk
import os
import glob
import random

# colors for the bboxes
COLORS = ['red', 'blue', 'yellow', 'pink', 'cyan', 'green', 'black']
# image sizes for the examples
SIZE = 256, 256

classLabels=['mat', 'door', 'sofa', 'chair', 'table', 'bed', 'ashcan', 'shoe']

class LabelTool():
def __init__(self, master):
# set up the main frame
self.parent = master
self.parent.title("LabelTool")
self.frame = Frame(self.parent)
self.frame.pack(fill=BOTH, expand=1)
self.parent.resizable(width = False, height = False)

# initialize global state
self.imageDir = ''
self.imageList= []
self.egDir = ''
self.egList = []
self.outDir = ''
self.cur = 0
self.total = 0
self.category = 0
self.imagename = ''
self.labelfilename = ''
self.tkimg = None

# initialize mouse state
self.STATE = {}
self.STATE['click'] = 0
self.STATE['x'], self.STATE['y'] = 0, 0

# reference to bbox
self.bboxIdList = []
self.bboxId = None
self.bboxList = []
self.hl = None
self.vl = None
self.currentClass = ''

# ----------------- GUI stuff ---------------------
# dir entry & load
self.label = Label(self.frame, text = "Image Dir:")
self.label.grid(row = 0, column = 0, sticky = E)
self.entry = Entry(self.frame)
self.entry.grid(row = 0, column = 1, sticky = W+E)
self.ldBtn = Button(self.frame, text = "Load", command = self.loadDir)
self.ldBtn.grid(row = 0, column = 2, sticky = W+E)

# main panel for labeling
self.mainPanel = Canvas(self.frame, cursor='tcross')
self.mainPanel.bind("<Button-1>", self.mouseClick)
self.mainPanel.bind("<Motion>", self.mouseMove)
self.parent.bind("<Escape>", self.cancelBBox)  # press <Espace> to cancel current bbox
self.parent.bind("s", self.cancelBBox)
self.parent.bind("a", self.prevImage) # press 'a' to go backforward
self.parent.bind("d", self.nextImage) # press 'd' to go forward
self.mainPanel.grid(row = 1, column = 1, rowspan = 4, sticky = W+N)

# showing bbox info & delete bbox
self.lb1 = Label(self.frame, text = 'Bounding boxes:')
self.lb1.grid(row = 1, column = 2,  sticky = W+N)
self.listbox = Listbox(self.frame, width = 22, height = 12)
self.listbox.grid(row = 2, column = 2, sticky = N)
self.btnDel = Button(self.frame, text = 'Delete', command = self.delBBox)
self.btnDel.grid(row = 3, column = 2, sticky = W+E+N)
self.btnClear = Button(self.frame, text = 'ClearAll', command = self.clearBBox)
self.btnClear.grid(row = 4, column = 2, sticky = W+E+N)

#select class type
self.classPanel = Frame(self.frame)
self.classPanel.grid(row = 5, column = 1, columnspan = 10, sticky = W+E)
label = Label(self.classPanel, text = 'class:')
label.grid(row = 5, column = 1,  sticky = W+N)

self.classbox = Listbox(self.classPanel,  width = 4, height = 2)
self.classbox.grid(row = 5,column = 2)
for each in range(len(classLabels)):
function = 'select' + classLabels[each]
print classLabels[each]
btnMat = Button(self.classPanel, text = classLabels[each], command = getattr(self, function))
btnMat.grid(row = 5, column = each + 3)

# control panel for image navigation
self.ctrPanel = Frame(self.frame)
self.ctrPanel.grid(row = 6, column = 1, columnspan = 2, sticky = W+E)
self.prevBtn = Button(self.ctrPanel, text='<< Prev', width = 10, command = self.prevImage)
self.prevBtn.pack(side = LEFT, padx = 5, pady = 3)
self.nextBtn = Button(self.ctrPanel, text='Next >>', width = 10, command = self.nextImage)
self.nextBtn.pack(side = LEFT, padx = 5, pady = 3)
self.progLabel = Label(self.ctrPanel, text = "Progress:     /    ")
self.progLabel.pack(side = LEFT, padx = 5)
self.tmpLabel = Label(self.ctrPanel, text = "Go to Image No.")
self.tmpLabel.pack(side = LEFT, padx = 5)
self.idxEntry = Entry(self.ctrPanel, width = 5)
self.idxEntry.pack(side = LEFT)
self.goBtn = Button(self.ctrPanel, text = 'Go', command = self.gotoImage)
self.goBtn.pack(side = LEFT)

# example pannel for illustration
self.egPanel = Frame(self.frame, border = 10)
self.egPanel.grid(row = 1, column = 0, rowspan = 5, sticky = N)
self.tmpLabel2 = Label(self.egPanel, text = "Examples:")
self.tmpLabel2.pack(side = TOP, pady = 5)
self.egLabels = []
for i in range(3):
self.egLabels.append(Label(self.egPanel))
self.egLabels[-1].pack(side = TOP)

# display mouse position
self.disp = Label(self.ctrPanel, text='')
self.disp.pack(side = RIGHT)

self.frame.columnconfigure(1, weight = 1)
self.frame.rowconfigure(10, weight = 1)

# for debugging
##        self.setImage()
##        self.loadDir()

def loadDir(self, dbg = False):
if not dbg:
s = self.entry.get()
self.parent.focus()
self.category = int(s)
else:
s = r'D:\workspace\python\labelGUI'
##        if not os.path.isdir(s):
##            tkMessageBox.showerror("Error!", message = "The specified dir doesn't exist!")
##            return
# get image list
self.imageDir = os.path.join(r'./Images', '%d' %(self.category))
self.imageList = glob.glob(os.path.join(self.imageDir, '*.jpg'))
if len(self.imageList) == 0:
print 'No .JPEG images found in the specified dir!'
return

# set up output dir
self.outDir = os.path.join(r'./Labels', '%d' %(self.category))
if not os.path.exists(self.outDir):
os.mkdir(self.outDir)

labeledPicList = glob.glob(os.path.join(self.outDir, '*.txt'))

for label in labeledPicList:
data = open(label, 'r')
if '0\n' == data.read():
data.close()
continue
data.close()
picture = label.replace('Labels', 'Images').replace('.txt', '.jpg')
if picture in self.imageList:
self.imageList.remove(picture)
# default to the 1st image in the collection
self.cur = 1
self.total = len(self.imageList)
self.loadImage()
print '%d images loaded from %s' %(self.total, s)

def loadImage(self):
# load image
imagepath = self.imageList[self.cur - 1]
self.img = Image.open(imagepath)
self.imgSize = self.img.size
self.tkimg = ImageTk.PhotoImage(self.img)
self.mainPanel.config(width = max(self.tkimg.width(), 400), height = max(self.tkimg.height(), 400))
self.mainPanel.create_image(0, 0, image = self.tkimg, anchor=NW)
self.progLabel.config(text = "%04d/%04d" %(self.cur, self.total))

# load labels
self.clearBBox()
self.imagename = os.path.split(imagepath)[-1].split('.')[0]
labelname = self.imagename + '.txt'
self.labelfilename = os.path.join(self.outDir, labelname)
bbox_cnt = 0
if os.path.exists(self.labelfilename):
with open(self.labelfilename) as f:
for (i, line) in enumerate(f):
if i == 0:
bbox_cnt = int(line.strip())
continue
tmp = [int(t.strip()) for t in line.split()]
##                    print tmp
self.bboxList.append(tuple(tmp))
tmpId = self.mainPanel.create_rectangle(tmp[0], tmp[1], \
tmp[2], tmp[3], \
width = 2, \
outline = COLORS[(len(self.bboxList)-1) % len(COLORS)])
self.bboxIdList.append(tmpId)
self.listbox.insert(END, '(%d, %d) -> (%d, %d)' %(tmp[0], tmp[1], tmp[2], tmp[3]))
self.listbox.itemconfig(len(self.bboxIdList) - 1, fg = COLORS[(len(self.bboxIdList) - 1) % len(COLORS)])

def saveImage(self):
with open(self.labelfilename, 'w') as f:
f.write('%d\n' %len(self.bboxList))
for bbox in self.bboxList:
f.write(' '.join(map(str, bbox)) + '\n')
print 'Image No. %d saved' %(self.cur)

def mouseClick(self, event):
if self.STATE['click'] == 0:
self.STATE['x'], self.STATE['y'] = event.x, event.y
#self.STATE['x'], self.STATE['y'] = self.imgSize[0], self.imgSize[1]
else:
x1, x2 = min(self.STATE['x'], event.x), max(self.STATE['x'], event.x)
y1, y2 = min(self.STATE['y'], event.y), max(self.STATE['y'], event.y)
if x2 > self.imgSize[0]:
x2 = self.imgSize[0]
if y2 > self.imgSize[1]:
y2 = self.imgSize[1]
self.bboxList.append((self.currentClass, x1, y1, x2, y2))
self.bboxIdList.append(self.bboxId)
self.bboxId = None
self.listbox.insert(END, '(%d, %d) -> (%d, %d)' %(x1, y1, x2, y2))
self.listbox.itemconfig(len(self.bboxIdList) - 1, fg = COLORS[(len(self.bboxIdList) - 1) % len(COLORS)])
self.STATE['click'] = 1 - self.STATE['click']

def mouseMove(self, event):
self.disp.config(text = 'x: %d, y: %d' %(event.x, event.y))
if self.tkimg:
if self.hl:
self.mainPanel.delete(self.hl)
self.hl = self.mainPanel.create_line(0, event.y, self.tkimg.width(), event.y, width = 2)
if self.vl:
self.mainPanel.delete(self.vl)
self.vl = self.mainPanel.create_line(event.x, 0, event.x, self.tkimg.height(), width = 2)
if 1 == self.STATE['click']:
if self.bboxId:
self.mainPanel.delete(self.bboxId)
self.bboxId = self.mainPanel.create_rectangle(self.STATE['x'], self.STATE['y'], \
event.x, event.y, \
width = 2, \
outline = COLORS[len(self.bboxList) % len(COLORS)])

def cancelBBox(self, event):
if 1 == self.STATE['click']:
if self.bboxId:
self.mainPanel.delete(self.bboxId)
self.bboxId = None
self.STATE['click'] = 0

def delBBox(self):
sel = self.listbox.curselection()
if len(sel) != 1 :
return
idx = int(sel[0])
self.mainPanel.delete(self.bboxIdList[idx])
self.bboxIdList.pop(idx)
self.bboxList.pop(idx)
self.listbox.delete(idx)

def clearBBox(self):
for idx in range(len(self.bboxIdList)):
self.mainPanel.delete(self.bboxIdList[idx])
self.listbox.delete(0, len(self.bboxList))
self.bboxIdList = []
self.bboxList = []

def selectmat(self):
self.currentClass = 'mat'
self.classbox.delete(0,END)
self.classbox.insert(0, 'mat')
self.classbox.itemconfig(0,fg = COLORS[0])

def selectdoor(self):
self.currentClass = 'door'
self.classbox.delete(0,END)
self.classbox.insert(0, 'door')
self.classbox.itemconfig(0,fg = COLORS[0])

def selectsofa(self):
self.currentClass = 'sofa'
self.classbox.delete(0,END)
self.classbox.insert(0, 'sofa')
self.classbox.itemconfig(0,fg = COLORS[0])

def selectchair(self):
self.currentClass = 'chair'
self.classbox.delete(0,END)
self.classbox.insert(0, 'chair')
self.classbox.itemconfig(0,fg = COLORS[0])

def selecttable(self):
self.currentClass = 'table'
self.classbox.delete(0,END)
self.classbox.insert(0, 'table')
self.classbox.itemconfig(0,fg = COLORS[0])

def selectbed(self):
self.currentClass = 'bed'
self.classbox.delete(0,END)
self.classbox.insert(0, 'bed')
self.classbox.itemconfig(0,fg = COLORS[0])

def selectashcan(self):
self.currentClass = 'ashcan'
self.classbox.delete(0,END)
self.classbox.insert(0, 'ashcan')
self.classbox.itemconfig(0,fg = COLORS[0])

def selectshoe(self):
self.currentClass = 'shoe'
self.classbox.delete(0,END)
self.classbox.insert(0, 'shoe')
self.classbox.itemconfig(0,fg = COLORS[0])

def prevImage(self, event = None):
self.saveImage()
if self.cur > 1:
self.cur -= 1
self.loadImage()

def nextImage(self, event = None):
self.saveImage()
if self.cur < self.total:
self.cur += 1
self.loadImage()

def gotoImage(self):
idx = int(self.idxEntry.get())
if 1 <= idx and idx <= self.total:
self.saveImage()
self.cur = idx
self.loadImage()

##    def setImage(self, imagepath = r'test2.png'):
##        self.img = Image.open(imagepath)
##        self.tkimg = ImageTk.PhotoImage(self.img)
##        self.mainPanel.config(width = self.tkimg.width())
##        self.mainPanel.config(height = self.tkimg.height())
##        self.mainPanel.create_image(0, 0, image = self.tkimg, anchor=NW)

if __name__ == '__main__':
root = Tk()
tool = LabelTool(root)
root.mainloop()

main.py

使用方法：   　　　　 (1) 在BBox-Label-Tool/Images目录下创建保存图片的目录， 目录以数字命名(BBox-Label-Tool/Images/1), 然后将待标注的图片copy到1这个目录下;　　　　 (2) 在BBox-Label-Tool目录下执行命令   python main.py　　　　 (3) 在工具界面上, Image Dir 框中输入需要标记的目录名(比如 1), 然后点击load按钮, 工具自动将Images/1目录下的图片加载进来;需要说明一下, 如果目录中的图片已经标注过,点击load时不会被重新加载进来.　　　　 (4) 该工具支持多类别标注, 画bounding boxs框标定之前,需要先选定类别,然后再画框.　　　　 (5) 一张图片标注完后, 点击Next>>按钮, 标注下一张图片,  图片label成功后,会在BBox-Label-Tool/Labels对应的目录下生成与图片文件名对应的label文件.     注意将该文件夹保存为label名字    （github上也有另外一个开源的label-box标注工具labelImg，由于是GUI界面，操作非常方便，也可以将提取的bbox生成为txt格式文件）

2 voc数据格式

(1)Annotations中保存的是xml格式的label信息

(2)ImageSet目录下的Main目录里存放的是用于表示训练的图片集和测试的图片集

(3)JPEGImages目录下存放所有图片集

(4)label目录下保存的是BBox-Label-Tool工具标注好的bounding box坐标文件，该目录下的文件就是待转换的label标签文件。

3 Label转换成VOC数据格式

    BBox-Label-Tool工具标注好的bounding box坐标文件转换成VOC数据格式的形式.具体的转换过程包括了两个步骤：（1）将BBox-Label-Tool下的txt格式保存的bounding box信息转换成VOC数据格式下以xml方式表示；（2）生成用于训练的数据集和用于测试的数据集。首先建立一个VOC2007文件夹，在其下面建立'JPEGImages'，'Annotations‘， ’label‘文件夹，将1步骤中生成的的所有txt文件转放到该label文件夹下，并将所有的图片转移到JPEGImages文件夹下。建立createXml.py  完成txt到xml的转换脚本，  放到和label文件夹同一目录下，执行脚本python createXml.py，生成xml。

#!/usr/bin/env pythonimport osimport sysimport cv2from itertools import islicefrom xml.dom.minidom import Documentlabels='label'imgpath='JPEGImages/'xmlpath_new='Annotations/'foldername='VOC2007'def insertObject(doc, datas):obj = doc.createElement('object')name = doc.createElement('name')name.appendChild(doc.createTextNode(datas[0]))obj.appendChild(name)pose = doc.createElement('pose')pose.appendChild(doc.createTextNode('Unspecified'))obj.appendChild(pose)truncated = doc.createElement('truncated')truncated.appendChild(doc.createTextNode(str(0)))obj.appendChild(truncated)difficult = doc.createElement('difficult')difficult.appendChild(doc.createTextNode(str(0)))obj.appendChild(difficult)bndbox = doc.createElement('bndbox')xmin = doc.createElement('xmin')xmin.appendChild(doc.createTextNode(str(datas[1])))bndbox.appendChild(xmin)ymin = doc.createElement('ymin')ymin.appendChild(doc.createTextNode(str(datas[2])))bndbox.appendChild(ymin)xmax = doc.createElement('xmax')xmax.appendChild(doc.createTextNode(str(datas[3])))bndbox.appendChild(xmax)ymax = doc.createElement('ymax')if  '\r' == str(datas[4])[-1] or '\n' == str(datas[4])[-1]:data = str(datas[4])[0:-1]else:data = str(datas[4])ymax.appendChild(doc.createTextNode(data))bndbox.appendChild(ymax)obj.appendChild(bndbox)return objdef create():for walk in os.walk(labels):for each in walk[2]:fidin=open(walk[0] + '/'+ each,'r')objIndex = 0for data in islice(fidin, 1, None):objIndex += 1data=data.strip('\n')datas = data.split(' ')if 5 != len(datas):print 'bounding box information error'continuepictureName = each.replace('.txt', '.jpg')imageFile = imgpath + pictureNameimg = cv2.imread(imageFile)imgSize = img.shapeif 1 == objIndex:xmlName = each.replace('.txt', '.xml')f = open(xmlpath_new + xmlName, "w")doc = Document()annotation = doc.createElement('annotation')doc.appendChild(annotation)folder = doc.createElement('folder')folder.appendChild(doc.createTextNode(foldername))annotation.appendChild(folder)filename = doc.createElement('filename')filename.appendChild(doc.createTextNode(pictureName))annotation.appendChild(filename)source = doc.createElement('source')database = doc.createElement('database')database.appendChild(doc.createTextNode('My Database'))source.appendChild(database)source_annotation = doc.createElement('annotation')source_annotation.appendChild(doc.createTextNode(foldername))source.appendChild(source_annotation)image = doc.createElement('image')image.appendChild(doc.createTextNode('flickr'))source.appendChild(image)flickrid = doc.createElement('flickrid')flickrid.appendChild(doc.createTextNode('NULL'))source.appendChild(flickrid)annotation.appendChild(source)owner = doc.createElement('owner')flickrid = doc.createElement('flickrid')flickrid.appendChild(doc.createTextNode('NULL'))owner.appendChild(flickrid)name = doc.createElement('name')name.appendChild(doc.createTextNode('idaneel'))owner.appendChild(name)annotation.appendChild(owner)size = doc.createElement('size')width = doc.createElement('width')width.appendChild(doc.createTextNode(str(imgSize[1])))size.appendChild(width)height = doc.createElement('height')height.appendChild(doc.createTextNode(str(imgSize[0])))size.appendChild(height)depth = doc.createElement('depth')depth.appendChild(doc.createTextNode(str(imgSize[2])))size.appendChild(depth)annotation.appendChild(size)segmented = doc.createElement('segmented')segmented.appendChild(doc.createTextNode(str(0)))annotation.appendChild(segmented)annotation.appendChild(insertObject(doc, datas))else:annotation.appendChild(insertObject(doc, datas))try:f.write(doc.toprettyxml(indent = '    '))f.close()fidin.close()except:passif __name__ == '__main__':create()

新建文件夹，命名为ImageSets，在ImageSets里再新建文件夹，命名为Main。我们可以通过xml名字，生成四个txt文件，即利用createTest.py 生成训练集和测试集标识文。

	main文件夹下会生成test.txt和train.txt，val.txt以及trainval.txt文件。test.txt是测试集，train.txt是训练集，val.txt是验证集，trainval.txt是训练和验证集.VOC2007中，trainval大概是整个数据集的50%，test也大概是整个数据集的50%；train大概是trainval的50%，val大概是trainval的50%    将生成的JPEGImages，JPEGImages，ImagesSets替换掉VOC2007中的五个文件夹，制作完成。参考博客：http://www.cnblogs.com/objectDetect/p/5780006.html http://www.voidcn.com/blog/sinat_30071459/article/p-5745727.html[/code]