保存标注对象到txt 制作xml

Posted 2021-02-06 crazybird123

1、算法将检测的目标名称和目标位置保存到txt文本

图片名  xmin ymin xmax ymax

(4).avi237face.jpg
4
smoke 83 234 142 251
hand 119 255 271 306
eye 178 148 216 163
eye 111 156 148 173

 

#!/usr/bin/python
# -*- coding: UTF-8 -*-

import os, h5py, cv2, sys, shutil
import numpy as np
from xml.dom.minidom import Document

rootdir = "G:/MTCNNTraining/faceData/train"
convet2yoloformat = True
convert2vocformat = True
resized_dim = (48, 48)

# 最小取20大小的脸，并且补齐
minsize2select = 1
usepadding = True



def convertimgset(img_set="train"):
    imgdir = rootdir + "/trainImages"
    gtfilepath = rootdir + "/SSDSave.txt"

    imagesdir = rootdir + "/images"
    vocannotationdir = rootdir + "/Annotations"
    labelsdir = rootdir + "/labels"

    if not os.path.exists(imagesdir):
        os.mkdir(imagesdir)
    if convet2yoloformat:
        if not os.path.exists(labelsdir):
            os.mkdir(labelsdir)
    if convert2vocformat:
        if not os.path.exists(vocannotationdir):
            os.mkdir(vocannotationdir)

    index = 0
    with open(gtfilepath, ‘r‘) as gtfile:
        while (True):  # and len(faces)<10
            filename = gtfile.readline()[:-1]
            if (filename == ""):
                break
            sys.stdout.write("
" + str(index) + ":" + filename + "			")
            sys.stdout.flush()
            imgpath = imgdir + "/" + filename
            img = cv2.imread(imgpath)
            if not img.data:
                break
            imgheight = img.shape[0]
            imgwidth = img.shape[1]
            maxl = max(imgheight, imgwidth)

            paddingleft = (maxl - imgwidth) >> 1
            paddingright = (maxl - imgwidth) >> 1
            paddingbottom = (maxl - imgheight) >> 1
            paddingtop = (maxl - imgheight) >> 1
            saveimg = cv2.copyMakeBorder(img, paddingtop, paddingbottom, paddingleft, paddingright, cv2.BORDER_CONSTANT,value=0)
            showimg = saveimg.copy()

            numbbox = int(gtfile.readline())
            bboxes = []
            bnames=[]
            for i in range(numbbox):
                line_read = gtfile.readline()
                line_cor = line_read.strip().split(" ")
                obj_name = line_cor[0]
                #line = line_cor[1:5]
                line = list(map(int,line_cor[1:5]))

                if (int(line[3]) <= 0 or int(line[2]) <= 0):
                    continue
                x = int(line[0]) + paddingleft #左上角顶点x
                y = int(line[1]) + paddingtop #左上角顶点y
                width = int(line[2]) - int(line[0]) + 1 #宽度
                height = int(line[3]) - int(line[1])+ 1 #高度
                bbox = (x, y, width, height)
                #x2 = x + width
                #y2 = y + height
                # face=img[x:x2,y:y2]
                if width >= minsize2select and height >= minsize2select:
                    bboxes.append(bbox)
                    bnames.append(obj_name)
                    #cv2.rectangle(showimg, (x, y), (x2, y2), (0, 255, 0))
                    # maxl=max(width,height)
                    # x3=(int)(x+(width-maxl)*0.5)
                    # y3=(int)(y+(height-maxl)*0.5)
                    # x4=(int)(x3+maxl)
                    # y4=(int)(y3+maxl)
                    # cv2.rectangle(img,(x3,y3),(x4,y4),(255,0,0))
                #else:
                    #cv2.rectangle(showimg, (x, y), (x2, y2), (0, 0, 255))


            #filename = filename.replace("/", "_")
            if len(bboxes) == 0:
                print ("warrning: no face")
                continue

            cv2.imwrite(imagesdir + "/" + filename, saveimg)

            #if convet2yoloformat:
                #height = saveimg.shape[0]
                #width = saveimg.shape[1]
                #txtpath = labelsdir + "/" + filename
                #txtpath = txtpath[:-3] + "txt"
                #ftxt = open(txtpath, ‘w‘)
                #for i in range(len(bboxes)):
                    #bbox = bboxes[i]
                    #xcenter = (bbox[0] + bbox[2] * 0.5) / width
                    #ycenter = (bbox[1] + bbox[3] * 0.5) / height
                    #wr = bbox[2] * 1.0 / width
                    #hr = bbox[3] * 1.0 / height
                    #txtline = "0 " + str(xcenter) + " " + str(ycenter) + " " + str(wr) + " " + str(hr) + "
"
                    #ftxt.write(txtline)
                #ftxt.close()



            if convert2vocformat:
                xmlpath = vocannotationdir + "/" + filename
                xmlpath = xmlpath[:-3] + "xml"
                doc = Document()
                annotation = doc.createElement(‘annotation‘)
                doc.appendChild(annotation)
                folder = doc.createElement(‘folder‘)
                folder_name = doc.createTextNode(‘widerface‘)
                folder.appendChild(folder_name)
                annotation.appendChild(folder)
                filenamenode = doc.createElement(‘filename‘)
                filename_name = doc.createTextNode(filename)
                filenamenode.appendChild(filename_name)
                annotation.appendChild(filenamenode)
                source = doc.createElement(‘source‘)
                annotation.appendChild(source)
                database = doc.createElement(‘database‘)
                database.appendChild(doc.createTextNode(‘wider face Database‘))
                source.appendChild(database)
                annotation_s = doc.createElement(‘annotation‘)
                annotation_s.appendChild(doc.createTextNode(‘PASCAL VOC2007‘))
                source.appendChild(annotation_s)
                image = doc.createElement(‘image‘)
                image.appendChild(doc.createTextNode(‘flickr‘))
                source.appendChild(image)
                flickrid = doc.createElement(‘flickrid‘)
                flickrid.appendChild(doc.createTextNode(‘-1‘))
                source.appendChild(flickrid)
                owner = doc.createElement(‘owner‘)
                annotation.appendChild(owner)
                flickrid_o = doc.createElement(‘flickrid‘)
                flickrid_o.appendChild(doc.createTextNode(‘widerFace‘))
                owner.appendChild(flickrid_o)
                name_o = doc.createElement(‘name‘)
                name_o.appendChild(doc.createTextNode(‘widerFace‘))
                owner.appendChild(name_o)
                size = doc.createElement(‘size‘)
                annotation.appendChild(size)
                width = doc.createElement(‘width‘)
                width.appendChild(doc.createTextNode(str(saveimg.shape[1])))
                height = doc.createElement(‘height‘)
                height.appendChild(doc.createTextNode(str(saveimg.shape[0])))
                depth = doc.createElement(‘depth‘)
                depth.appendChild(doc.createTextNode(str(saveimg.shape[2])))
                size.appendChild(width)
                size.appendChild(height)
                size.appendChild(depth)
                segmented = doc.createElement(‘segmented‘)
                segmented.appendChild(doc.createTextNode(‘0‘))
                annotation.appendChild(segmented)

                for i in range(len(bboxes)):
                    bbox = bboxes[i]
                    objects = doc.createElement(‘object‘)
                    annotation.appendChild(objects)
                    object_name = doc.createElement(‘name‘)
                    bnames_var = str(bnames[i])

                    object_name.appendChild(doc.createTextNode(bnames_var))
                    objects.appendChild(object_name)
                    pose = doc.createElement(‘pose‘)
                    pose.appendChild(doc.createTextNode(‘Unspecified‘))
                    objects.appendChild(pose)
                    truncated = doc.createElement(‘truncated‘)
                    truncated.appendChild(doc.createTextNode(‘1‘))
                    objects.appendChild(truncated)
                    difficult = doc.createElement(‘difficult‘)
                    difficult.appendChild(doc.createTextNode(‘0‘))
                    objects.appendChild(difficult)
                    bndbox = doc.createElement(‘bndbox‘)
                    objects.appendChild(bndbox)
                    xmin = doc.createElement(‘xmin‘)
                    xmin.appendChild(doc.createTextNode(str(bbox[0])))
                    bndbox.appendChild(xmin)
                    ymin = doc.createElement(‘ymin‘)
                    ymin.appendChild(doc.createTextNode(str(bbox[1])))
                    bndbox.appendChild(ymin)
                    xmax = doc.createElement(‘xmax‘)
                    xmax.appendChild(doc.createTextNode(str(bbox[0] + bbox[2])))
                    bndbox.appendChild(xmax)
                    ymax = doc.createElement(‘ymax‘)
                    ymax.appendChild(doc.createTextNode(str(bbox[1] + bbox[3])))
                    bndbox.appendChild(ymax)
                f = open(xmlpath, "w")
                f.write(doc.toprettyxml(indent=‘‘))
                f.close()
                # cv2.imshow("img",showimg)
            # cv2.waitKey()
            index = index + 1


def convertdataset():
    img_sets = ["train"]
    for img_set in img_sets:
        convertimgset(img_set)


if __name__ == "__main__":
    convertdataset()