from pycocotools.coco import COCO
import os
import shutil
from tqdm import tqdm
import skimage.io as io
import matplotlib.pyplot as plt
import cv2
from PIL import Image, ImageDraw
 
#the path you want to save your results for coco to voc
savepath="/media/huanglong/Newsmy/COCO/" #保存提取类的路径,我放在同一路径下
img_dir=savepath+'images/'
anno_dir=savepath+'Annotations/'
# datasets_list=['train2014', 'val2014']
datasets_list=['train2014']
 
classes_names = ['person'] #coco有80类，这里写要提取类的名字，以person为例
#Store annotations and train2014/val2014/... in this folder
dataDir= '/media/huanglong/Newsmy/COCO/' #原coco数据集
 
headstr = """<annotation>
 <folder>VOC</folder>
 <filename>%s</filename>
 <source>
 <database>My Database</database>
 <annotation>COCO</annotation>
 <image>flickr</image>
 <flickrid>NULL</flickrid>
 </source>
 <owner>
 <flickrid>NULL</flickrid>
 <name>company</name>
 </owner>
 <size>
 <width>%d</width>
 <height>%d</height>
 <depth>%d</depth>
 </size>
 <segmented>0</segmented>
"""
objstr = """ <object>
 <name>%s</name>
 <pose>Unspecified</pose>
 <truncated>0</truncated>
 <difficult>0</difficult>
 <bndbox>
  <xmin>%d</xmin>
  <ymin>%d</ymin>
  <xmax>%d</xmax>
  <ymax>%d</ymax>
 </bndbox>
 </object>
"""
 
tailstr = '''</annotation>
'''
 
#if the dir is not exists,make it,else delete it
def mkr(path):
 if os.path.exists(path):
 shutil.rmtree(path)
 os.mkdir(path)
 else:
 os.mkdir(path)
mkr(img_dir)
mkr(anno_dir)
def id2name(coco):
 classes=dict()
 for cls in coco.dataset['categories']:
 classes[cls['id']]=cls['name']
 return classes
 
def write_xml(anno_path,head, objs, tail):
 f = open(anno_path, "w")
 f.write(head)
 for obj in objs:
 f.write(objstr%(obj[0],obj[1],obj[2],obj[3],obj[4]))
 f.write(tail)
 
 
def save_annotations_and_imgs(coco,dataset,filename,objs):
 #eg:COCO_train2014_000000196610.jpg-->COCO_train2014_000000196610.xml
 anno_path=anno_dir+filename[:-3]+'xml'
 img_path=dataDir+dataset+'/'+filename
 print(img_path)
 dst_imgpath=img_dir+filename
 
 img=cv2.imread(img_path)
 #if (img.shape[2] == 1):
 # print(filename + " not a RGB image")
 # return
 shutil.copy(img_path, dst_imgpath)
 
 head=headstr % (filename, img.shape[1], img.shape[0], img.shape[2])
 tail = tailstr
 write_xml(anno_path,head, objs, tail)
 
 
def showimg(coco,dataset,img,classes,cls_id,show=True):
 global dataDir
 I=Image.open('%s/%s/%s'%(dataDir,dataset,img['file_name']))
 #通过id，得到注释的信息
 annIds = coco.getAnnIds(imgIds=img['id'], catIds=cls_id, iscrowd=None)
 # print(annIds)
 anns = coco.loadAnns(annIds)
 # print(anns)
 # coco.showAnns(anns)
 objs = []
 for ann in anns:
 class_name=classes[ann['category_id']]
 if class_name in classes_names:
  print(class_name)
  if 'bbox' in ann:
  bbox=ann['bbox']
  xmin = int(bbox[0])
  ymin = int(bbox[1])
  xmax = int(bbox[2] + bbox[0])
  ymax = int(bbox[3] + bbox[1])
  obj = [class_name, xmin, ymin, xmax, ymax]
  objs.append(obj)
  draw = ImageDraw.Draw(I)
  draw.rectangle([xmin, ymin, xmax, ymax])
 if show:
 plt.figure()
 plt.axis('off')
 plt.imshow(I)
 plt.show()
 
 return objs
 
for dataset in datasets_list:
 #./COCO/annotations/instances_train2014.json
 annFile='{}/annotations/instances_{}.json'.format(dataDir,dataset)
 
 #COCO API for initializing annotated data
 coco = COCO(annFile)

 #show all classes in coco
 classes = id2name(coco)
 print(classes)
 #[1, 2, 3, 4, 6, 8]
 classes_ids = coco.getCatIds(catNms=classes_names)
 print(classes_ids)
 for cls in classes_names:
 #Get ID number of this class
 cls_id=coco.getCatIds(catNms=[cls])
 img_ids=coco.getImgIds(catIds=cls_id)
 print(cls,len(img_ids))
 # imgIds=img_ids[0:10]
 for imgId in tqdm(img_ids):
  img = coco.loadImgs(imgId)[0]
  filename = img['file_name']
  # print(filename)
  objs=showimg(coco, dataset, img, classes,classes_ids,show=False)
  print(objs)
  save_annotations_and_imgs(coco, dataset, filename, objs)

# -*- coding: utf-8 -*-
# @Time : 2019/8/27 10：48
# @Author :Rock
# @File : voc2coco.py
# just for object detection
import xml.etree.ElementTree as ET
import os
import json

coco = dict()
coco['images'] = []
coco['type'] = 'instances'
coco['annotations'] = []
coco['categories'] = []

category_set = dict()
image_set = set()

category_item_id = 0
image_id = 0
annotation_id = 0


def addCatItem(name):
 global category_item_id
 category_item = dict()
 category_item['supercategory'] = 'none'
 category_item_id += 1
 category_item['id'] = category_item_id
 category_item['name'] = name
 coco['categories'].append(category_item)
 category_set[name] = category_item_id
 return category_item_id


def addImgItem(file_name, size):
 global image_id
 if file_name is None:
 raise Exception('Could not find filename tag in xml file.')
 if size['width'] is None:
 raise Exception('Could not find width tag in xml file.')
 if size['height'] is None:
 raise Exception('Could not find height tag in xml file.')
 img_id = "%04d" % image_id
 image_id += 1
 image_item = dict()
 image_item['id'] = int(img_id)
 # image_item['id'] = image_id
 image_item['file_name'] = file_name
 image_item['width'] = size['width']
 image_item['height'] = size['height']
 coco['images'].append(image_item)
 image_set.add(file_name)
 return image_id


def addAnnoItem(object_name, image_id, category_id, bbox):
 global annotation_id
 annotation_item = dict()
 annotation_item['segmentation'] = []
 seg = []
 # bbox[] is x,y,w,h
 # left_top
 seg.append(bbox[0])
 seg.append(bbox[1])
 # left_bottom
 seg.append(bbox[0])
 seg.append(bbox[1] + bbox[3])
 # right_bottom
 seg.append(bbox[0] + bbox[2])
 seg.append(bbox[1] + bbox[3])
 # right_top
 seg.append(bbox[0] + bbox[2])
 seg.append(bbox[1])

 annotation_item['segmentation'].append(seg)

 annotation_item['area'] = bbox[2] * bbox[3]
 annotation_item['iscrowd'] = 0
 annotation_item['ignore'] = 0
 annotation_item['image_id'] = image_id
 annotation_item['bbox'] = bbox
 annotation_item['category_id'] = category_id
 annotation_id += 1
 annotation_item['id'] = annotation_id
 coco['annotations'].append(annotation_item)


def parseXmlFiles(xml_path):
 for f in os.listdir(xml_path):
 if not f.endswith('.xml'):
  continue

 bndbox = dict()
 size = dict()
 current_image_id = None
 current_category_id = None
 file_name = None
 size['width'] = None
 size['height'] = None
 size['depth'] = None

 xml_file = os.path.join(xml_path, f)
 # print(xml_file)

 tree = ET.parse(xml_file)
 root = tree.getroot()
 if root.tag != 'annotation':
  raise Exception('pascal voc xml root element should be annotation, rather than {}'.format(root.tag))

 # elem is <folder>, <filename>, <size>, <object>
 for elem in root:
  current_parent = elem.tag
  current_sub = None
  object_name = None

  if elem.tag == 'folder':
  continue

  if elem.tag == 'filename':
  file_name = elem.text
  if file_name in category_set:
   raise Exception('file_name duplicated')

  # add img item only after parse <size> tag
  elif current_image_id is None and file_name is not None and size['width'] is not None:
  if file_name not in image_set:
   current_image_id = addImgItem(file_name, size)
   # print('add image with {} and {}'.format(file_name, size))
  else:
   raise Exception('duplicated image: {}'.format(file_name))
   # subelem is <width>, <height>, <depth>, <name>, <bndbox>
  for subelem in elem:
  bndbox['xmin'] = None
  bndbox['xmax'] = None
  bndbox['ymin'] = None
  bndbox['ymax'] = None

  current_sub = subelem.tag
  if current_parent == 'object' and subelem.tag == 'name':
   object_name = subelem.text
   if object_name not in category_set:
   current_category_id = addCatItem(object_name)
   else:
   current_category_id = category_set[object_name]

  elif current_parent == 'size':
   if size[subelem.tag] is not None:
   raise Exception('xml structure broken at size tag.')
   size[subelem.tag] = int(subelem.text)

  # option is <xmin>, <ymin>, <xmax>, <ymax>, when subelem is <bndbox>
  for option in subelem:
   if current_sub == 'bndbox':
   if bndbox[option.tag] is not None:
    raise Exception('xml structure corrupted at bndbox tag.')
   bndbox[option.tag] = int(option.text)

  # only after parse the <object> tag
  if bndbox['xmin'] is not None:
   if object_name is None:
   raise Exception('xml structure broken at bndbox tag')
   if current_image_id is None:
   raise Exception('xml structure broken at bndbox tag')
   if current_category_id is None:
   raise Exception('xml structure broken at bndbox tag')
   bbox = []
   # x
   bbox.append(bndbox['xmin'])
   # y
   bbox.append(bndbox['ymin'])
   # w
   bbox.append(bndbox['xmax'] - bndbox['xmin'])
   # h
   bbox.append(bndbox['ymax'] - bndbox['ymin'])
   # print('add annotation with {},{},{},{}'.format(object_name, current_image_id, current_category_id,
   #      bbox))
   addAnnoItem(object_name, current_image_id, current_category_id, bbox)


if __name__ == '__main__':
	#修改这里的两个地址，一个是xml文件的父目录；一个是生成的json文件的绝对路径
 xml_path = r'G:\dataset\COCO\person\coco_val2014\annotations\\'
 json_file = r'G:\dataset\COCO\person\coco_val2014\instances_val2014.json'
 parseXmlFiles(xml_path)
 json.dump(coco, open(json_file, 'w'))

# -*- coding: utf-8 -*-
# @Function:There are 20 classes in VOC data set. If you need to extract specific classes, you can use this program to extract them.
 
import os
import shutil
ann_filepath='E:/VOCdevkit/VOC2012/Annotations/'
img_filepath='E:/VOCdevkit/VOC2012/JPEGImages/'
img_savepath='E:TrafficDatasets/JPEGImages/'
ann_savepath='E:TrafficDatasets/Annotations/'
if not os.path.exists(img_savepath):
 os.mkdir(img_savepath)
 
if not os.path.exists(ann_savepath):
 os.mkdir(ann_savepath)
names = locals()
classes = ['aeroplane','bicycle','bird', 'boat', 'bottle',
  'bus', 'car', 'cat', 'chair', 'cow','diningtable',
  'dog', 'horse', 'motorbike', 'pottedplant',
  'sheep', 'sofa', 'train', 'tvmonitor', 'person']
 
 
for file in os.listdir(ann_filepath):
 print(file)
 
 fp = open(ann_filepath + '\\' + file) #打开Annotations文件
 ann_savefile=ann_savepath+file
 fp_w = open(ann_savefile, 'w')
 lines = fp.readlines()
 
 ind_start = []
 ind_end = []
 lines_id_start = lines[:] 
 
 lines_id_end = lines[:]
 
 classes1 = '\t\t<name>bicycle</name>\n'
 classes2 = '\t\t<name>bus</name>\n'
 classes3 = '\t\t<name>car</name>\n'
 classes4 = '\t\t<name>motorbike</name>\n'
 classes5 = '\t\t<name>train</name>\n'
 
 #在xml中找到object块，并将其记录下来
 while "\t<object>\n" in lines_id_start:
 a = lines_id_start.index("\t<object>\n")
 ind_start.append(a) #ind_start是<object>的行数
 lines_id_start[a] = "delete"
 
 
 while "\t</object>\n" in lines_id_end:
 b = lines_id_end.index("\t</object>\n")
 ind_end.append(b) #ind_end是</object>的行数
 lines_id_end[b] = "delete"
 
 #names中存放所有的object块
 i = 0
 for k in range(0, len(ind_start)):
 names['block%d' % k] = []
 for j in range(0, len(classes)):
  if classes[j] in lines[ind_start[i] + 1]:
  a = ind_start[i]
  for o in range(ind_end[i] - ind_start[i] + 1):
   names['block%d' % k].append(lines[a + o])
  break
 i += 1
 #print(names['block%d' % k])
 
 
 #xml头
 string_start = lines[0:ind_start[0]]
 
 #xml尾
 if((file[2:4]=='09') | (file[2:4]=='10') | (file[2:4]=='11')):
 string_end = lines[(len(lines) - 11):(len(lines))]
 else:
 string_end = [lines[len(lines) - 1]] 
 
 
 #在给定的类中搜索，若存在则，写入object块信息
 a = 0
 for k in range(0, len(ind_start)):
 if classes1 in names['block%d' % k]:
  a += 1
  string_start += names['block%d' % k]
 if classes2 in names['block%d' % k]:
  a += 1
  string_start += names['block%d' % k]
 if classes3 in names['block%d' % k]:
  a += 1
  string_start += names['block%d' % k]
 if classes4 in names['block%d' % k]:
  a += 1
  string_start += names['block%d' % k]
 if classes5 in names['block%d' % k]:
  a += 1
  string_start += names['block%d' % k]
 
 string_start += string_end
 # print(string_start)
 for c in range(0, len(string_start)):
 fp_w.write(string_start[c])
 fp_w.close()
 #如果没有我们寻找的模块，则删除此xml，有的话拷贝图片
 if a == 0:
 os.remove(ann_savepath+file)
 else:
 name_img = img_filepath + os.path.splitext(file)[0] + ".jpg"
 shutil.copy(name_img, img_savepath)
 fp.close()