Labelme json 文件与 Coco目标检测标注json 文件格式分析与转换 --- ##

Labelme json 文件与 Coco目标检测标注json 文件格式分析与转换

---

文件分析

• labelme json 文件

  labelme是一个标注工具，在conda环境下直接用命令行pip 或者 conda install labelme即可，使用时也是在相应虚拟环境下输入 labeleme 即可，以下介绍目标检测的json文件格式

  如下为一个labelme标注后生成的json文件：

  {
  	"version": "4.4.0", 
  	"flags": {}, 
  	"shapes": 
  		[{"label": "legal",
      	"points": [[662.0, 948.6666666666667], 			[1508.6666666666667, 	 	 	 1968.666666666667]], 
      "group_id": null, 
     	"shape_type": "rectangle", 
      "flags": {}}], 
      "imagePath": "1_P77V02#17231218232#98#2#Z#2020Y09M02D23H57m09s#1.jpg", 	
      "imageData": "/9j/4AAQSkZJRgABAQAAAQABAAD.....
  }
  

  其中重要的参数有shapes shape_type imagePath

  1. shapes: 其中包含了标注的具体信息，由列表组成，每一个元素是一个字典，一个字典包含了一个标注框的相关信息，如label是标签，points是标注的点，points的取值与shape_type相关，这里取的是rectangle即直接由矩形的对角线上两点确定一个矩形框。因此points中也只有两个点的信息，点的坐标为(x,y) ，坐标轴原点在左上角，原点向下为y正向，向右为x正向。

     2. imagePath是标注图片的文件名
     3. shape_type如上所说，记录了标记时选择的方式。

• Coco数据详解

相互转换

• 代码如下：

  # !/usr/bin/env python
  import importlib
  
  import argparse
  import json
  import matplotlib.pyplot as plt
  import skimage.io as io
  import cv2
  from labelme import utils
  import numpy as np
  import glob
  import PIL.Image
  from tqdm import tqdm
  
  
  class MyEncoder(json.JSONEncoder):
      def default(self, obj):
          if isinstance(obj, np.integer):
              return int(obj)
          elif isinstance(obj, np.floating):
              return float(obj)
          elif isinstance(obj, np.ndarray):
              return obj.tolist()
          else:
              return super(MyEncoder, self).default(obj)
  
  
  class labelme2coco(object):
      def __init__(self, labelme_json=[], save_json_path='./tran.json'):
          '''
          :param labelme_json: 所有labelme的json文件路径组成的列表
          :param save_json_path: json保存位置
          '''
          self.labelme_json = labelme_json
          self.save_json_path = save_json_path
          self.images = []
          self.categories = []
          self.annotations = []
          # self.data_coco = {}
          self.label = []
          self.annID = 1
          self.height = 0
          self.width = 0
  
          self.save_json()
  
      def data_transfer(self):
  
          for num, json_file in tqdm(enumerate(self.labelme_json)):
              with open(json_file, 'r') as fp:
                  data = json.load(fp)  # 加载json文件
                  self.images.append(self.image(data, num))
                  for shapes in data['shapes']:
                      label = shapes['label']
                      if label not in self.label:
                          self.categories.append(self.categorie(label))
                          self.label.append(label)
                      points = shapes['points']  # 这里的point是用rectangle标注得到的，只有两个点，需要转成四个点
                      #以下并不需要
  
                      # x1, y1 = min(points[0][0],points[1][0]), min(points[0][1],points[1][1])
                      # x4, y4 = max(points[0][0],points[1][0]), max(points[0][1],points[1][1])
                      # x2, y2 = x1, y4
                      # x3, y3 = x4, y1
                      # tmp_points = []
                      # tmp_points.append([x1, y1])
                      # tmp_points.append([x4, y4])
                      # tmp_points.append([x3, y3])
                      # tmp_points.append([x4, y4])
                      # points = tmp_points
  
                      self.annotations.append(self.annotation(points, label, num))
                      self.annID += 1
  
      def image(self, data, num):
          image = {}
          img = utils.img_b64_to_arr(data['imageData'])  # 解析原图片数据
          # img=io.imread(data['imagePath']) # 通过图片路径打开图片
          # img = cv2.imread(data['imagePath'], 0)
          height, width = img.shape[:2]
          img = None
          image['height'] = height
          image['width'] = width
          image['id'] = num + 1
          image['file_name'] = data['imagePath'].split('/')[-1]
  
          self.height = height
          self.width = width
  
          return image
  
      def categorie(self, label):
          categorie = {}
          categorie['supercategory'] = 'Cancer'
          categorie['id'] = len(self.label) + 1  # 0 默认为背景
          categorie['name'] = label
          return categorie
  
      def annotation(self, points, label, num):
          annotation = {}
          annotation['segmentation'] = [list(np.asarray(points).flatten())]
          annotation['iscrowd'] = 0
          annotation['image_id'] = num + 1
          # annotation['bbox'] = str(self.getbbox(points)) # 使用list保存json文件时报错（不知道为什么）
          # list(map(int,a[1:-1].split(','))) a=annotation['bbox'] 使用该方式转成list
          bbox = list(map(float, self.getbbox(points)))
          # x1,y1,x4,y4 = bbox
          # bbox[2] = x4 - x1
          # bbox[3] = y4 - y1
          # annotation['bbox'] = bbox
          annotation['bbox'] = list(map(float, self.getbbox(points)))
          annotation['area'] = annotation['bbox'][2] * annotation['bbox'][3]
          # annotation['category_id'] = self.getcatid(label)
          annotation['category_id'] = self.getcatid(label)
          annotation['id'] = self.annID
          return annotation
  
      def getcatid(self, label):
          for categorie in self.categories:
              if label == categorie['name']:
                  return categorie['id']
          return 1
  
      def getbbox(self, points):
          # img = np.zeros([self.height,self.width],np.uint8)
          # cv2.polylines(img, [np.asarray(points)], True, 1, lineType=cv2.LINE_AA)  # 画边界线
          # cv2.fillPoly(img, [np.asarray(points)], 1)  # 画多边形 内部像素值为1
          polygons = points
  
          mask = self.polygons_to_mask([self.height, self.width], polygons)
          return self.mask2box(mask)
  
      def mask2box(self, mask):
          '''从mask反算出其边框
          mask：[h,w]  0、1组成的图片
          1对应对象，只需计算1对应的行列号（左上角行列号，右下角行列号，就可以算出其边框）
          '''
          # np.where(mask==1)
          index = np.argwhere(mask == 1)
          rows = index[:, 0]
          clos = index[:, 1]
          # 解析左上角行列号
          left_top_r = np.min(rows)  # y
          left_top_c = np.min(clos)  # x
  
          # 解析右下角行列号
          right_bottom_r = np.max(rows)
          right_bottom_c = np.max(clos)
  
          # return [(left_top_r,left_top_c),(right_bottom_r,right_bottom_c)]
          # return [(left_top_c, left_top_r), (right_bottom_c, right_bottom_r)]
          # return [left_top_c, left_top_r, right_bottom_c, right_bottom_r]  # [x1,y1,x2,y2]
          return [left_top_c, left_top_r, right_bottom_c - left_top_c,
                  right_bottom_r - left_top_r]  # [x1,y1,w,h] 对应COCO的bbox格式
  
      def polygons_to_mask(self, img_shape, polygons):
          mask = np.zeros(img_shape, dtype=np.uint8)
          mask = PIL.Image.fromarray(mask)
          xy = list(map(tuple, polygons))
          PIL.ImageDraw.Draw(mask).polygon(xy=xy, outline=1, fill=1)
          mask = np.array(mask, dtype=bool)
          return mask
  
      def data2coco(self):
          data_coco = {}
          data_coco['images'] = self.images
          data_coco['categories'] = self.categories
          data_coco['annotations'] = self.annotations
          return data_coco
  
      def save_json(self):
          self.data_transfer()
          self.data_coco = self.data2coco()
          # 保存json文件
          json.dump(self.data_coco, open(self.save_json_path, 'w'), indent=4, cls=MyEncoder)
  
  
  # labelme_json = glob.glob(r'C:\Users\l\Desktop\target\*.json')
  labelme_json = glob.glob(r'C:\Users\l\Desktop\test_code\*.json')
  # labelme_json=['./Annotations/*.json']
  
  labelme2coco(labelme_json, r'C:\Users\l\Desktop\test_result\result.json')
  # labelme2coco(labelme_json, './json')
  

• 分析：

  1. 最下两行是运行的实际命令:

     labelme_json = glob.glob(r'C:\Users\l\Desktop\test_code\*.json')
     labelme2coco(labelme_json, r'C:\Users\l\Desktop\test_result\result.json')
     

     第一行获得某一文件夹下全部以.json结尾的文件，以列表保存在labelme_json变量中

     第二行执行程序，接下来分析程序

  2. class labelme2coco(object):
         def __init__(self, labelme_json=[], save_json_path='./tran.json'):
             '''
             :param labelme_json: 所有labelme的json文件路径组成的列表
             :param save_json_path: json保存位置
             '''
             self.labelme_json = labelme_json
             self.save_json_path = save_json_path
             self.images = []
             self.categories = []
             self.annotations = []
             # self.data_coco = {}
             self.label = []
             self.annID = 1
             self.height = 0
             self.width = 0
     
             self.save_json()
     

     此处进行一些初始化。

  3. def save_json(self):
             self.data_transfer()
             self.data_coco = self.data2coco()
             # 保存json文件
             json.dump(self.data_coco, open(self.save_json_path, 'w'), indent=4, cls=MyEncoder)
     

     self.data_transfer()把labelme的json文件中有用的数据读出来

     self.data_coco = self.data2coco()把类的属性取出来保存

  4. 具体注意在

     def getbbox(self, points):
             # img = np.zeros([self.height,self.width],np.uint8)
             # cv2.polylines(img, [np.asarray(points)], True, 1, lineType=cv2.LINE_AA)  # 画边界线
             # cv2.fillPoly(img, [np.asarray(points)], 1)  # 画多边形 内部像素值为1
             polygons = points
             
            mask = self.polygons_to_mask([self.height, self.width], polygons)
            return self.mask2box(mask)
     

     中操作后把labeme json中的 (xyxy)变成了(xywh)

     其他的比较易懂就不再分析