labelme格式数据转化为标准的coco数据集格式

labelme标注图像生成的json格式：

{
  "version": "3.11.2",
  "flags": {},
  "shapes": [# 每个对象的形状
    { # 第一个对象
      "label": "malignant",
      "line_color": null,
      "fill_color": null,
      "points": [# 边缘是由点构成，将这些点连在一起就是对象的边缘多边形
        [
          371, # 第一个点 x 坐标
          257  # 第一个点 y 坐标
        ],
        ...
        [
          412,
          255
        ]
      ],
      "shape_type": "polygon"  # 形状类型：多边形
    },
    {
      "label": "malignant",  # 第一个对象的标签
      "line_color": null,
      "fill_color": null,
      "points": [# 第二个对象
        [
          522,
          274
        ],
        ...
        [
          561,
          303
        ]
      ],
      "shape_type": "polygon"
    },
    {
      "label": "malignant", # 第二个对象的标签
      "line_color": null,
      "fill_color": null,
  "imagePath": "../../val2017/000001.jpg", # 原始图片的路径
  "imageData":"something too long ",# 原图像数据 通过该字段可以解析出原图像数据
  "imageHeight": 768,
  "imageWidth": 1024
}

coco标准数据集格式：

COCO通过大量使用Amazon Mechanical Turk来收集数据。COCO数据集现在有3种标注类型：object instances（目标实例）, object keypoints（目标上的关键点）, and image captions（看图说话），使用JSON文件存储。

基本的JSON结构体类型

这3种类型共享下面所列的基本类型，包括image、categories、annotation类型。

Images类型：

"images": [
        {
            "height": 768,
            "width": 1024,
            "id": 1,  #图片id
            "file_name": "000002.jpg"
        }
]

 categories类型：

"categories": [
        {
            "supercategory": "Cancer", #父类
            "id": 1,           #标签类别id，0表示背景
            "name": "benign"   #子类
        },
        {
            "supercategory": "Cancer",
            "id": 2,
            "name": "malignant"
        }
    ],

annotations类型：

"annotations": [
        {
            "segmentation": [#坐标点的坐标值
                [
                    418,
                    256,
                    391,
                    293,
                    406,
                    323,
                    432,
                    340,
                    452,
                    329,
                    458,
                    311,
                    458,
                    286,
                    455,
                    277,
                    439,
                    264,
                    418,
                    293,
                    391,
                    256
                ]
            ],
            "iscrowd": 0, #单个的对象（iscrowd=0)可能需要多个polygon来表示
            "image_id": 1, #和image的id保持一致
            "bbox": [      #标注的边框值  bbox是将segmentation包起来的水平矩形
                391.0,
                256.0,
                67.0,
                84.0
            ],
            "area": 5628.0,  #标注的边框面积
            "category_id": 1, #所属类别id
            "id": 1          #标注边框的id : 1,2,3...,n
        }
]

labelme 转化为coco

# -*- coding:utf-8 -*-
# !/usr/bin/env python

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

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 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
                    #points.append([points[0][0],points[1][1]])
                    #points.append([points[1][0],points[0][1]])
                    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]
        image['file_name'] = data['imagePath'][3:14]
        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
        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)#注意，源代码默认为1
        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)  # indent=4 更加美观显示


labelme_json = glob.glob('./Annotations/*.json')
# labelme_json=['./Annotations/*.json']

labelme2coco(labelme_json, './json/test.json')