目录
摘要
Object Instance 类型的标注格式
1、整体JSON文件格式
2、annotations字段
3、categories字段
Labelme转COCO的代码：
摘要
COCO的 全称是Common Objects in COntext，是微软团队提供的一个可以用来进行图像识别的数据集。MS COCO数据集中的图像分为训练、验证和测试集。COCO通过在Flickr上搜索80个对象类别和各种场景类型来收集图像，其使用了亚马逊的Mechanical Turk（AMT）。
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）。本文着重介绍object instances。
Object Instance 类型的标注格式
1、整体JSON文件格式
Object Instance这种格式的文件从头至尾按照顺序分为以下段落：
{
"info": info,
"licenses": [license],
"images": [image],
"annotations": [annotation],
"categories": [category]
}
2、annotations字段
annotations字段是包含多个annotation实例的一个数组，annotation类型本身又包含了一系列的字段，如这个目标的category id和segmentation mask。segmentation格式取决于这个实例是一个单个的对象（即iscrowd=0，将使用polygons格式）还是一组对象（即iscrowd=1，将使用RLE格式）。bbox是存放的物体标注信息，与VOC格式不同，COCO里面存储的格式是[左上角x坐标,左上角y坐标,物体的宽,物体的长],这点需要注意。如下所示：
annotation{
"id": int,
"image_id": int,
"category_id": int,
"segmentation": RLE or [polygon],
"area": float,
"bbox": [x,y,width,height],
"iscrowd": 0 or 1,
}
注意，单个的对象（iscrowd=0)可能需要多个polygon来表示，比如这个对象在图像中被挡住了。而iscrowd=1时（将标注一组对象，比如一群人）的segmentation使用的就是RLE格式。
另外，每个对象（不管是iscrowd=0还是iscrowd=1）都会有一个矩形框bbox ，矩形框左上角的坐标和矩形框的长宽会以数组的形式提供，数组第一个元素就是左上角的横坐标值。
area是area of encoded masks。
最后，annotation结构中的categories字段存储的是当前对象所属的category的id，以及所属的supercategory的name。
下面是从instances_val2017.json文件中摘出的一个annotation的实例：
{
"segmentation": [[510.66,423.01,511.72,420.03,510.45,416.0,510.34,413.02,510.77,410.26,\
510.77,407.5,510.34,405.16,511.51,402.83,511.41,400.49,510.24,398.16,509.39,\
397.31,504.61,399.22,502.17,399.64,500.89,401.66,500.47,402.08,499.09,401.87,\
495.79,401.98,490.59,401.77,488.79,401.77,485.39,398.58,483.9,397.31,481.56,\
396.35,478.48,395.93,476.68,396.03,475.4,396.77,473.92,398.79,473.28,399.96,\
473.49,401.87,474.56,403.47,473.07,405.59,473.39,407.71,476.68,409.41,479.23,\
409.73,481.56,410.69,480.4,411.85,481.35,414.93,479.86,418.65,477.32,420.03,\
476.04,422.58,479.02,422.58,480.29,423.01,483.79,419.93,486.66,416.21,490.06,\
415.57,492.18,416.85,491.65,420.24,492.82,422.9,493.56,424.39,496.43,424.6,\
498.02,423.01,498.13,421.31,497.07,420.03,497.07,415.15,496.33,414.51,501.1,\
411.96,502.06,411.32,503.02,415.04,503.33,418.12,501.1,420.24,498.98,421.63,\
500.47,424.39,505.03,423.32,506.2,421.31,507.69,419.5,506.31,423.32,510.03,\
423.01,510.45,423.01]],
"area": 702.1057499999998,
"iscrowd": 0,
"image_id": 289343,
"bbox": [473.07,395.93,38.65,28.67],
"category_id": 18,
"id": 1768
},
3、categories字段
categories是一个包含多个category实例的数组，而category结构体描述如下：
{
"id": int,
"name": str,
"supercategory": str,
}
从instances_val2017.json文件中摘出的2个category实例如下所示：
{
"supercategory": "person",
"id": 1,
"name": "person"
},
{
"supercategory": "vehicle",
"id": 2,
"name": "bicycle"
},
Labelme转COCO的代码：
# -*- coding:utf-8 -*-
# !/usr/bin/env python
import json
from labelme import utils
import numpy as np
import glob
import PIL.Image
labels={'一次性快餐盒':1,'书籍纸张':2,'充电宝':3,'剩饭剩菜':4,'包':5,
'垃圾桶':6,'塑料器皿':7,'塑料玩具':8,'塑料衣架':9,'大骨头':10,'干电池':11,
'快递纸袋':12,'插头电线':13,'旧衣服':14,'易拉罐':15,'枕头':16,'果皮果肉':17,'毛绒玩具':18,
'污损塑料':19,'污损用纸':20,'洗护用品':21,'烟蒂':22,'牙签':23,'玻璃器皿':24,'砧板':25,
'筷子':26,'纸盒纸箱':27,'花盆':28,'茶叶渣':29,'菜帮菜叶':30,'蛋壳':31,'调料瓶':32,
'软膏':33,'过期药物':34,'酒瓶':35,'金属厨具':36,'金属器皿':37,'金属食品罐':38,'锅':39,
'陶瓷器皿':40,'鞋':41,'食用油桶':42,'饮料瓶':43,'鱼骨':44}
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):
imagePath=json_file.split('.')[0]+'.jpg'
imageName=imagePath.split('\\')[-1]
print(imageName)
with open(json_file, 'r') as fp:
data = json.load(fp) # 加载json文件
self.images.append(self.image(data, num,imageName))
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,imagePath):
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'] = imagePath
self.height = height
self.width = width
return image
def categorie(self, label):
categorie = {}
categorie['supercategory'] = 'Cancer'
categorie['id'] = labels[label] # 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
print(label,annotation['category_id'])
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('D:/HWLabelme/*.json')
from sklearn.model_selection import train_test_split
trainval_files, test_files = train_test_split(labelme_json, test_size=0.2, random_state=55)
labelme2coco(trainval_files, 'instances_train2017.json')
labelme2coco(test_files, 'instances_val2017.json')
