label2COCO(area).py
网上找到的都是要积分下载，自己尝试着补充了下area计算，不一定正确．．
mask面积计算：
1.根据labelme生成的json文件里的points来生成mask
2.确定目标检测框的位置(左上角位置，右下角位置)
3.依次计算mask中一行像素与下一行像素组成的梯形的面积，由于mask一定是连续的，所以梯形的边长可以通过遍历当前行像素的值来求(像素为１表示属于mask)，最后对每一行求和．
完整代码如下（除了relArea其他是照搬的）
# -*- 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 labelme2coco(object):
def __init__(self,labelme_json=[],save_json_path='./new.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']:
print (shapes['label'])
label=shapes['label'].split('_')
print (json_file,label)
if label[1] not in self.label:
self.categories.append(self.categorie(label))
self.label.append(label[1])
points=shapes['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'] = label[0]
categorie['id']=len(self.label)+1 # 0 默认为背景
categorie['name'] = label[1]
return categorie
"""
自己写的计算mask面积的方法(只适用于单个对象polygen形状标注),先生成mask,然后依次计算相邻行像素组成的mask面积(上底＋下底)*h/2，h是像素１，底边长通过遍历当前行像素值得到(0为非mask)，最后求和得到mask面积
"""
def rleArea(self,points):
#points = [[100,105],[50,105],[50,200],[100,200]]
mask = self.polygons_to_mask([self.height,self.width], points)
# np.where(mask==1)
index = np.argwhere(mask == 1)
rows = index[:, 0]
clos = index[:, 1]
# 解析左上角行列号
start_h = np.min(rows) # y
start_w = np.min(clos) # x
# 解析右下角行列号
end_h = np.max(rows)
end_w = np.max(clos)
area = 0
#print start_h,end_h,start_w,end_w
for i in range(start_h,end_h):
top = 0
bottom = 0
for j in range(start_w,end_w):
if(mask[i,j] == 1):
top+=1
for j in range(start_w,end_w):
if(mask[i+1,j] == 1):
bottom+=1
#print (i,top,bottom)
area += (top+bottom)/2
return area
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)))
"""
自己写的计算mask面积的方法(只适用于单个对象polygen形状标注),先生成一个全黑的原图片大小的图片,然后填充标注得到的多边形,然后依次计算相邻行像素组成的mask面积(上底＋下底)*h/2，h是像素１，底边长通过遍历当前行像素值得到(0为非mask)，最后求和得到mask面积
"""
annotation['area'] = self.rleArea(points)
annotation['category_id'] = self.getcatid(label)
annotation['id'] = self.annID
return annotation
def getcatid(self,label):
for categorie in self.categories:
if label[1]==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) # indent=4 更加美观显示
labelme_json=glob.glob('./jsons/*.json')
# labelme_json=['./1.json']
labelme2coco(labelme_json,'./new.json')