The cityscapes dataset is equipped with a cityscapesscripts tool. There is an implementation file that defines the number of categories in the tool.
For example, if you don't want so many types of semantic segmentation, first modify the labels.py file, modify the trainId of the category you want to comment out to 255, and modify the ignoreInEval to True. Then run createTrainIdLabelImgs.py. This file reads the polygons of the json file and sets the polygon area to the value of trainId. The output file is similar
Among them, white is 255 and dark is the trainid value of each category.
Unfortunately, I didn't understand it. I also found the following method, which can also realize the function of generating the above marked map.
The first step is to find a list of categories corresponding to the label color of the data set: (this is generally available on the official website or on github, and I found the cityscapes on github)
Label = namedtuple('Label', [
'name',
'id',
'trainId',
'category',
'categoryId',
'hasInstances',
'ignoreInEval',
'color'])
labels = [
# name id trainId category catId hasInstances ignoreInEval color
Label( 'unlabeled' , 0 , 255 , 'void' , 0 , False , True , ( 0, 0, 0) ),
Label( 'ego vehicle' , 1 , 255 , 'void' , 0 , False , True , ( 0, 0, 0) ),
Label( 'rectification border' , 2 , 255 , 'void' , 0 , False , True , ( 0, 0, 0) ),
Label( 'out of roi' , 3 , 255 , 'void' , 0 , False , True , ( 0, 0, 0) ),
Label( 'static' , 4 , 255 , 'void' , 0 , False , True , ( 0, 0, 0) ),
Label( 'dynamic' , 5 , 255 , 'void' , 0 , False , True , (111, 74, 0) ),
Label( 'ground' , 6 , 255 , 'void' , 0 , False , True , ( 81, 0, 81) ),
Label( 'road' , 7 , 1 , 'flat' , 1 , False , False , (128, 64,128) ),
Label( 'sidewalk' , 8 , 2 , 'flat' , 1 , False , False , (244, 35,232) ),
Label( 'parking' , 9 , 255 , 'flat' , 1 , False , True , (250,170,160) ),
Label( 'rail track' , 10 , 255 , 'flat' , 1 , False , True , (230,150,140) ),
Label( 'building' , 11 , 3 , 'construction' , 2 , False , False , ( 70, 70, 70) ),
Label( 'wall' , 12 , 4 , 'construction' , 2 , False , False , (102,102,156) ),
Label( 'fence' , 13 , 5 , 'construction' , 2 , False , False , (190,153,153) ),
Label( 'guard rail' , 14 , 255 , 'construction' , 2 , False , True , (180,165,180) ),
Label( 'bridge' , 15 , 255 , 'construction' , 2 , False , True , (150,100,100) ),
Label( 'tunnel' , 16 , 255 , 'construction' , 2 , False , True , (150,120, 90) ),
Label( 'pole' , 17 , 6 , 'object' , 3 , False , False , (153,153,153) ),
Label( 'polegroup' , 18 , 255 , 'object' , 3 , False , True , (153,153,153) ),
Label( 'traffic light' , 19 , 7 , 'object' , 3 , False , False , (250,170, 30) ),
Label( 'traffic sign' , 20 , 8 , 'object' , 3 , False , False , (220,220, 0) ),
Label( 'vegetation' , 21 , 9 , 'nature' , 4 , False , False , (107,142, 35) ),
Label( 'terrain' , 22 , 10 , 'nature' , 4 , False , False , (152,251,152) ),
Label( 'sky' , 23 , 11 , 'sky' , 5 , False , False , ( 70,130,180) ),
Label( 'person' , 24 , 12 , 'human' , 6 , True , False , (220, 20, 60) ),
Label( 'rider' , 25 , 13 , 'human' , 6 , True , False , (255, 0, 0) ),
Label( 'car' , 26 , 14 , 'vehicle' , 7 , True , False , ( 0, 0,142) ),
Label( 'truck' , 27 , 15 , 'vehicle' , 7 , True , False , ( 0, 0, 70) ),
Label( 'bus' , 28 , 16 , 'vehicle' , 7 , True , False , ( 0, 60,100) ),
Label( 'caravan' , 29 , 255 , 'vehicle' , 7 , True , True , ( 0, 0, 90) ),
Label( 'trailer' , 30 , 255 , 'vehicle' , 7 , True , True , ( 0, 0,110) ),
Label( 'train' , 31 , 17 , 'vehicle' , 7 , True , False , ( 0, 80,100) ),
Label( 'motorcycle' , 32 , 18 , 'vehicle' , 7 , True , False , ( 0, 0,230) ),
Label( 'bicycle' , 33 , 19 , 'vehicle' , 7 , True , False , (119, 11, 32) ),
Label( 'license plate' , -1 , -1 , 'vehicle' , 7 , False , True , ( 0, 0,142) ),
]
The second step is to read the labels of labels into a color2index dictionary:
color2index = {}
color2index[(0, 0, 0)] = 0 # add an void class
for obj in labels:
if obj.ignoreInEval:
continue
idx = obj.trainId
label = obj.name
color = obj.color
color2index[color] = idx
print(color2index)The third step is to read in the label picture, and then compare the RGB value of each pixel in the picture with the color2index dictionary. If the same, record the index of the RGB value in color2index
Complete code:
import numpy as np
import scipy.misc
from collections import namedtuple
np.set_printoptions(threshold=np.inf)
Label = namedtuple('Label', [
'name',
'id',
'trainId',
'category',
'categoryId',
'hasInstances',
'ignoreInEval',
'color'])
labels = [
# name id trainId category catId hasInstances ignoreInEval color
Label( 'unlabeled' , 0 , 255 , 'void' , 0 , False , True , ( 0, 0, 0) ),
Label( 'ego vehicle' , 1 , 255 , 'void' , 0 , False , True , ( 0, 0, 0) ),
Label( 'rectification border' , 2 , 255 , 'void' , 0 , False , True , ( 0, 0, 0) ),
Label( 'out of roi' , 3 , 255 , 'void' , 0 , False , True , ( 0, 0, 0) ),
Label( 'static' , 4 , 255 , 'void' , 0 , False , True , ( 0, 0, 0) ),
Label( 'dynamic' , 5 , 255 , 'void' , 0 , False , True , (111, 74, 0) ),
Label( 'ground' , 6 , 255 , 'void' , 0 , False , True , ( 81, 0, 81) ),
Label( 'road' , 7 , 1 , 'flat' , 1 , False , False , (128, 64,128) ),
Label( 'sidewalk' , 8 , 2 , 'flat' , 1 , False , False , (244, 35,232) ),
Label( 'parking' , 9 , 255 , 'flat' , 1 , False , True , (250,170,160) ),
Label( 'rail track' , 10 , 255 , 'flat' , 1 , False , True , (230,150,140) ),
Label( 'building' , 11 , 3 , 'construction' , 2 , False , False , ( 70, 70, 70) ),
Label( 'wall' , 12 , 4 , 'construction' , 2 , False , False , (102,102,156) ),
Label( 'fence' , 13 , 5 , 'construction' , 2 , False , False , (190,153,153) ),
Label( 'guard rail' , 14 , 255 , 'construction' , 2 , False , True , (180,165,180) ),
Label( 'bridge' , 15 , 255 , 'construction' , 2 , False , True , (150,100,100) ),
Label( 'tunnel' , 16 , 255 , 'construction' , 2 , False , True , (150,120, 90) ),
Label( 'pole' , 17 , 6 , 'object' , 3 , False , False , (153,153,153) ),
Label( 'polegroup' , 18 , 255 , 'object' , 3 , False , True , (153,153,153) ),
Label( 'traffic light' , 19 , 7 , 'object' , 3 , False , False , (250,170, 30) ),
Label( 'traffic sign' , 20 , 8 , 'object' , 3 , False , False , (220,220, 0) ),
Label( 'vegetation' , 21 , 9 , 'nature' , 4 , False , False , (107,142, 35) ),
Label( 'terrain' , 22 , 10 , 'nature' , 4 , False , False , (152,251,152) ),
Label( 'sky' , 23 , 11 , 'sky' , 5 , False , False , ( 70,130,180) ),
Label( 'person' , 24 , 12 , 'human' , 6 , True , False , (220, 20, 60) ),
Label( 'rider' , 25 , 13 , 'human' , 6 , True , False , (255, 0, 0) ),
Label( 'car' , 26 , 14 , 'vehicle' , 7 , True , False , ( 0, 0,142) ),
Label( 'truck' , 27 , 15 , 'vehicle' , 7 , True , False , ( 0, 0, 70) ),
Label( 'bus' , 28 , 16 , 'vehicle' , 7 , True , False , ( 0, 60,100) ),
Label( 'caravan' , 29 , 255 , 'vehicle' , 7 , True , True , ( 0, 0, 90) ),
Label( 'trailer' , 30 , 255 , 'vehicle' , 7 , True , True , ( 0, 0,110) ),
Label( 'train' , 31 , 17 , 'vehicle' , 7 , True , False , ( 0, 80,100) ),
Label( 'motorcycle' , 32 , 18 , 'vehicle' , 7 , True , False , ( 0, 0,230) ),
Label( 'bicycle' , 33 , 19 , 'vehicle' , 7 , True , False , (119, 11, 32) ),
Label( 'license plate' , -1 , -1 , 'vehicle' , 7 , False , True , ( 0, 0,142) ),
]
if __name__ =='__main__':
color2index = {}
color2index[(0, 0, 0)] = 0 # add an void class
for obj in labels:
if obj.ignoreInEval:
continue
idx = obj.trainId
label = obj.name
color = obj.color
color2index[color] = idx
print(color2index)
img = r'F:\dataset\cityspaces\gtFine\train\aachen\aachen_000002_000019_gtFine_color.png'
img = scipy.misc.imread(img, mode='RGB')
height, weight, _ = img.shape
l = []
idx_mat = np.zeros((height, weight))
for h in range(height):
for w in range(weight):
color = tuple(img[h, w])
#print(color)
# print(color)
try:
index = color2index[color]
idx_mat[h, w] = index
if index not in l:
l.append(index)
except:
# no index, assign to void
idx_mat[h, w] = 0
idx_mat = idx_mat.astype(np.uint8)
print(l) #打印出现过的索引(类别)example:
Enter picture:
Output:
This indicates how many categories are in the label image
But if idx_max is output, the pixel value of the picture is all replaced by the index value, which is a number from 0 to 19 (a total of 20 categories)
Such as:
