-
Notifications
You must be signed in to change notification settings - Fork 29
/
Copy pathnet_canny.py
147 lines (108 loc) · 6.38 KB
/
net_canny.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
import torch
import torch.nn as nn
import numpy as np
from scipy.signal import gaussian
class Net(nn.Module):
def __init__(self, threshold=10.0, use_cuda=False):
super(Net, self).__init__()
self.threshold = threshold
self.use_cuda = use_cuda
filter_size = 5
generated_filters = gaussian(filter_size,std=1.0).reshape([1,filter_size])
self.gaussian_filter_horizontal = nn.Conv2d(in_channels=1, out_channels=1, kernel_size=(1,filter_size), padding=(0,filter_size//2))
self.gaussian_filter_horizontal.weight.data.copy_(torch.from_numpy(generated_filters))
self.gaussian_filter_horizontal.bias.data.copy_(torch.from_numpy(np.array([0.0])))
self.gaussian_filter_vertical = nn.Conv2d(in_channels=1, out_channels=1, kernel_size=(filter_size,1), padding=(filter_size//2,0))
self.gaussian_filter_vertical.weight.data.copy_(torch.from_numpy(generated_filters.T))
self.gaussian_filter_vertical.bias.data.copy_(torch.from_numpy(np.array([0.0])))
sobel_filter = np.array([[1, 0, -1],
[2, 0, -2],
[1, 0, -1]])
self.sobel_filter_horizontal = nn.Conv2d(in_channels=1, out_channels=1, kernel_size=sobel_filter.shape, padding=sobel_filter.shape[0]//2)
self.sobel_filter_horizontal.weight.data.copy_(torch.from_numpy(sobel_filter))
self.sobel_filter_horizontal.bias.data.copy_(torch.from_numpy(np.array([0.0])))
self.sobel_filter_vertical = nn.Conv2d(in_channels=1, out_channels=1, kernel_size=sobel_filter.shape, padding=sobel_filter.shape[0]//2)
self.sobel_filter_vertical.weight.data.copy_(torch.from_numpy(sobel_filter.T))
self.sobel_filter_vertical.bias.data.copy_(torch.from_numpy(np.array([0.0])))
# filters were flipped manually
filter_0 = np.array([ [ 0, 0, 0],
[ 0, 1, -1],
[ 0, 0, 0]])
filter_45 = np.array([ [0, 0, 0],
[ 0, 1, 0],
[ 0, 0, -1]])
filter_90 = np.array([ [ 0, 0, 0],
[ 0, 1, 0],
[ 0,-1, 0]])
filter_135 = np.array([ [ 0, 0, 0],
[ 0, 1, 0],
[-1, 0, 0]])
filter_180 = np.array([ [ 0, 0, 0],
[-1, 1, 0],
[ 0, 0, 0]])
filter_225 = np.array([ [-1, 0, 0],
[ 0, 1, 0],
[ 0, 0, 0]])
filter_270 = np.array([ [ 0,-1, 0],
[ 0, 1, 0],
[ 0, 0, 0]])
filter_315 = np.array([ [ 0, 0, -1],
[ 0, 1, 0],
[ 0, 0, 0]])
all_filters = np.stack([filter_0, filter_45, filter_90, filter_135, filter_180, filter_225, filter_270, filter_315])
self.directional_filter = nn.Conv2d(in_channels=1, out_channels=8, kernel_size=filter_0.shape, padding=filter_0.shape[-1] // 2)
self.directional_filter.weight.data.copy_(torch.from_numpy(all_filters[:, None, ...]))
self.directional_filter.bias.data.copy_(torch.from_numpy(np.zeros(shape=(all_filters.shape[0],))))
def forward(self, img):
img_r = img[:,0:1]
img_g = img[:,1:2]
img_b = img[:,2:3]
blur_horizontal = self.gaussian_filter_horizontal(img_r)
blurred_img_r = self.gaussian_filter_vertical(blur_horizontal)
blur_horizontal = self.gaussian_filter_horizontal(img_g)
blurred_img_g = self.gaussian_filter_vertical(blur_horizontal)
blur_horizontal = self.gaussian_filter_horizontal(img_b)
blurred_img_b = self.gaussian_filter_vertical(blur_horizontal)
blurred_img = torch.stack([blurred_img_r,blurred_img_g,blurred_img_b],dim=1)
blurred_img = torch.stack([torch.squeeze(blurred_img)])
grad_x_r = self.sobel_filter_horizontal(blurred_img_r)
grad_y_r = self.sobel_filter_vertical(blurred_img_r)
grad_x_g = self.sobel_filter_horizontal(blurred_img_g)
grad_y_g = self.sobel_filter_vertical(blurred_img_g)
grad_x_b = self.sobel_filter_horizontal(blurred_img_b)
grad_y_b = self.sobel_filter_vertical(blurred_img_b)
# COMPUTE THICK EDGES
grad_mag = torch.sqrt(grad_x_r**2 + grad_y_r**2)
grad_mag += torch.sqrt(grad_x_g**2 + grad_y_g**2)
grad_mag += torch.sqrt(grad_x_b**2 + grad_y_b**2)
grad_orientation = (torch.atan2(grad_y_r+grad_y_g+grad_y_b, grad_x_r+grad_x_g+grad_x_b) * (180.0/3.14159))
grad_orientation += 180.0
grad_orientation = torch.round( grad_orientation / 45.0 ) * 45.0
# THIN EDGES (NON-MAX SUPPRESSION)
all_filtered = self.directional_filter(grad_mag)
inidices_positive = (grad_orientation / 45) % 8
inidices_negative = ((grad_orientation / 45) + 4) % 8
height = inidices_positive.size()[2]
width = inidices_positive.size()[3]
pixel_count = height * width
pixel_range = torch.FloatTensor([range(pixel_count)])
if self.use_cuda:
pixel_range = torch.cuda.FloatTensor([range(pixel_count)])
indices = (inidices_positive.view(-1).data * pixel_count + pixel_range).squeeze()
channel_select_filtered_positive = all_filtered.view(-1)[indices.long()].view(1,height,width)
indices = (inidices_negative.view(-1).data * pixel_count + pixel_range).squeeze()
channel_select_filtered_negative = all_filtered.view(-1)[indices.long()].view(1,height,width)
channel_select_filtered = torch.stack([channel_select_filtered_positive,channel_select_filtered_negative])
is_max = channel_select_filtered.min(dim=0)[0] > 0.0
is_max = torch.unsqueeze(is_max, dim=0)
thin_edges = grad_mag.clone()
thin_edges[is_max==0] = 0.0
# THRESHOLD
thresholded = thin_edges.clone()
thresholded[thin_edges<self.threshold] = 0.0
early_threshold = grad_mag.clone()
early_threshold[grad_mag<self.threshold] = 0.0
assert grad_mag.size() == grad_orientation.size() == thin_edges.size() == thresholded.size() == early_threshold.size()
return blurred_img, grad_mag, grad_orientation, thin_edges, thresholded, early_threshold
if __name__ == '__main__':
Net()