US 2026/0105726 A1 · DISASTER SMOKE DETECTION METHOD BASED ON DEEP CONVOLUTIONAL NEURAL NETWORK

Abstract

A disaster smoke detection method includes: performing a first convolution operation on an input image to extract features to generate a primary feature map; performing enhancement processing on the primary feature map to obtain an enhanced feature map; performing multi-scale fusion on the enhanced feature map according to a second convolution operation to obtain a plurality of feature maps of different scales as high-level feature maps; respectively performing top-down feature fusion and bottom-up feature fusion on each high-level feature map at each scale according to a third convolution operation to correspondingly obtain a plurality of top-down fused feature maps and a plurality of bottom-up fused feature maps; fusing the top-down fused feature maps and the bottom-up fused feature maps to obtain a plurality of bidirectional cross-fused feature maps; and performing disaster and smoke detection on each of the bidirectional cross-fused feature maps.

A disaster smoke detection method based on a deep convolutional neural network, comprising:

performing a first convolution operation on an input image to extract features to generate a primary feature map;
performing enhancement processing on the primary feature map to obtain an enhanced feature map;
performing multi-scale fusion on the enhanced feature map according to a second convolution operation to obtain a plurality of feature maps of different scales as high-level feature maps;
respectively performing top-down feature fusion and bottom-up feature fusion on each high-level feature map at each scale according to a third convolution operation to correspondingly obtain a plurality of top-down fused feature maps and a plurality of bottom-up fused feature maps;
fusing the top-down fused feature maps and the bottom-up fused feature maps to obtain a plurality of bidirectional cross-fused feature maps;
and
performing disaster and smoke detection on each of the bidirectional cross-fused feature maps,
wherein the performing a first convolution operation on an input image to extract features to generate a primary feature map comprises:
performing a convolution operation on the input image through a spatial and channel reconstruction convolution module to obtain a basic feature map,
wherein the convolution operation of the spatial and channel reconstruction convolution module is expressed as the following formula:
X
′
=
ScConv
⁡
(
X
)
=
σ
act
(
BN
⁡
(
CRU
⁡
(
SRU
⁡
(
Conv
⁡
(
X
)
)
)
)
)
,
where X′ represents the basic feature map;
ScConv represents a spatial and channel reconstruction convolution operation;
Conv(X) represents a convolution operation of the input image X with a weight W, with a kernel size of k×k and a stride s, using automatic padding p to adjust a size of a feature map to be outputted;
SRU(X) is used for handling spatial redundancy;
CRU(X) is used for handling channel redundancy;
BN(·) represents a batch normalization operation;
and σact(·) represents an SiLU activation function;
and
performing a convolution operation on the basic feature map through a residual block to obtain the primary feature map,
wherein the convolution operation of the residual block is expressed as the following formula:
F
⁡
(
X
′
)
=
S
⁢
c
⁢
C
⁢
o
⁢
n
⁢
v
2
(
σ
act
(
B
⁢
N
1
(
S
⁢
c
⁢
C
⁢
o
⁢
n
⁢
v
1
(
X
′
)
)
)
)
;
and
residual connection of the residual block is expressed as the following formula:
Y
′
=
X
′
+
F
⁡
(
X
′
)
,
where ScConv1 and ScConv2 represent two consecutive spatial and channel reconstruction convolution operations, F(X′) represents a convolved feature mapping, and Y′ the primary feature map;
and
wherein the performing enhancement processing on the primary feature map to obtain an enhanced feature map comprises:
generating a weight matrix corresponding to the primary feature map through a convolution operation of an attention mechanism, and performing element-wise multiplication on the weight matrix and the primary feature map to obtain a first intermediate feature map,
wherein the convolution operation of the attention mechanism is expressed as the following formula:
A
=
Sigmoid
(
Conv
a
⁢
t
⁢
t
(
Y
′
)
)
,
where A represents the weight matrix, Convatt represents the convolution operation that generates the weight matrix, and Sigmoid represents a function for generating a normalized output;
and the first intermediate feature map is defined as Z′, and Z′=A⊙Y′;
generating an offset amount of a deformable convolutional layer of the first intermediate feature map through a local convolution operation, and performing a deformable convolution operation according to the offset amount of the deformable convolutional layer and the first intermediate feature map to obtain a second intermediate feature map,
wherein the offset amount of the deformable convolutional layer is expressed as the following formula:
Δ
⁢
p
=
C
⁢
o
⁢
n
⁢
v
offset
(
Z
′
)
;
and
wherein the deformable convolution operation is expressed as the following formula:
Z
″
=
DeformConv
⁡
(
Z
′
,
Δ
⁢
p
)
,
where Δp represents the offset amount of the deformable convolutional layer, Convoffset represents a convolution operation of an independent convolutional layer, DeformConv represents the deformable convolution operation, and Z″ represents the second intermediate feature map;
performing Gabor filtering processing on the second intermediate feature map to obtain a filtered feature map,
wherein the Gabor filtering processing is expressed as the following formula:
G
⁡
(
x
,
y
)
=
exp
⁡
(
-
x
2
+
γ
2
⁢
y
2
2
⁢
σ
gabor
2
)
⁢
cos
⁢
(
2
⁢
π
⁢
x
λ
+
ψ
)
,
where σgabor is used for controlling a width of a Gaussian function, γ is used for controlling an aspect ratio of an elliptical Gaussian distribution, λ represents a wavelength, ψ represents a phase offset, and x, y represents pixel coordinates;
and
adjusting a brightness and contrast of the filtered feature map to obtain the enhanced feature map.

215 more elements

Disaster smoke detection method based on deep convolutional neural network

Life of this patent

Disaster smoke detection method based on deep convolutional neural network

Life of this patent

Abstract

Claims8