暂无图片
暂无图片
暂无图片
暂无图片
暂无图片
基于并行注意力UNet的裂缝检测方法 - 刘凡, 王君锋, 陈峙宇, 许峰.pdf
123
9页
1次
2021-11-16
免费下载
DOI
:
issn
JournalofCom
p
uterResearchandDevelo
p
ment
(
):
,
 
稿
:
;
:
 
:
(
BK
);
(
B
);
(
)
Thisworkwassu
pp
ortedb
y
theNaturalScienceFoundationofJian
g
suProvince
(
BK
),
theFundamentalResearchFunds
fortheCentralUniversities
(
B
),
andtheO
p
enPro
j
ectoftheKe
y
Laborator
y
ofCoastalDisasterandProtection
(
Hohai
Universit
y
)
ofMinistr
y
ofEuducation
(
)
UNet
 
 
 
 
 
(
 
 
)
(
(
)
 
 
)
(
hhueducn
)
ParallelAttentionBasedUNetforCrackDetection
LiuFan
,
Wan
g
Junfen
g
,
ChenZhi
y
u
,
andXuFen
g
(
Colle
g
eo
f
Com
p
uterIn
f
ormation
,
HohaiUniversit
y
,
Nan
j
in
g
)
(
Ke
y
Laborator
y
o
f
CoastalDisasterandProtection
(
HohaiUniversit
y
),
Ministr
y
o
f
Education
,
Nan
j
in
g
)
Abstract Crackshavehiddensafet
y
hazardsto
p
ublicfacilities
,
socrackdetectionisessentialforthe
maintenanceof
p
ublicfacilitiesDuetotheinterferenceofnoise
,
li
g
ht
,
shadow
,
andotherfactorsin
thecrackima
g
es
,
theneuralnetworkiseasil
y
affecteddurin
g
thetrainin
gp
rocess
,
whichcauses
deviationsinthe
p
redictionresultsandreducesthe
p
redictioneffectTosu
pp
ressthesedisturbances
,
a
p
arallelattention mechanismisdesi
g
nedandthenthe
p
arallelattentionbased UNet
(
PAUNet
)
is
p
ro
p
osedb
y
embeddin
g
thisattention mechanism into UNetThe
p
arallelattention mechanism
increasesthewei
g
htsofcrackfeaturesfrom thetwodimensionsofchannelands
p
acetosu
pp
ress
interference
,
thenfusesthefeatures
g
eneratedb
y
thesetwodimensionstoobtainmorecom
p
lementar
y
crackfeaturesToverif
y
theeffectivenessofthe
p
ro
p
osedmethod
,
wehaveconductedex
p
erimentson
fourdatasetsEx
p
erimentalresultsshowthatourmethodout
p
erformstheexistin
gp
o
p
ularmethods
Meanwhile
,
to demonstratetheeffectivenessofthe
p
arallelattention mechanism
,
weconducta
com
p
arativeex
p
erimentwithotherfourattention mechanismsTheresultsshowthatthe
p
arallel
attentionmechanism
p
erformsbetterthanothers
Ke
y
words crackdetection
;
p
arallelattentionmechanism
;
UNet
;
su
pp
ressinterference
;
com
p
lementar
y
 
 
,
线
,
,
,
,
,
UNet
,
UNet
(
p
arallelattentionbasedUNet
,
PAUNet
)
,
,
,
,
,
,
,
,
 
;
;
UNet
;
;
 TP
  
,
,
,
,
广
,
,
,
[
]
[
]
[
]
[
]
[
]
,
,
,
,
,
,
,
,
广
[
]
[
]
[
]
[
]
,
,
,
使
,
线
,
,
,
,
UNet
,
UNet
,
,
,
,
 
,
广
Yao
[
]
,
,
Liu
[
]
UNet
,
,
,
,
Ali
[
]
,
CNN
,
,
Nie
[
]
YOLO
(
Youonl
y
lookonce
)
V
,
,
Son
g
[
]
,
,
,
,
Xian
g
[
]
,
,
Koni
g
[
]
UNet
,
,
ReLu
Wan
g
[
]
IUNet
,
,
使
Fan
[
]
UHierarchical
DilatedNetwork
(
UHDN
),
,
,
,
Li
[
]
(
convolutional
neuralnetwork
,
CNN
)
,
CNN
,
CNN
,
,
Li
[
]
UNet
Cli
q
ueNet
(
convolutional neuralnetworks with alternatel
y
u
p
datedcli
q
ue
)
UCli
q
ueNet
,
Cli
q
ueBlock
UNet
,
Ren
[
]
CrackSe
g
Net
,
,
,
,
,
 
:
UNet
of 9
免费下载
【版权声明】本文为墨天轮用户原创内容,转载时必须标注文档的来源(墨天轮),文档链接,文档作者等基本信息,否则作者和墨天轮有权追究责任。如果您发现墨天轮中有涉嫌抄袭或者侵权的内容,欢迎发送邮件至:contact@modb.pro进行举报,并提供相关证据,一经查实,墨天轮将立刻删除相关内容。

评论

关注
最新上传
暂无内容,敬请期待...
下载排行榜
Top250 周榜 月榜