T
E
L
K
O
M
N
I
K
A
T
elec
o
m
m
un
ica
t
io
n Co
m
pu
t
ing
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
24
,
No
.
1
,
Feb
r
u
ar
y
20
26
,
p
p
.
249
~
257
I
SS
N:
1
6
9
3
-
6
9
3
0
,
DOI
: 1
0
.
1
2
9
2
8
/TE
L
KOM
NI
KA.
v
24
i
1
.
2
7
2
1
2
249
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//jo
u
r
n
a
l.u
a
d
.
a
c.
id
/in
d
ex
.
p
h
p
/TELK
OM
N
I
K
A
A
pra
ctical
appro
a
ch
to Ca
ndi
Siw
a
3D
recons
tru
cti
o
n
with
CO
LM
A
P
a
nd
N
erfst
udio
H
elena
Widi
a
rt
i,
Ro
k
hm
a
t
F
ebria
nto
,
Ag
un
g
Alf
ia
ns
y
a
h
D
e
p
a
r
t
me
n
t
o
f
C
o
mp
u
t
e
r
S
y
st
e
ms E
n
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
,
Te
c
h
n
o
l
o
g
y
,
E
n
g
i
n
e
e
r
i
n
g
,
a
n
d
M
a
t
h
e
ma
t
i
c
s
,
P
r
a
set
i
y
a
M
u
l
y
a
U
n
i
v
e
r
si
t
y
,
J
a
k
a
r
t
a
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
May
14
,
2
0
2
5
R
ev
is
ed
No
v
11
,
2
0
2
5
Acc
ep
ted
Dec
8
,
2
0
2
5
We
d
e
m
o
n
stra
te
a
p
ra
c
ti
c
a
l
a
p
p
ro
a
c
h
fo
r
larg
e
-
sc
a
le
o
b
jec
t
th
re
e
-
d
i
m
e
n
sio
n
a
l
(
3D
)
re
c
o
n
str
u
c
ti
o
n
wit
h
fre
e
l
y
a
v
a
il
a
b
le
fra
m
e
wo
rk
s,
COL
M
AP
a
n
d
Ne
rfstu
d
io
.
We p
e
rfo
rm
e
d
th
e
re
c
o
n
stru
c
t
io
n
o
f
a
tem
p
le n
a
m
e
d
Ca
n
d
i
S
iwa
,
lo
c
a
ted
a
t
P
ra
m
b
a
n
a
n
S
it
e
,
wh
i
c
h
is
si
tu
a
ted
b
e
twe
e
n
Ce
n
tral
Ja
v
a
a
n
d
Yo
g
y
a
k
a
rta
P
ro
v
in
c
e
,
I
n
d
o
n
e
sia
.
We
u
ti
li
z
e
d
COLM
AP
a
n
d
Ne
rfstu
d
i
o
a
s
p
latfo
rm
s
fo
r
3
D
re
c
o
n
str
u
c
ti
o
n
fro
m
ima
g
e
s
c
a
p
t
u
re
d
b
y
a
n
e
v
e
ry
d
a
y
sm
a
rtp
h
o
n
e
.
I
n
th
e
3
D
m
o
d
e
l
c
o
n
stru
c
ti
o
n
p
r
o
c
e
ss
,
COLM
AP
g
e
n
e
ra
tes
a
d
e
n
se
p
o
i
n
t
c
l
o
u
d
,
wh
e
re
a
s Ne
rfstu
d
i
o
g
e
n
e
ra
tes
a
sc
e
n
e
fr
o
m
so
u
rc
e
ima
g
e
s.
We
se
lec
ted
9
6
ima
g
e
s
o
f
Ca
n
d
i
S
iwa
to
p
e
rfo
rm
re
c
o
n
str
u
c
ti
o
n
u
sin
g
COLM
AP.
As
a
re
su
lt
,
a
3
D
m
o
d
e
l
fo
r
t
h
e
tem
p
le
with
a
c
lea
r
stru
c
tu
re
a
n
d
c
o
lo
r
wa
s
o
b
se
rv
e
d
.
A
sc
e
n
e
re
n
d
e
re
d
in
M
P
4
fo
rm
a
t
wa
s
a
lso
g
e
n
e
r
a
ted
u
sin
g
Ne
rfstu
d
io
.
Ad
d
it
i
o
n
a
ll
y
,
we
p
e
rfo
rm
e
d
t
h
e
3
D
re
c
o
n
str
u
c
ti
o
n
fr
o
m
1
5
0
ima
g
e
s
tak
e
n
b
y
th
e
p
u
b
li
c
a
n
d
f
o
u
n
d
t
h
e
m
in
su
fficie
n
t
fo
r
c
o
n
str
u
c
ti
n
g
th
e
o
b
jec
t.
Th
is
o
c
c
u
rre
d
d
e
sp
it
e
th
e
n
u
m
b
e
r
o
f
ima
g
e
s
b
e
i
n
g
larg
e
r
t
h
a
n
t
h
o
se
u
se
d
i
n
t
h
e
p
re
v
i
o
u
s
re
c
o
n
str
u
c
ti
o
n
.
T
h
e
re
su
lt
s
in
d
ica
te
th
a
t
t
h
e
su
c
c
e
ss
o
f
a
c
ro
wd
so
u
rc
i
n
g
p
r
o
j
e
c
t
fo
r
re
c
o
n
st
ru
c
ti
n
g
a
larg
e
-
sc
a
le o
b
jec
t
sh
o
u
l
d
c
o
n
si
d
e
r
n
o
t
o
n
ly
th
e
n
u
m
b
e
r
o
f
ima
g
e
s
b
u
t
a
lso
t
h
e
v
a
riati
o
n
i
n
p
o
i
n
t
o
f
v
ie
w
a
n
d
t
h
e
c
o
m
p
lete
n
e
ss
o
f
t
h
e
wh
o
le stru
c
tu
re
.
K
ey
w
o
r
d
s
:
3
D
d
o
cu
m
e
n
tatio
n
3
D
r
ec
o
n
s
tr
u
ctio
n
C
o
m
p
u
ter
v
is
io
n
C
r
o
wd
s
o
u
r
cin
g
C
u
ltu
r
al
h
er
itag
e
Dig
itizatio
n
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Hele
n
a
W
id
iar
ti
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Sy
s
t
em
s
E
n
g
in
ee
r
in
g
Facu
lty
o
f
Scien
ce
,
T
ec
h
n
o
lo
g
y
,
E
n
g
i
n
ee
r
in
g
,
an
d
Ma
th
em
at
ics,
Pra
s
etiy
a
Mu
ly
a
Un
iv
er
s
ity
J
ak
ar
ta,
I
n
d
o
n
esia
E
m
ail:
h
elen
a.
wid
iar
ti@
p
r
asetiy
am
u
ly
a.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
R
esear
ch
in
th
r
ee
-
d
im
e
n
s
io
n
a
l
(
3D
)
r
ec
o
n
s
tr
u
ctio
n
h
as
alwa
y
s
b
ee
n
a
f
ascin
atin
g
f
ield
i
n
co
m
p
u
te
r
v
is
io
n
[
1
]
.
T
h
e
ad
v
a
n
ce
m
en
t
o
f
d
ig
ital
tech
n
o
lo
g
y
h
as
in
cr
ea
s
ed
th
e
p
r
o
ce
s
s
in
g
ca
p
ab
ilit
y
o
f
d
ev
ices
wh
ile
s
im
u
ltan
eo
u
s
ly
lo
wer
in
g
co
s
t
.
On
e
o
f
th
e
ap
p
licatio
n
s
f
o
r
th
is
tech
n
o
lo
g
y
is
th
e
p
r
eser
v
atio
n
o
f
c
u
ltu
r
al
h
er
itag
e.
Ma
n
y
s
tu
d
ies
h
av
e
f
o
cu
s
ed
o
n
th
e
r
ec
o
n
s
tr
u
c
tio
n
o
f
3
D
m
o
d
els
f
o
r
c
u
ltu
r
al
h
er
itag
e.
R
ec
en
t
wo
r
k
in
B
er
to
cc
i
et
a
l
.
[
2
]
d
em
o
n
s
tr
ate
d
3
D
d
i
g
itizatio
n
o
f
L
a
Ver
n
a
t
h
at
co
m
b
in
es
laser
s
ca
n
n
in
g
a
n
d
p
h
o
to
g
r
a
m
m
etr
y
.
L
iu
an
d
Ma
m
at
[
3
]
,
3
D
laser
s
ca
n
n
in
g
was
u
s
ed
to
ac
q
u
ir
e
p
o
in
t
clo
u
d
m
o
d
els
o
f
th
e
g
r
ea
t
ac
h
iev
em
en
t
p
alac
e
o
f
th
e
C
o
n
f
u
cian
tem
p
l
e.
C
o
s
tan
tin
o
et
a
l.
[
4
]
u
tili
ze
d
s
can
-
to
-
h
er
itag
e
b
u
ild
in
g
in
f
o
r
m
atio
n
m
o
d
elin
g
(
HB
I
M
)
f
o
r
th
e
c
o
n
s
er
v
atio
n
an
d
p
r
ese
r
v
atio
n
o
f
San
Nico
la
in
M
o
n
t
ed
o
r
o
c
h
u
r
c
h
,
I
taly
.
A
p
o
p
u
lar
ap
p
licatio
n
o
f
3
D
o
b
jects
is
au
g
m
en
ted
r
ea
lity
(
AR
)
.
I
n
AR
,
th
e
3
D
m
o
d
el
o
f
o
b
jects
ca
n
b
e
o
b
s
er
v
ed
d
i
g
itally
,
allo
win
g
to
u
r
is
ts
to
v
is
it
a
h
is
to
r
ical
s
ite
v
ir
tu
ally
.
Sp
allo
n
e
et
a
l
.
[
5
]
,
AR
an
d
v
ir
tu
al
r
ea
li
ty
(
VR
)
en
ab
le
v
is
ito
r
s
to
d
o
in
ter
ac
tiv
e
co
m
m
u
n
icatio
n
in
th
e
v
ir
t
u
al
m
u
s
eu
m
o
f
M
u
s
eo
D
’
ar
te
Or
ien
tale
Di
T
o
r
in
o
.
B
an
f
i
et
a
l
.
[
6
]
,
d
ata
v
is
u
aliza
tio
n
with
AR
is
p
r
esen
ted
at
th
e
Mu
s
eo
Naz
io
n
ale
R
o
m
an
o
,
I
taly
.
R
ec
en
tly
,
th
e
d
ig
ital
t
win
h
as
b
ec
o
m
e
a
n
attr
ac
tiv
e
r
esear
ch
to
p
ic
d
u
e
to
its
p
o
ten
tial
ap
p
li
ca
tio
n
s
in
I
n
d
u
s
tr
y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
TEL
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
24
,
No
.
1
,
Feb
r
u
ar
y
20
26
:
2
4
9
-
257
250
4
.
0
.
I
t
in
tr
o
d
u
ce
s
th
e
co
n
ce
p
t o
f
v
ir
tu
aliza
tio
n
o
f
an
o
b
ject,
wh
ich
is
n
o
t
lim
ited
to
o
n
ly
s
h
o
win
g
th
e
s
tr
u
ctu
r
e
o
r
co
l
o
r
i
n
3
D
f
o
r
m
.
I
n
d
ig
ital
t
win
,
th
e
b
eh
av
io
u
r
o
f
th
e
o
b
j
ec
t
ca
n
b
e
s
im
u
lated
as
well
[
7
]
.
T
h
e
a
p
p
licatio
n
s
o
f
d
ig
ital
t
win
r
an
g
e
f
r
o
m
m
an
u
f
ac
tu
r
in
g
to
u
r
b
an
lan
d
s
ca
p
in
g
.
W
e
ca
n
co
n
clu
d
e
th
at
th
e
3
D
m
o
d
el
o
f
a
n
o
b
ject
h
as m
an
y
p
o
ten
tial a
p
p
licatio
n
s
in
th
e
f
u
tu
r
e
.
T
h
e
co
m
m
o
n
m
eth
o
d
s
f
o
r
co
n
s
tr
u
ctin
g
a
3
D
m
o
d
el
o
f
an
o
b
ject
ar
e
p
h
o
t
o
g
r
am
m
et
r
y
,
tr
ian
g
u
latio
n
an
d
tim
e
-
of
-
f
lig
h
t
laser
s
ca
n
n
in
g
,
s
tr
u
ctu
r
ed
lig
h
t,
s
ter
eo
-
ca
lib
r
ated
o
p
tical
s
en
s
o
r
s
,
an
d
m
o
b
ile
lid
ar
[
8
]
.
I
n
p
h
o
to
g
r
am
m
etr
y
,
th
e
3
D
m
o
d
els
f
o
r
r
ea
l
o
b
jects
ar
e
cr
ea
ted
f
r
o
m
m
u
ltip
le
im
ag
es.
T
h
e
o
b
jects
in
ph
o
to
g
r
am
m
etr
y
ar
e
n
o
t
lim
i
ted
to
s
m
all
o
b
jects,
b
u
t
lar
g
e
o
b
jects,
as
well
as
a
r
ec
o
n
s
tr
u
ctio
n
o
f
a
s
ite.
E
x
am
p
les
o
f
u
s
in
g
p
h
o
to
g
r
am
m
etr
y
in
s
m
all
o
b
jects,
s
u
ch
as
a
s
tatu
e
o
r
f
ig
u
r
i
n
e,
ar
e
p
r
esen
ted
in
B
o
n
o
r
a
et
a
l
.
[
9
]
.
Me
an
wh
ile,
f
o
r
t
h
e
r
ec
o
n
s
tr
u
ctio
n
o
f
th
e
s
ite,
Sam
b
u
g
ar
o
et
a
l.
[
1
0
]
u
s
e
p
h
o
to
g
r
am
m
etr
y
to
r
e
p
r
esen
t
in
d
u
s
tr
ial
o
b
jects.
Pra
s
id
y
a
et
a
l
.
[
1
1
]
th
e
m
u
lti
-
m
o
d
e
s
en
s
o
r
p
lace
m
en
t,
co
m
b
in
in
g
lig
h
t
d
e
tectio
n
an
d
r
an
g
i
n
g
(
L
I
DAR
)
an
d
p
h
o
to
g
r
am
m
etr
y
,
was u
s
ed
to
ca
p
tu
r
e
th
e
Pra
m
b
an
an
T
em
p
le
’
s
d
etailed
s
tr
u
ctu
r
e.
Als
ad
ik
[
1
2
]
,
cr
o
wd
s
o
u
r
ce
d
an
d
web
-
b
ased
d
r
o
n
e
v
id
eo
s
we
r
e
u
s
ed
as
a
r
eso
u
r
ce
f
o
r
3
D
r
ec
o
n
s
tr
u
ctio
n
o
f
cu
ltu
r
al
h
er
itag
e
s
ites
.
On
e
o
f
t
h
e
p
o
p
u
lar
p
latf
o
r
m
s
f
o
r
p
h
o
to
g
r
am
m
etr
y
is
C
OL
MA
P.
I
t
was
in
tr
o
d
u
ce
d
f
ir
s
t
in
2
0
1
4
b
y
Sch
ö
n
b
er
g
er
an
d
Fra
h
m
[
1
3
]
.
I
t
u
tili
ze
d
s
tr
u
ctu
r
e
-
f
r
o
m
-
m
o
ti
o
n
(
SfM
)
,
wh
ich
esti
m
ates
3
D
s
tr
u
ctu
r
e
f
r
o
m
2
D
im
ag
es
f
r
o
m
m
u
ltip
le
p
o
i
n
ts
o
f
v
iew.
C
OL
MA
P
is
av
ailab
le
f
r
ee
ly
u
n
d
er
an
o
p
en
-
s
o
u
r
ce
l
icen
s
e.
B
ec
au
s
e
o
f
th
is
,
C
OL
MA
P
h
as
b
ee
n
u
s
ed
in
m
an
y
r
esear
ch
p
r
o
jects
[
1
4
]
,
[
1
5
]
.
R
ec
en
tly
,
n
eu
r
al
r
ad
ia
n
ce
f
ield
s
(
Ner
F
)
,
a
m
eth
o
d
th
at
u
tili
ze
s
ar
tific
ial
in
tellig
en
ce
(
AI
)
to
p
er
f
o
r
m
3
D
r
ec
o
n
s
tr
u
ctio
n
,
h
as
g
ain
e
d
p
o
p
u
lar
ity
as
well.
W
h
ile
C
OL
MA
P
em
p
lo
y
s
a
c
lass
ic
ap
p
r
o
ac
h
in
m
a
k
in
g
3
D
o
b
jects,
Ner
F
u
tili
ze
s
a
d
ee
p
lear
n
in
g
m
et
h
o
d
t
o
g
en
er
ate
a
s
ce
n
e
b
ased
o
n
two
-
d
im
en
s
io
n
al
(
2D
)
im
ag
es.
T
o
g
eth
er
,
C
OL
MA
P
an
d
Ner
f
ca
n
b
e
u
s
ed
to
cr
ea
te
a
p
o
in
t
clo
u
d
f
ile,
a
m
esh
f
ile,
an
d
a
s
ce
n
e
in
MP4
f
o
r
m
at.
N
er
F
u
s
es
th
e
ca
m
er
a
p
o
s
es
g
en
er
ated
b
y
C
OL
MA
P
to
cr
ea
te
a
s
ce
n
e
[
1
6
]
.
C
OL
MA
P c
an
esti
m
ate
ca
m
er
a
p
ar
a
m
eter
s
an
d
th
e
s
p
ar
s
e
p
o
in
t
cl
o
u
d
s
.
Ner
F
u
s
es th
em
f
o
r
cr
ea
tin
g
3
D
m
o
d
els.
T
h
u
s
,
with
b
o
th
to
o
ls
,
th
e
d
ig
itiza
tio
n
o
f
c
u
ltu
r
al
h
er
itag
e
ca
n
b
e
g
en
er
ate
d
in
3
D
v
is
u
aliza
tio
n
an
d
v
i
d
eo
.
I
n
th
is
wo
r
k
,
we
p
r
esen
t
a
wo
r
k
f
lo
w
to
u
s
e
C
OL
MA
P
an
d
N
er
f
s
tu
d
io
f
o
r
p
h
o
t
o
g
r
am
m
et
r
y
.
W
e
u
s
ed
a
L
in
u
x
-
b
ased
s
er
v
er
with
an
NVI
DI
A
g
r
ap
h
ics
p
r
o
ce
s
s
in
g
u
n
it
(
GPU
)
with
co
m
p
u
te
u
n
if
ied
d
ev
ice
ar
ch
itectu
r
e
(
C
UDA
)
s
u
p
p
o
r
t.
T
h
e
o
b
ject
o
f
in
te
r
est is
o
n
e
o
f
th
e
tem
p
les lo
ca
ted
in
s
id
e
th
e
C
an
d
i Pr
am
b
an
an
ar
ea
,
n
am
e
d
C
an
d
i Siwa
(
Sh
iv
a
T
em
p
le)
.
W
e
to
o
k
ar
o
u
n
d
1
5
0
im
ag
es a
n
d
p
er
f
o
r
m
e
d
3
D
r
e
co
n
s
tr
u
ctio
n
u
s
in
g
C
OL
MA
P.
L
ater
o
n
,
we
c
r
ea
ted
a
s
ce
n
e
b
ased
o
n
t
h
e
im
a
g
es
with
N
er
F.
W
e
also
p
er
f
o
r
m
ed
cr
o
wd
s
o
u
r
ci
n
g
,
wh
er
e
we
in
q
u
ir
ed
n
u
m
b
e
r
o
f
p
eo
p
le
v
is
itin
g
th
e
tem
p
le
to
t
ak
e
m
u
ltip
le
p
ictu
r
es.
B
ased
o
n
th
o
s
e
im
ag
es,
we
cr
ea
ted
a
3
D
m
o
d
el.
T
h
e
r
esu
lt
s
h
o
ws
th
at
th
e
3
D
m
o
d
el
g
e
n
er
ated
f
r
o
m
cr
o
wd
s
o
u
r
ci
n
g
f
ails
to
r
ep
r
esen
t
th
e
s
tr
u
ctu
r
e
o
f
t
h
e
o
b
ject.
W
e
p
r
o
p
o
s
e
a
p
r
ac
tical
ap
p
r
o
ac
h
f
o
r
u
tili
zin
g
C
OL
MA
P
an
d
Ner
F
to
r
ec
o
n
s
tr
u
ct
a
3
D
lar
g
e
-
s
ca
le
o
b
ject
with
s
u
f
f
icien
t
im
ag
es.
Ou
r
wo
r
k
f
lo
w
ca
n
b
e
r
ep
licate
d
to
g
et
th
e
3
D
m
o
d
el
o
f
an
o
b
ject
s
in
ce
b
o
th
th
e
f
r
am
ewo
r
k
(
C
OL
MA
P,
Ner
F)
an
d
h
ar
d
war
e
(
co
m
p
u
ter
,
s
m
a
r
tp
h
o
n
e)
a
r
e
ea
s
ily
ac
ce
s
s
ib
le.
T
h
e
d
ata
co
llectio
n
was
d
o
n
e
with
s
m
ar
t
p
h
o
n
es,
a
d
ev
ice
th
at
is
u
b
iq
u
ito
u
s
to
d
a
y
,
th
er
e
f
o
r
e
allo
ws
ev
er
y
o
n
e
t
o
co
n
tr
i
b
u
te
to
th
e
p
r
o
ject.
Fu
r
th
e
r
m
o
r
e
,
th
e
f
r
am
ewo
r
k
u
s
ed
in
th
is
wo
r
k
is
f
r
e
ely
av
ailab
le.
C
OL
MA
P i
s
an
im
p
lem
en
tati
o
n
o
f
th
e
SfM
tech
n
iq
u
e,
wh
e
r
e
th
e
g
e
o
m
etr
ical
f
ea
tu
r
e
o
f
a
s
tr
u
ctu
r
e
is
esti
m
ated
f
r
o
m
m
u
ltip
le
im
ag
es
f
r
o
m
d
if
f
er
en
t
p
o
i
n
ts
o
f
v
ie
w
[
1
3
]
.
C
OL
MA
P
is
an
o
p
en
-
s
o
u
r
ce
p
latf
o
r
m
f
o
r
cr
ea
tin
g
a
3
D
s
tr
u
ctu
r
e
an
d
ca
m
er
a
m
o
tio
n
s
f
r
o
m
m
u
ltip
le
i
m
ag
es.
C
OL
MA
P
ca
n
r
u
n
o
n
a
co
m
p
u
ter
with
a
ce
n
tr
al
p
r
o
ce
s
s
in
g
u
n
it
(
C
PU
)
,
b
u
t it
will p
r
o
d
u
ce
a
b
etter
r
esu
lt o
n
a
c
o
m
p
u
ter
with
a
GPU.
T
h
e
r
ec
o
n
s
tr
u
ctio
n
p
r
o
ce
s
s
f
o
l
lo
ws
th
e
s
tep
s
as
s
h
o
wn
in
Fig
u
r
e
1
[
1
3
]
.
First,
f
ea
tu
r
e
e
x
tr
ac
tio
n
an
d
m
atch
in
g
a
r
e
p
er
f
o
r
m
ed
.
T
h
e
r
esu
lts
ar
e
f
ea
tu
r
e
d
escr
ip
to
r
s
th
at
ar
e
s
to
r
e
d
as
a
n
ar
r
ay
to
d
escr
ib
e
a
lo
ca
l
f
ea
t
u
r
e
o
f
an
im
ag
e
.
Du
r
in
g
m
atch
in
g
p
r
o
ce
s
s
,
C
OL
MA
P
d
is
co
v
er
s
im
ag
es
an
d
p
er
f
o
r
m
s
a
n
aiv
e
s
ea
r
ch
f
o
r
a
p
air
o
f
im
ag
es.
I
t
id
en
tifie
s
a
p
o
ten
tia
l
m
atch
b
y
c
o
m
p
a
r
in
g
t
h
em
to
ea
ch
o
th
e
r
b
y
ca
lcu
latin
g
t
h
e
m
in
im
u
m
d
is
tan
ce
.
Nex
t,
im
ag
e
r
eg
is
tr
atio
n
m
atc
h
es
th
e
m
u
ltip
le
im
ag
es
in
to
a
3
D
m
o
d
el.
T
h
e
m
et
h
o
d
d
etec
ts
an
d
m
atch
es
k
ey
f
ea
tu
r
es
s
u
ch
as
co
r
n
er
s
an
d
ed
g
es
b
etwe
en
im
a
g
es.
I
f
a
v
alid
tr
an
s
f
o
r
m
atio
n
m
ap
s
a
s
u
f
f
icien
t
n
u
m
b
er
o
f
f
ea
tu
r
es
b
etwe
en
im
ag
es,
th
ey
ar
e
co
n
s
id
er
ed
g
e
o
m
etr
ically
v
er
if
ied
.
T
h
e
tr
an
s
f
o
r
m
ati
o
n
p
ar
am
eter
s
ar
e
co
m
p
u
ted
b
ased
o
n
th
ese
f
ea
tu
r
es.
T
h
e
r
esu
lt
o
f
th
e
r
ec
o
n
s
tr
u
ctio
n
is
a
m
esh
f
ile
th
at
is
f
o
r
m
ed
b
y
p
o
in
t
clo
u
d
s
ca
lcu
lated
in
t
h
e
p
r
ev
io
u
s
s
tep
.
T
h
e
r
ec
o
n
s
tr
u
ctio
n
is
d
o
n
e
in
c
r
em
en
tally
t
h
r
o
u
g
h
i
m
ag
e
r
e
g
is
tr
atio
n
,
tr
ian
g
u
latio
n
,
a
n
d
b
u
n
d
le
ad
ju
s
tm
en
t.
Ner
F
u
s
ed
d
ee
p
lear
n
in
g
to
cr
ea
te
a
s
ce
n
e
b
ased
o
n
m
u
ltip
le
im
ag
es.
Ner
F
r
ep
r
esen
ts
a
s
ce
n
e
with
f
iv
e
-
d
im
en
s
io
n
al
(
5D
)
f
u
n
ctio
n
(
,
,
)
,
wh
ich
ar
e
s
p
atial
co
o
r
d
i
n
ates
an
d
p
o
lar
an
g
les
(
an
d
)
.
T
h
e
o
u
tp
u
ts
ar
e
v
o
lu
m
e
d
e
n
s
ity
an
d
r
ed
,
g
r
ee
n
,
b
lu
e
(
R
GB
)
co
lo
r
v
alu
es,
s
y
m
b
o
lized
b
y
an
d
[
1
7
]
.
T
h
e
lear
n
in
g
in
Ner
F
is
b
ased
o
n
th
e
f
u
n
ctio
n
th
at
esti
m
ates th
e
p
ar
am
eter
s
as sh
o
wn
in
(
1
)
.
:
(
,
)
→
(
,
)
(
1
)
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
A
p
r
a
ctica
l a
p
p
r
o
a
ch
t
o
C
a
n
d
i S
iw
a
3
D
r
ec
o
n
s
tr
u
ctio
n
w
ith
C
OL
MAP
a
n
d
N
erfs
tu
d
io
(
Hele
n
a
Wid
ia
r
ti
)
251
T
wo
s
ig
n
if
ican
t
s
cien
tific
wo
r
k
s
in
th
e
d
ev
elo
p
m
en
t
o
f
N
eRF
ar
e
[
1
7
]
wh
ich
im
p
r
o
v
e
s
tr
ain
in
g
ef
f
icien
cy
u
s
in
g
d
ep
t
h
in
f
o
r
m
a
tio
n
o
b
tain
ed
f
r
o
m
C
OL
MA
P,
an
d
[
1
8
]
wh
ich
in
tr
o
d
u
ce
d
th
e
f
o
u
n
d
atio
n
al
NeRF
m
eth
o
d
f
o
r
r
ea
lis
tic
s
ce
n
e
r
ec
o
n
s
tr
u
ctio
n
an
d
n
o
v
el
v
iew
s
y
n
t
h
esis
.
F
i
g
u
r
e
1
.
C
O
L
M
AP
p
i
p
e
li
n
e
2.
M
E
T
H
O
D
W
e
p
er
f
o
r
m
ed
d
ata
co
llectio
n
an
d
r
ec
o
n
s
tr
u
ctio
n
f
o
r
a
lar
g
e
-
s
ca
le
o
b
ject.
T
h
e
o
b
ject
o
f
r
esear
ch
is
C
an
d
i
Siwa,
a
tem
p
le
lo
ca
ted
in
th
e
ce
n
ter
o
f
th
e
Pra
m
b
an
an
Sit
e.
T
h
er
e
a
r
e
two
r
ea
s
o
n
s
f
o
r
th
is
s
elec
tio
n
.
First,
C
an
d
i Siwa
is
th
e
lar
g
est
tem
p
le
in
s
id
e
t
h
e
Pra
m
b
an
a
n
Sit
e.
Seco
n
d
,
th
e
s
u
r
r
o
u
n
d
in
g
p
er
im
eter
o
f
C
an
d
i
Siwa
is
an
ar
ea
with
n
o
o
b
s
tacle
s
o
r
o
th
er
o
b
jects.
Peo
p
le
ca
n
ca
p
tu
r
e
im
ag
es
th
at
in
clu
d
e
th
e
wh
o
le
s
tr
u
ctu
r
e
o
f
th
e
tem
p
le
with
ea
s
e.
Pra
m
b
an
an
is
a
p
o
p
u
lar
to
u
r
is
t
at
tr
ac
tio
n
in
th
e
r
eg
io
n
.
I
n
t
h
e
Pra
m
b
an
an
ar
ea
,
th
e
tem
p
les
ar
e
d
is
tr
ib
u
ted
ac
r
o
s
s
th
e
ar
ea
in
v
ar
io
u
s
s
izes.
I
t
is
lo
ca
ted
in
C
en
tr
al
J
av
a
an
d
Yo
g
y
a
k
a
r
ta
Pro
v
in
ce
[
1
9
]
.
W
e
co
n
d
u
cte
d
o
u
r
d
ata
c
o
llectio
n
f
o
r
a
d
ay
in
Dec
em
b
er
2
0
2
4
.
Data
co
llectio
n
was
d
o
n
e
i
n
t
wo
p
ar
ts
.
T
h
e
f
ir
s
t p
ar
t
was
d
o
n
e
b
y
a
r
esear
ch
team
,
an
d
th
e
p
u
b
lic
d
id
th
e
s
ec
o
n
d
s
tep
.
Fo
r
th
e
f
ir
s
t
p
ar
t,
th
e
p
eo
p
le
in
ch
a
r
g
e
o
f
tak
in
g
th
e
p
ictu
r
es
cir
cled
ar
o
u
n
d
th
e
tem
p
le
an
d
to
o
k
th
e
im
ag
es
with
th
e
p
u
r
p
o
s
e
o
f
h
av
in
g
im
ag
es
with
m
an
y
o
v
e
r
lap
p
in
g
ar
ea
s
.
T
h
e
im
ag
es
s
h
all
co
v
er
th
e
wh
o
le
s
tr
u
ctu
r
e
o
f
th
e
tem
p
le.
Fo
r
th
e
s
ec
o
n
d
p
ar
t,
we
ask
ed
1
0
v
o
lu
n
teer
s
to
tak
e
ar
o
u
n
d
5
0
im
ag
es.
I
n
th
is
cr
o
wd
s
o
u
r
cin
g
p
r
o
ject,
th
e
v
o
lu
n
teer
s
wer
e
p
r
o
v
id
e
d
with
o
n
ly
g
en
er
al
g
u
id
a
n
ce
r
eg
ar
d
in
g
t
h
e
im
ag
e
co
llectio
n
p
r
o
ce
s
s
.
Sp
ec
if
ically
,
th
ey
wer
e
in
s
tr
u
cted
to
ca
p
tu
r
e
p
h
o
t
o
g
r
ap
h
s
wh
ile
m
o
v
i
n
g
a
r
o
u
n
d
th
e
tem
p
le
in
o
r
d
er
to
o
b
tain
co
v
er
ag
e
o
f
th
e
en
tire
s
tr
u
ctu
r
e.
Ho
we
v
er
,
d
etailed
m
eth
o
d
o
lo
g
ical
in
s
tr
u
ctio
n
s
s
u
c
h
as
p
r
escr
ib
in
g
th
e
in
ter
v
al
o
f
m
o
v
em
en
t
b
etwe
en
s
u
cc
ess
iv
e
s
h
o
ts
(
e.
g
.
,
tak
in
g
a
s
h
o
r
t
s
tep
b
ef
o
r
e
ea
ch
ca
p
tu
r
e)
wer
e
n
o
t
co
n
v
ey
e
d
.
C
o
n
s
eq
u
en
tly
,
th
e
g
u
id
an
ce
em
p
h
asized
o
v
er
a
ll
s
p
atial
co
v
er
ag
e
r
ath
er
th
an
ad
h
er
en
ce
to
a
s
tan
d
ar
d
ized
o
r
s
y
s
tem
atic
ac
q
u
is
itio
n
p
r
o
to
c
o
l.
Fo
r
3
D
r
ec
o
n
s
tr
u
ctio
n
,
we
s
elec
ted
C
OL
MA
P
an
d
Ner
F
as
o
u
r
to
o
ls
.
Du
r
in
g
r
ec
o
n
s
tr
u
ctio
n
with
C
OL
MA
P,
th
e
p
ar
am
eter
s
ar
e
s
elec
ted
au
to
m
atica
lly
.
T
h
e
m
eth
o
d
s
u
s
ed
in
au
to
m
atic
r
ec
o
n
s
tr
u
cto
r
f
o
r
f
ea
tu
r
e
ex
tr
ac
tio
n
,
f
ea
tu
r
e
m
atch
in
g
,
an
d
g
eo
m
etr
ic
v
er
if
icatio
n
s
tep
s
ar
e
s
ca
le
-
in
v
a
r
ian
t
f
ea
tu
r
e
tr
an
s
f
o
r
m
(
SIFT
)
,
ex
h
au
s
tiv
e
m
atc
h
er
,
an
d
r
a
n
d
o
m
s
am
p
le
c
o
n
s
en
s
u
s
(
R
ANSAC
)
with
ep
ip
o
lar
c
o
n
s
tr
ain
ts
.
T
h
e
r
esu
lt
g
en
er
ate
d
b
y
C
OL
MA
P th
at
h
as b
ee
n
o
b
s
er
v
ed
is
a
f
ile
with
a
p
ly
ex
ten
s
io
n
.
T
h
e
p
ly
f
ile
is
a
m
esh
r
ep
r
esen
tatio
n
o
f
th
e
o
b
ject
o
f
in
te
r
est.
Ner
f
s
tu
d
io
[
2
0
]
was
s
elec
ted
f
o
r
th
e
s
ce
n
e
cr
ea
tio
n
.
T
h
e
f
r
am
ewo
r
k
r
eq
u
ir
es
NVI
DI
A
with
C
UD
A
in
s
talled
o
n
th
e
s
er
v
er
.
Ner
f
s
tu
d
io
also
r
eq
u
ir
es
Py
T
o
r
ch
with
C
UDA
a
s
a
d
ep
en
d
en
cy
.
W
e
u
s
ed
Ner
f
s
tu
d
io
to
g
en
er
ate
a
s
ce
n
e
in
MP4
f
o
r
m
at,
with
th
e
s
o
u
r
ce
im
ag
es
s
im
ilar
to
t
h
o
s
e
u
s
ed
in
C
OL
MA
P.
Ner
f
s
tu
d
io
n
ee
d
s
C
OL
MA
P
to
o
b
tain
th
e
ex
ter
n
al
an
d
in
ter
n
al
p
ar
am
eter
s
o
f
th
e
ca
m
er
a
an
d
g
en
e
r
ate
p
o
in
t
clo
u
d
s
.
B
o
th
C
OL
MA
P
an
d
Ner
F
r
u
n
o
n
o
n
e
s
er
v
er
.
Fig
u
r
e
s
2
(
a)
an
d
(
b
)
s
h
o
w
th
e
o
v
er
all
wo
r
k
f
lo
w
o
f
o
u
r
r
esear
ch
,
an
d
th
e
d
ep
en
d
en
cy
an
d
r
esu
lt f
iles
o
f
C
OL
MA
P a
n
d
Ner
f
s
tu
d
io
.
(
a)
(
b
)
Fig
u
r
e
2
.
Flo
wch
ar
t
o
f
wo
r
k
i
n
(
a)
g
en
er
al
an
d
(
b
)
3
D
r
ec
o
n
s
tr
u
ctio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
TEL
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
24
,
No
.
1
,
Feb
r
u
ar
y
20
26
:
2
4
9
-
257
252
W
e
in
s
tal
led
th
e
C
OL
MA
P a
n
d
Ner
f
s
tu
d
io
o
n
a
s
er
v
er
eq
u
i
p
p
ed
with
an
NVI
DI
A
GPU
ca
r
d
.
Du
r
in
g
th
e
ex
p
er
im
en
t,
we
r
an
th
e
s
er
v
er
with
th
e
clien
t
h
o
s
t
co
n
n
e
cted
with
in
th
e
lo
ca
l
ar
ea
n
etwo
r
k
(
L
AN)
.
All
th
e
co
m
m
an
d
s
in
C
OL
MA
P
an
d
Ner
f
s
tu
d
io
wer
e
d
o
n
e
with
a
co
m
m
an
d
lin
e
in
ter
f
ac
e,
e
x
ce
p
t
f
o
r
th
e
MP4
g
en
er
atin
g
p
r
o
ce
s
s
,
wh
er
e
we
u
s
ed
g
r
ap
h
ical
u
s
er
in
ter
f
ac
e
(
GUI
)
f
o
r
Ner
f
s
tu
d
i
o
.
T
h
e
r
ec
o
n
s
tr
u
ctio
n
p
r
o
ce
s
s
in
r
ea
l tim
e
ca
n
b
e
m
o
n
ito
r
ed
t
h
r
o
u
g
h
Ner
f
s
tu
d
i
o
v
iewe
r
th
at
is
f
o
r
war
d
ed
t
o
th
e
d
ef
au
lt p
o
r
t 7
0
0
7
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
Fro
m
th
e
r
esear
ch
er
team
’
s
d
ataset,
9
6
im
ag
es
wer
e
s
elec
ted
am
o
n
g
1
5
0
im
ag
es
to
p
er
f
o
r
m
th
e
3
D
r
ec
o
n
s
tr
u
ctio
n
th
at
r
e
p
r
esen
ts
th
e
o
b
ject
with
g
o
o
d
q
u
ality
a
n
d
s
h
o
ws
th
e
s
tr
u
ctu
r
e
well.
On
ly
a
s
u
b
s
et
o
f
th
e
im
ag
es
was
s
elec
ted
,
s
in
ce
m
an
y
o
f
th
e
im
a
g
es
ex
h
ib
it
o
v
e
r
la
p
with
m
in
im
al
v
ar
iatio
n
.
T
h
e
s
ize
o
f
ea
ch
p
ictu
r
e
r
an
g
es
f
r
o
m
5
9
7
b
y
tes
to
1
MB.
T
h
e
s
am
p
les
o
f
im
ag
es
p
r
esen
ted
in
Fig
u
r
e
s
3
(
a)
an
d
(
b
)
ca
p
t
u
r
ed
f
r
o
m
d
if
f
er
e
n
t
p
o
in
ts
o
f
v
iew.
T
h
e
ca
m
e
r
a
u
s
ed
to
tak
e
th
e
im
ag
es is
Sam
s
u
n
g
SM
-
A5
2
8
B
s
m
ar
tp
h
o
n
e.
W
e
ask
ed
to
u
r
is
ts
wh
o
v
is
ited
th
e
s
ite
o
n
th
e
s
am
e
d
a
y
to
tak
e
im
ag
es
an
d
s
u
b
m
it
t
h
e
m
d
ir
ec
tly
.
Ov
er
all,
we
o
b
tain
ed
ar
o
u
n
d
2
4
0
im
ag
es
f
r
o
m
th
e
p
u
b
lic.
A
m
o
n
g
th
e
m
,
we
s
elec
ted
1
5
0
i
m
ag
es
to
p
er
f
o
r
m
3
D
r
ec
o
n
s
tr
u
ctio
n
,
ex
clu
d
in
g
im
a
g
es with
m
in
im
al
o
v
e
r
lap
.
T
h
e
s
am
p
les o
f
im
ag
es a
r
e
s
h
o
wn
in
Fig
u
r
e
s
4
(
a
)
an
d
(
b
)
b
o
th
s
h
o
w
d
if
f
er
en
t
p
o
in
ts
o
f
v
iew
with
in
co
m
p
lete
s
tr
u
ct
u
r
e.
(
a)
(
b
)
Fig
u
r
e
3
.
Sam
p
les o
f
im
ag
es t
ak
en
b
y
r
esear
ch
er
team
:
(
a)
l
ef
t v
iew
an
d
(
b
)
r
ig
h
t v
iew
(
a)
(
b
)
Fig
u
r
e
4
.
Sam
p
les o
f
im
ag
es t
ak
en
b
y
th
e
p
u
b
lic
with
in
co
m
p
lete
s
tr
u
ctu
r
e
:
(
a)
f
r
o
n
t
v
iew
an
d
(
b
)
lef
t
v
iew
T
h
e
3
D
r
ec
o
n
s
tr
u
ctio
n
o
f
C
an
d
i
Siwa
was
d
o
n
e
u
s
in
g
C
OL
MA
P
an
d
Ner
f
s
tu
d
io
.
W
e
r
u
n
b
o
t
h
f
r
am
ewo
r
k
s
o
n
a
s
er
v
er
eq
u
i
p
p
ed
with
an
NVI
DI
A
GPU
in
th
e
lo
ca
l
n
etwo
r
k
.
T
h
e
s
p
ec
if
icatio
n
o
f
th
e
s
er
v
er
is
s
h
o
wn
in
T
ab
le
1
.
T
h
e
p
r
o
p
o
s
ed
h
ar
d
war
e
c
o
n
f
ig
u
r
atio
n
,
co
m
p
r
is
in
g
an
NVI
DI
A
GeFo
r
ce
R
T
X
3
0
6
0
GPU,
an
AM
D
R
y
ze
n
7
5
7
0
0
X
8
-
co
r
e
p
r
o
ce
s
s
o
r
,
an
d
3
2
GB
o
f
R
AM
,
p
r
o
v
id
es
a
n
e
f
f
ec
tiv
e
b
alan
ce
b
etwe
en
co
m
p
u
tatio
n
al
p
er
f
o
r
m
an
ce
a
n
d
co
s
t.
T
h
is
s
etu
p
is
s
u
f
f
icien
t
to
p
er
f
o
r
m
th
e
r
e
q
u
ir
ed
3
D
r
ec
o
n
s
tr
u
ctio
n
task
s
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
A
p
r
a
ctica
l a
p
p
r
o
a
ch
t
o
C
a
n
d
i S
iw
a
3
D
r
ec
o
n
s
tr
u
ctio
n
w
ith
C
OL
MAP
a
n
d
N
erfs
tu
d
io
(
Hele
n
a
Wid
ia
r
ti
)
253
ef
f
icien
tly
wh
ile
r
em
ain
in
g
f
i
n
an
cially
ac
ce
s
s
ib
le
to
m
o
s
t
r
esear
ch
in
s
titu
tio
n
s
an
d
in
d
iv
id
u
al
p
r
ac
titi
o
n
er
s
.
C
o
m
p
ar
ed
to
h
i
g
h
-
en
d
s
er
v
er
s
o
r
d
ed
icate
d
GPU
clu
s
ter
s
,
th
e
co
n
f
ig
u
r
atio
n
r
e
p
r
esen
ts
a
p
r
ac
tical
an
d
co
s
t
-
ef
f
ec
tiv
e
s
o
lu
tio
n
f
o
r
s
m
all
-
to
m
ed
iu
m
-
s
ca
le
r
ec
o
n
s
tr
u
ctio
n
p
r
o
jects.
T
ab
le
1
.
R
ef
er
en
ce
s
er
v
er
s
p
e
cif
icatio
n
s
d
em
o
n
s
tr
atin
g
a
n
a
f
f
o
r
d
a
b
le
an
d
s
ca
lab
le
h
ar
d
wa
r
e
s
etu
p
H
a
r
d
w
a
r
e
c
o
mp
o
n
e
n
t
S
p
e
c
i
f
i
c
a
t
i
o
n
G
r
a
p
h
i
c
c
a
r
d
N
V
I
D
I
A
G
e
F
o
r
c
e
R
TX
3
0
6
0
C
P
U
m
o
d
e
l
A
M
D
R
y
z
e
n
7
5
7
0
0
X
8
-
c
o
r
e
p
r
o
c
e
ss
o
r
R
A
M
3
2
G
B
W
e
s
et
th
e
p
ar
am
eter
to
a
u
to
m
atic
to
r
u
n
C
OL
MA
P.
T
h
e
d
ef
a
u
lt
v
alu
e
o
f
p
ar
a
m
eter
s
in
au
to
m
atic_
r
ec
o
n
s
tr
u
cto
r
ar
e
o
p
tim
ized
to
r
ef
in
e
all
f
o
ca
l
len
g
th
,
p
r
in
ci
p
al
p
o
in
t,
an
d
d
is
to
r
t
io
n
p
ar
am
eter
s
.
T
h
e
m
an
u
ally
s
et
p
ar
am
eter
s
ar
e
u
s
ed
f
o
r
th
e
ca
s
e
wh
e
n
th
e
ca
m
er
a
ca
lib
r
atio
n
p
ar
am
eter
s
ar
e
k
n
o
wn
b
ef
o
r
e
h
an
d
.
Sin
ce
we
u
s
ed
an
ev
er
y
d
ay
s
m
ar
tp
h
o
n
e
to
tak
e
th
e
p
ictu
r
es,
t
h
e
au
to
m
atic
r
ec
o
n
s
tr
u
ctio
n
p
a
r
am
eter
s
ar
e
alr
ea
d
y
th
e
m
o
s
t su
itab
le
ch
o
ice,
s
in
ce
s
m
ar
tp
h
o
n
es h
a
v
e
u
n
k
n
o
wn
a
n
d
v
ar
ia
b
le
in
tr
in
s
ic
.
T
h
e
co
m
m
a
n
d
f
o
r
a
u
to
m
atic
r
ec
o
n
s
tr
u
ctio
n
is
:
co
lm
a
p
au
t
o
m
atic_
r
ec
o
n
s
tr
u
ct
o
r
--
wo
r
k
s
p
ac
e_
p
ath
$
DAT
ASET
_
PATH
--
im
ag
e_
p
ath
$
DAT
ASET
_
PATH
/im
ag
es,
wh
er
e
we
ch
a
n
g
ed
p
ar
am
eter
s
$
DAT
ASET
_
PATH
an
d
$
DAT
ASET
_
PATH
/im
ag
es
to
th
e
d
ir
ec
to
r
y
o
f
th
e
s
o
u
r
ce
im
ag
es
f
ile.
W
e
o
b
s
er
v
ed
th
e
ca
m
er
a
p
o
s
es
f
r
o
m
“
im
a
g
es.tx
t
”
an
d
t
h
e
in
tr
in
s
ics
f
r
o
m
“
ca
m
er
as.tx
t
”
.
T
h
ese
f
iles
ar
e
g
en
e
r
ated
f
r
o
m
“
ca
m
er
a.
b
in
”
an
d
“
im
ag
e.
b
in
”
in
C
OL
MA
P.
T
h
e
im
a
g
e.
tx
t
f
i
le
n
o
ted
th
at
th
e
n
u
m
b
er
o
f
im
ag
es
is
eq
u
al
to
9
6
,
wh
ile
th
e
m
ea
n
o
b
s
er
v
atio
n
s
p
er
im
a
g
e
is
4
4
0
7
.
4
3
7
.
Fro
m
“
c
am
er
as.tx
t
”
,
we
o
b
tain
th
at
th
e
m
o
d
el
u
s
ed
in
th
e
ca
m
er
a
is
SIM
PLE
_
R
ADI
AL
.
T
h
e
h
eig
h
t
o
f
th
e
im
ag
es
r
a
n
g
es
f
r
o
m
1
5
0
0
to
4
1
6
9
p
i
x
els.
T
h
e
wid
th
o
f
th
e
im
ag
es r
an
g
es f
r
o
m
3
0
0
0
t
o
3
1
2
0
p
i
x
els.
Fig
u
r
e
s
5
(
a)
an
d
(
b
)
illu
s
tr
ates
th
e
o
u
tp
u
t
f
r
o
m
“
f
u
s
ed
.
p
ly
”
f
ile
f
r
o
m
d
i
f
f
er
en
t
v
iewp
o
in
ts
.
Fro
m
th
e
r
esu
lt,
we
co
n
clu
d
e
th
at
th
e
3
D
m
esh
f
o
r
C
an
d
i Siwa
h
as su
cc
ee
d
ed
in
s
h
o
win
g
c
o
lo
r
a
n
d
th
e
o
v
er
all
s
tr
u
ctu
r
e
o
f
th
e
tem
p
le.
T
h
e
s
er
v
er
n
e
ed
ed
ar
o
u
n
d
2
-
3
h
o
u
r
s
to
g
en
er
ate
th
e
d
en
s
e
m
esh
.
T
h
e
tim
e
n
ee
d
ed
f
o
r
th
i
s
r
ec
o
n
s
tr
u
ctio
n
p
r
o
ject
is
r
el
ativ
ely
s
lo
w
an
d
m
a
y
n
o
t
b
e
s
u
itab
le
f
o
r
r
ea
l
wo
r
ld
s
ca
lab
ilit
y
.
Fu
r
th
er
im
p
r
o
v
em
e
n
ts
o
n
th
e
h
ar
d
wa
r
e
is
n
ee
d
ed
to
m
a
k
e
th
is
s
o
lu
tio
n
ap
p
licab
le
i
n
r
ea
l
wo
r
ld
f
o
r
r
ec
o
n
s
tr
u
ctio
n
p
r
o
jects,
esp
ec
ially
with
th
e
p
ar
ticip
atio
n
o
f
p
u
b
lic.
(
a)
(
b
)
Fig
u
r
e
5
.
SfM
3
D
m
o
d
el
o
f
th
e
o
b
ject
ca
p
tu
r
e
d
f
r
o
m
two
p
e
r
s
p
ec
tiv
es: (
a)
lef
t v
iew
an
d
(
b
)
r
ig
h
t
v
iew
W
e
u
s
ed
ar
o
u
n
d
1
5
0
im
a
g
es
to
g
en
e
r
ate
th
e
m
esh
f
ile.
T
h
e
r
esu
lt
is
s
h
o
wn
in
Fig
u
r
e
6
.
A
s
th
e
r
esu
lt
s
h
o
ws,
th
e
3
D
r
ec
o
n
s
tr
u
ctio
n
f
ailed
to
ca
p
tu
r
e
th
e
wh
o
le
s
tr
u
ctu
r
e
o
f
th
e
o
b
ject.
T
h
is
r
esu
lt
is
attr
ib
u
ted
to
th
e
lack
o
f
v
ar
iatio
n
in
p
o
in
t
o
f
v
iew,
wh
ich
r
ed
u
ce
d
g
eo
m
et
r
ic
in
f
o
r
m
atio
n
an
d
p
ar
alla
x
ess
en
tial
f
o
r
d
e
p
th
esti
m
atio
n
[
2
1
]
.
T
h
e
p
h
o
t
o
g
r
a
p
h
er
in
cr
o
wd
s
o
u
r
cin
g
g
r
o
u
p
s
tak
e
s
ev
er
al
im
ag
es
b
y
m
o
v
in
g
th
eir
h
an
d
p
o
s
itio
n
wh
ile
s
tan
d
in
g
at
th
e
s
am
e
p
o
in
t.
Fu
r
th
er
m
o
r
e,
s
o
m
e
o
f
th
e
i
m
ag
es
f
ailed
to
s
h
o
w
th
e
wh
o
le
s
tr
u
ctu
r
e
o
f
o
b
ject,
b
ec
au
s
e
th
e
p
h
o
t
o
g
r
ap
h
er
is
s
tan
d
in
g
to
o
cl
o
s
e
to
t
h
e
o
b
jec
t.
T
h
is
f
in
d
in
g
was
r
ep
o
r
ted
a
ls
o
in
[
2
2
]
,
[
2
3
]
in
wh
ich
m
o
s
t
o
f
im
ag
es
f
r
o
m
cr
o
wd
s
o
u
r
cin
g
wer
e
ta
k
en
clo
s
e
to
th
e
o
b
ject,
m
in
im
al
in
v
ar
ia
n
ce
to
illu
m
in
atio
n
an
d
o
n
l
y
ar
o
u
n
d
s
u
b
s
et
o
f
th
e
m
ca
n
b
e
u
s
ed
f
o
r
r
ec
o
n
s
tr
u
ctio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
TEL
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
24
,
No
.
1
,
Feb
r
u
ar
y
20
26
:
2
4
9
-
257
254
Fig
u
r
e
6
.
3
D
r
ec
o
n
s
tr
u
ctio
n
o
f
C
an
d
i Siwa
u
s
in
g
th
e
p
u
b
lic
-
ca
p
tu
r
ed
im
a
g
es
T
o
in
cr
ea
s
e
th
e
q
u
ality
o
f
r
ec
o
n
s
tr
u
ctio
n
,
f
ilter
in
g
was
a
p
p
lie
d
to
th
e
s
o
u
r
ce
im
a
g
es
f
o
r
r
ec
o
n
s
tr
u
ctin
g
th
e
o
b
ject
[
2
4
]
in
to
two
ca
teg
o
r
ies,
in
lier
an
d
o
u
tlier
.
T
h
e
cl
ass
if
icatio
n
was
d
o
n
e
with
p
ar
am
eter
,
d
ef
in
e
as
th
e
d
is
tan
ce
o
f
a
p
o
in
t
to
its
n
ea
r
est
n
eig
h
b
o
r
.
I
f
is
lar
g
er
th
an
g
lo
b
al
m
ea
n
an
d
s
tan
d
ar
d
d
ev
iatio
n
o
f
all
,
th
en
it is
co
n
s
id
er
ed
as a
n
o
u
tl
ier
.
Up
o
n
th
is
h
o
wev
er
,
r
esu
lts
ar
e
n
o
t m
u
ch
im
p
r
o
v
e
d
an
d
s
till
f
ail
to
s
h
o
w
th
e
wh
o
le
s
tr
u
ctu
r
e.
T
o
co
m
p
a
r
e
th
e
r
esu
lts
o
f
th
e
r
esear
ch
team
an
d
cr
o
wd
s
o
u
r
c
in
g
d
atasets
q
u
an
titativ
ely
,
th
e
Op
en
3
D
lib
r
ar
y
in
Py
t
h
o
n
was
u
s
ed
t
o
ca
lcu
late
p
o
in
t
d
en
s
ity
an
d
r
ep
r
o
jectio
n
er
r
o
r
.
T
h
e
r
esu
l
ts
,
s
u
m
m
ar
ized
in
T
ab
le
2
,
s
h
o
w
th
at
th
e
r
esear
ch
er
t
eam
’
s
d
ataset
ac
h
iev
es
s
lig
h
tly
h
ig
h
er
p
o
in
t
d
en
s
it
y
an
d
lo
wer
m
ea
n
r
ep
r
o
jectio
n
e
r
r
o
r
.
T
h
is
in
d
icate
s
m
o
r
e
ac
cu
r
ate
an
d
co
m
p
lete
r
ec
o
n
s
tr
u
ctio
n
s
wh
en
im
ag
e
s
ar
e
s
y
s
tem
atica
lly
co
llected
.
As
f
o
r
th
e
av
er
ag
e
o
v
er
lap
in
r
esear
ch
er
team
is
4
8
2
.
7
9
wh
ich
is
h
ig
h
er
th
an
cr
o
wd
s
o
u
r
cin
g
3
7
8
.
7
9
,
th
u
s
p
r
o
d
u
cin
g
b
etter
r
ec
o
n
s
tr
u
ctio
n
.
T
ab
le
2
.
C
o
m
p
a
r
is
o
n
o
f
3
D
r
e
co
n
s
tr
u
ctio
n
q
u
ality
m
etr
ics b
etwe
en
th
e
r
esear
ch
er
team
an
d
cr
o
wd
s
o
u
r
cin
g
d
atasets
P
a
r
a
me
t
e
r
s
R
e
se
a
r
c
h
e
r
t
e
a
m
C
r
o
w
d
so
u
r
c
i
n
g
P
o
i
n
t
d
e
n
s
i
t
y
3
3
8
2
7
8
8
3
0
3
7
7
6
5
M
e
a
n
r
e
p
r
o
j
e
c
t
i
o
n
e
r
r
o
r
1
.
3
2
9
4
1
2
1
.
5
0
6
7
4
A
v
e
r
a
g
e
o
v
e
r
l
a
p
(
sh
a
r
e
d
3
D
p
o
i
n
t
s
p
e
r
i
ma
g
e
p
a
i
r
)
4
8
2
.
9
7
3
7
8
.
7
9
Fig
u
r
e
s
7
(
a)
an
d
(
b
)
s
h
o
ws
s
id
e
b
y
s
id
e
co
m
p
a
r
is
o
n
o
f
b
o
th
r
esear
ch
team
an
d
cr
o
w
d
s
o
u
r
ci
n
g
r
esu
lts
.
T
h
e
cr
o
wd
s
o
u
r
cin
g
r
esu
lt
f
ail
ed
to
s
h
o
w
th
e
s
tr
u
ctu
r
e
an
d
t
ex
tu
r
e
o
f
th
e
tem
p
le
f
o
r
all
th
r
ee
p
o
in
ts
.
T
h
u
s
,
o
u
r
wo
r
k
d
em
o
n
s
tr
ates
th
e
d
if
f
er
e
n
ce
in
th
e
q
u
ality
o
f
r
ec
o
n
s
tr
u
ctio
n
o
b
jects
b
etwe
en
ex
p
er
t
(
r
esear
ch
er
team
)
an
d
p
u
b
lic
im
ag
es
th
r
o
u
g
h
cr
o
wd
s
o
u
r
cin
g
.
Similar
f
in
d
in
g
s
wer
e
o
b
s
er
v
ed
in
[
2
5
]
,
in
wh
ich
th
e
d
ata
th
at
h
ad
b
ee
n
co
n
tr
ib
u
ted
with
o
u
t
clea
r
g
u
i
d
an
ce
o
f
ten
s
u
f
f
er
s
f
r
o
m
r
e
d
u
ce
d
q
u
ality
an
d
c
o
m
p
leten
ess
,
wh
ich
alig
n
s
with
ch
allen
g
es
in
im
ag
e
-
b
ased
r
ec
o
n
s
tr
u
ctio
n
wh
e
n
co
n
t
r
ib
u
to
r
s
d
o
n
o
t
v
ar
y
th
eir
ca
p
t
u
r
e
v
ie
wp
o
in
ts
s
u
f
f
icien
tly
.
A
m
o
r
e
co
m
m
o
n
ap
p
r
o
ac
h
to
ac
h
iev
in
g
h
ig
h
er
p
u
b
lic
en
g
ag
em
en
t
an
d
o
b
tain
i
n
g
r
ec
o
n
s
tr
u
ctio
n
with
g
o
o
d
r
esu
lts
s
im
u
ltan
eo
u
s
ly
is
b
y
co
m
b
in
in
g
im
a
g
es f
r
o
m
b
o
th
team
s
,
as d
escr
ib
ed
in
[
2
6
]
.
(
a)
(
b
)
Fig
u
r
e
7
.
C
o
m
p
a
r
is
o
n
o
f
r
ec
o
n
s
tr
u
ctio
n
r
esu
lt f
o
r
(
a)
r
esear
ch
team
an
d
(
b
)
cr
o
wd
s
o
u
r
cin
g
with
an
n
o
tatio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
A
p
r
a
ctica
l a
p
p
r
o
a
ch
t
o
C
a
n
d
i S
iw
a
3
D
r
ec
o
n
s
tr
u
ctio
n
w
ith
C
OL
MAP
a
n
d
N
erfs
tu
d
io
(
Hele
n
a
Wid
ia
r
ti
)
255
Nex
t,
we
u
s
e
Ner
F
to
cr
ea
te
a
s
ce
n
e
b
ased
o
n
im
ag
es
tak
e
n
b
y
t
h
e
r
esear
ch
er
team
.
Fir
s
t,
we
p
u
t
ca
m
er
a.
b
in
an
d
im
ag
e.
b
i
n
f
ile
s
g
en
er
ated
b
y
C
OL
MA
P
in
th
e
wo
r
k
s
p
ac
e
f
o
l
d
er
.
T
h
en
we
r
u
n
th
e
c
o
m
m
an
d
:
ns
-
tr
ain
n
er
f
ac
to
c
o
lm
ap
--
d
ata
ca
n
d
is
iwa
--
ce
n
ter
-
m
eth
o
d
f
o
cu
s
.
T
h
is
s
tep
g
en
er
ates
“
co
n
f
ig
.
y
m
l
”
f
ile,
wh
ich
co
n
tain
s
p
ar
a
m
eter
s
f
o
r
tr
ain
i
n
g
.
W
e
f
o
u
n
d
th
at
th
e
u
tili
za
tio
n
o
f
GPU
is
ar
o
u
n
d
9
8
% f
o
r
th
is
p
r
o
ce
s
s
.
Desp
ite
th
is
,
th
e
tr
ain
in
g
p
r
o
ce
s
s
was
co
m
p
leted
s
u
cc
ess
f
u
lly
.
Fig
u
r
e
7
s
h
o
ws
th
e
ex
am
p
le
o
f
r
ea
l tim
e
v
iewin
g
o
f
3
D
re
co
n
s
tr
u
ctio
n
p
r
o
ce
s
s
in
Ner
f
Stu
d
io
.
Af
ter
th
e
tr
ain
in
g
p
r
o
ce
s
s
is
d
o
n
e,
we
u
s
e
th
e
r
en
d
er
m
en
u
f
r
o
m
Ner
f
s
tu
d
io
GUI
to
g
en
e
r
a
te
a
s
h
o
r
t
v
id
eo
.
I
n
o
r
d
er
to
d
o
th
is
,
we
s
elec
ted
o
n
e
o
f
th
e
tr
ain
in
g
ca
m
er
as
th
at
c
o
r
r
esp
o
n
d
en
t
to
th
e
s
tar
tin
g
v
iewp
o
in
t
o
f
th
e
s
ce
n
e.
T
h
e
r
esu
lt
is
p
r
esen
ted
in
Fig
u
r
e
8
.
T
h
e
s
c
en
e
r
ec
o
n
s
tr
u
ctio
n
ef
f
ec
tiv
ely
ca
p
tu
r
es
b
o
th
t
h
e
s
tr
u
ctu
r
al
d
etails an
d
th
e
c
o
lo
r
in
f
o
r
m
atio
n
o
f
th
e
s
u
r
r
o
u
n
d
in
g
en
v
ir
o
n
m
en
t.
Fig
u
r
e
8
.
3
D
r
ec
o
n
s
tr
u
ctio
n
r
e
al
tim
e
m
o
n
ito
r
in
g
with
Ner
f
s
t
u
d
io
GUI
4.
CO
NCLU
SI
O
N
I
n
th
is
wo
r
k
,
we
p
r
esen
t
a
p
r
a
ctica
l
ap
p
r
o
ac
h
to
u
tili
ze
C
OL
MA
P
an
d
Ner
f
s
tu
d
io
as
to
o
ls
to
p
er
f
o
r
m
3
D
r
ec
o
n
s
tr
u
ctio
n
.
T
h
e
o
b
ject
o
f
in
ter
est
is
C
an
d
i
Siwa,
a
te
m
p
le
lo
ca
ted
b
etwe
en
C
en
tr
al
J
av
a
Pro
v
in
ce
a
n
d
Yo
g
y
ak
ar
ta
Pro
v
in
ce
,
I
n
d
o
n
e
s
ia.
W
e
u
s
ed
L
in
u
x
-
b
as
ed
s
er
v
er
eq
u
ip
p
e
d
with
NVI
DI
A
GPU
ca
r
d
.
T
wo
r
ec
o
n
s
tr
u
ctio
n
r
esu
lts
ar
e
p
r
o
d
u
ce
d
.
T
h
e
f
ir
s
t r
esu
lt,
u
s
in
g
im
ag
es tak
en
b
y
th
e
team
(
9
6
im
ag
es),
s
u
cc
ess
f
u
lly
p
er
f
o
r
m
ed
3
D
r
ec
o
n
s
tr
u
ctio
n
with
clea
r
s
tr
u
ctu
r
e
a
n
d
co
lo
r
with
C
OL
MA
P.
T
h
e
s
ce
n
e
r
ec
o
n
s
tr
u
ctio
n
in
th
e
f
o
r
m
o
f
an
MP4
f
ile
h
as
b
ee
n
c
r
ea
ted
s
u
cc
ess
f
u
lly
as
well
wit
h
Ner
f
s
tu
d
io
.
Ho
wev
e
r
,
th
e
s
e
co
n
d
r
ec
o
n
s
tr
u
ctio
n
r
esu
lt,
u
s
in
g
im
a
g
es
tak
en
b
y
t
h
e
p
u
b
lic,
was
s
h
o
wn
t
o
b
e
in
s
u
f
f
icien
t
in
co
n
s
tr
u
ctin
g
th
e
o
b
ject,
with
an
u
n
clea
r
s
tr
u
ctu
r
e
an
d
co
lo
r
,
d
esp
i
te
th
e
lar
g
er
n
u
m
b
er
o
f
im
ag
es
(
1
5
0
im
ag
es).
T
h
is
r
esu
lt
is
attr
ib
u
ted
to
a
lack
o
f
v
ar
iatio
n
in
p
o
in
t
o
f
v
iew,
wh
er
e
p
h
o
to
g
r
a
p
h
er
s
tak
e
s
ev
e
r
al
im
ag
es
b
y
m
o
v
in
g
th
eir
h
an
d
p
o
s
itio
n
wh
ile
s
tan
d
in
g
at
t
h
e
s
am
e
p
o
in
t.
Ad
d
itio
n
ally
,
th
e
im
ag
es
d
o
n
o
t
c
ap
tu
r
e
th
e
wh
o
le
s
tr
u
ctu
r
e
o
f
t
h
e
o
b
ject.
T
h
e
r
ef
o
r
e
,
in
th
e
cr
o
wd
s
o
u
r
cin
g
ap
p
r
o
ac
h
,
it
is
es
s
en
tial
to
p
r
o
v
id
e
clea
r
g
u
id
an
ce
to
th
e
p
ar
ticip
an
ts
in
ca
p
tu
r
in
g
th
e
o
b
ject
to
en
s
u
r
e
th
e
co
v
er
a
g
e
o
f
th
e
wh
o
le
s
tr
u
ctu
r
e
f
r
o
m
v
a
r
io
u
s
p
o
in
ts
o
f
v
iew.
Su
ch
g
u
i
d
an
ce
ca
n
b
e
s
h
o
wn
as
a
p
ar
t
o
f
a
cr
o
w
d
s
o
u
r
cin
g
p
r
o
ject
th
r
o
u
g
h
v
i
d
eo
s
o
r
p
o
s
ter
s
.
Ou
r
r
ec
o
n
s
tr
u
ctio
n
task
to
o
k
ar
o
u
n
d
2
-
3
h
o
u
r
s
wh
ich
is
r
elativ
ely
s
lo
w
an
d
m
ay
lim
it
th
e
s
ca
lab
ilit
y
o
f
th
is
ap
p
r
o
ac
h
in
r
ea
l
-
w
o
r
ld
ap
p
licatio
n
s
.
Har
d
war
e
u
p
g
r
a
d
es
o
r
co
m
p
u
tatio
n
al
o
p
tim
izatio
n
s
ar
e
th
er
ef
o
r
e
n
ec
ess
ar
y
to
m
ak
e
th
is
r
ec
o
n
s
tr
u
ctio
n
s
o
lu
tio
n
p
r
ac
tical,
p
ar
ticu
lar
ly
wh
e
n
in
co
r
p
o
r
atin
g
lar
g
e
-
s
ca
le
p
u
b
lic
p
ar
ticip
ati
o
n
.
ACK
NO
WL
E
DG
M
E
N
T
S
Au
th
o
r
s
wo
u
ld
lik
e
to
t
h
an
k
Nau
m
i Sasm
ita,
a
s
tu
d
en
t in
C
o
m
p
u
ter
Sy
s
tem
E
n
g
in
ee
r
in
g
,
Un
iv
er
s
itas
Pra
s
etiy
a
Mu
ly
a
f
o
r
h
er
co
n
tr
i
b
u
tio
n
d
u
r
in
g
d
ata
c
o
llectio
n
.
T
h
is
wo
r
k
was
s
u
p
p
o
r
ted
b
y
t
h
e
Pra
s
etiy
a
Mu
ly
a
Un
iv
er
s
ity
th
r
o
u
g
h
2
0
2
4
I
n
ter
n
al
R
esear
ch
Gr
an
t
s
ch
em
e.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esear
ch
was f
u
n
d
e
d
b
y
I
n
ter
n
al
R
esear
ch
Gr
an
t sch
em
e
in
Pra
s
etiy
a
Mu
ly
a
Un
iv
er
s
it
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
TEL
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
24
,
No
.
1
,
Feb
r
u
ar
y
20
26
:
2
4
9
-
257
256
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT
)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Hele
n
a
W
id
iar
ti
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
R
o
k
h
m
at
Feb
r
ian
to
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Ag
u
n
g
Alf
ian
s
y
a
h
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
i
n
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
a
v
ailab
l
e
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
au
t
h
o
r
,
[
HW
]
,
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
L.
Zh
o
u
,
G
.
W
u
,
Y
.
Zu
o
,
X
.
C
h
e
n
,
a
n
d
H
.
H
u
,
“
A
c
o
m
p
r
e
h
e
n
s
i
v
e
r
e
v
i
e
w
o
f
v
i
si
o
n
-
b
a
s
e
d
3
D
r
e
c
o
n
s
t
r
u
c
t
i
o
n
me
t
h
o
d
s,”
S
e
n
s
o
rs
,
v
o
l
.
2
4
,
n
o
.
7
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
4
0
7
2
3
1
4
.
[
2
]
S
.
B
e
r
t
o
c
c
i
,
A
.
L
u
mi
n
i
,
a
n
d
A
.
C
o
t
t
i
n
i
,
“
V
i
r
t
u
a
l
t
o
u
r
a
n
d
3
D
d
i
g
i
t
i
s
a
t
i
o
n
a
s t
o
o
l
s
f
o
r
c
u
l
t
u
r
a
l
h
e
r
i
t
a
g
e
f
r
u
i
t
i
o
n
.
Th
e
r
o
b
b
i
a
n
e
a
t
t
h
e
san
c
t
u
a
r
y
o
f
La
V
e
r
n
a
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
2
1
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
u
l
t
u
r
e
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
:
f
ro
m
H
u
m
a
n
i
sm
t
o
D
i
g
i
t
a
l
H
u
m
a
n
i
t
i
e
s
,
O
c
t
.
2
0
2
4
,
p
p
.
1
–
12
,
d
o
i
:
1
0
.
1
1
4
5
/
3
7
1
9
2
3
6
.
3
7
1
9
2
7
5
.
[
3
]
S
.
Li
u
a
n
d
M
.
J
.
B
.
M
a
ma
t
,
“
A
p
p
l
i
c
a
t
i
o
n
o
f
3
D
l
a
ser s
c
a
n
n
i
n
g
t
e
c
h
n
o
l
o
g
y
f
o
r
map
p
i
n
g
a
n
d
a
c
c
u
r
a
c
y
a
ssessm
e
n
t
o
f
t
h
e
p
o
i
n
t
c
l
o
u
d
mo
d
e
l
f
o
r
t
h
e
G
r
e
a
t
A
c
h
i
e
v
e
me
n
t
P
a
l
a
c
e
h
e
r
i
t
a
g
e
b
u
i
l
d
i
n
g
,
”
H
e
ri
t
a
g
e
S
c
i
e
n
c
e
,
v
o
l
.
1
2
,
n
o
.
1
,
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
1
1
8
6
/
s4
0
4
9
4
-
024
-
0
1
2
5
2
-
y.
[
4
]
D
.
C
o
s
t
a
n
t
i
n
o
,
M
.
P
e
p
e
,
a
n
d
A
.
G
.
R
e
st
u
c
c
i
a
,
“
S
c
a
n
-
to
-
H
B
I
M
f
o
r
c
o
n
s
e
r
v
a
t
i
o
n
a
n
d
p
r
e
s
e
r
v
a
t
i
o
n
o
f
C
u
l
t
u
r
a
l
H
e
r
i
t
a
g
e
b
u
i
l
d
i
n
g
:
t
h
e
c
a
se
st
u
d
y
o
f
S
a
n
N
i
c
o
l
a
i
n
M
o
n
t
e
d
o
r
o
c
h
u
r
c
h
(
I
t
a
l
y
)
,
”
A
p
p
l
i
e
d
G
e
o
m
a
t
i
c
s
,
v
o
l
.
1
5
,
n
o
.
3
,
p
p
.
6
0
7
–
6
2
1
,
S
e
p
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
2
5
1
8
-
0
2
1
-
0
0
3
5
9
-
2.
[
5
]
R
.
S
p
a
l
l
o
n
e
,
F
.
L
a
m
b
e
r
t
i
,
M
.
G
u
g
l
i
e
l
mi
n
o
t
t
i
Tr
i
v
e
l
,
F
.
R
o
n
c
o
,
a
n
d
S
.
Ta
m
a
n
t
i
n
i
,
“
3
D
r
e
c
o
n
s
t
r
u
c
t
i
o
n
a
n
d
p
r
e
se
n
t
a
t
i
o
n
o
f
c
u
l
t
u
r
a
l
h
e
r
i
t
a
g
e
:
A
R
a
n
d
V
R
e
x
p
e
r
i
e
n
c
e
s
a
t
t
h
e
m
u
se
o
D
’
a
r
t
e
o
r
i
e
n
t
a
l
e
D
i
To
r
i
n
o
,
”
T
h
e
I
n
t
e
r
n
a
t
i
o
n
a
l
A
rc
h
i
v
e
s
o
f
t
h
e
Ph
o
t
o
g
r
a
m
m
e
t
ry
,
Re
m
o
t
e
S
e
n
s
i
n
g
a
n
d
S
p
a
t
i
a
l
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
X
LV
I
-
M
-
1
–
2
,
p
p
.
6
9
7
–
7
0
4
,
A
u
g
.
2
0
2
1
,
d
o
i
:
1
0
.
5
1
9
4
/
i
s
p
r
s
-
a
r
c
h
i
v
e
s
-
X
LV
I
-
M
-
1
-
2
0
2
1
-
6
9
7
-
2
0
2
1
.
[
6
]
F
.
B
a
n
f
i
,
M
.
P
o
n
t
i
sso
,
F
.
R
.
P
a
o
l
i
l
l
o
,
S
.
R
o
a
sci
o
,
C
.
S
p
a
l
l
i
n
o
,
a
n
d
C
.
S
t
a
n
g
a
,
“
I
n
t
e
r
a
c
t
i
v
e
a
n
d
i
mm
e
r
si
v
e
d
i
g
i
t
a
l
r
e
p
r
e
s
e
n
t
a
t
i
o
n
f
o
r
v
i
r
t
u
a
l
M
u
se
u
m:
V
R
a
n
d
A
R
f
o
r
s
e
man
t
i
c
e
n
r
i
c
h
m
e
n
t
o
f
m
u
se
o
N
a
z
i
o
n
a
l
e
R
o
ma
n
o
,
A
n
t
i
q
u
a
r
i
u
m
d
i
L
u
c
r
e
z
i
a
R
o
m
a
n
a
a
n
d
A
n
t
i
q
u
a
r
i
u
m
d
i
V
i
l
l
a
D
e
i
Q
u
i
n
t
i
l
i
,
”
I
S
PR
S
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
G
e
o
-
I
n
f
o
rm
a
t
i
o
n
,
v
o
l
.
1
2
,
n
o
.
2
,
Ja
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
i
j
g
i
1
2
0
2
0
0
2
8
.
[
7
]
S
.
B
o
s
c
h
e
r
t
a
n
d
R
.
R
o
se
n
,
“
D
i
g
i
t
a
l
t
w
i
n
—
t
h
e
si
m
u
l
a
t
i
o
n
a
s
p
e
c
t
,
”
i
n
Me
c
h
a
t
r
o
n
i
c
F
u
t
u
r
e
s
,
C
h
a
m:
S
p
r
i
n
g
e
r
I
n
t
e
r
n
a
t
i
o
n
a
l
P
u
b
l
i
s
h
i
n
g
,
2
0
1
6
,
p
p
.
5
9
–
74
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
3
1
9
-
3
2
1
5
6
-
1
_
5
.
[
8
]
R
.
G
.
B
o
b
o
c
,
E.
B
ă
u
t
u
,
F
.
G
î
r
b
a
c
i
a
,
N
.
P
o
p
o
v
i
c
i
,
a
n
d
D
.
-
M
.
P
o
p
o
v
i
c
i
,
“
A
u
g
men
t
e
d
r
e
a
l
i
t
y
i
n
c
u
l
t
u
r
a
l
h
e
r
i
t
a
g
e
:
A
n
o
v
e
r
v
i
e
w
o
f
t
h
e
l
a
st
d
e
c
a
d
e
o
f
a
p
p
l
i
c
a
t
i
o
n
s,”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
2
,
n
o
.
1
9
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
2
1
9
9
8
5
9
.
[
9
]
V
.
B
o
n
o
r
a
,
G
.
T
u
c
c
i
,
A
.
M
e
u
c
c
i
,
a
n
d
B
.
P
a
g
n
i
n
i
,
“
P
h
o
t
o
g
r
a
mm
e
t
r
y
a
n
d
3
D
P
r
i
n
t
i
n
g
f
o
r
M
a
r
b
l
e
S
t
a
t
u
e
s
R
e
p
l
i
c
a
s:
C
r
i
t
i
c
a
l
I
ssu
e
s
a
n
d
A
sses
sme
n
t
,
”
S
u
st
a
i
n
a
b
i
l
i
t
y
,
v
o
l
.
1
3
,
n
o
.
2
,
J
a
n
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
s
u
1
3
0
2
0
6
8
0
.
[
1
0
]
Z.
S
a
m
b
u
g
a
r
o
,
L.
O
r
l
a
n
d
i
,
a
n
d
N
.
C
o
n
c
i
,
“
3
D
r
e
c
o
n
st
r
u
c
t
i
o
n
met
h
o
d
s
i
n
i
n
d
u
st
r
i
a
l
s
e
t
t
i
n
g
s:
a
c
o
m
p
a
r
a
t
i
v
e
s
t
u
d
y
f
o
r
C
O
L
M
A
P
,
N
e
R
F
a
n
d
3
D
G
a
u
ssi
a
n
S
p
l
a
t
t
i
n
g
,
”
i
n
C
e
u
r W
o
r
k
sh
o
p
Pr
o
c
e
e
d
i
n
g
s
,
2
0
2
4
,
p
p
.
2
1
2
–
2
1
7
.
[
1
1
]
A
.
S
.
P
r
a
si
d
y
a
,
I
.
G
u
mi
l
a
r
,
I
.
M
e
i
l
a
n
o
,
I
.
I
k
a
p
u
t
r
a
,
R
.
M
u
r
y
a
m
t
o
,
a
n
d
E
.
N
.
A
r
r
o
f
i
q
o
h
,
“
T
h
r
e
e
-
d
i
m
e
n
si
o
n
a
l
d
i
g
i
t
a
l
d
o
c
u
m
e
n
t
a
t
i
o
n
f
o
r
t
h
e
c
o
n
ser
v
a
t
i
o
n
o
f
t
h
e
P
r
a
mb
a
n
a
n
t
e
m
p
l
e
c
l
u
st
e
r
u
s
i
n
g
g
u
i
d
e
d
m
u
l
t
i
-
s
e
n
so
r
t
e
c
h
n
i
q
u
e
s,”
H
e
ri
t
a
g
e
,
v
o
l
.
8
,
n
o
.
1
,
J
a
n
.
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
h
e
r
i
t
a
g
e
8
0
1
0
0
3
2
.
[
1
2
]
B
.
A
l
sa
d
i
k
,
“
C
r
o
w
d
s
o
u
r
c
e
d
r
o
n
e
i
ma
g
e
r
y
–
A
p
o
w
e
r
f
u
l
s
o
u
r
c
e
f
o
r
t
h
e
3
D
d
o
c
u
m
e
n
t
a
t
i
o
n
o
f
c
u
l
t
u
r
a
l
h
e
r
i
t
a
g
e
a
t
r
i
s
k
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Arc
h
i
t
e
c
t
u
ra
l
H
e
ri
t
a
g
e
,
v
o
l
.
1
6
,
n
o
.
7
,
p
p
.
9
7
7
–
9
8
7
,
J
u
l
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
8
0
/
1
5
5
8
3
0
5
8
.
2
0
2
0
.
1
8
5
3
8
5
1
.
[
1
3
]
J.
L.
S
c
h
ö
n
b
e
r
g
e
r
a
n
d
J.
-
M
.
F
r
a
h
m,
“
S
t
r
u
c
t
u
r
e
-
f
r
o
m
-
M
o
t
i
o
n
R
e
v
i
s
i
t
e
d
,
”
2
0
1
6
I
EE
E
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
e
r V
i
si
o
n
a
n
d
Pa
t
t
e
rn
Re
c
o
g
n
i
t
i
o
n
(
C
VPR)
,
2
0
1
6
,
p
p
.
4
1
0
4
-
4
1
1
3
,
d
o
i
:
1
0
.
1
1
0
9
/
C
V
P
R
.
2
0
1
6
.
4
4
5
.
[
1
4
]
L.
M
o
r
e
l
l
i
,
F
.
I
o
l
i
,
R
.
B
e
b
e
r
,
F
.
M
e
n
n
a
,
F
.
R
e
m
o
n
d
i
n
o
,
a
n
d
A
.
V
i
t
t
i
,
“
C
O
L
M
A
P
-
S
LA
M
:
A
f
r
a
mew
o
r
k
f
o
r
v
i
s
u
a
l
o
d
o
me
t
r
y
,
”
T
h
e
I
n
t
e
r
n
a
t
i
o
n
a
l
Arc
h
i
v
e
s
o
f
t
h
e
P
h
o
t
o
g
r
a
m
m
e
t
r
y
,
Re
m
o
t
e
S
e
n
s
i
n
g
a
n
d
S
p
a
t
i
a
l
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
X
LV
I
I
I
-
1
/
W
,
p
p
.
3
1
7
–
3
2
4
,
M
a
y
2
0
2
3
,
d
o
i
:
1
0
.
5
1
9
4
/
i
s
p
r
s
-
a
r
c
h
i
v
e
s
-
X
LV
I
I
I
-
1
-
W1
-
2
0
2
3
-
3
1
7
-
2
0
2
3
.
[
1
5
]
C
.
B
a
i
,
R
.
F
u
,
a
n
d
X
.
G
a
o
,
“
C
o
l
m
a
p
-
P
C
D
:
A
n
o
p
e
n
-
s
o
u
r
c
e
t
o
o
l
f
o
r
f
i
n
e
i
m
a
g
e
-
to
-
p
o
i
n
t
c
l
o
u
d
r
e
g
i
st
r
a
t
i
o
n
,
”
i
n
2
0
2
4
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Ro
b
o
t
i
c
s
a
n
d
A
u
t
o
m
a
t
i
o
n
(
I
C
RA)
,
M
a
y
2
0
2
4
,
p
p
.
1
7
2
3
–
1
7
2
9
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
R
A
5
7
1
4
7
.
2
0
2
4
.
1
0
6
1
1
5
8
2
.
[
1
6
]
C
.
L
l
u
l
l
,
N
.
B
a
l
o
i
a
n
,
B
.
B
u
st
o
s
,
K
.
K
u
p
c
z
i
k
,
I
.
S
i
p
i
r
a
n
,
a
n
d
A
.
B
a
l
o
i
a
n
,
“
Ev
a
l
u
a
t
i
o
n
o
f
3
D
r
e
c
o
n
st
r
u
c
t
i
o
n
f
o
r
c
u
l
t
u
r
a
l
h
e
r
i
t
a
g
e
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
A
p
r
a
ctica
l a
p
p
r
o
a
ch
t
o
C
a
n
d
i S
iw
a
3
D
r
ec
o
n
s
tr
u
ctio
n
w
ith
C
OL
MAP
a
n
d
N
erfs
tu
d
io
(
Hele
n
a
Wid
ia
r
ti
)
257
a
p
p
l
i
c
a
t
i
o
n
s,
”
i
n
2
0
2
3
I
EEE
/
C
V
F
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r V
i
si
o
n
W
o
rk
sh
o
p
s
(
I
C
C
VW
)
,
O
c
t
.
2
0
2
3
,
p
p
.
1
6
3
4
–
1
6
4
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
V
W
6
0
7
9
3
.
2
0
2
3
.
0
0
1
7
9
.
[
1
7
]
K
.
D
e
n
g
,
A
.
Li
u
,
J.
-
Y
.
Z
h
u
,
a
n
d
D
.
R
a
ma
n
a
n
,
“
D
e
p
t
h
-
su
p
e
r
v
i
se
d
N
e
R
F
:
F
e
w
e
r
v
i
e
w
s
a
n
d
f
a
s
t
e
r
t
r
a
i
n
i
n
g
f
o
r
f
r
e
e
,
”
i
n
2
0
2
2
I
EEE/
C
VF
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
Vi
si
o
n
a
n
d
P
a
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
(
C
VPR)
,
J
u
n
.
2
0
2
2
,
p
p
.
1
2
8
7
2
–
1
2
8
8
1
,
d
o
i
:
1
0
.
1
1
0
9
/
C
V
P
R
5
2
6
8
8
.
2
0
2
2
.
0
1
2
5
4
.
[
1
8
]
B
.
M
i
l
d
e
n
h
a
l
l
,
P
.
P
.
S
r
i
n
i
v
a
sa
n
,
M
.
Ta
n
c
i
k
,
J
.
T.
B
a
r
r
o
n
,
R
.
R
a
mam
o
o
r
t
h
i
,
a
n
d
R
.
N
g
,
“
N
e
R
F
:
R
e
p
r
e
se
n
t
i
n
g
sce
n
e
s
a
s
n
e
u
r
a
l
r
a
d
i
a
n
c
e
f
i
e
l
d
s
f
o
r
v
i
e
w
s
y
n
t
h
e
s
i
s,”
i
n
C
o
m
m
u
n
i
c
a
t
i
o
n
s
o
f
t
h
e
A
C
M
,
2
0
2
0
,
p
p
.
4
0
5
–
421
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
0
-
5
8
4
5
2
-
8
_
2
4
.
[
1
9
]
H
.
H
.
P
a
r
l
i
n
d
u
n
g
a
n
,
T
.
S
u
k
w
i
k
a
,
a
n
d
H
.
M
a
n
u
r
u
n
g
,
“
P
r
a
m
b
a
n
a
n
t
e
m
p
l
e
t
o
u
r
i
s
t
d
e
s
t
i
n
a
t
i
o
n
d
e
v
e
l
o
p
me
n
t
i
n
I
n
d
o
n
e
s
i
a
a
s
w
o
r
l
d
c
u
l
t
u
r
a
l
h
e
r
i
t
a
g
e
,
”
E
u
r
o
p
e
a
n
J
o
u
r
n
a
l
o
f
S
c
i
e
n
c
e
,
I
n
n
o
v
a
t
i
o
n
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
,
n
o
.
3
,
p
p
.
3
9
–
5
6
,
2
0
2
1
.
[
2
0
]
N
e
r
f
st
u
d
i
o
P
r
o
j
e
c
t
,
“
n
e
r
f
st
u
d
i
o
,
”
G
i
t
H
u
b
r
e
p
o
s
i
t
o
r
y
,
2
0
2
2
–
2
0
2
5
.
(
A
c
c
e
ss
e
d
A
u
g
.
0
1
,
2
0
2
5
)
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
g
i
t
h
u
b
.
c
o
m/
n
e
r
f
s
t
u
d
i
o
-
p
r
o
j
e
c
t
/
n
e
r
f
st
u
d
i
o
.
[
2
1
]
D
.
C
h
e
n
g
a
n
d
E.
C
h
’
n
g
,
“
H
a
r
n
e
ss
i
n
g
c
o
l
l
e
c
t
i
v
e
d
i
f
f
e
r
e
n
c
e
s
i
n
c
r
o
w
d
s
o
u
r
c
i
n
g
b
e
h
a
v
i
o
u
r
f
o
r
M
a
ss
p
h
o
t
o
g
r
a
mm
e
t
r
y
o
f
3
D
c
u
l
t
u
r
a
l
h
e
r
i
t
a
g
e
,
”
J
o
u
r
n
a
l
o
n
C
o
m
p
u
t
i
n
g
a
n
d
C
u
l
t
u
r
a
l
H
e
ri
t
a
g
e
,
v
o
l
.
1
6
,
n
o
.
1
,
p
p
.
1
–
2
3
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
4
5
/
3
5
6
9
0
9
0
.
[
2
2
]
E.
K
.
S
t
a
t
h
o
p
o
u
l
o
u
,
A
.
G
e
o
r
g
o
p
o
u
l
o
s,
G
.
P
a
n
a
g
i
o
t
o
p
o
u
l
o
s,
a
n
d
D
.
K
a
l
i
a
mp
a
k
o
s,
“
C
r
o
w
d
s
o
u
r
c
i
n
g
l
o
s
t
c
u
l
t
u
r
a
l
h
e
r
i
t
a
g
e
,
”
I
S
PR
S
An
n
a
l
s
o
f
t
h
e
Ph
o
t
o
g
ra
m
m
e
t
r
y
,
R
e
m
o
t
e
S
e
n
s
i
n
g
a
n
d
S
p
a
t
i
a
l
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
I
I
-
5
/
W
3
,
p
p
.
2
9
5
–
3
0
0
,
A
u
g
.
2
0
1
5
,
d
o
i
:
1
0
.
5
1
9
4
/
i
s
p
r
sa
n
n
a
l
s
-
II
-
5
-
W3
-
2
9
5
-
2
0
1
5
.
[
2
3
]
L.
M
o
r
e
l
l
i
e
t
a
l
.
,
“
T
h
e
l
e
g
a
c
y
o
f
s
y
c
a
mo
r
e
g
a
p
:
t
h
e
p
o
t
e
n
t
i
a
l
o
f
p
h
o
t
o
g
r
a
mm
e
t
r
i
c
A
I
f
o
r
r
e
v
e
r
se
e
n
g
i
n
e
e
r
i
n
g
l
o
st
h
e
r
i
t
a
g
e
w
i
t
h
c
r
o
w
d
s
o
u
r
c
e
d
d
a
t
a
,
”
T
h
e
I
n
t
e
r
n
a
t
i
o
n
a
l
Arc
h
i
v
e
s
o
f
t
h
e
P
h
o
t
o
g
r
a
m
m
e
t
ry,
Re
m
o
t
e
S
e
n
s
i
n
g
a
n
d
S
p
a
t
i
a
l
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
X
LV
I
I
I
-
2
–
2
,
p
p
.
2
8
1
–
2
8
8
,
J
u
n
.
2
0
2
4
,
d
o
i
:
1
0
.
5
1
9
4
/
i
s
p
r
s
-
a
r
c
h
i
v
e
s
-
X
LV
I
I
I
-
2
-
2
0
2
4
-
2
8
1
-
2
0
2
4
.
[
2
4
]
A
.
D
o
u
l
a
mi
s
,
A
.
V
o
u
l
o
d
i
mo
s
,
E
.
P
r
o
t
o
p
a
p
a
d
a
k
i
s,
N
.
D
o
u
l
a
mi
s
,
a
n
d
K
.
M
a
k
a
n
t
a
si
s,
“
A
u
t
o
mat
i
c
3
D
m
o
d
e
l
i
n
g
a
n
d
r
e
c
o
n
st
r
u
c
t
i
o
n
o
f
c
u
l
t
u
r
a
l
h
e
r
i
t
a
g
e
s
i
t
e
s fr
o
m Twi
t
t
e
r
i
m
a
g
e
s,”
S
u
st
a
i
n
a
b
i
l
i
t
y
,
v
o
l
.
1
2
,
n
o
.
1
0
,
M
a
y
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
s
u
1
2
1
0
4
2
2
3
.
[
2
5
]
F
.
B
i
l
j
e
c
k
i
,
Y
.
S
.
C
h
o
w
,
a
n
d
K
.
L
e
e
,
“
Q
u
a
l
i
t
y
o
f
c
r
o
w
d
s
o
u
r
c
e
d
g
e
o
s
p
a
t
i
a
l
b
u
i
l
d
i
n
g
i
n
f
o
r
ma
t
i
o
n
:
A
g
l
o
b
a
l
a
ss
e
ssm
e
n
t
o
f
O
p
e
n
S
t
r
e
e
t
M
a
p
a
t
t
r
i
b
u
t
e
s,
”
B
u
i
l
d
i
n
g
a
n
d
En
v
i
r
o
n
m
e
n
t
,
v
o
l
.
2
3
7
,
Ju
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
u
i
l
d
e
n
v
.
2
0
2
3
.
1
1
0
2
9
5
.
[
2
6
]
K
.
T
h
e
mi
s
t
o
c
l
e
o
u
s,
V
.
Ev
r
i
p
i
d
o
u
,
a
n
d
K
.
T
o
u
m
b
a
s,
“
M
o
n
i
t
o
r
i
n
g
c
u
l
t
u
r
a
l
h
e
r
i
t
a
g
e
s
i
t
e
s
a
t
r
i
sk
u
s
i
n
g
c
i
t
i
z
e
n
e
n
g
a
g
e
m
e
n
t
t
h
r
o
u
g
h
c
r
o
w
d
s
o
u
r
c
i
n
g
,
”
T
h
e
I
n
t
e
rn
a
t
i
o
n
a
l
Arc
h
i
v
e
s
o
f
t
h
e
P
h
o
t
o
g
r
a
m
m
e
t
ry,
R
e
m
o
t
e
S
e
n
s
i
n
g
a
n
d
S
p
a
t
i
a
l
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
X
LV
I
I
I
-
G
-
2
,
p
p
.
1
4
3
5
–
1
4
4
0
,
A
u
g
.
2
0
2
5
,
d
o
i
:
1
0
.
5
1
9
4
/
i
s
p
r
s
-
a
r
c
h
i
v
e
s
-
X
LV
I
I
I
-
G
-
2
0
2
5
-
1
4
3
5
-
2
0
2
5
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
H
e
lena
Wid
ia
r
ti
re
c
e
iv
e
d
th
e
Ba
c
h
e
lo
r
o
f
En
g
in
e
e
rin
g
d
e
g
re
e
in
El
e
c
tri
c
a
l
En
g
i
n
e
e
rin
g
fr
o
m
th
e
Un
i
v
e
rsity
o
f
In
d
o
n
e
sia
in
2
0
0
6
a
n
d
th
e
M
a
ste
r
o
f
S
c
ien
c
e
d
e
g
re
e
in
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
fro
m
th
e
Ko
re
a
A
d
v
a
n
c
e
d
In
st
it
u
te
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
o
l
o
g
y
(KA
IS
T),
S
o
u
th
K
o
re
a
,
in
2
0
0
9
.
S
h
e
is
c
u
rre
n
tl
y
a
F
a
c
u
lt
y
M
e
m
b
e
r
a
t
Un
iv
e
rsitas
P
ra
se
ti
y
a
M
u
ly
a
,
wh
e
re
sh
e
tea
c
h
e
s
a
n
d
c
o
n
d
u
c
ts
re
se
a
rc
h
in
t
h
e
De
p
a
rtme
n
t
o
f
C
o
m
p
u
ter
S
y
ste
m
s
En
g
i
n
e
e
rin
g
.
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
a
rti
ficia
l
i
n
telli
g
e
n
c
e
fo
r
n
e
x
t
-
g
e
n
e
ra
ti
o
n
n
e
two
r
k
a
n
d
Io
T.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
h
e
len
a
.
wid
iarti@p
ra
se
ti
y
a
m
u
ly
a
.
a
c
.
id
.
Ro
k
h
m
a
t
Febria
n
t
o
re
c
e
iv
e
d
t
h
e
Ba
c
h
e
lo
r
o
f
En
g
in
e
e
r
in
g
d
e
g
re
e
i
n
M
e
c
h
a
tro
n
ics
E
n
g
i
n
e
e
rin
g
fro
m
P
o
li
tek
n
ik
El
e
k
tr
o
n
ik
a
Ne
g
e
ri
S
u
ra
b
a
y
a
(P
ENS
)
,
S
u
ra
b
a
y
a
,
In
d
o
n
e
sia
,
a
n
d
th
e
M
a
ste
r
o
f
En
g
in
e
e
ri
n
g
d
e
g
re
e
in
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
wit
h
a
sp
e
c
ializa
ti
o
n
i
n
M
u
lt
ime
d
ia
In
tel
li
g
e
n
t
Ne
two
rk
fro
m
I
n
stit
u
t
Te
k
n
o
lo
g
i
S
e
p
u
l
u
h
No
p
e
m
b
e
r
(IT
S
),
S
u
ra
b
a
y
a
,
I
n
d
o
n
e
sia
.
He
is
c
u
rre
n
tl
y
a
F
a
c
u
lt
y
M
e
m
b
e
r
in
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
y
ste
m
s
En
g
in
e
e
rin
g
a
t
Un
iv
e
rsit
a
s
P
ra
se
ti
y
a
M
u
l
y
a
,
BS
D,
In
d
o
n
e
sia
.
H
i
s
r
e
se
a
rc
h
i
n
t
e
r
e
s
ts
i
n
c
l
u
d
e
r
o
b
o
t
i
c
s
,
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
,
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
a
n
d
c
o
m
p
u
t
e
r
v
i
s
i
o
n
,
w
i
t
h
a
p
a
r
t
i
c
u
l
a
r
f
o
c
u
s
o
n
d
e
v
e
l
o
p
i
n
g
i
n
t
e
l
l
i
g
e
n
t
r
o
b
o
t
s
t
h
a
t
i
n
c
o
r
p
o
r
a
t
e
A
I
t
o
e
n
h
a
n
c
e
t
h
e
i
r
f
u
n
c
t
i
o
n
a
l
i
t
y
.
H
e
i
s
a
c
t
i
v
e
l
y
i
n
v
o
l
v
e
d
i
n
m
u
l
t
i
d
i
s
c
i
p
l
i
n
a
r
y
r
e
se
a
rc
h
a
n
d
c
o
l
l
a
b
o
r
a
t
i
o
n
,
a
im
i
n
g
t
o
f
o
s
t
e
r
i
n
n
o
v
a
t
i
v
e
p
r
o
j
e
c
t
s
i
n
t
h
e
s
e
f
i
e
l
d
s
.
H
e
c
a
n
b
e
c
o
n
t
a
c
t
e
d
a
t
e
m
a
i
l
:
r
o
k
h
m
a
t
.
fe
b
r
i
a
n
to
@
p
r
a
s
e
t
i
y
a
m
u
l
y
a
.
a
c
.
i
d
.
Ag
u
n
g
Alfi
a
n
sy
a
h
re
c
e
iv
e
d
t
h
e
P
h
.
D.
d
e
g
re
e
i
n
M
a
t
h
e
m
a
ti
c
s
a
n
d
I
n
fo
rm
a
ti
c
s
fro
m
th
e
Un
i
v
e
rsity
d
e
la
M
e
d
it
e
r
ra
n
e
,
M
a
rse
il
le,
F
ra
n
c
e
.
He
is
c
u
rre
n
tl
y
a
F
a
c
u
lt
y
M
e
m
b
e
r
in
t
h
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
y
ste
m
s
En
g
i
n
e
e
rin
g
,
S
c
h
o
o
l
o
f
A
p
p
li
e
d
S
TE
M
,
U
n
iv
e
rsitas
P
ra
se
ti
y
a
M
u
l
y
a
,
Ta
n
g
e
ra
n
g
,
I
n
d
o
n
e
sia
.
His
c
u
rre
n
t
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
a
rti
f
icia
l
in
telli
g
e
n
c
e
,
c
o
m
p
u
ter
v
isi
o
n
,
m
e
d
ica
l
ima
g
e
p
ro
c
e
ss
in
g
,
2
D/3
D
ima
g
e
re
g
istratio
n
,
a
n
d
c
o
m
p
u
tati
o
n
a
l
m
e
th
o
d
s
in
e
n
g
in
e
e
rin
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
g
u
n
g
.
a
lfi
a
n
s
y
a
h
@p
ra
se
ti
y
a
m
u
l
y
a
.
a
c
.
id
.
Evaluation Warning : The document was created with Spire.PDF for Python.