I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
41
,
No
.
2
,
Feb
r
u
ar
y
20
26
,
p
p
.
589
~
600
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
41.
i
2
.
p
p
589
-
6
0
0
589
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Depth
estima
tion
in han
dheld
aug
mented
reality
:
a
revi
ew
M
uh
a
m
m
a
d Anwa
r
Ahm
a
d
1
,
No
rha
ida
M
o
hd
Su
a
ib
2
,
Aj
un
e
Wa
nis
I
s
m
a
il
1
1
V
i
C
u
b
e
La
b
,
F
a
c
u
l
t
y
o
f
C
o
m
p
u
t
i
n
g
,
U
n
i
v
e
r
si
t
i
Te
k
n
o
l
o
g
i
M
a
l
a
y
si
a
,
J
o
h
o
r
,
M
a
l
a
y
s
i
a
2
U
TM
B
i
g
D
a
t
a
C
e
n
t
e
r
,
I
b
n
u
S
i
n
a
I
n
st
i
t
u
t
e
o
f
S
c
i
e
n
t
i
f
i
c
a
n
d
I
n
d
u
st
r
i
a
l
R
e
se
a
r
c
h
,
U
n
i
v
e
r
si
t
i
Te
k
n
o
l
o
g
i
M
a
l
a
y
si
a
,
Jo
h
o
r
,
M
a
l
a
y
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
May
19
,
2
0
2
5
R
ev
is
ed
Dec
19
,
2
0
2
5
Acc
ep
ted
J
an
11
,
2
0
2
6
De
p
th
e
stim
a
ti
o
n
i
n
v
o
lv
e
s
c
a
p
tu
r
in
g
th
e
d
e
p
t
h
i
n
fo
rm
a
ti
o
n
o
f
a
sc
e
n
e
in
th
e
fo
rm
o
f
d
e
p
th
d
a
ta.
Th
is
d
e
p
th
in
fo
rm
a
ti
o
n
c
a
n
b
e
a
p
p
li
e
d
i
n
c
o
m
p
u
ter
v
isio
n
tas
k
s
to
e
n
h
a
n
c
e
p
e
rc
e
p
ti
o
n
a
n
d
c
o
m
p
re
h
e
n
si
o
n
.
I
n
h
a
n
d
h
e
ld
a
u
g
m
e
n
ted
re
a
li
ty
(AR),
d
e
p
th
e
stim
a
ti
o
n
re
fe
rs
to
th
e
c
a
p
a
b
il
it
y
o
f
a
h
a
n
d
h
e
ld
d
e
v
ice
to
e
stim
a
te
th
e
d
e
p
th
o
r
d
istan
c
e
o
f
o
b
jec
ts
in
th
e
re
a
l
wo
rld
b
a
se
d
o
n
i
n
p
u
t
fro
m
it
s
c
a
m
e
ra
fe
e
d
.
Cu
rre
n
tl
y
,
t
h
e
re
is
a
lac
k
o
f
wo
rk
th
a
t
re
v
iew
s
o
n
th
is
to
p
ic.
Th
u
s,
th
is
p
a
p
e
r
re
v
iew
s
a
n
d
d
is
c
u
ss
e
s
th
e
tec
h
n
o
l
o
g
ies
re
g
a
r
d
in
g
d
e
p
th
e
stim
a
ti
o
n
o
n
h
a
n
d
h
e
ld
d
e
v
ice
s
a
n
d
t
h
e
ir
a
p
p
li
c
a
ti
o
n
s
i
n
re
lati
o
n
to
AR.
We
e
m
p
lo
y
p
a
rti
a
ll
y
th
e
sy
ste
m
a
ti
c
re
v
iew
p
ro
c
e
d
u
re
to
a
ll
o
w
m
o
re
sp
e
c
ifi
c
fo
c
u
s
fo
r
o
u
r,
b
r
o
k
e
n
i
n
to
t
h
re
e
m
a
in
fo
c
u
se
s.
F
irst,
we
d
isc
u
ss
th
e
m
e
t
h
o
d
s
t
o
o
b
tain
d
e
p
t
h
d
a
ta
o
n
h
a
n
d
h
e
ld
d
e
v
ice
s.
Ne
x
t,
we
d
isc
u
ss
o
n
t
h
e
e
x
isti
n
g
fra
m
e
wo
rk
s
t
h
a
t
e
n
a
b
le
d
e
p
t
h
e
stim
a
ti
o
n
fo
r
h
a
n
d
h
e
l
d
AR.
T
h
e
n
,
we
c
o
m
p
il
e
a
n
d
d
isc
u
ss
th
e
a
p
p
li
c
a
ti
o
n
s
o
f
d
e
p
th
e
stim
a
ti
o
n
f
o
r
h
a
n
d
h
e
ld
AR
b
a
se
d
o
n
th
e
re
v
iew
e
d
p
a
p
e
r
s.
F
in
a
ll
y
,
we
d
isc
u
ss
t
h
e
n
o
v
e
lt
ies
a
n
d
li
m
i
tatio
n
s
o
f
th
e
c
u
rre
n
t
re
se
a
rc
h
to
d
e
term
in
e
th
e
g
a
p
s
in
t
h
is f
iel
d
o
f
re
se
a
rc
h
.
K
ey
w
o
r
d
s
:
Au
g
m
en
ted
r
ea
lity
Dep
th
d
ata
Dep
th
esti
m
atio
n
Dep
th
s
en
s
o
r
s
Han
d
h
eld
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
:
Mu
h
am
m
ad
A
n
war
Ah
m
ad
ViC
u
b
eL
ab
,
Facu
lty
o
f
C
o
m
p
u
tin
g
,
Un
iv
e
r
s
iti T
ek
n
o
lo
g
i M
alay
s
ia
8
1
3
1
0
J
o
h
o
r
,
Ma
lay
s
ia
E
m
ail: m
u
h
am
m
a
d
.
an
war
@
u
t
m
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
Dep
th
esti
m
atio
n
is
th
e
task
o
f
in
f
er
r
in
g
an
d
ex
tr
ac
tin
g
a
s
ce
n
e’
s
d
ep
t
h
d
ata.
T
h
is
d
ep
th
e
s
tim
atio
n
d
ata
ca
n
b
e
u
tili
ze
d
f
o
r
p
er
ce
p
tio
n
a
n
d
u
n
d
er
s
tan
d
in
g
o
f
v
ar
i
o
u
s
co
m
p
u
ter
v
is
io
n
a
p
p
licatio
n
s
s
u
ch
as
au
to
n
o
m
o
u
s
d
r
i
v
in
g
a
n
d
r
o
b
o
tics
n
av
ig
atio
n
[
1
]
.
W
h
ile
p
r
ev
io
u
s
r
esear
ch
h
as
u
s
ed
d
ep
t
h
c
am
er
as
s
u
ch
as
th
e
Mic
r
o
s
o
f
t
Kin
ec
t
an
d
I
n
tel
R
ea
lSen
s
e
[
2
]
,
[
3
]
,
th
e
em
e
r
g
en
c
e
o
f
in
cr
ea
s
in
g
l
y
p
o
wer
f
u
l
h
a
n
d
h
eld
d
ev
ices
h
as
c
h
a
n
g
e
d
t
h
e
r
es
e
a
r
c
h
l
a
n
d
s
c
ap
e
.
D
e
p
t
h
e
s
ti
m
a
ti
o
n
u
s
i
n
g
h
a
n
d
h
e
l
d
d
e
v
i
c
e
s
c
a
n
p
r
o
v
i
d
e
a
m
o
r
e
a
c
c
e
s
s
i
b
le
a
l
t
e
r
n
a
ti
v
e
c
o
m
p
a
r
e
d
t
o
t
h
e
t
r
a
d
i
t
i
o
n
a
l
s
et
u
p
s
[
1
]
.
T
h
e
w
i
d
e
s
p
r
e
a
d
u
s
e
o
f
h
a
n
d
h
e
l
d
o
r
m
o
b
i
l
e
d
e
v
i
c
e
s
i
n
r
e
c
e
n
t
y
e
a
r
s
h
a
s
s
i
g
n
i
f
ic
a
n
t
l
y
c
h
a
n
g
ed
h
o
w
p
e
o
p
l
e
e
n
g
a
g
e
w
i
t
h
t
e
c
h
n
o
l
o
g
y
[
4
]
.
S
m
a
r
t
p
h
o
n
e
s
a
n
d
t
a
b
l
e
t
s
a
r
e
a
l
r
e
a
d
y
c
o
m
m
o
n
i
n
d
a
i
l
y
l
i
v
e
s
.
S
o
m
e
o
f
t
h
e
s
e
d
e
v
i
c
e
s
a
r
e
a
ls
o
e
q
u
i
p
p
e
d
w
i
t
h
h
i
g
h
e
n
d
s
p
e
c
i
f
i
c
a
t
i
o
n
s
.
T
h
i
s
h
a
s
o
p
e
n
e
d
t
h
e
d
o
o
r
t
o
a
b
r
o
a
d
e
r
r
e
s
e
a
r
c
h
o
p
p
o
r
t
u
n
i
t
i
e
s
a
n
d
c
h
a
l
l
e
n
g
es
,
o
n
e
o
f
t
h
e
m
b
e
i
n
g
i
n
t
h
e
a
r
e
a
o
f
d
e
p
t
h
e
s
t
i
m
at
i
o
n
i
n
h
a
n
d
h
e
l
d
a
u
g
m
e
n
t
e
d
r
e
a
l
i
t
y
(
A
R
)
.
AR
i
s
a
t
e
c
h
n
o
l
o
g
y
s
u
p
e
r
i
m
p
o
s
e
s
d
i
g
i
t
a
l
c
o
n
te
n
t
o
n
t
o
r
e
a
l
-
w
o
r
l
d
e
n
v
i
r
o
n
m
e
n
t
t
h
r
o
u
g
h
s
p
e
c
i
f
i
c
d
i
s
p
l
a
y
s
[
5
]
.
A
v
a
r
ie
t
y
o
f
t
ec
h
n
o
l
o
g
i
c
a
l
t
o
o
l
s
a
r
e
u
s
e
d
,
i
n
c
l
u
d
i
n
g
m
u
l
t
i
m
e
d
i
a
a
p
p
l
i
c
a
t
i
o
n
s
,
3
D
m
o
d
e
l
l
i
n
g
,
t
r
a
c
k
i
n
g
a
n
d
r
e
g
i
s
t
r
a
ti
o
n
i
n
r
e
al
-
t
i
m
e
,
i
n
t
e
l
li
g
e
n
t
i
n
t
e
r
a
c
ti
o
n
,
an
d
s
en
s
in
g
[
6
]
.
AR
h
as
s
ee
n
u
s
ag
e
in
v
ar
io
u
s
in
d
u
s
tr
ies
s
u
ch
as
r
o
b
o
tics
[
7
]
an
d
ed
u
ca
tio
n
[
8
]
.
T
h
e
ab
il
ity
to
en
h
an
ce
th
e
s
u
r
r
o
u
n
d
in
g
with
v
alu
ab
le
in
f
o
r
m
atio
n
u
s
in
g
AR
ca
n
g
iv
e
s
i
g
n
if
ican
t b
o
o
s
t to
th
ese
f
ield
s
[
9
]
-
[
1
1
].
Dep
th
esti
m
atio
n
in
t
h
e
co
n
te
x
t
o
f
h
an
d
h
eld
AR
r
e
f
er
s
to
t
h
e
ab
ilit
y
o
f
a
h
an
d
h
eld
d
e
v
ice
to
esti
m
ate
th
e
d
ep
th
o
r
d
is
tan
ce
o
f
o
b
jects
in
th
e
r
ea
l
wo
r
ld
f
r
o
m
a
ca
m
er
a
f
ee
d
.
T
h
is
tech
n
o
lo
g
y
is
ess
en
tial
f
o
r
cr
ea
tin
g
r
ea
lis
tic
an
d
in
ter
ac
tiv
e
AR
ex
p
er
ien
ce
s
o
n
h
a
n
d
h
eld
d
e
v
ices,
p
ar
ticu
lar
ly
f
o
r
h
an
d
l
in
g
o
cc
lu
s
io
n
s
an
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
41
,
No
.
2
,
Feb
r
u
a
r
y
20
26
:
5
8
9
-
6
0
0
590
co
llis
io
n
d
etec
tio
n
[
1
2
]
.
Ho
wev
er
,
wh
ile
th
e
f
u
s
io
n
o
f
h
an
d
h
el
d
d
ev
ices
an
d
d
ep
th
esti
m
atio
n
s
h
o
ws
u
b
iq
u
ito
u
s
p
o
ten
tial,
th
er
e
a
r
e
s
till
s
ev
er
al
d
if
f
icu
lties
i
n
s
u
cc
ess
f
u
lly
in
teg
r
atin
g
d
ep
th
esti
m
atio
n
o
n
h
an
d
h
el
d
d
ev
ices
s
in
ce
th
ey
h
av
e
lim
ited
p
r
o
ce
s
s
in
g
r
eso
u
r
ce
s
an
d
ar
e
p
o
wer
-
co
n
s
tr
ain
e
d
.
B
ec
au
s
e
o
f
th
is
,
th
e
alg
o
r
ith
m
s
u
s
ed
f
o
r
d
ep
th
esti
m
atio
n
m
u
s
t
b
e
ca
r
ef
u
lly
c
h
o
s
en
to
s
tr
ik
e
a
co
m
p
r
o
m
is
e
b
etwe
en
ac
cu
r
ac
y
an
d
ef
f
icien
c
y
.
Dep
th
esti
m
ati
o
n
tech
n
iq
u
es
ca
n
h
elp
to
g
e
n
er
ate
ac
cu
r
ate
r
ep
r
esen
tatio
n
s
o
f
s
p
atial
r
elatio
n
s
.
Fo
r
ex
am
p
le,
s
em
an
tic
g
eo
-
r
e
g
is
tr
atio
n
im
p
r
o
v
es
th
e
g
lo
b
al
p
o
s
e
esti
m
atio
n
o
f
AR
s
y
s
te
m
s
th
r
o
u
g
h
d
etailed
d
ep
th
m
ap
s
d
e
r
iv
ed
f
r
o
m
v
id
eo
f
r
am
es,
wh
ich
ar
e
im
p
o
r
ta
n
t
wh
en
it
co
m
es
to
alig
n
in
g
v
ir
tu
al
o
b
jects
with
th
eir
r
e
al
-
wo
r
ld
co
u
n
ter
p
ar
ts
[
1
3
].
Ad
d
itio
n
ally
,
th
e
u
s
e
o
f
R
GB
-
D
ca
m
er
as
en
ab
les
th
e
co
l
lectio
n
o
f
d
ep
th
m
ap
s
th
at
m
ak
e
v
ir
tu
al
in
ter
ac
tio
n
s
m
o
r
e
r
ea
lis
tic
b
y
in
co
r
p
o
r
atin
g
lig
h
tin
g
co
n
d
itio
n
s
an
d
o
cc
lu
s
io
n
s
o
f
o
b
jects
in
to
c
o
n
s
id
er
atio
n
[
1
4
]
.
T
h
is
a
b
ilit
y
is
u
s
ef
u
l
in
ap
p
licatio
n
s
wh
er
e
p
r
ec
is
e
p
er
ce
p
ti
o
n
o
f
d
ep
th
is
r
e
q
u
ir
ed
,
s
u
ch
as
in
ed
u
ca
tio
n
al
to
o
ls
an
d
s
u
r
g
ica
l
n
av
ig
atio
n
s
y
s
tem
s
[
1
5
]
.
T
h
e
ch
allen
g
es
f
o
r
d
ep
th
p
er
c
ep
tio
n
f
o
r
h
a
n
d
h
el
d
d
ev
ices
is
s
ig
n
if
ican
t
d
u
e
to
t
h
eir
s
m
aller
s
cr
ee
n
s
a
n
d
as
to
u
ch
is
o
n
ly
2
D
it
m
ak
es
it
d
if
f
icu
lt
f
o
r
th
e
m
o
b
ile
d
ev
ices
to
s
elec
t
an
o
b
ject
th
at
is
f
a
r
awa
y
o
r
h
id
d
en
f
r
o
m
s
ig
h
t
.
R
ay
ca
s
tin
g
an
d
s
h
ad
o
w
d
is
p
lay
s
h
av
e
b
ee
n
s
u
g
g
ested
as
m
ea
n
s
o
f
ass
is
tin
g
u
s
er
s
in
th
e
ac
cu
r
ate
s
elec
tio
n
o
f
v
i
r
tu
al
o
b
jects
th
u
s
im
p
r
o
v
in
g
th
e
u
s
ab
i
lity
o
f
h
an
d
h
eld
AR
s
y
s
tem
s
[
1
6
].
B
ased
o
n
o
u
r
liter
atu
r
e
s
ea
r
ch
,
th
er
e
h
as
b
ee
n
n
o
wo
r
k
t
h
at
r
ev
iews
an
d
d
is
cu
s
s
es
th
e
em
er
g
in
g
tech
n
o
lo
g
ies r
eg
ar
d
in
g
d
e
p
th
esti
m
atio
n
o
n
h
an
d
h
el
d
d
ev
ice
s
.
T
h
u
s
,
o
u
r
g
o
al
f
o
r
th
is
r
ev
ie
w
is
to
d
is
co
v
er
th
e
cu
r
r
en
t
s
tate
-
of
-
t
h
e
-
ar
t
an
d
ch
allen
g
es
r
eg
ar
d
in
g
th
is
f
ield
th
u
s
o
u
r
m
ain
c
o
n
tr
ib
u
tio
n
is
p
r
o
v
id
i
n
g
in
s
ig
h
ts
in
to
th
e
p
r
ev
i
o
u
s
wo
r
k
s
th
at
h
av
e
b
ee
n
d
o
n
e
to
esti
m
ate
d
ep
th
f
o
r
u
s
e
in
h
an
d
h
eld
AR
.
I
n
th
is
r
ev
iew,
we
d
is
cu
s
s
th
e
g
en
er
al
a
p
p
licatio
n
s
o
f
d
ep
th
esti
m
atio
n
in
A
R
an
d
th
e
tech
n
o
lo
g
ies
to
im
p
lem
en
t
d
ep
t
h
esti
m
atio
n
in
h
an
d
h
eld
d
ev
ice
s
.
W
e
also
d
is
cu
s
s
o
n
th
e
g
en
er
al
p
ip
elin
e
an
d
f
lo
w
o
f
d
ep
t
h
esti
m
atio
n
as
we
ll
as
th
e
cu
r
r
e
n
t
ex
is
tin
g
lib
r
ar
ie
s
th
at
ca
n
p
r
o
v
i
d
e
d
e
p
th
esti
m
atio
n
f
o
r
h
a
n
d
h
el
d
AR
.
T
h
e
r
e
m
ain
in
g
s
ec
tio
n
s
o
f
th
e
p
ap
er
ar
e
o
r
g
an
ize
d
as
f
o
llo
ws:
s
ec
tio
n
2
d
is
cu
s
s
es
t
h
e
r
ev
iew
m
eth
o
d
o
l
o
g
y
.
Sectio
n
3
d
is
cu
s
s
es
th
e
o
v
er
v
iew
o
f
d
e
p
th
esti
m
atio
n
in
h
an
d
h
eld
AR
an
d
d
ep
th
d
at
a
ac
q
u
is
itio
n
m
eth
o
d
s
in
h
an
d
h
eld
AR
.
Sectio
n
4
d
escr
ib
es th
e
ex
is
tin
g
h
an
d
h
el
d
AR
f
r
am
ew
o
r
k
s
th
at
ar
e
a
b
l
e
to
p
er
f
o
r
m
d
e
p
th
esti
m
atio
n
.
Sectio
n
5
d
is
cu
s
s
es
th
e
ap
p
licatio
n
s
o
f
d
ep
th
esti
m
atio
n
in
AR
.
T
h
en
,
we
d
is
c
u
s
s
th
e
n
o
v
elties
an
d
lim
itati
o
n
s
o
f
th
e
r
ev
iewe
d
p
ap
er
s
in
s
ec
tio
n
6
an
d
c
o
n
clu
d
e
th
e
p
a
p
er
in
s
ec
tio
n
7.
2.
RE
VI
E
W
M
E
T
H
O
D
Fo
r
o
u
r
r
ev
iew,
th
e
m
eth
o
d
o
lo
g
y
p
ar
tially
f
o
llo
ws
th
e
p
r
o
ce
d
u
r
e
o
f
a
s
y
s
tem
atic
liter
atu
r
e
r
ev
iew,
in
wh
ich
we
d
ef
in
e
th
e
r
esear
c
h
q
u
esti
o
n
s
(
R
Q)
to
g
u
id
e
o
n
th
e
f
o
cu
s
o
f
th
e
r
e
v
iew
[
1
7
]
.
B
y
u
s
in
g
th
is
p
r
o
ce
d
u
r
e,
we
ar
e
ab
le
to
co
n
s
tr
ain
o
u
r
r
ev
iew
to
a
m
o
r
e
s
p
ec
i
f
ic
f
o
cu
s
.
T
h
e
RQ
ar
e
as
o
u
tlin
ed
in
T
ab
le
1
.
R
Q1
p
er
tain
s
to
th
e
m
eth
o
d
s
f
o
r
d
ep
th
d
ata
ac
q
u
is
itio
n
in
h
an
d
h
eld
AR
,
R
Q1
p
e
r
tain
s
to
th
e
ex
is
tin
g
f
r
am
ewo
r
k
s
th
at
allo
w
d
ep
th
esti
m
atio
n
in
h
an
d
h
eld
AR
,
an
d
R
Q3
p
e
r
tain
s
to
th
e
a
p
p
licatio
n
s
f
o
r
d
ep
th
esti
m
atio
n
in
h
an
d
h
eld
AR
.
T
ab
le
1
.
R
esear
ch
q
u
esti
o
n
s
R
Q
c
o
d
e
D
e
scri
p
t
i
o
n
R
Q
1
W
h
a
t
a
r
e
t
h
e
me
t
h
o
d
s f
o
r
d
e
p
t
h
d
a
t
a
a
c
q
u
i
s
i
t
i
o
n
i
n
h
a
n
d
h
e
l
d
A
R
?
R
Q
2
W
h
a
t
a
r
e
t
h
e
e
x
i
s
t
i
n
g
f
r
a
m
e
w
o
r
k
s t
h
a
t
a
l
l
o
w
d
e
p
t
h
e
s
t
i
m
a
t
i
o
n
i
n
h
a
n
d
h
e
l
d
A
R
?
R
Q
3
W
h
a
t
a
r
e
t
h
e
a
p
p
l
i
c
a
t
i
o
n
s fo
r
d
e
p
t
h
e
s
t
i
m
a
t
i
o
n
i
n
h
a
n
d
h
e
l
d
A
R
?
Pap
er
s
elec
tio
n
was
co
n
d
u
cte
d
b
y
s
ea
r
ch
in
g
th
e
m
ajo
r
in
d
ex
in
g
d
atab
ases
.
T
h
e
d
atab
ases
th
at
we
ch
o
s
e
in
clu
d
e
SC
OPUS,
W
o
S
,
an
d
AC
M
Dig
ital
L
ib
r
ar
y
.
W
e
u
s
ed
th
e
f
o
llo
win
g
k
ey
wo
r
d
co
m
b
in
atio
n
w
h
en
p
er
f
o
r
m
in
g
o
u
r
s
ea
r
c
h
:
(
“d
ep
th
”
OR
“d
ep
th
esti
ma
tio
n
”)
A
N
D
(
“h
a
n
d
h
eld
”
OR
“mo
b
ile”
OR
“s
ma
r
tp
h
o
n
e”
OR
“ta
b
let”)
A
N
D
“a
u
g
men
ted
r
ea
lity”
T
h
ese
k
ey
wo
r
d
s
ca
n
p
r
o
v
i
d
e
a
co
m
p
r
eh
en
s
iv
e
r
esu
lt
f
o
r
o
u
r
s
ea
r
ch
as
it
in
cl
u
d
es
th
e
u
s
u
al
ter
m
s
th
at
ar
e
u
s
ed
in
ev
er
y
d
ay
life
.
Ou
r
p
a
p
er
s
elec
tio
n
is
b
ased
o
n
ce
r
tain
c
r
iter
ia,
in
clu
d
in
g
lim
ited
to
t
h
e
f
iv
e
-
y
ea
r
p
er
io
d
f
r
o
m
2
0
1
8
to
2
0
2
3
,
p
ap
er
s
p
u
b
lis
h
ed
in
jo
u
r
n
al
an
d
c
o
n
f
er
e
n
ce
p
r
o
ce
ed
i
n
g
s
an
d
wr
itten
in
E
n
g
lis
h
.
Fro
m
th
e
s
ea
r
ch
r
esu
lts
,
a
to
tal
o
f
5
8
0
ar
ticles
wer
e
r
etu
r
n
ed
th
at
m
atch
ed
o
u
r
cr
iter
ia
.
Af
ter
s
cr
e
en
in
g
th
e
titl
es
an
d
ab
s
tr
ac
ts
,
we
s
elec
ted
2
6
p
ap
e
r
s
f
o
r
th
e
r
ev
iew.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Dep
th
esti
ma
tio
n
in
h
a
n
d
h
eld
a
u
g
men
ted
r
ea
lity:
a
r
ev
iew
(
Mu
h
a
mma
d
A
n
w
a
r
A
h
ma
d
)
591
On
ce
we
h
av
e
id
en
tifie
d
th
e
s
elec
ted
p
ap
er
s
f
o
r
r
ev
iew,
we
an
aly
ze
ea
ch
p
ap
er
an
d
co
m
p
iled
th
em
in
a
tab
le.
I
n
th
is
tab
le,
we
class
if
y
th
e
co
n
ten
ts
b
y
f
o
ll
o
win
g
th
e
o
u
tlin
ed
R
Q,
n
am
ely
th
e
d
ep
th
d
ata
ac
q
u
is
itio
n
,
th
e
f
r
am
ewo
r
k
s
u
s
ed
,
an
d
wh
ich
ar
ea
it
is
a
p
p
lied
.
W
e
also
m
a
k
e
n
o
te
o
f
th
e
s
tr
en
g
th
s
an
d
wea
k
n
ess
es
o
f
ea
ch
p
ap
er
in
th
e
tab
le.
T
h
u
s
,
f
r
o
m
th
is
tab
le
we
wer
e
ab
le
to
s
y
s
tem
atica
ll
y
r
ev
iew
th
e
p
ap
er
s
th
at
f
o
llo
w
o
u
r
f
o
c
u
s
b
ased
o
n
th
e
R
Q.
3.
DE
P
T
H
E
ST
I
M
AT
I
O
N
I
N
H
ANDH
E
L
D
AR
I
n
th
is
s
ec
tio
n
,
we
d
is
cu
s
s
o
n
th
e
o
v
er
v
iew
o
f
d
ep
th
esti
m
a
tio
n
in
AR
to
v
is
u
alize
th
e
g
en
er
al
lo
o
k
o
n
th
e
to
p
ic,
d
o
wn
to
o
u
r
f
o
cu
s
o
n
h
an
d
h
eld
AR
.
T
h
is
allo
ws
u
s
to
estab
lis
h
th
e
d
ir
ec
t
io
n
o
f
th
is
r
ev
iew.
T
h
e
d
e
p
th
d
ata
ac
q
u
is
itio
n
m
e
th
o
d
s
f
o
r
h
an
d
h
eld
A
R
ar
e
also
d
is
cu
s
s
ed
in
th
is
s
ec
tio
n
.
T
h
is
s
atis
f
ie
s
o
u
r
f
ir
s
t
r
esear
ch
q
u
esti
o
n
(
R
Q1
)
.
3
.
1
.
O
v
er
v
iew
o
f
depth
estim
a
t
io
n in
AR
Fo
r
th
is
r
ev
iew,
we
f
o
cu
s
o
n
h
an
d
h
el
d
d
ev
ices.
Fig
u
r
e
1
s
h
o
ws
an
o
v
er
v
iew
o
f
th
e
t
o
p
i
c
o
f
d
ep
t
h
esti
m
atio
n
in
AR
,
in
wh
ich
we
n
ar
r
o
w
d
o
wn
o
u
r
f
o
cu
s
.
W
e
s
tar
t
with
AR
d
is
p
lay
s
a
s
it
is
o
n
e
o
f
th
e
f
u
n
d
am
e
n
tals
o
f
AR
.
T
h
en
,
u
n
d
er
h
an
d
h
eld
d
is
p
lay
we
cla
s
s
if
y
th
e
f
o
cu
s
o
f
o
u
r
r
ev
iew
b
ased
o
n
th
e
R
Q
wh
ich
is
d
ep
t
h
d
ata
ac
q
u
is
itio
n
m
eth
o
d
s
,
ex
is
tin
g
f
r
am
ew
o
r
k
s
th
at
allo
w
d
ep
th
esti
m
ati
o
n
in
h
an
d
h
eld
AR
,
an
d
t
h
e
a
p
p
licatio
n
s
f
o
r
d
ep
th
esti
m
atio
n
in
h
a
n
d
h
eld
AR
.
T
h
er
e
a
r
e
m
u
ltip
le
way
s
to
v
i
ew
AR
ap
p
licatio
n
s
,
in
clu
d
in
g
h
ea
d
-
m
o
u
n
ted
d
is
p
lay
s
(
HM
D)
,
h
a
n
d
h
eld
d
e
v
ices,
o
r
p
r
o
jectio
n
-
b
ased
,
also
k
n
o
w
n
as
s
p
atial
au
g
m
en
ted
r
ea
lity
(
SAR
)
[
1
8
]
.
HM
Ds
ar
e
d
ev
ices
th
at
a
p
er
s
o
n
wea
r
s
o
n
th
e
h
ea
d
an
d
u
s
e
d
to
o
v
er
lay
v
ir
tu
al
an
d
r
ea
l
en
v
ir
o
n
m
en
ts
in
th
e
u
s
er
'
s
v
iew
[
1
9
]
.
Han
d
h
el
d
s
ar
e
m
in
iatu
r
e
co
m
p
u
ter
d
ev
i
ce
s
th
at
a
u
s
er
ca
n
g
r
asp
b
y
h
an
d
s
.
Sm
ar
tp
h
o
n
es,
p
er
s
o
n
al
d
ig
ital
ass
is
tan
ts
(
P
DA)
,
an
d
tab
lets
ar
e
co
m
m
o
n
l
y
u
s
ed
as
h
an
d
h
eld
AR
d
is
p
lay
s
[
2
0
]
.
SAR
em
p
lo
y
s
v
id
eo
p
r
o
jecto
r
s
,
o
p
tical
co
m
p
o
n
en
ts
,
h
o
lo
g
r
am
s
,
an
d
v
ar
io
u
s
tr
ac
k
i
n
g
tech
n
o
lo
g
ies
to
p
r
o
ject
v
is
u
al
in
f
o
r
m
atio
n
d
ir
ec
tly
o
n
to
tan
g
ib
le
o
b
jects.
T
h
is
v
ar
ian
t
in
d
esig
n
co
m
p
ar
ed
t
o
th
e
m
o
r
e
tr
a
d
it
io
n
al
m
ea
n
s
f
o
r
v
is
u
alis
atio
n
allo
ws
th
e
v
iewe
r
to
b
ec
o
m
e
b
etter
in
teg
r
ated
with
th
e
task
at
h
an
d
,
a
n
d
less
co
n
ce
r
n
ed
with
th
e
v
iewin
g
m
e
d
iu
m
[
2
1
].
Fig
u
r
e
1
.
Dep
t
h
esti
m
atio
n
in
h
an
d
h
el
d
AR
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
41
,
No
.
2
,
Feb
r
u
a
r
y
20
26
:
5
8
9
-
6
0
0
592
T
h
e
g
o
al
o
f
d
ep
th
esti
m
atio
n
is
to
ac
q
u
ir
e
th
e
d
is
tan
ce
m
ea
s
u
r
em
en
t
o
f
th
e
o
b
jects
in
th
e
im
ag
e
to
th
e
ca
m
er
a.
T
h
e
m
ea
s
u
r
em
en
t
o
b
tain
ed
is
ty
p
ically
s
to
r
ed
as
d
ep
th
m
ap
o
r
d
ep
th
d
ata.
On
h
an
d
h
el
d
AR
,
th
e
d
ata
ca
n
b
e
u
s
ed
f
o
r
v
ar
io
u
s
ap
p
licatio
n
s
,
in
clu
d
in
g
AR
.
W
h
ile
we
ar
e
f
o
cu
s
in
g
o
n
h
a
n
d
h
eld
d
ev
ices,
it
is
wo
r
th
n
o
tin
g
th
at
s
o
m
e
m
eth
o
d
s
ar
e
in
ter
o
p
er
ab
le
b
etwe
en
m
u
ltip
le
p
latf
o
r
m
s
,
s
u
ch
as
in
[
2
2
]
wh
er
e
b
y
th
ey
co
n
d
u
ct
th
eir
test
o
n
a
d
esk
t
o
p
an
d
o
n
a
s
m
ar
tp
h
o
n
e.
H
o
wev
er
,
it
is
clea
r
th
at
th
er
e
is
a
d
if
f
er
en
ce
in
p
er
f
o
r
m
an
ce
b
ec
au
s
e
o
f
th
e
lim
itatio
n
o
f
t
h
e
s
m
ar
tp
h
o
n
e.
T
h
u
s
,
o
u
r
r
ev
iew
h
ig
h
lig
h
ts
th
e
m
et
h
o
d
s
t
o
o
v
er
co
m
e
th
e
lim
itatio
n
s
an
d
d
is
cu
s
s
es th
e
f
u
tu
r
e
d
ir
ec
tio
n
s
in
th
is
r
esear
ch
f
ield
.
3
.
2
.
Dept
h
da
t
a
a
cquis
it
io
n in ha
nd
hel
d
AR
T
h
is
s
ec
tio
n
d
is
cu
s
s
e
s
th
e
tech
n
o
lo
g
ies an
d
m
eth
o
d
s
th
at
h
av
e
b
ee
n
u
s
ed
f
o
r
ac
q
u
ir
in
g
d
ep
t
h
d
ata
f
o
r
u
s
e
in
h
an
d
h
eld
AR
.
Fro
m
o
u
r
r
ea
d
in
g
s
,
we
ca
n
class
if
y
th
e
tech
n
o
lo
g
ies
as
d
ep
th
s
en
s
o
r
,
m
o
n
o
cu
lar
d
ep
th
esti
m
atio
n
(
s
ter
eo
a
n
d
s
in
g
le
im
ag
e)
,
an
d
s
ce
n
e
s
eg
m
en
t
atio
n
.
T
h
e
ex
p
lan
atio
n
f
o
r
e
ac
h
tech
n
o
lo
g
y
is
d
is
cu
s
s
ed
f
u
r
th
er
b
el
o
w.
3
.
2
.
1
.
Dept
h
s
ens
o
r
Dep
th
s
en
s
o
r
s
ar
e
s
p
ec
ialized
ca
m
er
as
th
at
ca
n
esti
m
ate
d
ep
th
s
.
I
n
liter
atu
r
e,
th
e
r
e
ar
e
m
u
ltip
le
r
esear
ch
th
at
h
av
e
u
tili
ze
d
d
ep
th
s
en
s
o
r
s
in
c
o
n
tex
t
o
f
d
ep
th
esti
m
atio
n
o
n
h
a
n
d
h
el
d
AR
,
wh
ich
ca
n
b
e
class
if
ied
as
u
s
in
g
t
im
e
o
f
f
lig
h
t
(
T
o
F
)
an
d
lig
h
t
d
etec
tio
n
an
d
r
an
g
in
g
(
L
iDAR
)
.
T
h
e
d
ep
th
s
en
s
o
r
s
ar
e
co
m
p
ar
ed
in
T
a
b
le
2
,
in
wh
ic
h
we
co
m
p
ar
e
th
e
s
en
s
in
g
m
e
ch
an
is
m
,
th
e
s
tr
en
g
th
s
an
d
li
m
itatio
n
s
o
f
T
o
F
a
n
d
L
iDAR
.
T
ab
le
2
.
Dep
th
s
en
s
o
r
s
co
m
p
a
r
is
o
n
To
F
Li
D
A
R
S
e
n
s
i
n
g
mec
h
a
n
i
sm
M
e
a
su
r
e
s t
h
e
t
i
me
t
a
k
e
n
f
o
r
a
l
i
g
h
t
t
o
t
r
a
v
e
l
t
o
a
n
o
b
j
e
c
t
a
n
d
b
a
c
k
t
o
d
e
t
e
r
m
i
n
e
d
i
s
t
a
n
c
e
[
2
3
]
U
t
i
l
i
z
e
s l
a
ser
-
p
u
l
se
t
i
me
-
of
-
f
l
i
g
h
t
d
a
t
a
t
o
me
a
su
r
e
d
i
s
t
a
n
c
e
s
a
n
d
b
a
c
k
-
sc
a
t
t
e
r
i
n
t
e
n
s
i
t
i
e
s
[
2
4
]
S
t
r
e
n
g
t
h
s
−
r
e
g
i
s
t
e
r
e
d
d
e
p
t
h
a
n
d
i
n
t
e
n
si
t
y
d
a
t
a
a
t
a
h
i
g
h
f
r
a
me
r
a
t
e
,
c
o
m
p
a
c
t
d
e
s
i
g
n
,
l
o
w
w
e
i
g
h
t
a
n
d
r
e
d
u
c
e
d
p
o
w
e
r
c
o
n
s
u
mp
t
i
o
n
[
2
5
]
−
c
a
n
o
p
e
r
a
t
e
u
n
d
e
r
l
o
w
o
r
c
o
mp
l
e
x
a
m
b
i
e
n
t
l
i
g
h
t
c
o
n
d
i
t
i
o
n
s
[
2
6
]
−
a
b
i
l
i
t
y
t
o
c
r
e
a
t
e
a
c
c
u
r
a
t
e
h
i
g
h
-
r
e
so
l
u
t
i
o
n
mo
d
e
l
s
[
2
7
]
−
a
l
l
o
w
s f
o
r
a
c
c
u
r
a
t
e
d
e
p
t
h
p
e
r
c
e
p
t
i
o
n
,
p
o
t
e
n
t
i
a
l
l
y
o
v
e
r
c
o
mi
n
g
c
u
r
r
e
n
t
l
i
mi
t
a
t
i
o
n
s
i
n
d
e
p
t
h
p
e
r
c
e
p
t
i
o
n
[
2
8
]
Li
mi
t
a
t
i
o
n
s
−
r
e
so
l
u
t
i
o
n
o
f
d
e
p
t
h
ma
p
s
c
a
p
t
u
r
e
d
b
y
To
F
c
a
mer
a
s i
s
l
i
mi
t
e
d
c
o
m
p
a
r
e
d
t
o
H
D
c
o
l
o
r
c
a
mer
a
s,
a
f
f
e
c
t
i
n
g
t
h
e
i
r
d
i
r
e
c
t
u
s
a
b
i
l
i
t
y
i
n
3
D
r
e
c
o
n
st
r
u
c
t
i
o
n
[
2
9
]
−
mea
s
u
r
e
me
n
t
a
c
c
u
r
a
c
y
i
s
d
e
g
r
a
d
e
d
b
y
mu
l
t
i
-
p
a
t
h
i
n
t
e
r
f
e
r
e
n
c
e
[
3
0
]
−
i
n
e
f
f
i
c
i
e
n
t
p
o
w
e
r
c
o
n
s
u
mp
t
i
o
n
[
3
1
]
−
d
e
t
a
i
l
e
d
d
a
t
a
a
c
q
u
i
s
i
t
i
o
n
,
e
s
p
e
c
i
a
l
l
y
i
n
sce
n
a
r
i
o
s
r
e
q
u
i
r
i
n
g
p
r
e
c
i
se
me
a
su
r
e
me
n
t
s
a
t
l
o
n
g
e
r
d
i
st
a
n
c
e
s
[
3
2
]
T
h
er
e
ar
e
s
o
m
e
wo
r
k
s
th
at
h
a
v
e
b
ee
n
d
o
n
e
th
at
u
tili
ze
d
ep
t
h
s
en
s
o
r
o
n
h
an
d
h
eld
d
ev
ices.
Used
h
an
d
p
o
s
e
esti
m
atio
n
f
r
o
m
d
e
p
th
d
a
ta
o
b
tain
e
d
f
r
o
m
a
d
ep
th
s
en
s
o
r
(
I
n
tel
R
ea
lSen
s
e
D4
3
5
)
attac
h
ed
t
o
s
m
ar
tp
h
o
n
e
(
Hu
awe
i
P2
0
)
[
3
3
]
.
L
iDAR
o
n
iPad
Pro
2
0
2
0
to
o
b
tain
d
e
p
th
d
ata
[
3
4
]
.
T
o
F
o
n
a
Go
o
g
le
T
an
g
o
d
ev
ice
[
3
5
]
-
[
3
7
]
.
Ho
wev
er
,
th
e
T
a
n
g
o
p
r
o
ject
was
d
is
co
n
tin
u
ed
b
y
Go
o
g
le
a
n
d
s
u
cc
ee
d
e
d
with
A
R
C
o
r
e
[
3
8
]
.
T
o
F
o
n
h
ig
h
-
en
d
s
m
ar
tp
h
o
n
es
th
at
h
av
e
T
o
F
ca
m
er
a
em
b
ed
d
ed
[
1
2
],
[
3
9
]
.
T
o
F
is
th
e
co
m
m
o
n
d
ep
th
s
en
s
o
r
f
o
u
n
d
o
n
h
ig
h
en
d
An
d
r
o
id
d
ev
ices,
m
e
an
wh
ile
L
iDAR
is
cu
r
r
en
tly
o
n
ly
av
ailab
le
o
n
iOS d
ev
ices [
4
0
].
3.
2
.
2
.
M
o
no
cula
r
depth
esti
m
a
t
io
n
A.
Ster
eo
v
is
io
n
I
n
g
e
n
er
al,
s
ter
eo
v
is
io
n
in
v
o
lv
es
s
ter
eo
m
atch
in
g
tech
n
iq
u
e,
wh
ich
is
u
s
in
g
two
o
r
m
o
r
e
ca
m
er
as
p
lace
d
at
k
n
o
wn
p
o
s
itio
n
s
to
c
ap
tu
r
e
th
e
s
am
e
s
ce
n
e
s
im
u
ltan
eo
u
s
ly
.
T
h
is
is
to
d
eter
m
in
e
wh
eth
er
two
p
ix
els
o
f
d
is
tin
ct
im
a
g
es
co
r
r
esp
o
n
d
to
t
h
e
s
am
e
p
o
in
t
in
th
e
r
ea
l
s
ce
n
e.
B
y
co
m
p
a
r
in
g
th
e
d
is
p
ar
ities
(
h
o
r
iz
o
n
tal
s
h
if
ts
)
b
etwe
en
c
o
r
r
esp
o
n
d
in
g
p
ix
els
i
n
th
e
im
ag
es,
th
e
d
ep
th
m
a
p
is
esti
m
ated
an
d
r
ef
in
ed
t
h
e
m
atc
h
ed
p
ix
els
b
ased
o
n
th
e
p
r
in
ci
p
les
o
f
tr
ia
n
g
u
latio
n
[
4
1
]
.
Ob
jects
th
at
ar
e
clo
s
er
t
o
th
e
ca
m
er
as
will
h
av
e
l
ar
g
er
d
is
p
ar
ities
.
I
n
s
ter
eo
v
is
io
n
,
i
m
ag
es
ar
e
ca
p
tu
r
ed
f
r
o
m
two
s
lig
h
tly
o
f
f
s
et
ca
m
er
as.
T
h
is
o
f
f
s
et
allo
ws
th
e
s
y
s
tem
to
ca
lcu
late
d
ep
th
in
f
o
r
m
atio
n
b
y
co
m
p
a
r
in
g
th
e
d
is
p
ar
ity
b
etwe
en
co
r
r
esp
o
n
d
in
g
p
o
in
ts
in
th
e
two
im
ag
es.
I
n
co
n
tex
t
o
f
m
o
n
o
cu
l
ar
ca
m
er
a,
th
e
tr
ian
g
u
latio
n
is
p
er
f
o
r
m
ed
b
ased
o
n
tr
ac
k
in
g
a
n
d
id
en
tify
i
n
g
two
k
ey
f
r
am
es
b
e
f
o
r
e
p
e
r
f
o
r
m
in
g
th
e
s
ter
eo
m
atch
in
g
to
o
b
tain
th
e
s
p
ar
s
e
d
ep
th
an
d
d
en
s
if
y
in
g
th
e
s
p
ar
s
e
d
ep
th
.
Vale
n
tin
et
a
l.
[
4
2
]
p
r
o
p
o
s
ed
a
p
ip
elin
e
o
f
d
ep
th
f
r
o
m
m
o
ti
o
n
f
o
r
m
o
n
o
c
u
lar
d
ep
th
esti
m
atio
n
o
n
h
an
d
h
eld
th
at
u
tili
ze
s
s
ter
eo
m
atch
in
g
as
p
ar
t
o
f
th
e
p
ip
elin
e
.
T
h
eir
wo
r
k
is
n
o
w
in
te
g
r
ated
in
t
h
e
Go
o
g
le
AR
C
o
r
e
f
r
am
ewo
r
k
,
as
Dep
th
API
[
4
3
]
.
T
h
is
API
h
as
b
ee
n
u
s
ed
in
o
th
er
wo
r
k
s
s
u
ch
as
Dep
th
L
a
b
[
4
4
]
in
wh
ic
h
th
ey
u
tili
ze
d
Dep
th
API
to
cr
ea
te
a
s
et
o
f
d
ep
th
in
ter
ac
tio
n
lib
r
ar
y
to
f
ac
ilit
ate
AR
d
ev
elo
p
e
r
s
in
u
s
in
g
th
e
d
ep
t
h
d
ata
in
th
e
API
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Dep
th
esti
ma
tio
n
in
h
a
n
d
h
eld
a
u
g
men
ted
r
ea
lity:
a
r
ev
iew
(
Mu
h
a
mma
d
A
n
w
a
r
A
h
ma
d
)
593
Mu
lti
-
v
iew
s
ter
eo
(
MV
S)
p
er
f
o
r
m
s
s
ter
eo
m
atch
in
g
with
m
o
r
e
t
h
an
two
ca
m
e
r
as,
wh
ic
h
in
ca
s
e
o
f
m
o
n
o
c
u
lar
ca
m
e
r
a,
m
o
r
e
t
h
an
two
k
e
y
f
r
am
es.
T
h
e
m
ain
g
o
al
is
to
im
p
r
o
v
e
th
e
ac
c
u
r
ac
y
co
m
p
ar
ed
to
s
ter
eo
v
is
io
n
an
d
r
ed
u
ce
th
e
p
r
esen
c
e
o
f
h
o
les
in
th
e
esti
m
ated
d
e
p
th
m
ap
.
Yan
g
et
a
l.
[
2
]
p
r
o
p
o
s
ed
u
s
in
g
th
e
MV
S
m
eth
o
d
esti
m
ate
m
o
n
o
c
u
lar
d
ep
th
.
T
h
eir
m
et
h
o
d
in
co
r
p
o
r
ates
a
d
ee
p
n
eu
r
al
n
etwo
r
k
m
o
d
el
t
o
r
ef
in
e
th
e
g
en
er
ated
d
ep
th
m
ap
an
d
r
e
d
u
ce
th
e
n
o
is
e
f
r
o
m
th
e
tr
ac
k
i
n
g
p
r
o
ce
s
s
.
T
h
ey
also
in
cl
u
d
e
in
cr
em
en
tal
m
esh
g
en
er
atio
n
i
n
th
eir
m
et
h
o
d
t
o
p
er
f
o
r
m
3
D
r
ec
o
n
s
tr
u
ctio
n
f
r
o
m
th
e
d
ep
t
h
m
ap
g
en
er
ate
d
.
B.
Sin
g
le
im
ag
e
Dee
p
lear
n
in
g
m
o
d
els,
s
u
ch
a
s
co
n
v
o
lu
ti
o
n
al
n
e
u
r
al
n
etwo
r
k
s
(
C
NNs),
ca
n
b
e
tr
ain
ed
o
n
d
ep
th
d
ata
to
esti
m
ate
d
ep
th
f
r
o
m
a
s
in
g
le
im
ag
e.
Sin
g
le
-
im
ag
e
d
ep
th
esti
m
atio
n
is
th
e
task
o
f
p
r
ed
ictin
g
th
e
d
ep
th
o
r
d
is
tan
ce
in
f
o
r
m
atio
n
f
o
r
ea
ch
p
ix
el
in
a
2
D
im
ag
e,
u
s
in
g
o
n
ly
a
s
in
g
le
im
ag
e
as
i
n
p
u
t.
I
t
is
a
lo
n
g
-
s
tan
d
in
g
p
r
o
b
lem
in
co
m
p
u
ter
v
is
io
n
a
n
d
h
as
o
n
ly
b
ee
n
a
b
le
to
b
e
ad
eq
u
ately
tack
led
with
th
e
a
d
v
e
n
t
o
f
d
ee
p
lea
r
n
in
g
[
4
5
]
.
As
with
t
h
e
lim
itatio
n
o
f
h
an
d
h
eld
d
ev
ices,
m
o
s
t
s
o
lu
ti
o
n
s
r
eq
u
ir
e
clien
t
-
s
er
v
er
s
y
s
tem
,
b
u
t
s
o
m
e
wo
r
k
s
h
av
e
b
ee
n
a
b
le
to
ac
h
iev
e
r
ea
l
-
tim
e
r
esu
lts
r
u
n
n
in
g
o
n
th
e
d
ev
ice
o
n
l
y
.
T
h
is
is
a
b
i
g
leap
in
p
r
o
g
r
ess
s
in
ce
it
m
in
im
ize
s
p
r
iv
ac
y
a
n
d
laten
cy
is
s
u
es [
4
5
]
.
Mo
s
t
o
f
th
e
s
o
lu
tio
n
s
p
r
o
p
o
s
e
d
p
er
f
o
r
m
s
k
n
o
wled
g
e
d
is
till
atio
n
,
a
p
r
o
ce
s
s
o
f
tr
an
s
f
er
r
i
n
g
k
n
o
wled
g
e
f
r
o
m
lar
g
e
r
m
o
d
els
to
a
m
o
r
e
co
m
p
ac
t
o
n
e
[
1
]
.
T
h
is
allo
ws
th
e
m
o
d
els
r
u
n
n
in
g
o
n
t
h
e
c
o
m
p
lex
h
ar
d
war
e
to
b
e
im
p
lem
en
te
d
o
n
s
o
m
e
h
a
n
d
h
eld
d
ev
ices.
An
o
th
er
o
p
ti
m
izatio
n
p
r
o
ce
s
s
is
th
r
o
u
g
h
n
eu
r
al
ar
c
h
itectu
r
e
s
ea
r
ch
(
NAS)
,
wh
ich
is
a
tech
n
iq
u
e
f
o
r
au
to
m
atin
g
th
e
m
o
d
elli
n
g
o
f
n
e
u
r
al
n
etwo
r
k
s
.
Me
th
o
d
s
f
o
r
NAS
ca
n
b
e
ca
teg
o
r
ized
ac
c
o
r
d
in
g
to
t
h
e
s
ea
r
ch
s
p
ac
e
wh
ich
d
ef
i
n
e
s
th
e
ty
p
e
o
f
n
e
u
r
al
n
etwo
r
k
th
at
ca
n
b
e
d
esig
n
ed
an
d
o
p
tim
ized
,
s
ea
r
ch
s
tr
ateg
y
wh
ich
d
ef
in
es
th
e
a
p
p
r
o
ac
h
u
s
ed
to
e
x
p
lo
r
e
th
e
s
ea
r
ch
s
p
ac
e
an
d
p
e
r
f
o
r
m
an
ce
esti
m
atio
n
s
tr
ateg
y
wh
ich
is
e
v
alu
atin
g
th
e
p
er
f
o
r
m
a
n
ce
o
f
a
p
o
s
s
ib
le
n
eu
r
al
n
etwo
r
k
f
r
o
m
its
d
esig
n
with
o
u
t
co
n
s
tr
u
ctin
g
a
n
d
tr
ain
in
g
th
e
m
o
d
el
[
4
6
].
As
it
is
th
e
n
o
r
m
f
o
r
d
ee
p
lear
n
in
g
s
o
lu
tio
n
s
,
d
atasets
p
lay
a
n
im
p
o
r
tan
t
r
o
le
f
o
r
tr
ain
in
g
t
h
e
m
o
d
els.
T
h
e
co
m
m
o
n
d
atasets
th
at
a
r
e
u
s
ed
i
n
liter
atu
r
e
f
o
r
h
an
d
h
eld
s
in
g
le
im
a
g
e
is
NYU
De
p
th
V2
,
Mid
d
le
b
u
r
y
2
0
1
4
,
Me
g
aDe
p
th
,
an
d
KI
T
T
I
d
ataset.
NYU
Dep
th
V2
is
co
m
p
o
s
ed
o
f
v
id
eo
s
eq
u
e
n
ce
s
f
r
o
m
a
v
ar
iety
o
f
in
d
o
o
r
s
ce
n
es
as
r
ec
o
r
d
ed
f
r
o
m
th
e
Mic
r
o
s
o
f
t
Kin
ec
t
[
4
7
]
.
I
t
f
ea
tu
r
es
1
,
4
4
9
la
b
eled
p
air
s
o
f
alig
n
ed
R
GB
an
d
d
ep
th
im
ag
es
[
4
8
].
T
h
e
Mid
d
leb
u
r
y
2
0
1
4
d
ataset
[
4
9
]
c
o
n
t
ain
s
3
3
im
ag
es.
T
h
ey
a
r
e
all
in
d
o
o
r
s
ce
n
es
with
v
ar
y
in
g
d
if
f
ic
u
lties
in
clu
d
in
g
r
ep
etitiv
e
s
tr
u
ctu
r
es,
o
cc
lu
s
io
n
s
,
wir
y
o
b
jects
an
d
u
n
te
x
tu
r
ed
a
r
ea
s
[
5
0
]
.
Me
g
aDe
p
th
[
5
1
]
o
n
e
o
f
t
h
e
lar
g
est
m
o
n
o
cu
lar
d
ep
th
esti
m
atio
n
d
ataset
co
n
s
is
tin
g
o
f
1
3
0
,
0
0
0
s
am
p
les.
Ho
wev
er
,
B
en
av
id
es
p
o
in
te
d
o
u
t
th
at
m
o
s
t
im
ag
es
h
av
e
lar
g
e
p
o
r
tio
n
s
o
f
in
v
ali
d
p
ix
els
t
h
at
ar
e
m
ask
ed
o
u
t
[
4
8
]
.
Fu
r
th
er
m
o
r
e,
all
p
h
o
to
s
co
llected
f
r
o
m
t
h
e
in
ter
n
et
th
u
s
th
e
q
u
ality
o
f
t
h
e
co
lo
r
im
ag
es
is
in
co
n
s
is
ten
t.
Oth
er
co
m
m
o
n
is
s
u
es
in
clu
d
e
m
o
tio
n
b
lu
r
,
n
o
is
e,
an
d
lack
o
f
d
etail
[
4
8
]
.
T
h
e
KI
T
T
I
d
a
taset
[
5
2
]
co
n
tain
s
9
3
,
0
0
0
s
am
p
les ac
q
u
ir
e
d
v
ia
L
iDAR
s
en
s
o
r
co
r
r
esp
o
n
d
in
g
to
5
6
s
ce
n
es.
I
n
Fig
u
r
e
2
th
e
Ph
o
n
eDe
p
th
d
ataset
was
p
r
o
p
o
s
ed
to
o
v
e
r
co
m
e
th
e
cu
r
r
en
t
lim
itatio
n
s
o
f
th
e
cu
r
r
en
t
d
atasets
wh
ich
in
clu
d
e
lo
w
q
u
ality
o
f
im
ag
es
f
r
o
m
m
eth
o
d
o
f
co
llectin
g
th
e
im
ag
es
,
s
p
ec
if
ic
d
o
m
ain
s
s
u
ch
as
au
to
n
o
m
o
u
s
d
r
i
v
in
g
,
a
n
d
s
m
a
ll
n
u
m
b
er
o
f
s
am
p
les
[
4
8
]
.
T
h
e
d
a
tasets
co
n
tain
6
,
0
3
5
im
a
g
es
o
f
wh
ich
1
,
2
0
2
ar
e
o
u
td
o
o
r
s
ce
n
es
a
n
d
4
,
8
3
3
ar
e
in
d
o
o
r
s
ce
n
es.
Fig
u
r
e
2
(
a)
s
h
o
ws
th
e
s
etu
p
o
f
Ph
o
n
eDe
p
th
d
ataset
ca
p
tu
r
e
co
n
n
ec
ted
t
o
th
e
PC
wh
ile
Fig
u
r
e
2
(
b
)
s
h
o
ws
a
clo
s
e
u
p
o
f
th
e
s
etu
p
.
T
h
e
im
ag
es
ar
e
o
b
tain
ed
f
r
o
m
two
h
an
d
h
el
d
d
e
v
ices
an
d
a
p
r
o
f
e
s
s
io
n
al
Z
E
D
d
ep
th
ca
m
er
a
as
th
e
g
r
o
u
n
d
tr
u
t
h
.
T
h
e
p
h
o
n
es
h
av
e
r
eso
lu
tio
n
o
f
4096
×
3
0
7
2
an
d
2
6
8
6
×
2
0
1
6
,
wh
ile
th
e
d
ep
th
ca
m
er
a
h
as a
r
eso
lu
tio
n
o
f
1
2
8
0
×7
2
0
.
(
a)
(
b
)
Fig
u
r
e
2
.
Ph
o
n
eDe
p
th
d
ataset
ca
p
tu
r
e
s
etu
p
[
4
8
]
(
a)
s
etu
p
o
f
Ph
o
n
eDe
p
th
d
ataset
ca
p
tu
r
e
c
o
n
n
ec
ted
t
o
th
e
PC
an
d
(
b
)
s
h
o
ws a
clo
s
e
u
p
o
f
th
e
s
etu
p
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
41
,
No
.
2
,
Feb
r
u
a
r
y
20
26
:
5
8
9
-
6
0
0
594
C.
I
m
ag
e
s
eg
m
en
tatio
n
I
m
ag
e
s
eg
m
e
n
tatio
n
all
o
ws
o
b
jects
in
a
s
ce
n
e
to
b
e
r
ep
r
es
en
ted
in
a
way
th
at
is
u
n
d
er
s
tan
d
ab
le
t
o
th
e
co
m
p
u
ter
f
o
r
f
u
r
th
er
an
aly
s
is
,
with
d
ep
th
b
ein
g
o
n
e
o
f
t
h
em
.
I
m
ag
e
s
eg
m
en
tatio
n
m
eth
o
d
is
m
o
r
e
s
u
itab
le
to
u
s
e
in
o
u
td
o
o
r
s
ce
n
ar
i
o
s
as
it
ca
n
o
v
e
r
co
m
e
th
e
d
is
tan
ce
lim
itatio
n
o
f
m
o
s
t
d
e
p
th
s
en
s
o
r
s
wh
ich
is
ar
o
u
n
d
5
-
20
m
[
5
3
]
.
I
n
liter
atu
r
e,
f
ew
h
av
e
d
o
n
e
im
a
g
e
s
eg
m
e
n
tatio
n
-
b
ased
d
ep
th
esti
m
atio
n
in
c
o
n
t
ex
t
o
f
h
an
d
h
eld
AR
,
an
d
all
o
f
th
em
u
s
e
clien
t
-
s
er
v
er
ar
ch
itectu
r
e.
T
h
e
im
ag
e
f
r
am
es
ar
e
ca
p
tu
r
ed
v
ia
h
an
d
h
eld
d
ev
ice
wh
ile
th
e
s
eg
m
en
tatio
n
task
is
o
f
f
l
o
ad
ed
t
o
a
h
ig
h
-
en
d
co
m
p
u
t
er
s
er
v
er
.
T
h
e
s
eg
m
en
tatio
n
task
s
eg
r
eg
ates
th
e
o
b
jects
in
th
e
im
a
g
e
in
lay
e
r
s
.
T
h
ese
lay
er
s
ca
n
b
e
u
s
ed
as
m
ask
s
f
o
r
u
s
e
in
AR
ap
p
licatio
n
s
s
u
ch
as
o
cc
lu
s
io
n
s
o
r
p
h
o
to
c
o
m
p
o
s
itio
n
[
5
4
]
,
[
5
5
].
4.
E
XI
ST
I
NG
F
RAM
E
WO
RK
S F
O
R
DE
P
T
H
E
ST
I
M
AT
I
O
N
I
N
H
ANDH
E
L
D
AR
I
m
p
lem
en
tin
g
d
ep
th
esti
m
atio
n
in
h
an
d
h
eld
AR
in
v
o
lv
es
s
elec
tin
g
s
u
itab
le
m
eth
o
d
s
o
r
l
ib
r
ar
ies
to
esti
m
ate
d
ep
th
f
r
o
m
th
e
d
e
v
ice'
s
ca
m
er
a
f
ee
d
.
T
h
er
e
ar
e
s
o
m
e
f
r
am
ewo
r
k
s
th
at
ca
n
b
e
u
s
ed
f
o
r
d
ep
th
esti
m
atio
n
in
h
an
d
h
eld
AR
.
I
n
th
is
s
ec
tio
n
we
d
is
cu
s
s
in
b
r
ief
f
o
r
ea
c
h
o
f
th
e
av
ailab
le
f
r
a
m
ewo
r
k
s
.
−
AR
C
o
r
e
Dep
th
API
:
AR
C
o
r
e
,
d
ev
elo
p
ed
b
y
Go
o
g
le,
is
an
AR
f
r
am
ewo
r
k
th
at
eq
u
ip
s
d
e
v
elo
p
er
s
with
ess
en
tial
tech
n
o
lo
g
ies
an
d
A
PIs
to
cr
ea
te
h
ig
h
-
q
u
ality
A
R
ap
p
licatio
n
s
f
o
r
h
a
n
d
h
el
d
d
ev
ices.
T
h
is
f
r
am
ewo
r
k
ca
n
b
e
d
ep
lo
y
ed
o
n
An
d
r
o
id
an
d
iOS
d
ev
ices.
T
h
e
d
ep
th
esti
m
atio
n
API
with
in
AR
C
o
r
e
u
tili
ze
s
a
s
in
g
le
ca
m
er
a
a
n
d
e
m
p
lo
y
s
th
e
Dep
th
f
r
o
m
Mo
tio
n
(
Df
M)
alg
o
r
ith
m
[
4
2
]
.
I
n
a
d
d
itio
n
,
it
ca
n
also
o
b
tain
d
ep
t
h
d
ata
f
r
o
m
T
o
F wh
en
av
ailab
le.
−
AR
Kit:
A
R
Kit
i
s
an
AR
f
r
am
ewo
r
k
d
e
v
elo
p
e
d
b
y
Ap
p
le
s
p
ec
if
ically
f
o
r
th
ei
r
o
wn
d
ev
ices
s
u
ch
as
iPh
o
n
e
o
r
iPad
.
T
h
e
f
r
am
ewo
r
k
f
ea
tu
r
es
ad
v
an
ce
d
d
ep
th
s
e
n
s
in
g
f
ea
tu
r
es
o
n
s
u
p
p
o
r
ted
Ap
p
le
d
ev
ices
th
a
t
h
av
e
L
iDAR
s
en
s
o
r
em
b
ed
d
ed
[
5
6
]
.
I
t
e
n
ab
les
in
s
tan
t
AR
o
b
ject
p
lace
m
en
t
with
o
u
t
th
e
n
ee
d
f
o
r
s
ca
n
n
in
g
f
ea
tu
r
e
p
o
i
n
ts
an
d
it
also
s
u
p
p
o
r
ts
o
cc
lu
s
io
n
h
an
d
li
n
g
o
f
p
eo
p
le.
−
L
ig
h
ts
h
ip
AR
DK:
th
e
d
ev
elo
p
er
s
o
f
Po
k
em
o
n
GO,
Nian
tic,
lau
n
ch
ed
th
e
L
ig
h
ts
h
ip
AR
DK
f
r
am
ewo
r
k
f
o
r
d
ev
elo
p
in
g
AR
ap
p
li
ca
tio
n
s
f
o
r
h
a
n
d
h
el
d
d
ev
ices
[
5
7
]
.
T
h
e
f
r
am
ew
o
r
k
s
u
p
p
o
r
ts
d
e
p
th
esti
m
atio
n
th
r
o
u
g
h
a
d
ep
th
esti
m
atio
n
m
o
d
el
b
ase
d
o
n
MV
S
[
5
8
]
.
E
a
r
lie
r
v
er
s
io
n
o
f
th
e
f
r
am
ew
o
r
k
is
s
tan
d
alo
n
e,
h
o
wev
er
r
ec
e
n
tly
th
e
d
ev
elo
p
er
s
r
elea
s
ed
v
er
s
io
n
3
.
0
,
wh
ic
h
in
teg
r
ates
th
e
f
r
a
m
ewo
r
k
with
th
e
Un
it
y
AR
Fo
u
n
d
atio
n
f
r
am
ewo
r
k
.
T
h
is
allo
ws
d
ev
elo
p
er
s
to
en
h
a
n
ce
AR
Fo
u
n
d
atio
n
f
ea
tu
r
e
s
e
ts
with
th
eir
s
,
in
clu
d
in
g
d
ep
th
esti
m
atio
n
.
−
E
asy
AR
:
E
asy
AR
is
an
AR
f
r
am
ewo
r
k
d
ev
el
o
p
ed
b
y
Vis
io
n
S
tar
I
n
f
o
r
m
atio
n
T
ec
h
n
o
lo
g
ies
[
5
9
]
.
T
h
is
f
r
am
ewo
r
k
is
ab
le
to
b
e
d
e
p
lo
y
ed
o
n
An
d
r
o
i
d
an
d
iOS
d
ev
ices.
T
h
e
d
ep
th
esti
m
atio
n
m
eth
o
d
is
u
n
d
is
clo
s
ed
,
b
u
t
it
is
ass
u
m
e
d
th
at
t
h
e
m
et
h
o
d
is
b
ased
o
n
s
in
g
le
im
a
g
e
m
o
n
o
c
u
lar
d
e
p
th
esti
m
atio
n
,
b
ased
o
n
th
e
d
o
cu
m
e
n
tatio
n
wh
ich
m
en
tio
n
ed
t
h
at
it
is
b
ased
o
n
R
GB
in
p
u
t
[
6
0
]
.
T
h
e
d
ep
th
d
ata
g
en
er
ated
b
y
th
e
f
r
am
ewo
r
k
c
an
b
e
u
s
ed
f
o
r
s
p
atial
m
a
p
p
in
g
an
d
o
cc
l
u
s
io
n
h
an
d
lin
g
.
5.
AP
P
L
I
CA
T
I
O
N
S O
F
DE
P
T
H
E
ST
I
M
A
T
I
O
N
I
N
H
AND
H
E
L
D
AR
T
h
is
s
ec
tio
n
ex
p
lo
r
es
th
e
ap
p
licatio
n
s
o
f
d
ep
th
esti
m
atio
n
i
n
h
an
d
h
eld
AR
.
W
e
h
av
e
class
if
ied
th
e
ap
p
licatio
n
s
th
at
wer
e
d
is
co
v
er
ed
in
o
u
r
r
e
v
iew
as
tr
ac
k
in
g
,
o
cc
lu
s
io
n
h
an
d
lin
g
,
3
D
r
ec
o
n
s
tr
u
ctio
n
,
co
llis
io
n
d
etec
tio
n
,
in
te
r
ac
tio
n
,
o
b
ject
r
ec
o
g
n
itio
n
,
im
p
r
o
v
e
d
lig
h
tin
g
,
n
av
ig
atio
n
,
an
d
co
n
te
n
t
cr
ea
ti
o
n
.
W
e
d
is
cu
s
s
th
e
r
elate
d
r
esear
ch
in
ea
c
h
o
f
th
e
ap
p
licatio
n
s
.
5
.
1
.
T
ra
c
k
ing
Dep
th
d
ata
allo
ws
A
R
ap
p
lica
tio
n
s
to
u
n
d
er
s
tan
d
th
e
d
ep
th
an
d
s
p
atial
r
elatio
n
s
h
ip
s
o
f
o
b
jects
in
th
e
u
s
er
'
s
en
v
ir
o
n
m
en
t.
T
h
is
en
a
b
l
es
m
o
r
e
ac
cu
r
ate
p
lace
m
en
t
a
n
d
s
ca
lin
g
o
f
v
ir
tu
al
o
b
jects,
m
ak
in
g
th
e
m
ap
p
ea
r
as
if
th
ey
ex
is
t
in
th
e
r
ea
l
wo
r
ld
[
3
9
]
.
Dep
th
esti
m
atio
n
h
elp
s
with
tr
ac
k
in
g
th
e
p
o
s
itio
n
an
d
m
o
v
e
m
en
t
o
f
th
e
d
ev
ice
in
r
ea
l
-
tim
e,
wh
ich
is
cr
u
cial
f
o
r
m
ai
n
tain
in
g
th
e
alig
n
m
en
t
o
f
v
ir
tu
al
o
b
jects
with
t
h
e
p
h
y
s
ical
wo
r
ld
.
T
r
ac
k
in
g
with
d
ep
t
h
d
ata
also
allo
ws
m
ar
k
er
less
o
v
er
lay
in
g
o
f
o
b
jects.
Used
d
ep
th
d
ata
t
o
o
b
tain
g
eo
m
etr
ic
p
r
o
p
er
t
y
o
f
r
ea
l
o
b
ject
an
d
u
s
e
as
co
r
r
esp
o
n
d
e
n
ce
f
o
r
p
o
s
e
esti
m
atio
n
b
etwe
en
tar
g
et
an
d
m
o
d
el
[
3
6
]
.
T
h
eir
m
eth
o
d
r
ep
lace
s
th
e
u
s
e
o
f
f
id
u
cial
m
ar
k
er
s
as
th
ey
m
e
n
tio
n
ed
th
at
m
a
r
k
er
s
ar
e
n
o
t
ef
f
icie
n
t
in
im
p
lem
e
n
tin
g
in
co
m
p
lex
i
n
d
u
s
tr
ial
en
v
ir
o
n
m
en
ts
b
ec
au
s
e
d
if
f
icu
lty
o
f
in
s
tallin
g
m
ar
k
er
s
in
p
r
ec
is
e
p
o
s
itio
n
.
T
r
ac
k
in
g
o
b
ject
v
elo
city
is
also
a
u
s
ef
u
l
ap
p
licatio
n
o
f
d
ep
t
h
d
ata.
Ob
t
ain
ed
d
e
p
th
d
ata
u
s
in
g
th
e
L
i
DAR
s
en
s
o
r
in
iPad
Pro
2
0
2
0
to
tr
ac
k
th
e
v
elo
city
o
f
r
o
b
o
t jo
in
ts
[
3
4
]
.
5
.
2
.
O
cc
lus
io
n
ha
nd
li
ng
AR
ap
p
s
ca
n
u
tili
ze
d
ep
th
in
f
o
r
m
atio
n
to
d
etec
t
p
h
y
s
ical
o
b
jects
in
th
e
s
ce
n
e
an
d
en
s
u
r
e
th
at
v
ir
tu
al
o
b
jects
ap
p
ea
r
b
eh
in
d
o
r
in
f
r
o
n
t
o
f
th
em
,
p
r
o
v
id
in
g
a
m
o
r
e
co
n
v
in
ci
n
g
an
d
im
m
er
s
iv
e
e
x
p
er
ien
ce
.
A
ty
p
ical
AR
s
y
s
tem
with
o
u
t
d
ep
th
u
n
d
er
s
tan
d
in
g
u
s
u
ally
ju
s
t
s
u
p
er
im
p
o
s
es
th
e
v
ir
tu
al
o
b
ject
o
n
th
e
r
ea
l
s
ce
n
e,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Dep
th
esti
ma
tio
n
in
h
a
n
d
h
eld
a
u
g
men
ted
r
ea
lity:
a
r
ev
iew
(
Mu
h
a
mma
d
A
n
w
a
r
A
h
ma
d
)
595
r
eg
ar
d
less
o
f
wh
eth
er
it
is
b
eh
in
d
o
r
in
f
r
o
n
t
o
f
o
b
jects
[
6
1
]
.
T
h
u
s
,
o
cc
lu
s
io
n
h
an
d
lin
g
is
an
im
p
o
r
tan
t
asp
ec
t
t
o
in
cr
ea
s
e
th
e
r
ea
lis
m
o
f
AR
[
6
2
]
.
T
h
is
en
s
u
r
es
th
at
th
e
u
s
e
r
ca
n
f
ee
l
th
at
t
h
e
o
b
ject
is
s
ea
m
less
ly
au
g
m
en
ted
in
th
e
s
ce
n
e.
5
.
3
.
3
D
re
co
ns
t
ruct
io
n
AR
h
as
b
ee
n
u
s
ed
to
f
ac
ilit
ate
th
e
p
r
o
ce
s
s
o
f
3
D
r
ec
o
n
s
tr
u
ctio
n
,
p
ar
ticu
lar
ly
d
u
r
i
n
g
th
e
o
b
ject
s
ca
n
n
in
g
.
T
h
is
s
e
et
a
l.
[
6
3
]
p
r
o
p
o
s
ed
an
en
h
an
ce
d
p
i
p
elin
e
f
o
r
3
D
r
ec
o
n
s
tr
u
ctio
n
u
s
in
g
a
m
o
b
ile
d
ev
ice
f
o
r
d
ata
ac
q
u
is
itio
n
an
d
p
e
r
f
o
r
m
in
g
r
ec
o
n
s
tr
u
ctio
n
o
n
a
r
em
o
te
s
er
v
er
.
T
h
e
m
et
h
o
d
o
p
tim
ized
t
h
e
u
s
er
ex
p
er
ien
ce
d
u
r
in
g
s
ca
n
n
in
g
b
y
in
co
r
p
o
r
atin
g
an
AR
o
b
ject
in
to
th
e
s
ce
n
e.
T
h
is
o
b
ject
g
u
i
d
es
t
h
e
u
s
er
d
u
r
in
g
d
ata
ac
q
u
is
itio
n
an
d
aid
s
in
s
elec
tin
g
th
e
k
e
y
f
r
am
es n
ec
ess
ar
y
to
p
r
o
d
u
ce
a
h
ig
h
-
q
u
ality
m
o
d
el
[6
4
]
.
5
.
4
.
Co
llis
io
n
det
ec
t
io
n
R
ea
l
tim
e
g
en
er
atio
n
o
f
s
ce
n
e
m
esh
an
d
u
s
e
as
th
e
co
llid
er
f
o
r
r
ea
l
o
b
jects.
T
ian
et
a
l
.
[
1
2
]
u
s
ed
v
o
x
els
to
r
ep
r
esen
t
th
e
s
ce
n
e
m
esh
.
Usi
n
g
th
is
m
eth
o
d
d
o
es
n
o
t
g
e
n
er
ate
a
d
e
tailed
g
eo
m
etr
ical
r
ep
r
esen
tatio
n
,
b
u
t
th
ey
a
r
g
u
e
d
th
at
d
etailed
g
e
o
m
etr
y
is
n
o
t
n
ec
ess
ar
y
f
o
r
c
o
llis
io
n
d
et
ec
tio
n
if
t
h
er
e
is
n
o
n
ee
d
f
o
r
ac
c
u
r
ate
r
esp
o
n
s
e.
P
iy
av
ich
ay
an
o
n
et
a
l.
[
6
4
]
u
s
e
d
Dep
th
API
t
o
o
b
tain
th
e
d
e
p
th
d
ata
a
n
d
u
s
ed
m
esh
g
en
er
atio
n
alg
o
r
ith
m
to
r
ec
o
n
s
tr
u
ct
th
e
s
ce
n
e
m
esh
.
T
h
ey
u
s
ed
th
is
m
esh
f
o
r
co
llis
i
o
n
d
etec
tio
n
d
u
r
in
g
telem
an
ip
u
latio
n
o
f
AR
en
v
ir
o
n
m
en
t.
Dep
t
h
L
ab
[
4
4
]
also
u
tili
ze
th
e
Dep
th
API
f
o
r
co
l
lis
io
n
d
etec
t
io
n
o
n
AR
C
o
r
e
-
b
ased
ap
p
licatio
n
s
.
5
.
5
.
I
nte
ra
ct
i
o
n
Dep
th
d
ata
ca
n
b
e
u
s
ed
to
d
etec
t
h
an
d
g
estu
r
es
an
d
p
o
s
e
esti
m
atio
n
.
Dep
th
d
ata
f
r
o
m
d
e
p
t
h
s
en
s
o
r
to
p
er
f
o
r
m
p
o
s
e
esti
m
atio
n
o
f
a
h
an
d
[
3
3
]
.
T
h
e
s
y
s
tem
g
en
er
at
es
3
D
s
k
eleto
n
an
d
u
s
es
th
e
h
an
d
p
o
s
t
esti
m
at
io
n
f
r
o
m
th
e
d
e
p
th
d
ata
to
s
im
u
l
ate
th
e
h
an
d
g
estu
r
es.
C
lien
t
-
s
er
v
er
s
y
s
tem
to
tr
an
s
m
it
d
ep
th
d
ata
f
r
o
m
L
ea
p
Mo
tio
n
,
a
h
an
d
g
estu
r
e
tr
ac
k
in
g
d
ep
t
h
s
en
s
o
r
to
a
h
an
d
h
eld
d
ev
ice
f
o
r
tar
g
et
s
elec
tio
n
o
n
o
cc
lu
d
e
d
an
d
d
is
tan
t
o
b
jects.
T
h
ey
u
s
ed
p
h
o
to
n
u
n
ity
n
etw
o
r
k
in
g
(
PUN)
,
a
n
etwo
r
k
in
g
lib
r
ar
y
th
at
u
s
es
tr
an
s
f
er
co
n
tr
o
l
p
r
o
to
co
l
(
T
C
P)
[
6
5
]
f
o
r
th
e
d
ata
tr
an
s
m
is
s
io
n
.
Sin
g
le
i
m
ag
e
esti
m
atio
n
m
eth
o
d
to
p
er
f
o
r
m
th
e
p
o
s
e
esti
m
atio
n
[
6
6
]
.
5
.
6
.
O
bje
c
t
re
co
g
nitio
n
Dep
th
in
f
o
r
m
atio
n
ca
n
ass
is
t
in
r
ec
o
g
n
izin
g
an
d
tr
ac
k
in
g
o
b
jects
in
th
e
s
ce
n
e,
wh
ich
is
v
alu
ab
le
f
o
r
ap
p
licatio
n
s
lik
e
v
ir
tu
al
tr
y
-
o
n
s
in
r
etail
o
r
id
en
tify
in
g
lan
d
m
ar
k
s
in
to
u
r
is
m
.
Sin
g
le
im
ag
e
esti
m
atio
n
to
d
etec
t
o
b
jects
an
d
s
en
d
a
u
d
i
o
f
ee
d
b
ac
k
t
o
a
v
is
u
ally
im
p
air
ed
p
er
s
o
n
[
6
7
]
.
W
ad
h
wa
e
t
a
l.
[
6
8
]
p
r
o
p
o
s
ed
h
u
m
an
d
etec
tio
n
f
o
r
cr
ea
tin
g
s
h
allo
w
d
ep
th
-
of
-
f
ield
u
s
in
g
a
s
in
g
le
ca
m
e
r
a
o
n
s
m
ar
tp
h
o
n
e.
T
h
e
m
eth
o
d
i
s
cu
r
r
en
tly
in
teg
r
ate
d
in
ca
m
er
a
ap
p
o
n
Go
o
g
le
s
m
ar
tp
h
o
n
e
s
,
k
n
o
wn
as
p
o
r
tr
ait
m
o
d
e
.
Hu
m
an
d
etec
tio
n
to
m
ea
s
u
r
e
d
is
tan
ce
b
etwe
en
h
u
m
an
s
f
o
r
m
o
n
ito
r
in
g
s
o
cial
d
is
tan
cin
g
[
6
9
]
.
Used
d
ep
th
f
r
o
m
Dep
th
API
to
d
etec
t f
o
o
d
s
f
o
r
esti
m
atin
g
th
e
ca
lo
r
ie
in
tak
e
o
f
a
m
ea
l
[
7
0
]
.
5
.
7
.
I
m
pro
v
ed
lig
hting
Dep
th
d
ata
ca
n
h
el
p
to
esti
m
ate
th
e
lig
h
tin
g
co
n
d
itio
n
o
f
t
h
e
en
v
ir
o
n
m
e
n
t,
th
u
s
im
p
r
o
v
i
n
g
th
e
AR
r
ea
lis
m
b
y
r
esp
o
n
d
in
g
to
ch
a
n
g
es
in
lig
h
tin
g
co
n
d
itio
n
s
.
E
n
v
ir
o
n
m
en
t
m
ap
f
r
o
m
d
ep
th
t
o
esti
m
ate
lig
h
tin
g
[
3
5
]
.
T
h
e
s
y
s
tem
was
ab
le
to
ac
h
iev
e
r
ea
l
tim
e
p
e
r
f
o
r
m
an
c
e,
wh
ich
allo
ws
th
e
s
im
u
latio
n
o
f
lig
h
tin
g
ef
f
ec
ts
wh
en
th
e
v
ir
t
u
al
o
b
ject
is
b
ein
g
m
o
v
e
d
s
u
ch
as sh
a
d
o
ws.
5
.
8
.
Na
v
ig
a
t
io
n
AR
n
av
ig
atio
n
a
p
p
s
ca
n
lev
e
r
ag
e
d
e
p
th
esti
m
atio
n
f
o
r
m
o
r
e
ac
cu
r
ac
y
an
d
p
r
ec
is
io
n
in
p
r
o
v
id
i
n
g
tu
r
n
-
by
-
tu
r
n
g
u
id
a
n
ce
,
av
o
i
d
in
g
o
b
ject,
an
d
p
r
esen
tin
g
co
n
tex
tu
ally
r
elev
an
t
in
f
o
r
m
atio
n
o
v
er
lay
s
.
Attach
ed
a
h
an
d
h
eld
d
ev
ice
with
AR
C
o
r
e
Dep
th
API
en
ab
led
to
a
r
o
b
o
t
f
o
r
th
e
p
ath
f
in
d
in
g
[
7
1
]
.
T
h
e
m
eth
o
d
allo
ws
th
e
im
p
lem
en
tatio
n
o
f
r
o
b
o
t
p
ath
f
in
d
in
g
an
d
p
lace
m
en
t w
ith
s
p
atial
awa
r
en
ess
with
o
u
t u
s
in
g
d
ep
t
h
s
en
s
o
r
s
.
5
.
9
.
Co
nte
nt
cr
e
a
t
io
n
AR
co
n
ten
t
cr
ea
to
r
s
ca
n
u
s
e
d
ep
th
esti
m
atio
n
to
alig
n
v
ir
tu
al
elem
en
ts
with
th
e
r
ea
l
wo
r
ld
,
s
im
p
lify
in
g
th
e
p
r
o
ce
s
s
o
f
d
es
ig
n
in
g
AR
ex
p
er
ie
n
ce
s
.
Av
in
a
s
h
an
d
Sh
ar
m
a
[
7
2
]
p
r
o
p
o
s
ed
a
a
d
ee
p
lear
n
i
n
g
-
b
ased
s
o
lu
tio
n
f
o
r
f
ac
e
r
ec
o
n
s
tr
u
ctio
n
th
at
p
r
ed
icts
th
e
d
ep
th
m
ap
s
o
f
th
e
f
ac
e,
b
o
th
f
o
r
war
d
an
d
b
ac
k
war
d
f
ac
in
g
.
T
h
e
s
o
lu
tio
n
is
also
ab
le
to
esti
m
ate
th
e
d
ep
th
o
f
t
h
e
o
cc
lu
d
e
d
p
ar
t
o
f
th
e
f
ac
e.
W
ith
th
is
m
eth
o
d
,
it
h
as
p
o
ten
tial
to
ac
ce
ler
ate
th
e
cr
ea
tio
n
o
f
3
D
av
atar
s
f
o
r
u
s
e
in
v
ar
io
u
s
ap
p
licatio
n
s
s
u
ch
as
v
ir
tu
al
m
ee
tin
g
s
o
r
m
etav
er
s
e.
T
s
u
n
ez
ak
i
et
a
l.
[
7
3
]
p
r
o
p
o
s
ed
a
3
D
r
ec
o
n
s
tr
u
c
tio
n
s
y
s
tem
th
at
i
s
ab
le
to
r
ep
r
o
d
u
ce
th
e
m
ater
ial
ap
p
ea
r
an
ce
s
u
ch
as
g
lo
s
s
in
ess
o
r
r
ef
lecta
n
ce
.
Face
b
o
o
k
r
es
ea
r
ch
er
s
p
r
esen
ted
a
p
h
o
to
m
an
ip
u
latio
n
m
eth
o
d
th
at
co
n
v
er
ts
a
2
D
p
h
o
to
in
to
d
ep
th
en
ab
le
d
3
D
p
h
o
to
[
7
4
]
.
Pro
p
o
s
ed
a
s
y
s
tem
th
at
s
eg
m
en
ts
th
e
b
ac
k
g
r
o
u
n
d
o
f
a
s
ce
n
e
an
d
r
ep
lace
with
a
v
ir
tu
al
b
ac
k
g
r
o
u
n
d
[
7
5
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
41
,
No
.
2
,
Feb
r
u
a
r
y
20
26
:
5
8
9
-
6
0
0
596
6.
DIS
CU
SS
I
O
N
S
T
h
is
s
ec
tio
n
d
is
cu
s
s
es
th
e
n
o
v
elties
an
d
lim
itatio
n
s
o
f
t
h
e
r
ev
iewe
d
p
a
p
er
s
.
Mo
s
t
o
f
th
e
r
ev
iewe
d
wo
r
k
s
ar
e
ab
le
t
o
p
r
o
v
id
e
o
f
r
ea
l
-
tim
e
s
o
lu
tio
n
s
,
wh
ich
is
im
p
o
r
tan
t
f
o
r
AR
ap
p
licatio
n
s
.
T
h
er
e
ar
e
also
wo
r
k
s
th
at
h
av
e
b
ee
n
im
p
le
m
en
ted
in
r
ea
l
w
o
r
ld
p
r
o
d
u
ct
s
s
u
ch
as
p
o
r
tr
ait
m
o
d
e
in
G
o
o
g
le
s
m
ar
tp
h
o
n
es,
AR
C
o
r
e
Dep
th
API
an
d
Face
b
o
o
k
'
s
3
D
p
h
o
t
o
g
r
a
p
h
y
f
e
atu
r
e.
T
h
ese
in
n
o
v
atio
n
s
h
ig
h
lig
h
t
th
e
p
r
ac
tical
ap
p
licatio
n
s
o
f
d
ep
th
p
er
ce
p
t
io
n
in
en
h
an
cin
g
u
s
er
e
x
p
er
i
en
ce
s
.
Fu
r
th
er
m
o
r
e,
th
e
r
e
is
also
wo
r
k
th
at
ca
n
en
ab
le
s
u
p
p
o
r
t
f
o
r
p
o
wer
u
s
er
s
,
as
d
em
o
n
s
tr
ated
in
[
3
9
]
.
E
x
ten
d
in
g
th
e
wo
r
k
s
p
ac
e
v
ir
t
u
ally
o
n
s
m
all
d
ev
ic
e
s
u
ch
as th
e
s
m
ar
tp
h
o
n
e
allo
w
m
o
r
e
d
ata
to
b
e
d
is
p
lay
e
d
with
o
u
t c
o
n
n
ec
ti
n
g
to
lar
g
e
r
d
is
p
l
ay
s
.
I
n
AR
,
o
cc
lu
s
io
n
h
an
d
lin
g
an
d
co
llis
io
n
d
etec
tio
n
em
er
g
e
a
s
cr
itical
asp
ec
ts
,
en
s
u
r
in
g
th
a
t
r
en
d
er
e
d
o
b
jects
f
o
llo
w
th
e
r
u
les
o
f
s
ig
h
t
an
d
p
h
y
s
ics
r
esp
ec
tiv
ely
.
Dep
th
u
n
d
er
s
tan
d
in
g
p
lay
s
a
p
iv
o
tal
r
o
le
in
en
ab
lin
g
ef
f
ec
tiv
e
o
cc
lu
s
io
n
h
an
d
lin
g
a
n
d
co
llis
io
n
d
etec
ti
o
n
with
in
AR
s
ce
n
es,
en
h
an
cin
g
im
m
er
s
io
n
an
d
r
ea
lis
m
.
So
m
e
wo
r
k
s
h
av
e
e
n
a
b
led
o
cc
lu
s
io
n
h
an
d
lin
g
an
d
c
o
llis
io
n
d
etec
tio
n
o
n
h
an
d
h
eld
AR
.
Ad
d
itio
n
ally
,
ef
f
o
r
ts
h
av
e
b
ee
n
d
ir
ec
ted
to
w
ar
d
s
f
ac
ilit
atin
g
AR
d
ev
elo
p
m
en
t
th
r
o
u
g
h
to
o
ls
lik
e
th
e
Dep
th
L
ab
lib
r
ar
y
.
T
h
is
r
eso
u
r
ce
en
a
b
les
d
ev
elo
p
e
r
s
to
h
ar
n
ess
d
ep
t
h
d
ata
f
r
o
m
p
la
tf
o
r
m
s
lik
e
th
e
AR
C
o
r
e
Dep
t
h
API
,
h
elp
in
g
with
task
s
s
u
ch
as
o
cc
lu
s
io
n
h
an
d
l
in
g
,
co
llis
io
n
d
etec
tio
n
,
an
d
l
ig
h
tin
g
m
a
n
ip
u
latio
n
.
Dep
th
esti
m
atio
n
ca
n
also
p
o
ten
tia
lly
en
h
an
ce
o
b
ject
d
et
ec
tio
n
task
s
.
B
y
lev
er
ag
in
g
d
e
p
th
in
f
o
r
m
atio
n
,
alg
o
r
ith
m
s
ca
n
m
o
r
e
ac
cu
r
ately
d
is
ce
r
n
th
e
s
p
atial
ch
a
r
ac
ter
i
s
tics
o
f
o
b
jects,
im
p
r
o
v
in
g
t
h
e
ef
f
icac
y
o
f
d
etec
tio
n
s
y
s
tem
s
ac
r
o
s
s
v
ar
io
u
s
d
o
m
ain
s
.
T
h
er
e
a
r
e
c
o
m
m
o
n
is
s
u
es
f
o
u
n
d
in
th
e
cu
r
r
en
t
r
esear
ch
.
No
tab
ly
th
e
co
m
p
u
tatio
n
al
lim
itatio
n
s
an
d
tr
ain
in
g
d
atasets
f
o
r
m
ac
h
in
e
lear
n
in
g
b
ased
s
o
lu
tio
n
s
.
Dep
th
d
ata
ca
n
also
b
e
am
b
ig
u
o
u
s
in
ce
r
tain
s
u
r
f
ac
e
tex
tu
r
es
s
u
ch
as
r
ef
lectiv
e,
s
h
i
n
y
o
r
tr
an
s
p
ar
e
n
t.
T
h
er
e
ar
e
al
s
o
wo
r
k
s
th
at
im
p
le
m
en
t
clie
nt
-
s
er
v
er
s
o
lu
tio
n
s
,
wh
ich
in
tr
o
d
u
ce
s
laten
cy
is
s
u
es.
A
co
n
s
is
ten
t
an
d
f
ast
n
etwo
r
k
co
n
n
ec
tio
n
is
r
eq
u
ir
ed
f
o
r
th
is
ty
p
e
o
f
s
o
lu
tio
n
to
wo
r
k
ef
f
icien
tly
.
Dep
th
s
en
s
o
r
s
h
av
e
b
ee
n
a
p
p
ea
r
in
g
o
n
h
an
d
h
eld
d
ev
ices,
h
o
wev
er
it
is
s
till
a
co
s
t
ly
s
o
lu
tio
n
th
at
is
o
n
ly
av
ailab
le
o
n
h
ig
h
en
d
d
ev
ices.
I
n
th
e
e
v
en
t
th
at
it
is
m
o
r
e
co
m
m
o
n
l
y
av
ailab
le
o
n
m
i
d
-
r
an
g
e
d
e
v
ices in
th
e
f
u
tu
r
e,
it i
s
p
r
ed
icted
th
at
m
o
r
e
r
esear
ch
will b
e
f
o
cu
s
in
g
o
n
th
is
d
ev
ice
.
B
ased
o
n
o
u
r
f
in
d
in
g
s
,
d
ep
th
esti
m
atio
n
in
h
an
d
h
eld
AR
h
as
b
ee
n
im
p
r
o
v
ed
s
ig
n
if
ican
tl
y
with
t
h
e
ar
r
iv
al
o
f
s
tate
-
of
-
th
e
-
ar
t
f
r
a
m
ewo
r
k
s
an
d
lib
r
ar
ies.
No
tab
l
y
,
Dep
th
API
an
d
AR
DK
allo
ws
d
ep
th
esti
m
atio
n
u
s
in
g
o
n
ly
th
e
R
GB
ca
m
er
a
o
n
d
ev
ice,
with
th
e
o
p
tio
n
o
f
u
s
in
g
T
o
F
wh
en
av
ailab
le.
T
h
is
will
allo
w
m
o
r
e
d
ev
elo
p
er
s
to
le
v
er
ag
e
th
e
tech
n
o
lo
g
y
as
it
will
b
e
ac
ce
s
s
ib
le
to
m
ass
iv
e
am
o
u
n
t
o
f
u
s
er
s
.
T
h
u
s
,
it
ca
n
b
e
p
r
ed
icted
th
at
th
e
ap
p
licatio
n
s
o
f
d
ep
t
h
esti
m
atio
n
in
h
an
d
h
e
ld
AR
th
at
was
d
is
cu
s
s
ed
will
b
e
r
ea
c
h
a
b
r
o
ad
er
au
d
ien
ce
.
Su
ch
im
p
licatio
n
s
will
also
in
cr
ea
s
e
m
o
tiv
atio
n
s
f
o
r
f
u
t
u
r
e
r
esear
ch
to
im
p
r
o
v
e
th
is
f
ield
f
u
r
th
e
r
.
T
h
is
s
tu
d
y
h
as
h
i
g
h
lig
h
ted
th
e
p
o
s
s
ib
le
r
esear
c
h
d
i
r
ec
tio
n
s
b
ased
o
n
th
e
cu
r
r
e
n
t
ac
h
iev
em
e
n
ts
an
d
lim
itatio
n
s
.
Ho
wev
er
,
s
in
ce
we
h
av
e
co
n
s
tr
ain
ed
o
u
r
f
o
cu
s
b
ased
o
n
th
e
R
Q,
it
i
s
p
o
s
s
ib
le
th
at
we
h
av
e
o
v
e
r
lo
o
k
ed
s
o
m
e
p
ap
er
s
th
at
m
ay
f
u
r
t
h
er
h
ig
h
lig
h
t
th
e
f
u
tu
r
e
d
ir
ec
tio
n
s
o
n
th
e
r
esear
ch
.
W
e
also
d
id
n
o
t
f
u
lly
ex
p
lo
r
e
o
n
ea
c
h
o
f
th
e
f
r
am
ewo
r
k
s
d
escr
ib
ed
.
A
m
o
r
e
in
-
d
ep
th
c
o
m
p
ar
is
o
n
o
f
ea
ch
f
r
am
ew
o
r
k
s
co
u
ld
b
e
ex
p
lo
r
e
d
in
th
e
f
u
tu
r
e.
7.
CO
NCLU
SI
O
N
I
n
th
is
p
a
p
er
,
we
r
ev
iewe
d
s
ev
er
al
p
a
p
er
s
r
eg
a
r
d
in
g
d
e
p
th
esti
m
atio
n
o
n
h
an
d
h
eld
AR
.
T
h
e
p
a
p
er
s
s
elec
ted
ar
e
r
an
g
ed
f
r
o
m
2
0
1
8
to
2
0
2
3
.
Fro
m
th
e
r
ev
iew,
we
p
r
o
v
id
e
an
o
v
er
v
iew
o
f
d
ep
th
esti
m
atio
n
in
AR
an
d
n
ar
r
o
w
d
o
wn
to
h
an
d
h
el
d
AR
in
ter
m
s
o
f
d
ep
th
d
ata
ac
q
u
is
it
io
n
m
eth
o
d
s
,
wh
ich
c
an
b
e
class
if
ied
as
d
ep
th
s
en
s
o
r
,
m
o
n
o
c
u
lar
d
e
p
t
h
esti
m
atio
n
an
d
im
a
g
e
s
eg
m
en
tatio
n
.
Mo
n
o
cu
lar
d
ep
th
es
tim
atio
n
ap
p
r
o
ac
h
ca
n
b
e
f
u
r
th
er
class
if
ied
as st
er
eo
v
is
io
n
a
n
d
s
in
g
le
im
ag
e
.
I
n
th
is
r
ev
iew
we
al
s
o
d
is
cu
s
s
o
n
th
e
ex
is
tin
g
f
r
am
ew
o
r
k
s
th
at
allo
w
d
ep
th
esti
m
atio
n
o
n
h
an
d
h
eld
d
ev
ices
f
o
r
u
s
e
in
AR
.
Fu
r
th
er
m
o
r
e,
th
e
ap
p
licatio
n
s
o
f
d
ep
t
h
esti
m
atio
n
in
h
an
d
h
eld
AR
wer
e
also
class
if
ied
an
d
d
is
cu
s
s
ed
b
ased
o
n
th
e
r
ev
iewe
d
p
ap
er
s
.
Fin
ally
,
we
d
is
cu
s
s
ed
o
n
th
e
n
o
v
elties
an
d
lim
itatio
n
s
o
f
th
e
cu
r
r
en
t
r
esear
ch
to
id
en
tif
y
th
e
r
esear
ch
d
ir
ec
tio
n
th
at
ca
n
b
e
p
u
r
s
u
ed
in
th
is
f
ield
o
f
r
esear
ch
.
T
h
e
ch
allen
g
es
th
at
s
till
o
f
f
er
r
o
o
m
f
o
r
im
p
r
o
v
em
en
t
in
clu
d
e
co
m
p
u
tatio
n
al
co
m
p
lex
ity
,
o
v
e
r
co
m
in
g
am
b
ig
u
o
u
s
d
ep
th
d
ata
d
u
e
to
ce
r
tain
s
u
r
f
ac
e
tex
t
u
r
e
s
an
d
laten
cy
is
s
u
es.
R
ec
o
m
m
en
d
atio
n
f
o
r
r
esear
ch
d
i
r
ec
tio
n
is
to
im
p
r
o
v
e
th
e
d
ep
th
ac
q
u
is
itio
n
m
eth
o
d
,
as it p
lay
s
a
m
ajo
r
r
o
le
in
th
e
r
esu
l
tin
g
d
ep
th
esti
m
atio
n
.
Ou
r
r
e
v
iew
u
n
d
er
s
co
r
es
th
e
s
ig
n
if
ican
ce
o
f
d
ep
th
esti
m
atio
n
in
h
a
n
d
h
eld
AR
an
d
em
p
h
asizes
th
e
on
g
o
in
g
n
ee
d
f
o
r
r
esear
ch
in
t
h
is
f
ield
.
W
e
lay
d
o
wn
th
e
f
o
u
n
d
atio
n
f
o
r
p
av
in
g
th
e
way
t
o
f
u
tu
r
e
r
esear
ch
.
I
t
is
o
u
r
h
o
p
e
th
at
o
u
r
r
e
v
iew
will
b
e
a
v
alu
ab
le
r
eso
u
r
ce
f
o
r
r
esear
c
h
er
s
an
d
p
r
ac
titi
o
n
e
r
s
im
p
r
o
v
in
g
d
ep
th
esti
m
atio
n
in
h
an
d
h
eld
AR
.
W
e
en
co
u
r
ag
e
f
u
r
th
er
r
esear
ch
an
d
in
n
o
v
atio
n
in
th
is
ex
citin
g
an
d
r
a
p
id
ly
d
ev
elo
p
in
g
ar
ea
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Dep
th
esti
ma
tio
n
in
h
a
n
d
h
eld
a
u
g
men
ted
r
ea
lity:
a
r
ev
iew
(
Mu
h
a
mma
d
A
n
w
a
r
A
h
ma
d
)
597
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
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
Data
av
ailab
ilit
y
is
n
o
t
ap
p
li
ca
b
le
to
th
is
p
ap
er
as
n
o
n
e
w
d
ata
wer
e
cr
ea
ted
o
r
an
aly
ze
d
in
th
is
s
tu
d
y
.
RE
F
E
R
E
NC
E
S
[
1
]
M
.
K
.
Y
u
c
e
l
,
V
.
D
I
mari
d
o
u
,
A
.
D
r
o
s
o
u
,
a
n
d
A
.
S
a
a
-
G
a
r
r
i
g
a
,
“
R
e
a
l
-
t
i
me
mo
n
o
c
u
l
a
r
d
e
p
t
h
e
st
i
ma
t
i
o
n
w
i
t
h
s
p
a
r
se
su
p
e
r
v
i
s
i
o
n
o
n
mo
b
i
l
e
,
”
i
n
I
EE
E
C
o
m
p
u
t
e
r
S
o
c
i
e
t
y
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
P
a
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
Wo
rks
h
o
p
s
,
J
u
n
.
2
0
2
1
,
p
p
.
2
4
2
8
–
2
4
3
7
,
d
o
i
:
1
0
.
1
1
0
9
/
C
V
P
R
W
5
3
0
9
8
.
2
0
2
1
.
0
0
2
7
5
.
[
2
]
X
.
Y
a
n
g
e
t
a
l
.
,
“
M
o
b
i
l
e
3
D
R
e
c
o
n
:
r
eal
-
t
i
m
e
m
o
n
o
c
u
l
a
r
3
D
r
e
c
o
n
st
r
u
c
t
i
o
n
o
n
a
m
o
b
i
l
e
p
h
o
n
e
,
”
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
Vi
su
a
l
i
z
a
t
i
o
n
a
n
d
C
o
m
p
u
t
e
r Gr
a
p
h
i
c
s
,
v
o
l
.
2
6
,
n
o
.
1
2
,
p
p
.
3
4
4
6
–
3
4
5
6
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
TV
C
G
.
2
0
2
0
.
3
0
2
3
6
3
4
.
[
3
]
F
.
E.
F
a
d
z
l
i
,
A
.
W
.
I
smai
l
,
S
.
A
.
K
.
I
sh
i
g
a
k
i
,
M
.
N
.
A
.
N
o
r
’
a
,
a
n
d
M
.
Y
.
F
.
A
l
a
d
i
n
,
“
R
e
a
l
-
t
i
me
3
D
r
e
c
o
n
s
t
r
u
c
t
i
o
n
met
h
o
d
f
o
r
h
o
l
o
g
r
a
p
h
i
c
t
e
l
e
p
r
e
se
n
c
e
,
”
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
2
,
n
o
.
8
,
p
.
4
0
0
9
,
A
p
r
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
2
0
8
4
0
0
9
.
[
4
]
M
.
S
.
L
u
n
d
i
n
g
,
J
.
E.
S
.
G
r
ø
n
b
æ
k
,
N
.
G
r
y
mer,
T
.
W
e
l
l
s
,
S
.
H
o
u
b
e
n
,
a
n
d
M
.
G
.
P
e
t
e
r
se
n
,
“
R
e
a
l
i
t
y
a
n
d
b
e
y
o
n
d
:
p
r
o
x
e
mi
c
s
a
s
a
l
e
n
s
f
o
r
d
e
s
i
g
n
i
n
g
h
a
n
d
h
e
l
d
c
o
l
l
a
b
o
r
a
t
i
v
e
a
u
g
me
n
t
e
d
r
e
a
l
i
t
y
,
”
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
AC
M
o
n
H
u
m
a
n
-
C
o
m
p
u
t
e
r
I
n
t
e
ra
c
t
i
o
n
,
v
o
l
.
7
,
n
o
.
I
S
S
,
p
p
.
2
1
–
4
0
,
O
c
t
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
4
5
/
3
6
2
6
4
6
3
.
[
5
]
P
.
M
i
l
g
r
a
m,
H
.
T
a
k
e
m
u
r
a
,
A
.
U
t
s
u
mi
,
a
n
d
F
.
K
i
sh
i
n
o
,
“
A
u
g
m
e
n
t
e
d
r
e
a
l
i
t
y
:
a
c
l
a
ss
o
f
d
i
s
p
l
a
y
s
o
n
t
h
e
r
e
a
l
i
t
y
-
v
i
r
t
u
a
l
i
t
y
c
o
n
t
i
n
u
u
m,
”
i
n
T
e
l
e
m
a
n
i
p
u
l
a
t
o
r
a
n
d
T
e
l
e
p
res
e
n
c
e
T
e
c
h
n
o
l
o
g
i
e
s
,
D
e
c
.
1
9
9
5
,
v
o
l
.
2
3
5
1
,
p
p
.
2
8
2
–
2
9
2
,
d
o
i
:
1
0
.
1
1
1
7
/
1
2
.
1
9
7
3
2
1
.
[
6
]
J.
C
.
P
.
C
h
e
n
g
,
K
.
C
h
e
n
,
a
n
d
W
.
C
h
e
n
,
“
C
o
mp
a
r
i
s
o
n
o
f
m
a
r
k
er
-
b
a
s
e
d
a
n
d
m
a
r
k
e
r
l
e
s
s
A
R
:
a
c
a
se
st
u
d
y
o
f
a
n
i
n
d
o
o
r
d
e
c
o
r
a
t
i
o
n
sy
st
e
m,
”
i
n
L
e
a
n
a
n
d
C
o
m
p
u
t
i
n
g
i
n
C
o
n
st
r
u
c
t
i
o
n
C
o
n
g
r
e
ss
-
Vo
l
u
m
e
1
:
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
J
o
i
n
t
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
i
n
g
i
n
C
o
n
st
r
u
c
t
i
o
n
,
Ju
l
.
2
0
1
7
,
p
p
.
4
8
3
–
4
9
0
,
d
o
i
:
1
0
.
2
4
9
2
8
/
j
c
3
-
2
0
1
7
/
0
2
3
1
.
[
7
]
M
.
W
u
e
t
a
l
.
,
“
O
p
t
i
m
i
z
i
n
g
a
s
s
e
m
b
l
y
p
r
o
c
e
s
s
e
s
w
i
t
h
a
u
g
m
e
n
t
e
d
r
e
a
l
i
t
y
:
a
c
a
s
e
s
t
u
d
y
o
n
T
u
r
t
l
e
B
o
t
s
,
”
I
n
d
o
n
e
s
i
a
n
J
o
u
r
n
a
l
o
f
E
l
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
3
5
,
n
o
.
3
,
p
p
.
1
5
4
7
–
1
5
5
5
,
S
e
p
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
3
5
.
i
3
.
p
p
1
5
4
7
-
1
5
5
5
.
[
8
]
C. L
.
Y
.
C
h
e
n
g
,
G
.
E.
S
u
,
J.
B
.
A
h
m
a
d
,
a
n
d
T.
S
u
t
i
k
n
o
,
“
G
a
m
e
-
b
a
se
d
a
u
g
men
t
e
d
r
e
a
l
i
t
y
l
e
a
r
n
i
n
g
o
f
S
a
r
a
w
a
k
h
i
st
o
r
y
i
n
e
n
h
a
n
c
i
n
g
c
u
l
t
u
r
a
l
h
e
r
i
t
a
g
e
p
r
e
serv
a
t
i
o
n
,
”
I
n
d
o
n
e
si
a
n
J
o
u
r
n
a
l
o
f
E
l
e
c
t
ri
c
a
l
En
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
3
4
,
n
o
.
3
,
p
p
.
1
7
1
8
–
1
7
2
9
,
Ju
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
3
4
.
i
3
.
p
p
1
7
1
8
-
1
7
2
9
.
[9
]
M
.
A
.
B
i
n
A
h
ma
d
,
N
.
M
.
S
u
a
i
b
,
a
n
d
A
.
W
.
I
smai
l
,
“
O
c
c
l
u
si
o
n
h
a
n
d
l
i
n
g
f
o
r
a
u
g
me
n
t
e
d
r
e
a
l
i
t
y
e
n
v
i
r
o
n
me
n
t
u
si
n
g
n
e
u
r
a
l
n
e
t
w
o
r
k
i
ma
g
e
s
e
g
me
n
t
a
t
i
o
n
:
a
r
e
v
i
e
w
,
”
i
n
AI
P
C
o
n
f
e
r
e
n
c
e
Pr
o
c
e
e
d
i
n
g
s
,
2
0
2
4
,
v
o
l
.
2
9
9
1
,
n
o
.
1
,
p
.
5
0
0
3
1
,
d
o
i
:
1
0
.
1
0
6
3
/
5
.
0
1
9
8
7
4
1
.
[
1
0
]
T.
K
h
a
n
,
K
.
J
o
h
n
s
t
o
n
,
a
n
d
J
.
O
p
h
o
f
f
,
“
T
h
e
i
mp
a
c
t
o
f
a
n
a
u
g
m
e
n
t
e
d
r
e
a
l
i
t
y
a
p
p
l
i
c
a
t
i
o
n
o
n
l
e
a
r
n
i
n
g
m
o
t
i
v
a
t
i
o
n
o
f
st
u
d
e
n
t
s
,
”
Ad
v
a
n
c
e
s i
n
H
u
m
a
n
-
C
o
m
p
u
t
e
r I
n
t
e
r
a
c
t
i
o
n
,
v
o
l
.
2
0
1
9
,
p
p
.
1
–
1
4
,
F
e
b
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
1
9
/
7
2
0
8
4
9
4
.
[
1
1
]
S
.
A
n
u
a
r
,
N
.
N
i
z
a
r
,
a
n
d
M
.
A
.
I
smai
l
,
“
Th
e
i
m
p
a
c
t
o
f
u
s
i
n
g
a
u
g
me
n
t
e
d
r
e
a
l
i
t
y
a
s
t
e
a
c
h
i
n
g
ma
t
e
r
i
a
l
o
n
st
u
d
e
n
t
s’
m
o
t
i
v
a
t
i
o
n
,
”
Asi
a
n
J
o
u
r
n
a
l
o
f
V
o
c
a
t
i
o
n
a
l
E
d
u
c
a
t
i
o
n
a
n
d
H
u
m
a
n
i
t
i
e
s
,
v
o
l
.
2
,
n
o
.
1
,
p
p
.
1
–
8
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
5
3
7
9
7
/
a
j
v
a
h
.
v
2
i
1
.
1
.
2
0
2
1
.
[
1
2
]
Y
.
Ti
a
n
,
Y
.
M
a
,
S
.
Q
u
a
n
,
a
n
d
Y
.
X
u
,
“
O
c
c
l
u
s
i
o
n
a
n
d
c
o
l
l
i
s
i
o
n
a
w
a
r
e
sm
a
r
t
p
h
o
n
e
A
R
u
si
n
g
t
i
m
e
-
of
-
f
l
i
g
h
t
c
a
mera,
”
i
n
L
e
c
t
u
re
N
o
t
e
s
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
i
n
c
l
u
d
i
n
g
s
u
b
ser
i
e
s
L
e
c
t
u
r
e
N
o
t
e
s
i
n
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
L
e
c
t
u
re
N
o
t
e
s
i
n
Bi
o
i
n
f
o
rm
a
t
i
c
s)
,
v
o
l
.
1
1
8
4
5
LN
C
S
,
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
9
,
p
p
.
1
4
1
–
1
5
3
.
[
1
3
]
H
.
P
.
C
h
i
u
,
V
.
M
u
r
a
l
i
,
R
.
V
i
l
l
a
m
i
l
,
G
.
D
.
K
e
ssl
e
r
,
S
.
S
a
mara
se
k
e
r
a
,
a
n
d
R
.
K
u
m
a
r
,
“
A
u
g
me
n
t
e
d
r
e
a
l
i
t
y
d
r
i
v
i
n
g
u
si
n
g
s
e
ma
n
t
i
c
g
e
o
-
r
e
g
i
st
r
a
t
i
o
n
,
”
i
n
2
5
t
h
I
EEE
C
o
n
f
e
re
n
c
e
o
n
Vi
r
t
u
a
l
Re
a
l
i
t
y
a
n
d
3
D
U
ser
I
n
t
e
rf
a
c
e
s,
VR
2
0
1
8
-
Pr
o
c
e
e
d
i
n
g
s
,
M
a
r
.
2
0
1
8
,
p
p
.
4
2
3
–
4
3
0
,
d
o
i
:
1
0
.
1
1
0
9
/
V
R
.
2
0
1
8
.
8
4
4
7
5
6
0
.
[
1
4
]
B
.
J.
B
o
o
m,
S
.
O
r
t
s
-
Esc
o
l
a
n
o
,
X
.
X
.
N
i
n
g
,
S
.
M
c
D
o
n
a
g
h
,
P
.
S
a
n
d
i
l
a
n
d
s
,
a
n
d
R
.
B
.
F
i
s
h
e
r
,
“
I
n
t
e
r
a
c
t
i
v
e
l
i
g
h
t
so
u
r
c
e
p
o
si
t
i
o
n
e
st
i
mat
i
o
n
f
o
r
a
u
g
me
n
t
e
d
r
e
a
l
i
t
y
w
i
t
h
a
n
R
G
B
-
D
c
a
mer
a
,
”
C
o
m
p
u
t
e
r
A
n
i
m
a
t
i
o
n
a
n
d
V
i
rt
u
a
l
W
o
rl
d
s
,
v
o
l
.
2
8
,
n
o
.
1
,
D
e
c
.
2
0
1
7
,
d
o
i
:
1
0
.
1
0
0
2
/
c
a
v
.
1
6
8
6
.
[
1
5
]
B
.
C
u
i
,
M
.
I
sl
a
m
,
L
.
B
a
i
,
a
n
d
H
.
R
e
n
,
“
S
u
r
g
i
c
a
l
-
D
I
N
O
:
a
d
a
p
t
e
r
l
e
a
r
n
i
n
g
o
f
f
o
u
n
d
a
t
i
o
n
mo
d
e
l
s
f
o
r
d
e
p
t
h
e
s
t
i
m
a
t
i
o
n
i
n
e
n
d
o
sc
o
p
i
c
su
r
g
e
r
y
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
e
r
Ass
i
st
e
d
Ra
d
i
o
l
o
g
y
a
n
d
S
u
r
g
e
r
y
,
v
o
l
.
1
9
,
n
o
.
6
,
p
p
.
1
0
1
3
–
1
0
2
0
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
5
4
8
-
0
2
4
-
0
3
0
8
3
-
5.
[1
6
]
P
.
W
a
c
k
e
r
,
O
.
N
o
w
a
k
,
S
.
V
o
e
l
k
e
r
,
a
n
d
J.
B
o
r
c
h
e
r
s,
“
Ev
a
l
u
a
t
i
n
g
me
n
u
t
e
c
h
n
i
q
u
e
s
f
o
r
h
a
n
d
h
e
l
d
A
R
w
i
t
h
a
smar
t
p
h
o
n
e
&
mi
d
-
a
i
r
p
e
n
,
”
i
n
C
o
n
f
e
r
e
n
c
e
Pr
o
c
e
e
d
i
n
g
s
-
2
2
n
d
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
H
u
m
a
n
-
C
o
m
p
u
t
e
r
I
n
t
e
r
a
c
t
i
o
n
w
i
t
h
M
o
b
i
l
e
D
e
v
i
c
e
s
a
n
d
S
e
r
v
i
c
e
s:
E
x
p
a
n
d
i
n
g
t
h
e
H
o
ri
z
o
n
o
f
Mo
b
i
l
e
I
n
t
e
r
a
c
t
i
o
n
,
M
o
b
i
l
e
H
C
I
2
0
2
0
,
O
c
t
.
2
0
2
0
,
p
p
.
1
–
1
0
,
d
o
i
:
1
0
.
1
1
4
5
/
3
3
7
9
5
0
3
.
3
4
0
3
5
4
8
.
[
1
7
]
B
.
K
i
t
c
h
e
n
h
a
m
,
O
.
P
e
a
r
l
B
r
e
r
e
t
o
n
,
D
.
B
u
d
g
e
n
,
M
.
T
u
r
n
e
r
,
J
.
B
a
i
l
e
y
,
a
n
d
S
.
Li
n
k
ma
n
,
“
S
y
s
t
e
m
a
t
i
c
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
s
i
n
s
o
f
t
w
a
r
e
e
n
g
i
n
e
e
r
i
n
g
-
A
s
y
st
e
ma
t
i
c
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
,
”
I
n
f
o
rm
a
t
i
o
n
a
n
d
S
o
f
t
w
a
r
e
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
5
1
,
n
o
.
1
,
p
p
.
7
–
1
5
,
J
a
n
.
2
0
0
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
f
so
f
.
2
0
0
8
.
0
9
.
0
0
9
.
[
1
8
]
F
.
Z
h
o
u
,
H
.
B
.
L.
D
u
n
,
a
n
d
M
.
B
i
l
l
i
n
g
h
u
r
st
,
“
Tr
e
n
d
s
i
n
a
u
g
me
n
t
e
d
r
e
a
l
i
t
y
t
r
a
c
k
i
n
g
,
i
n
t
e
r
a
c
t
i
o
n
a
n
d
d
i
sp
l
a
y
:
a
r
e
v
i
e
w
o
f
t
e
n
y
e
a
r
s
o
f
I
S
M
A
R
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
7
t
h
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
S
y
m
p
o
si
u
m
o
n
M
i
x
e
d
a
n
d
Au
g
m
e
n
t
e
d
R
e
a
l
i
t
y
2
0
0
8
,
I
S
MA
R
2
0
0
8
,
S
e
p
.
2
0
0
8
,
p
p
.
1
9
3
–
2
0
2
,
d
o
i
:
1
0
.
1
1
0
9
/
I
S
M
A
R
.
2
0
0
8
.
4
6
3
7
3
6
2
.
[
1
9
]
J.
C
a
r
mi
g
n
i
a
n
i
,
B
.
F
u
r
h
t
,
M
.
A
n
i
se
t
t
i
,
P
.
C
e
r
a
v
o
l
o
,
E
.
D
a
m
i
a
n
i
,
a
n
d
M
.
I
v
k
o
v
i
c
,
“
A
u
g
m
e
n
t
e
d
r
e
a
l
i
t
y
t
e
c
h
n
o
l
o
g
i
e
s,
sy
st
e
ms
a
n
d
a
p
p
l
i
c
a
t
i
o
n
s,
”
M
u
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
5
1
,
n
o
.
1
,
p
p
.
3
4
1
–
3
7
7
,
D
e
c
.
2
0
1
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
4
2
-
0
1
0
-
0
6
6
0
-
6.
[
2
0
]
D
.
W
a
g
n
e
r
a
n
d
D
.
S
c
h
m
a
l
s
t
i
e
g
,
“
H
a
n
d
h
e
l
d
a
u
g
me
n
t
e
d
r
e
a
l
i
t
y
d
i
s
p
l
a
y
s
,
”
i
n
Pro
c
e
e
d
i
n
g
s
-
I
EEE
V
i
rt
u
a
l
R
e
a
l
i
t
y
,
2
0
0
6
,
v
o
l
.
2
0
0
6
,
p
.
6
7
,
d
o
i
:
1
0
.
1
1
0
9
/
V
R
.
2
0
0
6
.
6
7
.
[
2
1
]
A
.
I
r
l
i
t
t
i
a
n
d
G
.
S
.
V
o
n
I
t
z
st
e
i
n
,
“
V
a
l
i
d
a
t
i
n
g
c
o
n
s
t
r
a
i
n
t
d
r
i
v
e
n
d
e
s
i
g
n
t
e
c
h
n
i
q
u
e
s
i
n
s
p
a
t
i
a
l
a
u
g
me
n
t
e
d
r
e
a
l
i
t
y
,
”
A
u
st
r
a
l
a
s
i
a
n
U
s
e
r
I
n
t
e
r
f
a
c
e
C
o
n
f
e
r
e
n
c
e
,
2
0
1
3
.
[
2
2
]
Y
.
H
.
Ji
n
,
I
.
T.
H
w
a
n
g
,
a
n
d
W
.
H
.
L
e
e
,
“
A
m
o
b
i
l
e
a
u
g
me
n
t
e
d
r
e
a
l
i
t
y
s
y
s
t
e
m
f
o
r
t
h
e
r
e
a
l
-
t
i
me
v
i
su
a
l
i
z
a
t
i
o
n
o
f
p
i
p
e
s i
n
p
o
i
n
t
c
l
o
u
d
d
a
t
a
w
i
t
h
a
d
e
p
t
h
se
n
s
o
r
,
”
E
l
e
c
t
r
o
n
i
c
s
(
S
w
i
t
z
e
rl
a
n
d
)
,
v
o
l
.
9
,
n
o
.
5
,
p
.
8
3
6
,
M
a
y
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
9
0
5
0
8
3
6
.
[
2
3
]
M
.
H
a
n
sar
d
,
S
.
Le
e
,
O
.
C
h
o
i
,
a
n
d
R
.
H
o
r
a
u
d
,
T
i
m
e
-
of
-
f
l
i
g
h
t
c
a
m
e
r
a
s:
Pr
i
n
c
i
p
l
e
s
,
m
e
t
h
o
d
s
a
n
d
a
q
p
p
l
i
c
a
t
i
o
n
s
.
S
p
r
i
n
g
e
r
P
u
b
l
i
s
h
i
n
g
C
o
m
p
a
n
y
,
I
n
c
o
r
p
o
r
a
t
e
d
,
2
0
1
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
41
,
No
.
2
,
Feb
r
u
a
r
y
20
26
:
5
8
9
-
6
0
0
598
[
2
4
]
A
.
Tr
a
m
e
l
l
i
,
S
.
C
a
p
p
u
c
c
i
,
E
.
V
a
l
e
n
t
i
n
i
,
L
.
R
o
s
si
,
a
n
d
I
.
L
i
si
,
“
N
e
a
r
s
h
o
r
e
san
d
b
a
r
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
S
a
b
a
u
d
i
a
(
I
t
a
l
y
)
w
i
t
h
L
i
D
A
R
d
a
t
a
:
T
h
e
F
H
y
L
a
p
p
r
o
a
c
h
,
”
Re
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
1
2
,
n
o
.
7
,
p
.
1
0
5
3
,
M
a
r
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s
1
2
0
7
1
0
5
3
.
[
2
5
]
S
.
F
o
i
x
,
G
.
A
l
e
n
y
à
,
a
n
d
C
.
T
o
r
r
a
s,
“
Lo
c
k
-
i
n
t
i
me
-
of
-
f
l
i
g
h
t
(
T
o
F
)
c
a
mer
a
s:
a
s
u
r
v
e
y
,
”
I
E
EE
S
e
n
s
o
rs
J
o
u
r
n
a
l
,
v
o
l
.
1
1
,
n
o
.
9
,
p
p
.
1
9
1
7
–
1
9
2
6
,
S
e
p
.
2
0
1
1
,
d
o
i
:
1
0
.
1
1
0
9
/
JS
EN
.
2
0
1
0
.
2
1
0
1
0
6
0
.
[
2
6
]
K
.
G
u
o
,
T.
Zh
a
i
,
E
.
P
a
s
h
o
l
l
a
r
i
,
C
.
J
.
V
a
r
l
a
m
o
s,
A
.
A
h
me
d
,
a
n
d
M
.
N
.
I
sl
a
m,
“
C
o
n
t
a
c
t
l
e
ss
v
i
t
a
l
s
i
g
n
mo
n
i
t
o
r
i
n
g
sy
s
t
e
m
f
o
r
h
e
a
r
t
a
n
d
r
e
sp
i
r
a
t
o
r
y
r
a
t
e
mea
s
u
r
e
m
e
n
t
s
w
i
t
h
m
o
t
i
o
n
c
o
m
p
e
n
s
a
t
i
o
n
u
s
i
n
g
a
n
e
a
r
-
i
n
f
r
a
r
e
d
t
i
me
-
of
-
f
l
i
g
h
t
c
a
mera
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
1
,
n
o
.
2
2
,
p
.
1
0
9
1
3
,
N
o
v
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
1
2
2
1
0
9
1
3
.
[
2
7
]
W
.
Y
.
H
a
n
e
t
a
l
.
,
“
D
e
v
e
l
o
p
m
e
n
t
o
f
t
h
r
e
e
-
d
i
me
n
si
o
n
a
l
b
r
e
a
s
t
s
c
a
n
a
n
d
mea
s
u
r
e
me
n
t
a
p
p
l
i
c
a
t
i
o
n
u
si
n
g
l
a
s
e
r
i
ma
g
i
n
g
d
e
t
e
c
t
i
o
n
a
n
d
r
a
n
g
i
n
g
se
n
so
r
o
n
i
P
h
o
n
e
,
”
P
l
a
s
t
i
c
a
n
d
R
e
c
o
n
s
t
r
u
c
t
i
v
e
S
u
r
g
e
ry
,
v
o
l
.
1
5
2
,
n
o
.
6
,
p
p
.
1
1
8
3
E
-
1
1
8
7
E,
M
a
r
.
2
0
2
3
,
d
o
i
:
10
.
1
0
9
7
/
P
R
S
.
0
0
0
0
0
0
0
0
0
0
0
1
0
4
0
5
.
[
2
8
]
K
.
Y
.
F
o
n
g
e
t
a
l
.
,
“
C
l
i
n
i
c
a
l
v
a
l
i
d
a
t
i
o
n
o
f
a
smar
t
p
h
o
n
e
a
p
p
l
i
c
a
t
i
o
n
f
o
r
a
u
t
o
mat
e
d
w
o
u
n
d
mea
s
u
r
e
m
e
n
t
i
n
p
a
t
i
e
n
t
s
w
i
t
h
v
e
n
o
u
s l
e
g
u
l
c
e
r
s,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
Wo
u
n
d
J
o
u
rn
a
l
,
v
o
l
.
2
0
,
n
o
.
3
,
p
p
.
7
5
1
–
7
6
0
,
A
u
g
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
1
1
/
i
w
j
.
1
3
9
1
8
.
[
2
9
]
L.
W
.
L
i
u
,
Y
.
Li
,
L
.
H
.
W
a
n
g
,
D
.
X
.
Li
,
a
n
d
M
.
Z
h
a
n
g
,
“
T
o
F
d
e
p
t
h
map
su
p
e
r
-
r
e
s
o
l
u
t
i
o
n
u
s
i
n
g
c
o
m
p
r
e
s
si
v
e
se
n
s
i
n
g
,
”
i
n
Pro
c
e
e
d
i
n
g
s
-
2
0
1
3
7
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
I
m
a
g
e
a
n
d
G
r
a
p
h
i
c
s,
I
C
I
G
2
0
1
3
,
J
u
l
.
2
0
1
3
,
p
p
.
1
3
5
–
1
3
8
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
G
.
2
0
1
3
.
3
3
.
[
3
0
]
M
.
H
o
r
i
o
e
t
a
l
.
,
“
R
e
s
o
l
v
i
n
g
m
u
l
t
i
-
p
a
t
h
i
n
t
e
r
f
e
r
e
n
c
e
i
n
c
o
m
p
r
e
ss
i
v
e
t
i
me
-
of
-
f
l
i
g
h
t
d
e
p
t
h
i
ma
g
i
n
g
w
i
t
h
a
mu
l
t
i
-
t
a
p
m
a
c
r
o
-
p
i
x
e
l
c
o
m
p
u
t
a
t
i
o
n
a
l
C
M
O
S
i
ma
g
e
se
n
s
o
r
,
”
S
e
n
so
rs
,
v
o
l
.
2
2
,
n
o
.
7
,
p
.
2
4
4
2
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
2
0
7
2
4
4
2
.
[
3
1
]
S
.
Le
e
,
D
.
L
e
e
,
P
.
C
h
o
i
,
a
n
d
D
.
P
a
r
k
,
“
A
c
c
u
r
a
c
y
–
p
o
w
e
r
c
o
n
t
r
o
l
l
a
b
l
e
l
i
d
a
r
se
n
s
o
r
sy
st
e
m
w
i
t
h
3
d
o
b
j
e
c
t
r
e
c
o
g
n
i
t
i
o
n
f
o
r
a
u
t
o
n
o
mo
u
s
v
e
h
i
c
l
e
,
”
S
e
n
so
r
s (S
w
i
t
ze
rl
a
n
d
)
,
v
o
l
.
2
0
,
n
o
.
1
9
,
p
p
.
1
–
2
0
,
O
c
t
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
0
1
9
5
7
0
6
.
[
3
2
]
G
.
L
u
e
t
z
e
n
b
u
r
g
,
A
.
K
r
o
o
n
,
a
n
d
A
.
A
.
B
j
ø
r
k
,
“
Ev
a
l
u
a
t
i
o
n
o
f
t
h
e
A
p
p
l
e
i
P
h
o
n
e
1
2
P
r
o
L
i
D
A
R
f
o
r
a
n
a
p
p
l
i
c
a
t
i
o
n
i
n
g
e
o
sci
e
n
c
e
s
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
r
t
s
,
v
o
l
.
1
1
,
n
o
.
1
,
N
o
v
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
1
-
0
1
7
6
3
-
9.
[
3
3
]
Y
.
C
h
e
,
Y
.
Q
i
,
a
n
d
Y
.
S
o
n
g
,
“
R
e
a
l
-
T
i
me
3
d
h
a
n
d
g
e
s
t
u
r
e
b
a
s
e
d
m
o
b
i
l
e
i
n
t
e
r
a
c
t
i
o
n
i
n
t
e
r
f
a
c
e
,
”
i
n
Ad
j
u
n
c
t
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
2
0
1
9
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
S
y
m
p
o
s
i
u
m
o
n
Mi
x
e
d
a
n
d
Au
g
m
e
n
t
e
d
Re
a
l
i
t
y
,
I
S
MA
R
-
Ad
j
u
n
c
t
2
0
1
9
,
O
c
t
.
2
0
1
9
,
p
p
.
2
2
8
–
2
3
2
,
d
o
i
:
1
0
.
1
1
0
9
/
I
S
M
A
R
-
A
d
j
u
n
c
t
.
2
0
1
9
.
0
0
-
4
1
.
[
3
4
]
A
.
Ze
a
,
M
.
F
e
n
n
e
l
,
a
n
d
U
.
D
.
H
a
n
e
b
e
c
k
,
“
R
o
b
o
t
j
o
i
n
t
t
r
a
c
k
i
n
g
w
i
t
h
m
o
b
i
l
e
d
e
p
t
h
c
a
m
e
r
a
s
f
o
r
a
u
g
me
n
t
e
d
r
e
a
l
i
t
y
a
p
p
l
i
c
a
t
i
o
n
s,
”
i
n
2
0
2
2
2
5
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
ren
c
e
o
n
I
n
f
o
rm
a
t
i
o
n
F
u
s
i
o
n
,
FU
S
I
O
N
2
0
2
2
,
J
u
l
.
2
0
2
2
,
p
p
.
1
–
8
,
d
o
i
:
1
0
.
2
3
9
1
9
/
F
U
S
I
O
N
4
9
7
5
1
.
2
0
2
2
.
9
8
4
1
3
4
1
.
[
3
5
]
R
.
M
o
n
r
o
y
,
M
.
H
u
d
o
n
,
a
n
d
A
.
S
m
o
l
i
c
,
“
D
y
n
a
m
i
c
e
n
v
i
r
o
n
me
n
t
ma
p
p
i
n
g
f
o
r
a
u
g
me
n
t
e
d
r
e
a
l
i
t
y
a
p
p
l
i
c
a
t
i
o
n
s
o
n
mo
b
i
l
e
d
e
v
i
c
e
s
,
”
a
rXi
v
p
re
p
r
i
n
t
a
rXi
v
:
1
8
0
9
.
0
8
1
3
4
,
2
0
1
8
.
[
3
6
]
D
.
K
i
m,
S
.
C
h
o
i
,
J
.
P
a
r
k
,
a
n
d
K
.
H
.
K
o
,
“
3
D
m
o
d
e
l
a
u
g
m
e
n
t
a
t
i
o
n
u
s
i
n
g
d
e
p
t
h
i
n
f
o
r
ma
t
i
o
n
i
n
a
n
A
R
e
n
v
i
r
o
n
me
n
t
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
AC
M
S
y
m
p
o
s
i
u
m
o
n
Vi
r
t
u
a
l
Re
a
l
i
t
y
S
o
f
t
w
a
r
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
V
RS
T
,
N
o
v
.
2
0
1
8
,
p
p
.
1
–
2
,
d
o
i
:
1
0
.
1
1
4
5
/
3
2
8
1
5
0
5
.
3
2
8
1
6
0
1
.
[
3
7
]
M
.
M
i
y
a
z
a
k
i
a
n
d
T.
K
o
mu
r
o
,
“
E
x
t
e
n
d
e
d
w
o
r
k
sp
a
c
e
u
s
i
n
g
a
smar
t
p
h
o
n
e
w
i
t
h
a
d
e
p
t
h
c
a
m
e
r
a
,
”
i
n
A
d
j
u
n
c
t
Pr
o
c
e
e
d
i
n
g
s
-
2
0
1
8
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
S
y
m
p
o
s
i
u
m
o
n
Mi
x
e
d
a
n
d
Au
g
m
e
n
t
e
d
Re
a
l
i
t
y
,
I
S
MA
R
-
Ad
j
u
n
c
t
2
0
1
8
,
O
c
t
.
2
0
1
8
,
p
p
.
1
1
5
–
1
1
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
S
M
A
R
-
A
d
j
u
n
c
t
.
2
0
1
8
.
0
0
0
4
6
.
[
3
8
]
J.
K
a
st
r
e
n
a
k
e
s,
“
G
o
o
g
l
e
’
s
p
r
o
j
e
c
t
t
a
n
g
o
i
s
sh
u
t
t
i
n
g
d
o
w
n
b
e
c
a
u
s
e
A
R
C
o
r
e
i
s
a
l
r
e
a
d
y
h
e
r
e
,
”
T
h
e
Ve
r
g
e
,
2
0
2
3
.
h
t
t
p
s
:
/
/
w
w
w
.
t
h
e
v
e
r
g
e
.
c
o
m/
2
0
1
7
/
1
2
/
1
5
/
1
6
7
8
2
5
5
6
/
p
r
o
j
e
c
t
-
t
a
n
g
o
-
g
o
o
g
l
e
-
sh
u
t
t
i
n
g
-
d
o
w
n
-
a
r
c
o
r
e
-
a
u
g
m
e
n
t
e
d
-
r
e
a
l
i
t
y
.
[
3
9
]
Y
.
Z
h
a
n
g
,
T
.
S
c
a
r
g
i
l
l
,
A
.
V
a
i
s
h
n
a
v
,
G
.
P
r
e
msa
n
k
a
r
,
M
.
D
i
F
r
a
n
c
e
sc
o
,
a
n
d
M
.
G
o
r
l
a
t
o
v
a
,
“
I
n
D
e
p
t
h
:
r
e
a
l
-
t
i
m
e
d
e
p
t
h
i
n
p
a
i
n
t
i
n
g
f
o
r
mo
b
i
l
e
a
u
g
me
n
t
e
d
r
e
a
l
i
t
y
,
”
P
ro
c
e
e
d
i
n
g
s
o
f
t
h
e
A
C
M
o
n
I
n
t
e
r
a
c
t
i
v
e
,
M
o
b
i
l
e
,
W
e
a
r
a
b
l
e
a
n
d
U
b
i
q
u
i
t
o
u
s
T
e
c
h
n
o
l
o
g
i
e
s
,
v
o
l
.
6
,
n
o
.
1
,
p
p
.
1
–
2
5
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
4
5
/
3
5
1
7
2
6
0
.
[
4
0
]
S
.
N
.
J
h
a
,
“
S
m
a
r
t
p
h
o
n
e
Li
D
A
R
mar
k
e
t
,
”
2
0
2
3
.
h
t
t
p
s:
/
/
w
w
w
.
f
a
c
t
mr
.
c
o
m/
r
e
p
o
r
t
/
sm
a
r
t
p
h
o
n
e
-
l
i
d
a
r
-
mark
e
t
(
a
c
c
e
ss
e
d
F
e
b
.
2
0
,
2
0
2
4
)
.
[
4
1
]
M
.
C
.
F
.
M
a
c
E
d
o
a
n
d
A
.
L
.
A
p
o
l
i
n
a
r
i
o
,
“
O
c
c
l
u
s
i
o
n
h
a
n
d
l
i
n
g
i
n
a
u
g
me
n
t
e
d
r
e
a
l
i
t
y
:
p
a
s
t
,
p
r
e
se
n
t
a
n
d
f
u
t
u
r
e
,
”
I
EEE
T
r
a
n
sa
c
t
i
o
n
s
o
n
Vi
s
u
a
l
i
za
t
i
o
n
a
n
d
C
o
m
p
u
t
e
r Gr
a
p
h
i
c
s
,
v
o
l
.
2
9
,
n
o
.
2
,
p
p
.
1
5
9
0
–
1
6
0
9
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
TV
C
G
.
2
0
2
1
.
3
1
1
7
8
6
6
.
[
4
2
]
J.
V
a
l
e
n
t
i
n
e
t
a
l
.
,
“
D
e
p
t
h
f
r
o
m
m
o
t
i
o
n
f
o
r
smar
t
p
h
o
n
e
A
R
,
”
S
I
G
G
RAPH
Asi
a
2
0
1
8
T
e
c
h
n
i
c
a
l
Pa
p
e
rs,
S
I
G
G
RAPH
As
i
a
2
0
1
8
,
v
o
l
.
3
7
,
n
o
.
6
,
p
p
.
1
–
1
9
,
D
e
c
.
2
0
1
8
,
d
o
i
:
1
0
.
1
1
4
5
/
3
2
7
2
1
2
7
.
3
2
7
5
0
4
1
.
[
4
3
]
“
D
e
p
t
h
A
d
d
s
R
e
a
l
i
sm |
A
R
C
o
r
e
|
G
o
o
g
l
e
D
e
v
e
l
o
p
e
r
s
.
”
h
t
t
p
s:
/
/
d
e
v
e
l
o
p
e
r
s
.
g
o
o
g
l
e
.
c
o
m/
a
r
/
d
e
v
e
l
o
p
/
d
e
p
t
h
(
a
c
c
e
sse
d
A
p
r
.
1
6
,
2
0
2
3
)
.
[
4
4
]
R
.
D
u
e
t
a
l
.
,
“
D
e
p
t
h
La
b
:
r
e
a
l
-
t
i
me
3
D
i
n
t
e
r
a
c
t
i
o
n
w
i
t
h
d
e
p
t
h
m
a
p
s
f
o
r
mo
b
i
l
e
a
u
g
m
e
n
t
e
d
r
e
a
l
i
t
y
,
”
i
n
U
I
S
T
2
0
2
0
-
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
3
3
r
d
A
n
n
u
a
l
AC
M
S
y
m
p
o
s
i
u
m
o
n
U
s
e
r
I
n
t
e
r
f
a
c
e
S
o
f
t
w
a
re
a
n
d
T
e
c
h
n
o
l
o
g
y
,
O
c
t
.
2
0
2
0
,
p
p
.
8
2
9
–
8
4
3
,
d
o
i
:
1
0
.
1
1
4
5
/
3
3
7
9
3
3
7
.
3
4
1
5
8
8
1
.
[
4
5
]
F
.
A
l
e
o
t
t
i
,
G
.
Za
c
c
a
r
o
n
i
,
L.
B
a
r
t
o
l
o
m
e
i
,
M
.
P
o
g
g
i
,
F
.
T
o
s
i
,
a
n
d
S
.
M
a
t
t
o
c
c
i
a
,
“
R
e
a
l
-
t
i
me
s
i
n
g
l
e
i
ma
g
e
d
e
p
t
h
p
e
r
c
e
p
t
i
o
n
i
n
t
h
e
w
i
l
d
w
i
t
h
h
a
n
d
h
e
l
d
d
e
v
i
c
e
s,
”
S
e
n
so
rs
(
S
w
i
t
zerl
a
n
d
)
,
v
o
l
.
2
1
,
n
o
.
1
,
p
p
.
1
–
1
7
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
1
0
1
0
0
1
5
.
[
4
6
]
T.
E
l
sk
e
n
,
J.
H
.
M
e
t
z
e
n
,
a
n
d
F
.
H
u
t
t
e
r
,
“
N
e
u
r
a
l
a
r
c
h
i
t
e
c
t
u
r
e
s
e
a
r
c
h
,
”
i
n
J
o
u
rn
a
l
o
f
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
R
e
se
a
rc
h
,
v
o
l
.
2
0
,
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
9
,
p
p
.
1
--
2
1
.
[
4
7
]
N
.
S
i
l
b
e
r
m
a
n
,
D
.
H
o
i
e
m,
P
.
K
o
h
l
i
,
a
n
d
R
.
F
e
r
g
u
s,
“
I
n
d
o
o
r
s
e
g
m
e
n
t
a
t
i
o
n
a
n
d
su
p
p
o
r
t
i
n
f
e
r
e
n
c
e
f
r
o
m
R
G
B
D
i
m
a
g
e
s,”
i
n
L
e
c
t
u
r
e
N
o
t
e
s
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
i
n
c
l
u
d
i
n
g
s
u
b
ser
i
e
s
L
e
c
t
u
r
e
N
o
t
e
s
i
n
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
L
e
c
t
u
re
N
o
t
e
s
i
n
Bi
o
i
n
f
o
rm
a
t
i
c
s)
,
v
o
l
.
7
5
7
6
LN
C
S
,
n
o
.
P
A
R
T
5
,
S
p
r
i
n
g
e
r
B
e
r
l
i
n
H
e
i
d
e
l
b
e
r
g
,
2
0
1
2
,
p
p
.
7
4
6
–
7
6
0
.
[
4
8
]
F
.
Ta
p
i
a
B
e
n
a
v
i
d
e
s,
A
.
I
g
n
a
t
o
v
,
a
n
d
R
.
T
i
mo
f
t
e
,
“
P
h
o
n
e
D
e
p
t
h
:
a
d
a
t
a
se
t
f
o
r
mo
n
o
c
u
l
a
r
d
e
p
t
h
e
s
t
i
mat
i
o
n
o
n
m
o
b
i
l
e
d
e
v
i
c
e
s,”
i
n
I
EEE
C
o
m
p
u
t
e
r
S
o
c
i
e
t
y
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
V
i
si
o
n
a
n
d
P
a
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
W
o
rks
h
o
p
s
,
J
u
n
.
2
0
2
2
,
v
o
l
.
2
0
2
2
-
J
u
n
e
,
p
p
.
3
0
4
8
–
3
0
5
5
,
d
o
i
:
1
0
.
1
1
0
9
/
C
V
P
R
W
5
6
3
4
7
.
2
0
2
2
.
0
0
3
4
4
.
[
4
9
]
D
.
S
c
h
a
r
s
t
e
i
n
e
t
a
l
.
,
“
H
i
g
h
-
r
e
s
o
l
u
t
i
o
n
st
e
r
e
o
d
a
t
a
s
e
t
s
w
i
t
h
s
u
b
p
i
x
e
l
-
a
c
c
u
r
a
t
e
g
r
o
u
n
d
t
r
u
t
h
,
”
i
n
L
e
c
t
u
re
N
o
t
e
s
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
i
n
c
l
u
d
i
n
g
s
u
b
s
e
ri
e
s
L
e
c
t
u
re
N
o
t
e
s
i
n
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
L
e
c
t
u
r
e
N
o
t
e
s
i
n
Bi
o
i
n
f
o
rm
a
t
i
c
s)
,
v
o
l
.
8
7
5
3
,
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
4
,
p
p
.
3
1
–
4
2
.
[
5
0
]
C
.
M
o
s
t
e
g
e
l
,
M
.
R
u
mp
l
e
r
,
F
.
F
r
a
u
n
d
o
r
f
e
r
,
a
n
d
H
.
B
i
sc
h
o
f
,
“
U
si
n
g
se
l
f
-
c
o
n
t
r
a
d
i
c
t
i
o
n
t
o
l
e
a
r
n
c
o
n
f
i
d
e
n
c
e
m
e
a
s
u
r
e
s
i
n
s
t
e
r
e
o
v
i
s
i
o
n
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
I
EEE
C
o
m
p
u
t
e
r
S
o
c
i
e
t
y
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
P
a
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
,
J
u
n
.
2
0
1
6
,
v
o
l
.
2
0
1
6
-
D
e
c
e
m,
p
p
.
4
0
6
7
–
4
0
7
6
,
d
o
i
:
1
0
.
1
1
0
9
/
C
V
P
R
.
2
0
1
6
.
4
4
1
.
[
5
1
]
Z.
Li
a
n
d
N
.
S
n
a
v
e
l
y
,
“
M
e
g
a
D
e
p
t
h
:
l
e
a
r
n
i
n
g
s
i
n
g
l
e
-
v
i
e
w
d
e
p
t
h
p
r
e
d
i
c
t
i
o
n
f
r
o
m
i
n
t
e
r
n
e
t
p
h
o
t
o
s
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
I
EEE
C
o
m
p
u
t
e
r
S
o
c
i
e
t
y
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
Vi
s
i
o
n
a
n
d
P
a
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
,
J
u
n
.
2
0
1
8
,
p
p
.
2
0
4
1
–
2
0
5
0
,
d
o
i
:
1
0
.
1
1
0
9
/
C
V
P
R
.
2
0
1
8
.
0
0
2
1
8
.
[
5
2
]
A
.
G
e
i
g
e
r
,
P
.
Le
n
z
,
C
.
S
t
i
l
l
e
r
,
a
n
d
R
.
U
r
t
a
s
u
n
,
“
V
i
s
i
o
n
mee
t
s
r
o
b
o
t
i
c
s:
T
h
e
K
I
TTI
d
a
t
a
se
t
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
R
o
b
o
t
i
c
s
Re
se
a
rc
h
,
v
o
l
.
3
2
,
n
o
.
1
1
,
p
p
.
1
2
3
1
–
1
2
3
7
,
A
u
g
.
2
0
1
3
,
d
o
i
:
1
0
.
1
1
7
7
/
0
2
7
8
3
6
4
9
1
3
4
9
1
2
9
7
.
[
5
3
]
T.
O
g
a
w
a
a
n
d
T
.
M
a
s
h
i
t
a
,
“
O
c
c
l
u
si
o
n
h
a
n
d
l
i
n
g
i
n
o
u
t
d
o
o
r
a
u
g
me
n
t
e
d
r
e
a
l
i
t
y
u
s
i
n
g
a
c
o
mb
i
n
a
t
i
o
n
o
f
ma
p
d
a
t
a
a
n
d
i
n
st
a
n
c
e
seg
m
e
n
t
a
t
i
o
n
,
”
i
n
Pro
c
e
e
d
i
n
g
s
-
2
0
2
1
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
S
y
m
p
o
s
i
u
m
o
n
M
i
x
e
d
a
n
d
A
u
g
m
e
n
t
e
d
Re
a
l
i
t
y
A
d
j
u
n
c
t
,
I
S
MA
R
-
Ad
j
u
n
c
t
2
0
2
1
,
O
c
t
.
2
0
2
1
,
p
p
.
2
4
6
–
2
5
0
,
d
o
i
:
1
0
.
1
1
0
9
/
I
S
M
A
R
-
A
d
j
u
n
c
t
5
4
1
4
9
.
2
0
2
1
.
0
0
0
5
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.