I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
p
u
t
er
Science
Vo
l.
1
2
,
No
.
2
,
N
o
v
e
m
b
er
201
8
,
p
p
.
5
8
5
~
5
9
1
I
SS
N:
2502
-
4752
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ee
cs
.
v
1
2
.i
2
.
p
p
585
-
5
9
1
585
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e.
co
m/jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
ijeec
s
I
m
ple
m
e
ntatio
n o
f
Ste
reo Vis
io
n S
e
m
i
-
G
lo
ba
l Blo
c
k
M
a
tching
M
ethods
f
o
r
Dist
a
nce Mea
sure
m
e
nt
Ra
den Ar
ief
Set
y
a
w
a
n
1
,
Rudy
Su
no
k
o
2
,
M
o
cha
m
m
a
d Ag
us
Cho
iro
n
3
,
P
a
nca
M
ud
j
i R
a
ha
rdj
o
4
1,
4
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
De
p
a
rtm
e
n
t,
Bra
w
ij
a
y
a
Un
iv
e
r
sit
y
,
In
d
o
n
e
sia
2,
3
M
e
c
h
a
n
ica
l
E
n
g
in
e
e
rin
g
De
p
a
rt
m
e
n
t,
Bra
w
ij
a
y
a
Un
iv
e
rsit
y
,
In
d
o
n
e
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
y
9
,
2
0
1
8
R
ev
i
s
ed
J
u
l
1
2
,
2
0
1
8
A
cc
ep
ted
Ju
l
2
1
,
2
0
1
8
S
tere
o
v
isio
n
h
a
s
b
e
c
o
m
e
a
n
a
tt
ra
c
ti
v
e
to
p
ic
re
se
a
rc
h
in
th
e
las
t
d
e
c
a
d
e
s.
M
a
n
y
i
m
p
le
m
e
n
tatio
n
s
su
c
h
a
s
t
h
e
a
u
t
o
n
o
m
o
u
s
c
a
r,
3
D
m
o
v
ie,
3
D
o
b
jec
t
g
e
n
e
ra
ti
o
n
,
a
re
p
r
o
d
u
c
e
d
u
si
n
g
t
h
is
tec
h
n
i
q
u
e
.
T
h
e
a
d
v
a
n
tag
e
s
o
f
u
sin
g
tw
o
c
a
m
e
ra
s
in
ste
re
o
v
isio
n
a
re
th
e
d
isp
a
rit
y
m
a
p
b
e
t
w
e
e
n
i
m
a
g
e
s.
Disp
a
rit
y
m
a
p
w
il
l
p
ro
d
u
c
e
d
istan
c
e
e
stim
a
ti
o
n
o
f
th
e
o
b
jec
t.
Dista
n
c
e
m
e
a
s
u
re
m
e
n
t
is
a
c
ru
c
ial
p
a
ra
m
e
ter
f
o
r
a
n
a
u
to
n
o
m
o
u
s
c
a
r.
T
h
e
d
istan
c
e
b
e
tw
e
e
n
c
o
rre
sp
o
n
d
in
g
p
o
i
n
ts
b
e
tw
e
e
n
th
e
lef
t
a
n
d
rig
h
t
im
a
g
e
s
m
u
st
b
e
p
re
c
ise
l
y
m
e
a
su
re
d
to
g
e
t
a
n
a
c
c
u
ra
te
d
ista
n
c
e
.
On
e
o
f
th
e
m
o
st
c
h
a
ll
e
n
g
in
g
in
ste
re
o
v
isio
n
is
to
f
in
d
c
o
rre
sp
o
n
d
in
g
p
o
in
ts
b
e
tw
e
e
n
le
f
t
a
n
d
rig
h
t
i
m
a
g
e
s
(
ste
re
o
m
a
tch
in
g
).
T
h
is
p
a
p
e
r
p
ro
p
o
se
d
d
istan
c
e
m
e
a
su
re
m
e
n
t
u
sin
g
ste
re
o
v
isio
n
u
sin
g
S
e
m
i
-
G
lo
b
a
l
Blo
c
k
M
a
tch
in
g
a
lg
o
rit
h
m
f
o
r
ste
re
o
m
a
tch
in
g
p
u
rp
o
se
.
T
h
e
o
b
jec
t
is
c
a
p
tu
re
d
u
sin
g
a
c
a
l
ib
ra
ted
ste
re
o
c
a
m
e
ra
.
T
h
e
i
m
a
g
e
s
p
a
ir
th
e
n
o
p
ti
m
ize
d
u
sin
g
W
L
S
F
il
ter
to
re
d
u
c
e
n
o
ise
s.
T
h
e
im
p
le
m
e
n
tatio
n
re
su
lt
s
o
f
th
is
a
lg
o
rit
h
m
a
re
f
u
rth
e
rm
o
re
c
o
n
v
e
rted
to
a
m
e
tri
c
u
n
it
fo
r
d
istan
c
e
m
e
a
su
re
m
e
n
t.
T
h
e
re
su
lt
s
h
o
w
s
th
a
t
th
e
ste
re
o
v
isio
n
d
istan
c
e
m
e
a
su
re
m
e
n
t
u
sin
g
S
e
m
i
-
G
lo
b
a
l
Blo
c
k
M
a
tch
in
g
g
iv
e
s
a
g
o
o
d
re
su
lt
.
T
h
e
o
b
t
a
in
e
d
b
e
st
re
su
lt
o
f
th
is
w
o
rk
c
o
n
tai
n
s erro
r
o
f
les
s th
a
n
1
%
f
o
r
1
m
d
istan
c
e
K
ey
w
o
r
d
s
:
Dis
ta
n
c
e
Me
as
u
r
e
m
e
n
t
Ster
eo
Ma
tch
in
g
Ster
eo
Vis
io
n
Co
p
y
rig
h
t
©
2
0
1
8
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
R
ad
en
A
r
ie
f
Set
y
a
w
an
,
E
lectr
ical
E
n
g
i
n
ee
r
i
n
g
Dep
ar
t
m
en
t
,
B
r
a
w
ij
ay
a
U
n
i
v
er
s
it
y
,
I
n
d
o
n
e
s
ia
.
E
m
ail:
r
ar
ief
@
u
b
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
d
ev
elo
p
m
e
n
t
o
f
d
ig
ital
i
m
ag
e
tec
h
n
o
lo
g
y
n
o
w
ad
a
y
s
is
g
r
o
w
i
n
g
r
ap
id
ly
.
Hi
g
h
er
ca
m
er
a
q
u
alit
y
,
f
aster
i
m
ag
e
p
r
o
ce
s
s
i
n
g
tec
h
n
o
lo
g
y
,
a
n
d
i
m
a
g
e
p
r
o
ce
s
s
in
g
m
et
h
o
d
s
g
i
v
e
a
s
ig
n
i
f
ica
n
t
i
m
p
ac
t
to
th
e
d
aily
h
u
m
a
n
li
f
e.
O
n
e
o
f
th
e
m
o
s
t
attr
ac
tiv
e
r
ese
ar
c
h
i
n
d
ig
ital
i
m
a
g
e
tec
h
n
o
lo
g
y
is
S
ter
eo
Vis
io
n
/3
D
i
m
a
g
i
n
g
.
Ster
eo
v
is
io
n
i
s
a
m
et
h
o
d
to
f
o
r
m
3
-
d
i
m
e
n
s
io
n
al
i
m
a
g
es
u
s
in
g
t
w
o
ca
m
er
as.
T
h
is
m
et
h
o
d
w
ill
g
e
n
er
ate
a
d
ep
th
m
ap
w
h
ic
h
p
r
o
v
id
es
i
n
f
o
r
m
at
io
n
ab
o
u
t
t
h
e
d
is
tan
ce
b
et
w
ee
n
an
o
b
j
ec
t
an
d
th
e
ca
m
er
a.
Ho
w
e
v
er
,
th
e
d
is
tan
ce
o
b
tain
ed
in
t
h
is
m
ea
s
u
r
e
m
en
t
i
s
s
til
l
li
m
ited
to
th
e
ass
u
m
p
tio
n
o
f
th
e
o
b
j
ec
t'
s
p
r
o
x
i
m
it
y
.
Dis
ta
n
ce
m
ea
s
u
r
e
m
e
n
t
i
s
ess
e
n
tial
i
n
v
ar
io
u
s
ap
p
licatio
n
s
,
s
u
ch
as
r
o
b
o
tics
,
au
to
n
o
m
o
u
s
ca
r
,
an
d
s
o
f
o
r
th
.
Se
v
er
al
p
r
ev
io
u
s
s
t
u
d
ies
h
a
v
e
atte
m
p
t
e
d
to
m
ea
s
u
r
e
d
i
s
ta
n
ce
u
s
i
n
g
s
ter
eo
v
i
s
io
n
.
T
j
an
d
r
an
eg
ar
a
e
t
al.
o
f
f
er
a
m
eth
o
d
f
o
r
esti
m
ati
n
g
th
e
d
is
tan
ce
b
et
w
ee
n
o
b
j
ec
ts
b
y
u
s
i
n
g
t
w
o
ca
m
er
as
[
1
]
.
T
h
e
m
et
h
o
d
o
f
f
er
ed
is
p
u
r
e
o
f
m
at
h
e
m
a
tical
ca
lc
u
latio
n
s
w
it
h
o
u
t
i
m
p
le
m
e
n
tatio
n
.
Mr
o
v
lj
e
et
al.
atte
m
p
ted
to
ap
p
l
y
d
is
t
an
ce
m
ea
s
u
r
e
m
e
n
t
s
to
m
ea
s
u
r
e
o
b
j
ec
ts
w
ith
d
is
tan
ce
s
b
et
w
ee
n
1
0
m
-
6
0
m
[
2
]
.
Ma
h
a
m
m
ed
,
in
an
o
t
h
er
s
tu
d
y
,
w
as
co
m
p
ar
i
n
g
s
ter
eo
v
is
io
n
m
ea
s
u
r
e
m
e
n
t
s
with
a
d
i
g
ital
la
s
er
r
an
g
e
-
f
i
n
d
er
[
3
]
.
T
h
e
m
ea
s
u
r
e
m
e
n
t
o
f
d
is
p
ar
it
y
h
as
b
ee
n
d
o
n
e
u
tili
zi
n
g
t
h
e
Fas
t
Ma
tc
h
in
g
u
s
in
g
C
r
o
s
s
-
C
o
r
r
elatio
n
B
a
s
ed
S
u
m
-
of
-
Sq
u
ar
ed
Di
f
f
er
en
ce
s
m
et
h
o
d
.
T
h
is
r
esear
ch
g
i
v
es t
h
e
r
elati
v
e
m
e
asu
r
e
m
en
t e
r
r
o
r
b
et
w
ee
n
1
.
1
3
% a
n
d
2
.
0
5
%.
B
ased
o
n
t
h
e
p
r
ev
io
u
s
w
o
r
k
,
o
n
e
o
f
th
e
m
o
s
t
i
m
p
o
r
tan
t
s
tep
s
to
m
ai
n
tai
n
th
e
a
c
cu
r
ac
y
o
f
m
ea
s
u
r
e
m
e
n
t
is
t
h
e
s
ter
eo
m
a
tch
i
n
g
m
et
h
o
d
.
Ster
eo
m
atc
h
i
n
g
is
a
m
et
h
o
d
to
f
i
n
d
co
r
r
esp
o
n
d
in
g
p
o
in
ts
i
n
a
p
air
o
f
im
a
g
es.
C
o
r
r
esp
o
n
d
in
g
p
o
in
ts
ca
n
b
e
r
ec
o
g
n
ized
th
r
o
u
g
h
s
ev
er
al
ef
f
icien
t
m
atc
h
i
n
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
1
2
,
No
.
2
,
No
v
e
m
b
er
201
8
:
5
8
5
–
5
9
1
586
alg
o
r
ith
m
s
[
4
]
,
[
5
]
.
T
h
e
q
u
alit
y
o
f
s
ter
eo
m
atch
in
g
r
elate
d
t
o
m
ea
s
u
r
e
m
e
n
t
ac
cu
r
ac
y
.
Se
m
i
-
Glo
b
al
Ma
tc
h
in
g
,
in
itial
l
y
p
r
o
p
o
s
ed
b
y
Hir
s
ch
m
u
ller
,
h
a
s
p
r
o
v
en
as
a
p
o
w
er
f
u
l
s
ter
eo
m
atc
h
i
n
g
a
lg
o
r
ith
m
f
o
r
v
ar
io
u
s
ap
p
licatio
n
.
T
h
is
m
et
h
o
d
m
in
i
m
izes a
g
lo
b
al
co
s
t f
u
n
c
tio
n
i
n
o
n
e
d
i
m
en
s
io
n
.
T
h
is
s
tu
d
y
ai
m
s
to
test
th
e
ac
cu
r
ac
y
o
f
d
is
ta
n
ce
m
ea
s
u
r
e
m
en
t
u
s
in
g
s
ter
eo
v
i
s
io
n
with
SGB
M
A
l
g
o
r
ith
m
i
n
s
ter
eo
m
atch
i
n
g
p
r
o
ce
s
s
.
I
n
th
is
w
o
r
k
,
t
w
o
L
o
g
itec
h
w
eb
ca
m
er
as
p
r
ep
ar
ed
as
th
e
s
ter
eo
ca
m
er
a.
T
h
e
C
a
m
er
a
ca
lib
r
ati
o
n
is
a
cr
itical
s
tep
to
g
et
ep
i
p
o
lar
lin
es
b
et
w
ee
n
i
m
ag
e
s
p
a
ir
.
I
t
m
u
s
t
b
e
d
o
n
e
b
ef
o
r
e
th
e
m
ea
s
u
r
e
m
en
t
p
r
o
ce
s
s
tak
e
s
p
lace
s
.
P
air
o
f
im
a
g
es
ca
p
tu
r
ed
b
y
th
e
ca
m
er
a
is
p
r
o
ce
s
s
ed
u
s
i
n
g
Ster
eo
Glo
b
al
B
lo
ck
Ma
tc
h
in
g
(
SGB
M)
.
SGB
M
i
s
a
m
o
d
i
f
ied
v
er
s
io
n
o
f
th
e
Se
m
i
-
Glo
b
al
Ma
tch
i
n
g
(
SB
M)
alg
o
r
ith
m
p
r
o
p
o
s
ed
b
y
Hir
s
ch
m
u
ller
[
6
]
,
[
7
]
.
T
h
e
i
m
p
l
e
m
en
tatio
n
o
f
t
h
i
s
m
et
h
o
d
u
s
i
n
g
t
h
e
Op
e
n
C
V
L
ib
r
ar
y
[
8
]
.
Nex
t,
th
e
W
L
S
Fil
ter
u
s
ed
to
o
p
ti
m
ize
t
h
e
o
u
tp
u
t
o
f
s
ter
eo
m
atc
h
i
n
g
[
9
]
.
Me
asu
r
e
m
e
n
t
ca
lib
r
atio
n
n
ee
d
ed
to
co
n
v
er
t
f
r
o
m
p
i
x
el
d
i
s
tan
ce
to
m
etr
ic
s
u
n
i
t.
S
u
b
s
eq
u
e
n
tl
y
,
t
h
e
o
b
tai
n
ed
d
ata
o
f
t
h
e
p
ix
e
l
d
is
tan
ce
ar
e
co
n
v
er
ted
in
to
m
etr
ics
u
n
i
t.
T
h
e
ca
lib
r
atio
n
r
e
s
u
lt
is
ca
lc
u
lated
to
f
i
n
d
t
h
e
r
eg
r
ess
io
n
f
o
r
m
u
la.
T
h
is
f
o
r
m
u
la
t
h
e
n
ap
p
lied
in
t
h
e
co
n
v
er
s
io
n
o
f
t
h
e
d
is
p
ar
it
y
v
al
u
e
to
th
e
m
etr
ic
u
n
it.
T
h
is
s
y
s
te
m
test
ed
w
i
th
an
o
th
er
o
b
j
ec
t a
n
d
d
is
tan
ce
v
a
r
iatio
n
to
f
i
n
d
th
e
m
ea
s
u
r
e
m
e
n
t a
cc
u
r
ac
y
.
2.
ST
E
RE
O
V
I
SI
O
N
C
h
ar
le
s
W
h
ea
t
s
to
n
e
in
itiated
th
e
r
esear
c
h
o
n
s
ter
eo
v
is
io
n
/
s
ter
eo
s
co
p
ic
m
ea
s
u
r
e
m
e
n
t
i
n
1
8
3
8
b
y
in
v
e
n
ti
n
g
s
ter
eo
i
m
a
g
es
u
s
in
g
eq
u
ip
m
e
n
t
to
v
ie
w
t
h
e
m
.
T
w
o
lef
t,
a
n
d
r
ig
h
t
ca
m
er
as
ar
e
u
s
ed
to
m
i
m
ic
t
h
e
h
u
m
a
n
e
y
e
an
d
p
lace
d
at
a
ce
r
tain
d
is
ta
n
ce
[
2
]
.
Ass
u
m
i
n
g
t
h
a
t b
o
th
ca
m
er
as a
r
e
p
er
f
ec
t
l
y
a
lig
n
ed
,
t
w
o
i
m
a
g
e
s
f
r
o
m
th
e
le
f
t
an
d
r
ig
h
t
ca
m
e
r
as
ar
e
ca
p
tu
r
ed
w
it
h
d
if
f
er
e
n
t
an
g
les.
F
u
r
th
er
m
o
r
e,
b
o
th
i
m
a
g
es
ar
e
u
s
ed
to
ca
lcu
late
t
h
e
d
is
ta
n
ce
b
et
w
ee
n
o
b
j
ec
ts
w
it
h
t
h
e
ca
m
er
a
u
s
i
n
g
tr
ig
o
n
o
m
e
tr
ic
p
r
in
cip
les.
Fig
u
r
e
1
d
escr
i
b
es
t
h
e
b
asic
p
r
in
cip
le
o
f
d
is
ta
n
ce
m
ea
s
u
r
e
m
en
t.
A
s
it
i
n
d
icate
s
,
C
1
r
ep
r
esen
ts
th
e
lef
t
ca
m
er
a,
an
d
C
2
r
ep
r
esen
ts
t
h
e
r
ig
h
t
ca
m
er
a.
T
h
e
B
ase
(
B
)
r
ep
r
esen
ts
t
h
e
d
is
tan
ce
b
et
w
ee
n
t
h
e
t
w
o
ca
m
er
as.
D
is
t
h
e
d
is
ta
n
ce
b
et
w
ee
n
t
h
e
Ob
j
ec
t a
n
d
th
e
ca
m
e
r
as.
T
h
e
an
g
le
φ0
is
t
h
e
v
ie
w
an
g
le
o
f
th
e
ca
m
er
a.
T
h
e
an
g
les φ1
an
d
φ2
ar
e
th
e
an
g
le
s
b
et
w
ee
n
t
h
e
n
o
r
m
al
v
ie
w
a
n
d
th
e
o
b
j
ec
t lo
ca
tio
n
s
.
Fig
u
r
e
1
.
T
h
e
Ster
eo
Vis
io
n
lay
o
u
t
T
h
e
Dis
tan
ce
(
D)
ca
n
b
e
ca
lcu
lated
u
s
i
n
g
t
h
e
b
asic tr
i
g
o
n
o
m
etr
y
as f
o
llo
w
s
.
(
1
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
I
mp
leme
n
ta
tio
n
o
f
S
tereo
V
is
io
n
S
emi
-
Glo
b
a
l B
lo
ck
Ma
tch
i
n
g
Meth
o
d
s
…
(
R
a
d
en
A
r
ief
S
etya
w
a
n
)
587
(
)
(
)
(
2
)
T
h
e
Dis
tan
ce
(
D)
ca
n
b
e
f
o
u
n
d
o
u
t
u
s
i
n
g
E
q
u
atio
n
2
if
th
e
d
is
tan
ce
b
et
w
ee
n
t
h
e
ca
m
er
as
(
B
)
,
th
e
v
ie
w
a
n
g
le
o
f
th
e
ca
m
er
a
(
φ0
)
an
d
th
e
d
is
p
ar
it
y
o
f
t
h
e
o
b
j
e
ct
f
r
o
m
t
h
e
lef
t
an
d
th
e
r
i
g
h
t
ca
m
er
as
ar
e
k
n
o
w
n
.
T
h
e
r
esu
lt
is
e
x
p
r
ess
ed
i
n
p
ix
els.
C
o
n
v
er
tin
g
t
h
e
p
ix
el
n
u
m
b
er
in
to
m
etr
ic
s
u
n
it
r
eq
u
ir
es
a
r
ef
er
e
n
ce
ca
lib
r
atio
n
.
3.
SE
M
I
-
G
L
O
B
AL
B
L
O
CK
M
AT
CH
I
N
G
AN
D
WL
S F
I
L
T
E
R
Se
m
i
-
Glo
b
al
m
atch
in
g
m
et
h
o
d
o
b
j
ec
tiv
e
is
to
m
i
n
i
m
ize
th
e
co
s
t
f
u
n
ctio
n
o
f
Glo
b
a
l
m
atc
h
i
n
g
m
et
h
o
d
.
E
q
u
atio
n
3
d
escr
ib
e
th
e
g
lo
b
al
co
s
t f
u
n
ctio
n
[
7
]
(
)
∑
(
(
)
∑
|
|
|
|
∑
|
|
|
|
)
(
3
)
C
(
p
,
Dp
)
is
t
h
e
s
u
m
o
f
a
p
i
x
el
-
w
i
s
e
m
atc
h
in
g
co
s
t
f
o
r
p
ix
el
p
at
th
e
ir
d
is
p
ar
it
y
Dp
.
T
h
e
F
u
n
ct
io
n
T
w
il
l
r
esu
lt
in
1
i
f
it
s
ar
g
u
m
e
n
t
is
tr
u
e,
an
d
0
if
f
al
s
e.
Np
is
t
h
e
n
ei
g
h
b
o
r
in
g
p
i
x
el
o
f
p
w
it
h
th
e
co
s
t
P
1
.
P2
is
ad
ap
ted
to
th
e
lo
ca
l
in
ten
s
it
y
g
r
ad
ien
t
f
o
r
th
e
n
ei
g
h
b
o
r
in
g
p
ix
el
p
an
d
q
.
SGM
ca
lcu
late
s
E
(
D)
alo
n
g
w
it
h
th
e
1
D
p
ath
f
r
o
m
8
d
ir
ec
tio
n
s
to
war
d
ea
ch
p
ix
el
o
f
in
ter
e
s
t (
Fi
g
u
r
e
2
)
.
Fig
u
r
e
2
.
P
ath
Dir
ec
tio
n
o
f
SG
M
T
h
e
C
o
s
t
o
f
all
p
ath
is
s
u
m
m
ed
f
o
r
ea
ch
p
ix
el
a
n
d
d
is
p
ar
it
y
.
T
h
e
d
is
p
ar
it
y
i
s
t
h
e
n
d
eter
m
i
n
ed
b
y
w
i
n
n
er
-
ta
k
es
-
All
p
r
in
cip
le.
T
h
e
i
m
p
le
m
e
n
tatio
n
o
f
t
h
e
SG
M
m
et
h
o
d
in
t
h
is
w
o
r
k
u
ti
liz
ed
SGB
M
lib
r
ar
y
o
f
Op
en
C
V
[
1
0
]
.
SGB
M
is
a
m
o
d
i
f
ied
v
er
s
io
n
o
f
th
e
SG
M
Me
th
o
d
w
i
th
th
e
ad
d
itio
n
al
p
ar
a
m
eter
to
li
m
i
t
d
is
p
ar
it
y
v
al
u
e,
w
in
d
o
w
s
s
ize
an
d
u
n
iq
u
en
e
s
s
r
atio
.
T
h
e
n
ex
t
s
tep
is
t
h
e
n
o
is
e
s
m
i
n
i
m
i
za
tio
n
b
y
u
s
in
g
th
e
W
eig
h
ted
L
ea
s
t Sq
u
ar
es
f
ilter
[
9
]
.
4.
E
XP
E
R
I
M
E
NT
T
h
e
ex
p
er
i
m
en
t
p
r
o
ce
d
u
r
e
b
ein
g
p
er
f
o
r
m
ed
o
n
t
h
i
s
w
o
r
k
i
s
d
escr
ib
ed
in
Fi
g
u
r
e
3
.
T
h
e
s
te
r
eo
i
m
ag
e
s
ar
e
p
r
o
d
u
ce
d
u
s
in
g
t
w
o
L
o
g
it
ec
h
9
2
0
USB
w
eb
ca
m
s
.
T
h
e
d
is
tan
ce
b
et
w
ee
n
t
h
e
t
w
o
ca
m
er
as
is
1
0
c
m
.
B
ased
o
n
th
e
tr
ig
o
n
o
m
etr
y
ca
lc
u
lati
o
n
p
r
in
cip
le,
t
h
e
r
an
g
e
o
f
d
i
s
tan
ce
m
ea
s
u
r
e
m
e
n
t
i
s
r
elate
d
to
th
e
d
is
ta
n
ce
b
et
w
ee
n
th
e
t
w
o
s
ter
eo
ca
m
e
r
as.
W
ith
1
0
cm
o
f
d
is
ta
n
ce
,
th
e
ex
p
ec
ted
m
ea
s
u
r
e
m
en
t
r
an
g
e
i
s
in
b
et
w
ee
n
5
0
cm
to
1
8
0
c
m
.
T
h
e
v
ie
w
a
n
g
le
o
f
t
h
i
s
w
eb
ca
m
is
7
8
d
eg
r
ee
s
.
T
h
is
w
id
e
a
n
g
le
i
n
cr
ea
s
es
t
h
e
p
o
s
s
ib
ili
t
y
o
f
im
a
g
e
d
is
to
r
tio
n
; t
h
er
ef
o
r
e,
th
e
ca
m
er
a
ca
lib
r
atio
n
is
es
s
en
t
i
al.
Fig
u
r
e
3
.
T
h
e
d
is
tan
ce
m
ea
s
u
r
e
m
en
t
p
r
o
ce
d
u
r
e
R
i
g
ht
C
am
Le
f
t
C
am
C
am
e
r
a
R
e
c
t
i
f
y
&
Und
i
st
o
r
t
P
o
i
nt
o
f
Int
e
r
e
st
S
e
l
e
c
t
i
o
n
S
t
e
r
e
o
M
at
c
hi
ng
W
LS
F
i
l
t
e
r
D
i
sp
ar
i
t
y
&
D
i
st
an
c
e
M
e
as
ur
e
m
e
nt
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
1
2
,
No
.
2
,
No
v
e
m
b
er
201
8
:
5
8
5
–
5
9
1
588
T
h
e
ca
m
er
a
ca
lib
r
atio
n
i
s
r
eq
u
ir
ed
to
en
s
u
r
e
t
h
at
b
o
th
ca
m
er
as
ar
e
i
n
p
er
f
ec
t
p
ar
allel
p
o
s
iti
o
n
an
d
to
r
e
m
o
v
e
d
is
to
r
tio
n
[
1
1
]
.
C
am
er
a
ca
lib
r
atio
n
also
g
en
er
ates
t
h
e
ep
ip
o
lar
lin
es
b
et
w
ee
n
co
r
r
esp
o
n
d
in
g
p
o
in
ts
o
n
i
m
a
g
es
p
air
.
T
h
ese
lin
e
s
c
h
an
g
e
t
h
e
co
m
p
le
x
it
y
o
f
s
ea
r
ch
i
n
g
f
r
o
m
2
D
to
1
D,
r
esu
lti
n
g
in
less
s
ea
r
ch
i
n
g
ti
m
e.
T
h
e
ca
lib
r
atio
n
is
p
er
f
o
r
m
ed
u
s
in
g
t
h
e
s
ta
n
d
ar
d
ch
es
s
-
b
o
ar
d
p
ictu
r
e.
Fi
g
u
r
e
4
a
n
d
F
ig
u
r
e
5
d
is
p
la
y
s
th
e
i
m
ag
e
ca
lib
r
atio
n
p
r
o
ce
s
s
.
T
h
e
f
o
llo
w
i
n
g
s
tep
i
s
t
h
e
d
etec
tio
n
o
f
t
h
e
o
b
j
ec
t.
T
h
e
o
b
j
ec
t
is
d
esig
n
ed
u
s
in
g
a
s
p
ec
if
i
c
p
atter
n
to
r
ed
u
ce
th
e
f
i
n
d
in
g
p
r
o
b
lem
.
Fig
u
r
e
4
.
T
h
e
ca
m
er
a
ca
lib
r
ati
o
n
Fig
u
r
e
5
.
T
h
e
E
p
ip
o
lar
L
in
es
o
n
th
e
ca
lib
r
ated
ca
m
er
a
Af
ter
th
e
p
r
ep
ar
atio
n
o
f
b
o
th
ca
m
er
a
s
,
th
e
y
ar
e
r
ea
d
y
to
m
ea
s
u
r
e
th
e
d
is
ta
n
ce
o
f
th
e
o
b
j
ec
t.
T
h
e
ca
lib
r
atio
n
m
atr
ix
p
r
o
d
u
ce
d
b
y
t
h
e
ca
lib
r
atio
n
p
r
o
ce
s
s
i
s
r
eq
u
ir
ed
to
r
e
m
o
v
e
ca
m
er
a
d
is
to
r
tio
n
a
n
d
to
f
in
d
th
e
ep
ip
o
lar
lin
es
o
n
b
o
th
i
m
a
g
es.
T
h
e
f
o
llo
w
i
n
g
s
te
p
i
s
t
h
e
s
ter
eo
ca
lcu
latio
n
p
r
o
ce
s
s
to
f
i
n
d
th
e
d
is
p
ar
it
y
m
ap
.
T
h
e
Se
m
i
-
Glo
b
al
B
lo
ck
Ma
tch
in
g
A
l
g
o
r
ith
m
(
SGB
M)
is
u
s
ed
f
o
r
th
is
p
u
r
p
o
s
e.
T
h
e
s
ter
eo
m
atch
i
n
g
alg
o
r
it
h
m
i
s
an
ess
e
n
tial
s
tep
in
g
en
er
ati
n
g
th
e
d
is
p
ar
it
y
m
a
p
.
I
n
th
is
ex
p
er
i
m
e
n
t,
th
e
o
b
j
ec
t
is
p
o
s
itio
n
ed
f
r
o
m
5
0
c
m
to
1
8
0
cm
in
f
r
o
n
t
o
f
t
h
e
ca
m
er
a.
Fi
g
u
r
e
6
an
d
Fig
u
r
e
7
s
h
o
w
s
th
e
p
r
o
ce
d
u
r
e
o
f
th
e
ex
p
er
i
m
e
n
t.
Fig
u
r
e
6
.
E
x
p
er
i
m
en
t P
r
o
ce
d
u
r
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
I
mp
leme
n
ta
tio
n
o
f
S
tereo
V
is
io
n
S
emi
-
Glo
b
a
l B
lo
ck
Ma
tch
i
n
g
Meth
o
d
s
…
(
R
a
d
en
A
r
ief
S
etya
w
a
n
)
589
Fo
r
th
e
f
ir
s
t
s
et
u
p
,
an
o
b
j
ec
t
is
p
lace
d
in
5
0
c
m
i
n
f
r
o
n
t
o
f
t
h
e
ca
m
er
a.
A
r
u
ler
is
p
lace
d
o
n
th
e
p
ath
be
t
w
ee
n
t
h
e
t
w
o
ca
m
er
as
as
a
r
ef
er
en
ce
.
T
h
e
m
ea
s
u
r
e
m
en
t
p
r
o
ce
s
s
i
s
e
x
ec
u
ted
b
y
d
o
u
b
le
-
clic
k
in
g
t
h
e
s
elec
ted
o
b
j
ec
t
o
n
th
e
s
cr
ee
n
.
T
h
e
o
u
tp
u
t
o
f
m
ea
s
u
r
e
m
e
n
t
i
s
w
r
i
tten
o
n
a
tex
t
f
ile.
T
h
e
n
ex
t
s
tep
is
d
o
n
e
b
y
in
cr
ea
s
i
n
g
t
h
e
d
is
tan
ce
b
et
wee
n
t
h
e
ca
m
er
a
a
n
d
t
h
e
o
b
j
ec
t
w
it
h
a
n
i
n
ter
v
al
o
f
1
0
c
m
.
T
h
e
r
esu
lt
o
f
t
h
e
m
ea
s
u
r
e
m
e
n
t a
l
g
o
r
ith
m
i
s
ex
p
r
ess
ed
in
p
ix
el
s
v
al
u
e.
Fig
u
r
e
7
.
Dis
tan
ce
Me
a
s
u
r
e
m
e
n
t E
k
s
p
er
i
m
e
n
t
5.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
T
h
e
f
ir
s
t
ex
p
er
i
m
en
t
is
to
d
et
er
m
in
e
t
h
e
r
elatio
n
s
h
ip
b
et
w
e
en
t
h
e
d
i
s
p
ar
it
y
a
n
d
t
h
e
o
b
j
ec
t
d
is
ta
n
ce
.
T
ab
le
1
s
h
o
w
s
th
e
r
elatio
n
s
h
ip
b
etw
ee
n
th
e
o
b
j
ec
t
d
is
tan
ce
s
w
it
h
th
e
d
is
p
ar
it
y
b
et
w
ee
n
i
m
ag
e
s
p
air
.
T
h
e
d
is
p
ar
it
y
v
alu
e
is
t
h
e
a
v
er
ag
e
o
r
3
x
3
p
ix
el
ar
o
u
n
d
t
h
e
p
o
i
n
t
o
f
i
n
ter
est
(
P
OI
)
.
Fig
u
r
e
8
in
d
icate
s
t
h
at
t
h
e
co
r
r
elatio
n
b
et
w
ee
n
t
h
e
d
is
t
an
ce
an
d
th
e
av
er
a
g
e
d
is
p
ar
it
y
is
n
o
t
li
n
ea
r
.
T
h
e
d
is
p
ar
it
y
v
al
u
e
in
cr
ea
s
es
ex
p
o
n
en
t
iall
y
w
h
e
n
t
h
e
o
b
j
e
ct
b
ec
o
m
e
s
clo
s
er
to
th
e
ca
m
er
a,
an
d
s
lo
w
l
y
d
ec
r
ea
s
es
w
h
e
n
th
e
d
is
tan
ce
in
cr
ea
s
es.
U
s
in
g
t
h
e
r
eg
r
es
s
io
n
m
et
h
o
d
th
e
p
o
l
y
n
o
m
ia
l
eq
u
a
tio
n
o
f
t
h
e
ch
ar
t
ca
n
b
e
f
o
u
n
d
an
d
ca
n
b
e
u
s
ed
as
th
e
co
n
v
er
s
io
n
f
o
r
m
u
la.
T
h
e
ef
f
ec
t
o
f
th
e
W
L
S
f
i
lter
i
m
p
le
m
e
n
tat
io
n
i
n
t
h
i
s
w
o
r
k
is
s
h
o
w
n
i
n
Fig
u
r
e
9
.
I
t
ca
n
b
e
s
ee
n
th
a
t
w
it
h
o
u
t th
e
W
L
S
f
ilter
i
n
g
t
h
e
o
u
tp
u
t i
m
ag
e
i
s
v
er
y
n
o
i
s
y
.
T
ab
le
1
.
R
ef
er
en
ce
Dis
ta
n
ce
v
s
Av
er
ag
e
Di
s
p
ar
it
y
Val
u
e
R
e
f
e
r
e
n
c
e
D
i
st
a
n
c
e
(
c
m
)
A
v
e
r
a
g
e
o
f
3
x
3
D
i
sp
a
r
i
t
y
v
a
l
u
e
50
0
.
9
8
8
4
6
2
0
9
5
60
0
.
8
5
3
9
6
4
1
2
70
0
.
7
1
7
3
4
3
0
2
7
80
0
.
6
1
6
2
5
8
4
0
9
90
0
.
5
3
9
2
7
0
4
7
2
1
0
0
0
.
4
7
9
8
0
4
1
4
5
1
1
0
0
.
4
3
0
9
0
2
7
7
8
1
2
0
0
.
3
9
1
9
8
8
5
7
1
1
3
0
0
.
3
5
8
8
9
3
9
5
3
1
4
0
0
.
3
3
2
2
4
2
8
3
9
1
5
0
0
.
3
0
6
2
1
3
8
3
1
1
6
0
0
.
2
8
7
4
9
7
4
9
6
1
7
0
0
.
2
4
9
7
8
4
7
3
6
1
8
0
0
.
2
3
2
4
0
8
3
1
2
Fig
u
r
e
8
.
Dis
tace
v
s
d
is
p
ar
it
y
y =
-
0.0005x
3
+
0.0153x
2
-
0.1896x
+
1.1659
0
0.2
0.4
0.6
0.8
1
1.2
50
60
70
80
90
1
0
0
1
1
0
1
2
0
1
3
0
1
4
0
1
5
0
1
6
0
1
7
0
1
8
0
Av
e
ra
ge
3x3 d
is
p
ar
ity
v
alu
e
Dis
ta
n
ce
in
cm
(Re
f
e
re
n
ce
)
T
ot
al
T
o
tal
Po
l
y
. (
T
o
tal
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
1
2
,
No
.
2
,
No
v
e
m
b
er
201
8
:
5
8
5
–
5
9
1
590
Fig
u
r
e
9
.
R
esu
lt o
f
W
L
S Filt
er
I
m
p
le
m
e
n
tatio
n
.
L
e
f
t i
m
ag
e,
b
ef
o
r
e
W
L
S f
il
ter
,
r
ig
h
t i
m
a
g
e
af
t
er
W
L
S
Fil
ter
T
h
e
s
ec
o
n
d
ex
p
er
i
m
en
t
i
s
to
d
eter
m
i
n
e
t
h
e
m
ea
s
u
r
e
m
en
t
er
r
o
r
.
T
ab
le
2
s
h
o
w
s
th
e
r
esu
lt
o
f
th
e
m
ea
s
u
r
e
m
e
n
t.
T
h
e
o
b
tai
n
ed
er
r
o
r
r
ate
w
as
v
er
y
h
i
g
h
w
h
en
t
h
e
o
b
j
ec
t
w
a
s
to
o
clo
s
e
to
th
e
ca
m
er
a.
T
h
e
d
is
tan
ce
b
et
w
ee
n
t
h
e
t
w
o
ca
m
er
as
i
s
1
0
c
m
,
g
i
v
i
n
g
th
e
b
est
m
ea
s
u
r
e
m
e
n
t
ac
c
u
r
ac
y
o
n
1
0
0
cm
.
W
h
e
n
th
e
d
is
tan
ce
b
et
w
ee
n
t
h
e
ca
m
er
a
an
d
th
e
o
b
j
ec
t
in
cr
ea
s
es,
th
e
e
r
r
o
r
m
ea
s
u
r
e
m
e
n
t
w
ill
in
cr
ea
s
e.
T
h
e
h
ig
h
est
er
r
o
r
h
as
b
ee
n
ac
h
iev
ed
w
h
e
n
t
h
e
r
ef
er
en
ce
d
i
s
tan
ce
w
as
5
0
c
m
w
it
h
2
.
5
%
er
r
o
r
.
I
f
t
h
e
o
b
j
ec
t
d
is
tan
ce
i
s
le
s
s
th
a
n
100c
m
,
t
h
e
r
es
u
lt
o
f
s
ter
eo
v
i
s
io
n
m
ea
s
u
r
e
m
e
n
t
is
h
i
g
h
er
t
h
an
r
e
f
er
en
ce
,
b
u
t
w
h
en
th
e
d
is
tan
ce
o
f
o
b
j
ec
t
is
m
o
r
e
t
h
a
n
1
0
0
cm
,
t
h
e
r
esu
lt o
f
m
ea
s
u
r
e
m
e
n
t i
s
less
t
h
a
n
th
e
r
ef
er
en
ce
.
T
a
ble 2
.
M
e
a
s
ure
m
e
nt
re
s
ult
s
D
i
st
a
n
c
e
R
e
f
(
c
m)
S
t
e
r
e
o
v
i
si
o
n
me
a
su
r
e
me
n
t
E
r
r
o
r
1
2
3
4
A
v
g
50
51
50
51
53
5
1
.
2
5
2
.
5
0
%
60
61
61
62
61
6
1
.
2
5
2
.
0
8
%
70
70
75
71
69
7
1
.
2
5
1
.
7
9
%
80
83
80
82
79
81
1
.
2
5
%
90
90
92
93
89
91
1
.
1
1
%
1
0
0
1
0
1
1
0
2
99
99
1
0
0
.
2
5
0
.
2
5
%
1
1
0
1
0
7
1
0
9
1
1
4
1
1
3
1
1
0
.
7
5
0
.
6
8
%
1
2
0
1
1
6
1
1
9
1
2
1
1
1
9
1
1
8
.
7
5
1
.
0
4
%
1
3
0
1
2
9
1
2
8
1
2
9
1
2
8
1
2
8
.
5
1
.
1
5
%
1
4
0
1
3
0
1
4
2
1
4
1
1
4
0
1
3
8
.
2
5
1
.
2
5
%
1
5
0
1
4
9
1
4
8
1
4
7
1
4
8
1
4
8
1
.
3
3
%
1
6
0
1
5
8
1
5
9
1
5
9
1
5
4
1
5
7
.
5
1
.
5
6
%
1
7
0
1
6
9
1
6
8
1
6
7
1
6
5
1
6
7
.
2
5
1
.
6
2
%
1
8
0
1
7
7
1
7
9
1
7
5
1
7
6
1
7
6
.
7
5
1
.
8
1
%
Fig
u
r
e
1
0
s
h
o
w
s
t
h
at
th
e
m
e
asu
r
e
m
en
t
r
es
u
lt
is
h
ig
h
er
th
an
r
ef
er
en
ce
w
h
e
n
th
e
d
is
ta
n
ce
b
et
w
ee
n
o
b
j
ec
t a
n
d
ca
m
er
a
i
s
b
elo
w
1
m
an
d
lo
w
er
if
t
h
e
d
is
ta
n
ce
is
m
o
r
e
t
h
a
n
1
m
.
Fig
u
r
e
1
0
.
Me
asu
r
e
m
e
n
t U
s
in
g
SGB
M
Me
th
o
d
0
50
100
150
200
0
2
4
6
8
10
12
14
16
D
i
st
an
c
e
(
c
m
)
N
u
m
b
e
r
o
f
Trials
R
ul
e
r
S
t
e
r
e
o
m
e
as
ur
e
m
e
nt
(
c
m
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
I
mp
leme
n
ta
tio
n
o
f
S
tereo
V
is
io
n
S
emi
-
Glo
b
a
l B
lo
ck
Ma
tch
i
n
g
Meth
o
d
s
…
(
R
a
d
en
A
r
ief
S
etya
w
a
n
)
591
6.
CO
NCLU
SI
O
N
T
h
e
d
is
tan
ce
m
ea
s
u
r
e
m
en
t
u
s
in
g
s
ter
eo
v
is
io
n
m
et
h
o
d
h
a
s
b
ee
n
p
r
o
p
o
s
ed
.
T
h
e
r
esu
lt
o
f
th
is
w
o
r
k
in
d
icate
s
t
h
at
t
h
e
Se
m
i
-
Glo
b
al
B
lo
ck
Ma
tch
i
n
g
m
et
h
o
d
g
i
v
es
a
g
o
o
d
r
esu
lt,
w
it
h
an
er
r
o
r
r
ate
o
f
less
th
a
n
1
0
%,
b
u
t
th
e
m
ea
s
u
r
e
m
e
n
t
r
esu
lt
i
s
n
o
t
co
r
r
elate
d
lin
ea
r
ly
w
it
h
t
h
e
r
ea
l
m
ea
s
u
r
e
m
e
n
t.
I
t
ca
n
b
e
co
n
clu
d
ed
th
at
th
e
s
ter
eo
v
i
s
io
n
m
e
th
o
d
p
r
o
v
id
es
an
alter
n
ati
v
e
f
o
r
n
o
n
-
co
n
tact
d
is
tan
ce
m
ea
s
u
r
e
m
e
n
t.
Ho
w
e
v
er
,
b
ec
au
s
e
o
f
th
e
co
m
p
le
x
it
y
o
f
s
u
p
p
o
r
ted
co
m
p
o
n
e
n
ts
,
v
er
y
c
ar
ef
u
l
ca
lib
r
atio
n
a
n
d
p
r
ec
is
e
ad
j
u
s
t
m
e
n
t
b
et
w
ee
n
ca
m
er
as a
r
e
h
i
g
h
l
y
r
eq
u
ir
ed
to
g
iv
e
a
b
etter
r
esu
lt.
RE
F
E
R
E
NC
E
S
[1
]
E.
T
jan
d
ra
n
e
g
a
ra
.
“
Dista
n
c
e
Esti
m
a
ti
o
n
A
lg
o
rit
h
m
f
o
r
S
tere
o
P
a
ir
Im
a
g
e
s”
.
Co
m
p
u
t.
En
g
.
,
2
0
0
5
.
[2
]
J.
M
ro
v
lj
e
a
n
d
D.
V
ra
n
.
“
Dista
n
c
e
m
e
a
su
rin
g
b
a
se
d
o
n
ste
re
o
sc
o
p
i
c
p
ictu
re
s”
9
th
In
tern
a
ti
o
n
a
l
P
h
D
W
o
rk
sh
o
p
o
n
S
y
st
e
m
Co
n
tro
l
Y
o
u
n
g
G
e
n
e
ra
ti
o
n
V
iew
p
o
in
t.
2
0
0
8
;2
:
1
–
6.
[3
]
M
.
a
M
a
h
a
m
m
e
d
,
A
.
I.
M
e
lh
u
m
,
a
n
d
F
.
a
Ko
c
h
e
ry
,
“
Ob
jec
t
Dista
n
c
e
M
e
a
su
re
m
e
n
t
b
y
S
tere
o
V
isio
n
,
”
In
tern
a
ti
o
n
a
l
Jo
u
rn
a
l
o
f
S
c
ien
c
e
a
n
d
A
p
p
li
e
d
In
f
o
r
m
a
ti
o
n
T
e
c
h
n
o
lo
g
y
.
2
0
1
3
;2
(
2
)
:
5
–
8.
[4
]
D.
S
c
h
a
rste
in
,
R.
S
z
e
li
sk
i,
a
n
d
R.
Zab
ih
,
“
A
ta
x
o
n
o
m
y
a
n
d
e
v
a
lu
a
ti
o
n
o
f
d
e
n
se
tw
o
-
f
ra
m
e
st
e
re
o
c
o
rre
sp
o
n
d
e
n
c
e
a
lg
o
rit
h
m
s,” In
tern
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Co
m
p
u
ter V
isi
o
n
.
2
0
0
2
,
4
7
(
1
)
:
1
3
1
–
1
4
0
.
[5
]
G
.
Co
c
o
ru
ll
o
,
P
.
Co
rs
o
n
e
ll
o
,
F
.
F
ru
sta
c
i,
a
n
d
S
.
P
e
rr
i,
“
A
n
e
ff
icie
n
t
h
a
rd
w
a
re
-
o
rie
n
ted
ste
re
o
m
a
tch
in
g
a
lg
o
rit
h
m
,
”
M
icro
p
r
o
c
e
ss
o
rs an
d
M
icro
sy
ste
m
s.
2
0
1
6
;
4
6
:
2
1
–
3
3
.
[6
]
H.
Hirsc
h
u
ll
e
r,
“
S
tere
o
p
ro
c
e
ss
in
g
b
y
se
m
i
-
g
o
b
a
l
m
a
tch
in
g
a
n
d
m
u
tu
a
l
in
f
o
rm
a
ti
o
n
,
”
IEE
E
T
ra
n
s
P
a
tt
e
rn
A
n
a
l
M
a
c
h
In
tell.
2
0
0
8
;
3
0
(
2
):
3
2
8
–
3
4
1
.
[7
]
H.
Hirsc
h
m
ü
ll
e
r
a
n
d
D.
S
c
h
a
rste
in
,
“
Ev
a
lu
a
ti
o
n
o
f
Co
st
F
u
n
c
t
io
n
s
f
o
r
S
tere
o
M
a
tch
i
n
g
,
”
2
0
0
7
IE
EE
Co
n
f
e
re
n
c
e
Co
m
p
u
ter V
isi
o
n
a
n
d
P
a
tt
e
rn
Re
c
o
g
n
it
io
n
.
2
0
0
7
:
1
–
8.
[8
]
U.
S
tep
h
a
n
e
,
V
UJ
A
S
INO
V
IC
F
re
d
e
ric,
“
S
tere
o
-
V
isio
n
,
”
G
it
Hu
b
,
2
0
1
8
A
v
a
il
a
b
le:
h
tt
p
s:/
/g
it
h
u
b
.
c
o
m
/L
e
a
rn
T
e
c
h
W
it
h
Us
/S
te
re
o
-
V
isio
n
.
[9
]
W
.
L
iu
,
X
.
Ch
e
n
,
C.
S
h
e
n
,
Z.
L
iu
,
a
n
d
J.
Ya
n
g
,
“
S
e
m
i
-
G
lo
b
a
l
Weig
h
ted
L
e
a
st
S
q
u
a
re
s
in
I
m
a
g
e
F
il
terin
g
,
”
P
ro
c
.
IEE
E
In
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
Co
m
p
u
ter Visio
n
,
2
0
1
7
;
5
8
6
2
–
5
8
7
0
.
[1
0
]
C.
L
ü
,
X
.
W
a
n
g
,
a
n
d
Y.
S
h
e
n
,
“
A
ste
re
o
v
isio
n
m
e
a
su
re
m
e
n
t
s
y
st
e
m
Ba
se
d
o
n
Op
e
n
CV
,
”
P
ro
c
e
e
d
i
n
g
s
o
f
th
e
2
0
1
3
6
th
I
n
tern
a
ti
o
n
a
l
C
o
n
g
re
ss
o
n
Im
a
g
e
a
n
d
S
ig
n
a
l
P
ro
c
e
ss
in
g
.
2
0
1
3
,
2
:7
1
8
–
7
2
2
.
[1
1
]
W
.
S
a
n
k
o
w
sk
i,
M
.
W
ło
d
a
rc
z
y
k
,
D.
Ka
c
p
e
rsk
i,
a
n
d
K.
G
r
a
b
o
w
s
k
i,
“
Esti
m
a
ti
o
n
o
f
m
e
a
su
re
m
e
n
t
u
n
c
e
rtain
ty
in
ste
re
o
v
isio
n
sy
ste
m
ଝ
,”
I
m
a
g
e
V
isio
n
C
o
m
p
u
ti
n
g
.
2
0
1
7
;
6
1
:7
0
–
8
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.