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.
3
8
,
No
.
1
,
A
p
r
il
20
2
5
,
p
p
.
1
61
~
1
71
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
8
.
i
1
.
pp
1
61
-
1
71
161
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Video
mo
sa
ic:
em
plo
y
ing
an eff
icie
nt
O
RB
feature
e
x
trac
tion
techniqu
e wi
th
ha
mm
ing
distance
ma
tching for e
nh
a
nced
performa
nce
Sh
rid
ha
r
H
1
,
Su
nil
S
.
H
a
ra
ka
nn
a
na
v
a
r
2
,
Vidy
a
s
hree
K
a
na
bu
r
3
,
J
a
y
a
la
x
m
i H
4
1
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
C
o
m
mu
n
i
c
a
t
i
o
n
En
g
i
n
e
e
r
i
n
g
,
G
o
v
e
r
n
m
e
n
t
En
g
i
n
e
e
r
i
n
g
C
o
l
l
e
g
e
,
H
a
v
e
r
i
,
V
i
sv
e
sv
a
r
a
y
a
T
e
c
h
n
o
l
o
g
i
c
a
l
U
n
i
v
e
r
s
i
t
y
,
B
e
l
a
g
a
v
i
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
C
o
m
mu
n
i
c
a
t
i
o
n
En
g
i
n
e
e
r
i
n
g
,
N
i
t
t
e
M
e
e
n
a
k
sh
i
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
,
B
a
n
g
a
l
o
r
e
,
I
n
d
i
a
3
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
C
o
m
mu
n
i
c
a
t
i
o
n
En
g
i
n
e
e
r
i
n
g
,
N
a
t
i
o
n
a
l
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
,
M
a
n
g
a
l
o
r
e
,
I
n
d
i
a
4
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
C
o
m
mu
n
i
c
a
t
i
o
n
En
g
i
n
e
e
r
i
n
g
,
A
c
h
a
r
y
a
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
,
B
a
n
g
a
l
o
r
e
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Mar
31
,
2
0
2
4
R
ev
is
ed
Sep
13
,
2
0
2
4
Acc
ep
ted
Oct
30
,
2
0
2
4
Vid
e
o
m
o
sa
icin
g
is
a
c
o
m
p
u
ter
v
isio
n
a
n
d
ima
g
e
p
r
o
c
e
ss
in
g
tec
h
n
iq
u
e
u
se
d
to
c
re
a
te
a
p
a
n
o
ra
m
ic
o
r
wid
e
-
a
n
g
le
v
iew
fro
m
a
se
q
u
e
n
c
e
o
f
v
id
e
o
fra
m
e
s.
Th
e
g
o
a
l
is
to
se
a
m
les
sly
c
o
m
b
in
e
m
u
lt
i
p
le
v
i
d
e
o
fra
m
e
s
to
fo
r
m
a
larg
e
r
a
n
d
m
o
re
c
o
m
p
re
h
e
n
siv
e
v
iew
o
f
a
sc
e
n
e
.
In
re
c
e
n
t
y
e
a
rs,
th
e
field
o
f
ima
g
e
p
ro
c
e
ss
in
g
h
a
s
witn
e
ss
e
d
a
g
ro
wi
n
g
i
n
tere
st
in
v
i
d
e
o
m
o
sa
ic
re
se
a
r
c
h
o
win
g
to
it
s
a
p
p
l
ica
ti
o
n
i
n
su
r
v
e
il
lan
c
e
a
n
d
d
e
fe
n
se
a
p
p
li
c
a
ti
o
n
s.
T
h
is
p
a
p
e
r
in
tro
d
u
c
e
s
a
n
a
u
t
o
m
a
ti
c
a
lg
o
rit
h
m
fo
r
v
id
e
o
m
o
sa
ic
c
re
a
ti
o
n
,
a
d
d
re
ss
in
g
th
e
a
li
g
n
m
e
n
t
a
n
d
b
len
d
in
g
o
f
n
o
n
-
o
v
e
rlap
p
i
n
g
fra
m
e
s
with
i
n
e
a
c
h
in
p
u
t
v
id
e
o
.
Th
e
p
r
o
p
o
se
d
a
l
g
o
ri
th
m
n
a
v
i
g
a
tes
th
ro
u
g
h
se
v
e
ra
l
k
e
y
ste
p
s
t
o
a
c
h
iev
e
a
se
a
m
les
s
a
n
d
c
o
n
ti
n
u
o
u
s
m
o
sa
i
c
,
p
a
rti
c
u
larly
tac
k
l
in
g
issu
e
s
re
late
d
to
c
a
m
e
ra
m
o
ti
o
n
a
n
d
c
o
n
te
n
t
v
a
riatio
n
s
a
c
ro
ss
fr
a
m
e
s.
Th
e
e
ffe
c
t
o
f
th
e
g
o
o
d
n
u
m
b
e
r
o
f
m
a
tch
e
s
to
b
e
c
h
o
se
n
wh
il
e
p
e
rfo
rm
i
n
g
fra
m
e
stit
c
h
in
g
i
s
e
v
a
lu
a
ted
.
Th
e
p
ro
p
o
se
d
a
lg
o
rit
h
m
e
ffe
c
ti
v
e
ly
p
ro
d
u
c
e
s
a
v
id
e
o
m
o
sa
ic
with
a
li
g
n
e
d
a
n
d
b
len
d
e
d
n
o
n
-
o
v
e
rl
a
p
p
in
g
fra
m
e
s,
re
su
lt
in
g
in
a
v
isu
a
ll
y
c
o
n
ti
n
u
o
u
s
m
o
sa
ic
.
Th
e
o
u
tp
u
t
v
i
d
e
o
se
rv
e
s
a
s
a
tes
tam
e
n
t
to
th
e
a
l
g
o
rit
h
m
’
s
p
ro
we
ss
i
n
a
d
d
re
ss
in
g
c
h
a
ll
e
n
g
e
s
re
late
d
t
o
v
id
e
o
fra
m
e
a
li
g
n
m
e
n
t
a
n
d
b
len
d
in
g
.
K
ey
w
o
r
d
s
:
Ho
m
o
g
r
a
p
h
y
Ma
tr
ix
Mo
s
aicin
g
Pan
o
r
am
a
im
ag
es
T
h
r
esh
o
ld
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
:
Sh
r
id
h
ar
H
Dep
ar
tm
en
t o
f
E
lectr
o
n
ics an
d
C
o
m
m
u
n
icatio
n
E
n
g
in
ee
r
i
n
g
,
Go
v
er
n
m
e
n
t
E
n
g
in
ee
r
in
g
C
o
lleg
e
Hav
er
i
,
Vis
v
esv
ar
ay
a
T
ec
h
n
o
l
o
g
ical
Un
iv
er
s
ity
B
elag
av
i,
5
9
0
0
1
8
,
E
m
ail:
s
h
r
id
h
ar
4
7
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
Vid
eo
m
o
s
aicin
g
is
a
co
m
p
u
ter
v
is
io
n
tech
n
iq
u
e
u
s
ed
to
cr
ea
te
a
s
ea
m
less
p
an
o
r
am
ic
o
r
m
o
s
aic
im
ag
e
f
r
o
m
a
s
eq
u
e
n
ce
o
f
o
v
e
r
lap
p
in
g
v
id
eo
f
r
a
m
es.
T
h
is
p
r
o
ce
s
s
is
lik
e
cr
ea
tin
g
a
p
an
o
r
am
a
f
r
o
m
m
u
ltip
le
s
till
im
ag
es,
b
u
t
in
th
is
ca
s
e,
it
’
s
ap
p
lied
to
a
co
n
tin
u
o
u
s
v
id
eo
s
tr
ea
m
.
Vid
eo
m
o
s
aicin
g
h
as
v
ar
io
u
s
ap
p
licatio
n
s
,
in
clu
d
in
g
s
u
r
v
e
illan
ce
,
r
o
b
o
tics
,
v
ir
tu
al
r
ea
l
ity
,
an
d
m
o
r
e.
I
t
allo
ws
f
o
r
th
e
cr
ea
tio
n
o
f
a
p
an
o
r
am
ic
o
r
wid
e
-
a
n
g
le
r
e
p
r
esen
tatio
n
o
f
a
s
ce
n
e,
wh
ich
ca
n
p
r
o
v
id
e
a
b
etter
u
n
d
er
s
tan
d
in
g
o
f
th
e
en
v
ir
o
n
m
en
t o
r
en
h
a
n
ce
th
e
v
is
u
al
ex
p
er
ien
ce
.
Vid
eo
m
o
s
aicin
g
is
cr
u
cial
f
o
r
n
u
m
er
o
u
s
ap
p
licatio
n
s
wh
er
e
cr
ea
tin
g
a
b
r
o
ad
,
c
o
m
p
r
e
h
e
n
s
iv
e
v
iew
f
r
o
m
lim
ited
p
er
s
p
ec
tiv
es
is
n
ec
ess
ar
y
.
I
t
is
ex
ten
s
iv
ely
u
s
ed
in
f
ield
s
s
u
c
h
as
s
u
r
v
eillan
c
e,
r
em
o
te
s
en
s
in
g
,
m
ed
ical
im
ag
in
g
,
an
d
v
ir
tu
al
r
ea
lity
.
I
n
s
u
r
v
eillan
ce
,
v
id
eo
m
o
s
aicin
g
allo
ws f
o
r
th
e
m
o
n
i
to
r
in
g
o
f
lar
g
e
ar
ea
s
u
s
in
g
f
ewe
r
ca
m
e
r
as,
p
r
o
v
i
d
in
g
s
ec
u
r
ity
p
er
s
o
n
n
el
with
a
co
m
p
r
eh
e
n
s
iv
e
v
iew
o
f
th
e
en
v
ir
o
n
m
e
n
t.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
1
,
Ap
r
il
20
2
5
:
1
61
-
1
71
162
I
n
m
ed
ical
im
ag
in
g
,
it
ca
n
b
e
u
s
ed
to
co
m
b
i
n
e
im
ag
es
f
r
o
m
en
d
o
s
co
p
ic
o
r
m
icr
o
s
co
p
ic
ca
m
er
as
to
p
r
o
v
id
e
d
etailed
,
lar
g
e
-
s
ca
le
v
iews
o
f
tis
s
u
es
o
r
o
r
g
an
s
,
aid
in
g
in
m
o
r
e
ac
cu
r
ate
d
iag
n
o
s
es.
Fo
r
v
ir
tu
al
r
ea
lity
,
v
id
eo
m
o
s
aicin
g
en
h
a
n
ce
s
u
s
er
ex
p
er
ien
ce
b
y
o
f
f
er
in
g
m
o
r
e
im
m
er
s
iv
e
en
v
ir
o
n
m
en
ts
th
r
o
u
g
h
p
an
o
r
am
ic
v
iews.
T
h
e
im
p
ac
t
o
f
v
id
eo
m
o
s
aic
in
g
lies
in
its
ab
ilit
y
to
en
h
an
ce
th
e
v
is
u
aliza
tio
n
o
f
s
p
a
tial
en
v
ir
o
n
m
en
ts
,
im
p
r
o
v
in
g
th
e
ef
f
ec
tiv
e
n
ess
o
f
a
n
aly
s
is
an
d
d
ec
is
io
n
-
m
ak
in
g
p
r
o
ce
s
s
es
ac
r
o
s
s
v
ar
io
u
s
in
d
u
s
tr
ies.
Ad
d
itio
n
ally
,
v
id
eo
m
o
s
aicin
g
co
n
t
r
ib
u
tes
to
r
eso
u
r
ce
o
p
ti
m
izatio
n
,
r
e
d
u
cin
g
th
e
n
ee
d
f
o
r
m
u
ltip
le
ca
m
er
a
s
etu
p
s
an
d
th
er
eb
y
lo
wer
in
g
c
o
s
ts
an
d
co
m
p
lex
ity
in
im
ag
in
g
s
y
s
tem
s
.
T
h
is
tech
n
iq
u
e
is
v
ital
f
o
r
s
itu
atio
n
s
r
eq
u
ir
in
g
en
h
an
ce
d
s
itu
atio
n
a
l
awa
r
en
ess
,
en
ab
lin
g
co
m
p
r
eh
en
s
iv
e
an
aly
s
is
f
r
o
m
a
lim
ited
d
ataset.
Vid
eo
mos
aicin
g
in
v
o
l
v
es sev
er
al
k
e
y
asp
ec
ts
as d
escr
ib
ed
in
Fig
u
r
e
1
.
Fig
u
r
e
1
.
Key
co
n
ce
p
ts
an
d
s
tep
s
in
v
o
lv
ed
in
v
id
e
o
m
o
s
aici
n
g
−
I
m
ag
e
ac
q
u
is
itio
n
:
v
id
eo
m
o
s
aicin
g
ty
p
ically
s
tar
ts
with
ca
p
tu
r
in
g
a
s
eq
u
en
ce
o
f
o
v
e
r
lap
p
in
g
im
a
g
es
o
r
v
id
eo
f
r
am
es u
s
in
g
a
ca
m
e
r
a
o
r
o
th
er
im
a
g
in
g
d
ev
ices.
−
I
m
ag
e
r
eg
is
tr
atio
n
a
n
d
f
ea
t
u
r
e
ex
tr
ac
tio
n
:
th
e
f
i
r
s
t
s
tep
in
v
id
eo
m
o
s
aicin
g
is
alig
n
in
g
o
r
r
eg
is
ter
in
g
co
n
s
ec
u
tiv
e
v
i
d
eo
f
r
am
es.
T
h
i
s
p
r
o
ce
s
s
in
v
o
lv
es
f
in
d
in
g
co
r
r
esp
o
n
d
en
c
e
b
etwe
en
f
ea
tu
r
es
o
r
p
o
in
ts
i
n
th
e
f
r
am
es
an
d
tr
an
s
f
o
r
m
i
n
g
th
e
m
to
m
atch
a
co
m
m
o
n
r
ef
er
en
ce
f
r
am
e.
C
o
m
m
o
n
tech
n
i
q
u
es
f
o
r
im
ag
e
r
eg
is
tr
atio
n
in
clu
d
e
f
ea
t
u
r
e
m
atch
in
g
,
o
p
tical
f
lo
w,
an
d
r
i
g
id
o
r
af
f
in
e
t
r
an
s
f
o
r
m
atio
n
s
.
T
h
ese
f
ea
tu
r
es
h
elp
to
f
in
d
co
r
r
esp
o
n
d
in
g
p
o
i
n
ts
in
d
if
f
er
e
n
t f
r
am
es.
−
Ho
m
o
g
r
a
p
h
y
esti
m
atio
n
:
a
m
ath
em
atica
l
tr
an
s
f
o
r
m
atio
n
,
k
n
o
wn
as
a
h
o
m
o
g
r
a
p
h
y
o
r
a
p
er
s
p
ec
tiv
e
tr
an
s
f
o
r
m
atio
n
is
ca
lcu
lated
to
m
ap
p
o
in
ts
f
r
o
m
o
n
e
f
r
am
e
to
an
o
th
er
.
T
h
is
tr
an
s
f
o
r
m
atio
n
c
o
n
s
id
er
s
th
e
ca
m
er
a
’
s
p
o
s
itio
n
an
d
o
r
ien
tatio
n
ch
an
g
es
b
etwe
en
f
r
a
m
es.
I
n
ca
s
es
wh
er
e
th
e
ca
m
er
a
u
n
d
e
r
g
o
es
p
r
o
jectiv
e
tr
a
n
s
f
o
r
m
atio
n
s
(
e.
g
.
,
r
o
tatio
n
s
an
d
tr
an
s
latio
n
s
)
,
a
h
o
m
o
g
r
ap
h
y
m
atr
ix
is
u
s
ed
to
war
p
an
d
alig
n
f
r
am
es
co
r
r
ec
tly
.
T
h
is
tr
an
s
f
o
r
m
atio
n
ac
co
u
n
ts
f
o
r
p
er
s
p
ec
tiv
e
d
is
to
r
tio
n
s
an
d
e
n
s
u
r
es
th
at
th
e
f
r
am
es f
it to
g
eth
er
p
r
o
p
er
ly
.
−
W
ar
p
in
g
an
d
b
le
n
d
in
g
:
wh
e
n
we
s
titch
two
o
r
m
o
r
e
im
ag
es,
th
e
ed
g
es
at
th
e
p
o
in
t
o
f
s
titch
ar
e
p
r
o
m
in
en
t,
an
d
s
o
th
e
s
titch
ed
im
ag
e
l
o
o
k
s
ar
tific
ial
an
d
n
o
t
r
ea
lis
tic.
T
h
er
ef
o
r
e,
we
n
ee
d
im
a
g
e
war
p
in
g
an
d
b
len
d
in
g
o
p
er
atio
n
s
.
T
h
is
s
tep
en
s
u
r
es
th
at
th
e
im
ag
es
o
r
f
r
am
es
f
it
to
g
eth
e
r
s
ea
m
less
ly
,
m
in
im
izin
g
v
is
ib
le
s
ea
m
s
o
r
ar
tifa
cts.
(
W
e
ca
n
ju
s
t
in
clu
d
e
th
e
s
en
ten
c
e
in
g
r
ee
n
in
s
tead
o
f
r
ed
.
E
v
e
n
th
e
s
en
ten
ce
in
b
lack
g
iv
es th
e
m
ea
n
in
g
as in
g
r
ee
n
)
.
−
Sti
tch
in
g
:
t
h
e
alig
n
ed
f
r
am
es
ar
e
f
in
ally
s
titch
ed
to
g
eth
er
to
cr
ea
te
a
s
in
g
le,
co
n
tin
u
o
u
s
p
an
o
r
am
ic
im
ag
e
o
r
v
id
eo
.
T
h
e
g
o
al
is
to
cr
ea
t
e
a
s
in
g
le,
s
ea
m
less
m
o
s
a
ic
i
m
ag
e
f
r
o
m
t
h
e
o
v
er
la
p
p
in
g
f
r
am
es.
T
h
er
e
ar
e
d
if
f
er
en
t
s
titch
in
g
alg
o
r
ith
m
s
av
ailab
le,
r
an
g
in
g
f
r
o
m
s
im
p
l
e
lin
ea
r
b
len
d
in
g
to
m
o
r
e
co
m
p
lex
m
et
h
o
d
s
lik
e
g
r
ap
h
-
cu
t o
p
tim
izatio
n
o
r
b
u
n
d
le
a
d
ju
s
tm
en
t.
T
h
e
r
est
o
f
th
e
p
ap
er
is
o
r
g
an
ized
as
f
o
llo
ws.
Af
te
r
f
o
r
m
ally
in
tr
o
d
u
ci
n
g
t
h
e
to
p
ic
o
f
v
id
e
o
m
o
s
aicin
g
,
we
p
r
o
v
id
e
an
o
v
er
v
iew
o
f
th
e
v
ar
i
o
u
s
ch
allen
g
es
ass
o
ciate
d
with
th
is
tech
n
iq
u
e
in
s
ec
tio
n
2
.
W
e
th
en
h
ig
h
lig
h
t
th
e
m
o
tiv
a
tio
n
b
eh
in
d
o
u
r
wo
r
k
in
s
ec
tio
n
3
.
Sectio
n
4
d
is
cu
s
s
es
r
elate
d
wo
r
k
b
y
o
th
er
r
es
ea
r
ch
er
s
an
d
i
d
en
tifie
s
g
ap
s
in
th
e
ex
is
tin
g
liter
atu
r
e.
Se
ctio
n
s
5
an
d
6
p
r
esen
t
o
u
r
p
r
o
b
lem
s
tatem
en
t
an
d
th
e
im
p
lem
en
tatio
n
o
f
o
u
r
p
r
o
p
o
s
ed
s
o
lu
tio
n
,
d
etailin
g
th
e
m
eth
o
d
o
l
o
g
y
a
n
d
tec
h
n
iq
u
es
em
p
lo
y
ed
.
W
e
p
r
o
v
id
e
a
s
tep
-
by
-
s
tep
an
a
ly
s
is
o
f
o
u
r
r
esu
lts
i
n
s
ec
tio
n
7
.
Fin
ally
,
we
co
n
clu
d
e
th
e
p
ap
er
with
a
s
u
m
m
ar
y
o
f
o
u
r
p
r
o
p
o
s
ed
w
o
r
k
a
n
d
a
d
i
s
cu
s
s
io
n
o
f
th
e
s
co
p
e
f
o
r
f
u
tu
r
e
r
esear
ch
d
ir
ec
tio
n
s
in
s
ec
tio
n
8
.
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
V
id
eo
mo
s
a
ic:
emp
lo
yi
n
g
a
n
e
fficien
t O
R
B
fea
tu
r
e
ex
tr
a
ctio
n
tech
n
iq
u
e
w
ith
h
a
mmin
g
…
(
S
h
r
id
h
a
r
H
)
163
2.
CH
AL
L
E
NG
E
S
O
F
VID
E
O
M
O
SAI
C
I
NG
Vid
eo
m
o
s
aicin
g
,
wh
ile
a
v
alu
ab
le
tech
n
iq
u
e,
co
m
es
with
s
ev
er
al
ch
allen
g
es
an
d
lim
it
atio
n
s
th
at
n
ee
d
to
b
e
ad
d
r
ess
ed
f
o
r
s
u
cc
e
s
s
f
u
l
im
p
lem
en
tatio
n
.
Her
e
ar
e
s
o
m
e
o
f
th
e
p
r
im
ar
y
ch
allen
g
es
ass
o
ciate
d
wit
h
v
id
eo
m
o
s
aick
in
g
.
−
C
am
er
a
ca
lib
r
atio
n
:
ac
c
u
r
ate
ca
m
er
a
ca
lib
r
atio
n
is
ess
en
tial
f
o
r
v
id
e
o
m
o
s
aicin
g
.
Var
iat
io
n
s
in
ca
m
e
r
a
pa
r
am
eter
s
,
s
u
ch
as
f
o
ca
l
le
n
g
th
,
d
is
to
r
tio
n
,
an
d
s
en
s
o
r
ch
ar
ac
ter
is
tics
,
ca
n
lead
to
i
n
ac
cu
r
ac
ies
in
th
e
s
titch
in
g
p
r
o
ce
s
s
.
Pro
p
er
c
alib
r
atio
n
tech
n
iq
u
es a
r
e
r
e
q
u
ir
ed
to
co
m
p
e
n
s
ate
f
o
r
th
ese
v
a
r
iatio
n
s
.
−
Mo
tio
n
co
m
p
e
n
s
atio
n
:
b
o
th
c
am
er
a
an
d
s
ce
n
e
m
o
tio
n
p
o
s
e
s
ig
n
if
ican
t
ch
allen
g
es.
C
am
er
a
m
o
v
em
e
n
ts
,
s
u
ch
as
p
an
n
in
g
,
tilt
in
g
,
o
r
z
o
o
m
in
g
,
n
ee
d
to
b
e
ac
co
u
n
ted
f
o
r
to
esti
m
ate
th
e
co
r
r
ec
t
tr
an
s
f
o
r
m
atio
n
s
b
etwe
en
f
r
am
es.
Ad
d
itio
n
all
y
,
d
y
n
am
ic
s
ce
n
e
elem
en
ts
,
lik
e
m
o
v
in
g
o
b
jects
o
r
p
e
o
p
le,
ca
n
ca
u
s
e
m
is
alig
n
m
en
t a
n
d
a
r
tifa
cts in
th
e
m
o
s
aic.
−
Par
allax
ef
f
ec
ts
:
p
ar
allax
o
cc
u
r
s
wh
en
o
b
jects
at
d
if
f
er
en
t
d
ep
th
s
in
th
e
s
ce
n
e
ap
p
ea
r
to
m
o
v
e
r
elativ
e
to
ea
ch
o
t
h
er
w
h
en
th
e
ca
m
er
a
m
o
v
es.
Han
d
lin
g
p
ar
allax
is
c
h
allen
g
in
g
,
as
it
ca
n
lead
t
o
m
is
alig
n
m
en
t
an
d
g
h
o
s
tin
g
in
t
h
e
m
o
s
aic.
Ad
v
an
ce
d
tech
n
iq
u
es m
ay
b
e
r
eq
u
ir
e
d
to
m
itig
ate
th
ese
ef
f
ec
ts
.
−
Featu
r
e
m
atch
in
g
an
d
tr
ac
k
i
n
g
:
f
ea
tu
r
e
-
b
ased
v
id
eo
m
o
s
aicin
g
r
elies
o
n
d
etec
tin
g
an
d
m
atch
in
g
k
ey
p
o
in
ts
in
f
r
am
es.
C
h
allen
g
es
a
r
is
e
wh
en
th
e
s
ce
n
e
lack
s
d
is
tin
ctiv
e
f
ea
tu
r
es
o
r
wh
e
n
th
er
e
ar
e
ch
an
g
es
in
lig
h
tin
g
co
n
d
itio
n
s
.
R
o
b
u
s
t
f
ea
tu
r
e
m
atch
in
g
a
n
d
tr
ac
k
in
g
alg
o
r
ith
m
s
ar
e
n
ec
ess
ar
y
t
o
h
an
d
le
th
ese
s
itu
atio
n
s
.
−
C
o
m
p
u
tatio
n
al
in
ten
s
ity
:
v
id
eo
m
o
s
aicin
g
ca
n
b
e
co
m
p
u
tati
o
n
ally
in
ten
s
iv
e,
esp
ec
ially
wh
en
d
ea
lin
g
with
h
ig
h
-
r
eso
lu
tio
n
v
id
e
o
s
tr
ea
m
s
o
r
m
an
y
f
r
am
es.
R
ea
l
-
tim
e
v
id
eo
m
o
s
aicin
g
ap
p
licatio
n
s
r
eq
u
ir
e
ef
f
icien
t
alg
o
r
ith
m
s
an
d
h
ar
d
wa
r
e
ac
ce
l
er
atio
n
to
p
r
o
ce
s
s
f
r
am
es q
u
ic
k
ly
.
−
L
en
s
d
is
to
r
tio
n
s
:
ca
m
er
a
len
s
es
in
tr
o
d
u
ce
d
is
to
r
tio
n
s
th
at
ca
n
af
f
ec
t
th
e
ac
cu
r
ac
y
o
f
th
e
m
o
s
aicin
g
p
r
o
ce
s
s
.
C
o
r
r
ec
tin
g
len
s
d
is
to
r
tio
n
s
is
cr
u
cial
f
o
r
alig
n
i
n
g
f
r
a
m
es c
o
r
r
ec
tly
.
−
Seam
less
b
len
d
in
g
:
ac
h
iev
in
g
s
ea
m
less
b
len
d
in
g
b
etwe
en
ad
jace
n
t
f
r
am
es
is
a
n
o
n
-
tr
iv
ial
task
.
Mism
atch
es
in
b
r
ig
h
tn
ess
,
co
lo
r
,
o
r
ex
p
o
s
u
r
e
ca
n
r
esu
lt
in
v
is
ib
le
s
ea
m
s
in
th
e
m
o
s
aic.
So
p
h
is
ticated
b
len
d
in
g
tech
n
iq
u
es a
r
e
n
ee
d
e
d
to
p
r
o
d
u
ce
h
ig
h
-
q
u
ality
r
esu
lts
.
−
R
eso
u
r
ce
co
n
s
tr
ain
ts
:
in
r
es
o
u
r
ce
-
c
o
n
s
tr
ain
ed
en
v
i
r
o
n
m
e
n
ts
,
s
u
ch
as
m
o
b
ile
d
ev
ices
o
r
d
r
o
n
es,
th
e
p
r
o
ce
s
s
in
g
p
o
we
r
an
d
m
em
o
r
y
av
ailab
le
f
o
r
v
id
eo
m
o
s
aicin
g
m
ay
b
e
lim
ited
.
E
f
f
icien
t
alg
o
r
ith
m
s
ar
e
r
eq
u
ir
ed
to
m
ee
t th
ese
co
n
s
tr
ain
ts
.
−
R
o
b
u
s
tn
ess
an
d
r
eliab
ilit
y
:
v
id
eo
m
o
s
aicin
g
s
y
s
tem
s
m
u
s
t
b
e
r
o
b
u
s
t
an
d
r
eliab
le
in
v
ar
i
o
u
s
r
ea
l
-
wo
r
ld
s
ce
n
ar
io
s
.
T
h
ey
s
h
o
u
ld
h
an
d
l
e
d
if
f
er
en
t
lig
h
tin
g
co
n
d
itio
n
s
,
wea
th
er
co
n
d
itio
n
s
,
a
n
d
s
ce
n
e
co
m
p
lex
ities
wh
ile
p
r
o
v
id
i
n
g
ac
cu
r
ate
an
d
co
n
s
is
ten
t r
esu
lts
.
−
User
in
ter
ac
tio
n
:
in
s
o
m
e
ca
s
es,
u
s
er
in
ter
ac
tio
n
m
ay
b
e
r
e
q
u
ir
ed
to
co
r
r
ec
t
er
r
o
r
s
o
r
g
u
id
e
th
e
m
o
s
aicin
g
p
r
o
ce
s
s
,
esp
ec
ially
in
ch
allen
g
in
g
s
ce
n
ar
io
s
.
Vid
eo
m
o
s
aicin
g
is
a
p
o
wer
f
u
l
tech
n
i
q
u
e
f
o
r
cr
ea
tin
g
p
an
o
r
am
ic
o
r
wid
e
-
an
g
le
v
ie
ws
f
r
o
m
a
s
eq
u
en
ce
o
f
im
a
g
es
o
r
v
id
e
o
f
r
am
es.
I
t
in
v
o
lv
es
f
ea
tu
r
e
e
x
tr
ac
tio
n
,
tr
an
s
f
o
r
m
atio
n
esti
m
atio
n
,
a
n
d
im
ag
e
s
titch
in
g
to
p
r
o
d
u
ce
a
s
ea
m
l
ess
r
ep
r
esen
tatio
n
o
f
a
s
ce
n
e
,
with
ap
p
licatio
n
s
r
an
g
i
n
g
f
r
o
m
s
u
r
v
eillan
ce
to
en
ter
tain
m
en
t
a
n
d
b
ey
o
n
d
.
De
s
p
ite
th
ese
ch
allen
g
es,
a
d
v
an
c
es
in
co
m
p
u
ter
v
is
io
n
a
n
d
im
a
g
e
p
r
o
ce
s
s
in
g
h
a
v
e
led
to
th
e
d
e
v
elo
p
m
e
n
t o
f
m
o
r
e
r
o
b
u
s
t a
n
d
ef
f
icien
t
v
id
eo
m
o
s
aicin
g
tech
n
iq
u
es.
3.
M
O
T
I
VAT
I
O
N
O
F
VID
E
O
M
O
SAI
CING
T
h
e
m
o
ti
v
atio
n
b
e
h
in
d
v
id
e
o
m
o
s
aicin
g
s
tem
s
f
r
o
m
th
e
n
ee
d
to
ca
p
tu
r
e
an
d
r
e
p
r
esen
t
a
b
r
o
ad
er
an
d
m
o
r
e
im
m
er
s
iv
e
v
iew
o
f
a
s
ce
n
e
o
r
en
v
ir
o
n
m
en
t th
a
n
wh
at
a
s
in
g
le
ca
m
er
a
f
r
am
e
ca
n
p
r
o
v
id
e.
T
h
is
tech
n
iq
u
e
ad
d
r
ess
es v
ar
io
u
s
p
r
ac
tical
an
d
co
n
ce
p
tu
al
n
ee
d
s
ac
r
o
s
s
d
if
f
e
r
en
t f
ield
s
an
d
a
p
p
licatio
n
s
:
−
E
n
h
an
ce
d
f
ield
o
f
v
iew:
o
n
e
o
f
th
e
p
r
im
ar
y
m
o
tiv
atio
n
s
is
to
ex
p
an
d
th
e
f
ield
o
f
v
iew
b
ey
o
n
d
th
e
lim
itatio
n
s
o
f
a
s
in
g
le
ca
m
er
a
f
r
am
e.
Vid
eo
m
o
s
aicin
g
en
a
b
les
th
e
cr
ea
tio
n
o
f
p
an
o
r
a
m
ic
o
r
wid
e
-
an
g
le
im
ag
es
o
r
v
id
e
o
s
,
allo
win
g
v
i
ewe
r
s
to
s
ee
m
o
r
e
o
f
th
e
s
ce
n
e
with
o
u
t
th
e
n
ee
d
f
o
r
s
p
ec
ial
ized
wid
e
-
an
g
le
len
s
es o
r
eq
u
ip
m
e
n
t.
−
I
m
p
r
o
v
ed
v
is
u
aliza
tio
n
:
v
id
eo
m
o
s
aics
p
r
o
v
id
e
a
m
o
r
e
co
m
p
r
eh
en
s
iv
e
an
d
co
h
er
en
t
r
e
p
r
esen
tatio
n
o
f
a
s
ce
n
e.
T
h
is
ca
n
en
h
an
ce
th
e
v
i
s
u
aliza
tio
n
an
d
u
n
d
er
s
tan
d
in
g
o
f
co
m
p
le
x
en
v
ir
o
n
m
en
ts
,
m
a
k
in
g
it e
asier
to
an
aly
s
e,
n
av
ig
ate,
o
r
a
p
p
r
ec
iat
e
th
e
s
u
r
r
o
u
n
d
in
g
s
.
−
I
m
m
er
s
iv
e
ex
p
er
ien
ce
s
:
in
a
p
p
licatio
n
s
lik
e
v
ir
tu
al
r
ea
lity
an
d
au
g
m
en
ted
r
ea
lity
,
v
i
d
eo
m
o
s
aicin
g
co
n
tr
ib
u
tes
to
cr
ea
tin
g
im
m
er
s
iv
e
ex
p
er
ien
ce
s
.
B
y
s
titch
in
g
to
g
eth
er
m
u
ltip
le
f
r
am
es
o
r
v
id
eo
s
,
it
allo
ws
u
s
er
s
to
ex
p
lo
r
e
an
d
i
n
ter
ac
t w
ith
v
ir
tu
al
en
v
i
r
o
n
m
e
n
ts
in
a
n
atu
r
al
an
d
e
n
g
ag
in
g
way
.
−
Su
r
v
eillan
ce
an
d
s
ec
u
r
ity
:
v
i
d
eo
m
o
s
aicin
g
is
v
alu
ab
le
in
s
u
r
v
eillan
ce
an
d
s
ec
u
r
ity
s
y
s
tem
s
.
I
t
en
ab
les
co
n
tin
u
o
u
s
m
o
n
ito
r
in
g
o
f
lar
g
e
ar
ea
s
u
s
in
g
a
s
in
g
le
ca
m
er
a
o
r
a
n
etwo
r
k
o
f
ca
m
er
as.
T
h
is
ca
n
b
e
cr
u
cial
f
o
r
d
etec
tin
g
an
d
tr
ac
k
in
g
in
tr
u
d
er
s
o
r
u
n
u
s
u
al
ac
tiv
ities
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
1
,
Ap
r
il
20
2
5
:
1
61
-
1
71
164
−
Nav
ig
atio
n
an
d
r
o
b
o
tics
:
v
id
e
o
m
o
s
aicin
g
is
ess
en
tial
f
o
r
n
av
ig
atio
n
a
n
d
a
u
to
n
o
m
o
u
s
r
o
b
o
tics
.
I
t
h
elp
s
r
o
b
o
ts
an
d
au
to
n
o
m
o
u
s
v
eh
ic
les
u
n
d
er
s
tan
d
an
d
n
a
v
ig
ate
t
h
eir
s
u
r
r
o
u
n
d
in
g
s
m
o
r
e
e
f
f
ec
tiv
ely
,
wh
eth
er
in
d
o
o
r
s
(
e
.
g
.
,
i
n
war
eh
o
u
s
es)
o
r
o
u
t
d
o
o
r
s
(
e
.
g
.
,
f
o
r
s
elf
-
d
r
iv
i
n
g
ca
r
s
)
.
−
C
u
ltu
r
al
h
er
itag
e
p
r
eser
v
atio
n
:
v
id
eo
m
o
s
aicin
g
is
u
s
ed
to
ca
p
tu
r
e
h
ig
h
-
r
eso
lu
tio
n
im
ag
es
o
f
h
is
to
r
ical
s
ites
,
ar
tifa
cts,
an
d
ar
two
r
k
.
I
t
aid
s
in
p
r
eser
v
in
g
cu
ltu
r
al
h
e
r
itag
e
b
y
cr
ea
tin
g
d
etailed
v
is
u
al
r
ec
o
r
d
s
f
o
r
d
o
cu
m
e
n
tatio
n
an
d
r
esto
r
atio
n
p
u
r
p
o
s
es.
−
Scien
tific
an
d
en
v
ir
o
n
m
en
tal
m
o
n
ito
r
in
g
:
r
esear
ch
er
s
u
s
e
v
id
eo
m
o
s
aicin
g
to
s
tu
d
y
an
d
d
o
cu
m
en
t
n
atu
r
al
en
v
ir
o
n
m
en
ts
,
ec
o
s
y
s
tem
s
,
an
d
g
eo
lo
g
ical
f
ea
tu
r
es.
I
t
all
o
ws
f
o
r
th
e
cr
ea
tio
n
o
f
p
a
n
o
r
am
ic
v
iews
f
o
r
s
cien
tific
an
aly
s
is
an
d
en
v
ir
o
n
m
en
tal
m
o
n
ito
r
i
n
g
.
−
E
n
ter
tain
m
en
t
an
d
m
ed
ia:
in
th
e
en
ter
tain
m
e
n
t
in
d
u
s
tr
y
,
v
id
e
o
m
o
s
aics
ar
e
em
p
lo
y
ed
f
o
r
cr
ea
ti
n
g
b
r
ea
th
tak
in
g
cin
em
atic
s
h
o
ts
,
en
h
an
cin
g
s
to
r
y
tellin
g
,
a
n
d
o
f
f
er
in
g
v
iewe
r
s
a
m
o
r
e
im
m
er
s
iv
e
v
is
u
al
ex
p
er
ien
ce
.
−
Ar
ch
itectu
r
al
an
d
r
ea
l
estate:
v
id
eo
m
o
s
aicin
g
h
el
p
s
in
s
h
o
wca
s
in
g
ar
ch
itectu
r
e
an
d
r
ea
l
estate
p
r
o
p
er
ties
.
I
t
en
ab
les
th
e
c
r
ea
tio
n
o
f
i
m
m
er
s
i
v
e
v
ir
tu
al
t
o
u
r
s
,
allo
win
g
p
o
te
n
tial
b
u
y
e
r
s
o
r
cli
en
ts
to
ex
p
lo
r
e
p
r
o
p
er
ties
r
em
o
tely
.
−
E
d
u
ca
tio
n
a
n
d
tr
ain
i
n
g
:
v
id
e
o
m
o
s
aics
ca
n
b
e
u
s
ed
i
n
e
d
u
ca
tio
n
al
s
ettin
g
s
to
p
r
o
v
id
e
s
tu
d
en
ts
with
in
ter
ac
tiv
e
an
d
in
f
o
r
m
ativ
e
v
is
u
al
co
n
ten
t,
allo
win
g
th
em
to
ex
p
lo
r
e
h
is
to
r
ical
s
ites
,
s
cien
ti
f
ic
p
h
en
o
m
e
n
a,
an
d
m
o
r
e.
−
E
m
er
g
en
c
y
r
esp
o
n
s
e:
d
u
r
in
g
d
is
aster
m
an
ag
em
en
t
an
d
em
e
r
g
en
cy
r
esp
o
n
s
e
o
p
er
atio
n
s
,
v
id
eo
m
o
s
aicin
g
ca
n
p
r
o
v
id
e
an
o
v
e
r
v
iew
o
f
t
h
e
af
f
ec
ted
ar
ea
s
,
aid
i
n
g
in
d
ec
i
s
io
n
-
m
ak
in
g
an
d
r
eso
u
r
ce
allo
ca
tio
n
.
4.
L
I
T
E
R
AT
U
R
E
SU
RVE
Y
Vid
eo
m
o
s
aicin
g
is
a
tech
n
iq
u
e
th
at
in
v
o
lv
es
s
titch
in
g
to
g
eth
er
m
u
ltip
le
v
id
e
o
f
r
a
m
es
to
cr
ea
te
a
p
an
o
r
am
ic
o
r
m
o
s
aic
v
iew,
w
h
ich
is
u
s
ef
u
l
in
ap
p
licatio
n
s
s
u
ch
as
s
u
r
v
eillan
ce
,
r
o
b
o
tics
,
an
d
v
ir
tu
al
r
ea
lity
.
Ma
n
y
r
esear
ch
er
s
h
av
e
co
n
tr
ib
u
ted
to
ad
v
an
ci
n
g
th
is
f
ield
th
r
o
u
g
h
in
n
o
v
ativ
e
ap
p
r
o
a
ch
es.
Fo
r
in
s
tan
ce
,
W
an
g
et
a
l.
[
1
]
d
e
v
elo
p
ed
a
m
eth
o
d
u
s
in
g
an
im
p
r
o
v
ed
H
ar
r
is
alg
o
r
ith
m
f
o
r
f
ea
tu
r
e
p
o
i
n
t
ex
tr
ac
tio
n
a
n
d
a
two
-
lev
el
Gau
s
s
ian
p
y
r
am
i
d
f
o
r
s
m
o
o
th
i
n
g
,
ac
h
iev
in
g
h
ig
h
-
r
eso
lu
tio
n
p
a
n
o
r
am
ic
im
ag
es
u
p
to
8
K.
Su
m
an
t
r
i
an
d
Par
k
[
2
]
p
r
o
p
o
s
ed
a
n
et
wo
r
k
f
o
r
s
y
n
t
h
esizin
g
h
ig
h
-
q
u
al
ity
3
6
0
-
d
e
g
r
ee
p
an
o
r
am
a
s
with
a
f
o
cu
s
o
n
r
ed
u
cin
g
h
ig
h
-
f
r
eq
u
en
cy
a
r
tif
ac
ts
,
th
u
s
en
h
an
cin
g
v
is
u
al
r
ea
lis
m
.
B
ai
[
3
]
p
r
o
v
id
e
d
an
o
v
er
v
iew
o
f
im
ag
e
m
o
s
aic
tech
n
o
lo
g
y
,
em
p
h
asizin
g
alg
o
r
ith
m
s
f
o
r
im
ag
e
p
r
ep
r
o
ce
s
s
in
g
,
r
eg
is
tr
atio
n
,
an
d
f
u
s
io
n
.
Par
is
o
tto
et
a
l.
[
4
]
d
escr
ib
ed
a
p
r
im
al
-
d
u
al
o
p
tim
izatio
n
al
g
o
r
ith
m
,
h
ig
h
lig
h
tin
g
th
e
s
ig
n
if
ican
ce
o
f
o
p
tim
izatio
n
tech
n
i
q
u
es
in
v
i
d
eo
m
o
s
aicin
g
.
C
h
an
g
an
a
n
d
C
h
ilv
er
i
[
5
]
tailo
r
e
d
th
e
Har
r
is
co
r
n
er
d
etec
tio
n
alg
o
r
ith
m
f
o
r
s
ter
eo
im
ag
e
f
e
atu
r
e
m
atch
in
g
,
wh
ile
Du
et
a
l.
[
6
]
e
n
h
a
n
ce
d
m
ed
ical
im
a
g
e
v
is
u
aliza
tio
n
b
y
co
m
b
in
in
g
s
m
o
o
th
,
tex
t
u
r
e,
a
n
d
ed
g
e
in
f
o
r
m
atio
n
.
X.
L
an
et
a
l.
[
7
]
co
m
b
in
ed
GM
S
ch
a
r
ac
ter
is
tics
with
th
e
R
ANSA
C
a
lg
o
r
ith
m
to
im
p
r
o
v
e
im
ag
e
r
eg
is
tr
atio
n
ac
cu
r
ac
y
an
d
ef
f
icien
cy
.
Yan
g
an
d
Ma
o
[
8
]
u
tili
ze
d
an
im
p
r
o
v
e
d
SI
FT
alg
o
r
ith
m
f
o
r
f
ea
tu
r
e
ex
tr
ac
tio
n
in
in
tellig
en
t
s
u
r
v
eillan
ce
s
y
s
tem
s
.
Han
et
a
l.
[
9
]
i
n
tr
o
d
u
ce
d
a
c
o
r
n
er
d
etec
tio
n
al
g
o
r
ith
m
co
m
b
in
in
g
Har
r
is
an
d
SUSAN
m
eth
o
d
s
to
r
ef
in
e
r
esu
lts
.
L
i
et
a
l.
[
1
0
]
d
e
v
elo
p
e
d
a
m
o
s
aic
an
d
h
y
b
r
id
f
u
s
io
n
alg
o
r
ith
m
b
ased
o
n
p
y
r
am
id
d
ec
o
m
p
o
s
itio
n
,
im
p
r
o
v
in
g
c
o
l
o
r
f
id
elity
an
d
g
h
o
s
tin
g
elim
in
atio
n
.
Kan
g
et
a
l.
[
1
1
]
f
o
cu
s
ed
o
n
co
m
p
r
eh
e
n
s
iv
e
p
an
o
r
am
ic
im
a
g
e
s
titch
in
g
,
ad
d
r
ess
in
g
ch
allen
g
es
r
elate
d
to
co
lo
r
f
u
s
io
n
an
d
te
x
tu
r
e
f
ea
t
u
r
es.
Xiu
et
a
l.
[
1
2
]
lev
er
ag
ed
NSC
T
an
d
ANM
F
alg
o
r
ith
m
s
to
e
n
h
an
ce
im
ag
e
f
u
s
io
n
ef
f
icien
cy
.
R
en
a
n
d
R
en
[
1
3
]
u
s
ed
th
e
SUR
F
alg
o
r
ith
m
f
o
r
f
ea
tu
r
e
e
x
tr
ac
tio
n
,
o
f
f
er
i
n
g
b
etter
s
titch
in
g
q
u
ality
with
a
d
ap
tiv
e
f
u
s
io
n
.
R
.
R
en
a
n
d
Q.
L
ee
et
a
l.
[
1
4
]
in
tr
o
d
u
ce
d
a
r
e
al
-
tim
e
p
an
o
r
a
m
ic
v
id
eo
m
o
s
aic
s
y
s
tem
u
s
in
g
GPU
ac
c
eler
atio
n
,
em
p
h
asizin
g
p
r
ac
tical
ap
p
licatio
n
s
an
d
o
v
e
r
co
m
in
g
f
ea
t
u
r
e
p
o
in
t
s
ca
r
city
.
Nie
et
a
l.
[
1
5
]
d
ev
el
o
p
ed
R
ich
3
6
0
,
a
s
y
s
tem
th
at
ad
d
r
ess
es
p
ar
allax
an
d
en
h
an
c
es
p
an
o
r
am
ic
v
id
e
o
ex
p
er
ien
c
es.
W
ei
et
a
l.
[
1
6
]
f
o
cu
s
ed
o
n
v
id
eo
s
titch
in
g
an
d
s
tab
ilizatio
n
f
o
r
h
an
d
h
eld
ca
m
er
as,
d
ea
lin
g
with
ch
allen
g
es
lik
e
s
h
ak
in
ess
an
d
p
ar
al
lax
.
Li
et
a
l.
[
1
7
]
p
r
esen
ted
a
B
ay
esian
f
u
s
io
n
tech
n
iq
u
e
f
o
r
h
ig
h
-
r
eso
lu
tio
n
im
ag
e
r
ec
o
v
er
y
f
r
o
m
d
e
g
r
ad
ed
o
b
s
er
v
atio
n
s
.
Sh
r
id
h
ar
et
a
l.
[
1
8
]
ad
d
r
es
s
ed
d
is
to
r
tio
n
in
f
is
h
-
e
y
e
len
s
p
an
o
r
am
as
th
r
o
u
g
h
m
u
lti
-
b
an
d
im
ag
e
b
le
n
d
in
g
,
im
p
r
o
v
in
g
v
is
u
al
d
etail
in
v
ir
tu
al
r
ea
lity
.
W
an
g
et
a
l.
[
1
9
]
im
p
lem
en
ted
a
p
ip
eli
n
e
u
s
in
g
h
is
to
g
r
am
eq
u
aliza
tio
n
,
f
ea
tu
r
e
ex
tr
ac
ti
o
n
,
R
ANSAC
m
o
tio
n
esti
m
atio
n
,
an
d
im
a
g
e
war
p
in
g
t
o
cr
ea
te
s
ea
m
less
p
an
o
r
am
as.
L
in
et
a
l.
[
2
0
]
au
to
m
ated
co
astl
in
e
im
ag
e
s
titc
h
in
g
with
a
wav
elet
f
u
s
io
n
ap
p
r
o
ac
h
,
m
itig
atin
g
s
h
ad
o
w
is
s
u
es
an
d
en
h
a
n
cin
g
v
is
u
al
q
u
ality
.
Fin
ally
,
Sh
r
id
h
ar
et
a
l.
[
2
1
]
p
r
o
p
o
s
ed
a
n
o
v
e
l
s
titch
in
g
m
eth
o
d
p
r
io
r
itizin
g
n
atu
r
al
m
o
s
aics
an
d
ad
d
r
ess
in
g
ch
allen
g
es
lik
e
ca
m
er
a
m
o
tio
n
a
n
d
illu
m
in
atio
n
ch
an
g
es,
s
h
o
wca
s
in
g
r
o
b
u
s
tn
ess
an
d
au
to
m
atio
n
.
Mo
s
t
ex
is
tin
g
v
id
eo
m
o
s
aici
n
g
tech
n
iq
u
es
r
ely
o
n
co
m
p
lex
im
ag
e
p
r
o
ce
s
s
in
g
m
eth
o
d
s
.
I
n
o
u
r
p
r
o
p
o
s
ed
wo
r
k
,
we
ad
d
r
ess
t
h
is
co
m
p
lex
ity
b
y
p
r
o
v
id
i
n
g
a
s
im
p
le
s
o
lu
tio
n
f
o
r
c
r
ea
tin
g
s
ea
m
less
v
id
eo
m
o
s
aics.
W
e
in
clu
d
e
h
is
to
g
r
am
m
atch
in
g
to
alig
n
v
id
eo
f
r
am
es,
wh
ich
h
elp
s
cr
ea
te
a
s
m
o
o
th
p
an
o
r
am
a
.
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
V
id
eo
mo
s
a
ic:
emp
lo
yi
n
g
a
n
e
fficien
t O
R
B
fea
tu
r
e
ex
tr
a
ctio
n
tech
n
iq
u
e
w
ith
h
a
mmin
g
…
(
S
h
r
id
h
a
r
H
)
165
Ad
d
itio
n
ally
,
we
s
elec
t
f
r
am
es
with
a
h
ig
h
er
p
er
ce
n
tag
e
o
f
m
atch
es
to
co
n
s
tr
u
ct
th
e
m
o
s
aic.
T
o
th
e
b
est
o
f
o
u
r
k
n
o
wled
g
e
,
th
is
n
o
v
el
ap
p
r
o
ac
h
h
as n
o
t b
ee
n
p
r
e
v
io
u
s
ly
ex
p
lo
r
ed
in
th
e
liter
atu
r
e.
5.
P
RO
P
O
SE
D
M
E
T
H
O
D
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
is
s
h
o
wn
in
Fig
u
r
e
2
.
T
h
e
o
b
jectiv
e
o
f
v
id
eo
m
o
s
aicin
g
is
to
cr
ea
te
a
s
in
g
le,
co
n
tin
u
o
u
s
,
an
d
p
an
o
r
am
ic
r
ep
r
esen
tatio
n
o
f
a
s
ce
n
e
o
r
en
v
ir
o
n
m
e
n
t
b
y
s
ea
m
less
ly
s
titch
in
g
to
g
eth
e
r
m
u
ltip
le
v
id
eo
f
r
am
es o
r
im
ag
es.
I
n
ad
d
itio
n
to
th
is
:
−
A
s
ea
m
less
in
teg
r
atio
n
:
a
v
id
eo
m
o
s
aicin
g
m
o
d
el
is
d
ev
elo
p
ed
to
cr
ea
te
a
m
o
s
aic
th
at
ap
p
ea
r
s
as
a
s
in
g
le,
co
h
er
en
t
im
a
g
e
o
r
v
id
eo
,
with
n
o
v
is
ib
le
s
ea
m
s
o
r
ar
tifa
cts
at
th
e
b
o
u
n
d
ar
ies
wh
er
e
f
r
a
m
es
ar
e
jo
in
ed
.
Ach
iev
in
g
s
ea
m
less
in
teg
r
atio
n
is
cr
u
cial
to
p
r
o
v
id
e
a
n
atu
r
a
l a
n
d
im
m
er
s
iv
e
v
iewin
g
ex
p
e
r
ien
ce
.
−
E
v
alu
atio
n
o
f
p
er
f
o
r
m
a
n
ce
: to
ev
alu
ate
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
p
r
o
p
o
s
ed
v
id
e
o
m
o
s
aicin
g
m
o
d
el,
we
f
o
c
u
s
o
n
its
ab
ilit
y
to
p
r
o
d
u
ce
h
ig
h
-
q
u
ality
m
o
s
aics th
at
m
ain
tain
v
is
u
al
f
id
elity
an
d
s
p
atial
co
n
t
in
u
ity
.
T
h
e
s
tep
s
in
v
o
lv
ed
m
atch
i
n
g
th
e
cu
r
r
en
t
f
r
am
e
with
th
e
p
r
ev
io
u
s
f
r
am
e
u
s
ed
in
o
u
r
co
d
e
to
m
atch
f
ea
tu
r
es
b
etwe
en
th
e
cu
r
r
en
t a
n
d
p
r
e
v
i
o
u
s
f
r
am
es f
o
r
v
id
e
o
m
o
s
aicin
g
:
Fig
u
r
e
2
.
Pro
p
o
s
ed
m
o
d
el
a.
OR
B
f
ea
tu
r
e
d
etec
tio
n
−
I
n
o
u
r
c
o
d
e,
we
u
s
e
th
e
OR
B
f
ea
tu
r
e
d
etec
tio
n
alg
o
r
ith
m
to
d
etec
t
k
ey
p
o
in
ts
(
f
ea
tu
r
es)
in
b
o
th
th
e
cu
r
r
en
t a
n
d
p
r
ev
io
u
s
f
r
am
es.
−
OR
B
i
s
ef
f
icien
t
an
d
well
-
s
u
i
ted
f
o
r
r
ea
l
-
tim
e
ap
p
licatio
n
s
,
m
ak
in
g
it
a
p
o
p
u
lar
ch
o
ice
f
o
r
f
ea
tu
r
e
d
etec
tio
n
.
b.
OR
B
f
ea
tu
r
e
d
escr
ip
tio
n
−
Fo
r
ea
ch
k
ey
p
o
in
t
d
etec
ted
b
y
OR
B
,
d
escr
ip
to
r
s
ar
e
co
m
p
u
ted
.
Descr
ip
to
r
s
en
co
d
e
in
f
o
r
m
atio
n
ab
o
u
t th
e
l
o
ca
l im
ag
e
p
atc
h
ar
o
u
n
d
e
ac
h
k
e
y
p
o
in
t.
c.
Featu
r
e
m
atch
in
g
−
W
e
u
s
e
a
b
r
u
te
-
f
o
r
ce
m
atch
er
(
cv
2
.
B
FMatc
h
er
)
to
m
atch
th
e
d
escr
ip
to
r
s
o
f
k
ey
p
o
in
ts
b
e
twee
n
th
e
cu
r
r
en
t a
n
d
p
r
ev
io
u
s
f
r
am
es.
−
T
h
e
cv
2
.
B
FMatc
h
er
u
s
es
th
e
Ham
m
in
g
d
is
tan
ce
as
th
e
d
is
t
an
ce
m
etr
ic
an
d
p
er
f
o
r
m
s
cr
o
s
s
-
ch
ec
k
in
g
to
f
in
d
m
u
tu
al
m
atch
es.
d.
Ma
tch
in
g
f
ilter
in
g
with
R
ANSAC
−
Af
ter
o
b
tain
in
g
th
e
in
itial m
at
ch
es,
we
ap
p
ly
a
f
ilter
to
r
em
o
v
e
an
y
i
n
co
r
r
ec
t c
o
r
r
esp
o
n
d
en
ce
.
−
Ou
r
co
d
e
c
h
ec
k
s
th
e
n
u
m
b
e
r
o
f
m
atch
es
(
len
(
m
atc
h
es))
an
d
u
s
es th
is
as a
f
ilter
in
g
cr
iter
io
n
.
−
I
f
th
er
e
ar
e
m
o
r
e
t
h
an
th
r
esh
o
ld
m
atch
es,
we
u
s
e
th
e
R
ANS
AC
a
lg
o
r
ith
m
to
esti
m
ate
a
tr
an
s
f
o
r
m
atio
n
m
atr
ix
(
h
o
m
o
g
r
ap
h
y
)
th
at
alig
n
s
th
e
f
r
am
es.
−
R
ANSA
C
h
elp
s
in
f
ilter
in
g
o
u
t o
u
tlier
s
an
d
o
b
tain
in
g
a
r
o
b
u
s
t tr
an
s
f
o
r
m
atio
n
m
o
d
el.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
1
,
Ap
r
il
20
2
5
:
1
61
-
1
71
166
e.
W
ar
p
in
g
with
h
o
m
o
g
r
a
p
h
y
−
On
ce
we
h
av
e
esti
m
ated
th
e
h
o
m
o
g
r
ap
h
y
m
atr
ix
u
s
in
g
R
ANSAC
,
we
war
p
th
e
cu
r
r
en
t
f
r
am
e
to
alig
n
it with
th
e
p
r
e
v
io
u
s
f
r
a
m
e.
−
T
h
e
cv
2
.
wa
r
p
Per
s
p
ec
tiv
e
f
u
n
c
tio
n
is
u
s
ed
to
ap
p
ly
th
is
tr
an
s
f
o
r
m
atio
n
a
n
d
alig
n
th
e
f
r
a
m
es.
f.
Up
d
atin
g
p
r
ev
io
u
s
f
r
am
e
:
−
T
h
e
cu
r
r
e
n
t f
r
am
e
,
af
ter
war
p
i
n
g
,
b
ec
o
m
es th
e
n
ew
“
p
r
ev
io
u
s
f
r
am
e”
f
o
r
th
e
n
e
x
t iter
atio
n
.
−
T
h
is
s
tep
en
s
u
r
es th
at
y
o
u
m
ai
n
tain
a
co
n
tin
u
o
u
s
alig
n
m
en
t
o
f
f
r
am
es a
s
y
o
u
p
r
o
ce
s
s
th
e
v
id
eo
.
B
y
f
o
llo
win
g
th
ese
s
tep
s
,
we
ca
n
m
atch
f
ea
tu
r
es
b
etwe
en
f
r
am
es,
f
ilter
th
e
m
atch
es,
esti
m
ate
a
tr
an
s
f
o
r
m
atio
n
,
an
d
cr
ea
te
a
m
o
s
aic
v
id
eo
.
T
h
e
OR
B
alg
o
r
ith
m
p
lay
s
a
cr
u
cial
r
o
le
in
f
ea
tu
r
e
d
etec
tio
n
an
d
d
escr
ip
tio
n
,
m
a
k
in
g
it
p
o
s
s
ib
le
to
f
in
d
co
r
r
esp
o
n
d
en
ce
b
etwe
en
f
r
am
es
a
n
d
alig
n
t
h
em
ef
f
ec
tiv
el
y
f
o
r
m
o
s
aicin
g
.
T
h
e
t
h
r
esh
o
ld
o
n
th
e
n
u
m
b
er
o
f
m
atch
es
co
n
tr
o
ls
wh
en
R
ANSAC
-
b
ased
tr
an
s
f
o
r
m
atio
n
esti
m
atio
n
is
ap
p
lied
,
co
n
tr
i
b
u
tin
g
to
r
o
b
u
s
tn
ess
in
th
e
p
r
ese
n
ce
o
f
v
ar
y
in
g
lev
els o
f
o
v
er
la
p
b
etwe
en
f
r
am
es.
6.
P
RO
P
O
SE
D
VID
E
O
M
O
S
A
I
CING
A
L
G
O
RI
T
H
M
St
ep
1
:
in
p
u
t:
p
r
o
v
id
e
th
e
p
at
h
to
th
e
in
p
u
t
v
id
e
o
f
ile
(
v
id
e
o
_
p
ath
)
an
d
s
et
a
n
o
v
er
la
p
p
e
r
ce
n
tag
e
t
h
r
esh
o
ld
(
o
v
er
lap
_
th
r
esh
o
l
d
)
.
Step
2
:
i
n
itializatio
n
:
−
I
n
itialize
th
e
v
id
eo
ca
p
tu
r
e
o
b
j
ec
t (
ca
p
)
to
o
p
en
th
e
in
p
u
t v
id
eo
f
ile.
−
C
h
ec
k
if
th
e
v
id
e
o
f
ile
o
p
en
ed
s
u
cc
ess
f
u
lly
.
I
f
n
o
t,
r
etu
r
n
an
er
r
o
r
.
−
R
ea
d
th
e
f
ir
s
t f
r
am
e
f
r
o
m
th
e
v
id
eo
to
d
eter
m
in
e
th
e
f
r
am
e
d
im
en
s
io
n
s
.
Step
3
:
o
u
tp
u
t v
id
eo
s
etu
p
−
Def
in
e
th
e
p
ath
a
n
d
c
o
d
ec
f
o
r
th
e
o
u
tp
u
t v
id
eo
.
−
I
n
itialize
th
e
v
id
eo
wr
iter
o
b
ject
with
th
e
s
p
ec
if
ied
co
d
ec
a
n
d
f
r
am
e
d
im
e
n
s
io
n
s
f
o
r
cr
ea
t
in
g
th
e
o
u
tp
u
t
v
id
eo
.
Step
4
:
f
r
am
e
p
r
o
ce
s
s
in
g
lo
o
p
−
I
n
itialize
v
ar
iab
les.
a.
Mo
s
aic:
c
r
ea
te
an
em
p
ty
m
o
s
aic
an
d
s
et
it to
th
e
f
ir
s
t f
r
a
m
e.
b.
p
r
ev
_
f
r
am
e:
s
et
th
e
p
r
e
v
io
u
s
f
r
am
e
as th
e
f
ir
s
t f
r
am
e.
−
L
o
o
p
th
r
o
u
g
h
th
e
v
id
eo
f
r
am
e
s
a.
R
ea
d
th
e
n
ex
t f
r
a
m
e
f
r
o
m
th
e
v
id
eo
.
b.
C
alcu
late
th
e
o
v
er
lap
p
er
ce
n
tag
e
(
o
v
er
la
p
_
p
e
r
ce
n
t)
b
etwe
en
th
e
p
r
e
v
io
u
s
f
r
am
e
an
d
t
h
e
cu
r
r
e
n
t
f
r
am
e.
c.
C
h
ec
k
if
o
v
er
la
p
_
p
e
r
ce
n
t is less
th
an
th
e
s
p
ec
if
ied
o
v
e
r
lap
_
t
h
r
esh
o
ld
.
I
f
o
v
e
r
lap
_
p
e
r
ce
n
t is b
elo
w
th
e
th
r
esh
o
ld
−
Use O
R
B
f
ea
tu
r
e
d
etec
tio
n
an
d
m
atch
in
g
to
alig
n
a
n
d
b
len
d
th
e
f
r
am
es.
−
I
f
th
er
e
ar
e
en
o
u
g
h
g
o
o
d
m
atc
h
es
(
e.
g
.
,
m
o
r
e
th
an
4
0
0
)
,
c
o
m
p
u
te
a
h
o
m
o
g
r
a
p
h
y
m
atr
i
x
(
M)
to
alig
n
th
e
f
r
am
es.
−
W
ar
p
th
e
cu
r
r
en
t
f
r
am
e
to
al
ig
n
with
th
e
p
r
ev
i
o
u
s
f
r
a
m
e
u
s
in
g
th
e
h
o
m
o
g
r
ap
h
y
m
atr
ix
.
Up
d
ate
th
e
m
o
s
aic
b
y
b
len
d
in
g
t
h
e
alig
n
e
d
f
r
am
e
with
t
h
e
p
r
e
v
io
u
s
m
o
s
aic.
−
Set th
e
p
r
ev
io
u
s
f
r
am
e
to
t
h
e
n
o
n
-
o
v
er
lap
p
i
n
g
f
r
am
e.
W
r
ite
th
e
m
o
s
aice
d
f
r
a
m
e
to
th
e
o
u
tp
u
t v
id
eo
.
−
Dis
p
lay
th
e
m
o
s
aice
d
f
r
am
e
a
n
d
c
h
ec
k
f
o
r
a
k
e
y
b
o
ar
d
in
ter
r
u
p
tio
n
(
e
.
g
.
,
‘
q
’
k
ey
)
t
o
s
to
p
th
e
p
r
o
ce
s
s
.
Step
5
:
clea
n
u
p
a
n
d
f
i
n
aliza
tio
n
−
Af
ter
p
r
o
ce
s
s
in
g
all
f
r
a
m
es,
r
e
lease
th
e
v
id
eo
ca
p
tu
r
e
an
d
wr
iter
o
b
jects.
−
C
lo
s
e
an
y
o
p
en
win
d
o
ws.
Step
6
:
o
u
tp
u
t: th
e
alg
o
r
ith
m
p
r
o
d
u
ce
s
a
v
id
e
o
m
o
s
aic
wh
er
e
n
o
n
-
o
v
er
lap
p
in
g
f
r
am
es a
r
e
a
lig
n
ed
an
d
b
len
d
ed
to
cr
ea
te
a
co
n
ti
n
u
o
u
s
m
o
s
aic,
an
d
th
e
o
u
tp
u
t v
id
eo
is
s
av
ed
.
T
h
is
alg
o
r
ith
m
allo
ws
y
o
u
to
co
n
tr
o
l
wh
ich
f
r
am
es
ar
e
in
clu
d
ed
in
th
e
m
o
s
aic
b
ased
o
n
t
h
eir
o
v
er
lap
with
th
e
p
r
ev
i
o
u
s
f
r
am
e
,
m
ak
i
n
g
it
s
u
itab
le
f
o
r
ca
s
es
wh
er
e
y
o
u
wan
t
t
o
m
o
s
aic
o
n
ly
n
o
n
-
o
v
er
lap
p
i
n
g
f
r
am
es
in
a
v
id
eo
s
eq
u
en
ce
.
Yo
u
ca
n
ad
ju
s
t
th
e
o
v
er
la
p
_
th
r
esh
o
ld
a
n
d
o
th
e
r
p
ar
a
m
eter
s
to
cu
s
to
m
ize
th
e
b
eh
a
v
io
r
o
f
th
e
alg
o
r
ith
m
.
7.
RO
L
E
OF
T
H
E
NUM
B
E
R
O
F
M
AT
CH
E
S O
N
VID
E
O
M
O
SAI
C
T
h
e
n
u
m
b
e
r
o
f
m
atch
es
in
a
f
ea
tu
r
e
-
b
ased
im
ag
e
s
titch
in
g
o
r
m
o
s
aicin
g
p
r
o
ce
s
s
ca
n
in
d
ee
d
af
f
ec
t
th
e
q
u
ality
o
f
th
e
r
esu
ltin
g
m
o
s
aic.
−
R
o
b
u
s
tn
ess
to
d
is
to
r
tio
n
s
:
a
l
ar
g
er
n
u
m
b
er
o
f
m
atch
es
m
e
an
s
th
at
m
o
r
e
k
ey
p
o
i
n
ts
in
t
h
e
im
ag
es
h
av
e
b
ee
n
s
u
cc
ess
f
u
lly
m
atch
ed
[
2
2
]
.
T
h
is
is
p
ar
ticu
lar
l
y
b
e
n
ef
i
cial
wh
en
th
e
in
p
u
t
im
a
g
es
h
av
e
s
ig
n
if
ican
t
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
V
id
eo
mo
s
a
ic:
emp
lo
yi
n
g
a
n
e
fficien
t O
R
B
fea
tu
r
e
ex
tr
a
ctio
n
tech
n
iq
u
e
w
ith
h
a
mmin
g
…
(
S
h
r
id
h
a
r
H
)
167
g
eo
m
etr
ic
a
n
d
r
ad
io
m
etr
ic
v
a
r
iatio
n
s
.
R
o
b
u
s
t
m
atch
es
h
elp
en
s
u
r
e
th
at
th
e
s
titch
in
g
p
r
o
ce
s
s
ca
n
h
an
d
le
d
is
to
r
tio
n
s
s
u
ch
as r
o
tatio
n
s
,
s
ca
lin
g
,
an
d
p
er
s
p
ec
tiv
e
c
h
an
g
e
s
.
−
B
etter
esti
m
atio
n
o
f
tr
a
n
s
f
o
r
m
atio
n
s
:
m
o
r
e
m
atch
es
p
r
o
v
id
e
m
o
r
e
d
ata
p
o
in
ts
f
o
r
esti
m
atin
g
th
e
tr
an
s
f
o
r
m
atio
n
s
(
h
o
m
o
g
r
ap
h
y
o
r
af
f
i
n
e
tr
an
s
f
o
r
m
atio
n
s
)
t
h
at
alig
n
th
e
im
a
g
es.
W
h
en
th
er
e
ar
e
m
a
n
y
m
atch
es,
it
’
s
m
o
r
e
lik
ely
t
h
at
a
co
n
s
is
ten
t
tr
an
s
f
o
r
m
atio
n
ca
n
b
e
esti
m
ated
,
wh
ic
h
h
elp
s
r
ed
u
ce
m
is
alig
n
m
en
t a
n
d
d
is
to
r
tio
n
s
in
th
e
m
o
s
aic
[
2
3
]
.
−
Ou
tlier
r
ejec
tio
n
:
f
ea
tu
r
e
m
at
ch
in
g
o
f
ten
in
v
o
lv
es
th
e
s
tep
o
f
r
ejec
tin
g
o
u
tlier
m
atch
es.
Hav
in
g
m
o
r
e
m
atch
es
allo
ws
f
o
r
a
m
o
r
e
e
f
f
ec
tiv
e
o
u
tlier
r
ejec
tio
n
p
r
o
c
ess
.
Ou
tlier
s
ca
n
b
e
ca
u
s
ed
b
y
f
ac
to
r
s
lik
e
m
o
v
in
g
o
b
jects
o
r
im
ag
e
n
o
is
e.
A
r
o
b
u
s
t
m
atch
in
g
a
n
d
r
ej
ec
tio
n
p
r
o
ce
s
s
ca
n
r
em
o
v
e
th
ese
o
u
tlier
s
an
d
im
p
r
o
v
e
t
h
e
o
v
e
r
all
q
u
ality
[
2
4
]
.
−
C
o
m
p
leten
ess
o
f
in
f
o
r
m
ati
o
n
: a
lar
g
er
n
u
m
b
er
o
f
m
atc
h
es
m
ea
n
s
th
at
y
o
u
’
r
e
u
s
in
g
m
o
r
e
in
f
o
r
m
atio
n
f
r
o
m
th
e
in
p
u
t im
a
g
es to
cr
ea
te
th
e
m
o
s
aic.
T
h
is
r
esu
lts
in
a
m
o
r
e
co
m
p
r
eh
e
n
s
iv
e
r
ep
r
esen
tatio
n
o
f
th
e
s
ce
n
e.
8.
RE
SU
L
T
S
AND
D
I
SCU
SS
I
O
N
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
is
test
e
d
o
n
th
r
ee
d
atasets
in
Py
th
o
n
s
o
f
twar
e
h
av
in
g
3
2
-
b
it
an
d
h
as
b
ee
n
ex
ec
u
ted
in
s
y
s
tem
with
co
n
f
ig
u
r
atio
n
i4
p
r
o
ce
s
s
o
r
,
8
GB
R
AM
,
2
G
B
ca
ch
e
m
e
m
o
r
y
an
d
2
.
8
GHz
p
r
o
ce
s
s
o
r
.
Fig
u
r
e
3
s
h
o
ws
th
e
im
ag
es
wh
en
th
e
th
r
esh
o
l
d
f
o
r
th
e
n
u
m
b
er
o
f
m
atc
h
es
is
m
u
ch
less
th
an
th
e
ac
tu
al
m
atch
es
b
etwe
en
t
h
e
p
r
ev
io
u
s
an
d
th
e
c
u
r
r
e
n
t
f
r
am
e.
As
ca
n
b
e
s
ee
n
f
r
o
m
t
h
e
ab
o
v
e
f
ig
u
r
e,
t
h
e
im
ag
es
ar
e
m
is
alig
n
ed
.
Fig
u
r
e
4
s
h
o
w
s
th
e
ef
f
ec
t
o
n
th
e
m
o
s
aic
f
r
a
m
e
wh
en
th
e
t
h
r
esh
o
ld
f
o
r
t
h
e
n
u
m
b
e
r
o
f
m
atch
es
is
m
u
ch
clo
s
er
to
th
e
ac
tu
al
m
atch
es
b
etwe
en
th
e
p
r
e
v
io
u
s
an
d
th
e
cu
r
r
en
t
f
r
a
m
e.
I
t
is
o
b
s
er
v
ed
t
h
at
th
e
p
r
o
b
lem
o
f
m
is
alig
n
m
en
t
is
o
v
er
co
m
e
b
y
in
cr
ea
s
in
g
th
e
th
r
esh
o
ld
.
T
h
er
ef
o
r
e,
as
th
e
th
r
esh
o
ld
f
o
r
th
e
n
u
m
b
er
o
f
m
atch
es
b
etwe
en
th
e
f
r
am
es
in
cr
ea
s
es,
i
t
i
s
s
ee
n
th
at
t
h
e
v
id
eo
m
o
s
aic
is
m
u
ch
clea
r
er
,
s
m
o
o
th
er
,
an
d
ali
g
n
ed
well.
As
th
e
th
r
esh
o
ld
in
cr
ea
s
es,
it
will
in
cr
ea
s
e
th
e
c
o
m
p
u
tatio
n
al
tim
e
b
u
t
ag
ain
it
’
s
in
m
illi
s
ec
o
n
d
s
,
s
o
it d
o
esn
’
t r
ea
lly
m
a
k
e
a
b
i
g
im
p
ac
t o
n
t
h
e
m
o
s
aic
o
u
t
p
u
t.
Fig
u
r
e
3
.
R
ea
l tim
e
s
ce
n
e
s
h
o
win
g
m
o
r
e
m
atch
in
g
p
o
in
ts
Fig
u
r
e
4
.
R
ea
l tim
e
s
ce
n
e
s
h
o
win
g
less
m
atch
in
g
p
o
i
n
ts
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
1
,
Ap
r
il
20
2
5
:
1
61
-
1
71
168
I
n
th
e
p
r
o
p
o
s
ed
wo
r
k
,
we
ch
o
o
s
e
a
v
id
eo
co
v
e
r
in
g
lar
g
ely
v
ar
y
in
g
f
r
am
es.
W
e
ex
p
er
i
m
en
ted
with
v
ar
io
u
s
v
alu
es
o
f
th
r
esh
o
ld
o
f
g
o
o
d
n
u
m
b
er
o
f
m
atch
es
b
etwe
en
th
e
two
ad
jace
n
t
f
r
am
es.
Fig
u
r
e
5
s
h
o
ws
a
n
im
ag
e
co
m
p
ar
in
g
th
e
s
am
e
tw
o
f
r
am
es
with
th
e
th
r
esh
o
ld
o
n
n
u
m
b
er
o
f
g
o
o
d
m
atch
es
b
e
in
g
in
Fig
u
r
es
5
(
a
)
1
0
,
Fig
u
r
e
5
(
b
)
1
0
0
,
a
n
d
Fig
u
r
e
5
(
c)
4
0
0
r
esp
ec
tiv
ely
.
(
a)
(
b
)
(
c)
Fig
u
r
e
5
.
T
h
r
esh
o
ld
o
n
n
u
m
b
e
r
o
f
g
o
o
d
m
atch
es
(
a)
1
0
,
(
b
)
1
0
0
,
an
d
(
c)
400
W
e
n
o
ticed
th
at
wh
en
th
r
esh
o
ld
is
1
0
,
th
e
cu
r
r
en
t
f
r
am
es
ar
e
h
ig
h
ly
m
is
alig
n
e
d
to
p
r
ev
io
u
s
f
r
am
e,
an
d
th
e
y
ca
n
n
o
t b
e
s
titch
ed
to
g
eth
er
to
g
et
a
p
a
n
o
r
am
ic
v
ie
w.
Als
o
,
to
o
m
an
y
f
r
am
es
a
r
e
to
b
e
i
n
clu
d
ed
to
g
et
an
en
tire
v
id
eo
m
o
s
aic.
W
h
en
th
e
th
r
esh
o
l
d
is
4
0
0
,
we
s
ee
th
at
th
e
s
ce
n
es
ca
n
b
e
ca
p
tu
r
ed
ea
s
ily
an
d
s
o
m
e
o
f
th
e
f
r
am
es
ca
n
b
e
ea
s
ily
s
k
ip
p
ed
to
g
et
th
e
p
an
o
r
am
ic
v
ie
w
o
f
th
e
en
tire
s
ce
n
e.
As
we
f
u
r
th
er
in
cr
ea
s
e
th
e
th
r
esh
o
ld
,
th
e
ef
f
ec
t is th
e
s
am
e.
T
h
e
ev
alu
atio
n
m
etr
ic
[2
5
]
m
ea
s
u
r
es
s
u
ch
as
r
o
o
t
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
R
MSE
)
to
q
u
an
tify
th
e
ac
cu
r
ac
y
o
f
m
o
tio
n
esti
m
atio
n
.
T
h
e
R
MSE
in
r
eg
e
n
er
ated
im
ag
e
is
th
eo
r
etica
lly
ca
lcu
l
ated
u
s
in
g
(
1
)
an
d
tab
u
lated
in
T
ab
le
1
.
=
(
1
)
∑
[
(
,
)
−
′
(
,
)
]
2
−
1
=
0
∑
[
(
,
)
−
′
(
,
)
]
2
−
1
=
0
(
1
)
W
h
er
e
MSE
is
th
e
R
MSE
o
b
t
ain
ed
,
x
(
i
,
j
)
is
th
e
o
r
ig
i
n
al
i
m
ag
e,
x
’
(
i,
j)
is
th
e
r
eg
e
n
er
at
ed
im
ag
e,
an
d
M*
N
is
th
e
to
tal
n
u
m
b
er
o
f
r
o
ws
an
d
co
lu
m
n
s
o
f
th
e
im
ag
e.
T
a
b
le.
1
s
h
o
ws
th
e
t
h
eo
r
etica
l
R
MSE
ca
lcu
lated
o
n
ea
ch
o
f
th
e
r
eg
e
n
er
ated
im
a
g
e
s
.
T
ab
le
1
.
T
h
eo
r
etica
l RMSE
ca
lcu
lated
o
n
ea
c
h
o
f
t
h
e
r
eg
e
n
e
r
ated
im
ag
es
F
i
g
u
r
e
d
e
t
a
i
l
s
N
o
.
o
f
g
o
o
d
m
a
t
c
h
e
s
R
M
S
E
5
(
a
)
10
3
.
8
4
5
(
b
)
1
0
0
6
.
1
2
5
(
c
)
4
0
0
7
.
2
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
V
id
eo
mo
s
a
ic:
emp
lo
yi
n
g
a
n
e
fficien
t O
R
B
fea
tu
r
e
ex
tr
a
ctio
n
tech
n
iq
u
e
w
ith
h
a
mmin
g
…
(
S
h
r
id
h
a
r
H
)
169
W
e
also
tr
ied
to
s
ee
th
e
im
p
ac
t
o
f
g
o
o
d
m
atc
h
es
o
n
R
MS
E
b
etwe
en
th
e
two
co
n
s
ec
u
tiv
e
f
r
am
es.
T
h
is
g
iv
es
u
s
id
ea
s
o
f
h
o
w
d
i
f
f
er
en
t
t
h
ese
two
c
o
n
s
ec
u
tiv
e
f
r
am
es.
T
h
e
lar
g
e
r
th
e
v
alu
e
o
f
R
MSE
,
th
e
m
o
r
e
d
if
f
er
en
t
th
e
f
r
am
es
an
d
less
is
th
e
p
r
o
b
ab
ilit
y
o
f
in
clu
d
in
g
o
v
er
lap
p
i
n
g
f
r
am
es
in
th
e
o
u
tp
u
t
v
id
eo
m
o
s
aic.
B
u
t
a
to
o
h
ig
h
o
f
R
MSE
will
m
is
alig
n
th
e
v
id
eo
f
r
am
es
a
n
d
in
cr
ea
s
es
th
e
c
h
an
ce
s
o
f
m
is
s
in
g
r
elev
a
n
t
f
r
am
e
d
etails.
T
h
er
ef
o
r
e,
we
ex
p
e
r
im
en
ted
with
d
if
f
er
e
n
t
n
u
m
b
e
r
s
o
f
g
o
o
d
m
atch
es
b
etwe
en
t
h
e
f
r
a
m
es
an
d
th
eir
co
r
r
esp
o
n
d
in
g
R
MSE
as
tab
u
lated
in
T
ab
le
1
.
I
t
is
s
ee
n
th
at
4
0
0
is
th
e
o
p
tim
u
m
n
u
m
b
e
r
o
f
g
o
o
d
m
atc
h
es
b
etwe
en
f
r
a
m
es
as
it
p
r
o
v
id
es
a
g
o
o
d
tr
ad
e
-
o
f
f
b
etwe
en
co
m
p
u
tatio
n
ef
f
icien
cy
an
d
q
u
al
ity
o
f
o
u
tp
u
t
v
i
d
eo
m
o
s
aic.
Her
e,
it
is
im
p
o
r
tan
t
to
n
o
te
t
h
at
an
e
x
tr
em
ely
lar
g
e
n
u
m
b
er
o
f
m
atch
es
ar
en
’
t
alwa
y
s
b
etter
.
T
o
m
an
y
m
atc
h
es
m
ig
h
t
in
tr
o
d
u
ce
m
o
r
e
p
o
ten
tial
f
o
r
er
r
o
r
s
,
esp
ec
ially
wh
en
d
ea
lin
g
with
s
ce
n
es
th
at
h
av
e
r
ep
ea
ted
p
atter
n
s
o
r
a
lo
t o
f
cl
u
tter
.
Ad
d
itio
n
ally
,
c
o
m
p
u
tatio
n
al
r
eso
u
r
ce
s
ca
n
b
ec
o
m
e
a
l
im
itin
g
f
ac
to
r
as
th
e
n
u
m
b
er
o
f
m
atc
h
es
’
in
c
r
ea
s
es,
wh
ich
ca
n
af
f
ec
t
th
e
s
titch
in
g
p
r
o
ce
s
s
’
s
ef
f
icien
cy
.
S
o
,
wh
ile
a
h
ig
h
er
n
u
m
b
er
o
f
m
atc
h
es
ar
e
d
esira
b
le,
th
er
e
is
u
s
u
ally
a
p
r
ac
tical
r
a
n
g
e
b
ased
o
n
t
h
e
n
atu
r
e
o
f
th
e
s
ce
n
e
an
d
th
e
co
m
p
u
tatio
n
al
r
eso
u
r
ce
s
a
v
ailab
le.
B
alan
cin
g
th
e
n
u
m
b
er
o
f
m
atch
es
an
d
th
e
q
u
ality
o
f
m
atch
es
is
k
ey
to
ac
h
iev
in
g
th
e
b
est
m
o
s
aic
r
es
u
lts
f
o
r
y
o
u
r
s
p
ec
if
ic
ap
p
licati
o
n
an
d
th
at
is
wh
y
we
ch
o
o
s
e
4
0
0
as
th
e
o
p
tim
al
n
u
m
b
er
o
f
g
o
o
d
m
atch
es to
o
b
tain
a
v
id
eo
p
an
o
r
am
ic
v
iew.
9.
CO
NCLU
SI
O
NS A
ND
F
UT
URE SCO
P
E
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
a
d
d
r
ess
es
ch
allen
g
es
in
cr
ea
tin
g
s
ea
m
less
an
d
co
n
tin
u
o
u
s
v
id
e
o
m
o
s
aics,
f
o
cu
s
in
g
o
n
ca
m
er
a
m
o
tio
n
an
d
co
n
te
n
t
v
ar
iatio
n
s
ac
r
o
s
s
f
r
am
es.
T
h
e
co
r
e
al
g
o
r
ith
m
r
esid
es
in
a
f
r
am
e
p
r
o
ce
s
s
in
g
lo
o
p
,
i
n
itializin
g
v
ar
iab
les
lik
e
a
m
o
s
aic
co
n
tain
er
an
d
th
e
p
r
ev
i
o
u
s
f
r
a
m
e.
I
te
r
atin
g
th
r
o
u
g
h
v
i
d
eo
f
r
am
es,
it
ca
lcu
lates
o
v
er
la
p
p
er
ce
n
tag
es.
W
h
en
b
elo
w
t
h
e
th
r
esh
o
ld
,
th
e
al
g
o
r
ith
m
u
s
es
OR
B
f
ea
tu
r
e
d
etec
tio
n
an
d
m
atch
in
g
f
o
r
f
r
am
e
alig
n
m
en
t.
T
h
e
s
u
cc
ess
f
u
l
m
atch
es
y
ield
a
h
o
m
o
g
r
ap
h
y
m
atr
ix
(
M
)
.
T
h
e
cu
r
r
e
n
t
f
r
a
m
e
war
p
s
to
alig
n
with
th
e
p
r
ev
io
u
s
o
n
e
u
s
in
g
th
e
m
atr
ix
,
u
p
d
atin
g
t
h
e
m
o
s
aic
th
r
o
u
g
h
b
len
d
in
g
.
T
h
is
iter
ativ
e
p
r
o
ce
s
s
co
n
tin
u
es
u
n
til
th
e
r
esu
ltin
g
m
o
s
aic
f
r
am
e
to
th
e
o
u
tp
u
t
v
i
d
eo
,
d
is
p
lay
ed
,
an
d
m
o
n
ito
r
ed
f
o
r
i
n
ter
r
u
p
tio
n
s
.
T
h
e
alg
o
r
ith
m
ef
f
ec
tiv
ely
p
r
o
d
u
ce
s
a
v
id
eo
m
o
s
aic
with
alig
n
ed
,
b
le
n
d
ed
n
o
n
-
o
v
er
lap
p
i
n
g
f
r
am
es,
h
ig
h
lig
h
t
in
g
its
p
r
o
wess
in
ad
d
r
ess
in
g
v
id
eo
f
r
am
e
alig
n
m
en
t
an
d
b
l
en
d
in
g
ch
allen
g
es.
T
h
e
o
u
tp
u
t
v
id
eo
s
er
v
es
as
ev
i
d
en
ce
o
f
th
e
al
g
o
r
ith
m
’
s
ca
p
ab
ilit
ies.
Ou
r
f
in
d
in
g
s
d
em
o
n
s
tr
ate
th
e
alg
o
r
ith
m
’
s
p
o
ten
tial
to
im
p
ac
t
t
h
e
r
esear
ch
f
ield
an
d
o
f
f
er
v
a
lu
ab
le
in
s
ig
h
ts
f
o
r
p
r
ac
tical
ap
p
licatio
n
s
.
B
y
p
r
o
v
id
in
g
a
r
o
b
u
s
t
an
d
ef
f
icien
t
s
o
lu
tio
n
,
th
is
wo
r
k
p
a
v
es
th
e
way
f
o
r
f
u
tu
r
e
a
d
v
an
ce
m
en
ts
in
v
id
eo
m
o
s
aicin
g
tech
n
o
lo
g
y
,
co
n
t
r
ib
u
tin
g
to
t
h
e
b
r
o
ad
er
g
o
als
o
f
en
h
a
n
cin
g
v
is
u
al
ex
p
er
ien
ce
s
an
d
ex
p
an
d
in
g
th
e
ca
p
a
b
ilit
ies
o
f
co
m
p
u
ter
v
is
io
n
s
y
s
tem
s
.
W
h
ile,
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
s
h
o
ws
p
r
o
m
is
e,
th
e
r
e
ar
e
o
p
p
o
r
tu
n
ities
f
o
r
f
u
r
t
h
er
r
esear
ch
an
d
d
ev
el
o
p
m
en
t.
A
d
d
itio
n
ally
,
e
x
p
an
d
in
g
t
h
e
al
g
o
r
ith
m
t
o
h
a
n
d
le
h
i
g
h
er
r
eso
lu
tio
n
s
an
d
m
o
r
e
s
ig
n
if
ican
t
p
ar
allax
ef
f
ec
ts
co
u
ld
en
h
an
ce
its
ap
p
licab
ilit
y
to
m
o
r
e
ch
allen
g
in
g
s
ce
n
ar
io
s
.
E
x
p
lo
r
in
g
h
ar
d
war
e
ac
ce
ler
atio
n
o
p
tio
n
s
,
s
u
ch
as
GPU
p
r
o
ce
s
s
in
g
,
co
u
ld
also
o
p
tim
ize
th
e
alg
o
r
ith
m
f
o
r
r
ea
l
-
tim
e
ap
p
licatio
n
s
in
r
eso
u
r
ce
-
co
n
s
tr
ain
ed
en
v
ir
o
n
m
en
ts
.
RE
F
E
R
E
NC
E
S
[
1
]
K
.
W
a
n
g
,
T.
Y
a
n
g
,
X
.
Zh
a
n
g
,
a
n
d
M
.
T
a
n
g
,
“
A
n
i
m
p
r
o
v
e
d
u
l
t
r
a
-
h
i
g
h
d
e
f
i
n
i
t
i
o
n
p
a
n
o
r
a
mi
c
v
i
d
e
o
mo
s
a
i
c
met
h
o
d
f
o
r
a
i
r
p
o
r
t
sce
n
e
,
”
i
n
2
0
2
2
I
EEE
8
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
s,
I
C
C
C
2
0
22
,
D
e
c
.
2
0
2
2
,
p
p
.
2
0
7
6
–
2
0
8
0
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
C
5
6
3
2
4
.
2
0
2
2
.
1
0
0
6
5
8
9
9
.
[
2
]
J.
S
.
S
u
ma
n
t
r
i
a
n
d
K
.
P
a
r
k
,
“
3
6
0
p
a
n
o
r
a
ma
s
y
n
t
h
e
s
i
s
f
r
o
m
a
sp
a
r
se
s
e
t
o
f
i
ma
g
e
s
o
n
a
l
o
w
-
p
o
w
e
r
d
e
v
i
c
e
,
”
I
EEE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
C
o
m
p
u
t
a
t
i
o
n
a
l
I
m
a
g
i
n
g
,
v
o
l
.
6
,
p
p
.
1
1
7
9
–
1
1
9
3
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
T
C
i
.
2
0
2
0
.
3
0
1
1
8
5
4
.
[
3
]
X
.
B
a
i
,
“
O
v
e
r
v
i
e
w
o
f
i
m
a
g
e
m
o
sa
i
c
t
e
c
h
n
o
l
o
g
y
b
y
c
o
m
p
u
t
e
r
v
i
s
i
o
n
a
n
d
d
i
g
i
t
a
l
i
m
a
g
e
p
r
o
c
e
ssi
n
g
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
2
0
2
1
I
EE
E
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
D
a
t
a
S
c
i
e
n
c
e
a
n
d
C
o
m
p
u
t
e
r
Ap
p
l
i
c
a
t
i
o
n
,
I
C
D
S
C
A
2
0
2
1
,
O
c
t
.
2
0
2
1
,
p
p
.
5
6
9
–
5
7
2
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
D
S
C
A
5
3
4
9
9
.
2
0
2
1
.
9
6
5
0
3
2
9
.
[
4
]
S
.
P
a
r
i
so
t
t
o
,
L.
C
a
l
a
t
r
o
n
i
,
A
.
B
u
g
e
a
u
,
N
.
P
a
p
a
d
a
k
i
s,
a
n
d
C
.
B
.
S
c
h
o
n
l
i
e
b
,
“
V
a
r
i
a
t
i
o
n
a
l
o
sm
o
si
s
f
o
r
n
o
n
-
l
i
n
e
a
r
i
ma
g
e
f
u
si
o
n
,
”
I
EEE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
I
m
a
g
e
Pro
c
e
ss
i
n
g
,
v
o
l
.
2
9
,
p
p
.
5
5
0
7
–
5
5
1
6
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
P
.
2
0
2
0
.
2
9
8
3
5
3
7
.
[
5
]
K
.
S
.
C
h
a
n
g
a
n
a
n
d
P
.
G
.
C
h
i
l
v
e
r
i
,
“
S
t
e
r
e
o
i
ma
g
e
f
e
a
t
u
r
e
ma
t
c
h
i
n
g
u
si
n
g
H
a
r
r
i
s
c
o
r
n
e
r
d
e
t
e
c
t
i
o
n
a
l
g
o
r
i
t
h
m,
”
i
n
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
A
u
t
o
m
a
t
i
c
C
o
n
t
r
o
l
a
n
d
D
y
n
a
m
i
c
O
p
t
i
m
i
z
a
t
i
o
n
T
e
c
h
n
i
q
u
e
s,
I
C
AC
D
O
T
2
0
1
6
,
S
e
p
.
2
0
1
7
,
p
p
.
6
9
1
–
6
9
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
C
D
O
T.
2
0
1
6
.
7
8
7
7
6
7
5
.
[
6
]
J.
D
u
,
W
.
Li
,
a
n
d
H
.
Ta
n
,
“
Th
r
e
e
-
l
a
y
e
r
i
m
a
g
e
r
e
p
r
e
se
n
t
a
t
i
o
n
b
y
a
n
e
n
h
a
n
c
e
d
i
l
l
u
mi
n
a
t
i
o
n
-
b
a
se
d
i
ma
g
e
f
u
si
o
n
me
t
h
o
d
,
”
I
E
EE
J
o
u
r
n
a
l
o
f
Bi
o
m
e
d
i
c
a
l
a
n
d
H
e
a
l
t
h
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
2
4
,
n
o
.
4
,
p
p
.
1
1
6
9
–
1
1
7
9
,
A
p
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
J
B
H
I
.
2
0
1
9
.
2
9
3
0
9
7
8
.
[
7
]
X
.
La
n
,
B
.
G
u
o
,
Z
.
H
u
a
n
g
,
a
n
d
S
.
Z
h
a
n
g
,
“
A
n
i
mp
r
o
v
e
d
U
A
V
a
e
r
i
a
l
i
m
a
g
e
mo
s
a
i
c
a
l
g
o
r
i
t
h
m b
a
s
e
d
o
n
G
M
S
-
R
A
N
S
A
C
,
”
i
n
2
0
2
0
I
EEE
5
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
i
g
n
a
l
a
n
d
I
m
a
g
e
Pro
c
e
ssi
n
g
,
I
C
S
I
P
2
0
2
0
,
O
c
t
.
2
0
2
0
,
p
p
.
1
4
8
–
1
5
2
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
S
I
P
4
9
8
9
6
.
2
0
2
0
.
9
3
3
9
2
8
3
.
[
8
]
P
.
Y
a
n
g
a
n
d
Z.
M
a
o
,
“
T
h
e
r
e
s
e
a
r
c
h
o
n
i
ma
g
e
m
o
sai
c
s
f
o
r
i
n
t
e
l
l
i
g
e
n
t
v
i
d
e
o
su
r
v
e
i
l
l
a
n
c
e
,
”
i
n
I
C
I
N
A
2
0
1
0
-
2
0
1
0
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
n
f
o
rm
a
t
i
o
n
,
N
e
t
w
o
r
k
i
n
g
a
n
d
A
u
t
o
m
a
t
i
o
n
,
Pro
c
e
e
d
i
n
g
s
,
O
c
t
.
2
0
1
0
,
v
o
l
.
2
,
p
p
.
V
2
-
59
-
V2
-
6
2
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
N
A
.
2
0
1
0
.
5
6
3
6
7
8
4
.
[
9
]
S
.
H
a
n
,
W
.
Y
u
,
H
.
Y
a
n
g
,
a
n
d
S
.
W
a
n
,
“
A
n
i
m
p
r
o
v
e
d
c
o
r
n
e
r
d
e
t
e
c
t
i
o
n
a
l
g
o
r
i
t
h
m
b
a
se
d
o
n
h
a
r
r
i
s
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
2
0
1
8
C
h
i
n
e
s
e
Au
t
o
m
a
t
i
o
n
C
o
n
g
ress
,
C
AC
2
0
1
8
,
N
o
v
.
2
0
1
8
,
p
p
.
1
5
7
5
–
1
5
8
0
,
d
o
i
:
1
0
.
1
1
0
9
/
C
A
C
.
2
0
1
8
.
8
6
2
3
8
1
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
1
,
Ap
r
il
20
2
5
:
1
61
-
1
71
170
[
1
0
]
H
.
Li
,
J
.
W
a
n
g
,
a
n
d
C
.
H
a
n
,
“
I
mag
e
mo
sa
i
c
a
n
d
h
y
b
r
i
d
f
u
si
o
n
a
l
g
o
r
i
t
h
m
b
a
se
d
o
n
p
y
r
a
mi
d
d
e
c
o
m
p
o
si
t
i
o
n
,
”
i
n
P
ro
c
e
e
d
i
n
g
s
-
2
0
2
0
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
V
i
r
t
u
a
l
Re
a
l
i
t
y
a
n
d
V
i
s
u
a
l
i
z
a
t
i
o
n
,
I
C
VRV
2
0
2
0
,
N
o
v
.
2
0
2
0
,
p
p
.
2
0
5
–
2
0
8
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
V
R
V
5
1
3
5
9
.
2
0
2
0
.
0
0
0
4
9
.
[
1
1
]
H
.
K
a
n
g
,
L
.
X
u
e
f
e
i
,
a
n
d
Z
.
W
e
n
h
u
i
,
“
A
n
a
d
a
p
t
i
v
e
f
u
s
i
o
n
p
a
n
o
r
a
mi
c
i
m
a
g
e
mo
s
a
i
c
a
l
g
o
r
i
t
h
m
b
a
s
e
d
o
n
c
i
r
c
u
l
a
r
LB
P
f
e
a
t
u
r
e
a
n
d
H
S
V
c
o
l
o
r
sy
s
t
e
m
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
2
0
2
0
I
EE
E
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
B
i
g
D
a
t
a
a
n
d
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
I
C
I
B
A
2
0
2
0
,
N
o
v
.
2
0
2
0
,
p
p
.
9
4
–
1
0
0
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
B
A
5
0
1
6
1
.
2
0
2
0
.
9
2
7
7
3
4
8
.
[
1
2
]
C
.
X
i
u
,
J.
F
a
n
g
,
a
n
d
J.
Zh
a
n
g
,
“
I
mag
e
s
t
i
t
c
h
i
n
g
me
t
h
o
d
b
a
se
d
o
n
a
d
a
p
t
i
v
e
w
e
i
g
h
t
e
d
f
u
s
i
o
n
,
”
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
3
3
r
d
C
h
i
n
e
se
C
o
n
t
r
o
l
a
n
d
D
e
c
i
s
i
o
n
C
o
n
f
e
r
e
n
c
e
,
C
C
D
C
2
0
2
1
,
p
p
.
3
0
9
9
–
3
1
0
3
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
C
C
D
C
5
2
3
1
2
.
2
0
2
1
.
9
6
0
2
5
2
9
.
[
1
3
]
H
.
R
e
n
a
n
d
Q
.
R
e
n
,
“
R
e
a
l
-
t
i
me
p
a
n
o
r
a
mi
c
v
i
d
e
o
mo
s
a
i
c
s
y
st
e
m
b
a
se
d
o
n
map
p
i
n
g
t
a
b
l
e
a
n
d
G
P
U
a
c
c
e
l
e
r
a
t
i
o
n
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
3
3
rd
C
h
i
n
e
se
C
o
n
t
r
o
l
a
n
d
D
e
c
i
si
o
n
C
o
n
f
e
re
n
c
e
,
C
C
D
C
2
0
2
1
,
M
a
y
2
0
2
1
,
p
p
.
8
1
2
–
8
1
6
,
d
o
i
:
1
0
.
1
1
0
9
/
C
C
D
C
5
2
3
1
2
.
2
0
2
1
.
9
6
0
1
6
7
6
.
[
1
4
]
J.
Le
e
,
B
.
K
i
m,
K
.
K
i
m,
Y
.
K
i
m,
a
n
d
J.
N
o
h
,
“
R
i
c
h
3
6
0
:
o
p
t
i
m
i
z
e
d
sp
h
e
r
i
c
a
l
r
e
p
r
e
se
n
t
a
t
i
o
n
f
r
o
m
st
r
u
c
t
u
r
e
d
p
a
n
o
r
a
m
i
c
c
a
mer
a
a
r
r
a
y
s,
”
A
C
M
T
ra
n
s
a
c
t
i
o
n
s
o
n
G
ra
p
h
i
c
s
,
v
o
l
.
3
5
,
n
o
.
4
,
p
p
.
1
–
1
1
,
Ju
l
.
2
0
1
6
,
d
o
i
:
1
0
.
1
1
4
5
/
2
8
9
7
8
2
4
.
2
9
2
5
9
8
3
.
[
1
5
]
Y
.
N
i
e
,
T.
S
u
,
Z
.
Z
h
a
n
g
,
H
.
S
u
n
,
a
n
d
G
.
L
i
,
“
D
y
n
a
m
i
c
v
i
d
e
o
s
t
i
t
c
h
i
n
g
v
i
a
sh
a
k
i
n
e
ss
r
e
m
o
v
i
n
g
,
”
I
E
EE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
I
m
a
g
e
Pro
c
e
ssi
n
g
,
v
o
l
.
2
7
,
n
o
.
1
,
p
p
.
1
6
4
–
1
7
8
,
J
a
n
.
2
0
1
8
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
P
.
2
0
1
7
.
2
7
3
6
6
0
3
.
[
1
6
]
Q
.
W
e
i
,
N
.
D
o
b
i
g
e
o
n
,
a
n
d
J.
Y
.
T
o
u
r
n
e
r
e
t
,
“
B
a
y
e
si
a
n
f
u
si
o
n
o
f
m
u
l
t
i
-
b
a
n
d
i
ma
g
e
s,
”
I
EEE
J
o
u
r
n
a
l
o
n
S
e
l
e
c
t
e
d
T
o
p
i
c
s
i
n
S
i
g
n
a
l
Pro
c
e
ssi
n
g
,
v
o
l
.
9
,
n
o
.
6
,
p
p
.
1
1
1
7
–
1
1
2
7
,
S
e
p
.
2
0
1
5
,
d
o
i
:
1
0
.
1
1
0
9
/
JS
TSP
.
2
0
1
5
.
2
4
0
7
8
5
5
.
[
1
7
]
X
.
L
i
,
W
.
Z
h
u
,
a
n
d
Q
.
Z
h
u
,
“
P
a
n
o
r
a
mi
c
v
i
d
e
o
st
i
t
c
h
i
n
g
b
a
se
d
o
n
mu
l
t
i
-
b
a
n
d
i
ma
g
e
b
l
e
n
d
i
n
g
,
”
i
n
T
e
n
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
G
ra
p
h
i
c
s
a
n
d
I
m
a
g
e
Pr
o
c
e
ssi
n
g
(
I
C
G
I
P
2
0
1
8
)
,
M
a
y
2
0
1
9
,
p
.
8
2
,
d
o
i
:
1
0
.
1
1
1
7
/
1
2
.
2
5
2
4
2
4
7
.
[
1
8
]
H
.
S
h
r
i
d
h
a
r
,
S
.
S
.
H
a
r
a
k
a
n
n
a
n
a
v
a
r
,
V
.
K
a
n
a
b
u
r
,
a
n
d
H
.
Ja
y
a
l
a
x
m
i
,
“
P
e
r
f
o
r
ma
n
c
e
a
n
a
l
y
si
s
o
f
f
e
a
t
u
r
e
b
a
se
d
m
u
l
t
i
p
l
e
d
e
s
c
r
i
p
t
o
r
s
w
i
t
h
h
i
st
o
g
r
a
m
e
q
u
a
l
i
z
a
t
i
o
n
f
o
r
i
ma
g
e
mo
s
a
i
c
i
n
g
,
”
I
n
d
i
a
n
J
o
u
r
n
a
l
O
f
S
c
i
e
n
c
e
An
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
6
,
n
o
.
3
1
,
p
p
.
2
3
8
0
–
2
3
8
7
,
A
u
g
.
2
0
2
3
,
d
o
i
:
1
0
.
1
7
4
8
5
/
i
j
s
t
/
v
1
6
i
3
1
.
4
3
3
.
[
1
9
]
B
.
W
a
n
g
,
H
.
L
i
,
a
n
d
W
.
H
u
,
“
R
e
sea
r
c
h
o
n
k
e
y
t
e
c
h
n
i
q
u
e
s
o
f
m
u
l
t
i
-
r
e
s
o
l
u
t
i
o
n
c
o
a
st
l
i
n
e
i
m
a
g
e
f
u
si
o
n
b
a
s
e
d
o
n
o
p
t
i
ma
l
s
e
a
m
-
l
i
n
e
,
”
Ea
rt
h
S
c
i
e
n
c
e
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
3
,
n
o
.
2
,
p
p
.
3
3
3
–
3
4
4
,
J
u
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
2
1
4
5
-
019
-
0
0
4
2
1
-
z.
[
2
0
]
C
.
C
.
Li
n
,
S
.
U
.
P
a
n
k
a
n
t
i
,
K
.
N
.
R
a
m
a
m
u
r
t
h
y
,
a
n
d
A
.
Y
.
A
r
a
v
k
i
n
,
“
A
d
a
p
t
i
v
e
a
s
-
n
a
t
u
r
a
l
-
as
-
p
o
ssi
b
l
e
i
mag
e
st
i
t
c
h
i
n
g
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
I
E
EE
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
Vi
si
o
n
a
n
d
P
a
t
t
e
rn
Re
c
o
g
n
i
t
i
o
n
,
Ju
n
.
2
0
1
5
,
v
o
l
.
0
7
-
12
-
Ju
n
e
-
2
0
1
5
,
p
p
.
1
1
5
5
–
1
1
6
3
,
d
o
i
:
1
0
.
1
1
0
9
/
C
V
P
R
.
2
0
1
5
.
7
2
9
8
7
1
9
.
[
2
1
]
H
.
S
h
r
i
d
h
a
r
,
B
.
N
e
e
l
g
a
r
,
a
n
d
R
.
P
r
e
man
a
n
d
a
,
“
A
n
i
mp
r
o
v
e
d
i
m
a
g
e
f
u
si
o
n
t
e
c
h
n
i
q
u
e
b
a
se
d
o
n
w
a
v
e
l
e
t
a
n
d
e
d
g
e
g
r
a
d
i
e
n
t
s
t
o
a
u
g
me
n
t
s
p
a
t
i
a
l
p
r
o
mi
n
e
n
c
e
o
f
i
ma
g
e
f
e
a
t
u
r
e
s
,
”
i
n
3
r
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
El
e
c
t
ri
c
a
l
,
E
l
e
c
t
r
o
n
i
c
s
,
C
o
m
m
u
n
i
c
a
t
i
o
n
,
C
o
m
p
u
t
e
r
T
e
c
h
n
o
l
o
g
i
e
s
a
n
d
O
p
t
i
m
i
z
a
t
i
o
n
T
e
c
h
n
i
q
u
e
s
,
I
C
EE
C
C
O
T
2
0
1
8
,
D
e
c
.
2
0
1
8
,
p
p
.
4
1
6
–
4
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
EE
C
C
O
T
4
3
7
2
2
.
2
0
1
8
.
9
0
0
1
4
7
0
.
[
2
2
]
A
.
L.
R
.
S
i
r
i
a
n
i
,
I
.
B
.
d
e
C
.
M
i
r
a
n
d
a
,
S
.
A
.
M
e
h
d
i
z
a
d
e
h
,
a
n
d
D
.
F
.
P
e
r
e
i
r
a
,
“
C
h
i
c
k
e
n
t
r
a
c
k
i
n
g
a
n
d
i
n
d
i
v
i
d
u
a
l
b
i
r
d
a
c
t
i
v
i
t
y
mo
n
i
t
o
r
i
n
g
u
si
n
g
t
h
e
B
o
T
-
S
O
R
T
a
l
g
o
r
i
t
h
m,”
A
g
ri
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
5
,
n
o
.
4
,
p
p
.
1
6
7
7
–
1
6
9
3
,
S
e
p
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
g
r
i
e
n
g
i
n
e
e
r
i
n
g
5
0
4
0
1
0
4
.
[
2
3
]
J.
M
.
G
ó
r
r
i
z
e
t
a
l
.
,
“
C
o
mp
u
t
a
t
i
o
n
a
l
a
p
p
r
o
a
c
h
e
s
t
o
e
x
p
l
a
i
n
a
b
l
e
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
:
a
d
v
a
n
c
e
s
i
n
t
h
e
o
r
y
,
a
p
p
l
i
c
a
t
i
o
n
s
a
n
d
t
r
e
n
d
s,”
I
n
f
o
rm
a
t
i
o
n
F
u
si
o
n
,
v
o
l
.
1
0
0
,
p
.
1
0
1
9
4
5
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
f
f
u
s
.
2
0
2
3
.
1
0
1
9
4
5
.
[
2
4
]
C
.
W
.
Li
n
,
S
.
H
o
n
g
,
M
.
L
i
n
,
X
.
H
u
a
n
g
,
a
n
d
J.
L
i
u
,
“
B
i
r
d
p
o
s
t
u
r
e
r
e
c
o
g
n
i
t
i
o
n
b
a
se
d
o
n
t
a
r
g
e
t
k
e
y
p
o
i
n
t
s
e
s
t
i
m
a
t
i
o
n
i
n
d
u
a
l
-
t
a
s
k
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
,
”
E
c
o
l
o
g
i
c
a
l
I
n
d
i
c
a
t
o
rs
,
v
o
l
.
1
3
5
,
p
.
1
0
8
5
0
6
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
c
o
l
i
n
d
.
2
0
2
1
.
1
0
8
5
0
6
.
[2
5
]
C
.
R
e
n
t
e
r
i
a
,
J.
S
u
á
r
e
z
,
A
.
L
i
c
u
d
i
n
e
,
a
n
d
S
.
A
.
B
o
p
p
a
r
t
,
“
D
e
p
i
x
e
l
a
t
i
o
n
a
n
d
e
n
h
a
n
c
e
me
n
t
o
f
f
i
b
e
r
b
u
n
d
l
e
i
mag
e
s
b
y
b
u
n
d
l
e
r
o
t
a
t
i
o
n
,
”
A
p
p
l
i
e
d
O
p
t
i
c
s
,
v
o
l
.
5
9
,
n
o
.
2
,
p
.
5
3
6
,
J
a
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
3
6
4
/
a
o
.
5
9
.
0
0
0
5
3
6
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Mr.
S
h
r
id
h
a
r
H
re
c
e
iv
e
d
th
e
B.
E
d
e
g
re
e
in
El
e
c
tro
n
ics
a
n
d
Co
m
m
u
n
ica
ti
o
n
En
g
i
n
e
e
rin
g
(S
.
T.
J.I.
T
,
Ra
n
e
b
e
n
n
u
r)
a
n
d
M
.
Tec
h
d
e
g
re
e
in
th
e
stre
a
m
o
f
VLS
I
De
sig
n
a
n
d
Emb
e
d
d
e
d
S
y
ste
m
s
(V.T
.
U.
Re
g
io
n
a
l
Ce
n
ter)
u
n
d
e
r
Visv
e
sv
a
ra
y
a
Tec
h
n
o
lo
g
ica
l
Un
i
v
e
rsity
,
Jn
a
n
a
S
a
n
g
a
m
a
,
Be
lag
a
v
i,
Ka
rn
a
tak
a
,
In
d
ia.
He
is
c
u
rre
n
tl
y
wo
r
k
i
n
g
a
s
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
in
E
lec
tro
n
ics
a
n
d
Co
m
m
u
n
ica
ti
o
n
E
n
g
i
n
e
e
rin
g
De
p
t,
G
o
v
e
rn
m
e
n
t
En
g
in
e
e
rin
g
C
o
ll
e
g
e
Ha
v
e
ri
-
5
8
1
1
1
0
,
Ka
rn
a
tak
a
I
n
d
ia.
He
h
a
s
1
6
y
e
a
rs
o
f
tea
c
h
i
n
g
e
x
p
e
rien
c
e
.
He
h
a
s
p
u
b
li
sh
e
d
a
ro
u
n
d
3
a
rt
icle
s
in
P
e
e
r
re
c
e
iv
e
d
I
n
tern
a
ti
o
n
a
l
Jo
u
rn
a
l.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
c
o
m
p
u
ter
v
isio
n
,
ima
g
e
p
a
tt
e
rn
re
c
o
g
n
it
i
o
n
,
a
n
d
b
i
o
m
e
tri
c
s
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sh
rid
h
a
r
4
7
@
g
m
a
il
.
c
o
m
.
Dr
.
S
u
n
il
S
.
H
a
r
a
k
a
n
n
a
n
a
v
a
r
re
c
e
iv
e
d
th
e
B.
E
.
d
e
g
re
e
i
n
El
e
c
tro
n
ics
a
n
d
Co
m
m
u
n
ica
ti
o
n
E
n
g
i
n
e
e
rin
g
(
S
.
T.
J.I.
T
Ra
n
e
b
e
n
n
u
r)
a
n
d
M
.
Tec
h
d
e
g
re
e
i
n
th
e
stre
a
m
o
f
M
icro
e
lec
tro
n
ics
a
n
d
Co
n
tr
o
l
S
y
ste
m
s
(NMAM
IT,
Ni
tt
e
)
u
n
d
e
r
Visv
e
sv
a
ra
y
a
Tec
h
n
o
lo
g
ica
l
Un
iv
e
rsity
,
Jn
a
n
a
S
a
n
g
a
m
a
,
Be
lag
a
v
i,
Ka
rn
a
tak
a
,
I
n
d
ia.
He
is
c
u
rre
n
tl
y
w
o
rk
i
n
g
a
s
a
n
As
so
c
iate
P
ro
fe
ss
o
r
in
E
lec
tro
n
i
c
s
a
n
d
Co
m
m
u
n
ica
ti
o
n
En
g
in
e
e
r
in
g
De
p
t
Nitt
e
M
e
e
n
a
k
s
h
i
In
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
Ye
lah
a
n
k
a
,
Ba
n
g
a
lo
re
-
5
6
0
0
6
4
,
Ka
rn
a
tak
a
In
d
ia.
He
h
a
s
1
4
y
e
a
rs
o
f
Tea
c
h
in
g
E
x
p
e
rien
c
e
.
He
h
a
s
p
u
b
li
s
h
e
d
a
ro
u
n
d
2
5
a
rti
c
les
in
P
e
e
r
re
c
e
iv
e
d
In
tern
a
ti
o
n
a
l
Jo
u
rn
a
l.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
c
o
m
p
u
ter
v
isi
o
n
,
ima
g
e
p
a
tt
e
rn
re
c
o
g
n
it
i
o
n
,
a
n
d
b
io
m
e
tri
c
s
.
He
is
a
l
ife
m
e
m
b
e
r
o
f
In
d
ian
S
o
c
iet
y
f
o
r
Tec
h
n
ica
l
E
d
u
c
a
ti
o
n
(LM
I
S
TE
).
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
s
u
n
il
s
h
1
4
3
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.