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.
23
,
No
.
2
,
A
u
g
u
s
t
2
0
2
1
,
p
p
.
8
0
2
~
8
1
0
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
23
.i
2
.
pp
802
-
8
1
0
802
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Efficien
t
re
co
nfig
ura
ble archit
ectu
re f
o
r mo
v
ing
obj
ect
detec
tion wit
h mo
tion co
mpens
a
tio
n
Sridev
i N
.
, M
.
M
ee
na
k
s
hi
De
p
a
rtem
e
n
t
o
f
EIE
,
Dr Am
b
e
d
k
a
r
In
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
,
Ba
n
g
a
lo
re
,
Ka
rn
a
tak
a
,
I
n
d
ia
VTU,
Be
lag
a
v
i,
Ka
rn
a
tak
a
,
In
d
ia
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
8
,
2
0
2
1
R
ev
is
ed
J
u
n
2
5
,
2
0
2
1
Acc
ep
ted
J
u
l 7
,
2
0
2
1
Th
e
d
e
tec
ti
o
n
a
n
d
trac
k
i
n
g
o
f
o
b
jec
t
in
larg
e
d
a
ta
su
rv
e
il
la
n
c
e
re
q
u
ires
a
p
ro
p
e
r
m
o
ti
o
n
e
stim
a
ti
o
n
a
n
d
c
o
m
p
e
n
sa
ti
o
n
tec
h
n
i
q
u
e
s
wh
ich
a
re
g
e
n
e
ra
ll
y
u
se
d
t
o
d
e
tec
t
a
c
c
u
ra
te
m
o
v
e
m
e
n
t
fro
m
v
i
d
e
o
stre
a
m
.
In
t
h
is
p
a
p
e
r,
a
n
o
v
e
l
h
a
rd
wa
re
lev
e
l
a
rc
h
it
e
c
tu
re
i
n
v
o
l
v
i
n
g
m
o
ti
o
n
d
e
tec
ti
o
n
,
e
stim
a
ti
o
n
,
a
n
d
c
o
m
p
e
n
sa
ti
o
n
is
p
ro
p
o
se
d
fo
r
re
a
l
-
ti
m
e
imp
lem
e
n
tatio
n
.
T
h
e
m
o
ti
o
n
v
e
c
to
rs
a
re
o
b
tai
n
e
d
u
si
n
g
1
6
×
1
6
s
u
b
-
b
lo
c
k
s
wit
h
a
n
o
v
e
l
p
a
ra
ll
e
l
D
fli
p
f
lo
p
a
rc
h
it
e
c
tu
re
in
th
is
wo
r
k
to
a
rriv
e
a
t
a
n
o
p
ti
m
ise
d
a
rc
h
it
e
c
tu
re
.
Th
e
su
m
o
f
a
b
so
lu
te
d
iffere
n
c
e
(S
AD
)
is
th
e
n
c
a
lcu
late
d
b
y
o
p
ti
m
ize
d
a
b
so
l
u
te
d
iffere
n
c
e
a
n
d
a
d
d
e
r
b
l
o
c
k
s d
e
sig
n
e
d
u
sin
g
k
o
g
g
e
-
sto
n
e
a
d
d
e
r
wh
i
c
h
h
e
l
p
s
i
n
imp
ro
v
i
n
g
th
e
sp
e
e
d
o
f
th
e
a
rc
h
it
e
c
tu
re
.
Th
e
c
o
n
tr
o
ll
e
r
b
lo
c
k
is
d
e
sig
n
e
d
b
y
fin
it
e
sta
te
m
a
c
h
in
e
m
o
d
e
l
u
se
d
fo
r
sy
n
c
h
ro
n
iza
ti
o
n
o
f
a
ll
t
h
e
o
p
e
ra
ti
o
n
s.
F
u
rth
e
r,
t
h
e
c
o
m
p
a
ra
t
o
r
a
n
d
c
o
m
p
e
n
sa
ti
o
n
b
l
o
c
k
s
a
re
o
p
ti
m
ize
d
b
y
u
si
n
g
b
a
sic
lo
g
ica
l
e
lem
e
n
ts
a
n
d
th
e
Ko
g
g
e
-
st
o
n
e
a
d
d
e
r.
F
i
n
a
ll
y
,
th
e
p
ro
p
o
se
d
a
rc
h
it
e
c
tu
re
is
imp
lem
e
n
ted
o
n
Zy
n
q
Z7
-
10
fiel
d
-
p
r
o
g
ra
m
m
a
b
le
g
a
te
a
rra
y
(
F
P
G
A
)
a
n
d
sim
u
late
d
u
sin
g
S
y
ste
m
G
e
n
e
ra
to
r
to
o
l
f
o
r
re
a
l
t
ime
traffic
sig
n
a
l.
Th
e
h
a
r
d
wa
re
a
n
d
so
ftwa
r
e
p
a
ra
m
e
ters
a
re
c
o
m
p
a
re
d
wit
h
t
h
e
e
x
isti
n
g
tec
h
n
iq
u
e
s
wh
ich
sh
o
ws
th
a
t
t
h
e
p
ro
p
o
se
d
a
rc
h
it
e
c
t
u
re
is
e
fficie
n
t
th
a
n
e
x
isti
n
g
m
e
th
o
d
s o
f
d
e
sig
n
.
K
ey
w
o
r
d
s
:
FP
GA
ar
ch
itectu
r
e
Mo
tio
n
co
m
p
en
s
atio
n
Mo
tio
n
esti
m
atio
n
Vid
eo
p
r
o
ce
s
s
in
g
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
:
Srid
ev
i N
.
Dep
ar
tm
en
t o
f
E
lectr
o
n
ics an
d
I
n
s
tr
u
m
en
tatio
n
E
n
g
i
n
ee
r
in
g
Dr
Am
b
ed
k
ar
I
n
s
titu
te
o
f
T
ec
h
n
o
lo
g
y
Ou
ter
R
in
g
R
o
ad
,
Ma
llath
ah
al
li,
B
an
g
alo
r
e,
Kar
n
atak
a
,
I
n
d
i
a
E
m
ail: sr
id
ev
ee
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
m
o
v
in
g
o
b
ject
d
etec
tio
n
alg
o
r
ith
m
s
ar
e
m
ain
ly
u
s
ed
in
d
if
f
er
e
n
t
ap
p
licatio
n
s
s
u
ch
as
s
u
r
v
eillan
ce
an
d
tr
a
f
f
ic
m
o
n
it
o
r
in
g
[
1
]
.
Am
o
n
g
th
ese
a
p
p
li
ca
tio
n
s
,
m
o
v
em
en
t
d
etec
tio
n
an
d
c
o
r
r
ec
tio
n
s
ar
e
m
ain
ly
u
s
ed
in
tr
af
f
ic
m
o
n
it
o
r
in
g
s
y
s
tem
s
.
Fo
r
th
e
ca
s
e
o
f
tr
af
f
ic
s
ig
n
al,
th
e
p
r
o
ce
s
s
in
g
alg
o
r
ith
m
an
d
ar
ch
itectu
r
e
m
u
s
t
d
etec
t
a
n
d
c
o
r
r
ec
t
th
e
m
o
tio
n
at
h
ig
h
s
p
ee
d
wh
ich
r
e
q
u
ir
es
to
im
p
lem
en
t
th
e
alg
o
r
ith
m
an
d
ar
ch
itectu
r
e
in
a
p
p
licatio
n
-
s
p
e
cif
ic
in
teg
r
ated
cir
c
u
it
(
ASI
C
)
lev
el
h
ar
d
wa
r
e.
Dete
ctin
g
th
e
tar
g
et
f
r
o
m
s
tatic
ca
m
er
a
is
s
im
p
le
a
n
d
ea
s
y
th
an
th
o
s
e
f
r
o
m
th
e
m
o
v
i
n
g
ca
m
e
r
a
wh
ic
h
in
v
o
lv
es
th
e
esti
m
atio
n
an
d
co
m
p
en
s
atio
n
o
f
g
lo
b
al
m
o
tio
n
ca
u
s
ed
b
y
th
e
ca
m
e
r
a,
wh
ic
h
is
m
o
u
n
ted
o
n
m
o
v
in
g
p
latf
o
r
m
[
2
]
.
Mo
r
eo
v
er
,
b
lo
c
k
b
ased
m
o
tio
n
esti
m
atio
n
is
o
n
e
o
f
th
e
m
o
s
t
im
p
o
r
tan
t
ap
p
r
o
ac
h
to
esti
m
ate
th
e
m
o
tio
n
ca
u
s
ed
b
y
th
e
m
o
v
em
en
t
o
f
th
e
o
b
ject
th
at
ar
e
m
o
v
in
g
in
th
e
v
id
e
o
s
tr
ea
m
.
Dif
f
er
en
t
ty
p
es
o
f
m
o
tio
n
est
im
atio
n
alg
o
r
ith
m
s
ar
e
p
r
o
p
o
s
ed
to
esti
m
ate
th
e
m
o
tio
n
f
r
o
m
th
e
in
p
u
t
v
id
eo
s
tr
ea
m
s
wh
ich
a
r
e
t
h
en
u
s
ed
t
o
d
etec
t
c
o
m
p
o
n
en
ts
th
at
ar
e
in
m
o
tio
n
.
T
h
e
ac
cu
r
ac
y
o
f
th
is
esti
m
a
tio
n
is
d
ir
ec
tly
r
elate
d
to
t
h
e
o
v
er
all
ac
c
u
r
ate
d
etec
tio
n
.
T
h
e
th
r
ee
s
tep
s
ea
r
ch
(
T
SS
)
,
th
e
f
o
u
r
s
tep
s
ea
r
ch
(
FS
S),
d
iam
o
n
d
s
ea
r
ch
,
s
u
cc
ess
iv
e
elim
in
atio
n
s
ea
r
ch
an
d
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:
2502
-
4
7
5
2
E
fficien
t reco
n
fig
u
r
a
b
le
a
r
ch
it
ec
tu
r
e
fo
r
mo
vin
g
o
b
ject
d
etec
tio
n
w
ith
mo
tio
n
co
mp
e
n
s
a
tio
n
(
S
r
id
ev
i N
.
)
803
ad
ap
tiv
e
s
ea
r
ch
win
d
o
w
s
ize
[3
]
-
[
5
]
ar
e
s
o
m
e
o
f
m
o
s
t
co
m
m
o
n
ly
u
s
ed
m
o
tio
n
esti
m
atio
n
alg
o
r
ith
m
s
,
wh
ich
g
en
er
ates
h
ig
h
q
u
ality
m
o
tio
n
esti
m
atio
n
,
am
o
n
g
t
h
o
s
e
alg
o
r
ith
m
s
,
f
u
ll
s
ea
r
ch
m
o
tio
n
e
s
tim
atio
n
is
wid
ely
u
s
ed
to
esti
m
ate
m
o
tio
n
d
u
e
to
its
v
ar
io
u
s
ad
v
an
ta
g
es o
v
er
o
t
h
er
esti
m
atio
n
tech
n
iq
u
e.
Mo
r
eo
v
er
,
d
u
e
to
th
e
co
m
p
lex
d
ata
f
lo
w
o
f
m
o
s
t
o
f
th
o
s
e
tech
n
iq
u
es,
v
er
y
lar
g
e
-
s
ca
le
in
teg
r
atio
n
(
VL
SI
)
lev
el
im
p
lem
en
tatio
n
s
ar
e
n
o
t
p
o
s
s
ib
le.
Alth
o
u
g
h
s
o
m
e
VL
SI
ar
ch
itectu
r
es
ar
e
p
r
esen
t
to
im
p
lem
en
t
m
o
tio
n
esti
m
atio
n
tech
n
iq
u
es,
th
e
d
etec
tio
n
ac
c
u
r
ac
y
is
lo
w
an
d
th
e
o
v
er
all
h
ar
d
war
e
u
tili
za
tio
n
s
ar
e
h
ig
h
,
wh
ich
m
ak
es
th
o
s
e
ar
c
h
itectu
r
e
ar
e
n
o
t
s
u
itab
le
f
o
r
r
ea
l
tim
e
h
ig
h
s
p
ee
d
ap
p
licatio
n
s
[
6
]
.
On
th
e
o
th
er
h
an
d
,
th
e
f
u
ll
s
ea
r
ch
m
o
tio
n
esti
m
atio
n
alg
o
r
ith
m
s
h
o
ws
r
eg
u
lar
d
ata
f
lo
w
wh
ich
m
ak
es
it
s
u
itab
le
to
im
p
lem
en
t
it
th
r
o
u
g
h
VL
SI
ar
ch
itectu
r
e.
I
n
th
e
ca
s
e
o
f
m
o
tio
n
esti
m
at
io
n
th
e
cu
r
r
e
n
t
an
d
r
ef
er
en
ce
b
lo
ck
in
ad
jace
n
t
f
r
am
es
ar
e
u
s
ed
to
d
ef
in
e
m
o
t
io
n
v
ec
to
r
[
7
]
,
[
8
]
,
wh
ich
is
u
s
ed
to
esti
m
ate
r
eq
u
ir
ed
m
o
tio
n
s
.
T
h
e
f
u
ll
s
ea
r
ch
b
lo
ck
m
atc
h
in
g
m
o
tio
n
esti
m
atio
n
is
th
e
o
n
e
m
o
s
t
p
o
p
u
lar
m
o
tio
n
esti
m
atio
n
alg
o
r
ith
m
.
I
n
th
is
ca
s
e,
th
e
cu
r
r
en
t
f
r
a
m
es
ar
e
s
u
b
d
iv
id
e
d
in
to
a
f
in
ite
n
u
m
b
e
r
o
f
s
u
b
-
b
lo
ck
s
,
wh
ich
ar
e
th
er
e
u
s
ed
to
f
in
d
b
est
m
atch
ed
b
lo
ck
s
in
th
e
r
ef
er
en
ce
f
r
a
m
es.
Ho
wev
er
,
Mo
tio
n
b
ased
tar
g
et
d
etec
tio
n
r
ely
o
n
ca
m
er
a
m
o
tio
n
co
m
p
e
n
s
atio
n
an
d
co
r
r
ec
tio
n
.
Mo
tio
n
esti
m
atio
n
an
d
c
o
m
p
e
n
s
atio
n
p
lay
s
an
im
p
o
r
ta
n
t
r
o
le
in
t
h
e
g
lo
b
al
m
o
tio
n
co
m
p
en
s
atio
n
.
W
h
ich
r
e
q
u
ir
e
s
th
e
m
o
tio
n
in
th
e
v
id
eo
f
r
am
es
to
b
e
esti
m
ated
an
d
th
e
u
n
wan
ted
m
o
tio
n
in
d
u
ce
d
d
u
e
to
th
e
m
o
v
em
en
t
o
f
th
e
ca
m
e
r
a
to
b
e
co
m
p
en
s
ated
.
Hen
ce
,
to
a
d
d
r
ess
th
e
f
a
cts
d
is
cu
s
s
ed
ab
o
v
e
in
th
is
p
ap
er
,
an
ef
f
i
cien
t
h
ar
d
war
e
ar
ch
itectu
r
e
to
im
p
lem
en
t
a
f
u
ll
s
ea
r
ch
m
o
tio
n
esti
m
atio
n
alg
o
r
ith
m
to
d
etec
t m
o
v
in
g
o
b
jects a
n
d
co
m
p
en
s
ate
f
o
r
t
h
e
eg
o
-
m
o
tio
n
i
s
p
r
esen
ted
.
T
h
e
g
e
n
er
al
b
lo
ck
d
iag
r
am
o
f
th
e
m
o
tio
n
esti
m
atio
n
an
d
g
lo
b
al
m
o
tio
n
co
m
p
e
n
s
atio
n
is
g
iv
en
in
F
ig
u
r
e
1
an
d
th
e
o
p
er
atio
n
is
ex
p
lain
b
elo
w.
I
n
th
e
p
r
ep
r
o
ce
s
s
in
g
th
e
in
p
u
t
v
id
eo
s
tr
ea
m
is
co
n
v
er
ted
in
to
n
u
m
b
er
f
r
am
es wh
ich
ar
e
th
en
co
n
v
er
ted
in
t
o
d
if
f
er
e
n
t f
o
r
m
at
f
o
r
h
ar
d
wa
r
e
p
r
o
ce
s
s
in
g
.
T
h
e
p
r
o
ce
s
s
ed
f
r
am
es
is
th
en
g
iv
e
n
to
th
e
m
o
tio
n
es
tim
atio
n
b
lo
c
k
to
f
in
d
th
e
m
o
v
in
g
p
ar
ts
in
t
h
e
v
i
d
eo
.
T
h
e
v
ec
to
r
s
th
u
s
d
etec
ted
n
o
t
o
n
ly
co
n
tain
s
th
e
m
o
v
em
en
t
d
u
e
to
th
e
tar
g
et
p
r
esen
t
i
n
th
e
v
id
e
o
b
u
t
also
th
e
m
o
v
e
m
en
t
ca
u
s
ed
b
y
th
e
m
o
v
em
en
t
o
f
th
e
s
en
s
o
r
th
at
is
u
s
ed
to
ca
p
tu
r
e
th
e
v
id
eo
.
T
h
er
ef
o
r
e
it
is
r
eq
u
ir
ed
to
el
i
m
in
ate
th
e
g
lo
b
al
m
o
tio
n
ca
u
s
ed
b
y
th
e
ca
m
er
a
wh
ich
is
ac
h
iev
ed
in
t
h
is
wo
r
k
with
th
e
ad
d
itio
n
o
f
c
o
m
p
en
s
atio
n
b
lo
ck
.
Fig
u
r
e
1
.
W
o
r
k
i
n
g
m
et
h
o
d
o
f
p
r
o
p
o
s
ed
m
o
tio
n
esti
m
atio
n
a
n
d
co
r
r
ec
tio
n
T
h
e
ar
c
h
itectu
r
e
p
r
o
p
o
s
ed
h
er
e
is
d
esig
n
e
d
u
s
in
g
v
er
y
h
ig
h
s
p
ee
d
i
n
teg
r
ated
cir
cu
it
(
VHSI
C
)
h
ar
d
war
e
d
escr
ip
tio
n
lan
g
u
ag
e
(
VHDL
)
lan
g
u
ag
e
an
d
v
ali
d
ate
o
n
th
e
FP
GA
p
latf
o
r
m
.
T
h
e
co
n
tr
ib
u
tio
n
o
f
th
is
wo
r
k
is
h
ig
h
lig
h
te
d
b
elo
w
:
−
At
f
ir
s
t th
e
co
n
tr
o
ller
b
lo
ck
is
o
p
tim
ized
b
y
d
esig
n
in
g
it u
s
in
g
s
im
p
le
co
u
n
te
r
.
−
T
h
e
u
s
e
o
f
k
o
g
g
e
-
s
to
n
e
a
d
d
er
im
p
r
o
v
es th
e
s
p
ee
d
o
f
o
p
er
ati
o
n
o
f
th
e
ar
h
itectu
r
e.
−
Fu
r
th
er
,
to
r
ed
u
ce
t
h
e
o
v
e
r
all
h
ar
d
war
e
u
tili
za
tio
n
s
d
ata
r
eu
s
e
tech
n
iq
u
e
is
u
s
ed
.
−
T
h
e
p
r
o
p
o
s
ed
ar
ch
itectu
r
e
is
e
v
alu
ated
b
y
co
n
s
id
er
i
n
g
th
r
ee
d
if
f
er
en
t tr
a
f
f
ic
s
ce
n
ar
io
s
.
−
Fu
r
th
e
r
,
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
ar
ch
itectu
r
e
is
ev
alu
ated
u
s
in
g
tr
u
e
a
n
d
f
alse d
etec
tio
n
r
at
e
.
Or
g
an
izatio
n
:
T
h
e
o
r
g
an
izatio
n
o
f
th
e
r
em
ain
in
g
to
p
ics
o
f
t
h
is
p
ap
er
is
:
s
ec
tio
n
2
e
x
p
lain
s
th
e
n
o
v
el
h
ar
d
war
e
a
r
ch
itectu
r
e
f
o
r
m
o
tio
n
esti
m
atio
n
,
f
o
llo
wed
b
y
r
esu
l
ts
an
d
d
is
cu
s
s
io
n
in
s
e
ctio
n
3
an
d
f
in
ally
co
n
clu
s
io
n
ar
e
d
r
awn
i
n
s
ec
tio
n
4.
2.
RE
L
AT
E
D
WO
RK
Sev
er
al
r
esear
ch
er
s
co
n
tr
ib
u
te
d
n
u
m
er
o
u
s
m
eth
o
d
s
to
esti
m
ate
an
d
co
m
p
en
s
ate
th
e
m
o
tio
n
,
f
ew
ar
e
d
is
cu
s
s
ed
h
er
e.
Pak
d
am
an
et
a
l.
[
9
]
p
r
esen
ted
a
s
ca
lab
le
f
ast
m
o
tio
n
esti
m
atio
n
alg
o
r
ith
m
th
r
o
u
g
h
l
o
w
co
m
p
lex
an
d
s
ca
lab
le
tech
n
iq
u
es
wh
ich
u
s
es
m
o
s
t
p
o
p
u
lar
“
test
zo
n
e
(
T
Z
)
”
f
o
r
m
o
tio
n
e
s
tim
atio
n
alg
o
r
ith
m
an
d
is
u
s
ef
u
l
to
g
et
ef
f
icien
t
v
id
eo
co
d
i
n
g
(
HE
VC
)
.
Her
e
in
th
is
p
ap
er
a
s
in
g
le
r
eliab
le
s
tar
tin
g
p
o
i
n
t
is
f
o
u
n
d
to
r
ep
lace
th
e
f
ir
s
t
s
tep
o
f
th
e
T
Z
s
ea
r
ch
alg
o
r
ith
m
.
T
h
e
c
o
m
p
u
tatio
n
al
co
m
p
lex
ity
,
d
at
a
d
ep
en
d
en
c
y
with
n
eig
h
b
o
r
in
g
b
lo
ck
s
an
d
d
e
f
icie
n
cy
o
f
co
m
p
u
tatio
n
al
ad
j
u
s
tab
ilit
y
ar
e
th
e
d
r
awb
ac
k
s
o
f
th
is
alg
o
r
ith
m
.
I
n
p
ap
er
[
1
0
]
a
co
m
p
ar
ativ
e
s
tu
d
y
o
f
v
a
r
io
u
s
mo
tio
n
esti
m
at
io
n
alg
o
r
ith
m
s
an
d
o
p
er
atio
n
al
cy
cle
f
o
r
m
o
tio
n
v
ec
to
r
s
ea
r
ch
is
ev
alu
ated
b
y
co
m
p
ar
i
n
g
th
e
ex
is
tin
g
co
n
v
en
tio
n
al
f
u
ll
s
ea
r
ch
alg
o
r
i
th
m
with
th
e
n
ew
alg
o
r
ith
m
d
ev
elo
p
ed
b
y
t
h
em
.
Fro
m
t
h
e
r
esu
lts
th
ey
co
n
cl
u
d
ed
t
h
at
o
p
er
atio
n
cy
cle
o
f
p
r
o
p
o
s
ed
m
et
h
o
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
23
,
No
.
2
,
Au
g
u
s
t 2
0
2
1
:
802
-
8
1
0
804
in
[
1
0
]
is
f
ew
tim
es
s
m
aller
t
h
an
th
at
o
f
f
u
ll
s
ea
r
ch
alg
o
r
ith
m
b
u
t
th
e
cir
cu
it
s
ize
is
g
r
ea
te
r
th
an
th
e
f
u
ll
s
ea
r
ch
alg
o
r
ith
m
.
M
o
g
u
s
et
a
l.
[
1
1
]
d
is
cu
s
s
ed
th
e
p
r
o
ce
s
s
o
f
m
o
tio
n
esti
m
atio
n
wh
ich
g
en
er
ate
s
m
o
tio
n
v
ec
to
r
s
to
d
eter
m
in
e
t
h
e
co
m
p
en
s
atio
n
f
r
o
m
p
r
ed
ictio
n
f
r
am
e.
Her
e,
to
o
v
er
c
o
m
e
th
e
d
r
awb
ac
k
s
o
f
th
e
al
g
o
r
ith
m
a
b
lo
ck
m
atch
in
g
m
o
tio
n
esti
m
a
tio
n
alg
o
r
ith
m
is
also
u
s
ed
.
I
n
p
ap
er
[
1
2
]
th
e
n
o
v
el
ar
ch
itect
u
r
e
f
o
r
lo
w
-
laten
c
y
an
d
h
ig
h
t
h
r
o
u
g
h
p
u
t
p
r
o
g
r
am
m
ab
le
m
o
tio
n
esti
m
ato
r
is
p
r
e
s
en
ted
.
Her
e
m
o
tio
n
is
esti
m
ated
b
y
ap
p
ly
in
g
f
u
ll
-
s
ea
r
ch
an
d
h
ier
ar
c
h
ical
s
ea
r
ch
alg
o
r
ith
m
s
.
T
wo
-
s
tep
s
ea
r
ch
o
n
g
r
a
y
co
d
ed
v
id
eo
f
r
am
es f
o
r
m
o
tio
n
esti
m
atio
n
is
p
r
o
p
o
s
ed
i
n
[
1
3
]
.
I
n
t
h
is
m
eth
o
d
m
o
tio
n
is
esti
m
ated
u
s
i
n
g
two
s
tep
s
.
Firstl
y
th
e
b
asic
m
o
tio
n
v
ec
to
r
s
ar
e
cal
cu
lated
u
s
in
g
m
o
s
t
s
ig
n
if
i
ca
n
t
b
its
o
f
g
r
ay
co
d
e
d
b
it
p
lan
es.
I
n
th
e
s
ec
o
n
d
s
tag
e
m
o
tio
n
v
ec
to
r
s
ar
e
o
b
tain
ed
b
y
u
s
in
g
an
ad
a
p
tiv
e
s
ea
r
ch
p
atter
n
.
Gh
ar
av
i
a
n
d
Mills
[
1
4
]
p
r
o
p
o
s
ed
a
n
o
v
el
b
lo
ck
-
m
atch
in
g
m
o
tio
n
esti
m
atio
n
to
f
in
d
th
e
b
est
m
atch
b
y
co
n
s
id
er
i
n
g
th
e
b
eh
av
io
r
o
f
in
d
iv
id
u
al
p
els
wh
ich
p
lay
s
m
o
r
e
ac
tiv
e
r
o
le
in
esti
m
atin
g
th
e
m
o
tio
n
an
d
r
esu
lts
in
b
etter
p
er
f
o
r
m
a
n
ce
th
an
m
ea
n
-
ab
s
o
lu
te
-
d
if
f
er
en
ce
.
B
h
a
t
t
a
c
h
a
r
y
y
a
et
a
l
.
[
1
5
]
ar
e
wo
r
k
ed
o
n
b
lo
ck
-
b
ased
m
o
tio
n
esti
m
atio
n
tech
n
iq
u
e
an
d
im
p
lem
en
ted
s
ix
-
le
v
el
n
ested
d
o
-
lo
o
p
f
u
ll
-
s
ea
r
ch
b
lo
ck
-
m
atch
in
g
m
o
tio
n
esti
m
atio
n
alg
o
r
ith
m
.
Her
e
th
e
alg
o
r
ith
m
is
im
p
lem
en
ted
in
two
p
h
ases
.
I
n
th
e
f
i
r
s
t
p
h
ase
u
s
in
g
2
5
m
o
v
ie
f
r
am
es
with
o
u
t
b
r
ea
k
i
n
g
th
em
in
to
m
ac
r
o
-
b
lo
ck
s
a
n
d
in
th
e
s
ec
o
n
d
p
h
ase
th
e
s
am
e
is
im
p
lem
en
te
d
af
t
er
b
r
ea
k
in
g
in
to
t
h
e
r
esp
ec
tiv
e
m
ac
r
o
-
b
lo
ck
s
.
E
f
f
icien
t
m
o
tio
n
esti
m
atio
n
alg
o
r
ith
m
u
s
in
g
o
n
l
y
d
iam
o
n
d
s
ea
r
ch
g
r
id
to
m
ee
t
th
e
r
eq
u
ir
em
en
t
o
f
p
o
r
tab
le
an
d
lo
w
p
o
wer
d
ev
ice
is
p
r
esen
ted
in
th
e
p
ap
er
[
1
6
]
u
s
in
g
s
u
b
-
s
am
p
lin
g
a
n
d
p
ix
el
tr
u
n
c
atio
n
to
r
e
d
u
ce
th
e
co
m
p
lex
it
y
,
s
o
th
e
y
co
n
clu
d
ed
th
at
p
r
o
p
o
s
ed
d
iam
o
n
d
g
r
id
s
ea
r
ch
(
DGS
)
alg
o
r
ith
m
tak
es
less
n
u
m
b
er
o
f
s
ea
r
ch
p
o
in
t
an
d
h
av
e
co
m
p
ar
a
b
le
p
ea
k
s
ig
n
al
to
n
o
is
e
r
atio
(
PS
NR
)
an
d
b
it
-
r
ate
as
co
m
p
ar
ed
to
o
th
e
r
s
tate
o
f
th
e
ar
t
m
o
tio
n
esti
m
atio
n
alg
o
r
ith
m
.
R
ef
er
en
ce
[
1
7
]
Ad
d
r
ess
ed
th
e
p
r
o
b
lem
o
f
ar
e
a
ef
f
icien
cy
o
f
ca
r
r
y
s
elec
t
ad
d
er
b
y
av
o
i
d
in
g
th
e
u
s
e
o
f
Z
FC
an
d
m
u
ltip
lex
er
.
Dis
cr
ete
co
s
in
e
tr
an
s
f
o
r
m
-
b
ased
m
o
tio
n
-
esti
m
atio
n
(
DX
T
-
ME
)
is
p
r
esen
ted
in
th
e
p
a
p
er
[
1
8
]
,
th
is
alg
o
r
ith
m
p
r
o
v
id
es
th
e
e
x
ac
t
d
is
p
lace
m
en
t
o
f
th
e
o
b
ject
o
f
in
ter
e
s
t,
m
ak
in
g
it
s
u
itab
le
f
o
r
f
i
n
e
-
g
r
ain
e
d
tr
ac
k
in
g
.
B
o
o
n
th
ep
et
a
l.
[
1
9
]
,
p
ar
alle
l
h
ar
d
war
e
ar
ch
itectu
r
e
f
o
r
co
m
p
u
tin
g
ME
b
y
u
s
in
g
s
ca
le
-
in
v
ar
ian
t
-
f
ea
tu
r
e
-
tr
an
s
f
o
r
m
(
SIFT
)
is
p
r
o
p
o
s
ed
.
Her
e
in
th
is
p
ap
er
th
e
a
u
th
o
r
s
ap
p
lied
f
ast
f
o
u
r
ier
tr
a
n
s
f
o
r
m
(
FFT
)
to
r
ed
u
c
e
th
e
co
m
p
lex
ity
i
n
SIFT
alg
o
r
i
th
m
also
th
e
f
ea
tu
r
es
th
at
ar
e
d
etec
ted
ar
e
f
u
lly
i
n
v
ar
ian
t
t
o
im
ag
e
s
ca
lin
g
an
d
r
o
tatio
n
.
T
h
e
p
r
o
p
o
s
ed
ar
ch
it
ec
tu
r
e
will
in
cr
ea
s
e
th
e
s
p
ee
d
o
f
o
p
er
atio
n
d
u
e
to
th
e
u
s
e
o
f
k
o
g
g
esto
n
e
a
d
d
e
r
an
d
th
e
d
ata
r
eu
s
e
tech
n
i
q
u
e
will o
p
tim
ize
th
e
o
v
er
all
ar
c
h
i
tectu
r
e
.
3.
P
RO
P
O
SE
D
M
E
T
H
O
D
T
h
e
h
a
r
d
w
a
r
e
a
r
c
h
i
te
c
t
u
r
e
p
r
o
p
o
s
e
d
i
n
t
h
is
p
a
p
e
r
t
o
i
m
p
l
e
m
en
t
m
o
t
i
o
n
e
s
t
i
m
a
ti
o
n
is
s
h
o
w
n
i
n
F
i
g
u
r
e
2
.
T
h
e
ar
ch
itectu
r
e
m
ain
l
y
in
clu
d
es
d
if
f
er
en
t
ty
p
es
o
f
m
em
o
r
y
u
n
it,
ab
s
o
lu
te
d
if
f
e
r
en
ce
b
lo
c
k
,
ad
d
er
a
r
r
ay
b
o
ck
,
co
m
p
ar
ato
r
,
an
d
c
o
n
tr
o
ller
u
n
it
r
esp
ec
tiv
ely
th
e
1
6
×
1
6
b
lo
c
k
s
ize
is
u
s
ed
as
c
u
r
r
en
t
b
lo
c
k
to
g
et
th
e
m
o
tio
n
v
ec
to
r
s
wh
ich
ar
e
s
to
r
ed
in
th
e
ex
ter
n
al
m
em
o
r
y
b
lo
ck
s
,
wh
ich
is
ca
p
ab
le
o
f
s
to
r
in
g
en
ti
r
e
f
r
am
e
u
n
til
it
is
p
r
o
ce
s
s
ed
.
T
h
e
cu
r
r
e
n
t
b
lo
ck
an
d
th
e
s
u
b
d
iv
id
ed
co
m
p
u
tat
io
n
al
b
lo
ck
o
b
tain
e
d
b
y
d
iv
id
in
g
th
e
f
r
am
e
in
to
n
u
m
b
er
o
f
s
u
b
-
b
lo
ck
s
ar
e
r
o
u
ted
th
r
o
u
g
h
t
h
e
d
e
m
u
x
b
lo
c
k
to
d
is
tr
ib
u
te
t
h
em
in
to
th
r
ee
m
em
o
r
y
b
lo
ck
s
n
am
ely
SUB
M1
,
SUB
M2
an
d
SUB
M3
r
esp
ec
tiv
ely
.
T
h
es
e
m
em
o
r
ies
s
to
r
e
cu
r
r
en
t
s
u
b
m
atr
ix
an
d
ad
jace
n
t
s
u
b
m
atr
ix
p
ix
el
v
alu
es.
T
h
e
s
to
r
ed
p
ix
el
v
alu
es
ar
e
th
en
u
s
ed
to
ca
lcu
late
t
h
e
s
u
cc
es
s
iv
e
ap
p
r
o
x
im
atio
n
d
if
f
er
en
ce
s
(
SAD)
th
r
o
u
g
h
w
h
ich
t
h
e
m
o
tio
n
s
ar
e
d
etec
ted
an
d
co
r
r
ec
ted
th
r
o
u
g
h
co
m
p
ar
e
an
d
co
r
r
ec
tio
n
b
lo
ck
.
T
h
e
m
o
tio
n
f
ea
tu
r
es
s
to
r
ed
in
th
e
m
o
tio
n
v
ec
t
o
r
m
em
o
r
y
ar
e
th
en
u
s
ed
as
r
ef
er
e
n
ce
s
to
th
e
n
ex
t
f
r
am
e.
T
h
e
co
n
tr
o
ller
b
lo
c
k
is
u
s
ed
to
co
n
tr
o
l th
e
o
v
e
r
all
o
p
er
atio
n
b
y
co
n
t
r
o
llin
g
t
h
e
d
ata
-
p
at
h
o
f
th
e
ar
ch
itectu
r
e.
Fig
u
r
e
2
.
Har
d
war
e
ar
ch
itectu
r
e
o
f
m
o
tio
n
esti
m
atio
n
an
d
co
r
r
ec
tio
n
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:
2502
-
4
7
5
2
E
fficien
t reco
n
fig
u
r
a
b
le
a
r
ch
it
ec
tu
r
e
fo
r
mo
vin
g
o
b
ject
d
etec
tio
n
w
ith
mo
tio
n
co
mp
e
n
s
a
tio
n
(
S
r
id
ev
i N
.
)
805
3
.
1
.
P
re
pro
ce
s
s
ing
T
h
e
d
ir
ec
t
v
id
eo
f
r
a
m
es
ar
e
n
o
t
co
m
p
atib
le
an
d
p
o
r
tab
le
f
o
r
h
ar
d
war
e
p
r
o
ce
s
s
in
g
d
u
e
t
o
d
if
f
er
en
t
f
o
r
m
ats
o
f
v
id
eo
s
e
x
is
tin
g
.
As
a
r
esu
lt,
it
is
n
ec
ess
ar
y
to
co
n
v
er
t
it
in
to
a
n
u
m
b
er
o
f
f
r
a
m
es
wh
ich
ar
e
p
er
f
o
r
m
ed
b
y
s
y
s
tem
g
en
er
ato
r
to
o
l
with
th
e
h
elp
o
f
MA
T
L
AB
to
o
l.
I
t
is
n
o
r
m
ally
u
s
ed
t
o
co
n
v
er
t
th
e
in
p
u
t
v
id
eo
in
to
a
f
in
ite
n
u
m
b
er
o
f
f
r
am
es o
f
s
tan
d
ar
d
s
ize
.
3
.
2
.
Co
ntr
o
ller
T
h
e
co
n
tr
o
ller
b
lo
c
k
is
u
s
ed
t
o
co
n
tr
o
l
th
e
o
v
er
all
d
ata
f
lo
w
eith
er
b
y
ac
tiv
atin
g
o
r
d
ea
c
tiv
atin
g
th
e
r
eq
u
ir
ed
b
lo
ck
s
.
I
n
th
e
b
e
g
i
n
n
in
g
o
f
th
e
o
p
e
r
atio
n
,
th
e
s
elec
t
lin
e
o
f
th
e
DE
MU
X
is
s
et
to
0
wh
ich
allo
ws
th
e
f
ir
s
t
s
u
b
-
m
atr
ix
p
ix
els
to
en
te
r
in
s
u
b
-
m
em
o
r
y
1
.
Af
ter
1
6
clo
ck
cy
cles,
t
h
e
ab
s
o
lu
te
d
if
f
er
en
ce
b
l
o
ck
s
tar
ts
ca
lcu
latin
g
th
e
ab
s
o
lu
te
d
if
f
e
r
en
ce
v
alu
es
f
r
o
m
th
e
c
u
r
r
e
n
t
b
lo
c
k
.
At
th
is
tim
e,
th
e
co
n
tr
o
ll
er
b
lo
ck
s
elec
ts
th
e
s
u
b
-
m
em
o
r
y
2
t
h
r
o
u
g
h
DE
MU
X
b
lo
ck
.
T
h
e
ab
s
o
lu
te
d
if
f
er
en
ce
o
f
two
s
u
b
-
m
at
r
ix
es
s
tar
ts
ca
lcu
latin
g
v
alu
es
till
4
9
th
clo
c
k
c
y
cle
a
n
d
th
e
f
in
al
SAD
v
alu
es
s
tar
ts
at
5
0
th
clo
ck
cy
cle
an
d
it
is
im
p
le
m
en
ted
b
y
s
im
p
le
co
u
n
ter
lo
g
ics.
T
h
e
h
a
r
d
w
a
r
e
a
r
c
h
it
e
c
t
u
r
e
t
o
d
e
s
i
g
n
t
h
e
c
o
n
t
r
o
l
l
e
r
b
l
o
c
k
is
g
iv
e
n
i
n
F
i
g
u
r
e
3
w
h
i
c
h
c
o
n
s
is
ts
o
f
c
o
u
n
t
e
r
,
d
e
c
i
s
i
o
n
m
a
k
e
r
b
l
o
c
k
a
n
d
e
n
co
d
e
r
b
l
o
c
k
.
T
h
e
c
o
u
n
t
e
r
b
l
o
c
k
s
t
a
r
t
s
c
o
u
n
t
i
n
g
at
e
v
e
r
y
r
is
i
n
g
e
d
g
e
o
f
t
h
e
c
l
o
c
k
p
u
l
s
e
w
h
e
n
r
e
s
et
(
r
s
t
)
s
i
g
n
a
l
is
h
i
g
h
w
h
i
c
h
i
s
t
h
e
n
u
s
e
d
b
y
d
e
c
i
s
i
o
n
m
a
k
e
r
b
l
o
c
k
t
o
d
e
c
i
d
e
th
e
c
o
r
r
e
c
t
s
e
q
u
e
n
c
e
o
f
s
u
b
-
b
l
o
c
k
s
t
o
b
e
ac
t
i
v
at
e
d
an
d
t
h
e
n
t
h
i
s
i
s
e
n
c
o
d
e
d
b
y
t
h
e
e
n
c
o
d
e
r
b
l
o
c
k
t
o
a
c
t
i
v
at
e
t
h
e
p
r
o
c
e
s
s
i
n
g
e
l
e
m
e
n
ts
i
n
c
o
r
r
e
c
t
s
e
q
u
e
n
c
e
.
A
f
t
e
r
t
h
e
m
o
t
i
o
n
v
e
c
t
o
r
c
a
l
c
u
la
t
i
o
n
o
f
t
h
r
e
e
c
o
n
s
e
c
u
t
i
v
e
1
6
×
1
6
s
u
b
-
m
a
tr
i
c
e
s
a
r
e
c
o
m
p
l
e
t
e
d
,
t
h
e
e
n
t
i
r
e
c
o
n
t
r
o
ll
e
r
is
r
e
s
et
t
o
it
s
i
n
it
i
al
c
o
n
d
i
t
i
o
n
a
n
d
t
h
e
o
p
e
r
a
t
i
o
n
s
ta
r
t
s
f
r
o
m
t
h
e
b
e
g
i
n
n
i
n
g
.
Fig
u
r
e
3
.
Pro
p
o
s
ed
c
o
n
tr
o
ller
ar
ch
itectu
r
e
3
.
3
.
M
o
t
io
n det
ec
t
io
n
T
h
e
m
o
tio
n
v
ec
to
r
s
ar
e
u
s
ed
to
d
etec
t
th
e
m
o
v
e
m
en
t
f
r
o
m
an
y
v
id
e
o
s
eq
u
en
ce
u
s
in
g
ab
s
o
lu
te
d
if
f
er
en
ce
,
ar
r
ay
o
f
a
d
d
er
s
an
d
d
ec
is
io
n
m
ak
er
b
lo
ck
.
3.
3
.
1
.
Abs
o
lute
diff
er
ence
T
o
ca
lcu
late
th
e
ab
s
o
lu
te
d
if
f
e
r
en
ce
b
etwe
en
n
eig
h
b
o
r
in
g
f
r
a
m
es,
it is
ess
en
tial to
s
to
r
e
th
e
p
ix
el
o
f
th
ese
f
r
am
es in
to
tem
p
o
r
ar
y
m
em
o
r
y
f
o
r
p
r
o
ce
s
s
in
g
an
d
th
e
ar
ch
itectu
r
e
is
g
iv
en
i
n
F
ig
u
r
e
4
.
Fig
u
r
e
4
.
T
e
m
p
o
r
a
r
y
s
to
r
a
g
e
o
f
f
r
am
es
T
h
e
s
h
if
t
r
eg
is
ter
ar
ch
itectu
r
e
d
esig
n
ed
u
s
in
g
D
f
lip
-
f
lo
p
s
ar
e
m
ain
ly
u
s
ed
f
o
r
th
is
p
u
r
p
o
s
e.
T
h
e
ar
ch
itectu
r
e
wh
ich
is
u
s
ed
to
s
to
r
e
th
e
f
r
am
es
ar
e
g
iv
en
in
Fig
u
r
e
3
wh
er
e
th
e
D_
FF
b
lo
ck
is
u
s
ed
to
s
to
r
e
th
e
p
ix
el
v
alu
es
wh
ich
a
r
e
th
en
u
s
ed
to
ca
lcu
late
t
h
e
a
b
s
o
lu
te
d
i
f
f
er
en
ce
.
T
h
e
p
a
r
allel
ar
ch
itec
tu
r
e
o
f
t
h
e
D_
FF
is
an
ad
v
a
n
tag
e
f
o
r
f
ast p
r
o
ce
s
s
in
g
o
f
th
e
d
ata
c
o
m
p
ar
e
d
to
e
x
is
tin
g
tech
n
iq
u
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
23
,
No
.
2
,
Au
g
u
s
t 2
0
2
1
:
802
-
8
1
0
806
T
h
e
ab
s
o
lu
te
d
if
f
er
en
ce
v
alu
e
s
b
etwe
en
th
e
cu
r
r
en
t
b
lo
ck
a
n
d
ad
jace
n
t
b
lo
ck
s
ar
e
ca
lcu
la
ted
in
th
i
s
b
lo
ck
.
Fo
r
m
o
tio
n
esti
m
atio
n
p
u
r
p
o
s
e,
it
is
es
s
en
tial
to
p
er
f
o
r
m
th
e
ab
s
o
lu
te
d
if
f
er
en
ce
(
AD)
at
b
lo
ck
lev
el
wh
ich
r
eq
u
ir
es
a
h
i
g
h
s
p
ee
d
s
u
b
tr
ac
to
r
.
As
a
r
esu
lt,
th
e
n
o
r
m
al
s
u
b
tr
ac
t
o
r
ar
c
h
itectu
r
e
is
r
ep
lace
d
b
y
th
e
kogge
-
s
to
n
e
ad
d
er
[
2
0
]
in
b
in
a
r
y
ar
ith
m
etic.
T
h
e
eq
u
a
tio
n
f
o
r
ab
s
o
lu
te
d
if
f
er
en
ce
is
g
iv
e
n
b
elo
w
in
(
1
)
:
(
)
=
|
−
|
(
1
)
W
h
er
e,
A
an
d
B
ar
e
th
e
p
ix
els o
f
cu
r
r
en
t a
n
d
r
ef
e
r
en
ce
f
r
am
e
r
esp
ec
tiv
ely
.
T
h
e
h
ar
d
war
e
ar
c
h
itectu
r
e
is
u
s
ed
to
o
b
tain
th
e
a
b
s
o
lu
te
d
i
f
f
er
en
ce
is
s
h
o
wn
in
th
e
Fig
u
r
e
5
wh
e
r
e
th
e
u
s
e
o
f
k
o
g
g
e
-
s
to
n
e
a
d
d
er
r
esu
lted
in
o
p
tim
izatio
n
o
f
th
e
en
tire
ar
ch
itectu
r
e.
T
h
e
s
u
b
tr
a
ctio
n
is
m
o
d
eled
b
y
ad
d
itio
n
in
b
i
n
ar
y
ar
ith
m
etic
wh
ich
is
th
en
u
s
ed
to
f
in
d
t
h
e
s
ig
n
o
f
th
e
r
esu
ltan
t
d
ata
th
r
o
u
g
h
c
o
n
ca
ten
atio
n
b
lo
ck
.
De
p
en
d
in
g
u
p
o
n
th
e
o
u
tp
u
t
o
f
th
e
co
n
ca
ten
atio
n
b
lo
c
k
,
th
e
MU
X
b
lo
ck
s
en
d
th
e
r
e
s
u
ltan
t
v
alu
e
o
r
2
’
s
co
m
p
lem
en
t
o
f
th
e
r
esu
ltan
t
v
alu
e
to
th
e
o
u
tp
u
t
wh
ich
is
th
e
ab
s
o
lu
te
d
if
f
er
e
n
ce
v
alu
e
o
f
b
o
th
in
p
u
t
s
ig
n
al.
Fo
r
p
r
o
p
er
o
p
tim
izatio
n
,
th
e
2
’
s
co
m
p
lem
en
t is im
p
lem
e
n
ted
b
y
k
o
g
g
e
-
s
to
n
e
ad
d
er
b
lo
ck
o
n
ly
.
Fig
u
r
e
5
.
Har
d
war
e
ar
ch
itectu
r
e
o
f
a
b
s
o
lu
te
d
if
f
e
r
en
ce
3
.
3
.
2
.
Adder
a
rr
a
y
T
h
e
Ko
g
g
e
-
Sto
n
e
ad
d
er
[
2
0
]
a
r
ch
itectu
r
e
is
u
s
ed
to
b
u
ild
th
e
ad
d
er
a
r
r
ay
in
p
ar
allel
f
ash
io
n
.
3.
4
.
Dec
is
io
n blo
ck
T
h
e
b
asic
co
m
p
a
r
ato
r
b
lo
ck
is
u
s
ed
to
co
m
p
ar
e
th
e
m
atch
ed
f
r
am
e
f
r
o
m
s
to
r
ed
v
ec
to
r
s
in
t
h
e
m
o
tio
n
v
ec
to
r
m
em
o
r
y
b
lo
ck
f
o
r
ac
c
u
r
ate
m
o
tio
n
v
ec
to
r
.
I
t
is
n
o
r
m
ally
d
o
n
e
t
h
r
o
u
g
h
lo
g
ical
c
o
m
p
ar
ato
r
b
l
o
ck
an
d
th
e
h
ar
d
war
e
ar
ch
itectu
r
e
o
f
m
o
tio
n
esti
m
atio
n
is
g
iv
en
i
n
F
ig
u
r
e
6
.
Fig
u
r
e
6
.
Har
d
war
e
ar
ch
itectu
r
e
o
f
m
o
tio
n
d
etec
tio
n
3
.
5
.
L
o
ca
l
m
e
m
o
ry
T
h
e
p
i
x
els
p
r
esen
t
in
s
ea
r
ch
a
r
ea
m
atr
ix
ar
e
s
to
r
ed
in
th
e
lo
ca
l
m
em
o
r
y
u
n
it
w
h
ich
c
o
n
s
is
ts
o
f
th
r
ee
m
em
o
r
y
b
lo
c
k
s
n
am
ely
SUB
M1
,
SUB
M2
an
d
SUB
M3
r
e
s
p
ec
tiv
ely
.
T
h
ese
m
em
o
r
ies
a
r
e
u
s
ed
to
s
to
r
e
th
e
th
r
ee
co
n
s
ec
u
tiv
e
1
6
×
1
6
b
l
o
c
k
s
th
r
o
u
g
h
DE
MU
X
b
lo
c
k
th
r
o
u
g
h
s
elec
t
lin
e
wh
ich
is
co
n
tr
o
lled
b
y
co
u
n
ter
b
lo
ck
.
T
h
e
d
ata
en
te
r
s
as p
ix
els o
f
1
6
b
its
in
r
o
w
b
y
r
o
w
f
r
o
m
to
p
to
b
o
tto
m
d
ir
ec
tio
n
t
h
r
o
u
g
h
co
u
n
ter
l
o
g
ic.
3
.
6
.
M
o
t
io
n c
o
rr
ec
t
io
n
T
h
e
m
o
tio
n
v
ec
to
r
o
f
all
o
v
er
l
ap
p
in
g
b
lo
ck
s
p
r
esen
t
in
t
h
e
c
o
r
r
esp
o
n
d
in
g
f
r
am
es
m
u
s
t
b
e
s
to
r
ed
in
a
m
em
o
r
y
b
lo
c
k
f
o
r
f
u
r
th
er
p
r
o
ce
s
s
in
g
an
d
its
ar
ch
itectu
r
e
is
g
iv
en
in
Fig
u
r
e
7
.
T
h
e
m
o
ti
o
n
v
ec
t
o
r
m
e
m
o
r
y
b
lo
ck
is
u
s
ed
to
s
to
r
e
th
e
ca
l
cu
lated
m
o
tio
n
v
ec
to
r
s
f
r
o
m
th
e
SAD
d
ata
th
r
o
u
g
h
c
o
m
p
a
r
e
an
d
co
m
p
en
s
ate
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:
2502
-
4
7
5
2
E
fficien
t reco
n
fig
u
r
a
b
le
a
r
ch
it
ec
tu
r
e
fo
r
mo
vin
g
o
b
ject
d
etec
tio
n
w
ith
mo
tio
n
co
mp
e
n
s
a
tio
n
(
S
r
id
ev
i N
.
)
807
b
lo
ck
.
I
t
is
im
p
lem
en
ted
b
y
b
lo
ck
R
AM
av
ailab
le
o
n
th
e
FP
GA
b
o
ar
d
.
T
h
e
s
ize
o
f
th
e
R
AM
b
lo
ck
d
ep
e
n
d
s
u
p
o
n
th
e
f
r
am
e
s
ize
an
d
th
e
SAD
m
atr
ix
s
ize.
I
n
m
an
y
ca
s
es
th
e
u
s
e
o
f
s
im
p
le
co
m
p
ar
is
o
n
tech
n
iq
u
e
in
tr
o
d
u
ce
s
s
o
m
e
f
alse
d
etec
tio
n
wh
ic
h
h
as
to
b
e
r
em
o
v
ed
b
y
c
o
r
r
ec
tio
n
b
l
o
ck
.
T
h
e
N×
N
b
lo
ck
s
a
r
e
u
s
ed
to
in
ter
p
o
late
2
N×
2
N
o
v
er
lap
p
ed
b
lo
ck
s
.
T
h
e
m
o
d
u
les
f
o
r
esti
m
atin
g
f
o
r
war
d
m
o
ti
o
n
,
b
i
d
ir
ec
tio
n
al
m
o
tio
n
an
d
s
m
o
o
th
in
g
s
p
atial
m
o
ti
o
n
ar
e
th
e
s
am
e
as
th
o
s
e
in
th
e
o
r
ig
i
n
al
alg
o
r
ith
m
[
2
1
]
with
m
o
d
if
icatio
n
o
f
m
o
tio
n
c
o
m
p
e
n
s
atio
n
ar
c
h
itectu
r
e
with
co
u
n
ter
c
o
n
tr
o
lle
d
r
eg
is
ter
s
in
s
tead
o
f
R
AM
co
n
tr
o
lled
.
T
h
e
n
o
v
el
a
r
ch
itectu
r
e
u
s
ed
to
i
m
p
lem
en
t
th
e
m
o
tio
n
co
m
p
en
s
atio
n
th
r
o
u
g
h
in
te
r
p
o
latio
n
[
2
1
]
is
g
iv
en
i
n
Fig
u
r
e
8
.
T
h
e
m
o
tio
n
v
ec
to
r
s
o
b
tain
ed
ar
e
th
e
n
s
to
r
ed
in
to
an
o
th
e
r
tem
p
o
r
ar
y
m
em
o
r
y
wh
ich
ar
e
th
en
u
s
ed
f
o
r
co
m
p
en
s
atin
g
th
e
m
o
tio
n
th
r
o
u
g
h
in
ter
p
o
latio
n
ar
r
a
y
to
g
en
er
ate
th
e
co
r
r
ec
ted
m
o
tio
n
v
ec
to
r
.
T
h
e
en
tire
ar
ch
it
ec
tu
r
e
is
co
n
tr
o
lled
b
y
th
e
c
o
n
tr
o
ller
b
l
o
ck
f
o
r
p
r
o
p
er
s
y
n
ch
r
o
n
izatio
n
.
Fig
u
r
e
7
.
Har
d
war
e
ar
ch
itectu
r
e
o
f
m
o
tio
n
v
ec
to
r
m
em
o
r
y
Fig
u
r
e
8
.
Har
d
war
e
ar
ch
itectu
r
e
o
f
m
o
tio
n
c
o
r
r
ec
tio
n
4.
RE
SU
L
T
S
A
ND
D
IS
CU
SS
I
O
N
T
h
e
m
o
tio
n
esti
m
atio
n
an
d
co
r
r
ec
tio
n
ar
ch
itectu
r
e
a
r
e
d
esig
n
ed
u
s
in
g
VHDL
an
d
v
alid
ated
th
e
d
esig
n
u
s
in
g
Xilin
x
E
DA
to
o
l
f
o
r
Z
y
n
q
Z
7
-
1
0
p
latf
o
r
m
.
4
.
1
.
F
P
G
A
im
plem
ent
a
t
io
n
T
h
e
ar
ch
itectu
r
e
p
r
o
p
o
s
ed
in
th
is
wo
r
k
is
im
p
lem
en
ted
o
n
d
ig
ital
Z
y
n
q
Z
7
-
1
0
FP
GA.
T
h
e
s
tan
d
ar
d
VHDL
co
d
in
g
tech
n
iq
u
e
is
u
s
ed
to
d
esig
n
th
e
ar
ch
itectu
r
e
an
d
is
s
im
u
lated
u
s
in
g
Xilin
x
1
4
.
5
d
esig
n
s
u
ite
to
o
l.
T
h
e
h
a
r
d
war
e
u
tili
za
tio
n
o
f
th
e
p
r
o
p
o
s
ed
m
o
tio
n
esti
m
atio
n
an
d
c
o
m
p
en
s
atio
n
a
r
c
h
itectu
r
e
is
g
iv
en
in
th
e
T
ab
le
1
with
its
in
ter
m
e
d
iate
co
m
p
o
n
en
ts
.
T
ab
le
1
.
Har
d
war
e
u
tili
za
tio
n
s
o
f
m
o
tio
n
esti
m
atio
n
an
d
co
r
r
ec
tio
n
ar
ch
itectu
r
e
P
a
r
a
me
t
e
r
s
S
A
D
C
o
m
p
a
r
a
t
o
r
C
o
n
t
r
o
l
M
e
m
o
r
y
To
t
a
l
M
o
d
u
l
e
F
P
G
A
Zy
n
q
Z7
-
10
(
x
c
7
z
0
1
0
-
1
c
l
g
4
0
0
c
)
S
l
i
c
e
r
e
g
i
s
t
e
r
s
6
1
4
4
1
3
5
21
6
1
5
4
1
2
4
5
0
S
l
i
c
e
LU
Ts
6
2
9
9
1
4
6
4
6
0
2
1
8
4
9
0
8
LU
T
-
FF
p
a
i
r
s
2
9
1
0
86
12
1
8
5
0
5
1
7
M
a
x
i
m
u
m
f
r
e
q
u
e
n
c
y
(
M
H
z
)
1
4
3
2
.
6
6
5
3
2
1
.
4
0
4
6
5
0
.
3
4
7
7
0
7
.
2
1
4
3
2
1
.
4
0
4
T
h
e
Sy
s
tem
g
en
er
ato
r
to
o
l
is
u
s
ed
to
in
p
u
t
th
e
r
ea
l
tim
e
v
id
eo
in
th
e
d
esig
n
ed
ar
c
h
itectu
r
e,
th
r
o
u
g
h
s
tan
d
ar
d
in
ter
f
ac
i
n
g
m
eth
o
d
s
.
Her
e
th
e
in
p
u
t
v
id
eo
is
f
ed
t
o
th
e
FP
GA
u
s
in
g
im
ag
e
p
r
o
ce
s
s
in
g
to
o
lb
o
x
i
n
MA
T
L
AB
.
T
h
e
m
o
tio
n
v
ec
to
r
s
th
u
s
ca
lcu
lated
o
n
FP
GA
ar
e
th
en
u
s
ed
b
y
th
e
MA
T
L
AB
to
o
l
to
i
n
s
er
t
b
o
x
es
f
o
r
b
etter
v
is
u
aliza
tio
n
.
4
.
2
.
P
er
f
o
r
m
a
nce
a
na
ly
s
is
T
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
p
r
o
p
o
s
ed
ar
ch
itectu
r
e
i
n
ter
m
s
o
f
h
ar
d
war
e
u
tili
za
tio
n
s
an
d
d
etec
tio
n
ac
cu
r
ac
y
ar
e
d
is
cu
s
s
ed
as f
o
llo
ws.
4
.
2
.
1
.
Sim
ula
t
io
n
T
h
e
d
esig
n
e
d
a
r
ch
itectu
r
e
is
s
im
u
lated
b
y
tak
i
n
g
t
h
r
ee
d
if
f
e
r
en
t
s
ce
n
ar
io
s
l
o
w
d
e
n
s
ity
tr
a
f
f
ic,
h
i
g
h
d
en
s
ity
tr
af
f
ic
an
d
v
id
e
o
s
team
ca
p
tu
r
ed
u
s
in
g
m
o
v
in
g
ca
m
er
a
to
ev
alu
ate
t
h
e
d
etec
tio
n
ac
cu
r
ac
y
o
f
th
e
s
y
s
tem
.
T
h
e
s
tatis
t
ical
p
ar
am
eter
s
s
u
ch
as
d
etec
tio
n
ac
cu
r
ac
y
,
tr
u
e
d
etec
tio
n
r
ate,
f
alse
d
et
ec
tio
n
r
ate
an
d
n
o
t
d
etec
ted
r
a
te
[
2
2
]
ar
e
ca
lcu
lated
to
v
alid
ate
th
e
d
esig
n
ed
ar
ch
itectu
r
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
23
,
No
.
2
,
Au
g
u
s
t 2
0
2
1
:
802
-
8
1
0
808
Fig
u
r
e
s
9
-
1
1
s
h
o
ws
o
n
e
r
an
d
o
m
f
r
am
e
o
f
th
e
en
tire
s
im
u
la
tio
n
f
o
r
n
o
r
m
al
tr
af
f
ic,
d
en
s
e
tr
af
f
ic
an
d
v
id
eo
tak
en
f
r
o
m
m
o
v
i
n
g
ca
m
er
a
r
esp
ec
tiv
ely
.
Fro
m
th
e
ca
lcu
latio
n
it
is
f
o
u
n
d
th
at
th
e
tr
u
e
d
etec
tio
n
r
ate
is
9
3
.
7
9
%
a
n
d
f
alse
d
etec
tio
n
r
at
e
o
f
4
.
2
1
%.
Un
d
er
d
e
n
s
e
tr
af
f
i
c
co
n
d
itio
n
th
e
tr
u
e
d
etec
tio
n
r
ate
o
f
9
3
.
0
1
%
an
d
th
e
f
alse d
etec
tio
n
r
ate
is
1
3
.
0
2
% is
o
b
tain
ed
b
y
r
an
d
o
m
ly
s
elec
tin
g
th
e
f
r
am
e
f
r
o
m
th
e
en
tire
s
im
u
latio
n
.
Ho
wev
er
,
th
e
v
id
eo
ta
k
en
f
r
o
m
m
o
v
in
g
ca
m
e
r
a
s
h
o
ws
th
e
tr
u
e
d
etec
tio
n
r
ate
o
f
9
2
.
9
3
%
an
d
f
alse
d
etec
tio
n
r
ate
o
f
1
1
.
9
1
%.
T
h
e
r
an
d
am
f
r
am
e
tak
en
f
r
o
m
t
h
e
en
tire
s
im
u
latio
n
r
esu
lt.
E
v
alu
atio
n
o
f
v
a
r
io
u
s
p
ar
am
e
ter
s
ar
e
g
iv
en
in
T
ab
le
2
.
Hig
h
er
v
alu
e
o
f
tr
u
e
d
etec
tio
n
r
ate
in
d
icate
s
th
e
b
etter
d
etec
tio
n
ac
cu
r
ac
y
.
L
o
w
v
alu
e
o
f
n
o
t
d
etec
ted
r
ate
in
d
icate
s
co
r
r
ec
t
d
etec
tio
n
.
T
h
r
o
u
g
h
th
e
a
n
aly
s
is
it
is
o
b
s
er
v
ed
th
at
th
e
d
ev
elo
p
e
d
alg
o
r
ith
m
is
ca
p
ab
l
e
o
f
d
etec
tin
g
th
e
o
b
jects th
at
ar
e
in
m
o
tio
n
.
Fig
u
r
e
9
.
Simu
latio
n
r
es
u
lts
o
f
n
o
r
m
al
tr
a
f
f
ic
f
lo
w
Fig
u
r
e
1
0
.
Simu
latio
n
r
esu
lts
o
f
n
o
r
m
al
d
e
n
s
e
f
lo
w
Fig
u
r
e
1
1
.
Simu
latio
n
r
es
u
lts
o
f
d
etec
tio
n
w
h
en
th
e
ca
m
er
a
is
in
m
o
tio
n
T
ab
le
2
.
T
h
e
p
er
f
o
r
m
a
n
ce
p
ar
am
eter
s
with
r
esp
ec
t to
n
o
r
m
a
l tr
af
f
ic
s
ce
n
ar
io
D
i
f
f
e
r
e
n
t
S
e
n
a
r
i
o
Tr
u
e
D
e
t
e
c
t
i
o
n
R
a
t
e
F
a
l
se
D
e
t
e
c
t
i
o
n
N
o
t
D
e
t
e
c
t
e
d
R
a
t
e
N
o
r
mal
9
3
.
7
9
%
4
.
2
1
%
3
.
1
1
%
D
e
n
se
9
3
.
0
1
%
1
3
.
0
2
%
6
.
0
2
%
M
o
v
i
n
g
C
a
m
e
r
a
9
2
.
9
3
%
1
1
.
9
1
%
9
.
5
5
%
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:
2502
-
4
7
5
2
E
fficien
t reco
n
fig
u
r
a
b
le
a
r
ch
it
ec
tu
r
e
fo
r
mo
vin
g
o
b
ject
d
etec
tio
n
w
ith
mo
tio
n
co
mp
e
n
s
a
tio
n
(
S
r
id
ev
i N
.
)
809
4
.
2
.
2
.
Co
m
pa
riso
ns
wit
h
ex
is
t
ing
t
ec
hn
iqu
es
T
h
e
d
etec
tio
n
ac
cu
r
ac
y
o
f
th
e
p
r
o
p
o
s
ed
ar
c
h
itectu
r
e
is
co
m
p
ar
ed
with
t
h
e
ex
is
tin
g
a
r
c
h
itectu
r
eto
ch
ec
k
th
e
ac
c
u
r
ac
y
wh
ich
is
g
iv
en
in
T
a
b
le
3
.
Fro
m
t
h
e
tab
l
e
it
ca
n
b
e
s
ee
n
th
at
th
e
p
r
o
p
o
s
ed
ar
ch
itectu
r
e
is
ab
le
to
d
etec
t th
e
m
o
v
in
g
o
b
je
ct
ac
cu
r
ately
th
an
ex
is
tin
g
.
T
ab
le
3
.
Dete
ctio
n
ac
c
u
r
ac
y
c
o
m
p
ar
is
o
n
s
o
f
p
r
o
p
o
s
ed
a
r
ch
it
ec
tu
r
e
with
ex
is
tin
g
A
u
t
h
o
rs
Te
c
h
n
i
q
u
e
s
M
a
x
i
m
u
m
A
c
c
u
r
a
c
y
C
h
i
h
-
Y
a
n
g
e
t
a
l
.
[
2
3
]
I
mag
e
B
i
t
-
P
l
a
n
e
s
f
o
r
R
e
a
l
-
Ti
m
e
V
i
d
e
o
S
u
r
v
e
i
l
l
a
n
c
e
8
6
.
3
0
%
Y
u
a
n
d
F
e
n
f
e
n
[
2
4
]
O
p
t
i
c
a
l
f
l
o
w
8
9
.
0
0
%
S
r
i
d
e
v
i
e
t
a
l
.
[
2
5
]
G
a
u
ss
i
a
n
M
i
x
t
u
r
e
M
o
d
e
l
w
i
t
h
M
o
r
p
h
o
l
o
g
i
c
a
l
f
i
l
t
e
r
9
3
.
1
8
%
H
a
i
d
i
Z
h
u
e
t
a
l
.
[
2
6
]
Y
O
LO
8
8
.
5
9
%
P
r
o
p
o
se
d
A
r
c
h
i
t
e
c
t
u
r
e
S
A
D
B
a
se
d
C
o
mp
a
r
i
s
o
n
9
3
.
7
9
%
T
h
e
h
a
r
d
war
e
u
tili
za
tio
n
s
o
f
th
e
p
r
o
p
o
s
ed
ar
ch
itectu
r
e
ar
e
co
m
p
ar
ed
with
th
e
p
r
o
p
o
s
ed
m
o
tio
n
esti
m
atio
n
an
d
co
m
p
en
s
atio
n
ar
ch
itectu
r
e
p
r
esen
ted
b
y
J
in
g
y
an
an
d
Pen
g
[
2
7
]
wh
ich
is
g
i
v
en
in
th
e
T
ab
le
4
.
T
h
e
ar
ch
itectu
r
e
p
r
esen
ted
b
y
J
in
g
y
an
an
d
Pen
g
[
2
7
]
wa
s
im
p
lem
en
ted
o
n
Z
y
n
q
FP
GA
with
h
ig
h
lev
el
p
r
o
g
r
a
m
m
in
g
m
eth
o
d
(
C
/C
+
+
lan
g
u
a
g
e)
wh
ic
h
ar
e
n
o
t
u
s
ef
u
l
to
d
esig
n
p
ar
allel
o
p
tim
ized
h
ar
d
war
e
ar
ch
itectu
r
e.
On
th
e
o
th
er
h
an
d
,
th
e
p
r
o
p
o
s
ed
ar
ch
itectu
r
e
is
im
p
lem
en
ted
u
s
in
g
H
DL
lan
g
u
ag
e
with
ar
ch
itectu
r
al
m
o
d
if
icatio
n
to
g
et
o
p
tim
ized
h
ar
d
war
e
u
tili
za
tio
n
s
T
ab
le
4
.
Har
d
war
e
co
m
p
ar
is
o
n
s
o
f
p
r
o
p
o
s
ed
a
r
ch
itectu
r
e
wi
th
ex
is
tin
g
P
a
r
a
me
t
e
r
s
Ji
n
g
y
a
n
a
n
d
P
e
n
g
[
2
7
]
Jae
c
h
a
n
C
h
o
e
t
a
l
.
[
2
8
]
P
r
o
p
o
se
d
a
r
c
h
i
t
e
c
t
u
r
e
F
P
G
A
Zy
n
q
-
7
V
i
r
t
e
x
-
5
Zy
n
q
-
7
S
l
i
c
e
R
e
g
i
s
t
e
r
1
2
7
6
7
1
3
2
4
5
1
2
4
5
0
S
l
i
c
e
LU
Ts
3
7
7
6
1
----
9
0
8
LU
T
-
F
F
P
a
i
r
s
2
7
8
7
5
----
5
1
7
M
a
x
i
m
u
m
F
r
e
q
u
e
n
c
y
(
M
H
z
)
1
2
8
2
0
0
3
2
1
.
4
0
4
5.
CO
NCLU
SI
O
N
Mo
tio
n
esti
m
atio
n
an
d
co
m
p
e
n
s
atio
n
is
o
n
e
o
f
th
e
m
o
s
t
im
p
o
r
tan
t
m
et
h
o
d
to
d
etec
t
a
n
d
co
r
r
ec
t
th
e
g
lo
b
al
m
o
tio
n
ca
u
s
ed
b
y
th
e
ca
m
er
a.
Fu
r
th
er
,
m
an
y
co
m
p
u
ter
v
is
io
n
ap
p
licatio
n
s
d
em
a
n
d
h
ig
h
s
p
ee
d
,
less
h
ar
d
war
e
u
tili
za
tio
n
in
th
e
ar
ch
itectu
r
e.
I
n
th
is
p
ap
er
,
co
n
s
id
er
in
g
th
e
f
u
ll
s
ea
r
ch
b
lo
ck
b
ased
m
eth
o
d
an
ef
f
icien
t
h
ar
d
wa
r
e
ar
ch
itectu
r
e
f
o
r
m
o
tio
n
esti
m
atio
n
a
n
d
co
m
p
e
n
s
atio
n
f
o
r
p
r
o
p
er
o
b
ject
d
etec
tio
n
is
d
ev
elo
p
e
d
.
Fu
r
th
e
r
,
th
e
ar
ch
ite
ctu
r
e
is
ev
alu
ated
b
y
co
n
s
id
er
i
n
g
th
r
ee
d
if
f
er
en
t
tr
a
f
f
ic
c
o
n
d
i
tio
n
s
.
To
o
p
tim
ize
th
e
h
ar
d
war
e
u
tili
za
tio
n
,
th
e
s
u
m
o
f
a
b
s
o
lu
te
d
if
f
e
r
en
ce
ar
c
h
itectu
r
e
is
o
p
tim
ized
b
y
u
s
in
g
kogge
-
s
to
n
e
ad
d
e
r
.
T
h
e
co
u
n
ter
lo
g
ic
is
u
s
ed
to
o
p
tim
ize
th
e
co
n
t
r
o
ller
ar
c
h
itectu
r
e
b
y
ad
o
p
tin
g
f
in
ite
s
tate
m
ac
h
in
e
(
FSM
)
m
o
d
elin
g
th
er
e
b
y
1
2
4
5
0
s
lice
r
eg
is
ter
an
d
5
1
7
L
UT
-
FF
p
air
s
a
r
e
u
s
ed
to
d
ev
elo
p
th
e
ar
ch
i
tectu
r
e
.
T
h
e
en
tire
ar
ch
itectu
r
e
is
im
p
lem
e
n
ted
o
n
Z
y
n
q
-
Z7
-
1
0
FP
GA
.
T
h
e
e
x
p
er
im
en
tal
v
alid
ati
o
n
p
r
o
v
ed
t
h
at
th
e
ac
c
u
r
ac
y
o
f
9
3
.
7
9
% a
n
d
th
e
o
p
er
atin
g
s
p
e
ed
o
f
3
2
1
.
4
0
4
wh
ich
is
h
ig
h
c
o
m
p
ar
ed
wi
th
s
o
m
e
o
f
th
e
ex
i
s
tin
g
tech
n
iq
u
es.
RE
F
E
R
E
NC
E
S
[1
]
Zh
u
,
J.,
Wan
g
,
Z.
,
Wan
g
,
S
.
,
a
n
d
Ch
e
n
,
S
.
,
“
M
o
v
i
n
g
Ob
jec
t
De
t
e
c
ti
o
n
Ba
se
d
o
n
Ba
c
k
g
ro
u
n
d
C
o
m
p
e
n
sa
ti
o
n
a
n
d
De
e
p
Lea
rn
in
g
,
”
S
y
mm
e
try
,
v
o
l
.
1
2
,
n
o
.
1
2
,
p
p
.
1
-
1
2
,
2
0
2
0
,
d
o
i:
1
0
.
3
3
9
0
/sy
m
1
2
1
2
1
9
6
5
.
[2
]
Bh
a
tt
a
c
h
a
ry
a
,
S
.
,
Id
re
e
s,
H
.
,
S
a
lee
m
i,
I.
,
Ali,
S
.
,
a
n
d
S
h
a
h
,
M
.
,
“
M
o
v
i
n
g
Ob
jec
t
De
tec
ti
o
n
a
n
d
Trac
k
in
g
i
n
F
o
rwa
r
d
Lo
o
k
in
g
In
fra
-
Re
d
Ae
rial
Im
a
g
e
ry
,
”
M
a
c
h
in
e
Vi
sio
n
Bey
o
n
d
Vi
si
b
le
S
p
e
c
tru
m
,
p
p
.
2
2
1
-
2
5
2
,
2
0
1
1
,
d
o
i:
1
0
.
1
0
0
7
/9
7
8
-
3
-
6
4
2
-
1
1
5
6
8
-
4
_
1
0
.
[3
]
Ba
sh
a
,
S
.
,
a
n
d
Ka
n
n
a
n
,
M
.
,
“
Li
tera
tu
re
su
r
v
e
y
o
n
m
o
ti
o
n
e
stim
a
ti
o
n
tec
h
n
i
q
u
e
s
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
En
g
i
n
e
e
rin
g
&
T
e
c
h
n
o
lo
g
y
,
v
o
l.
7
,
n
o
.
2
.
1
2
,
p
.
3
9
4
,
Ap
r.
2
0
1
8
,
d
o
i
:
1
0
.
1
4
4
1
9
/i
jet.
v
7
i2
.
1
2
.
1
1
3
5
8
.
[4
]
Ve
rm
a
,
N.,
S
a
h
u
,
T.
,
a
n
d
S
a
h
u
,
P
.
,
“
Eff
icie
n
t
m
o
ti
o
n
e
stim
a
ti
o
n
b
y
fa
st
t
h
re
e
ste
p
se
a
rc
h
a
lg
o
rit
h
m
s,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
Res
e
a
rc
h
in
El
e
c
trica
l
,
El
e
c
tro
n
ics
a
n
d
In
str
u
me
n
ta
t
io
n
E
n
g
in
e
e
rin
g
,
v
o
l.
1
,
n
o
.
5,
p
p
.
3
8
0
-
3
8
5
,
No
v
.
2
0
1
2
.
[5
]
Ah
m
a
d
i
A.
a
n
d
Az
a
d
fa
r
M
.
M
.
,
“
Im
p
lem
e
n
tatio
n
o
f
F
a
st
M
o
ti
o
n
E
stim
a
ti
o
n
Alg
o
rit
h
m
s
a
n
d
C
o
m
p
a
riso
n
with
F
u
ll
S
e
a
rc
h
M
e
th
o
d
in
H.2
6
4
,
”
IJ
CS
NS
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
Ne
two
rk
S
e
c
u
r
it
y
,
v
o
l
.
8
,
n
o.
3
,
pp.
1
3
9
-
1
4
3
,
M
a
r.
2
0
0
8
.
[6
]
S
a
n
z
C.
,
G
a
rrid
o
M
.
J.
,
a
n
d
M
e
n
e
se
s
J.
M
.
,
“
VLS
I
Arc
h
it
e
c
tu
re
f
o
r
M
o
ti
o
n
Esti
m
a
ti
o
n
u
si
n
g
t
h
e
Blo
c
k
-
M
a
tch
i
n
g
Alg
o
rit
h
m
,
”
Pro
c
e
e
d
i
n
g
s
o
f
th
e
Eu
r
o
p
e
a
n
c
o
n
fer
e
n
c
e
o
n
De
sig
n
a
n
d
T
e
st
,
1
9
9
6
,
p
p
.
3
1
0
-
3
1
4
,
d
o
i:
1
0
.
1
1
0
9
/E
DTC.
1
9
9
6
.
4
9
4
3
1
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
23
,
No
.
2
,
Au
g
u
s
t 2
0
2
1
:
802
-
8
1
0
810
[7
]
Yo
u
sa
f,
A.,
Ha
n
if,
M
.
S
.
,
K
h
a
n
,
M
.
J.,
Iq
b
a
l,
M
.
,
a
n
d
Kh
u
rsh
i
d
,
K.
,
“
Ro
b
u
st
a
n
d
c
o
m
p
u
tatio
n
a
ll
y
e
fficie
n
t
o
n
l
in
e
ima
g
e
sta
b
il
isa
ti
o
n
fra
m
e
wo
rk
b
a
se
d
o
n
a
d
a
p
ti
v
e
d
u
a
l
m
o
t
io
n
v
e
c
to
r
in
teg
ra
ti
o
n
,
”
IE
T
C
o
mp
u
ter
Vi
sio
n
,
v
o
l.
1
3
,
no
.
5
,
p
p
.
4
6
1
-
4
6
8
,
2
0
1
9
,
d
o
i:
1
0
.
1
0
4
9
/i
e
t
-
c
v
i.
2
0
1
8
.
5
3
6
8
.
[8
]
Tan
g
,
J.
W.
,
S
h
a
i
k
h
-
Hu
si
n
,
N.,
S
h
e
ik
h
,
U.
U.,
a
n
d
M
a
rso
n
o
,
M
.
N.
,
“
F
P
G
A
-
Ba
s
e
d
Re
a
l
-
Ti
m
e
M
o
v
i
n
g
Tar
g
e
t
De
tec
ti
o
n
S
y
ste
m
fo
r
U
n
m
a
n
n
e
d
Ae
rial
Ve
h
icle
Ap
p
li
c
a
ti
o
n
,
”
I
n
te
rn
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Rec
o
n
fi
g
u
r
a
b
le
Co
m
p
u
ti
n
g
,
v
o
l.
2
0
1
6
,
n
o
.
3
,
p
p
.
1
-
1
6
,
2
0
1
6
,
d
o
i:
1
0
.
1
1
5
5
/
2
0
1
6
/8
4
5
7
9
0
8
.
[9
]
P
a
k
d
a
m
a
n
,
F
.
,
Ha
sh
e
m
i,
M
.
R
.
,
a
n
d
G
h
a
n
b
a
ri
,
M
.
,
“
A
l
o
w
c
o
m
p
lex
it
y
a
n
d
c
o
m
p
u
tati
o
n
a
ll
y
sc
a
la
b
le
fa
st
m
o
ti
o
n
e
stim
a
ti
o
n
a
lg
o
r
it
h
m
fo
r
HEV
C
,
”
M
u
lt
ime
d
ia
T
o
o
ls
a
n
d
A
p
p
li
c
a
ti
o
n
s
,
v
o
l.
7
9
,
p
p
.
1
1
6
3
9
-
1
1
6
6
6
,
2
0
2
0
,
d
o
i:
1
0
.
1
0
0
7
/s1
1
0
4
2
-
0
1
9
-
0
8
5
9
3
-
y
.
[1
0
]
Bn
a
d
o
u
,
R.
,
Hira
m
o
ri,
M
.
,
Iwa
d
e
,
S
.
,
M
a
k
i
n
o
,
H.,
Y
o
sh
imu
ra
,
T.
,
a
n
d
M
a
tsu
d
a
,
Y.
,
“
A S
tu
d
y
o
n
M
o
t
io
n
Esti
m
a
ti
o
n
Alg
o
rit
h
m
f
o
r
M
o
v
in
g
P
ictu
re
s
,
”
2
0
1
6
IE
EE
5
t
h
Gl
o
b
a
l
Co
n
fe
re
n
c
e
o
n
Co
n
su
me
r
E
lec
tro
n
ics
,
p
p
.
1
-
3
,
2
0
1
6
,
d
o
i:
1
0
.
1
1
0
9
/G
CCE.
2
0
1
6
.
7
8
0
0
4
3
9
.
[1
1
]
M
o
g
u
s,
F
.
A.,
Li
u
,
X.
,
a
n
d
Wan
g
,
L.
,
“
Ev
a
lu
a
t
io
n
o
f
t
h
e
P
e
rfo
rm
a
n
c
e
o
f
M
o
t
io
n
Est
ima
ti
o
n
Alg
o
r
it
h
m
s
i
n
Vi
d
e
o
Co
d
i
n
g
,
”
In
T
h
e
2
n
d
IEE
E
In
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
I
n
fo
rm
a
t
io
n
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
,
2
0
1
0
,
p
p
.
3
6
9
3
-
3
6
9
6
,
d
o
i:
1
0
.
1
1
0
9
/ICIS
E.
2
0
1
0
.
5
6
9
1
6
4
3
.
[1
2
]
S
h
u
,
Q.,
a
n
d
Ch
e
n
,
H.
,
“
An
e
f
ficie
n
t
imp
lem
e
n
tatio
n
o
f
m
o
ti
o
n
e
stim
a
ti
o
n
a
l
g
o
rit
h
m
s,”
Pro
c
e
e
d
in
g
s
o
f
4
t
h
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
S
o
li
d
-
S
t
a
te a
n
d
IC
T
e
c
h
n
o
l
o
g
y
,
1
9
9
5
,
d
o
i
:
1
0
.
1
1
0
9
/ICS
ICT.
1
9
9
5
.
5
0
3
3
9
4
.
[1
3
]
Ch
a
tt
e
rjee
,
S
.
K.,
a
n
d
Vitt
a
p
u
,
S
.
K.
,
“
An
Eff
icie
n
t
M
o
ti
o
n
Est
ima
ti
o
n
Al
g
o
rit
h
m
fo
r
M
o
b
il
e
Vid
e
o
Ap
p
li
c
a
ti
o
n
s
,
”
2
0
1
9
S
e
c
o
n
d
In
ter
n
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
Ad
v
a
n
c
e
d
Co
mp
u
t
a
ti
o
n
a
l
a
n
d
Co
mm
u
n
ica
t
io
n
Pa
r
a
d
i
g
ms
(ICACCP
)
,
2
0
1
9
,
p
p
.
1
-
5,
d
o
i:
1
0
.
1
1
0
9
/ICAC
CP
.
2
0
1
9
.
8
8
8
2
9
4
8
.
[1
4
]
G
h
a
ra
v
i
H.
a
n
d
M
il
ls
M.
,
“
Blo
c
k
m
a
tch
in
g
M
o
ti
o
n
Esti
m
a
ti
o
n
A
lg
o
rit
h
m
s
,
”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Circ
u
it
s
a
n
d
S
y
ste
ms
, v
o
l.
3
7
,
no
.
5
,
p
p
.
6
4
9
-
6
5
1
,
1
9
9
0
,
d
o
i:
1
0
.
1
1
0
9
/3
1
.
5
5
0
1
0
.
[1
5
]
B
h
a
t
t
a
c
h
a
r
y
y
a
,
D
.
,
C
h
a
k
r
a
b
a
r
t
i
,
A
.
,
a
n
d
M
i
s
r
a
,
S
.
,
“
D
e
s
i
g
n
a
n
d
S
i
m
u
l
a
t
i
o
n
o
f
P
a
r
a
l
l
e
l
A
l
g
o
r
i
t
h
m
s
f
o
r
M
o
t
i
o
n
E
s
t
i
m
a
t
i
o
n
,
”
1
0
t
h
I
E
E
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
r
m
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
2
0
0
7
,
p
p
.
2
9
-
3
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
T
.
2
0
0
7
.
4
4
.
[1
6
]
S
in
g
h
K.
,
a
n
d
Ah
a
m
e
d
,
S
.
R
.
,
“
A
Ne
w
M
o
ti
o
n
Esti
m
a
ti
o
n
Alg
o
r
it
h
m
fo
r
Hig
h
Eff
icie
n
t
Vi
d
e
o
C
o
d
i
n
g
S
tan
d
a
rd
,
”
2
0
1
5
A
n
n
u
a
l
IEE
E
In
d
ia
Co
n
fer
e
n
c
e
(INDICO
N)
,
2
0
1
5
,
p
p
.
1
-
5
,
d
o
i:
1
0
.
1
1
0
9
/INDICO
N.
2
0
1
5
.
7
4
4
3
6
1
4
.
[1
7
]
Tap
a
sv
i,
B.
,
S
in
d
u
ri
,
K.
B.
,
Lak
s
h
m
i,
B.
G
.
S
.
S
.
B.
,
a
n
d
Ku
m
a
r,
N.
U.
,
“
Im
p
lem
e
n
tatio
n
o
f
6
4
-
Bi
t
Ko
g
g
e
S
to
n
e
Ca
rry
S
e
lec
t
Ad
d
e
r
with
ZF
C
fo
r
Eff
icie
n
t
Are
a
,
”
In
2
0
1
5
IE
EE
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
El
e
c
t
ric
a
l,
Co
mp
u
ter
a
n
d
Co
mm
u
n
ica
t
io
n
T
e
c
h
n
o
l
o
g
ie
s (ICE
CCT
)
,
2
0
1
5
,
p
p
.
1
-
6
,
d
o
i:
1
0
.
1
1
0
9
/ICE
CCT.
2
0
1
5
.
7
2
2
6
1
5
4
.
[1
8
]
M
ish
ra
P.
,
Ap
o
o
r
v
a
R
.
,
P
a
rv
a
ti
k
a
r
B.
B.
,
a
n
d
Na
ir
L.
,
“
Arc
h
i
tec
tu
re
s
fo
r
F
P
G
A
-
Ba
se
d
Im
p
lem
e
n
tatio
n
o
f
M
o
ti
o
n
Esti
m
a
ti
o
n
o
f
Dy
n
a
m
ic
O
b
sta
c
les
fo
r
A
u
to
n
o
m
o
u
s
R
o
b
o
t
Na
v
ig
a
ti
o
n
,
”
2
0
1
1
T
h
ir
d
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Co
mp
u
t
a
ti
o
n
a
l
I
n
telli
g
e
n
c
e
,
Co
m
mu
n
ica
t
io
n
S
y
ste
ms
a
n
d
Ne
tw
o
rk
s
,
2
0
1
1
,
d
o
i:
1
0
.
1
1
0
9
/CICS
y
N
.
2
0
1
1
.
68
.
[1
9
]
Bo
o
n
th
e
p
N.
,
Ch
a
m
n
o
n
g
th
a
i
K
.
,
a
n
d
P
h
e
n
sa
d
sa
e
n
g
P.
,
“
A F
P
G
A
-
b
a
se
d
S
IF
T
Arc
h
it
e
c
tu
re
fo
r
M
o
ti
o
n
Esti
m
a
ti
o
n
i
n
Vid
e
o
Co
d
i
n
g
,
”
2
0
1
8
Glo
b
a
l
W
ir
e
les
s S
u
mm
it
(GW
S
)
,
2
0
1
9
,
p
p
.
3
8
3
-
3
8
8
,
d
o
i:
1
0
.
1
1
0
9
/G
WS
.
2
0
1
8
.
8
6
8
6
4
0
3
.
[2
0
]
Xia
n
g
L.
M
.
,
Zab
i
d
i
M
.
A.
,
M
.
,
Aw
a
b
,
A.
H.,
a
n
d
Ab
Ra
h
m
a
n
,
A.
A.
H.
,
“
VLS
I
Im
p
lme
n
tatio
n
o
f
a
F
a
st
Ko
g
g
e
-
S
to
n
e
P
a
ra
ll
e
l
-
P
re
fix
A
d
d
e
r
,
”
J
o
u
rn
a
l
o
f
P
h
y
sic
s:
Co
n
fer
e
n
c
e
S
e
rie
s
,
2
0
1
8
,
v
o
l.
1
0
4
9
,
n
o
.
1
,
p
p
.
1
-
1
0
,
d
o
i:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/1
0
4
9
/1
/
0
1
2
0
7
7
.
[2
1
]
Zh
a
n
g
D.
Y
.
,
Ji
Y.
T.
,
a
n
d
Wan
g
X.
M.
,
“
A
Weig
h
ted
M
o
t
io
n
C
o
m
p
e
n
sa
ti
o
n
In
ter
p
o
lati
o
n
M
e
th
o
d
fo
r
Im
p
ro
v
in
g
S
id
e
I
n
fo
rm
a
ti
o
n
in
Distri
b
u
te
d
Vid
e
o
C
o
d
in
g
,
”
A
p
p
l
ied
M
e
c
h
a
n
ics
a
n
d
M
a
ter
ia
ls
,
v
o
l.
5
1
9
,
p
p
.
6
7
2
-
6
7
6
,
2
0
1
4
,
d
o
i:
1
0
.
4
0
2
8
/www
.
sc
ien
ti
fic.n
e
t/
AMM
.
5
1
9
-
5
2
0
.
6
7
0
.
[2
2
]
S
rid
e
v
i
N
.
a
n
d
M
e
e
n
a
k
s
h
i
M
.
,
“
Eff
icie
n
t
M
o
v
in
g
Ve
h
icle
De
tec
ti
o
n
Alg
o
rit
h
m
fo
r
Va
rio
u
s
Traffic
Co
n
d
it
i
o
n
s
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
r
n
a
l
o
f
Re
c
e
n
t
T
e
c
h
n
o
lo
g
y
a
n
d
E
n
g
i
n
e
e
rin
g
(IJ
RT
E)
,
p
p
-
6
0
6
9
-
6
0
7
6
,
S
e
p
.
2
0
1
9
,
d
o
i:
1
0
.
3
5
9
4
0
/
ij
rte.C5
6
1
9
.
0
9
8
3
1
9
.
[2
3
]
Ch
ih
-
Ya
n
g
L.
,
Zh
i
-
Ya
o
J.
,
a
n
d
Wei
-
Ya
n
g
L.
,
“
Im
a
g
e
Bit
-
P
lan
e
s
Re
p
re
se
n
tatio
n
f
o
r
M
o
v
in
g
Ob
j
e
c
t
De
tec
ti
o
n
i
n
Re
a
l
-
Ti
m
e
Vid
e
o
S
u
r
v
e
il
lan
c
e
,
”
2
0
1
6
IEE
E
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Co
n
su
me
r
El
e
c
tro
n
ics
-
T
a
iwa
n
(ICCE
-
T
W
)
,
2
0
1
6
,
p
p
.
1
-
2
,
d
o
i:
1
0
.
1
1
0
9
/I
CCE
-
TW
.
2
0
1
6
.
7
5
2
0
9
4
9
.
[2
4
]
Zh
a
n
g
Y.
a
n
d
Wa
n
g
F
.
,
“
Im
p
ro
v
e
d
o
p
ti
c
a
l
flo
w
a
lg
o
rit
h
m
o
f
m
o
v
in
g
o
b
jec
t
De
tec
ti
o
n
,
”
2
0
1
5
Fi
ft
h
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
I
n
stru
me
n
t
a
ti
o
n
a
n
d
M
e
a
su
re
me
n
t,
Co
mp
u
ter
,
Co
mm
u
n
ica
ti
o
n
a
n
d
C
o
n
tro
l
(
IM
CCC)
,
2
0
1
6
,
p
p
.
1
9
6
-
1
9
9
,
d
o
i:
1
0
.
1
1
0
9
/IM
CCC
.
2
0
1
5
.
4
8
.
[2
5
]
S
rid
e
v
i
N.,
a
n
d
M
e
e
n
a
k
sh
i
M.
,
“
Eff
icie
n
t
M
o
v
e
m
e
n
t
C
o
m
p
e
n
sa
ti
o
n
a
n
d
De
tec
ti
o
n
Al
g
o
ri
th
m
u
sin
g
Blo
b
De
tec
ti
o
n
a
n
d
M
o
d
ifi
e
d
Ka
lma
n
F
il
ter
,
”
2
0
2
0
5
th
I
n
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
C
o
mm
u
n
ic
a
ti
o
n
a
n
d
El
e
c
tro
n
ics
S
y
ste
ms
(ICCES
)
,
2
0
2
0
,
pp
-
2
6
4
-
2
6
8
,
d
o
i
:
1
0
.
1
1
0
9
/ICC
ES
4
8
7
6
6
.
2
0
2
0
.
9
1
3
8
0
3
1
.
[2
6
]
Zh
u
H.
,
Wei
H.
,
L
i
B.
,
Yu
a
n
X.
,
a
n
d
Ke
h
tarn
a
v
a
z
N.
,
“
Re
a
l
-
Ti
m
e
M
o
v
i
n
g
O
b
jec
t
De
tec
ti
o
n
in
Hig
h
-
Re
so
l
u
ti
o
n
Vid
e
o
S
e
n
si
n
g
,
”
S
e
n
s
o
rs
,
v
o
l.
2
0
,
n
o
.
1
2
,
p
p
.
1
-
1
5
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/s2
0
1
2
3
5
9
1
.
[2
7
]
S
h
e
J.
a
n
d
Du
P
.
,
“
F
P
G
A
-
Ba
se
d
M
o
ti
o
n
Esti
m
a
ti
o
n
Alg
o
rit
h
m
Op
ti
m
iza
ti
o
n
,
”
M
icr
o
p
ro
c
e
ss
o
rs
a
n
d
M
icr
o
sy
ste
ms
,
v
o
l.
8
0
,
p
p
.
1
-
1
3
,
2
0
2
1
,
d
o
i:
1
0
.
1
0
1
6
/j
.
m
icp
r
o
.
2
0
2
0
.
1
0
3
5
5
5
.
[2
8
]
Ch
o
J.
,
J
u
n
g
Y
.
,
Kim
D.
,
Lee
S
.
,
a
n
d
Ju
n
g
Y.
,
“
M
o
v
in
g
Ob
jec
t
De
tec
ti
o
n
Ba
se
d
o
n
Op
ti
c
a
l
F
l
o
w
Es
ti
m
a
ti
o
n
a
n
d
a
G
a
u
ss
ian
M
ix
tu
re
M
o
d
e
l
f
o
r
A
d
v
a
n
c
e
d
Driv
e
r
As
sista
n
c
e
S
y
st
e
m
s
,
”
S
e
n
so
rs
,
v
o
l.
1
9
,
n
o
.
4
,
p
p
.
1
-
1
4
,
2
0
1
9
,
d
o
i:
1
0
.
3
3
9
0
/s1
9
1
4
3
2
1
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.