I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
p
u
t
er
Science
Vo
l.
10
,
No
.
2
,
May
201
8
,
p
p
.
8
1
7
~8
2
6
I
SS
N:
2502
-
4752
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ee
cs
.
v
1
0
.
i2
.
p
p
817
-
8
2
6
817
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e.
co
m/jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
ijeec
s
Ro
bust Visio
n
-
ba
sed M
ultiple
Mo
v
ing
O
bj
ect
Detect
io
n and
Tra
ck
ing
fro
m
Vi
deo
Sequen
ces
O
t
h
m
a
n O
m
ra
n K
ha
lifa
,
No
run Abd
ul M
a
lek
*
,
K
a
zi
I
s
t
ia
qu
e
Ah
m
ed,
F
a
ra
h Abd
ul
Ra
h
m
a
n
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
a
n
d
Co
m
p
u
ter E
n
g
in
e
e
rin
g
,
Ku
ll
iy
y
a
h
o
f
En
g
in
e
e
rin
g
In
tern
a
ti
o
n
a
l
Isla
m
ic Un
iv
e
rsit
y
M
a
la
y
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
N
ov
17
,
2
0
1
7
R
ev
i
s
ed
J
an
2
5
,
2
0
1
8
A
cc
ep
ted
F
eb
1
9
,
2
0
1
8
De
tec
ti
o
n
o
f
M
o
v
in
g
Ob
jec
ts
a
n
d
T
ra
c
k
in
g
is
o
n
e
o
f
th
e
m
o
st
c
o
n
c
e
rn
e
d
issu
e
a
n
d
is
b
e
in
g
v
a
stly
u
se
d
a
t
h
o
m
e
,
b
u
si
n
e
ss
a
n
d
m
o
d
e
rn
a
p
p
li
c
a
ti
o
n
s.
It
is
u
se
d
to
id
e
n
ti
f
y
a
n
d
trac
k
o
f
a
n
e
n
ti
ty
in
a
sig
n
if
i
c
a
n
t
w
a
y
.
T
h
is
p
a
p
e
r
il
lu
stra
tes
th
e
wa
y
to
d
e
tec
t
m
u
l
ti
p
le
o
b
jec
ts
u
sin
g
b
a
c
k
g
ro
u
n
d
s
u
b
trac
ti
o
n
m
e
th
o
d
s
a
n
d
e
x
trac
t
e
a
c
h
o
b
jec
t
f
e
a
tu
re
s
b
y
u
sin
g
S
p
e
e
d
-
Up
Ro
b
u
st
F
e
a
tu
re
a
lg
o
rit
h
m
a
n
d
trac
k
th
e
f
e
a
tu
re
s
t
h
ro
u
g
h
k
-
Ne
a
re
st
Ne
ig
h
b
o
r
p
ro
c
e
ss
in
g
f
ro
m
d
if
fe
re
n
t
su
rv
e
il
lan
c
e
v
id
e
o
s
se
q
u
e
n
ti
a
ll
y
.
In
th
e
d
e
tec
ti
o
n
o
f
o
b
j
e
c
t
o
f
e
a
c
h
f
ra
m
e
,
p
ix
e
l
d
iffere
n
c
e
is
c
a
lcu
late
d
w
it
h
re
sp
e
c
t
to
th
e
re
f
e
re
n
c
e
b
a
c
k
g
ro
u
n
d
f
ra
m
e
f
o
r
th
e
d
e
te
c
ti
o
n
o
f
a
n
o
b
jec
t
w
h
ich
is
o
n
ly
su
it
a
b
le
f
o
r
a
n
y
i
d
e
a
l
sta
ti
c
c
o
n
d
i
ti
o
n
w
it
h
th
e
c
o
n
si
d
e
ra
ti
o
n
o
f
li
g
h
ts
f
ro
m
th
e
e
n
v
iro
n
m
e
n
t.
T
h
u
s,
th
is
m
e
th
o
d
w
il
l
d
e
tec
t
th
e
c
o
m
p
lete
o
b
jec
t
a
n
d
th
e
e
x
trac
ted
f
e
a
tu
re
w
il
l
b
e
c
a
rried
o
u
t
f
o
r
th
e
trac
k
in
g
o
f
th
e
o
b
jec
t
in
th
e
m
u
lt
ip
le
v
id
e
o
s
b
y
o
n
e
b
y
o
n
e
v
id
e
o
.
It
is
e
x
p
e
c
ted
t
h
a
t
t
h
is
p
ro
p
o
se
d
m
e
th
o
d
c
a
n
c
o
m
m
e
n
d
a
b
l
y
a
b
o
li
sh
th
e
im
p
a
c
t
o
f
th
e
c
h
a
n
g
in
g
o
f
li
g
h
t
s.
K
ey
w
o
r
d
s
:
De
tec
ti
o
n
o
f
m
o
v
in
g
o
b
jec
t
T
ra
c
k
in
g
Re
fe
re
n
c
e
b
a
c
k
g
ro
u
n
d
S
URF
KNN
Co
p
y
rig
h
t
©
2
0
1
8
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
No
r
u
n
A
b
d
u
l M
ale
k
,
Dep
ar
t
m
en
t o
f
E
lectr
ical
an
d
C
o
m
p
u
ter
E
n
g
in
ee
r
i
n
g
,
Ku
lli
y
y
ah
o
f
E
n
g
in
ee
r
i
n
g
I
n
ter
n
atio
n
al
I
s
la
m
ic
U
n
iv
er
s
it
y
Ma
la
y
s
ia
E
m
ail:
n
o
r
u
n
@
i
iu
m
.
ed
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
I
n
co
m
p
u
ter
v
is
io
n
,
th
e
a
u
to
m
atic
v
is
u
al
d
etec
tio
n
o
f
a
th
in
g
,
as
w
el
l
as
tr
ac
k
i
n
g
,
is
o
n
e
m
o
s
t
th
o
u
g
h
t
-
p
r
o
v
o
k
in
g
d
is
p
u
tes
at
h
o
m
e
s
,
b
u
s
in
e
s
s
e
s
,
an
d
i
n
d
u
s
t
r
ies.
T
h
e
n
u
m
b
er
o
f
v
i
s
u
al
d
et
ec
tio
n
a
n
d
tr
ac
k
i
n
g
ap
p
licatio
n
s
ar
e
v
o
l
u
m
in
o
u
s
w
h
ile
t
h
o
s
e
e
x
te
n
s
i
v
e
v
ar
ieties
o
f
t
h
e
ap
p
licatio
n
s
ca
n
b
e
f
o
u
n
d
a
s
w
el
l
in
r
ec
o
n
n
ais
s
an
ce
s
y
s
te
m
,
v
eh
icle
tr
ac
k
in
g
a
n
d
ae
r
o
s
p
ac
e
ap
p
licatio
n
s
ar
e
th
e
n
a
m
es
o
f
a
f
e
w
.
B
y
u
s
i
n
g
co
n
v
e
n
tio
n
al
m
o
tio
n
est
i
m
at
io
n
m
et
h
o
d
s
an
d
p
atter
n
r
ec
o
g
n
i
tio
n
,
th
e
r
eso
lu
tio
n
s
f
o
r
tr
ac
k
in
g
a
n
d
d
etec
ti
o
n
o
f
ab
s
tr
ac
t
th
i
n
g
s
s
p
ec
i
f
icall
y
v
e
h
icles,
in
g
e
n
er
al,
i
s
a
d
eli
n
q
u
en
t.
I
n
o
n
e
h
a
n
d
,
d
etec
tio
n
o
f
m
o
v
i
n
g
t
h
i
n
g
s
f
r
o
m
th
e
b
ac
k
g
r
o
u
n
d
i
m
a
g
e
to
th
e
c
o
n
tin
u
o
u
s
v
id
eo
f
r
a
m
e
s
ar
e
tr
ea
ted
as
r
ec
o
g
n
itio
n
o
f
t
h
e
m
o
v
in
g
tar
g
et
s
an
d
o
n
th
e
o
th
er
h
a
n
d
,
f
i
n
d
in
g
v
ar
io
u
s
lo
ca
tio
n
s
o
f
t
h
e
m
o
v
i
n
g
t
h
i
n
g
s
i
n
a
v
id
eo
is
tr
ea
ted
as
tr
ac
k
in
g
o
f
t
h
e
m
o
v
i
n
g
tar
g
ets.
T
o
d
etec
t
an
d
tr
ac
k
d
o
w
n
th
o
s
e
m
o
v
in
g
o
b
j
ec
ts
,
it
r
eq
u
ir
es
p
r
o
ce
s
s
to
p
er
f
o
r
m
s
u
c
h
k
in
d
o
f
tas
k
.
Su
b
tr
ac
tio
n
o
f
t
w
o
co
n
s
ec
u
ti
v
e
f
r
a
m
es,
s
u
b
tr
ac
tio
n
o
f
b
ac
k
g
r
o
u
n
d
f
r
o
m
f
r
a
m
e
s
a
n
d
o
p
tica
l
f
lo
w
ar
e
t
h
e
m
ai
n
o
f
th
e
w
ell
-
k
n
o
w
n
m
et
h
o
d
s
f
o
r
th
e
m
o
v
i
n
g
o
b
j
ec
t
d
etec
tio
n
[
1
]
.
I
n
th
e
Op
tical
Flo
w
m
o
v
i
n
g
o
b
j
ec
t
d
etec
tio
n
p
r
o
ce
d
u
r
e
[
2
]
,
th
e
f
lo
w
f
ield
i
m
ag
e
i
s
ca
lcu
lated
an
d
th
e
d
is
tr
ib
u
tio
n
o
f
t
h
e
f
ea
t
u
r
e
is
d
o
n
e
b
y
cl
u
s
te
r
p
r
o
ce
s
s
in
g
w
h
ic
h
is
b
etter
.
B
u
t
th
is
p
r
o
ce
d
u
r
e
is
n
o
t
s
u
i
ta
b
le
f
o
r
r
ea
l
-
ti
m
e
p
r
o
ce
s
s
i
n
g
b
ec
au
s
e
o
f
its
lar
g
e
a
m
o
u
n
t o
f
ca
lc
u
latio
n
an
d
it
s
s
en
s
it
iv
i
t
y
to
n
o
i
s
e
an
d
lac
k
o
f
an
ti
-
n
o
i
s
e
p
er
f
o
r
m
a
n
ce
[
3
]
.
On
th
e
o
t
h
er
h
a
n
d
,
in
b
ac
k
g
r
o
u
n
d
s
u
b
tr
ac
tio
n
p
r
o
ce
d
u
r
e
[
3
]
,
th
e
m
o
v
i
n
g
o
b
j
ec
t
is
d
etec
ted
b
y
s
u
b
tr
ac
ti
n
g
t
h
e
b
ac
k
g
r
o
u
n
d
f
r
o
m
th
e
cu
r
r
en
t
f
r
a
m
e,
is
a
s
i
m
p
le
p
r
o
ce
d
u
r
e
an
d
i
n
t
h
e
ca
s
e
o
f
alr
ea
d
y
k
n
o
w
n
b
ac
k
g
r
o
u
n
d
,
t
h
is
p
r
o
ce
s
s
co
u
ld
ab
le
to
p
r
o
v
id
e
a
co
m
p
lete
in
f
o
r
m
at
io
n
ab
o
u
t
th
e
o
b
j
ec
ts
.
Fo
r
t
h
e
f
ea
t
u
r
e
ex
tr
ac
tio
n
,
th
er
e
ar
e
m
a
n
y
a
v
ailab
le
m
et
h
o
d
s
s
u
c
h
asS
p
ee
d
-
Up
R
o
b
u
s
t
Featu
r
e
s
(
SUR
F)
w
h
ic
h
is
a
s
p
ee
d
-
u
p
Ver
s
io
n
Scal
e
I
n
v
ar
ian
t
Fea
t
u
r
e
T
r
an
s
f
o
r
m
s
(
SIFT
)
.
Ma
n
y
a
u
t
h
o
r
s
,
[
1
]
,
[
4
]
–
[
6
]
u
tili
ze
ce
r
tai
n
f
a
m
iliar
it
y
to
p
r
o
v
id
e
th
e
v
i
d
eo
ad
v
an
ce
m
e
n
t
b
y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
10
,
No
.
2
,
Ma
y
2
0
1
8
:
8
1
7
–
8
2
6
818
d
ef
in
i
n
g
th
e
r
elatio
n
s
h
ip
b
et
wee
n
o
b
j
ec
ts
w
it
h
s
p
atial,
te
m
p
o
r
al,
an
d
c
o
-
o
cc
u
r
r
en
ce
.
On
th
e
o
th
er
h
an
d
,
m
an
y
au
th
o
r
s
h
i
g
h
lig
h
t
[
3
]
,
[
4
]
,
[
7
]
th
e
d
is
p
u
te
o
f
f
i
n
d
in
g
m
u
lti
p
le
o
b
j
ec
ts
f
r
o
m
th
e
co
n
tin
u
o
u
s
s
eq
u
en
ce
o
f
th
e
f
r
a
m
e
a
s
r
elate
d
f
r
a
m
es.
I
n
[
4
]
s
h
o
w
s
t
h
e
tr
ac
k
i
n
g
o
f
t
h
e
o
b
j
ec
t
an
d
p
r
o
p
o
s
ed
a
m
et
h
o
d
to
lo
ca
lize
th
e
o
b
j
ec
t
in
t
h
e
i
m
a
g
e
a
n
d
th
e
y
s
h
o
w
e
d
th
at
it
w
o
r
k
s
b
etter
w
it
h
S
UR
F
f
ea
t
u
r
e
ex
tr
ac
tio
n
a
n
d
i
m
p
r
o
v
ed
C
a
m
s
h
i
f
t
alg
o
r
ith
m
b
y
a
u
to
m
atica
ll
y
ad
j
u
s
tin
g
t
h
e
ill
u
m
in
at
io
n
to
f
in
d
o
u
t
a
lo
s
t
tar
g
et
to
tr
ac
k
d
o
w
n
o
f
t
h
e
f
ea
tu
r
e
s
o
f
th
e
o
b
j
ec
t.
Mo
r
e
o
v
er
,
th
e
au
t
h
o
r
s
[
8
]
,
s
h
o
w
s
t
h
e
tr
ac
k
i
n
g
s
tr
ateg
y
u
s
in
g
t
h
e
s
a
m
e
C
a
m
s
h
i
f
t
p
r
o
ce
d
u
r
e
f
o
r
th
e
PT
Z
C
a
m
er
a.
Nev
er
t
h
ele
s
s
,
t
h
is
r
esear
ch
w
o
r
k
d
id
n
o
t
p
r
o
v
i
d
e
s
atis
f
ac
to
r
y
o
u
tp
u
t
p
er
f
o
r
m
an
ce
f
o
r
th
e
i
m
a
g
e
w
it
h
o
u
t stro
n
g
i
m
ag
e
te
x
t
u
r
e
an
d
th
eir
f
ea
tu
r
es a
s
s
h
o
w
n
i
n
F
ig
u
r
e
1
.
Fig
u
r
e
1
.
Gen
er
al
R
ep
r
esen
tati
o
n
o
f
th
e
S
y
s
te
m
Ho
w
e
v
er
[
5
]
s
h
o
w
ed
s
u
cc
es
s
f
u
ll
y
f
o
r
th
e
s
a
m
e
s
o
r
t
o
f
i
m
a
g
e
o
b
j
ec
ts
w
h
ic
h
also
tak
en
in
to
co
n
s
id
er
atio
n
o
f
m
u
ltip
le
s
it
u
a
tio
n
s
.
I
t
s
h
o
w
s
th
at
i
t
w
ill
w
o
r
k
p
er
f
ec
tl
y
i
f
t
h
e
i
m
ag
e
o
b
j
ec
t
s
ca
led
d
o
w
n
o
r
u
p
an
d
ch
a
n
g
e
in
r
o
tatio
n
in
m
u
lt
ip
le
o
b
j
e
ct
d
etec
tio
n
r
esear
ch
.
Ho
w
e
v
er
,
it d
id
n
o
t p
r
o
v
id
e
an
y
c
lear
in
f
o
r
m
atio
n
f
o
r
th
e
2
o
r
m
o
r
e
d
is
t
in
ct
i
m
ag
es
w
h
er
e
f
o
r
t
h
e
r
e
s
ea
r
ch
i
t r
e
q
u
ir
ed
d
if
f
er
en
t
s
o
r
t o
f
o
b
j
ec
t to
b
e
id
en
ti
f
ied
a
n
d
it
is
also
n
o
t
clea
r
o
n
t
h
e
v
id
eo
s
eg
m
en
ta
tio
n
p
ar
t.
Si
m
ilar
l
y
b
y
u
s
i
n
g
I
m
p
r
o
v
ed
K
L
T
T
r
ac
k
in
g
C
lass
if
ier
ab
o
v
e
SUR
F,
[
6
]
s
i
m
u
la
ted
t
r
ac
k
in
g
t
h
e
d
etec
ted
o
b
j
ec
t
b
y
e
x
tr
ac
tin
g
t
h
e
f
ea
t
u
r
es
u
s
in
g
SU
R
F
an
d
tr
ac
k
d
o
w
n
th
e
f
ea
tu
r
e
u
s
i
n
g
K
L
T
f
o
r
m
u
lt
ip
le
o
b
j
ec
ts
.
I
n
[
2
]
,
t
h
e
De
m
o
n
s
tr
ated
Kal
m
a
n
c
h
a
n
n
el
i
s
u
tili
ze
d
to
s
ca
le
th
e
co
n
d
itio
n
o
f
an
o
b
j
e
ctiv
e
q
u
es
tio
n
.
A
n
o
p
tical
s
tr
ea
m
ca
n
g
au
g
e
th
e
s
p
ee
d
s
o
f
a
p
r
o
test
an
d
u
s
in
g
d
ef
o
r
m
ab
le
f
r
ag
m
en
t
m
et
h
o
d
[
9
]
co
n
f
ir
m
ed
a
n
ap
p
r
o
ac
h
to
p
er
ce
iv
e
an
d
tr
ac
k
m
u
ltip
le
o
b
j
ec
t
in
C
C
T
V
b
y
i
n
v
ie
w
o
f
s
p
atial
co
n
s
tr
ai
n
s
a
m
o
n
g
t
h
e
o
b
j
ec
ts
th
r
o
u
g
h
th
e
b
en
ef
it
s
o
f
HOG
f
ea
t
u
r
e
ex
tr
ac
tio
n
.
C
o
n
v
er
s
e
l
y
,
[
1
0
]
ex
em
p
li
f
ie
s
ad
ap
tiv
e
f
u
s
i
o
n
ce
n
ter
ed
m
a
n
i
f
o
ld
f
ea
t
u
r
es
w
h
ile
co
m
p
ar
i
s
o
n
d
ef
i
n
e
t
h
at
t
h
e
f
u
s
io
n
ce
n
ter
ed
ap
p
r
o
ac
h
is
m
o
r
e
s
to
u
t
t
h
a
n
t
h
e
ar
ti
f
ac
t
r
u
le
an
d
p
r
ej
u
d
iced
s
u
m
r
u
le.
I
n
[
1
]
,
th
e
a
u
t
h
o
r
s
an
al
y
ze
d
th
e
i
r
w
o
r
k
an
d
th
e
y
u
tili
ze
s
a
s
tatic
ca
m
e
r
a
f
o
r
v
id
eo
an
d
th
e
m
ai
n
ed
g
e
o
f
f
r
a
m
e
co
n
s
id
er
ed
as
a
f
o
u
n
d
atio
n
o
u
tli
n
e.
A
t
th
at
p
o
i
n
t,
t
h
e
f
o
u
n
d
atio
n
w
as
r
ed
u
ce
d
f
r
o
m
t
h
e
c
u
r
r
en
t
ed
g
e
o
f
t
h
e
f
r
a
m
e.
Ho
w
e
v
er
,
t
h
o
s
e
p
ap
er
co
u
ld
n
o
t
clea
r
l
y
p
r
esen
t
ex
a
m
p
les
f
o
r
r
ea
d
er
’
s
co
m
p
r
eh
en
s
io
n
.
T
ab
le
1
lis
ted
a
s
u
m
m
ar
y
o
f
liter
at
u
r
e
r
ev
ie
w
s
th
at
ar
e
b
ein
g
u
s
ed
in
t
h
i
s
r
esear
ch
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
R
o
b
u
s
t V
is
io
n
-
b
a
s
ed
Mu
ltip
le
Mo
vin
g
Ob
ject
Dete
ctio
n
a
n
d
Tr
a
ck
in
g
fr
o
m
V
id
eo
…
(
K
a
z
i I
s
tia
q
u
e
A
h
med
)
819
T
ab
le
1
.
R
elate
d
L
iter
atu
r
es
R
ev
ie
w
S
u
m
m
ar
y
R
e
sea
r
c
h
T
i
t
l
e
A
p
p
r
o
a
c
h
S
t
r
e
n
g
t
h
s
M
u
l
t
i
p
l
e
O
b
j
e
c
t
T
r
a
c
k
i
n
g
u
si
n
g
K
a
l
man
F
i
l
t
e
r
a
n
d
O
p
t
i
c
a
l
F
l
o
w
[
2
]
S
i
mu
l
a
t
i
o
n
K
a
l
man
c
h
a
n
n
e
l
i
s
u
t
i
l
i
z
e
d
t
o
sc
a
l
e
t
h
e
c
o
n
d
i
t
i
o
n
o
f
a
n
o
b
j
e
c
t
l
o
c
a
t
i
o
n
.
A
n
o
p
t
i
c
a
l
f
l
o
w
c
a
n
i
d
e
n
t
i
f
y
t
h
e
s
p
e
e
d
s o
f
a
n
o
b
j
e
c
t
.
M
o
v
i
n
g
O
b
j
e
c
t
D
e
t
e
c
t
i
o
n
a
n
d
T
r
a
c
k
i
n
g
f
o
r
V
i
d
e
o
S
u
r
v
e
i
l
l
a
n
c
e
[
1
]
S
i
mu
l
a
t
i
o
n
I
t
u
t
i
l
i
z
e
s
a
st
a
t
i
c
c
a
me
r
a
f
o
r
v
i
d
e
o
a
n
d
t
h
e
mai
n
e
d
g
e
o
f
f
r
a
me
c
o
n
si
d
e
r
e
d
a
s
a
f
o
u
n
d
a
t
i
o
n
o
u
t
l
i
n
e
.
A
t
t
h
a
t
p
o
i
n
t
,
t
h
e
f
o
u
n
d
a
t
i
o
n
w
a
s re
d
u
c
e
d
f
r
o
m t
h
e
c
u
r
r
e
n
t
e
d
g
e
o
f
t
h
e
f
r
a
me
.
O
b
j
e
c
t
t
r
a
c
k
i
n
g
u
s
i
n
g
i
mp
r
o
v
e
d
C
a
m
sh
i
f
t
w
i
t
h
S
U
R
F
me
t
h
o
d
[
7
]
A
n
a
l
y
t
i
c
a
l
a
n
d
S
i
mu
l
a
t
i
o
n
S
U
R
F
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
a
n
d
i
m
p
r
o
v
e
d
C
a
msh
i
f
t
a
l
g
o
r
i
t
h
m
b
y
a
u
t
o
mat
i
c
a
l
l
y
a
d
j
u
s
t
i
n
g
t
h
e
i
l
l
u
mi
n
a
t
i
o
n
t
o
f
i
n
d
o
u
t
l
o
st
t
a
r
g
e
t
t
o
t
r
a
c
k
d
o
w
n
o
f
t
h
e
f
e
a
t
u
r
e
s o
f
t
h
e
o
b
j
e
c
t
T
r
a
f
f
i
c
S
i
g
n
R
e
c
o
g
n
i
t
i
o
n
U
si
n
g
S
U
R
F
:
S
p
e
e
d
e
d
U
p
R
o
b
u
st
F
e
a
t
u
r
e
D
e
scri
p
t
o
r
a
n
d
A
r
t
i
f
i
c
i
a
l
N
e
u
r
a
l
N
e
t
w
o
r
k
C
l
a
ssi
f
i
e
r
[
1
1
]
S
i
mu
l
a
t
i
o
n
H
i
g
h
r
a
t
e
a
c
c
u
r
a
c
y
t
o
r
e
c
o
g
n
i
z
e
,
c
o
l
o
r
-
b
a
se
d
se
g
me
n
t
a
t
i
o
n
a
l
o
n
g
w
i
t
h
t
h
e
mo
r
p
h
o
l
o
g
i
c
a
l
a
n
d
g
e
o
m
e
t
r
i
c
a
l
p
r
o
p
e
r
t
i
e
s
M
u
l
t
i
p
l
e
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
f
o
r
s
mart
T
V
sh
o
p
p
i
n
g
v
i
d
e
o
u
si
n
g
p
o
i
n
t
t
o
p
o
i
n
t
f
e
a
t
u
r
e
b
a
se
d
S
U
R
F
me
t
h
o
d
[
5
]
S
i
mu
l
a
t
i
o
n
S
u
c
c
e
ssf
u
l
l
y
si
mu
l
a
t
e
d
f
o
r
t
h
e
same
so
r
t
o
f
i
mag
e
o
b
j
e
c
t
s
w
h
i
c
h
a
l
so
t
a
k
e
n
i
n
t
o
c
o
n
s
i
d
e
r
a
t
i
o
n
o
f
m
u
l
t
i
p
l
e
si
t
u
a
t
i
o
n
s
i
.
e
.
i
f
t
h
e
i
m
a
g
e
o
b
j
e
c
t
sc
a
l
e
d
d
o
w
n
o
r
u
p
a
n
d
c
h
a
n
g
e
i
n
t
h
e
r
o
t
a
t
i
o
n
in
m
u
l
t
i
p
l
e
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
i
t
w
o
r
k
s fi
n
e
M
u
l
t
i
p
l
e
O
b
j
e
c
t
T
r
a
c
k
i
n
g
b
y
I
mp
r
o
v
e
d
K
L
T
T
r
a
c
k
e
r
O
v
e
r
S
U
R
F
F
e
a
t
u
r
e
s
[
6
]
A
n
a
l
y
t
i
c
a
l
a
n
d
S
i
mu
l
a
t
i
o
n
f
r
o
n
t
f
a
c
i
n
g
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
a
n
d
r
e
c
o
g
n
i
t
i
o
n
f
o
r
mu
l
t
i
p
l
e
o
b
j
e
c
t
s
2.
P
RO
P
O
SE
D
M
E
T
H
O
D
T
h
e
m
ai
n
o
b
j
ec
tiv
e
o
f
th
is
s
y
s
te
m
is
to
p
r
o
v
id
e
r
o
b
u
s
tn
e
s
s
an
d
ac
cu
r
ac
y
f
o
r
th
e
d
etec
tio
n
o
f
th
e
m
u
ltip
le
m
o
v
i
n
g
o
b
j
ec
ts
th
r
o
u
g
h
d
e
v
elo
p
in
g
an
a
lg
o
r
it
h
m
a
n
d
tr
ac
k
t
h
e
d
etec
ted
o
b
j
ec
t
f
ea
tu
r
es
i
n
t
h
e
v
id
eo
f
r
a
m
e
s
.
I
n
p
u
t
V
i
d
e
o
F
r
a
m
e
S
e
l
e
c
t
i
o
n
,
S
e
p
a
r
a
t
i
o
n
a
n
d
C
o
n
v
e
r
s
i
o
n
I
n
P
r
o
g
r
e
s
s
F
r
a
m
e
S
u
b
t
r
a
c
t
B
a
c
k
g
r
o
u
n
d
R
e
f
e
r
e
n
c
e
F
r
a
m
e
P
e
r
f
o
r
m
Mo
r
p
h
o
l
o
g
i
c
a
l
F
i
l
t
e
r
O
p
e
r
a
t
i
o
n
t
o
C
l
e
a
n
F
o
r
e
g
r
o
u
n
d
D
e
t
e
c
t
Mo
v
i
n
g
O
b
j
e
c
t
i
n
t
h
e
F
r
a
m
e
s
B
a
c
k
g
r
o
u
n
d
R
e
f
e
r
e
n
c
e
F
r
a
m
e
D
e
t
e
c
t
t
h
e
F
e
a
t
u
r
e
s
o
f
A
l
l
O
b
j
e
c
t
s
u
s
i
n
g
S
U
R
F
T
r
a
c
k
i
n
g
a
l
l
t
h
e
o
b
j
e
c
t
s
F
e
a
t
u
r
e
Fig
u
r
e
2
.
Ov
er
v
ie
w
o
f
th
e
P
r
o
ce
s
s
i
n
g
Step
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
10
,
No
.
2
,
Ma
y
2
0
1
8
:
8
1
7
–
8
2
6
820
i.
B
y
u
s
i
n
g
Stat
ic
ca
m
er
a
s
it
is
r
eq
u
ir
ed
to
tak
e
in
p
u
t
v
id
eo
f
o
r
p
r
o
ce
s
s
in
g
an
d
co
n
v
er
t
f
r
a
m
es
to
i
m
a
g
es
w
h
er
e
th
e
f
ir
s
t 2
5
f
r
a
m
es
w
ill b
e
tr
ea
ted
as th
e
B
ac
k
g
r
o
u
n
d
.
ii.
Af
ter
t
h
e
last
B
ac
k
g
r
o
u
n
d
tr
ain
in
g
f
r
a
m
e,
n
ex
t
f
r
a
m
e
is
tr
ea
ted
as
t
h
e
i
n
-
p
r
o
g
r
ess
f
r
a
m
e
a
n
d
ap
p
l
y
B
ac
k
g
r
o
u
n
d
s
u
b
tr
ac
tio
n
m
et
h
o
d
th
r
o
u
g
h
s
u
b
tr
ac
ti
n
g
b
ac
k
g
r
o
u
n
d
r
ef
er
en
ce
f
r
a
m
e.
iii.
I
t
m
a
y
co
n
tai
n
n
o
i
s
e
an
d
it
m
u
s
t
r
eq
u
ir
e
r
ed
u
ci
n
g
n
o
i
s
e.
T
o
r
ed
u
ce
n
o
is
e
an
d
to
r
ec
eiv
e
clea
r
f
o
r
eg
r
o
u
n
d
o
b
j
ec
ts
,
f
ilter
u
s
i
n
g
m
o
r
p
h
o
lo
g
ica
l f
il
ter
s
an
d
m
o
v
in
g
o
b
j
ec
ts
ar
e
d
etec
ted
.
iv
.
Fro
m
th
e
d
etec
ted
o
b
j
ec
ts
,
ex
tr
ac
t f
ea
tu
r
es e
ac
h
i
n
d
iv
id
u
al
b
y
u
s
in
g
SU
R
F.
v.
T
r
ac
k
th
e
d
etec
ted
f
ea
t
u
r
es
in
th
e
v
id
eo
b
y
t
h
e
k
-
NN
al
g
o
r
it
h
m
an
d
i
n
ea
c
h
f
r
a
m
e
tr
ac
k
i
n
g
s
tep
t
h
e
o
b
j
ec
t f
ea
tu
r
es
w
i
ll b
e
s
et
as t
h
e
o
ld
f
ea
tu
r
e.
3.
RE
S
E
ARCH
M
E
T
H
O
D
A
m
o
d
el
o
f
ap
p
ea
r
an
ce
,
m
o
d
el
o
f
lo
ca
tio
n
]
a
n
d
a
s
tr
ate
g
y
f
o
r
s
ea
r
ch
i
n
g
ar
e
th
e
t
h
r
ee
m
aj
o
r
co
m
p
o
n
e
n
t
s
i
n
an
y
tr
ac
k
in
g
s
y
s
te
m
.
Fo
r
th
e
p
r
o
p
o
s
ed
m
u
lt
ip
le
o
b
j
ec
t
d
etec
tio
n
an
d
tr
ac
k
in
g
w
e
g
e
n
er
alize
th
e
ap
p
ea
r
an
ce
m
o
d
el
u
s
in
g
f
o
r
th
e
d
etec
tio
n
u
s
i
n
g
b
ac
k
g
r
o
u
n
d
s
u
b
tr
ac
tio
n
m
et
h
o
d
w
h
ich
is
f
o
llo
w
ed
b
y
th
e
ex
tr
ac
tio
n
o
f
f
ea
t
u
r
es b
y
S
UR
F a
n
d
co
n
ti
n
u
o
u
s
tr
ac
k
in
g
b
y
t
h
e
KNN.
3
.
1
.
Sp
ee
d
-
Up R
o
b
us
t
F
ea
t
ures (
SURF
)
Scale
-
I
n
v
ar
ia
n
t
Featu
r
e
T
r
an
s
f
o
r
m
(
SIFT
)
is
a
n
e
f
f
ec
tiv
e
w
a
y
to
d
ea
l
w
i
th
h
i
g
h
li
g
h
t
id
en
ti
f
icat
io
n
p
r
esen
ted
b
y
[
1
2
]
.
T
h
e
SUR
F
-
ca
lc
u
latio
n
d
ep
en
d
s
o
n
s
im
ilar
s
ta
n
d
ar
d
s
an
d
s
tep
s
,
h
o
w
e
v
er
,
it
u
s
es
a
n
alter
n
ate
p
lan
an
d
it
o
u
g
h
t
to
g
iv
e
b
etter
o
u
tco
m
e
s
,
q
u
ic
k
e
r
.
W
ith
a
s
p
ec
if
ic
en
d
g
o
al
to
r
ec
o
g
n
ize
in
cl
u
d
e
f
o
cu
s
es
i
n
a
s
ca
le
-
i
n
v
ar
ia
n
t
w
a
y
,
SIFT
u
tili
ze
s
a
f
all
in
g
s
ep
ar
atin
g
ap
p
r
o
ac
h
w
h
er
ea
s
th
e
D
if
f
er
en
ce
o
f
Gau
s
s
ia
n
s
,
Do
G,
is
ascer
tai
n
e
d
o
n
co
n
tin
u
o
u
s
l
y
d
o
w
n
s
ca
led
p
ictu
r
es
[
1
3
]
.
3
.
2
.
K
ey
po
int
Det
ec
t
io
n Usin
g
SURF
Gen
er
all
y
,
t
h
e
m
eth
o
d
to
ac
co
m
p
lis
h
s
ca
le
i
n
v
ar
ian
ce
i
s
to
lo
o
k
at
th
e
p
ictu
r
e
at
v
ar
io
u
s
s
ca
les,
s
ca
le
s
p
ac
e,
u
tili
zi
n
g
Ga
u
s
s
ia
n
p
iece
s
.
B
o
th
SIFT
an
d
SUR
F
p
ar
titi
o
n
s
t
h
e
s
ca
le
s
p
ac
e
i
n
to
lev
els
an
d
o
ctav
es.
An
o
ctav
e
co
m
p
ar
es
to
a
m
u
l
tip
l
y
in
g
o
f
σ
,
an
d
th
e
o
ctav
e
is
p
ar
titi
o
n
ed
in
to
co
n
s
is
te
n
tl
y
d
is
p
er
s
ed
lev
els
as
s
h
o
w
n
in
F
ig
u
r
e
3
.
Fig
u
r
e
3
: o
ctav
es
w
it
h
3
lev
el
s
,
th
e
ar
ea
f
o
r
th
e
3
×3
×3
n
o
n
-
m
o
s
t e
x
tr
e
m
e
co
n
ce
al
m
e
n
t u
s
ed
to
id
en
ti
f
y
ele
m
e
n
ts
i
s
h
i
g
h
li
g
h
ted
f
r
o
m
[
1
3
]
.
Fig
u
r
e
4
: I
n
teg
r
al
i
m
a
g
es
f
o
r
A
r
ea
co
m
p
u
tatio
n
f
r
o
m
[
7
]
B
o
th
m
e
th
o
d
o
lo
g
ies
as
s
e
m
b
l
e
a
p
y
r
a
m
id
o
f
r
ea
ctio
n
m
ap
s
,
w
it
h
v
ar
io
u
s
lev
el
s
in
s
id
e
o
ctav
es.
A
r
ea
ctio
n
g
u
id
e
is
t
h
e
co
n
s
eq
u
e
n
ce
o
f
an
o
p
er
atio
n
o
n
th
e
p
ictu
r
e.
T
h
e
in
tr
ig
u
e
f
o
cu
s
e
s
ar
e
th
e
f
o
cu
s
es
t
h
at
ar
e
o
u
tr
ag
eo
u
s
a
m
o
n
g
8
n
ei
g
h
b
o
r
s
in
t
h
e
p
r
ese
n
t
le
v
el
a
n
d
its
2
×9
n
eig
h
b
o
r
s
in
t
h
e
le
v
el
b
en
e
ath
o
r
m
o
r
e.
T
h
is
is
a
n
o
n
-
g
r
ea
te
s
t
co
n
ce
al
m
e
n
t
in
a
3
×3
×3
n
eig
h
b
o
r
h
o
o
d
,
th
e
co
n
n
ec
tio
n
b
et
w
ee
n
le
v
els,
o
cta
v
es,
an
d
n
eig
h
b
o
r
h
o
o
d
is
o
u
tli
n
ed
in
Fi
g
u
r
e
4
o
n
to
p
o
f
th
i
s
s
e
g
m
e
n
t
[
1
3
]
.
SUR
F
i
s
d
escr
ib
ed
b
y
t
h
e
u
til
izatio
n
o
f
e
s
s
e
n
tial
p
ic
tu
r
es.
I
t
is
d
escr
ib
ed
,
th
e
co
u
n
ts
o
f
t
h
e
zo
n
e
o
f
an
u
p
r
ig
h
t
r
ec
tan
g
u
lar
d
is
tr
ic
t
ar
e
less
e
n
ed
to
f
o
u
r
o
p
er
atio
n
s
,
a
n
d
th
e
co
m
p
u
tatio
n
o
f
f
ir
s
t
-
r
eq
u
e
s
t
Haa
r
w
a
v
elet
r
ea
ctio
n
w
ill
b
e
s
i
x
o
p
er
atio
n
s
.
T
h
e
ce
n
tr
al
i
m
a
g
e
o
f
t
h
e
i
m
a
g
e
I
(
x
,
y
)
(
0
≤
x
≤
M,
0
≤
y
≤
N)
ca
n
b
e
w
e
ll
-
d
ef
in
ed
b
y
t
h
e
f
o
r
m
u
la
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
R
o
b
u
s
t V
is
io
n
-
b
a
s
ed
Mu
ltip
le
Mo
vin
g
Ob
ject
Dete
ctio
n
a
n
d
Tr
a
ck
in
g
fr
o
m
V
id
eo
…
(
K
a
z
i I
s
tia
q
u
e
A
h
med
)
821
(
)
=
∑
∑
(
,
)
≤
=
0
≤
=
0
(
1
)
I
n
[
1
4
]
d
is
p
lay
s
h
o
w
to
ac
h
iev
e
r
ec
k
less
p
i
x
el
in
ten
s
itie
s
,
w
h
ich
ca
n
b
e
co
n
s
id
er
ed
b
y
:
∑
(
)
=
[
∑
(
)
+
∑
(
)
]
−
[
∑
(
)
+
∑
(
)
]
(
2
)
Gau
s
s
ia
n
p
y
r
a
m
id
,
i.e
.
,
th
e
p
ictu
r
e
s
ca
le
s
p
ac
e
is
p
r
i
n
cip
all
y
u
s
ed
to
d
is
co
v
er
in
tr
i
g
u
e
f
o
cu
s
es
i
n
v
ar
io
u
s
s
ca
les.
Her
e,
Ga
u
s
s
ia
n
p
ar
ts
ca
n
b
e
ch
a
n
g
ed
in
s
iz
e
to
m
ak
e
t
h
e
Ga
u
s
s
ian
p
y
r
a
m
id
.
A
s
ta
k
i
n
g
a
f
ter
f
i
g
u
r
e
ap
p
ea
r
s
,
L
ap
lacia
n
o
f
G
au
s
s
ian
i
s
ap
p
r
o
x
i
m
ated
to
th
e
cr
ate
ch
an
n
el.
Fig
u
r
e
5
.
I
n
tr
ig
u
e
Fo
cu
s
o
f
L
a
p
lacia
n
o
f
Ga
u
s
s
ian
Fro
m
[
1
3
]
Utilizi
n
g
t
h
i
s
s
tr
ate
g
y
,
d
i
f
f
er
en
t
la
y
er
s
o
f
t
h
e
s
ca
le
-
s
p
ac
e
p
y
r
a
m
id
ca
n
b
e
h
a
n
d
led
all
th
e
w
h
ile
a
n
d
it
in
v
a
lid
ates
t
h
e
n
ee
d
to
s
u
b
s
a
m
p
l
e
th
e
p
ict
u
r
e,
ac
co
r
d
in
g
l
y
h
av
i
n
g
b
etter
ex
ec
u
t
io
n
.
T
o
f
ig
u
r
e
o
u
t
i
f
a
p
o
in
t
is
m
o
s
t e
x
tr
e
m
e,
t
h
e
d
eter
m
in
a
n
t
o
f
Hess
ian
i
s
u
tili
ze
d
at
t
h
e
i
n
tr
ig
u
e
p
u
r
p
o
s
es o
f
r
estrict
io
n
.
Ass
u
m
e
f
(
x
,
y
)
i
s
a
p
er
s
is
ten
t c
ap
ac
it
y
w
it
h
t
w
o
f
a
cto
r
s
,
th
en
t
h
e
Hes
s
ian
f
r
a
m
e
w
o
r
k
i
s
:
ℋ
(
f
(
x
,
y
)
)
=
[
2
2
2
2
2
2
]
(
3
)
an
d
th
e
d
eter
m
i
n
a
n
t
:
ℋ
(
f
(
x
,
y
)
)
=
de
t
ℋ
=
[
2
2
∗
2
2
]
−
[
2
∗
2
]
(
4
)
I
f
d
et
<0
,
w
h
ich
m
ea
n
s
t
h
e
E
ig
en
v
al
u
es
o
f
h
a
v
e
d
if
f
er
en
t
s
i
g
n
s
,
an
d
t
h
en
t
h
e
p
o
i
n
t
is
n
o
t
a
co
n
f
i
n
ed
m
a
x
i
m
u
m
.
Ot
h
er
w
is
e
it
is
a
m
a
x
i
m
u
m
an
d
f
r
o
m
[
1
0
]
,
R
ep
lacin
g
f
(
x
,
y
)
w
ith
I
(
x
,
y
)
,
th
e
Hess
ia
n
m
atr
i
x
o
f
th
e
i
m
a
g
e
is
:
ℋ
(
f
(
x
,
y
)
)
=
[
(
,
)
(
,
)
(
,
)
(
,
)
]
(
5
)
an
d
(
)
=
∑
∑
(
,
)
≤
=
0
≤
=
0
W
h
ile
th
e
v
al
u
e
o
f
(
,
)
=
(
)
∗
2
2
(
σ
)
an
d
(
,
)
=
(
)
∗
2
(
σ)
3
.
3
.
I
nte
re
s
t
po
int
Det
ec
t
io
n Usi
ng
SURF
SUR
F
i
n
tr
ig
u
e
p
o
in
t
d
escr
ip
to
r
ascer
tain
s
t
h
e
Haa
r
r
ea
ctio
n
s
in
b
o
th
X
a
n
d
Y
o
r
g
a
n
izes
i
n
th
e
cir
cle
lo
ca
le
f
o
cu
s
ed
at
in
tr
ig
u
e
f
o
cu
s
es
w
i
th
a
s
w
ee
p
o
f
6
σ
.
I
t
d
ep
en
d
s
o
n
t
h
e
p
r
ed
o
m
i
n
an
t
i
n
tr
o
d
u
ctio
n
s
o
f
all
th
e
in
tr
i
g
u
e
f
o
cu
s
e
s
.
T
h
e
s
p
an
o
f
Haa
r
w
av
ele
t
is
4
σ
,
an
d
th
e
to
tal
o
f
v
ec
to
r
s
is
co
m
p
u
ted
in
ea
ch
6
0
d
eg
r
ee
s
in
th
e
cir
cle.
A
t
lo
n
g
last
,
t
h
e
in
tr
o
d
u
ctio
n
w
it
h
th
e
b
ig
g
e
s
t
to
tal
o
f
v
ec
to
r
s
is
t
h
e
o
v
er
w
h
el
m
i
n
g
i
n
tr
o
d
u
ctio
n
.
T
h
e
p
r
o
ce
d
u
r
e
ap
p
ea
r
ed
in
th
e
ac
co
m
p
a
n
y
i
n
g
f
ig
u
r
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
10
,
No
.
2
,
Ma
y
2
0
1
8
:
8
1
7
–
8
2
6
822
Fig
u
r
e
6
.
A
s
s
i
g
n
m
e
n
t
f
o
r
Or
ien
tatio
n
Fro
m
[
7
]
Af
ter
t
h
e
a
s
s
u
r
an
ce
o
f
o
v
er
w
h
el
m
i
n
g
i
n
tr
o
d
u
ctio
n
,
[
1
3
]
d
esc
r
ib
es
a
s
q
u
ar
e
w
i
n
d
o
w
is
b
u
ilt
w
h
ic
h
is
f
o
cu
s
ed
at
ea
ch
i
n
tr
i
g
u
e
p
o
in
t
w
i
th
a
s
id
e
le
n
g
t
h
o
f
2
0
σ
.
A
t
th
at
p
o
in
t,
it
is
p
ar
titi
o
n
ed
in
to
4
×4
s
u
b
-
d
is
tr
ic
t
an
d
th
e
w
a
v
el
et
r
ea
ct
io
n
i
s
f
ig
u
r
ed
in
b
o
th
t
h
e
o
v
er
w
h
el
m
i
n
g
i
n
tr
o
d
u
ctio
n
a
n
d
th
e
in
tr
o
d
u
ctio
n
v
er
tica
l
to
it.
On
th
e
o
f
f
c
h
an
ce
t
h
at
w
e
ch
a
r
ac
ter
ize
th
e
w
a
v
elet
o
f
x
an
d
y
a
s
d
x
an
d
dy
,
th
e
n
th
er
e
w
i
ll
b
e
4
v
alu
es
Σ
d
x
,
Σ
d
y
,
Σ
|
d
x
|
,
Σ
|
d
y
|
,
a
n
d
ab
s
o
lu
t
el
y
it
w
ill
b
e
a
6
4
-
le
n
g
th
v
ec
to
r
f
o
r
ea
ch
i
n
tr
ig
u
e
p
o
in
t.
I
n
th
i
s
m
a
n
n
er
,
it
i
s
p
o
s
s
ib
le
to
ac
q
u
ir
e
th
e
d
escr
ip
to
r
s
eg
m
e
n
t b
y
n
o
r
m
aliz
in
g
it.
3
.
4
.
k
-
Nea
re
s
t
Neig
h
bo
r
(
k
-
NN)
Cla
s
s
if
ier
K
-
Nea
r
est
Nei
g
h
b
o
r
(
KNN
s
t
ar
tin
g
n
o
w
a
n
d
i
n
to
t
h
e
f
o
r
ese
ea
b
le
f
u
tu
r
e)
i
s
o
n
e
o
f
t
h
o
s
e
c
alcu
latio
n
s
th
at
ar
e
ex
ce
p
tio
n
al
l
y
ea
s
y
to
s
ee
h
o
w
ev
er
w
o
r
k
s
u
n
i
m
a
g
in
ab
ly
w
ell
p
r
ac
ticall
y
s
p
ea
k
i
n
g
.
A
d
d
itio
n
all
y
,
it
i
s
s
h
o
ck
in
g
l
y
ad
ap
tab
le
an
d
its
ap
p
licatio
n
s
r
u
n
f
r
o
m
v
is
io
n
t
o
p
r
o
tein
s
to
co
m
p
u
tatio
n
al
g
eo
m
e
tr
y
to
ch
ar
ts
et
ce
ter
a.
KNN
is
a
n
o
n
-
p
ar
a
m
et
r
ic
s
lu
g
g
i
s
h
lear
n
in
g
ca
lcu
la
ti
o
n
.
Au
th
o
r
s
i
n
[
1
5
]
ex
p
lain
ed
w
h
e
n
th
e
m
et
h
o
d
is
n
o
n
-
p
ar
a
m
etr
ic,
it
i
m
p
lie
s
t
h
at
it d
o
esn
'
t
m
a
k
e
an
y
s
u
p
p
o
s
iti
o
n
s
o
n
t
h
e
h
id
d
en
i
n
f
o
r
m
atio
n
ap
p
r
o
p
r
iatio
n
.
T
h
is
is
q
u
ite
v
al
u
ab
le,
as
in
t
h
i
s
p
r
esen
t
r
ea
lit
y
,
t
h
e
v
a
s
t
m
aj
o
r
ity
o
f
th
e
d
o
w
n
to
ea
r
th
in
f
o
r
m
at
io
n
d
o
es
n
o
t
r
eg
ar
d
th
e
o
r
d
in
ar
y
h
y
p
o
th
et
ical
s
u
s
p
icio
n
s
m
ad
e
(
e.
g
.
Gau
s
s
ia
n
b
len
d
s
,
d
ir
ec
tl
y
d
is
ti
n
ct
a
n
d
s
o
o
n
)
.
3
.
5
.
Ass
u
m
ptio
n
s
in t
he
K
NN
Cl
a
s
s
if
ier
KNN
ac
ce
p
t
t
h
at
t
h
e
i
n
f
o
r
m
a
tio
n
is
in
an
ele
m
en
t
s
p
ac
e.
A
ll
t
h
e
m
o
r
e
p
r
ec
is
el
y
,
t
h
e
i
n
f
o
r
m
atio
n
f
o
cu
s
es
ar
e
in
a
m
etr
ic
s
p
a
ce
.
T
h
e
in
f
o
r
m
at
io
n
ca
n
b
e
s
ca
lar
s
o
r
p
o
ten
tiall
y
ev
e
n
m
u
ltid
i
m
e
n
s
io
n
al
v
ec
to
r
s
[
1
6
]
Sin
ce
th
e
f
o
cu
s
es
ar
e
in
h
i
g
h
li
g
h
t
s
p
ac
e,
th
e
y
h
a
v
e
a
th
o
u
g
h
t
o
f
s
ep
ar
atio
n
–
T
h
is
n
ee
d
n
o
t
r
ea
ll
y
b
e
a
E
u
clid
ea
n
s
ep
ar
atio
n
in
s
p
ite
o
f
th
e
f
ac
t th
at
i
t is t
h
e
o
n
e
r
eg
u
lar
l
y
u
ti
lized
.
3
.
6
.
K
NN
f
o
r
Densi
t
y
E
s
t
i
m
a
t
io
n
I
n
s
p
ite
o
f
th
e
f
ac
t
th
a
t
o
r
d
e
r
r
em
ai
n
s
t
h
e
ess
e
n
tia
l
u
til
iz
atio
n
o
f
KNN,
w
e
ca
n
u
tili
z
e
it
to
d
o
th
ic
k
n
e
s
s
e
s
ti
m
atio
n
to
o
.
Si
n
c
e
KNN
is
n
o
n
-
p
ar
a
m
etr
ic,
it
c
an
d
o
esti
m
a
tio
n
f
o
r
d
is
cr
etio
n
ar
y
d
i
s
s
e
m
i
n
atio
n
s
.
T
h
e
th
o
u
g
h
t
is
f
u
n
d
a
m
e
n
tall
y
th
e
s
a
m
e
as
u
til
izatio
n
o
f
P
ar
ze
n
w
i
n
d
o
w
.
R
at
h
er
t
h
an
u
tili
z
in
g
h
y
p
er
cu
b
e
a
n
d
p
o
r
tio
n
ca
p
ac
ities
,
f
o
r
ev
alu
a
tin
g
th
e
t
h
ic
k
n
e
s
s
at
a
p
o
in
t
x
,
p
u
t
a
h
y
p
er
c
u
b
e
f
o
cu
s
ed
at
x
an
d
co
n
ti
n
u
e
ex
p
an
d
in
g
it
s
s
ize
til
l k
n
eig
h
b
o
r
s
ar
e
ca
u
g
h
t.
P
r
esen
t
l
y
ap
p
r
aise th
e
t
h
ic
k
n
e
s
s
u
tili
zi
n
g
th
e
eq
u
atio
n
,
(
)
=
(
6
)
an
d
(
)
=
∑
∑
(
,
)
≤
=
0
≤
=
0
W
h
er
e
n
is
th
e
a
g
g
r
eg
ate
n
u
m
b
er
o
f
V
i
s
th
e
v
o
l
u
m
e
o
f
t
h
e
h
y
p
er
cu
b
e.
See
t
h
at
t
h
e
n
u
m
er
ato
r
is
b
asicall
y
co
n
s
is
ten
t a
n
d
th
e
t
h
i
ck
n
e
s
s
i
s
af
f
ec
ted
b
y
t
h
e
v
o
l
u
m
e[
1
3
]
.
4.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
I
n
th
e
f
o
llo
w
i
n
g
o
u
tp
u
ts
,
t
h
e
r
esu
lt
s
o
f
th
e
s
i
m
u
latio
n
f
o
r
th
e
m
o
v
i
n
g
o
b
j
ec
t
d
etec
tio
n
h
as
b
ee
n
s
h
o
w
n
w
h
er
e
w
e
p
ar
ticu
lar
l
y
u
s
ed
a
s
till
ca
m
er
a
to
r
ec
o
r
d
v
id
eo
f
r
a
m
es.
I
n
th
e
f
o
llo
w
i
n
g
f
i
g
u
r
es,
it
i
s
s
h
o
w
n
B
ac
k
g
r
o
u
n
d
R
e
f
er
en
ce
Fra
m
e
(
Fig
u
r
e
7
)
.
Fro
m
t
h
e
i
n
-
p
r
o
g
r
ess
f
r
a
m
e,
t
h
e
b
ac
k
g
r
o
u
n
d
i
m
ag
e
s
u
b
tr
ac
ted
to
d
etec
t
f
o
r
eg
r
o
u
n
d
m
u
ltip
le
o
b
j
ec
ts
(
Fig
u
r
e
8
)
w
h
ich
i
n
d
icat
e
th
e
d
if
f
er
en
ce
b
et
w
ee
n
t
h
e
i
n
-
p
r
o
g
r
es
s
o
r
ig
in
al
f
r
a
m
e
a
n
d
th
e
r
ef
er
e
n
ce
b
ac
k
g
r
o
u
n
d
f
r
a
m
e.
T
h
e
n
ex
t
i
m
a
g
e
(
Fig
u
r
e
9
)
in
d
icate
s
t
h
e
m
o
r
p
h
o
lo
g
icall
y
f
il
ter
ed
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
R
o
b
u
s
t V
is
io
n
-
b
a
s
ed
Mu
ltip
le
Mo
vin
g
Ob
ject
Dete
ctio
n
a
n
d
Tr
a
ck
in
g
fr
o
m
V
id
eo
…
(
K
a
z
i I
s
tia
q
u
e
A
h
med
)
823
f
r
a
m
e
o
f
t
h
at
r
esp
ec
tiv
e
f
o
r
eg
r
o
u
n
d
f
r
a
m
e
f
o
r
a
clea
r
f
o
r
eg
r
o
u
n
d
an
d
w
h
ic
h
is
f
o
llo
w
ed
b
y
t
h
e
d
etec
tio
n
o
f
o
b
j
ec
ts
.
T
h
e
d
etec
ted
o
b
j
ec
ts
ar
e
s
e
g
m
e
n
ted
a
n
d
g
ath
er
th
e
f
ea
t
u
r
es
f
o
r
s
tr
o
n
g
e
s
t
p
o
in
t
s
u
s
i
n
g
SU
R
F.
B
y
co
n
tin
u
o
u
s
l
y
tr
ac
k
i
n
g
t
h
e
d
ete
cted
f
ea
tu
r
e
s
i
n
th
e
v
id
eo
b
y
t
h
e
k
-
N
N
alg
o
r
it
h
m
,
in
ea
ch
s
t
ep
,
th
e
n
e
w
o
b
j
ec
t
f
ea
t
u
r
es
w
ill b
e
s
et
as t
h
e
o
ld
f
ea
tu
r
e
in
F
ig
u
r
e
1
0
-
15.
Fig
u
r
e
1
.
R
ef
er
en
ce
B
ac
k
g
r
o
u
n
d
[
1
3
]
Fig
u
r
e
2
.
Fo
r
eg
r
o
u
n
d
Fra
m
e
a
f
ter
S
u
b
tr
ac
tio
n
f
r
o
m
Fi
g
u
r
e
7
(
Ma
y
C
o
n
tai
n
No
is
e)
Fig
u
r
e
3
.
Sid
e
b
y
Sid
e
U
n
clea
r
an
d
C
lear
i
m
a
g
e
(
af
ter
ap
p
ly
in
g
Mo
r
p
h
o
lo
g
ical
Fil
ter
)
Fig
u
r
e
4
.
A
Mo
v
i
n
g
Ob
j
ec
t
w
i
th
Stro
n
g
es
t Fea
tu
r
e
P
o
in
ts
o
f
th
e
Ob
j
ec
t (
u
s
i
n
g
SU
R
F)
Fig
u
r
e
5
.
Stro
n
g
es
t Fea
t
u
r
e
P
o
in
ts
f
r
o
m
Fra
m
e
9
4
(
u
s
i
n
g
SUR
F).
Fig
u
r
e
6
.
Dete
cted
Ob
j
ec
t Fea
tu
r
e
Ma
tch
i
n
g
in
Fra
m
e
9
4
(
u
s
i
n
g
S
UR
F)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
10
,
No
.
2
,
Ma
y
2
0
1
8
:
8
1
7
–
8
2
6
824
Fig
u
r
e
7
.
Dete
cted
Ob
j
ec
t
o
n
Fra
m
e
94
Fig
u
r
e
8
.
A
ll
Dete
c
ted
Ob
j
ec
ts
in
th
e
Fra
m
e
94
Fig
u
r
e
9
5
: A
f
ter
T
r
ac
k
in
g
u
n
ti
l
Fra
m
e
N
u
m
b
er
134
5.
CO
NCLU
SI
O
N
W
ith
t
h
e
m
u
lt
ip
le
o
cc
u
r
r
en
ce
s
,
th
e
m
ax
i
m
u
m
m
u
l
tip
le
o
b
j
ec
t
d
etec
tio
n
w
o
r
k
s
f
o
r
t
h
e
s
a
m
e
t
y
p
es
o
f
o
b
j
ec
ts
.
Ho
w
e
v
er
,
f
o
r
th
e
m
u
ltip
le
o
b
j
ec
t
d
etec
tio
n
an
d
t
r
ac
k
in
g
i
n
m
u
ltip
le
v
id
eo
f
il
es,
it
is
d
e
f
i
n
itel
y
r
eq
u
ir
ed
to
d
etec
t
d
if
f
er
en
t
t
y
p
es
o
f
o
b
j
ec
t
in
t
h
e
s
a
m
e
o
r
t
h
e
d
if
f
er
en
t
v
id
eo
f
iles
.
T
h
e
o
b
j
ec
tiv
e
o
f
t
h
i
s
w
o
r
k
to
d
etec
t
m
u
ltip
le
o
b
j
ec
t
w
it
h
s
a
m
e
o
r
d
if
f
er
en
t
t
y
p
e
s
i
n
t
h
e
s
a
m
e
o
r
d
if
f
er
en
t
v
id
eo
f
ile
s
o
n
e
b
y
o
n
e
u
s
i
n
g
p
o
in
t
u
s
i
n
g
f
ea
tu
r
e
p
o
i
n
t
to
f
ea
tu
r
e
p
o
in
t
m
a
tch
i
n
g
.
O
n
e
o
f
t
h
e
e
x
tr
e
m
e
p
l
u
s
p
o
i
n
t
f
o
r
u
s
i
n
g
t
h
is
p
r
o
p
o
s
ed
tactic
th
at
it c
a
n
d
etec
t th
e
o
b
j
ec
ts
n
o
t
w
it
h
s
tan
d
i
n
g
a
s
ca
le
al
ter
atio
n
o
r
in
-
p
la
n
e
v
ar
iatio
n
.
ACK
NO
WL
E
D
G
E
M
E
NT
T
h
is
w
o
r
k
w
as
s
u
p
p
o
r
ted
b
y
R
esear
ch
I
n
f
o
r
m
a
tio
n
Gr
an
t
Sch
e
m
e
2
0
1
6
f
r
o
m
I
n
ter
n
atio
n
al
I
s
la
m
i
c
Un
i
v
er
s
it
y
Ma
la
y
s
ia.
T
h
e
au
t
h
o
r
s
w
o
u
ld
li
k
e
to
th
a
n
k
E
le
ctr
ical
an
d
C
o
m
p
u
ter
E
n
g
i
n
e
er
in
g
D
ep
ar
t
m
en
t,
K
u
lli
y
y
ah
o
f
E
n
g
in
ee
r
i
n
g
f
o
r
s
u
p
p
o
r
tin
g
t
h
e
r
esear
ch
.
RE
F
E
R
E
NC
E
S
[
1
]
M.
J
.
J
.
J
a
d
h
av
,
“
Mo
v
i
n
g
Ob
j
ec
t
Dete
ctio
n
an
d
T
r
ac
k
in
g
f
o
r
Vid
eo
Su
r
v
el
lian
ce
,
”
I
n
t.
J.
E
n
g
.
R
es.
Gen
.
S
ci.
,
v
o
l.
2
,
n
o
.
4
,
p
p
.
3
7
2
–
3
7
8
,
2
0
1
4
.
[
2
]
S.
Sh
a
n
tai
y
a,
K.
Ver
m
a,
a
n
d
K.
Me
h
ta
,
“
Mu
ltip
le
Ob
j
ec
t
T
r
ac
k
in
g
u
s
in
g
Ka
l
m
a
n
Fil
t
er
an
d
Op
tical
Flo
w
,
”
E
u
r
.
J.
A
d
v.
E
n
g
.
Tech
n
o
l.
,
v
o
l.
2
,
n
o
.
2
,
p
p
.
3
4
–
3
9
,
2
0
1
5
.
[
3
]
J
.
Z
h
a
n
g
,
S.
Xu
,
K.
Hu
a
n
g
,
an
d
T
.
L
u
o
,
“Ac
cu
r
ate
Mo
v
i
n
g
T
ar
g
et
Dete
ct
io
n
B
ased
o
n
B
ac
k
g
r
o
u
n
d
Su
b
tr
ac
tio
n
a
n
d
SUS
A
N,
”
I
n
t.
J.
C
o
mp
u
t.
E
lectr.
E
n
g
.
,
v
o
l.
4
,
n
o
.
4
,
p
p
.
4
3
6
–
4
3
9
,
2
0
1
2
.
[
4
]
S.
J
o
s
h
i,
S.
Gu
j
ar
ath
i,
a
n
d
A
.
Mir
g
e,
“
M
o
v
in
g
Ob
j
ec
t
T
r
ac
k
in
g
Me
th
o
d
u
s
i
n
g
I
m
p
r
o
v
ed
C
a
m
s
h
if
t
w
it
h
Su
r
f
A
lg
o
r
it
h
m
,
''
I
n
t.
J.
A
d
v.
S
ci.
E
n
g
.
Tech
n
o
l.
,
v
o
l.
2
,
n
o
.
2
,
p
p
.
1
4
–
1
8
,
2
0
1
4
.
[
5
]
D.
C
h
h
ab
r
a
an
d
A
.
Ver
m
a,
“
Mu
ltip
le
o
b
ject
d
etec
tio
n
fo
r
s
ma
r
t
TV
s
h
o
p
p
in
g
vid
e
o
u
s
in
g
p
o
in
t
to
p
o
in
t
fea
tu
r
e
b
a
s
ed
S
UR
F
meth
o
d
,
”
2
0
1
6
I
n
t.
C
o
n
f
.
I
n
v
e
n
.
C
o
m
p
u
t.
T
ec
h
n
o
l.
(
I
C
I
C
T
)
,
C
o
im
b
ato
r
e
,
p
p
.
1
–
6
,
2016.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
R
o
b
u
s
t V
is
io
n
-
b
a
s
ed
Mu
ltip
le
Mo
vin
g
Ob
ject
Dete
ctio
n
a
n
d
Tr
a
ck
in
g
fr
o
m
V
id
eo
…
(
K
a
z
i I
s
tia
q
u
e
A
h
med
)
825
[
6
]
V.
B
u
d
d
u
b
ar
ik
i,
“
M
u
ltip
le
Ob
j
ec
t
T
r
ac
k
in
g
b
y
I
m
p
r
o
v
ed
K
L
T
T
r
ac
k
er
Ov
er
SUR
F Fea
t
u
r
es,”
2
0
1
5
.
[
7
]
J
.
L
i,
J
.
Z
h
a
n
g
,
Z
.
Z
h
o
u
,
W
.
Gu
o
,
B
.
W
an
g
,
a
n
d
Q.
Z
h
ao
,
“Ob
ject
tr
a
ck
in
g
u
s
in
g
imp
r
o
ve
d
C
a
msh
ift
w
ith
S
UR
F
meth
o
d
,
”
I
n
ter
n
a
tio
n
al
W
o
r
k
s
h
o
p
o
n
Op
en
-
S
o
u
r
ce
So
f
t
w
ar
e
f
o
r
Scien
t
if
i
c
C
o
m
p
u
tatio
n
(
OSSC
)
,
2
0
1
1
,
p
p
.
1
3
6
-
141.
[
8
]
W
.
So
n
g
,
“Real
-
ti
m
e
Mo
v
in
g
Ob
j
ec
t
T
r
ac
k
in
g
S
y
s
te
m
U
s
in
g
C
a
m
-
s
h
i
f
t
A
lg
o
r
it
h
m
,
”
TELK
O
MN
I
K
A
I
n
d
o
n
es.
J.
E
lectr.
E
n
g
,
v
o
l.
1
1
,
n
o
.
1
1
,
p
p
.
6
6
1
1
–
6
6
1
7
,
2
0
1
3
.
[
9
]
F.
T
en
g
an
d
Q.
L
iu
,
“
R
o
b
u
s
t
Mu
ltip
le
Sh
ip
T
r
ac
k
in
g
in
I
n
la
n
d
W
ater
w
a
y
C
C
T
V
Sy
s
te
m
,
”
TELK
O
MN
I
K
A
I
n
d
o
n
es.
J.
E
l
ec
tr
.
E
n
g
.
,
v
o
l.
1
2
,
n
o
.
1
1
,
p
p
.
7
7
7
2
–
7
7
7
7
,
2
0
1
4
.
[
1
0
]
J
.
C
ao
,
L
.
Gu
o
,
J
.
W
an
g
,
a
n
d
D.
W
u
,
“
Ob
j
ec
t
T
r
ac
k
in
g
M
eth
o
d
B
ased
o
n
a
Ne
w
M
u
lti
-
Featu
r
e
F
u
s
io
n
Stra
teg
y
,”
I
n
d
o
n
esia
n
Jo
u
r
n
a
l
o
f
E
lectrica
l
E
n
g
in
ee
r
in
g
a
n
d
C
o
mp
u
ter
S
cien
ce
(
I
JE
E
C
S
)
,
v
o
l.
1
2
,
n
o
.
9
,
p
p
.
6
8
1
1
–
6
8
1
8
,
2
0
1
4
.
[
1
1
]
M.
Z
.
A
b
ed
in
,
P
.
Dh
ar
a
n
d
K.
Deb
,
“T
r
a
ffic S
ig
n
R
ec
o
g
n
itio
n
Usi
n
g
S
UR
F
:
S
p
ee
d
ed
Up
R
o
b
u
s
t F
ea
tu
r
e
Descri
p
to
r
a
n
d
A
r
tifi
cia
l
N
eu
r
a
l
N
etw
o
r
k
C
la
s
s
ifie
r
,
”
I
n
ter
n
at
io
n
al
C
o
n
f
er
e
n
ce
o
n
E
lectr
ical
an
d
C
o
m
p
u
ter
E
n
g
in
ee
r
i
n
g
(
I
C
E
C
E
)
,
p
p
.
1
9
8
–
2
0
1
,
2
0
1
6
.
[
1
2
]
D.
G.
L
o
w
e,
“
Di
s
ti
n
cti
v
e
i
m
a
g
e
f
ea
t
u
r
es
f
r
o
m
s
ca
le
i
n
v
ar
ia
n
t
k
e
y
p
o
i
n
ts
,
”
I
n
t.
J.
C
o
mp
u
t.
V
is
.
,
v
o
l.
6
0
,
p
p
.
9
1
–
1
1
0
2
0
0
4
2
,
2
0
0
4
.
[
1
3
]
J
.
T
.
P
ed
e
r
s
en
,
“St
u
d
y
g
r
o
u
p
SUR
F
:
Feat
u
r
e
d
etec
tio
n
&
d
escr
ip
tio
n
,
”
A
ar
h
u
s
Un
iv
er
s
ite
t:
A
ar
h
u
s
,
Den
m
ar
k
,
p
p
.
1
–
1
2
,
2
0
1
1
.
[
1
4
]
S.
E
m
ar
o
s
e
an
d
B
.
P
in
n
a
m
a
n
e
n
i
,
“
Face
R
ec
o
g
n
itio
n
an
d
P
er
s
o
n
L
o
ca
lizatio
n
u
s
i
n
g
S
UR
F
f
o
r
A
u
to
m
ated
A
tte
n
d
an
ce
S
y
s
te
m
,
”
I
n
tern
a
tio
n
a
l J
o
u
r
n
a
l o
f Co
mp
u
ter A
p
p
lica
tio
n
s
, N
o.
8,
Octo
b
er
,
2
0
1
4
.
[
1
5
]
R
.
Mu
r
alid
h
ar
a
n
,
“
Ob
j
e
ct
R
ec
o
g
n
itio
n
Usi
n
g
K
-
Nea
r
est
Nei
g
h
b
o
r
Su
p
p
o
r
ted
B
y
E
i
g
en
Va
lu
e
Ge
n
er
ated
Fro
m
th
e
Featu
r
e
s
o
f
a
n
I
m
ag
e,
”
I
n
tern
a
tio
n
a
l
Jo
u
r
n
a
l
o
f
I
n
n
o
v
a
tive
R
esea
r
ch
in
C
o
mp
u
ter
a
n
d
C
o
mmu
n
ica
tio
n
E
n
g
i
n
ee
r
in
g
,
Vo
l.
2
(
8
)
,
p
p
.
5
5
2
1
–
5
5
2
8
,
2
0
1
4
.
[
1
6
]
R
.
Mu
r
alid
h
ar
a
n
an
d
C
.
C
h
an
d
r
asek
ar
,
“Ob
j
ec
t
r
ec
o
g
n
itio
n
u
s
i
n
g
SVM
-
KNN
b
ased
o
n
g
eo
m
etr
ic
m
o
m
e
n
t i
n
v
ar
ia
n
t,”
I
n
t.
J.
C
o
mp
u
t.
Tr
en
d
s
Tech
n
o
l.
,
v
o
l.
1
,
n
o
.
3
,
p
p
.
2
1
5
–
2
2
0
,
2
0
1
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
10
,
No
.
2
,
Ma
y
2
0
1
8
:
8
1
7
–
8
2
6
826
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Oth
m
a
n
O
m
r
a
n
Kh
a
li
f
a
r
e
c
e
i
v
e
d
h
is
Ba
c
h
e
lo
r’s
d
e
g
re
e
in
El
e
c
tro
n
ic
En
g
in
e
e
rin
g
f
ro
m
th
e
G
a
r
y
o
u
n
is
Un
iv
e
rsit
y
,
L
ib
y
a
in
1
9
8
6
.
He
o
b
tai
n
e
d
h
is
M
a
ste
r
d
e
g
re
e
in
El
e
c
tro
n
ics
S
c
ien
c
e
En
g
in
e
e
rin
g
a
n
d
P
h
D
i
n
Dig
it
a
l
Im
a
g
e
P
ro
c
e
ss
in
g
f
ro
m
Ne
wc
a
stle
Un
iv
e
rsit
y
,
UK
in
1
9
9
6
a
n
d
2
0
0
0
re
sp
e
c
ti
v
e
l
y
.
He
w
o
rk
e
d
i
n
in
d
u
strial
f
o
r
e
ig
h
t
y
e
a
rs
a
n
d
h
e
is
c
u
rre
n
tl
y
a
P
ro
f
e
ss
o
r
a
t
El
e
c
tri
c
a
l
a
n
d
Co
m
p
u
ter
En
g
in
e
e
rin
g
De
p
a
rtme
n
t,
In
tern
a
ti
o
n
a
l
Isla
m
ic
Un
iv
e
rsit
y
M
a
la
y
sia
.
His
a
re
a
o
f
re
se
a
r
c
h
in
tere
st
is
C
o
m
m
u
n
ica
ti
o
n
S
y
ste
m
s,
In
f
o
r
m
a
t
io
n
t
h
e
o
ry
a
n
d
C
o
d
in
g
,
Dig
it
a
l
im
a
g
e
/
v
id
e
o
p
ro
c
e
ss
in
g
,
c
o
d
i
n
g
a
n
d
Co
m
p
re
ss
io
n
,
W
a
v
e
lets,
F
ra
c
tal
a
n
d
P
a
tt
e
r
n
Re
c
o
g
n
it
io
n
.
He
p
u
b
li
s
h
e
d
m
o
re
th
a
n
4
5
0
p
a
p
e
rs
in
i
n
tern
a
ti
o
n
a
l
j
o
u
r
n
a
ls
a
n
d
Co
n
f
e
re
n
c
e
s.
He
is
S
IEE
E
m
e
m
b
e
r,
IEE
E
c
o
m
p
u
ter,
Im
a
g
e
p
ro
c
e
ss
in
g
a
n
d
C
o
m
m
u
n
ica
ti
o
n
S
o
c
iety
m
e
m
b
e
r.
No
r
u
n
Abd
u
l
M
a
le
k
o
b
tain
e
d
h
e
r
P
h
D
d
e
g
re
e
f
ro
m
S
c
h
o
o
l
o
f
El
e
c
tro
n
ic,
El
e
c
tri
c
a
l
a
n
d
S
y
st
e
m
s
En
g
in
e
e
rin
g
,
L
o
u
g
h
b
o
r
o
u
g
h
Un
iv
e
rsity
,
UK
in
2
0
1
3
.
S
h
e
h
a
s
b
e
e
n
a
p
p
o
in
ted
a
s
a
n
A
s
sista
n
t
P
ro
f
e
ss
o
r
in
E
lec
tri
c
a
l
a
n
d
C
o
m
p
u
ter
En
g
i
n
e
e
rin
g
De
p
a
rtme
n
t,
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
,
In
tern
a
ti
o
n
a
l
Isla
m
ic
Un
iv
e
rsit
y
M
a
la
y
sia
(IIUM
).
He
r
re
s
e
a
rc
h
i
n
tere
st
in
c
lu
d
e
s
to
a
n
ten
n
a
a
n
d
p
ro
p
a
g
a
ti
o
n
,
sig
n
a
l
p
ro
c
e
ss
in
g
p
a
rti
c
u
larly
o
f
a
n
ten
n
a
a
rra
y
s,
a
l
g
o
rit
h
m
s
a
n
d
w
irele
s
s
c
o
m
m
u
n
ica
ti
o
n
sy
ste
m
s.
S
h
e
is
a
n
a
c
ti
v
e
m
e
m
b
e
r
o
f
th
e
IEE
E,
a
r
e
g
istere
d
m
e
m
b
e
r
o
f
th
e
Bo
a
rd
o
f
En
g
in
e
e
rs M
a
la
y
sia
(BEM
)
a
n
d
In
sti
tu
te
o
f
En
g
in
e
e
rs M
a
lay
sia
(IE
M
).
K
a
z
i
Is
tia
q
u
e
A
h
m
e
d
p
u
rsu
in
g
h
is
M
a
ste
r
d
e
g
re
e
f
ro
m
El
e
c
tri
c
a
l
a
n
d
C
o
m
p
u
ter
En
g
in
e
e
ri
n
g
,
Ku
ll
iy
a
h
o
f
En
g
in
e
e
rin
g
,
In
tern
a
ti
o
n
a
l
Isla
m
ic
Un
iv
e
rsit
y
M
a
la
y
s
ia,
M
a
lay
sia
.
He
o
b
tain
e
d
h
is
Ba
c
h
e
lo
r
o
f
S
c
ien
c
e
En
g
i
n
e
e
rin
g
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
f
ro
m
Ba
n
g
lad
e
sh
Un
iv
e
rsit
y
o
f
Bu
sin
e
ss
a
n
d
T
e
c
h
n
o
lo
g
y
,
Ba
n
g
lad
e
sh
.
He
w
o
rk
e
d
f
o
r
th
e
in
d
u
stry
m
o
re
th
a
n
th
re
e
y
e
a
rs.
His
re
s
e
a
rc
h
in
tere
st
a
re
a
in
im
a
g
e
p
ro
c
e
ss
in
g
,
Bio
m
e
d
ica
l
Im
a
g
e
p
ro
c
e
ss
in
g
,
Da
ta
M
in
i
n
g
,
Ne
tw
o
rk
in
g
,
In
f
o
rm
a
ti
o
n
th
e
o
ry
a
n
d
Co
d
i
n
g
,
Dig
it
a
l
ima
g
e
/
v
id
e
o
p
ro
c
e
ss
in
g
a
n
d
P
a
tt
e
r
n
Re
c
o
g
n
it
i
o
n
.
Fa
r
a
h
Diy
a
n
a
A
b
d
u
l
R
a
h
m
a
n
o
b
tain
e
d
h
e
r
P
h
D
d
e
g
re
e
f
ro
m
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ic
En
g
i
n
e
e
rin
g
,
Un
iv
e
rsity
o
f
Bristo
l,
UK
in
2
0
1
5
.
S
h
e
h
a
s
b
e
e
n
a
p
p
o
in
ted
a
s
a
n
A
s
sista
n
t
P
ro
f
e
ss
o
r
in
E
lec
tri
c
a
l
a
n
d
C
o
m
p
u
ter
En
g
i
n
e
e
rin
g
De
p
a
rtme
n
t,
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
,
In
tern
a
ti
o
n
a
l
Isla
m
ic
Un
iv
e
rsit
y
M
a
la
y
sia
(IIUM
).
He
r
r
e
se
a
rc
h
in
tere
st
in
c
lu
d
e
s
im
a
g
e
a
n
d
v
id
e
o
p
ro
c
e
ss
in
g
,
v
id
e
o
q
u
a
li
ty
e
v
a
lu
a
ti
o
n
,
m
u
lt
ime
d
ia
tran
sm
issio
n
a
n
d
w
irele
ss
c
o
m
m
u
n
ica
ti
o
n
sy
ste
m
s.
S
h
e
is
a
n
a
c
ti
v
e
m
e
m
b
e
r
o
f
th
e
IEE
E,
a
r
e
g
istere
d
m
e
m
b
e
r
o
f
th
e
Bo
a
rd
o
f
En
g
in
e
e
rs M
a
la
y
sia
(
BEM
)
a
n
d
In
sti
tu
te
o
f
En
g
in
e
e
rs M
a
lay
sia
(IE
M
).
Evaluation Warning : The document was created with Spire.PDF for Python.