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.
9
,
No
.
3
,
Ma
r
ch
2
0
1
8
,
p
p
.
577
~
582
I
SS
N:
2502
-
4752
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ee
cs
.
v
9
.
i
3
.
p
p
5
7
7
-
582
577
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
M
ulti
-
co
lo
r Jo
int
Proba
bility Stat
istics M
o
del
-
ba
sed
O
bje
ct
Tra
ck
ing
Sy
ste
m
P
.
P
a
la
nicha
m
y
De
p
a
rtme
n
t
o
f
M
a
th
e
m
a
ti
c
s,
A
M
ET
Un
iv
e
rsit
y
,
Ch
e
n
n
a
i
,
I
n
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
No
v
21
,
2
0
1
7
R
ev
i
s
ed
J
an
2
9
,
2
0
1
8
A
cc
ep
ted
Feb
1
7
,
2
0
1
8
F
o
r
c
o
n
ti
n
u
o
u
s
targ
e
t
f
o
ll
o
w
in
g
u
n
d
e
r
c
o
m
p
lex
sc
e
n
e
,
a
n
o
b
jec
ti
v
e
f
o
ll
o
w
in
g
c
a
lcu
latio
n
in
li
g
h
t
o
f
m
u
lt
i
-
sh
a
d
i
n
g
jo
i
n
t
l
ik
e
li
h
o
o
d
in
v
e
stig
a
ti
o
n
m
o
d
e
l
wa
s
in
tro
d
u
c
e
d
.
T
h
e
c
a
lcu
latio
n
e
m
b
ra
c
e
d
sh
a
d
in
g
h
ist
o
g
ra
m
to
sp
e
a
k
to
th
e
a
c
tu
a
l
fa
c
tu
a
l
trad
e
m
a
r
k
w
it
h
Ca
m
sh
a
f
t
sta
n
d
a
rd
a
n
d
c
o
m
p
lete
d
e
x
p
lo
ra
to
ry
re
se
a
rc
h
in
su
c
h
a
n
g
les
a
s
m
u
lt
ich
a
n
n
e
l
j
o
in
t
s
h
a
d
in
g
h
ig
h
li
g
h
ts
m
e
a
su
re
m
e
n
ts,
p
ro
jec
ti
o
n
d
e
li
n
e
a
te
we
ig
h
ted
p
re
p
a
rin
g
,
th
e
f
o
ll
o
w
in
g
w
in
d
o
w
siz
e
a
n
d
p
o
siti
o
n
a
sc
e
rtain
in
g
,
c
a
lcu
latio
n
h
a
n
d
li
n
g
c
o
m
p
o
n
e
n
t
o
f
c
o
u
rs
e
.
It
u
t
il
ise
d
re
d
,
g
re
e
n
,
b
l
u
e
,
ti
n
t,
l
u
m
in
a
n
c
e
c
h
a
n
n
e
l
sh
a
d
in
g
a
s
th
e
o
b
jec
ti
v
e
w
a
tch
e
d
a
tt
rib
u
tes
,
a
n
d
p
lan
n
e
d
t
h
e
c
o
m
p
u
tatio
n
tec
h
n
i
q
u
e
g
iv
e
n
th
e
li
k
e
li
h
o
o
d
m
e
a
su
re
m
e
n
t
to
re
c
o
g
n
ise
a
n
y
sh
a
d
in
g
f
o
c
u
s
f
ro
m
th
e
c
o
m
p
o
u
n
d
sc
e
n
e
.
It
li
k
e
w
ise
s
e
tt
led
th
e
c
o
u
n
ti
n
g
m
e
th
o
d
f
o
r
f
o
ll
o
w
in
g
w
in
d
o
w
siz
e
a
n
d
p
o
siti
o
n
w
h
ich
a
d
ju
ste
d
th
e
m
u
lt
i
-
sh
a
d
i
n
g
m
o
d
e
l.
Util
izin
g
w
e
i
g
h
ti
n
g
p
ro
jec
ti
o
n
o
u
tl
i
n
e
stra
teg
y
,
th
e
f
o
u
n
d
a
ti
o
n
o
b
stru
c
ti
o
n
a
ro
u
n
d
t
h
e
o
b
jec
ti
v
e
p
o
te
n
ti
a
l
territ
o
ry
w
a
s
d
isp
e
n
se
d
w
it
h
.
F
i
n
a
ll
y
,
m
o
re
re
a
so
n
a
b
le
jo
in
i
n
g
ju
d
g
m
e
n
t
a
n
d
t
h
e
c
a
lcu
latio
n
c
y
c
l
e
ten
e
ts
w
e
re
a
d
v
a
n
c
e
d
.
Af
ter
th
e
tes
t
a
c
c
re
d
it
a
ti
o
n
,
t
h
e
o
n
g
o
in
g
e
x
e
c
u
ti
o
n
a
n
d
re
c
o
g
n
it
i
o
n
p
ro
p
o
rti
o
n
in
tro
d
u
c
e
a
d
e
c
e
n
t
o
u
tco
m
e
.
K
ey
w
o
r
d
s
:
Ca
m
sh
a
f
t
M
u
lt
i
-
c
o
lo
u
r
m
o
d
e
l
P
r
o
b
a
b
il
it
y
sta
ti
stics
T
a
r
g
e
t
trac
k
in
g
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
:
P
.
P
alan
ich
a
m
y
,
Dep
ar
t
m
en
t o
f
Ma
th
e
m
at
ics,
A
ME
T
Un
i
v
er
s
it
y
,
C
h
en
n
ai,
I
n
d
ia.
1.
I
NT
RO
D
UCT
I
O
N
Sh
ad
i
n
g
d
ata
is
t
h
e
b
est
ex
e
m
p
lif
icatio
n
o
f
th
e
o
b
j
ec
tiv
e
elem
en
t
d
ata.
T
h
e
ex
h
u
m
i
n
g
a
n
d
u
tili
s
atio
n
o
f
s
h
ad
i
n
g
d
ata
h
as
b
ee
n
a
cr
itical
r
esear
ch
co
u
r
s
e
i
n
m
an
y
tar
g
ets
f
o
llo
w
in
g
ca
lc
u
la
tio
n
s
.
A
s
a
g
en
er
al
d
eleg
ate,
C
a
m
s
h
a
f
t [
1
]
ca
lcu
la
tio
n
u
t
ilis
ed
t
h
e
s
h
ad
in
g
h
i
s
to
g
r
a
m
as t
h
e
r
ea
l
m
o
d
el
an
d
f
o
ll
o
w
ed
th
e
o
b
j
ec
tiv
e
b
y
f
i
n
d
i
n
g
th
e
"
ce
n
tr
o
id
"
o
f
w
eig
h
ted
g
u
id
e
iter
ati
v
el
y
[
2
]
.
T
h
is
h
y
p
o
t
h
esi
s
g
iv
e
s
n
ec
es
s
a
r
y
r
u
le
s
to
t
h
e
p
lan
o
f
s
h
ad
i
n
g
f
o
llo
w
i
n
g
ca
lc
u
lati
o
n
.
B
e
th
at
as
it
m
a
y
,
th
e
r
eli
an
ce
o
f
C
a
m
s
h
a
f
t
tr
ad
it
io
n
al
ca
lcu
latio
n
o
n
HS
V
s
h
ad
i
n
g
m
o
d
el
ad
d
itio
n
all
y
c
o
n
f
i
n
es
t
h
e
ex
te
n
t
o
f
u
ti
lis
at
io
n
o
f
th
e
m
a
th
[
3
]
.
A
t
th
e
p
o
in
t
w
h
en
t
h
e
s
h
ad
i
n
g
m
o
d
el
ca
n
't
ad
j
u
s
t
to
t
h
e
p
r
o
g
r
ess
io
n
s
o
f
tar
g
et
a
ttrib
u
te
s
,
t
h
e
e
x
ec
u
t
io
n
o
f
th
e
ca
lc
u
latio
n
e
n
o
r
m
o
u
s
l
y
d
i
m
in
is
h
ed
[
4
]
.
I
n
th
is
m
a
n
n
er
,
n
u
m
er
o
u
s
r
esear
c
h
er
s
at
h
o
m
e
an
d
ab
r
o
ad
s
tar
t
to
r
esear
ch
h
o
w
to
r
ef
r
esh
a
n
d
ex
ten
d
t
h
e
d
ep
ictio
n
m
o
d
el
o
f
s
h
ad
i
n
g
[
5
]
.
Fo
r
th
e
b
u
n
g
le
b
et
w
ee
n
tar
g
et
s
h
ad
i
n
g
m
o
d
el
a
n
d
r
ef
er
en
ce
la
y
o
u
t
b
r
o
u
g
h
t
ab
o
u
t
b
y
t
i
m
e
c
h
a
n
g
e
s
,
Nu
m
m
iar
o
p
r
o
p
o
s
ed
a
v
er
s
a
tile
s
h
ad
i
n
g
b
ased
ca
lcu
latio
n
[
6
]
.
I
m
a
g
e
Su
p
er
-
R
eso
l
u
tio
n
Us
in
g
W
av
elet
T
r
an
s
f
o
r
m
atio
n
B
ased
Gen
etic
A
l
g
o
r
ith
m
i
s
p
r
esen
ted
in
t
h
is
p
ap
er
[
7
]
.
W
r
itin
g
co
n
te
m
p
lated
h
o
w
to
as
s
e
m
b
l
e
Gau
s
s
ia
n
b
len
d
d
i
s
p
la
y
o
n
t
ar
g
et
an
d
u
til
is
e
t
h
e
E
M
ca
lc
u
latio
n
to
r
ef
r
es
h
it
w
h
e
n
th
e
n
e
w
p
er
ce
p
tio
n
s
ar
r
iv
ed
R
o
b
er
t
T
.
I
n
th
is
p
ap
er
also
d
escr
ib
ed
in
,
R
ec
o
g
n
i
ti
o
n
an
d
T
r
ac
k
in
g
o
f
Mo
v
in
g
Ob
j
ec
t
in
Un
d
er
w
ater
So
n
ar
I
m
ag
e
s
[
1
2
]
.
I
n
th
is
ar
ticle
d
escr
ib
ed
an
d
th
e
C
o
llin
s
p
r
o
p
o
s
ed
th
e
R
GB
s
tr
aig
h
t c
o
m
b
i
n
atio
n
s
tr
ateg
y
an
d
u
p
g
r
ad
ed
th
e
s
ec
u
r
it
y
o
f
t
h
e
s
h
ad
in
g
q
u
alitie
s
b
y
s
h
ad
i
n
g
m
ix
.
W
r
iti
n
g
s
a
n
d
en
h
a
n
ce
d
th
e
m
ea
n
m
o
v
e
an
d
C
a
m
s
h
i
f
t
ca
lc
u
latio
n
b
y
b
u
il
d
in
g
a
m
u
l
ti
-
s
h
ad
in
g
m
o
d
el
f
o
r
th
e
o
b
j
ec
tiv
es
i
n
v
ar
io
u
s
p
er
s
p
ec
tiv
e
s
.
I
n
th
is
p
ap
er
also
d
escr
ib
ed
in
,
Dete
ctio
n
o
f
g
lau
co
m
a
b
ased
o
n
c
o
lo
u
r
m
o
m
en
t
s
a
n
d
SVM
class
if
ier
u
s
i
n
g
k
m
ea
n
s
clu
s
ter
i
n
g
[
8
]
.
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
.
9
,
No
.
3
,
Ma
r
ch
2
0
1
8
:
5
7
7
–
5
8
2
578
2.
M
UL
T
I
-
CO
L
O
UR
J
O
I
N
T
F
E
AT
URE D
E
SC
RIP
T
I
O
N
2
.
1
.
M
ulti
-
cha
nn
el
Da
t
a
Ac
qu
is
it
io
n
Mu
lti
-
c
h
an
n
el
is
R
,
G,
B
,
H,
Y
f
iv
e
s
h
ad
i
n
g
ch
an
n
el
s
.
J
o
in
t
u
ti
lis
at
io
n
o
f
th
e
m
ca
n
p
o
r
tr
ay
th
e
ex
ter
n
al
s
h
ad
in
g
h
i
g
h
l
ig
h
t
s
all
th
e
m
o
r
e
co
m
p
letel
y
.
R
,
G,
B
is
t
h
e
r
ed
,
g
r
ee
n
,
b
lu
e
s
e
g
m
en
ts
i
n
R
GB
s
h
ad
in
g
s
p
ac
e.
Y
is
t
h
e
l
u
m
in
a
n
ce
p
o
r
t
io
n
i
n
YU
V
s
h
ad
in
g
s
p
ac
e.
H
is
t
h
e
ti
n
t
s
ec
tio
n
i
n
H
SV
s
h
ad
in
g
s
p
ac
e.
S
h
ad
i
n
g
s
p
ac
e
is
a
th
r
ee
-
d
i
m
e
n
s
io
n
al
o
r
g
an
i
s
e
f
r
a
m
e
w
o
r
k
.
E
ac
h
s
h
ad
in
g
is
co
m
m
u
n
icate
d
b
y
a
p
o
in
t.
I
n
R
GB
s
h
ad
i
n
g
s
p
ac
e,
r
ed
,
g
r
ee
n
an
d
b
lu
e
ar
e
th
e
ess
e
n
tia
l
co
m
p
o
n
e
n
ts
.
I
n
YUV
s
p
ac
e,
ea
ch
s
h
ad
in
g
h
a
s
a
lu
m
in
a
n
ce
f
lag
Y,
an
d
t
w
o
ch
r
o
m
in
a
n
ce
s
ig
n
als
U
an
d
V.
T
h
e
HSV
s
p
ac
e
in
co
r
p
o
r
ates
th
r
ee
s
e
g
m
en
ts
:
H,
S,
V.
H
s
p
ea
k
s
t
o
to
n
e,
an
d
S
s
p
ea
k
s
to
i
m
m
er
s
i
o
n
an
d
V
s
p
ea
k
s
to
s
h
i
n
e.
A
s
ap
p
ea
r
ed
in
Fig
u
r
e
1
.
T
h
e
s
h
ad
e
H
is
to
d
ep
ict
th
e
p
r
o
p
er
ties
o
f
h
ig
h
s
h
ad
in
g
.
T
h
e
ca
m
s
h
a
f
t
ca
lcu
latio
n
is
to
u
tili
s
e
th
e
H
ch
a
n
n
e
l
in
f
o
r
m
a
tio
n
to
p
o
r
tr
ay
th
e
o
b
j
ec
tiv
e
q
u
al
ities
.
I
n
th
i
s
p
a
p
er
also
d
escr
ib
ed
in
,
Mo
tio
n
E
s
ti
m
atio
n
Sear
c
h
Alg
o
r
it
h
m
Usi
n
g
Ne
w
C
r
o
s
s
Hex
a
g
o
n
-
Dia
m
o
n
d
Sear
ch
P
at
ter
n
[
1
3
]
.
Fig
u
r
e
1.
HSV
C
o
lo
u
r
s
p
ac
e
Fro
m
an
R
GB
co
lo
u
r
f
o
r
m
at
i
m
a
g
e,
H,
S,
V
co
m
p
o
n
e
n
ts
o
f
ea
ch
p
ix
el
ca
n
b
e
g
ai
n
ed
b
y
t
h
e
f
o
llo
w
in
g
eq
u
atio
n
s
,
i
n
w
h
ich
R
,
G,
an
d
B
v
alu
es r
a
n
g
e
f
r
o
m
0
to
1
:
Af
ter
th
i
s
tr
an
s
f
o
r
m
at
io
n
,
th
e
h
u
e
i
n
f
o
r
m
atio
n
H
r
an
g
es
f
r
o
m
0
°
to
3
6
0
°.
S
an
d
V
r
an
g
e
f
r
o
m
0
to
1
.
T
o
f
ac
ilit
ate
t
h
e
u
s
e
o
f
h
i
s
t
o
g
r
a
m
an
a
l
y
s
is
,
w
e
o
f
ten
ad
j
u
s
t
th
e
m
to
th
e
r
an
g
e
[
0
,
2
5
5
]
.
T
h
en
th
e
d
ata
d
is
tr
ib
u
tio
n
s
o
f
YHV
c
h
a
n
n
el
s
ca
n
b
e
s
h
o
w
n
i
n
t
h
e
Fi
g
u
r
e
2.
Fig
u
r
e
2
.
Data
d
is
tr
ib
u
tio
n
i
n
YHV
ch
a
n
n
e
ls
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
Mu
lti
-
co
lo
r
Jo
in
t P
r
o
b
a
b
ilit
y
S
ta
tis
tics
Mo
d
el
-
b
a
s
ed
Ob
ject
Tr
a
ck
in
g
S
ystem
(
P
.
P
a
la
n
ich
a
m
)
579
Fro
m
th
e
i
m
a
g
e
ab
o
v
e,
w
e
ca
n
s
ee
th
a
t
th
e
V
i
n
HSV
i
s
s
i
m
ilar
to
th
e
Y
i
n
YUV,
an
d
th
e
y
b
o
th
d
escr
ib
e
th
e
b
r
ig
h
t
n
es
s
o
f
a
p
ict
u
r
e.
Ho
w
e
v
er
,
as
t
h
e
V
h
as
t
h
e
lo
s
s
o
f
a
cc
u
r
ac
y
w
h
e
n
tr
an
s
f
o
r
m
ed
f
r
o
m
[
0
,
1
]
to
[
0
,
2
5
5
]
,
w
e
u
s
e
t
h
e
Y
co
m
p
o
n
e
n
t a
s
o
n
e
o
f
th
e
s
ta
n
d
ar
d
ch
an
n
els.
I
ts
ca
lcu
latio
n
eq
u
atio
n
i
s
(
5
)
.
2
.
2
.
Q
ua
ntif
ica
t
io
n o
f
M
ul
t
i
-
Cha
nn
el
Da
t
a
Af
ter
g
e
tti
n
g
R
,
G,
B
,
H,
Y
f
i
v
e
-
ch
a
n
n
el
i
n
f
o
r
m
atio
n
,
w
e
o
u
g
h
t to
ev
al
u
ate
ea
c
h
ch
a
n
n
el
i
n
f
o
r
m
at
io
n
to
co
m
p
u
te
th
e
li
k
eli
h
o
o
d
d
is
p
er
s
io
n
i
n
t
h
e
m
ea
s
u
r
ab
le
r
e
g
io
n
o
f
tar
g
e
t
attr
ib
u
tes.
T
h
e
s
u
p
p
o
s
ed
ev
alu
at
io
n
is
to
p
ar
titi
o
n
t
h
e
c
h
a
n
n
el
i
n
f
o
r
m
atio
n
i
n
to
a
f
e
w
lev
e
ls
in
[
0
,
2
5
5
]
.
I
ts
m
o
ti
v
atio
n
i
s
to
ac
co
m
p
li
s
h
t
h
e
b
es
t
ad
j
u
s
t
o
f
tar
g
et
r
ec
o
g
n
itio
n
a
n
d
ad
ap
tatio
n
to
i
n
ter
n
al
f
ail
u
r
e.
Sin
ce
t
h
e
d
i
s
co
v
er
y
is
ex
c
ess
i
v
el
y
d
elica
te
i
n
256
-
lev
el,
s
li
g
h
t
v
ac
il
latio
n
s
o
f
lig
h
t
o
r
d
if
f
er
e
n
t
co
m
p
o
n
e
n
ts
ca
n
b
r
in
g
ab
o
u
t
t
h
e
r
ea
l
s
t
atio
n
ch
a
n
g
e
s
,
th
e
n
tar
g
et
li
k
eli
h
o
o
d
tu
r
n
s
o
u
t
to
b
e
in
ac
c
u
r
ate,
last
l
y
f
o
c
u
s
f
o
l
lo
w
i
n
g
w
o
u
ld
co
m
e
u
p
s
h
o
r
t.
I
n
t
h
i
s
p
ap
er
also
d
escr
ib
ed
in
,
C
h
a
n
g
e
Dete
c
tio
n
f
r
o
m
R
e
m
o
tel
y
Sen
s
ed
I
m
a
g
es
B
ased
o
n
Statio
n
ar
y
W
av
elet
T
r
an
s
f
o
r
m
[
1
0
]
.
So
w
e
o
u
g
h
t
to
p
ar
titi
o
n
t
h
e
in
f
o
r
m
atio
n
i
n
to
a
f
e
w
le
v
els
a
n
d
k
ee
p
th
e
v
ac
il
latio
n
o
f
tar
g
et
c
h
an
n
el
in
f
o
r
m
atio
n
i
n
s
id
e
a
s
i
m
ilar
le
v
el.
A
t
th
a
t
p
o
in
t,
t
h
e
ad
ap
tati
o
n
to
a
n
o
n
-
cr
itical
f
ail
u
r
e
o
f
a
f
r
a
m
e
w
o
r
k
m
ad
e
s
tr
id
es.
Ob
v
io
u
s
l
y
,
t
h
e
d
iv
is
io
n
o
u
g
h
t
n
o
t
to
b
e
to
o
u
n
p
lea
s
an
t.
So
m
eth
in
g
el
s
e,
d
iv
er
s
e
i
n
f
o
r
m
atio
n
w
ill
b
e
co
n
f
o
u
n
d
ed
in
o
n
e
s
a
m
e
lev
e
l
if
th
e
ex
ter
n
al
s
h
ad
in
g
is
n
e
ar
f
o
u
n
d
atio
n
.
A
t
t
h
at
p
o
in
t,
it
co
u
ld
less
en
t
h
e
lo
ca
tio
n
ex
ec
u
tio
n
o
f
f
r
a
m
e
wo
r
k
.
As
ap
p
ea
r
ed
in
Fi
g
ur
e
2
,
co
n
s
id
er
in
g
R
,
G,
B
,
Y
ch
a
n
n
els
a
n
d
H
c
h
an
n
el
h
av
e
d
i
s
ti
n
cti
v
e
s
m
o
o
th
n
es
s
,
w
e
p
ar
titi
o
n
R
,
G,
B
,
Y
c
h
a
n
n
els i
n
to
5
1
lev
els a
n
d
s
ep
ar
ati
o
n
H
ch
a
n
n
el
i
n
to
1
7
lev
els.
E
ac
h
ch
a
n
n
e
l in
f
o
r
m
at
i
o
n
is
co
m
m
u
n
ica
ted
as
:
2
.
3
.
Ca
lcula
t
io
n
o
f
J
o
int
P
ro
ba
bil
it
y
a
nd
G
re
y
P
ro
j
ec
t
io
n
T
h
e
ex
ac
t
r
an
g
e
o
f
tar
g
et
attr
ib
u
tes
i
s
a
n
ar
r
an
g
e
m
en
t
o
f
p
ix
els
w
h
ich
is
u
til
is
ed
to
asc
er
tain
t
h
e
m
u
lti
-
ch
a
n
n
el
s
h
ad
i
n
g
q
u
ali
ti
es
o
f
a
tar
g
e
t.
T
h
is
ter
r
ito
r
y
h
as
a
p
lace
w
it
h
tar
g
et
f
o
llo
w
i
n
g
w
i
n
d
o
w
.
W
h
ile
in
tr
o
d
u
ci
n
g
t
h
e
ca
lc
u
latio
n
,
t
h
e
ac
t
u
al
r
eg
io
n
is
eq
u
iv
a
le
n
t
to
tar
g
et
f
o
llo
w
i
n
g
w
i
n
d
o
w
.
I
n
tak
in
g
a
f
ter
co
m
p
u
tatio
n
s
,
it
c
h
ar
ac
ter
is
es
th
e
ar
r
an
g
e
m
e
n
t
o
f
p
ix
el
s
w
h
i
ch
d
ar
k
estee
m
i
s
m
o
r
e
n
o
te
wo
r
th
y
t
h
an
ei
g
h
t
a
s
th
e
ac
t
u
al
r
an
g
e
o
f
tar
g
et
q
u
a
liti
es
i
n
s
id
e
t
h
e
f
o
llo
w
in
g
w
i
n
d
o
w
.
A
t
t
h
at
p
o
in
t
tall
y
th
e
in
f
o
r
m
atio
n
o
f
ea
c
h
lev
el
o
f
f
i
v
e
c
h
an
n
el
s
a
n
d
as
ce
r
tain
t
h
e
r
ea
l
lik
e
lih
o
o
d
tab
le.
T
h
e
p
r
o
b
ab
ilit
y
o
f
ea
c
h
c
h
an
n
el
lev
el
w
ill
b
e
co
m
m
u
n
icate
d
as:
T
ar
g
et
f
o
llo
w
in
g
w
i
n
d
o
w
is
a
p
o
ten
tial
tar
g
et
r
ec
tan
g
u
l
ar
r
an
g
e
an
d
ad
d
itio
n
all
y
ca
lcu
latio
n
w
i
n
d
o
w
.
T
h
e
w
i
n
d
o
w
is
c
h
ar
a
cter
is
ed
p
h
y
s
icall
y
at
f
ir
s
t
a
n
d
g
o
tten
b
y
ascer
tai
n
i
n
g
later
o
n
.
T
ak
in
g
af
ter
(
6
)
,
w
e
ca
n
co
m
p
u
te
t
h
e
f
i
v
e
ch
a
n
n
el
lo
o
k
-
i
n
to
tab
les
f
r
o
m
p
ix
el
to
lik
eli
h
o
o
d
,
an
d
af
ter
w
ar
d
s
,
d
eter
m
i
n
e
s
o
m
e
p
ix
el
lik
e
lih
o
o
d
b
y
(
7
)
.
B
ase
o
n
h
y
p
o
t
h
esi
s
o
v
er
,
th
e
ca
lc
u
l
atio
n
f
i
n
d
s
t
h
e
f
i
v
e
c
h
an
n
el
p
r
o
b
ab
ilit
y
o
f
a
p
ix
el
in
th
e
o
b
j
ec
tiv
e
f
o
llo
w
in
g
w
i
n
d
o
w
,
an
d
f
i
g
u
r
e
th
e
j
o
in
t
tar
g
et
lik
eli
h
o
o
d
P
o
f
th
is
p
ix
e
l.
A
t
th
at
p
o
in
t,
it
ch
an
g
es
t
h
e
P
to
th
e
r
an
g
e
[
0
,
2
5
5
]
t
o
g
et
th
e
d
i
m
li
k
eli
h
o
o
d
esti
m
a
tio
n
o
f
t
h
i
s
p
ix
el
a
n
d
ch
an
g
e
ev
er
y
o
n
e
o
f
th
e
p
ix
e
ls
i
n
t
h
e
o
b
j
ec
tiv
e
f
o
llo
w
i
n
g
w
i
n
d
o
w
to
g
et
th
e
r
i
s
k
d
ar
k
p
r
o
j
ec
tio
n
g
u
id
e
o
f
t
h
e
tar
g
e
t
f
o
llo
w
i
n
g
r
eg
io
n
.
A
lo
n
g
t
h
e
s
e
li
n
es,
w
e
p
ick
u
p
m
u
lti
-
s
h
ad
in
g
j
o
in
t
t
ar
g
et
attr
ib
u
te
s
b
y
th
e
s
tr
ateg
y
f
o
r
m
u
lti
-
s
h
a
d
in
g
j
o
in
t
lik
eli
h
o
o
d
in
s
ig
h
t
s
s
h
o
w.
I
n
t
h
is
p
ap
er
also
d
escr
ib
ed
in
,
r
e
v
ie
w
i
n
g
t
h
e
E
f
f
ec
ti
v
it
y
Facto
r
in
E
x
i
s
ti
n
g
T
ec
h
n
iq
u
es o
f
I
m
ag
e
Fo
r
en
s
ic
s
[
1
1
]
.
2
.
4
.
P
r
o
ce
du
re
o
f
Z
o
ne
Weig
hte
d P
ro
j
ec
t
io
n
T
ar
g
et
f
o
llo
w
in
g
w
i
n
d
o
w
i
s
a
p
o
ten
tial
tar
g
et
r
ec
ta
n
g
le
ar
e
a,
s
o
th
e
o
b
j
ec
tiv
e
r
eg
io
n
is
a
s
u
b
s
et
o
f
th
e
tar
g
et
f
o
llo
w
i
n
g
w
i
n
d
o
w
.
W
h
ile
f
i
g
u
r
in
g
t
h
e
lik
el
ih
o
o
d
d
i
m
o
f
th
e
tar
g
et
f
o
llo
w
in
g
win
d
o
w
a
s
in
d
icate
d
b
y
t
h
e
p
r
esen
t
lo
o
k
-
i
n
to
tab
le
o
f
tar
g
et
r
is
k
,
w
e
m
o
r
e
o
f
te
n
th
an
n
o
t
d
u
p
licate
th
e
d
ar
k
o
f
tar
g
et
f
o
llo
w
i
n
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
9
,
No
.
3
,
Ma
r
ch
2
0
1
8
:
5
7
7
–
5
8
2
580
w
i
n
d
o
w
w
it
h
a
ca
lc
u
late
α
r
e
q
u
est
to
le
s
s
e
n
t
h
e
f
o
u
n
d
atio
n
cla
m
o
u
r
.
E
s
tee
m
α
is
i
n
t
h
e
v
ici
n
it
y
o
f
0
a
n
d
1
,
an
d
th
e
n
ea
r
er
to
th
e
i
n
s
id
e,
th
e
litt
ler
α
is
.
As f
ar
as p
o
s
s
ib
le
w
ill r
el
y
o
n
u
p
o
n
th
e
te
s
t c
o
n
d
itio
n
.
C
o
n
s
id
er
in
g
th
e
p
la
n
n
ed
s
ta
n
d
ar
d
o
f
w
ei
g
h
tin
g
p
r
o
j
ec
tio
n
in
a
m
ea
n
m
o
v
e,
w
e
d
e
v
is
e
a
tec
h
n
iq
u
e
f
o
r
w
ei
g
h
ted
p
r
ep
ar
in
g
ca
lled
t
y
p
ical
p
iv
o
t
p
r
o
p
o
r
tio
n
p
r
o
j
ec
tio
n
.
I
t
ch
ar
ac
ter
i
s
es
x
r
as
th
e
e
x
te
n
t
o
f
th
e
s
ep
ar
atio
n
f
r
o
m
p
ix
e
l
Q(
x
,
y
)
to
t
h
e
i
n
s
id
e
a
n
d
t
h
e
s
ep
ar
atio
n
f
r
o
m
Q
to
X
p
iv
o
t
in
X.
A
d
d
itio
n
all
y
,
it
ch
ar
ac
ter
is
es
y
r
as
t
h
e
e
x
te
n
t
o
f
th
e
s
ep
ar
atio
n
f
r
o
m
Q
t
o
th
e
m
id
d
le
an
d
th
e
s
ep
ar
atio
n
f
r
o
m
Q
to
Y
in
Y
：
Def
i
n
e
α
as t
h
e
w
ei
g
h
ted
f
ac
to
r
o
f
th
e
p
ix
el
Q:
W
h
er
e
b
is
th
e
ad
j
u
s
t
m
e
n
t
f
ac
t
o
r
b
etw
ee
n
0
an
d
1
,
an
d
it is
0
.
5
in
th
i
s
p
ap
er
.
T
h
r
o
u
g
h
co
r
r
elatio
n
,
w
e
f
i
n
d
th
at
th
e
w
ei
g
h
t
in
g
p
r
ep
ar
in
g
ca
n
u
n
d
o
u
b
ted
l
y
d
is
p
o
s
e
o
f
th
e
co
m
m
o
tio
n
o
b
s
tr
u
ctio
n
o
f
th
e
r
ea
r
w
in
d
o
w
ed
g
e.
B
e
th
at
a
s
i
t
m
a
y
,
o
v
er
-
w
ei
g
h
ti
n
g
w
i
ll li
k
e
w
i
s
e
in
f
l
u
e
n
c
e
th
e
ex
ten
t
o
f
f
o
cu
s
in
t
h
e
f
o
llo
win
g
w
i
n
d
o
w
.
So
it
'
s
i
m
p
er
ati
v
e
to
d
is
co
v
er
th
e
ad
j
u
s
t
p
o
i
n
t
f
o
r
th
e
lev
e
l
o
f
w
ei
g
h
ti
n
g
.
C
alcu
late
b
is
in
te
n
d
ed
f
o
r
th
is
is
s
u
e.
Fig
u
r
e
3.
R
ef
lect
t
h
e
e
f
f
ec
t a
n
al
y
s
i
s
o
f
w
ei
g
h
ted
p
r
o
j
ec
tio
n
3.
O
UT
L
I
NE
O
F
CA
L
CU
L
AT
I
O
N
H
ANDL
I
N
G
I
NS
T
RU
M
E
NT
Af
ter
t
h
e
o
v
er
th
r
ee
s
ec
tio
n
s
ar
e
f
i
n
is
h
ed
,
w
e
'
ll
d
escr
ib
e
t
h
e
p
r
o
ce
s
s
i
n
g
d
ev
ice
o
f
t
h
e
ca
lcu
latio
n
n
ex
t.
W
it
h
a
s
p
ec
if
ic
e
n
d
g
o
al
to
d
ec
r
ea
s
e
th
e
co
m
p
u
ta
tio
n
al
lo
ad
an
d
en
h
a
n
ce
th
e
r
eg
is
ter
in
g
ex
ac
t
n
e
s
s
,
li
m
ited
iter
ati
v
e
cir
cle
co
m
p
o
n
en
t
i
n
lig
h
t
o
f
tar
g
et
w
i
n
d
o
w
w
ill
b
e
u
tili
s
ed
as
a
p
ar
t
o
f
th
e
ca
lcu
latio
n
.
Fig
u
r
e
4
d
ep
icts
th
e
en
tire
p
r
o
ce
d
u
r
e.
Fro
m
F
ig
u
r
e
4
,
th
e
w
h
o
le
p
r
o
ce
s
s
ca
n
b
e
co
m
m
u
n
icate
d
th
a
t
r
ig
h
t
o
f
f
th
e
b
at
in
p
u
t
t
h
e
f
i
v
e
-
ch
a
n
n
e
l
p
ictu
r
e
i
n
f
o
r
m
at
io
n
a
n
d
asc
er
tain
t
h
e
j
o
in
t
lik
e
lih
o
o
d
lo
o
k
-
in
to
tab
le
i
n
t
h
e
o
b
j
ec
tiv
e
attr
ib
u
te
s
f
ac
t
u
al
r
a
n
g
e,
t
h
e
n
ch
a
n
g
e
ev
er
y
p
ix
el
in
t
h
e
f
o
llo
w
i
n
g
w
i
n
d
o
w
to
g
et
th
e
p
r
o
j
ec
tio
n
o
f
r
is
k
d
ar
k
as
p
er
th
e
lo
o
k
-
in
to
tab
le,
n
ex
t
p
ick
u
p
th
e
p
lace
s
o
f
tar
g
et
a
n
d
w
i
n
d
o
w
to
m
ee
t
to
th
e
o
b
j
ec
tiv
e
ce
n
tr
o
id
th
r
o
u
g
h
li
m
ited
iter
a
tiv
e
o
p
er
atio
n
s
an
d
m
o
d
i
f
y
t
h
e
m
ea
s
u
r
e
o
f
w
i
n
d
o
w
,
a
n
d
af
ter
th
at
f
i
g
u
r
e
th
e
ac
tu
al
q
u
ali
ties
m
ea
s
u
r
ab
le
ter
r
ito
r
y
a
n
d
en
ter
th
e
f
o
llo
w
i
n
g
ac
tio
n
.
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
Mu
lti
-
co
lo
r
Jo
in
t P
r
o
b
a
b
ilit
y
S
ta
tis
tics
Mo
d
el
-
b
a
s
ed
Ob
ject
Tr
a
ck
in
g
S
ystem
(
P
.
P
a
la
n
ich
a
m
)
581
Fig
u
r
e
4.
Flo
w
c
h
ar
t
4.
J
O
I
NT
-
CH
ANN
E
L
P
E
RF
O
RM
ANCE AN
AL
Y
S
IS
J
o
in
t
-
ch
a
n
n
el
e
n
h
a
n
ce
s
th
e
ex
p
r
ess
i
v
e
q
u
al
ities
o
f
a
tar
g
et
an
d
i
m
p
r
o
v
e
s
t
h
e
ac
t
u
al
r
ec
o
g
n
itio
n
ab
ilit
y
o
f
ca
lc
u
latio
n
.
A
s
ap
p
ea
r
ed
in
Fi
g
u
r
e
2
,
f
r
o
m
v
is
u
al
p
er
ce
p
tio
n
,
th
e
p
h
y
s
ical
attr
ib
u
tes
p
o
r
tr
ay
al
o
f
H
-
ch
an
n
el
w
h
ic
h
C
a
m
s
h
i
f
t
d
ep
en
d
s
o
n
is
n
o
t a
s
r
ich
a
s
th
at
o
f
an
o
th
er
ch
a
n
n
el.
Fig
u
r
e
5.
T
a
r
g
et
tr
ac
k
in
g
f
o
r
d
if
f
er
en
t c
o
lo
u
r
I
t
d
em
o
n
s
tr
ates
t
h
e
id
en
ti
f
icat
io
n
i
m
p
ac
ts
o
f
th
e
ca
lc
u
latio
n
f
o
r
v
ar
io
u
s
s
h
ad
in
g
tar
g
et
s
.
I
t
m
ea
n
s
t
o
ch
ec
k
t
h
e
h
ig
h
lo
ca
tio
n
ab
ilit
y
o
f
m
u
l
ti
-
ch
a
n
n
e
l
f
o
r
d
if
f
er
en
t
h
u
es.
B
e
th
at
a
s
it
m
a
y
,
C
a
m
s
h
i
f
t
ca
lc
u
latio
n
i
s
in
v
a
lid
f
o
r
t
h
e
s
it
e
o
f
b
l
u
e
a
n
d
d
ee
p
f
o
cu
s
in
Fi
g
u
r
e
5
.
B
lu
e
an
d
d
ar
k
s
h
ad
i
n
g
is
n
o
t
u
n
m
i
s
ta
k
ab
le
i
n
H
ch
an
n
el.
5.
CO
NCLU
SI
O
N
An
o
b
j
ec
tiv
e
f
o
llo
w
i
n
g
ca
lc
u
l
atio
n
is
g
i
v
e
n
m
u
l
ti
-
s
h
ad
in
g
j
o
in
t
li
k
eli
h
o
o
d
ex
a
m
in
at
io
n
m
o
d
el
w
as
p
r
o
p
o
s
ed
in
th
i
s
p
ap
er
.
I
t
m
ad
e
s
o
m
e
i
m
p
o
r
ta
n
t
i
n
v
e
s
ti
g
atio
n
s
o
n
t
h
e
u
n
co
v
er
in
g
o
f
tar
g
et
m
u
lti
-
s
h
ad
in
g
d
ata.
I
n
th
i
s
ar
ticle
also
d
escr
ib
ed
in
,
Fu
zz
y
R
eg
io
n
Me
r
g
i
n
g
u
s
i
n
g
F
u
zz
y
S
i
m
ilar
it
y
Me
a
s
u
r
e
m
e
n
t
o
n
I
m
ag
e
Seg
m
en
tatio
n
[
9
]
.
I
n
p
ar
ticu
l
ar
,
s
o
m
e
n
e
w
in
v
o
lu
tio
n
s
wer
e
d
is
p
lay
ed
o
n
s
h
ad
in
g
h
i
g
h
l
ig
h
t
s
h
o
w
,
zo
n
e
w
ei
g
h
ted
p
r
o
j
ec
tio
n
,
an
d
f
o
ll
o
w
i
n
g
w
i
n
d
o
w
f
i
g
u
r
in
g
.
T
est
s
en
s
u
r
ed
t
h
e
e
x
ce
lle
n
t
e
x
ec
u
tio
n
o
f
t
h
e
m
u
lti
-
s
h
ad
i
n
g
m
o
d
el
i
n
C
o
m
p
le
x
S
ce
n
e.
B
e
th
a
t
as
it
m
a
y
,
a
f
e
w
p
o
in
ts
o
f
i
n
ter
est
o
u
g
h
t
to
b
e
en
h
an
ce
d
la
ter
o
n
.
T
h
e
m
o
s
t
e
f
f
icien
t
m
e
th
o
d
to
s
tr
ea
m
l
in
e
t
h
e
j
o
in
t
s
y
s
te
m
o
f
m
u
lti
-
s
h
ad
in
g
u
tili
s
i
n
g
t
h
e
r
elatio
n
s
a
m
o
n
g
t
h
e
f
i
v
e
ch
a
n
n
e
ls
w
o
u
ld
b
e
a
cr
itic
al
s
u
b
s
ta
n
ce
o
f
o
u
r
s
u
b
s
eq
u
en
t
r
esear
ch
.
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
.
9
,
No
.
3
,
Ma
r
ch
2
0
1
8
:
5
7
7
–
5
8
2
582
RE
F
E
R
E
NC
E
S
[1
]
Bra
d
sk
i
G
R.
Co
mp
u
ter
Vi
sio
n
F
a
c
e
T
ra
c
k
in
g
a
s
a
Co
mp
o
n
e
n
t
o
f
a
Per
c
e
p
tu
a
l
Us
e
r
In
ter
fa
c
e
.
In
P
r
o
c
.
o
f
th
e
I
EE
E
W
o
rk
sh
o
p
A
p
p
li
c
a
ti
o
n
s o
f
Co
m
p
u
ter
Visio
n
.
1
9
9
8
;
2
1
4
-
2
1
9
.
[2
]
Nu
m
m
iaro
K,
Ko
ll
e
r
-
M
e
ier
E,
V
a
n
G
o
o
l
L
.
A
n
a
d
a
p
ti
v
e
c
o
lo
u
r
-
b
a
se
d
p
a
rti
c
le
f
il
ter.
Im
a
g
e
a
n
d
v
is
io
n
c
o
m
p
u
ti
n
g
,
2
0
0
3
;
21
(
1
):
9
9
-
1
1
0
.
[3
]
Zh
o
u
S
K,
Ch
e
ll
a
p
p
a
R,
M
o
g
h
a
d
d
a
m
B.
V
isu
a
l
trac
k
in
g
a
n
d
re
c
o
g
n
it
io
n
u
sin
g
a
p
p
e
a
ra
n
c
e
-
a
d
a
p
ti
v
e
m
o
d
e
ls
in
p
a
rti
c
le f
il
ters
.
IEE
E
T
ra
n
sa
c
ti
o
n
s o
n
Im
a
g
e
Pr
o
c
e
ss
in
g
.
2
0
0
4
;
13
(
1
1
):
1
4
9
1
-
1
5
0
6
.
[4
]
L
e
ich
ter
I,
L
in
d
e
n
b
a
u
m
M
,
Riv
li
n
E
.
M
e
a
n
-
s
h
if
t
trac
k
in
g
w
it
h
m
u
lt
ip
le
re
f
e
re
n
c
e
c
o
lo
u
r
h
ist
o
g
ra
m
s.
Co
m
p
u
ter
V
isio
n
a
n
d
Im
a
g
e
Un
d
e
rsta
n
d
in
g
.
2
0
1
0
;
1
1
4
(
3
):
4
0
0
-
4
0
8
.
[5
]
Zu
o
J,
L
ian
g
Y,
P
a
n
Q,
Zh
a
o
CH
,
Zh
a
n
g
HC.
Ca
m
sh
if
t
tr
a
c
k
e
r
b
a
se
d
o
n
m
u
lt
ip
le
c
o
lo
u
r
d
istri
b
u
ti
o
n
m
o
d
e
ls.
A
c
t
a
A
u
to
m
a
ti
c
a
S
in
ica
.
2
0
0
8
;
34
(7
):
7
3
6
-
7
4
2
.
[6
]
WA
N
G
Q,
JI
AN
G
S
H,
ZH
A
N
G
JQ
,
HU
B.
A
n
A
p
p
ro
a
c
h
to
Im
p
ro
v
e
th
e
P
e
rf
o
rm
a
n
c
e
o
f
M
e
a
n
-
sh
if
t
T
ra
c
k
in
g
A
l
g
o
rit
h
m
.
J
o
u
rn
a
l
o
f
Fu
d
a
n
U
n
i
v
e
rs
it
y
(
Na
tu
ra
l
S
c
ien
c
e
)
.
2
0
0
7
;
46
(1
):
8
5
-
9
0
.
[7
]
P
a
n
d
a
S
S
,
Je
n
a
G
.
Im
a
g
e
S
u
p
e
r
-
Re
so
lu
ti
o
n
Us
i
n
g
W
a
v
e
let
T
ra
n
s
f
o
r
m
a
ti
o
n
Ba
se
d
G
e
n
e
ti
c
A
lg
o
rit
h
m
.
In
Co
mp
u
t
a
ti
o
n
a
l
I
n
telli
g
e
n
c
e
in
D
a
ta
M
in
i
n
g
.
S
p
rin
g
e
r
In
d
ia.
2
0
1
6
;
2
:
3
5
5
-
3
6
1
.
[8
]
S
u
re
n
d
iran
J,
S
a
ra
v
a
n
a
n
S
V,
m
a
n
iv
a
n
n
a
n
K.
De
tec
ti
o
n
o
f
g
lau
c
o
m
a
b
a
se
d
o
n
c
o
lo
u
r
m
o
m
e
n
ts
a
n
d
S
V
M
c
las
sif
ier
u
sin
g
k
m
e
a
n
s clu
ste
rin
g
,
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
P
h
a
rm
a
c
y
a
n
d
T
e
c
h
n
o
l
o
g
y
.
2
0
1
6
;
8
(
3
):
1
6
1
3
9
-
1
6
1
4
8
.
[9
]
W
a
wa
n
G
u
n
a
w
a
n
,
Ag
u
s
Zain
a
l
A
ri
f
in
.
F
u
z
z
y
R
e
g
io
n
M
e
rg
in
g
u
sin
g
F
u
z
z
y
S
i
m
il
a
rit
y
M
e
a
su
re
m
e
n
t
o
n
Im
a
g
e
S
e
g
m
e
n
tatio
n
.
I
n
ter
n
a
t
io
n
a
l
J
o
u
r
n
a
l
o
f
E
lec
trica
l
a
n
d
Co
mp
u
ter
E
n
g
i
n
e
e
rin
g
(
IJ
ECE
).
2
0
1
7
;
7
(6
):
3
4
0
2
-
3
4
1
0
.
[1
0
]
A
b
h
ish
e
k
S
h
a
rm
a
,
T
a
ru
n
G
u
lati.
Ch
a
n
g
e
De
tec
ti
o
n
f
ro
m
Re
m
o
tely
S
e
n
se
d
Im
a
g
e
s
Ba
se
d
o
n
S
tatio
n
a
ry
W
a
v
e
let
T
ra
n
s
f
o
r
m
.
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
(
IJ
ECE
).
2
0
1
7
;
7
(
6
):
3
3
9
5
-
3
4
0
1
.
[1
1
]
S
h
a
sh
id
h
a
r
T
M
,
Ra
m
e
sh
KB.
Re
v
ie
w
in
g
th
e
Eff
e
c
ti
v
it
y
F
a
c
to
r
in
Ex
isti
n
g
T
e
c
h
n
iq
u
e
s
o
f
Im
a
g
e
F
o
re
n
sic
s.
In
ter
n
a
t
io
n
a
l
J
o
r
u
n
a
l
o
f
E
lec
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
(
IJ
ECE
).
2
0
1
7
;
7
(6
):
3
5
5
8
-
3
5
6
9
.
[1
2
]
S
.
Ka
rth
ik
,
V.A
n
n
a
p
o
o
ra
n
i,
S
.
Di
n
e
sh
k
u
m
a
r.
Re
c
o
g
n
it
io
n
a
n
d
T
ra
c
k
in
g
o
f
M
o
v
in
g
Ob
jec
t
in
Un
d
e
rw
a
ter
S
o
n
a
r
Im
a
g
e
s.
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
M
C
S
q
u
a
re
S
c
ien
ti
fi
c
Res
e
a
rc
h
(
IJ
M
S
R).
2
0
1
6
;
8
(
1
):
9
3
-
98.
[1
3
]
Ra
jav
e
lu
T
.
M
o
ti
o
n
Esti
m
a
ti
o
n
S
e
a
rc
h
A
lg
o
rit
h
m
Us
in
g
Ne
w
Cro
ss
He
x
a
g
o
n
-
Dia
m
o
n
d
S
e
a
rc
h
P
a
tt
e
rn
.
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
M
C
S
q
u
a
re
S
c
ien
ti
fi
c
Res
e
a
rc
h
(
IJ
M
S
R
).
2
0
1
5
;
7
(1
)
:1
0
4
-
1
1
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.