I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineeri
ng
a
nd
Co
m
p
u
t
er
Science
Vo
l.
9
,
No
.
1
,
J
an
u
ar
y
201
8
,
p
p
.
12
~
14
I
SS
N:
2502
-
4752
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ee
cs
.
v
9
.
i1
.
p
p
12
-
14
12
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
No
v
el Method
f
o
r
Det
e
ction o
f
Ship
Doc
k
ed
i
n
H
a
rbo
r
in
H
ig
h
Reso
lution Re
m
o
t
e Sensing
I
m
a
g
e
K
.
Ra
g
ha
v
i
De
p
a
rtme
n
t
o
f
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
A
M
ET
Un
iv
e
rsit
y
,
Ch
e
n
n
a
i
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
9
,
2
0
1
7
R
ev
i
s
ed
No
v
2
0
,
2
0
1
7
A
cc
ep
ted
Dec
1
1
,
2
0
1
7
T
ra
n
sp
o
rt
d
isc
o
v
e
ry
u
ti
li
z
in
g
g
re
a
t
d
e
term
in
a
ti
o
n
re
m
o
te
d
e
tec
ti
n
g
p
ictu
re
s
is
a
h
o
t
re
se
a
rc
h
th
e
m
e
in
b
o
th
m
il
it
a
r
y
a
n
d
n
o
n
m
il
it
a
r
y
p
e
rso
n
n
e
l
a
p
p
li
c
a
ti
o
n
s.
In
t
h
is
p
a
p
e
r,
a
n
o
th
e
r
tec
h
n
i
q
u
e
f
o
r
i
d
e
n
ti
f
ica
ti
o
n
o
f
b
o
a
ts
d
o
c
k
e
d
in
a
h
a
rb
o
r
w
a
s
p
ro
p
o
se
d
,
i
n
w
h
ich
,
Ha
rris
c
o
rn
e
r
id
e
n
ti
f
ier
c
o
n
so
li
d
a
ted
w
it
h
n
e
a
rb
y
strik
in
g
lo
c
a
le
e
x
a
m
in
a
ti
o
n
w
e
re
u
ti
li
z
e
d
to
e
x
tri
c
a
te
th
e
im
p
o
rt
a
n
t
sh
a
rp
-
c
a
lcu
late
d
e
le
m
e
n
t
id
e
n
ti
f
ied
w
it
h
th
e
f
o
re
p
iec
e
o
f
a
sh
ip
in
sa
telli
t
e
p
ictu
re
s.
T
h
is
tec
h
n
iq
u
e
c
a
n
d
e
c
id
e
th
e
c
o
u
rse
o
f
th
e
sh
ip
w
h
e
n
t
h
e
sh
ip
is
d
isti
n
g
u
is
h
e
d
.
T
h
e
a
f
tere
ff
e
c
ts
o
f
tes
ts
o
n
a
f
e
w
g
re
a
t
d
e
ter
m
in
a
ti
o
n
re
m
o
te
d
e
tec
ti
n
g
im
a
g
e
s c
o
n
f
ir
m
e
d
th
e
v
iab
il
it
y
o
f
th
e
p
ro
p
o
se
d
str
a
teg
y
.
K
ey
w
o
r
d
s
:
C
lu
s
ter
i
n
g
Featu
r
e
E
x
tr
ac
t
io
n
Hig
h
R
e
s
o
lu
tio
n
L
o
ca
l Salie
n
t Re
g
io
n
Sh
ip
Dete
ctio
n
Co
p
y
rig
h
t
©
2
0
1
8
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
K.
R
ag
h
av
i
,
Ass
i
s
tan
t P
r
o
f
ess
o
r
,
Dep
ar
tm
e
n
t o
f
I
n
f
o
r
m
at
io
n
T
ec
h
n
o
lo
g
y
A
ME
T
Un
i
v
er
s
it
y
,
C
h
en
n
ai
.
1.
I
NT
RO
D
UCT
I
O
N
As
o
f
late,
a
lo
t
o
f
g
r
ea
t
d
eter
m
in
at
io
n
r
e
m
o
te
d
etec
ti
n
g
s
a
tellite,
f
o
r
ex
a
m
p
le,
Qu
ic
k
b
ir
d
,
W
o
r
ld
v
ie
w
,
Geo
E
y
e,
w
as
p
r
o
g
r
ess
i
v
el
y
p
u
t
in
to
b
u
s
i
n
e
s
s
o
p
er
atio
n
.
Su
b
s
eq
u
e
n
tl
y
,
g
r
ea
t
r
eso
lu
tio
n
s
a
tellit
e
p
ictu
r
es
ar
e
b
r
o
ad
ly
u
tili
ze
d
a
s
a
p
ar
t
o
f
b
o
th
m
ilit
ar
y
a
n
d
r
eg
u
lar
citize
n
ap
p
licatio
n
s
.
R
e
co
g
n
itio
n
o
f
S
h
ip
s
in
Har
b
o
r
i
n
R
e
m
o
te
Se
n
s
i
n
g
I
m
a
g
e
B
ased
o
n
L
o
ca
l
Self
-
s
i
m
ilar
it
y
a
n
d
Feat
u
r
e
d
etec
ti
o
n
w
it
h
a
u
to
m
atic
s
ca
le
s
elec
t
io
n
ar
e
d
escr
ib
ed
b
y
[
1
]
[
2
]
.
T
h
er
e
w
er
e
m
an
y
ex
a
m
in
e
s
o
n
th
e
d
i
s
co
v
er
y
o
f
s
h
ip
f
o
cu
s
es
in
th
e
o
ce
an
,
y
et
f
e
w
co
n
s
id
er
ed
t
h
e
s
h
ip
d
o
ck
ed
i
n
t
h
e
h
ar
b
o
r
.
Dis
p
atc
h
T
ar
g
et
r
e
v
elatio
n
S
ch
e
m
e
f
o
r
Op
tical
R
e
m
o
te
Sen
s
i
n
g
I
m
a
g
es
i
s
e
x
p
lain
ed
b
y
[
3
]
.
Z
h
ao
Yi
n
g
-
h
ai
e
x
h
ib
ited
a
s
h
ip
tar
g
et
lo
ca
tio
n
co
n
s
p
ir
e
f
o
r
o
p
tical
r
em
o
te
d
etec
tin
g
p
ictu
r
es
b
y
u
t
i
lizi
n
g
a
d
if
f
er
en
tia
tio
n
b
o
x
s
ep
ar
atin
g
o
v
er
th
e
s
tan
d
ar
d
d
ev
iatio
n
h
ig
h
li
g
h
t
p
la
n
es.
A
Ne
w
Me
th
o
d
f
o
r
S
h
ip
De
tectio
n
B
as
ed
o
n
Feat
u
r
e
F
u
s
io
n
i
n
Op
tical
I
m
a
g
e
a
n
d
A
co
m
b
i
n
ed
co
r
n
er
an
d
ed
g
e
d
et
ec
to
r
ar
e
d
escr
ib
e
d
b
y
[
4
]
[
5
]
.
Yo
u
Xiao
-
J
ian
p
r
o
p
o
s
ed
an
o
th
er
s
h
ip
r
ec
o
g
n
i
tio
n
tech
n
iq
u
e
in
li
g
h
t
o
f
h
i
g
h
lig
h
t
co
m
b
in
a
tio
n
o
f
m
u
lt
i
-
p
h
an
to
m
p
ictu
r
e
an
d
P
A
N
p
ictu
r
e
.
Fu
zz
y
C
s
tr
a
n
g
e
p
o
in
ts
clu
s
ter
i
n
g
al
g
o
r
ith
m
i
s
d
is
cu
s
s
ed
b
y
[
6
]
.
I
n
d
o
w
n
to
ea
r
th
u
s
e
o
f
th
ese
s
tr
ateg
ie
s
,
co
m
p
lex
co
m
p
o
n
en
t
ex
tr
ac
tio
n
an
d
co
o
r
d
i
n
ati
n
g
ar
e
r
eq
u
ir
ed
;
th
e
o
v
er
w
h
el
m
i
n
g
c
alcu
latio
n
w
ei
g
h
t
'
s
h
ar
d
to
m
e
et
th
e
p
r
er
eq
u
is
i
tes
o
f
q
u
ic
k
h
an
d
lin
g
.
K
-
s
tr
a
n
g
e
p
o
in
ts
cl
u
s
ter
i
n
g
al
g
o
r
ith
m
e
x
p
lain
ed
b
y
[
7
]
.
C
o
n
s
id
er
in
g
t
h
e
co
m
p
o
s
it
io
n
o
f
t
h
e
b
o
w
s
h
o
w
s
u
p
clea
r
l
y
,
w
e
in
itial
l
y
u
til
ize
th
e
Har
r
is
co
r
n
er
d
is
co
v
er
y
ca
lc
u
latio
n
r
ec
o
g
n
ize
t
h
e
p
o
ten
tial
b
o
w
i
n
r
e
m
o
te
d
etec
tin
g
p
ictu
r
e,
an
d
af
ter
th
at
d
i
s
s
ec
t t
h
e
ele
m
en
t
o
f
n
eig
h
b
o
r
h
o
o
d
ess
e
n
tial
n
es
s
,
to
u
n
d
er
s
tan
d
t
h
e
q
u
ick
e
x
tr
ac
tio
n
o
f
th
e
b
o
w
.
Dete
ctio
n
o
f
g
la
u
co
m
a
b
ased
o
n
co
lo
r
m
o
m
e
n
t
s
an
d
SVM
class
if
ier
u
s
i
n
g
k
m
ea
n
cl
u
s
ter
in
g
is
d
is
cu
s
s
ed
b
y
[
8
]
.
I
n
th
i
s
p
ap
er
,
Firstl
y
m
o
r
p
h
o
lo
g
ical
h
a
n
d
l
in
g
is
u
tili
ze
d
to
e
x
p
el
th
e
litt
le
d
ab
an
d
f
ill
t
h
e
m
is
s
i
n
g
p
ix
el.
Fu
r
t
h
er
m
o
r
e,
m
ak
e
a
r
o
u
n
d
f
o
r
m
at.
Ha
n
d
Geo
m
etr
y
R
ec
o
g
n
i
tio
n
b
ase
d
o
n
o
p
ti
m
ized
K
-
Me
an
s
C
lu
s
ter
i
n
g
a
n
d
Seg
m
en
tatio
n
Alg
o
r
it
h
m
is
d
escr
ib
ed
b
y
[
9
]
.
I
d
en
tif
icatio
n
o
f
c
h
ick
e
n
e
g
g
s
u
s
i
n
g
w
ater
m
ar
k
i
m
a
g
e
u
s
i
n
g
s
e
v
er
a
l
m
et
h
o
d
s
ar
e
ex
p
ec
ted
to
p
r
o
v
id
e
r
esu
lt
s
as d
esire
d
is
d
escr
ib
ed
in
[
1
0
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2502
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
9
,
No
.
1
,
J
an
u
ar
y
2
0
1
8
:
12
–
14
13
2.
P
RO
P
O
SE
D
M
E
T
H
O
D
W
e
in
tr
o
d
u
ce
d
a
n
o
v
el
tech
n
i
q
u
e
f
o
r
id
en
tify
i
n
g
s
h
ip
s
d
o
ck
ed
in
a
h
ar
b
o
r
b
y
co
m
in
g
to
th
e
Har
r
is
co
r
n
er
f
i
n
d
er
s
tr
ate
g
y
an
d
t
h
e
n
ea
r
b
y
r
e
m
ar
k
ab
le
ar
ea
e
x
a
m
i
n
atio
n
tech
n
iq
u
e.
T
h
is
ap
p
r
o
ac
h
m
a
k
es
f
u
ll
u
tili
za
t
io
n
o
f
t
h
e
i
m
p
o
r
tan
t
s
h
ar
p
-
ca
lc
u
lated
co
m
p
o
n
e
n
t
id
en
ti
f
ied
w
it
h
a
f
o
r
e
p
iece
o
f
a
s
h
ip
in
s
atel
lite
p
ic
tu
r
es.
T
h
e
tech
n
iq
u
e
ca
n
n
o
t
j
u
s
t
id
e
n
ti
f
y
a
ll
s
h
ip
tar
g
ets
d
o
ck
ed
i
n
h
ar
b
o
r
r
ap
id
l
y
an
d
ad
eq
u
atel
y
,
ad
d
itio
n
all
y
d
ec
id
e
th
e
co
u
r
s
e
o
f
th
e
s
h
ip
.
I
n
v
e
s
tig
a
tes a
f
e
w
h
ig
h
r
eso
l
u
t
io
n
s
r
e
m
o
te
d
etec
ti
n
g
p
ictu
r
e
co
n
f
ir
m
ed
th
e
v
iab
ilit
y
o
f
o
u
r
tech
n
iq
u
e.
W
ith
a
s
p
ec
if
ic
en
d
g
o
al
to
c
h
ec
k
th
e
p
r
o
p
o
s
ed
m
e
th
o
d
i
n
th
i
s
p
ap
er
,
w
e
tes
t
o
u
r
s
tr
at
eg
y
o
n
a
f
e
w
h
ig
h
r
eso
lu
tio
n
s
o
p
tical.
I
n
th
e
p
r
o
g
r
ess
io
n
o
f
id
en
ti
f
y
i
n
g
t
h
e
f
ir
s
t
p
ictu
r
e
u
tili
zi
n
g
H
ar
r
is
co
r
n
er
d
is
co
v
er
y
tec
h
n
iq
u
e,
w
e
ca
n
g
et
th
e
p
o
ten
tial b
o
w
s
o
f
b
o
ats
Arc
hite
ct
ure
Dia
g
ra
m
Fig
u
r
e
1
.
A
r
ch
itectu
r
e
Dia
g
r
a
m
T
h
e
o
u
tco
m
es
r
ep
r
esen
t
th
at
t
h
e
f
alse
aler
ts
ar
e
ex
tr
ao
r
d
in
ar
il
y
d
i
m
i
n
is
h
ed
,
an
d
th
e
b
o
w
s
o
f
b
o
ats
ar
e
d
is
tin
g
u
is
h
ed
.
I
n
an
y
ca
s
e
,
a
s
i
m
ilar
b
o
w
r
ea
cts
to
a
f
e
w
b
r
o
ch
u
r
es,
s
o
w
e
o
u
g
h
t
t
o
u
tili
ze
t
h
e
g
r
o
u
p
in
g
ca
lcu
latio
n
.
3.
DIS
CU
SS
I
O
N
R
e
m
o
te
s
e
n
s
i
n
g
i
m
a
g
e
s
h
o
w
n
in
f
i
g
u
r
e
2
ca
n
b
e
o
b
tain
ed
w
i
th
h
i
g
h
r
eso
l
u
tio
n
o
p
tical
i
m
a
g
e.
T
h
is
is
o
b
tain
ed
u
s
i
n
g
co
r
n
er
d
etec
tio
n
m
et
h
o
d
; h
er
e
d
ir
ec
tio
n
o
f
t
h
e
s
h
ip
is
ca
lc
u
lated
.
C
o
n
f
ir
m
a
tio
n
P
r
etr
ea
tm
e
n
t
I
m
ag
e
R
ap
id
l
y
ex
tr
ac
tio
n
C
lu
s
ter
i
n
g
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
N
o
ve
l Meth
o
d
fo
r
Dete
ctio
n
o
f
S
h
ip
Do
ck
e
d
I
n
Ha
r
b
o
r
I
n
Hi
g
h
R
eso
lu
tio
n
R
emo
te
S
en
s
in
g
…
(
K
.
R
a
g
h
a
vi
)
14
Fig
u
r
e
2
.
R
e
m
o
te
Se
n
s
i
n
g
I
m
a
g
e
4.
CO
NCLU
SI
O
N
T
h
e
p
ap
er
m
a
k
es
f
u
ll
u
ti
lizati
o
n
o
f
t
h
e
e
s
s
e
n
tial
s
h
ar
p
-
ca
lc
u
lated
co
m
p
o
n
en
t
id
en
t
if
ied
w
i
th
t
h
e
f
o
r
e
p
iece
o
f
a
s
h
ip
i
n
s
atelli
te
p
i
ctu
r
es,
a
n
d
a
n
o
v
el
tec
h
n
iq
u
e
is
j
o
in
in
g
t
h
e
Har
r
is
co
r
n
er
id
en
ti
f
ier
,
an
d
th
e
n
ea
r
b
y
r
e
m
ar
k
ab
le
ar
ea
ex
a
m
i
n
atio
n
i
s
p
r
o
p
o
s
ed
.
T
h
e
s
tr
ateg
y
ca
n
n
o
t
j
u
s
t
r
ap
id
l
y
a
n
d
ad
eq
u
atel
y
d
is
t
in
g
u
is
h
th
e
s
h
ip
tar
g
et
d
o
ck
ed
in
h
ar
b
o
r
s
;
ad
d
itio
n
all
y
,
d
ec
id
e
th
e
h
ea
d
in
g
o
f
th
e
b
o
ats.
I
n
v
est
ig
ates
a
f
e
w
g
r
ea
t
d
eter
m
in
at
io
n
r
e
m
o
te
d
etec
ti
n
g
p
ictu
r
es c
h
ec
k
t
h
e
ad
eq
u
ac
y
o
f
th
e
tec
h
n
iq
u
e.
RE
F
E
R
E
NC
E
S
[1
]
HU
Ju
n
-
Hu
a
,
e
t
a
l.
Re
c
o
g
n
it
i
o
n
o
f
S
h
ip
s
in
Ha
rb
o
r
i
n
Re
m
o
te
S
e
n
sin
g
Im
a
g
e
Ba
s
e
d
o
n
L
o
c
a
l
S
e
lf
-
si
m
il
a
rit
y
.
J
o
u
rn
a
l
o
f
Ima
g
e
Gr
a
p
h
ics
.
2
0
0
9
;
1
4
(
4
):5
9
1
-
5
9
7
.
[2
]
L
in
d
e
b
e
rg
T
o
n
y
.
F
e
a
tu
re
d
e
tec
ti
o
n
w
it
h
a
u
t
o
m
a
ti
c
sc
a
le se
lec
ti
o
n
.
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
C
o
mp
u
ter
Vi
sio
n
.
1
9
9
8
.
[3
]
ZHA
O
Yin
g
-
h
a
i,
e
t
a
l.
Disp
a
tch
T
a
rg
e
t
re
v
e
la
ti
o
n
S
c
h
e
me
fo
r
Op
ti
c
a
l
Rem
o
te
S
e
n
sin
g
Ima
g
e
s
.
Op
to
El
e
c
tro
n
ic
En
g
in
e
e
rin
g
.
2
0
0
8
[4
]
Yo
u
X
iao
ji
a
n
,
e
t
a
l.
A
Ne
w
M
e
th
o
d
f
o
r
S
h
ip
De
tec
ti
o
n
Ba
se
d
o
n
Fea
t
u
re
F
u
sio
n
i
n
Op
t
ica
l
Im
a
g
e
.
C
o
m
p
u
ter
En
g
in
e
e
rin
g
a
n
d
A
p
p
li
c
a
ti
o
n
s.
2
0
0
5
.
[5
]
Ha
rris
C,
S
tep
h
e
n
s M
.
A
c
o
mb
in
e
d
c
o
rn
e
r
a
n
d
e
d
g
e
d
e
tec
to
r
.
4
th
A
l
v
e
y
V
isio
n
C
o
n
f
e
re
n
c
e
.
1
9
8
8
.
[6
]
Jo
h
n
s
o
n
T
,
S
in
g
h
S
K.,
F
u
zz
y
C
stra
n
g
e
p
o
i
n
ts clu
ste
rin
g
a
l
g
o
ri
th
m
.
In
In
f
o
rm
a
ti
o
n
Co
m
m
u
n
ica
ti
o
n
a
n
d
Em
b
e
d
d
e
d
S
y
st
e
m
s (ICICE
S
).
2
0
1
6
;
1
(
5
).
[7
]
Jo
h
n
s
o
n
T
,
S
in
g
h
S
K.
K
-
str
a
n
g
e
p
o
in
ts
c
lu
ste
ri
n
g
a
lg
o
rith
m
.
I
n
Co
m
p
u
tatio
n
a
l
In
telli
g
e
n
c
e
in
D
a
ta
M
in
in
g
1
:
415
-
4
2
5
.
[8
]
S
u
re
n
d
iran
J,
S
a
ra
v
a
n
a
n
S
V
,
Km
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
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
c
lu
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
.
8
(3
):
1
6
1
3
9
-
1
6
1
4
8
.
[9
]
S
a
ra
v
a
n
a
n
N,
H
a
n
d
G
e
o
m
e
tr
y
R
e
c
o
g
n
it
io
n
b
a
se
d
o
n
o
p
t
im
ize
d
K
-
M
e
a
n
s
Clu
ste
rin
g
a
n
d
S
e
g
m
e
n
ta
ti
o
n
A
lg
o
rit
h
m
.
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
.
2
0
1
3
.
[1
0
]
Yu
d
h
a
n
a
,
A
.
,
S
u
n
a
rd
i,
S
a
if
u
ll
a
h
,
S
.
S
e
g
m
e
n
tatio
n
c
o
m
p
a
rin
g
e
g
g
s
w
a
t
e
r
m
a
r
k
in
g
i
m
a
g
e
a
n
d
o
rig
in
a
l
im
a
g
e
.
Bu
ll
e
ti
n
o
f
El
e
c
trica
l
En
g
in
e
e
rin
g
a
n
d
In
f
o
rm
a
ti
c
s
.
6
(1
)
,
p
p
.
4
7
-
5
3
,
2
0
1
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.