I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
14
,
No
.
6
,
Dec
em
b
er
20
24
,
p
p
.
6
3
3
2
~
6
3
3
8
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
14
i
6
.
pp
6
3
3
2
-
633
8
6332
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Co
mpa
riso
n of alg
o
rithms for t
he
detec
tion o
f
ma
ri
ne ves
sels
with
ma
chi
ne vis
i
o
n
J
o
s
é
Ro
dríg
uez
-
G
o
nza
les,
J
un
io
r
Niqu
in
-
J
a
im
es,
E
rnest
o
P
a
iv
a
-
P
er
edo
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
S
c
h
o
o
l
o
f
M
e
c
h
a
t
r
o
n
i
c
s
E
n
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
s
i
d
a
d
Te
c
n
o
l
ó
g
i
c
a
d
e
l
P
e
r
ú
,
L
i
ma,
P
e
r
u
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
2
1
,
2
0
2
4
R
ev
is
ed
J
u
l 2
7
,
2
0
2
4
Acc
ep
ted
Au
g
6
,
2
0
2
4
Th
e
d
e
tec
ti
o
n
o
f
m
a
rin
e
v
e
ss
e
l
s
fo
r
re
v
e
n
u
e
c
o
n
tr
o
l
h
a
s
m
a
n
y
trac
k
in
g
d
e
ficie
n
c
ies
,
wh
ich
h
a
s
re
su
lt
e
d
in
lo
ss
e
s
o
f
lo
g
isti
c
a
l
re
so
u
rc
e
s,
ti
m
e
,
a
n
d
m
o
n
e
y
.
Ho
we
v
e
r,
d
ig
it
a
l
c
a
m
e
ra
s
a
re
n
o
t
fu
ll
y
e
x
p
l
o
it
e
d
si
n
c
e
th
e
y
c
a
p
tu
re
ima
g
e
s
to
re
c
o
g
n
ize
th
e
v
e
ss
e
ls
a
n
d
g
iv
e
imm
e
d
iate
n
o
ti
c
e
to
t
h
e
c
o
n
tr
o
l
c
e
n
ter.
Th
e
a
n
a
ly
z
e
d
ima
g
e
s
g
o
t
h
ro
u
g
h
a
n
i
n
c
re
d
ib
l
y
d
e
taile
d
p
ro
c
e
ss
,
wh
ich
,
th
a
n
k
s
t
o
n
e
u
ra
l
train
i
n
g
,
a
ll
o
ws
u
s
to
re
c
o
g
n
ize
v
e
ss
e
ls
wit
h
o
u
t
fa
lse
p
o
siti
v
e
s.
To
d
o
th
is,
we
m
u
st
u
n
d
e
rsta
n
d
t
h
e
b
e
h
a
v
i
o
r
o
f
o
b
jec
t
d
e
tec
ti
o
n
;
we
m
u
st
k
n
o
w
c
rit
ica
l
iss
u
e
s
su
c
h
a
s
n
e
u
ra
l
train
in
g
,
ima
g
e
d
ig
it
iza
ti
o
n
,
ty
p
e
s
o
f
fil
ters
,
a
n
d
m
a
c
h
in
e
lea
rn
in
g
,
a
m
o
n
g
o
th
e
rs.
We
p
re
se
n
t
re
su
lt
s
b
y
c
o
m
p
a
rin
g
two
d
e
v
e
lo
p
m
e
n
t
e
n
v
iro
n
m
e
n
ts
wit
h
t
h
e
ir
c
o
rr
e
sp
o
n
d
in
g
a
lg
o
rit
h
m
s,
m
a
k
in
g
t
h
e
re
c
o
g
n
i
ti
o
n
o
f
sh
ip
s
imm
e
d
iate
ly
u
n
d
e
r
n
e
u
ra
l
train
in
g
.
I
n
c
o
n
c
l
u
sio
n
,
i
t
is
a
n
a
l
y
z
e
d
b
a
se
d
o
n
1
0
0
ima
g
e
s
t
o
m
e
a
su
re
th
e
b
o
a
t
d
e
tec
ti
o
n
c
a
p
a
b
il
it
y
b
e
twe
e
n
b
o
t
h
a
lg
o
rit
h
m
s,
th
e
re
sp
o
n
se
ti
m
e
,
a
n
d
t
h
e
e
ffe
c
ti
v
e
n
e
ss
o
f
a
n
ima
g
e
o
b
tain
e
d
b
y
a
d
ig
it
a
l
c
a
m
e
ra
.
Th
e
re
su
lt
o
b
tai
n
e
d
b
y
YO
LO
v
7
wa
s
1
0
0
%
e
ffe
c
ti
v
e
u
n
d
e
r
t
h
e
a
p
p
li
c
a
ti
o
n
o
f
p
ro
c
e
ss
in
g
tec
h
n
iq
u
e
s
b
a
se
d
o
n
n
e
u
ra
l
n
e
tw
o
rk
s
in
c
o
n
v
o
lu
t
io
n
a
l
n
e
u
ra
l
n
e
two
rk
(
CNN
)
re
g
io
n
s
c
o
m
p
a
re
d
to
M
ATLAB,
wh
ich
a
p
p
li
e
s
p
r
o
c
e
ss
in
g
m
e
tri
c
s
b
a
se
d
o
n
m
o
rp
h
o
lo
g
ica
l
ima
g
e
s,
o
b
tain
in
g
lo
w res
u
lt
s.
K
ey
w
o
r
d
s
:
Alg
o
r
ith
m
s
Dete
ctio
n
Ma
ch
in
e
lear
n
in
g
Neu
r
al
n
etwo
r
k
s
Sh
ip
s
YOL
O
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
:
E
r
n
esto
Paiv
a
-
Per
ed
o
Facu
lty
o
f
E
n
g
in
ee
r
in
g
,
Un
iv
e
r
s
id
ad
T
ec
n
o
ló
g
ica
d
el
Per
ú
1
2
5
Nata
lio
San
ch
ez
Stre
et,
San
ta
B
ea
tr
iz
Ur
b
an
izatio
n
,
C
er
ca
d
o
d
e
L
im
a
,
L
im
a,
Per
u
E
m
ail:
c2
2
3
9
5
@
u
tp
.
ed
u
.
p
e
1.
I
NT
RO
D
UCT
I
O
N
C
u
r
r
en
tly
,
tech
n
o
lo
g
y
h
as
all
o
wed
u
s
to
cr
ea
te
s
y
s
tem
s
d
esig
n
ed
to
d
etec
t
o
b
jects,
wh
ich
ca
n
b
e
o
r
ien
ted
to
e
n
v
ir
o
n
m
en
tal
m
o
n
ito
r
in
g
o
f
th
e
o
ce
an
s
[
1
]
–
[
3
]
.
L
ik
ewise,
o
b
ject
d
etec
tio
n
h
a
s
d
ev
elo
p
e
d
,
w
h
ich
allo
ws u
s
to
im
p
lem
en
t it
in
d
i
f
f
er
en
t f
ield
s
an
d
ar
ea
s
wh
er
e
m
ac
h
in
e
v
is
io
n
is
b
en
ef
icial
[
4
]
–
[
8
]
.
First,
o
n
e
o
f
th
e
ap
p
licatio
n
ar
ea
s
is
r
ela
ted
to
s
ec
u
r
ity
s
y
s
tem
s
th
r
o
u
g
h
im
ag
es
o
b
tain
ed
f
r
o
m
d
ig
ital
s
u
r
v
eillan
ce
ca
m
er
as;
th
ese
ca
m
er
as
ca
p
tu
r
e
in
f
o
r
m
atio
n
an
alo
g
ically
s
to
r
ed
an
d
p
r
o
ce
s
s
ed
with
a
m
icr
o
p
r
o
ce
s
s
o
r
,
wh
ich
tr
an
s
f
o
r
m
s
to
d
ig
ital
s
ig
n
als
to
an
aly
ze
th
em
[
9
]
.
Seco
n
d
ly
,
it
is
o
r
ien
ted
in
m
ed
icin
e
to
o
b
tain
ea
r
ly
d
iag
n
o
s
es
o
f
d
is
ea
s
es.
T
h
r
o
u
g
h
th
e
p
r
o
ce
s
s
in
g
o
f
X
-
r
ay
i
m
ag
es
an
d
co
m
p
u
ted
to
m
o
g
r
ap
h
y
(
CT
)
s
ca
n
s
,
th
e
m
ed
ical
p
r
o
f
ess
io
n
al
ca
n
m
ak
e
co
r
r
ec
t
d
ec
is
io
n
s
f
o
r
th
e
f
in
al
d
iag
n
o
s
is
[
1
0
]
.
T
h
ir
d
ly
,
we
ca
n
f
in
d
in
d
u
s
tr
ial
au
to
m
atio
n
p
r
o
ce
s
s
es
th
at
h
elp
b
etter
r
esu
lts
in
m
an
ag
i
n
g
m
a
n
u
f
ac
tu
r
in
g
c
o
n
tr
o
l,
o
b
ject
class
if
icatio
n
,
v
er
if
icatio
n
,
an
d
d
etec
tio
n
o
f
p
r
o
d
u
ct
d
ef
ec
ts
[
1
1
]
,
[
1
2
]
.
F
in
ally
,
it
is
u
s
ed
in
th
e
g
u
id
a
n
ce
o
f
au
to
n
o
m
o
u
s
v
eh
icles,
wh
er
e
ca
m
er
as
ca
p
t
u
r
e
im
a
g
es
at
d
if
f
er
en
t
an
g
les
an
d
in
r
ea
l
-
tim
e,
as
it
allo
ws
o
b
s
tacle
d
etec
tio
n
,
s
af
e
n
av
ig
atio
n
,
an
d
tr
a
f
f
ic
s
ig
n
r
ec
o
g
n
itio
n
,
am
o
n
g
o
th
er
s
[
1
3
]
,
[
1
4
]
.
T
h
e
s
h
ip
d
etec
tio
n
m
eth
o
d
s
f
r
o
m
im
ag
es
o
b
tain
e
d
f
r
o
m
d
if
f
er
en
t
s
p
atial
o
r
ien
tatio
n
s
h
av
e
b
ee
n
aim
ed
at
an
aly
zi
n
g
th
e
d
im
en
s
io
n
s
o
f
s
h
ip
s
f
o
r
d
etec
tio
n
[
5
]
,
[
8
]
.
Fo
r
ex
a
m
p
le,
we
f
o
u
n
d
a
r
ticles
d
ea
lin
g
with
s
h
ip
d
etec
tio
n
f
r
o
m
s
atellite
im
ag
es
[
7
]
.
I
n
a
d
d
itio
n
,
th
is
in
f
o
r
m
atio
n
o
n
th
e
d
etec
tio
n
an
d
tr
ac
k
in
g
o
f
o
b
jects
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
C
o
mp
a
r
is
o
n
o
f a
lg
o
r
ith
ms fo
r
th
e
d
etec
tio
n
o
f m
a
r
in
e
ve
s
s
els w
ith
…
(
Jo
s
é
R
o
d
r
íg
u
ez
-
Go
n
z
a
les
)
6333
in
th
e
m
ar
in
e
en
v
ir
o
n
m
en
t
i
s
b
ased
o
n
r
ea
l
-
tim
e
v
id
eo
r
ec
o
r
d
in
g
s
,
wh
er
e
th
e
y
wo
r
k
with
a
d
y
n
am
ic
s
u
b
tr
ac
tio
n
o
f
b
ac
k
g
r
o
u
n
d
s
;
th
e
alg
o
r
ith
m
it
u
s
es
allo
ws
it
to
d
r
aw
d
if
f
er
en
ce
s
f
r
o
m
ca
p
tu
r
ed
im
ag
es
to
f
o
c
u
s
an
d
tr
ac
k
th
e
tar
g
et
[
8
]
.
On
t
h
e
o
th
e
r
h
a
n
d
,
t
h
e
an
al
y
s
is
o
f
th
e
d
if
f
er
en
t
s
h
ip
d
etec
tio
n
m
eth
o
d
s
s
tar
ts
f
r
o
m
ae
r
ial
p
latf
o
r
m
s
,
wh
er
e
d
ig
ital
ca
m
er
as
ca
p
t
u
r
e
th
e
im
ag
es
t
o
an
aly
ze
th
em
an
d
v
alid
ate
th
e
p
r
esen
ce
o
f
s
h
ip
s
in
th
e
ar
ea
[
1
5
]
.
Fro
m
th
ese
in
v
esti
g
atio
n
s
,
it
is
co
n
clu
d
e
d
th
at
th
e
m
eth
o
d
s
u
s
ed
to
d
ete
ct
v
ess
els
ar
e
b
ased
o
n
o
r
ien
tatio
n
,
wh
ich
c
o
n
f
ir
m
s
th
e
p
r
esen
ce
o
f
s
h
ip
s
at
s
ea
,
in
ad
d
itio
n
to
m
o
n
ito
r
i
n
g
f
is
h
in
g
ar
ea
s
,
m
ar
i
n
e
d
is
p
lace
m
en
t c
o
n
tr
o
l,
an
d
s
ea
r
ch
an
d
r
escu
e
o
f
v
ess
els.
T
h
e
ca
p
tu
r
e
o
f
im
a
g
es
f
r
o
m
a
n
u
n
m
a
n
n
ed
s
u
r
f
ac
e
v
e
h
icle
p
r
esen
ts
an
o
v
er
ly
b
r
o
a
d
ar
ea
o
f
r
esear
ch
with
g
r
ea
t
p
r
o
jectio
n
s
f
o
r
th
e
f
u
tu
r
e.
De
p
en
d
in
g
o
n
th
e
p
r
o
j
ec
t's
s
co
p
e,
two
ty
p
es
o
f
im
a
g
es
ca
n
b
e
u
s
ed
to
d
etec
t
o
b
jects
in
m
ar
in
e
im
ag
es:
r
ed
,
g
r
ee
n
,
an
d
b
l
u
e
(
R
GB
)
an
d
in
f
r
ar
e
d
.
I
n
th
at
s
en
s
e,
th
e
R
GB
im
ag
es
ar
e
th
e
m
o
s
t
s
u
itab
le
f
o
r
h
a
v
in
g
th
e
m
o
s
t
d
etailed
o
b
ject
d
e
tectio
n
ar
ea
s
in
ce
it
allo
ws
t
r
ac
k
in
g
with
h
ig
h
ac
cu
r
ac
y
[
5
]
,
[
1
6
]
,
[
1
7
]
.
On
t
h
e
o
th
er
h
an
d
,
i
n
f
r
ar
e
d
im
ag
e
s
p
r
esen
t
a
b
etter
r
esp
o
n
s
e
wh
en
wo
r
k
in
g
in
d
a
r
k
o
r
clo
u
d
y
en
v
ir
o
n
m
e
n
ts
,
b
u
t
t
h
e
q
u
ality
o
f
d
etails
is
d
e
f
icien
t
[
1
8
]
,
[
1
9
]
.
Fin
ally
,
it
was
d
etec
ted
th
at
m
o
s
t
r
esear
ch
wo
r
k
s
em
p
lo
y
co
m
p
lex
m
eth
o
d
s
f
o
r
tr
ac
k
i
n
g
m
ar
in
e
v
eh
icles
with
im
ag
es
,
leav
in
g
asid
e
th
e
d
etec
tio
n
o
f
o
b
jects u
s
ed
b
y
m
o
r
p
h
o
lo
g
ical
im
ag
e
p
r
o
ce
s
s
in
g
co
m
m
an
d
s
.
Fro
m
th
is
p
r
em
is
e,
two
o
b
ject
d
etec
tio
n
m
eth
o
d
s
ar
e
co
m
p
a
r
ed
:
th
e
m
et
h
o
d
o
f
m
o
r
p
h
o
lo
g
ical
im
ag
e
p
r
o
ce
s
s
in
g
an
d
th
e
o
th
er
b
y
i
m
ag
e
d
etec
tio
n
alg
o
r
ith
m
b
as
ed
o
n
n
e
u
r
al
n
etwo
r
k
s
th
at
ca
n
b
e
tr
ain
ed
.
First,
f
ilter
in
g
,
er
o
d
i
n
g
,
an
d
b
in
ar
iz
in
g
alg
o
r
ith
m
s
ar
e
u
s
ed
in
th
e
MA
T
L
AB
p
r
o
ce
s
s
in
g
en
v
ir
o
n
m
en
t
to
h
ig
h
lig
h
t
th
e
p
r
esen
ce
o
f
a
s
h
ip
th
at
w
as
tak
en
b
y
a
d
ig
ital
ca
m
er
a
[
2
0
]
.
Seco
n
d
,
th
e
im
ag
e
ca
p
t
u
r
ed
b
y
th
e
d
ig
ital
ca
m
er
a
is
lo
ad
ed
in
to
th
e
YO
L
O
v
7
en
v
ir
o
n
m
en
t,
w
h
ich
h
as
b
ee
n
p
r
e
v
io
u
s
ly
tr
ain
ed
to
r
ec
o
g
n
ize
o
b
jects
[
2
1
]
.
Fin
ally
,
th
e
r
esu
lts
will b
e
co
m
p
ar
ed
b
ased
o
n
1
0
0
s
am
p
les p
r
o
ce
s
s
ed
b
y
b
o
th
al
g
o
r
ith
m
s
.
2.
M
E
T
H
O
D
2
.
1
.
Sh
ip det
ec
t
io
n u
s
ing
M
AT
L
AB
a
lg
o
rit
hm
s
2
.
1
.
1
.
Ca
pturing
a
n im
a
g
e
a
nd
cha
ng
ing
t
o
g
ra
y
s
ca
le
I
n
itially
,
th
e
p
r
o
g
r
a
m
en
v
i
r
o
n
m
en
t
lo
ad
s
th
e
im
ag
e,
d
ep
i
cted
in
Fig
u
r
e
1
(
a)
.
T
o
f
ac
ilit
ate
f
u
r
th
er
an
aly
s
is
,
we
tr
an
s
itio
n
th
e
im
ag
e
in
to
a
c
o
lo
r
s
ca
le,
as
d
em
o
n
s
tr
ated
in
Fig
u
r
e
1
(
b
)
.
Utilizin
g
weig
h
ted
g
r
ay
s
ca
le
en
h
an
ce
s
o
u
r
ab
ilit
y
to
s
cr
u
tin
ize
co
lo
r
lay
er
s
in
g
r
ea
ter
d
etail;
as d
ep
icted
in
Fig
u
r
es 1
(
c)
to
(
e
)
,
we
o
b
s
er
v
e
th
e
g
r
ay
s
ca
le
r
ep
r
ese
n
tatio
n
s
o
f
in
d
iv
id
u
al
co
lo
r
la
y
er
s
.
Fig
u
r
e
1
illu
s
tr
ates
th
e
im
ag
e
an
aly
s
is
b
ased
o
n
lay
e
r
s
,
f
ea
t
u
r
in
g
Fig
u
r
e
1
(
a)
s
h
o
wca
s
in
g
th
e
o
r
ig
i
n
al
R
GB
im
ag
e
d
ev
o
id
o
f
a
n
y
f
ilter
s
;
Fig
u
r
e
1
(
b
)
ex
h
ib
itin
g
th
e
im
ag
e
o
f
th
e
s
ea
b
ed
tr
an
s
f
o
r
m
e
d
in
to
weig
h
t
ed
g
r
ay
s
ca
le;
Fig
u
r
e
1
(
c)
p
o
r
t
r
ay
in
g
th
e
d
ar
k
en
ed
r
en
d
itio
n
o
f
th
e
s
ea
b
e
d
in
th
e
r
ed
lay
e
r
;
Fig
u
r
e
1
(
d
)
r
ev
ea
lin
g
th
e
s
ea
b
ed
im
a
g
e
with
lig
h
t
co
lo
r
s
r
em
o
v
ed
in
th
e
g
r
ee
n
la
y
er
; a
n
d
Fig
u
r
e
1
(
e)
d
is
p
lay
in
g
t
h
e
s
ea
b
ed
im
ag
e
with
lig
h
t c
o
lo
r
s
elim
in
ated
i
n
th
e
b
lu
e
lay
er
.
Fig
u
r
e
2
a
n
aly
ze
s
th
e
d
is
to
r
ti
o
n
b
e
h
av
io
r
co
n
ce
r
n
in
g
th
e
g
r
ay
s
ca
le.
Fig
u
r
e
2
(
a)
s
h
o
ws
t
h
e
o
r
ig
in
al
im
ag
e
in
R
GB
,
wh
ich
will
b
e
p
r
o
ce
s
s
ed
.
On
th
e
o
th
er
h
an
d
,
Fig
u
r
e
2
(
b
)
s
h
o
ws
th
e
im
ag
e'
s
h
is
to
g
r
am
co
n
v
er
ted
to
g
r
a
y
s
ca
le.
T
h
e
f
i
lter
was
ap
p
lied
f
r
o
m
0
-
2
0
0
i
n
th
e
g
r
ay
s
ca
le
a
p
p
licatio
n
.
Fin
ally
,
th
e
r
esu
lts
o
f
th
e
h
is
to
g
r
am
o
f
th
e
r
ed
lay
e
r
(
th
e
ap
p
lied
f
ilter
r
an
g
es
f
r
o
m
0
-
2
5
0
)
,
g
r
ee
n
lay
er
(
th
e
u
s
ed
f
ilter
is
r
ed
u
ce
d
f
r
o
m
0
-
1
9
0
)
,
an
d
b
lu
e
lay
er
(
f
ilter
ap
p
lied
is
r
ed
u
ce
d
f
r
o
m
0
-
1
5
0
)
ar
e
p
r
esen
ted
in
Fig
u
r
es
2
(
c)
to
(
e
)
,
r
esp
ec
tiv
ely
.
(
a)
(
b
)
(
c)
(
d
)
(
e)
Fig
u
r
e
1
.
I
m
ag
e
a
n
aly
s
is
b
ased
o
n
la
y
er
s
:
(
a)
o
r
ig
in
al
im
ag
e
with
o
u
t f
ilter
s
ap
p
lied
,
(
b
)
t
h
e
im
ag
e
o
f
t
h
e
s
ea
b
ed
ap
p
lied
to
g
r
a
y
s
ca
le
,
(
c
)
t
h
e
im
ag
e
o
f
th
e
s
ea
b
e
d
in
th
e
p
r
o
ce
s
s
o
f
d
a
r
k
en
i
n
g
,
(
d
)
t
h
e
im
ag
e
o
f
t
h
e
s
ea
b
ed
with
o
u
t th
e
lig
h
t c
o
lo
r
s
,
an
d
(
e
)
t
h
e
im
a
g
e
o
f
t
h
e
s
ea
b
ed
with
o
u
t lig
h
t c
o
lo
r
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
6
3
3
2
-
6
3
3
8
6334
(
a)
(
b
)
(
c)
(
d
)
(
e)
Fig
u
r
e
2
.
R
ep
r
esen
tatio
n
wh
en
ap
p
lied
to
g
r
ay
s
ca
le:
(
a)
o
r
ig
i
n
al
im
ag
e,
(
b
)
g
r
ay
weig
h
te
d
,
(
c)
r
ed
ca
p
e,
(
d
)
g
r
ee
n
ca
p
e
,
an
d
(
e)
b
lu
e
ca
p
e
2
.
1
.
3
.
I
m
a
g
e
t
hresh
o
ldi
ng
T
h
e
o
r
ig
in
al
im
a
g
e
u
n
d
e
r
g
o
es
g
r
ay
s
ca
le
f
ilter
in
g
,
ap
p
l
y
in
g
a
th
r
esh
o
ld
wh
er
e
g
r
ay
t
o
n
es
b
elo
w
6
0
ar
e
elim
in
ated
,
r
em
o
v
in
g
p
i
x
els
ex
ce
ed
in
g
th
is
th
r
esh
o
l
d
.
Fig
u
r
e
3
illu
s
tr
ates
th
e
o
u
tco
m
es
o
f
th
ese
p
r
o
ce
d
u
r
es
alo
n
g
s
id
e
t
h
e
eli
m
in
atio
n
o
f
n
o
n
-
o
b
ject
p
ix
el
s
.
I
n
Fig
u
r
e
3
(
a)
,
we
o
b
s
er
v
e
th
e
o
r
ig
i
n
al
im
ag
e
ca
p
tu
r
ed
b
y
th
e
d
ig
ital
ca
m
er
a
in
R
GB
co
lo
r
s
.
Fo
llo
win
g
th
i
s
,
in
Fig
u
r
e
3
(
b
)
,
th
e
a
p
p
lied
lay
er
s
h
o
wca
s
es
th
e
im
ag
e
co
n
v
er
te
d
to
g
r
ay
s
ca
le.
Du
r
in
g
th
is
co
n
v
er
s
io
n
p
r
o
c
ess
,
a
th
r
esh
o
ld
o
f
6
0
is
s
e
t
f
o
r
en
h
an
ce
d
n
o
is
e
ex
tr
ac
tio
n
,
as
d
ep
icted
in
Fig
u
r
e
3
(
c)
.
T
h
e
r
esu
ltin
g
im
ag
e
s
ar
e
p
r
esen
ted
to
d
em
o
n
s
tr
at
e
th
e
p
r
o
g
r
ess
io
n
o
f
im
ag
e
th
r
esh
o
ld
i
n
g
.
(
a)
(
b
)
(
c)
Fig
u
r
e
3
.
I
m
ag
e
th
r
esh
o
ld
in
g
:
(
a)
n
o
f
ilter
s
ap
p
lied
,
(
b
)
i
m
a
g
e
with
th
e
f
ilter
ap
p
lied
to
g
r
a
y
s
ca
le
,
an
d
(
c)
i
m
ag
e
u
s
ed
with
th
e
th
r
esh
o
ld
o
f
6
0
2
.
1
.
4
.
O
bje
ct
f
ilte
r
T
h
e
im
ag
e
h
ar
b
o
r
s
ex
te
r
n
al
n
o
is
es
r
eq
u
ir
in
g
r
em
o
v
al
th
r
o
u
g
h
a
n
o
is
e
ex
tr
ac
tio
n
p
r
o
ce
s
s
b
ased
o
n
a
p
r
ed
eter
m
in
e
d
th
r
esh
o
l
d
.
I
n
Fig
u
r
e
4
,
it
is
cr
u
cial
to
en
s
u
r
e
a
clea
n
p
r
o
ce
s
s
to
m
in
im
ize
th
e
r
is
k
o
f
f
alse
p
o
s
itiv
es
d
u
r
in
g
d
etec
tio
n
.
Fi
g
u
r
e
4
(
a
)
illu
s
tr
ates
th
e
in
itia
l
s
tag
e
o
f
n
o
is
e
ex
tr
ac
tio
n
,
k
n
o
wn
as
o
p
en
in
g
,
wh
er
e
n
o
is
e
a
n
aly
s
is
an
d
e
x
tr
ac
tio
n
o
c
cu
r
.
Su
b
s
eq
u
en
tl
y
,
in
Fig
u
r
e
4
(
b
)
,
lab
eled
e
x
tr
ac
tio
n
,
th
e
f
in
al
elim
in
atio
n
o
f
n
o
is
e
o
r
im
p
u
r
ities
is
ex
ec
u
ted
to
f
ac
ilit
ate
ac
cu
r
ate
v
ess
el
d
etec
tio
n
.
Fig
u
r
e
4
d
ep
icts
th
e
s
eq
u
en
tial
s
tep
s
o
f
th
e
n
o
is
e
clea
n
in
g
p
r
o
ce
s
s
,
em
p
h
asizi
n
g
th
e
im
p
o
r
ta
n
ce
o
f
m
eticu
lo
u
s
ex
ec
u
tio
n
to
p
r
ep
ar
e
f
o
r
v
ess
el
s
u
r
v
ey
ef
f
ic
ien
tly
.
(
a)
(
b
)
Fig
u
r
e
4
.
No
is
e
clea
n
in
g
p
r
o
c
ess
:
(
a)
n
o
is
e
an
aly
s
is
an
d
ex
tr
ac
tio
n
an
d
(
b
)
f
in
al
p
r
e
p
ar
atio
n
f
o
r
v
ess
el
s
u
r
v
ey
2
.
1
.
5
.
Rec
o
g
nitio
n o
f
t
he
s
hip
T
h
e
im
ag
e
tr
ea
ted
b
y
f
ilter
s
r
ec
o
g
n
izes
th
e
v
ess
el.
T
h
e
id
en
tific
atio
n
p
r
o
ce
s
s
was
n
o
is
e
ex
tr
ac
tio
n
s
.
Du
r
in
g
th
e
p
r
o
ce
s
s
,
a
b
lu
e
r
ec
tan
g
le
was
estab
li
s
h
ed
,
as
s
h
o
wn
in
Fig
u
r
e
5
,
wh
er
e
th
e
tar
g
et
to
b
e
id
en
tifie
d
,
in
th
is
ca
s
e,
th
e
s
h
ip
,
is
h
ig
h
li
g
h
ted
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
C
o
mp
a
r
is
o
n
o
f a
lg
o
r
ith
ms fo
r
th
e
d
etec
tio
n
o
f m
a
r
in
e
ve
s
s
els w
ith
…
(
Jo
s
é
R
o
d
r
íg
u
ez
-
Go
n
z
a
les
)
6335
Fig
u
r
e
5
.
Vess
el
s
u
r
v
ey
r
esu
lt
2
.
2
.
Vess
el
det
ec
t
io
n us
ing
t
h
e
YO
L
O
v
7
a
lg
o
ri
t
hm
2
.
2
.
1
.
Alg
o
rit
hm
t
ra
ini
ng
T
o
tr
ain
an
alg
o
r
ith
m
in
YOL
O
v
7
,
a
d
atab
ase
o
f
at
least
5
0
0
im
ag
es
f
o
r
tr
ain
in
g
an
d
th
eir
r
esp
ec
tiv
e
lab
els
o
f
th
e
o
b
ject
to
b
e
d
etec
ted
is
n
ec
ess
ar
y
.
Su
b
s
eq
u
en
tly
,
th
e
lear
n
in
g
f
r
am
ewo
r
k
an
d
th
e
n
u
m
b
er
o
f
tr
ain
in
g
ep
o
c
h
s
ar
e
d
ef
in
e
d
,
a
n
d
th
e
r
esu
lt
o
f
ex
ec
u
tin
g
th
e
tr
ain
in
g
co
d
e
will
n
o
t
d
eliv
e
r
a
n
eu
r
al
n
etwo
r
k
ca
p
ab
le
o
f
r
ec
o
g
n
izin
g
o
b
ject
s
lik
e
th
o
s
e
o
f
th
e
lab
els
o
f
th
e
tr
ain
in
g
im
a
g
es
[
2
1
]
,
[
2
2
]
.
S
u
b
s
eq
u
en
tly
,
in
th
e
test
p
h
ase,
1
0
0
im
a
g
es a
r
e
s
et
f
o
r
p
r
o
ce
s
s
in
g
an
d
s
h
ip
d
etec
ti
o
n
,
o
b
tain
ed
o
u
t o
f
th
e
5
0
0
tr
a
in
in
g
im
ag
es.
2
.
2
.
2
.
I
m
a
g
e
inp
ut
T
o
ef
f
ec
tiv
ely
u
tili
ze
th
e
YO
L
O
v
7
alg
o
r
ith
m
,
it
i
s
im
p
er
ativ
e
to
u
n
d
er
s
tan
d
its
f
u
n
ctio
n
ality
as
a
n
eu
r
al
n
etwo
r
k
s
p
ec
ializin
g
in
b
o
u
n
d
in
g
b
o
x
p
r
ed
ictio
n
s
.
Ob
ject
d
etec
tio
n
th
r
o
u
g
h
YOL
O
in
v
o
lv
es
lev
er
ag
in
g
n
eu
r
al
n
etwo
r
k
ar
ch
itectu
r
es
th
at
em
p
lo
y
lear
n
ed
m
o
d
els
f
o
r
d
etec
tio
n
task
s
[
2
3
]
,
[
2
4
]
.
T
h
ese
m
o
d
els,
in
clu
d
i
n
g
Fas
ter
R
-
C
NN
an
d
Ma
s
k
R
-
C
NN,
ex
ce
l
in
lo
ca
tin
g
m
u
ltip
le
o
b
jects
with
in
im
ag
es,
o
f
ten
g
en
er
atin
g
p
i
x
el
-
lev
el
m
ask
s
[
2
5
]
.
Ho
wev
er
,
ch
allen
g
es
s
u
ch
as
n
o
is
e
an
d
class
im
b
ala
n
ce
s
p
er
s
is
t
in
th
is
p
r
o
ce
s
s
.
T
h
e
ch
o
s
en
en
v
ir
o
n
m
en
t
f
o
r
im
p
lem
en
tin
g
th
e
alg
o
r
ith
m
is
C
ONDA
,
a
p
r
o
g
r
am
m
in
g
p
latf
o
r
m
f
ac
ilit
atin
g
in
ter
ac
tio
n
with
P
y
th
o
n
f
o
r
ex
ec
u
tin
g
o
b
ject
r
ec
o
g
n
itio
n
task
s
.
Pre
ce
d
in
g
i
ts
d
ep
lo
y
m
en
t,
th
e
alg
o
r
ith
m
u
n
d
er
g
o
es
tr
ain
in
g
b
ased
o
n
s
h
i
p
lab
els
ass
ig
n
ed
with
in
th
e
im
ag
e
d
ataset
[
2
6
]
.
Fig
u
r
e
6
d
elin
ea
tes
th
e
s
eq
u
en
tial
s
tep
s
in
tr
ai
n
in
g
th
e
n
eu
r
al
n
etwo
r
k
an
d
d
ete
ctin
g
o
b
jects.
I
t
o
u
tlin
es
k
ey
c
o
m
p
o
n
en
ts
s
u
ch
as
th
e
d
ataset
f
o
r
tr
ain
in
g
im
a
g
es,
th
e
C
ONDA
p
r
o
g
r
am
m
in
g
en
v
ir
o
n
m
en
t
f
o
r
alg
o
r
ith
m
d
ev
elo
p
m
e
n
t,
th
e
YOL
O
v
7
n
eu
r
al
n
etwo
r
k
v
er
s
io
n
ap
p
lied
,
th
e
d
ir
e
ct
im
ag
e
in
p
u
t
ca
p
tu
r
ed
b
y
a
d
i
g
ital
ca
m
er
a,
th
e
t
r
ain
in
g
p
h
ase
f
o
r
t
h
e
n
eu
r
al
n
etwo
r
k
,
an
d
th
e
e
v
en
tu
al
d
etec
tio
n
r
es
u
lts
.
2
.
2
.
3
.
E
x
ec
utio
n o
f
t
he
det
ec
t
io
n a
lg
o
rit
hm
B
ef
o
r
e
in
itializin
g
th
e
s
to
p
p
in
g
p
r
o
ce
s
s
,
y
o
u
m
u
s
t
en
ter
th
e
ad
d
r
ess
o
f
th
e
im
ag
e
wh
er
e
y
o
u
wan
t
to
d
etec
t
th
e
o
b
ject.
W
ith
in
a
lo
ca
l
en
v
ir
o
n
m
en
t,
we
m
u
s
t
h
a
v
e
a
p
r
e
-
tr
ain
ed
m
o
d
el
s
in
ce
th
e
d
ata
s
et
m
u
s
t
b
e
r
elate
d
to
v
ess
els
f
o
r
d
etec
tio
n
.
Fin
ally
,
a
f
ter
r
u
n
n
i
n
g
th
e
alg
o
r
ith
m
,
th
e
r
esu
ltin
g
im
ag
e
will
lo
o
k
lik
e
Fig
u
r
e
7
,
wh
e
r
e
a
b
o
x
d
e
m
ar
c
ates th
e
v
ess
el.
D
A
T
A
S
E
T
C
O
N
D
A
Y
O
L
O
V
7
D
IR
E
C
T
IMA
G
E
T
O
P
R
O
C
E
S
S
T
R
A
IN
IN
G
D
E
T
E
C
T
IO
N
Fig
u
r
e
6
.
Pro
ce
s
s
d
iag
r
am
f
o
r
u
s
in
g
YOL
O
Fig
u
r
e
7
.
R
esu
lt o
f
v
ess
el
s
u
r
v
ey
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
6
3
3
2
-
6
3
3
8
6336
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
A
co
m
p
a
r
is
o
n
o
f
t
h
e
two
m
e
th
o
d
s
f
o
r
o
b
ject
d
etec
tio
n
wa
s
ca
r
r
ied
o
u
t,
an
d
th
e
o
b
jectiv
e
was
to
d
eter
m
in
e
th
e
ac
cu
r
ac
y
an
d
r
ec
o
g
n
itio
n
tim
e.
T
h
e
ev
al
u
a
tio
n
h
as
led
to
d
if
f
er
en
t
r
esu
lts
;
b
o
th
tim
es
ar
e
co
n
tr
ad
icto
r
y
co
n
c
er
n
in
g
th
e
d
etec
ted
,
with
a
lo
n
g
er
wai
tin
g
tim
e
in
r
ec
o
g
n
itio
n
b
u
t
with
a
s
u
cc
ess
f
u
l
o
u
tco
m
e.
T
h
e
p
a
r
am
eter
s
to
b
e
co
n
s
id
er
ed
f
o
r
t
h
e
ev
alu
atio
n
ar
e
o
b
ject
d
etec
tio
n
tim
e
a
n
d
d
etec
ted
ar
ea
[
2
7
]
.
3
.
1
.
O
bje
c
t
det
ec
t
io
n t
i
m
e
R
esp
o
n
s
e
tim
e
is
a
cr
u
cial
p
ar
am
eter
in
d
etec
tio
n
s
y
s
tem
s
,
r
ef
lectin
g
th
e
alg
o
r
ith
m
'
s
ef
f
icien
cy
.
Ho
wev
er
,
th
is
p
ar
am
eter
'
s
s
ig
n
if
ican
ce
is
m
ag
n
if
ied
wh
e
n
a
cc
o
m
p
an
ied
b
y
p
r
ec
is
e
d
etec
tio
n
s
,
r
en
d
e
r
in
g
it
a
r
eliab
le
r
ef
er
en
ce
p
o
in
t.
T
o
a
s
s
es
s
r
esp
o
n
s
e
tim
es
ac
cu
r
ate
ly
,
an
ev
alu
atio
n
was
co
n
d
u
c
ted
o
n
1
0
0
im
ag
es
d
is
tin
ct
f
r
o
m
th
e
5
0
0
u
s
ed
f
o
r
tr
ain
in
g
th
e
n
etwo
r
k
.
Fig
u
r
e
8
co
m
p
ar
es
th
e
im
ag
e
p
r
o
ce
s
s
in
g
tim
es
b
etwe
en
th
e
two
alg
o
r
ith
m
s
.
T
h
e
d
ep
ict
ed
v
alu
es
p
er
tain
to
th
e
p
r
o
ce
s
s
in
g
tim
e
s
o
f
t
h
ese
1
0
0
d
is
tin
ct
im
ag
es
.
Sp
ec
if
ically
,
“
T
im
e
M
(
s
)
”
d
en
o
tes
th
e
r
esp
o
n
s
e
tim
e
with
in
th
e
MA
T
L
AB
en
v
ir
o
n
m
e
n
t,
wh
ile
“
T
im
e
Y(
s
)
”
r
ep
r
esen
ts
th
e
r
esp
o
n
s
e
tim
e
with
in
th
e
C
ONDA
en
v
ir
o
n
m
en
t
em
p
lo
y
i
n
g
t
h
e
Y
OL
O
n
eu
r
al
n
etwo
r
k
.
No
tab
l
y
,
wh
ile
o
n
e
alg
o
r
ith
m
m
ay
ex
h
ib
it
lo
n
g
er
waitin
g
tim
es,
th
e
d
etec
tio
n
ac
cu
r
ac
y
ten
d
s
to
b
e
h
ig
h
er
,
alig
n
in
g
m
o
r
e
clo
s
ely
with
th
e
d
esire
d
tar
g
ets
[
2
8
]
.
T
h
ese
r
esu
lts
u
n
d
er
s
co
r
e
th
e
tr
ad
e
-
o
f
f
s
b
etwe
e
n
p
r
o
ce
s
s
in
g
s
p
ee
d
an
d
d
etec
tio
n
ac
cu
r
ac
y
,
h
ig
h
lig
h
tin
g
th
e
co
m
p
lex
ities
in
h
er
en
t i
n
alg
o
r
ith
m
ic
p
er
f
o
r
m
an
ce
e
v
alu
atio
n
[
2
9
]
.
Fig
u
r
e
8
.
C
o
m
p
a
r
is
o
n
o
f
im
ag
e
p
r
o
ce
s
s
in
g
tim
e
3
.
2
.
Det
ec
t
ed
a
re
a
T
o
d
eter
m
in
e
t
h
e
c
o
r
r
ec
tn
ess
o
f
im
a
g
e
d
etec
tio
n
,
a
cr
iter
i
o
n
is
estab
lis
h
ed
wh
e
r
e
h
ig
h
lig
h
tin
g
o
v
er
h
alf
o
f
th
e
o
b
jects
is
d
ee
m
ed
s
u
cc
ess
f
u
l
d
etec
tio
n
(
ass
ig
n
ed
a
v
alu
e
o
f
1
)
wh
ile
h
ig
h
lig
h
ti
n
g
less
th
an
h
alf
is
co
n
s
id
er
ed
u
n
s
u
cc
ess
f
u
l
(
ass
ig
n
ed
a
v
alu
e
o
f
0
)
.
Fig
u
r
e
9
c
o
m
p
ar
es
th
e
d
etec
tio
n
e
f
f
ec
tiv
en
ess
b
etwe
en
two
alg
o
r
ith
m
s
b
ased
o
n
ev
alu
atio
n
s
co
n
d
u
cte
d
o
n
1
0
0
im
ag
es d
is
tin
ct
f
r
o
m
th
e
tr
ain
in
g
d
atase
t.
Fig
u
r
e
9
.
C
o
m
p
a
r
is
o
n
o
f
d
etec
tio
n
ef
f
ec
tiv
en
ess
o
f
t
h
e
two
a
lg
o
r
ith
m
s
(
s)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
C
o
mp
a
r
is
o
n
o
f a
lg
o
r
ith
ms fo
r
th
e
d
etec
tio
n
o
f m
a
r
in
e
ve
s
s
els w
ith
…
(
Jo
s
é
R
o
d
r
íg
u
ez
-
Go
n
z
a
les
)
6337
I
n
Fig
u
r
e
9
,
“
E
f
f
ec
ti
v
en
ess
M
”
r
ep
r
esen
ts
th
e
r
esp
o
n
s
e
in
th
e
MA
T
L
AB
en
v
ir
o
n
m
e
n
t,
wh
ile
“
E
f
f
ec
tiv
en
ess
Y
”
s
ig
n
if
ies
t
h
e
r
esp
o
n
s
e
in
th
e
C
ONDA
en
v
ir
o
n
m
en
t
u
tili
zin
g
th
e
YOL
O
n
eu
r
al
n
etwo
r
k
.
T
h
e
d
is
p
lay
ed
v
alu
es
in
d
icate
th
e
ef
f
ec
tiv
en
ess
o
f
s
h
ip
d
etec
tio
n
f
o
r
ea
ch
alg
o
r
ith
m
.
R
em
ar
k
ab
ly
,
th
e
r
esu
lts
d
em
o
n
s
tr
ate
th
at
th
e
YOL
O
alg
o
r
ith
m
o
u
tp
er
f
o
r
m
s
t
h
e
MA
T
L
AB
alg
o
r
ith
m
r
eg
ar
d
in
g
d
etec
tio
n
ef
f
ec
tiv
en
ess
.
T
h
is
o
b
s
er
v
atio
n
u
n
d
er
s
co
r
es
th
e
s
u
p
er
io
r
ity
o
f
th
e
YOL
O
alg
o
r
ith
m
in
a
cc
u
r
ately
d
etec
tin
g
s
h
ip
s
with
in
im
ag
es.
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
ad
d
r
ess
ed
th
e
p
r
o
b
lem
o
f
d
etec
tin
g
m
a
r
in
e
v
es
s
els
f
o
r
in
co
m
e
co
n
tr
o
l,
h
i
g
h
l
ig
h
tin
g
th
e
d
ef
icien
cies
in
ex
is
tin
g
m
o
n
i
to
r
in
g
m
eth
o
d
s
.
A
s
o
lu
tio
n
was
p
r
o
p
o
s
ed
b
ased
o
n
th
e
u
n
d
er
u
tili
ze
d
u
s
e
o
f
d
ig
ital
ca
m
er
as
an
d
th
e
u
s
e
o
f
n
eu
r
al
n
etwo
r
k
s
.
C
o
m
p
ar
is
o
n
b
etwe
en
th
e
two
d
ev
elo
p
m
en
t
en
v
ir
o
n
m
e
n
ts
an
d
th
eir
r
esp
ec
tiv
e
alg
o
r
ith
m
s
r
ev
ea
led
th
at
th
e
YOL
O
v
7
alg
o
r
ith
m
,
wh
ic
h
in
co
r
p
o
r
a
tes
n
eu
r
al
n
etwo
r
k
p
r
o
ce
s
s
in
g
,
o
u
tp
er
f
o
r
m
s
MA
T
L
AB
b
ased
o
n
m
o
r
p
h
o
lo
g
ical
im
ag
e
p
r
o
ce
s
s
in
g
m
etr
ic
s
.
T
h
e
e
v
alu
atio
n
f
o
cu
s
ed
o
n
o
b
ject
d
etec
tio
n
ti
m
e
an
d
d
etec
ted
ar
ea
as c
r
itica
l p
ar
am
eter
s
.
Ob
ject
d
etec
tio
n
tim
e
an
aly
s
i
s
s
h
o
wed
lo
n
g
er
wait
tim
es
in
th
e
YOL
O
alg
o
r
ith
m
b
u
t
with
m
o
r
e
ac
cu
r
ate
an
d
s
u
cc
ess
f
u
l
d
etec
tio
n
r
esu
lts
.
Desp
ite
th
e
ex
ten
d
ed
p
r
o
ce
s
s
in
g
tim
es,
th
e
YOL
O
alg
o
r
ith
m
o
u
tp
er
f
o
r
m
s
MA
T
L
AB
in
ter
m
s
o
f
ef
f
icien
cy
a
n
d
ac
c
u
r
ac
y
in
o
b
ject
d
etec
tio
n
.
T
h
e
ev
al
u
atio
n
o
f
th
e
d
etec
ted
ar
ea
h
ig
h
lig
h
te
d
th
e
s
u
p
er
io
r
ity
o
f
th
e
YOL
O
alg
o
r
ith
m
co
m
p
ar
ed
to
MA
T
L
AB
.
T
h
e
ef
f
ec
tiv
en
ess
o
f
v
ess
el
d
etec
tio
n
was
m
o
r
e
p
r
o
m
in
en
t
in
th
e
YOL
O
alg
o
r
ith
m
,
p
r
o
v
id
in
g
m
o
r
e
s
atis
f
ac
to
r
y
an
d
ac
cu
r
ate
r
esu
lts
in
m
o
r
e
th
an
5
0
% o
f
th
e
ca
s
es e
v
alu
ated
.
I
n
s
u
m
m
ar
y
,
th
is
s
tu
d
y
d
em
o
n
s
tr
ates
th
e
ef
f
ec
tiv
e
n
ess
o
f
th
e
YOL
O
v
7
alg
o
r
ith
m
im
p
lem
en
tatio
n
in
m
ar
in
e
v
ess
el
d
etec
tio
n
co
m
p
ar
ed
to
MA
T
L
AB
.
Desp
ite
th
e
lo
n
g
e
r
p
r
o
ce
s
s
in
g
tim
es,
th
e
YOL
O
alg
o
r
ith
m
o
f
f
er
s
m
o
r
e
ac
cu
r
ate
an
d
e
f
f
i
cien
t
r
esu
lts
in
ter
m
s
o
f
o
b
je
ct
d
etec
tio
n
.
T
h
is
wo
r
k
lay
s
th
e
f
o
u
n
d
atio
n
f
o
r
im
p
r
o
v
in
g
r
e
v
en
u
e
c
o
n
tr
o
l t
h
r
o
u
g
h
a
d
v
an
ce
d
v
ess
el
tr
ac
k
in
g
tech
n
o
lo
g
ies.
RE
F
E
R
E
NC
E
S
[
1
]
J.
W
o
o
,
C
.
Y
u
,
a
n
d
N
.
K
i
m,
“
D
e
e
p
r
e
i
n
f
o
r
c
e
me
n
t
l
e
a
r
n
i
n
g
-
b
a
se
d
c
o
n
t
r
o
l
l
e
r
f
o
r
p
a
t
h
f
o
l
l
o
w
i
n
g
o
f
a
n
u
n
m
a
n
n
e
d
su
r
f
a
c
e
v
e
h
i
c
l
e
,
”
O
c
e
a
n
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
8
3
,
p
p
.
1
5
5
–
1
6
6
,
J
u
l
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
o
c
e
a
n
e
n
g
.
2
0
1
9
.
0
4
.
0
9
9
.
[
2
]
Q
.
C
a
i
,
Q
.
W
a
n
g
,
Y
.
Zh
a
n
g
,
Z
.
H
e
,
a
n
d
Y
.
Z
h
a
n
g
,
“
LWD
N
e
t
-
a
l
i
g
h
t
w
e
i
g
h
t
w
a
t
e
r
-
o
b
st
a
c
l
e
s
d
e
t
e
c
t
i
o
n
n
e
t
w
o
r
k
f
o
r
u
n
ma
n
n
e
d
su
r
f
a
c
e
v
e
h
i
c
l
e
s
,
”
Ro
b
o
t
i
c
s
a
n
d
A
u
t
o
n
o
m
o
u
s
S
y
s
t
e
m
s
,
v
o
l
.
1
6
6
,
A
u
g
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
o
b
o
t
.
2
0
2
3
.
1
0
4
4
5
3
.
[
3
]
K
.
F
.
H
a
n
se
n
,
L.
Y
a
o
,
K
.
R
e
n
,
S
.
W
a
n
g
,
W
.
L
i
u
,
a
n
d
Y
.
L
i
u
,
“
I
mag
e
s
e
g
men
t
a
t
i
o
n
i
n
m
a
r
i
n
e
e
n
v
i
r
o
n
m
e
n
t
s
u
s
i
n
g
c
o
n
v
o
l
u
t
i
o
n
a
l
LSTM
f
o
r
t
e
m
p
o
r
a
l
c
o
n
t
e
x
t
,
”
Ap
p
l
i
e
d
O
c
e
a
n
Re
s
e
a
rc
h
,
v
o
l
.
1
3
9
,
O
c
t
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
p
o
r
.
2
0
2
3
.
1
0
3
7
0
9
.
[
4
]
Q
.
Y
u
a
n
d
Y
.
S
u
,
“
Lo
c
a
l
d
e
f
o
g
g
i
n
g
a
l
g
o
r
i
t
h
m
f
o
r
t
h
e
f
i
r
st
f
r
a
m
e
i
m
a
g
e
o
f
u
n
ma
n
n
e
d
su
r
f
a
c
e
v
e
h
i
c
l
e
s
b
a
se
d
o
n
a
r
a
d
a
r
-
p
h
o
t
o
e
l
e
c
t
r
i
c
s
y
s
t
e
m,
”
J
o
u
r
n
a
l
o
f
M
a
r
i
n
e
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
0
,
n
o
.
7
,
J
u
l
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
j
mse
1
0
0
7
0
9
6
9
.
[
5
]
Z.
L
i
u
,
Y
.
Z
h
a
n
g
,
X
.
Y
u
,
a
n
d
C
.
Y
u
a
n
,
“
U
n
m
a
n
n
e
d
su
r
f
a
c
e
v
e
h
i
c
l
e
s
:
a
n
o
v
e
r
v
i
e
w
o
f
d
e
v
e
l
o
p
m
e
n
t
s
a
n
d
c
h
a
l
l
e
n
g
e
s,”
A
n
n
u
a
l
Re
v
i
e
w
s i
n
C
o
n
t
ro
l
,
v
o
l
.
4
1
,
p
p
.
7
1
–
9
3
,
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
r
c
o
n
t
r
o
l
.
2
0
1
6
.
0
4
.
0
1
8
.
[
6
]
H
.
K
i
m,
D
.
K
i
m
,
a
n
d
S
.
-
M
.
L
e
e
,
“
M
a
r
i
n
e
o
b
j
e
c
t
se
g
m
e
n
t
a
t
i
o
n
a
n
d
t
r
a
c
k
i
n
g
b
y
l
e
a
r
n
i
n
g
mar
i
n
e
r
a
d
a
r
i
ma
g
e
s
f
o
r
a
u
t
o
n
o
m
o
u
s
su
r
f
a
c
e
v
e
h
i
c
l
e
s
,
”
I
EEE
S
e
n
s
o
rs
J
o
u
r
n
a
l
,
v
o
l
.
2
3
,
n
o
.
9
,
p
p
.
1
0
0
6
2
–
1
0
0
7
0
,
M
a
y
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
JS
EN
.
2
0
2
3
.
3
2
5
9
4
7
1
.
[
7
]
D
.
K
.
P
r
a
sa
d
,
D
.
R
a
j
a
n
,
L
.
R
a
c
h
m
a
w
a
t
i
,
E
.
R
a
j
a
b
a
l
l
y
,
a
n
d
C
.
Q
u
e
k
,
“
V
i
d
e
o
p
r
o
c
e
ss
i
n
g
f
r
o
m
e
l
e
c
t
r
o
-
o
p
t
i
c
a
l
s
e
n
s
o
r
s
f
o
r
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
i
n
a
m
a
r
i
t
i
me
e
n
v
i
r
o
n
m
e
n
t
:
a
s
u
r
v
e
y
,
”
I
E
EE
T
ra
n
s
a
c
t
i
o
n
s
o
n
I
n
t
e
l
l
i
g
e
n
t
T
r
a
n
sp
o
rt
a
t
i
o
n
S
y
s
t
e
m
s
,
v
o
l
.
1
8
,
n
o
.
8
,
p
p
.
1
9
9
3
–
2
0
1
6
,
A
u
g
.
2
0
1
7
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
TS.2
0
1
6
.
2
6
3
4
5
8
0
.
[
8
]
U
.
K
a
n
j
i
r
,
H
.
G
r
e
i
d
a
n
u
s,
a
n
d
K
.
O
št
i
r
,
“
V
e
sse
l
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
f
r
o
m
sp
a
c
e
b
o
r
n
e
o
p
t
i
c
a
l
i
m
a
g
e
s:
a
l
i
t
e
r
a
t
u
r
e
su
r
v
e
y
,
”
Re
m
o
t
e
S
e
n
s
i
n
g
o
f
E
n
v
i
ro
n
m
e
n
t
,
v
o
l
.
2
0
7
,
p
p
.
1
–
2
6
,
M
a
r
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
se
.
2
0
1
7
.
1
2
.
0
3
3
.
[
9
]
Z.
H
u
,
J
.
Z
h
o
u
,
a
n
d
E
.
Z
h
a
n
g
,
“
I
mp
r
o
v
i
n
g
t
r
a
f
f
i
c
s
a
f
e
t
y
t
h
r
o
u
g
h
t
r
a
f
f
i
c
a
c
c
i
d
e
n
t
r
i
s
k
a
ssessm
e
n
t
,
”
S
u
st
a
i
n
a
b
i
l
i
t
y
,
v
o
l
.
1
5
,
n
o
.
4
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
u
1
5
0
4
3
7
4
8
.
[
1
0
]
R
.
H
.
M
o
ss
e
t
a
l
.
,
“
S
k
i
n
c
a
n
c
e
r
r
e
c
o
g
n
i
t
i
o
n
b
y
c
o
m
p
u
t
e
r
v
i
si
o
n
,
”
C
o
m
p
u
t
e
ri
ze
d
M
e
d
i
c
a
l
I
m
a
g
i
n
g
a
n
d
G
ra
p
h
i
c
s
,
v
o
l
.
1
3
,
n
o
.
1
,
p
p
.
3
1
–
3
6
,
Ja
n
.
1
9
8
9
,
d
o
i
:
1
0
.
1
0
1
6
/
0
8
9
5
-
6
1
1
1
(
8
9
)
9
0
0
7
6
-
1.
[
1
1
]
Y
.
Ta
n
g
e
t
a
l
.
,
“
O
p
t
i
m
i
z
a
t
i
o
n
st
r
a
t
e
g
i
e
s
o
f
f
r
u
i
t
d
e
t
e
c
t
i
o
n
t
o
o
v
e
r
c
o
me
t
h
e
c
h
a
l
l
e
n
g
e
o
f
u
n
st
r
u
c
t
u
r
e
d
b
a
c
k
g
r
o
u
n
d
i
n
f
i
e
l
d
o
r
c
h
a
r
d
e
n
v
i
r
o
n
m
e
n
t
:
a
r
e
v
i
e
w
,
”
Pre
c
i
si
o
n
Ag
ri
c
u
l
t
u
r
e
,
v
o
l
.
2
4
,
n
o
.
4
,
p
p
.
1
1
8
3
–
1
2
1
9
,
A
u
g
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
1
1
1
9
-
023
-
1
0
0
0
9
-
9.
[
1
2
]
T.
L
u
o
e
t
a
l
.
,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
w
e
e
d
s
e
e
d
s
b
a
s
e
d
o
n
v
i
s
u
a
l
i
ma
g
e
s
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
,
”
I
n
f
o
rm
a
t
i
o
n
Pro
c
e
ss
i
n
g
i
n
Ag
r
i
c
u
l
t
u
re
,
v
o
l
.
1
0
,
n
o
.
1
,
p
p
.
4
0
–
5
1
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
p
a
.
2
0
2
1
.
1
0
.
0
0
2
.
[
1
3
]
L.
W
a
n
g
e
t
a
l
.
,
“
A
r
e
v
i
e
w
o
f
m
e
t
h
o
d
s
f
o
r
sh
i
p
d
e
t
e
c
t
i
o
n
w
i
t
h
e
l
e
c
t
r
o
-
o
p
t
i
c
a
l
i
m
a
g
e
s
i
n
m
a
r
i
n
e
e
n
v
i
r
o
n
m
e
n
t
s,
”
J
o
u
r
n
a
l
o
f
M
a
ri
n
e
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
9
,
n
o
.
1
2
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
j
mse
9
1
2
1
4
0
8
.
[
1
4
]
Z.
S
h
a
o
e
t
a
l
.
,
“
M
u
l
t
i
-
sca
l
e
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
m
o
d
e
l
f
o
r
a
u
t
o
n
o
m
o
u
s
s
h
i
p
n
a
v
i
g
a
t
i
o
n
i
n
m
a
r
i
t
i
m
e
e
n
v
i
r
o
n
me
n
t
,
”
J
o
u
r
n
a
l
o
f
M
a
r
i
n
e
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
0
,
n
o
.
1
1
,
N
o
v
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
j
ms
e
1
0
1
1
1
7
8
3
.
[
1
5
]
M
.
F
.
F
i
n
g
a
s
a
n
d
C
.
E.
B
r
o
w
n
,
“
R
e
v
i
e
w
o
f
s
h
i
p
d
e
t
e
c
t
i
o
n
f
r
o
m
a
i
r
b
o
r
n
e
p
l
a
t
f
o
r
ms,”
C
a
n
a
d
i
a
n
J
o
u
rn
a
l
o
f
R
e
m
o
t
e
S
e
n
si
n
g
,
v
o
l
.
2
7
,
n
o
.
4
,
p
p
.
3
7
9
–
3
8
5
,
A
u
g
.
2
0
0
1
,
d
o
i
:
1
0
.
1
0
8
0
/
0
7
0
3
8
9
9
2
.
2
0
0
1
.
1
0
8
5
4
8
8
0
.
[
1
6
]
W
.
H
a
n
,
A
.
K
u
e
r
b
a
n
,
Y
.
Y
a
n
g
,
Z
.
H
u
a
n
g
,
B
.
L
i
u
,
a
n
d
J.
G
a
o
,
“
M
u
l
t
i
-
v
i
si
o
n
n
e
t
w
o
r
k
f
o
r
a
c
c
u
r
a
t
e
a
n
d
r
e
a
l
-
t
i
me
sma
l
l
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
i
n
o
p
t
i
c
a
l
r
e
m
o
t
e
s
e
n
s
i
n
g
i
m
a
g
e
s,”
I
EEE
G
e
o
sc
i
e
n
c
e
a
n
d
R
e
m
o
t
e
S
e
n
s
i
n
g
L
e
t
t
e
rs
,
v
o
l
.
1
9
,
p
p
.
1
–
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
LG
R
S
.
2
0
2
0
.
3
0
4
4
4
2
2
.
[
1
7
]
A
.
Z
h
o
u
,
W
.
X
i
e
,
a
n
d
J.
P
e
i
,
“
I
n
f
r
a
r
e
d
mari
t
i
m
e
t
a
r
g
e
t
d
e
t
e
c
t
i
o
n
u
si
n
g
t
h
e
h
i
g
h
o
r
d
e
r
st
a
t
i
st
i
c
f
i
l
t
e
r
i
n
g
i
n
f
r
a
c
t
i
o
n
a
l
F
o
u
r
i
e
r
d
o
m
a
i
n
,
”
I
n
f
r
a
re
d
P
h
y
si
c
s &
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
9
1
,
p
p
.
1
2
3
–
1
3
6
,
J
u
n
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
f
r
a
r
e
d
.
2
0
1
8
.
0
4
.
0
0
6
.
[
1
8
]
D
.
Z
h
o
u
,
S
.
Q
i
u
,
Y
.
S
o
n
g
,
a
n
d
K
.
X
i
a
,
“
A
p
e
d
e
st
r
i
a
n
e
x
t
r
a
c
t
i
o
n
a
l
g
o
r
i
t
h
m
b
a
se
d
o
n
si
n
g
l
e
i
n
f
r
a
r
e
d
i
m
a
g
e
,
”
I
n
f
ra
re
d
Ph
y
si
c
s
&
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
0
5
,
M
a
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
f
r
a
r
e
d
.
2
0
2
0
.
1
0
3
2
3
6
.
[
1
9
]
Z.
L
i
u
e
t
a
l
.
,
“
I
n
f
r
a
r
e
d
s
a
l
i
e
n
t
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
b
a
se
d
o
n
g
l
o
b
a
l
g
u
i
d
e
d
l
i
g
h
t
w
e
i
g
h
t
n
o
n
-
l
o
c
a
l
d
e
e
p
f
e
a
t
u
r
e
s,”
I
n
f
ra
r
e
d
Ph
y
si
c
s
&
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
6
3
3
2
-
6
3
3
8
6338
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
1
5
,
Ju
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
f
r
a
r
e
d
.
2
0
2
1
.
1
0
3
6
7
2
.
[
2
0
]
J.
A
n
e
t
a
l
.
,
“
E
n
h
a
n
c
e
me
n
t
o
f
m
a
r
i
n
e
l
a
n
t
e
r
n
’
s
v
i
si
b
i
l
i
t
y
u
n
d
e
r
h
i
g
h
h
a
z
e
u
si
n
g
A
I
c
a
mer
a
a
n
d
se
n
s
o
r
-
b
a
s
e
d
c
o
n
t
r
o
l
s
y
s
t
e
m
,
”
Mi
c
r
o
m
a
c
h
i
n
e
s
,
v
o
l
.
1
4
,
n
o
.
2
,
Ja
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
mi
1
4
0
2
0
3
4
2
.
[
2
1
]
X
.
H
a
n
,
L.
Z
h
a
o
,
Y
.
N
i
n
g
,
a
n
d
J.
H
u
,
“
S
h
i
p
Y
O
LO
:
a
n
e
n
h
a
n
c
e
d
m
o
d
e
l
f
o
r
sh
i
p
d
e
t
e
c
t
i
o
n
,
”
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
T
ra
n
s
p
o
r
t
a
t
i
o
n
,
v
o
l
.
2
0
2
1
,
p
p
.
1
–
1
1
,
J
u
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
1
/
1
0
6
0
1
8
2
.
[
2
2
]
J.
-
Y
.
S
h
e
n
,
C
.
-
K
.
Lu
,
a
n
d
L.
G
.
L
i
m
,
“
A
n
o
v
e
l
d
e
e
p
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
p
o
o
l
i
n
g
a
l
g
o
r
i
t
h
m
f
o
r
s
mal
l
f
l
o
a
t
i
n
g
o
b
j
e
c
t
s
d
e
t
e
c
t
i
o
n
,
”
i
n
2
0
2
3
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
n
s
u
m
e
r
El
e
c
t
ro
n
i
c
s
-
T
a
i
w
a
n
(
I
C
C
E
-
T
a
i
w
a
n
)
,
J
u
l
.
2
0
2
3
,
p
p
.
1
7
5
–
1
7
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
E
-
Ta
i
w
a
n
5
8
7
9
9
.
2
0
2
3
.
1
0
2
2
6
7
5
4
.
[
2
3
]
H
.
F
u
,
R
.
Z
h
a
n
g
,
X
.
N
i
n
g
,
a
n
d
Y
.
W
a
n
g
,
“
S
h
i
p
d
e
t
e
c
t
i
o
n
b
a
s
e
d
o
n
i
mp
r
o
v
e
d
Y
O
LO
a
l
g
o
r
i
t
h
m,”
i
n
2
0
2
1
4
0
t
h
C
h
i
n
e
se
C
o
n
t
r
o
l
C
o
n
f
e
re
n
c
e
(
C
C
C
)
,
J
u
l
.
2
0
2
1
,
p
p
.
8
1
8
1
–
8
1
8
6
,
d
o
i
:
1
0
.
2
3
9
1
9
/
C
C
C
5
2
3
6
3
.
2
0
2
1
.
9
5
4
9
9
6
7
.
[
2
4
]
H
.
D
.
Tr
u
n
g
,
“
A
c
o
mp
a
r
i
s
o
n
o
f
Y
O
LO
n
e
t
w
o
r
k
s
f
o
r
s
h
i
p
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
f
r
o
m
o
p
t
i
c
a
l
r
e
m
o
t
e
-
se
n
si
n
g
i
ma
g
e
s
,
”
i
n
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
H
y
b
r
i
d
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
s
,
2
0
2
3
,
p
p
.
4
3
–
5
2
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
1
-
2
7
4
0
9
-
1
_
5
.
[
2
5
]
Y
.
Zh
o
u
,
“
A
Y
O
LO
-
N
L
o
b
j
e
c
t
d
e
t
e
c
t
o
r
f
o
r
r
e
a
l
-
t
i
m
e
d
e
t
e
c
t
i
o
n
,
”
E
x
p
e
rt
S
y
s
t
e
m
s
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
3
8
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
3
.
1
2
2
2
5
6
.
[
2
6
]
S
.
F
e
f
i
l
a
t
y
e
v
,
D
.
G
o
l
d
g
o
f
,
M
.
S
h
r
e
v
e
,
a
n
d
C
.
L
e
mb
k
e
,
“
D
e
t
e
c
t
i
o
n
a
n
d
t
r
a
c
k
i
n
g
o
f
sh
i
p
s
i
n
o
p
e
n
se
a
w
i
t
h
r
a
p
i
d
l
y
m
o
v
i
n
g
b
u
o
y
-
mo
u
n
t
e
d
c
a
mer
a
s
y
st
e
m,”
O
c
e
a
n
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
5
4
,
p
p
.
1
–
1
2
,
N
o
v
.
2
0
1
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
o
c
e
a
n
e
n
g
.
2
0
1
2
.
0
6
.
0
2
8
.
[
2
7
]
J.
Y
u
,
D
.
H
u
a
n
g
,
X
.
S
h
i
,
W
.
L
i
,
a
n
d
X
.
W
a
n
g
,
“
R
e
a
l
-
t
i
me
m
o
v
i
n
g
sh
i
p
d
e
t
e
c
t
i
o
n
f
r
o
m
l
o
w
-
r
e
s
o
l
u
t
i
o
n
l
a
r
g
e
-
s
c
a
l
e
r
e
m
o
t
e
se
n
si
n
g
i
ma
g
e
s
e
q
u
e
n
c
e
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
3
,
n
o
.
4
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
3
0
4
2
5
8
4
.
[
2
8
]
A
.
P
.
W
.
A
l
d
r
y
a
n
i
e
t
a
l
.
,
“
D
e
v
e
l
o
p
men
t
o
f
sh
i
p
d
e
t
e
c
t
i
o
n
u
s
i
n
g
O
P
EN
C
V
Y
O
LO
me
t
h
o
d
o
n
u
n
ma
n
n
e
d
p
r
o
t
o
t
y
p
e
b
o
a
t
f
o
r
mo
n
i
t
o
r
i
n
g
n
a
t
i
o
n
a
l
se
a
,
”
i
n
2
0
2
2
7
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
W
o
rks
h
o
p
o
n
Bi
g
D
a
t
a
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
e
c
u
ri
t
y
(
I
WB
I
S
)
,
O
c
t
.
2
0
2
2
,
p
p
.
7
–
1
2
,
d
o
i
:
1
0
.
1
1
0
9
/
I
W
B
I
S
5
6
5
5
7
.
2
0
2
2
.
9
9
2
4
8
9
1
.
[
2
9
]
M
.
K
u
mar
a
n
d
R
.
B
h
a
t
t
,
“
A
n
a
p
p
r
o
a
c
h
t
o
w
a
r
d
s
r
e
a
l
-
t
i
m
e
o
b
j
e
c
t
d
e
t
e
c
t
o
r
u
s
i
n
g
o
p
e
n
C
V
,
”
i
n
2
0
2
2
1
1
t
h
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
S
y
st
e
m
M
o
d
e
l
i
n
g
&
A
d
v
a
n
c
e
m
e
n
t
i
n
Re
se
a
r
c
h
T
r
e
n
d
s
(
S
MA
RT)
,
D
e
c
.
2
0
2
2
,
p
p
.
9
8
1
–
9
8
5
,
d
o
i
:
1
0
.
1
1
0
9
/
S
M
A
R
T
5
5
8
2
9
.
2
0
2
2
.
1
0
0
4
6
7
5
1
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
J
o
sé
Ro
d
r
í
g
u
e
z
-
G
o
n
z
a
les
e
n
g
i
n
e
e
rin
g
stu
d
e
n
t
a
t
th
e
Un
iv
e
r
sid
a
d
Tec
n
o
ló
g
ica
d
e
l
P
e
r
ú
.
C
u
rre
n
tl
y
,
h
e
is
a
n
e
le
c
tro
n
ic
tec
h
n
icia
n
fo
r
t
h
e
e
n
g
in
e
e
rin
g
a
re
a
o
f
a
n
e
lec
tro
n
ic
se
c
u
rit
y
c
o
m
p
a
n
y
.
He
c
a
n
b
e
c
o
n
t
a
c
ted
b
y
e
-
m
a
il
:
1
6
3
0
3
4
8
@u
t
p
.
e
d
u
.
p
e
.
J
u
n
i
o
r
Niq
u
i
n
-
J
a
im
e
s
En
g
in
e
e
rin
g
stu
d
e
n
t
a
t
th
e
U
n
iv
e
rsi
d
a
d
Tec
n
o
l
ó
g
ica
d
e
l
P
e
rú
.
He
c
u
rre
n
tl
y
wo
r
k
s
a
s
a
tec
h
n
ica
l
sp
e
c
ialist
a
t
tele
fó
n
ica
.
H
is
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
e
n
e
rg
y
sy
ste
m
s,
a
rti
ficia
l
i
n
telli
g
e
n
c
e
,
a
n
d
m
e
c
h
a
tro
n
ic
sy
ste
m
s
.
He
c
a
n
b
e
c
o
n
tac
ted
b
y
e
-
m
a
il
:
1
6
1
2
6
3
6
@
u
tp
.
e
d
u
.
p
e
.
Er
n
e
sto
Pa
iv
a
-
Per
e
d
o
g
ra
d
u
a
ted
a
s
a
n
e
lec
tri
c
a
l
m
e
c
h
a
n
ica
l
e
n
g
in
e
e
r
fro
m
th
e
Un
iv
e
rsid
a
d
d
e
P
iu
ra
i
n
P
e
ru
i
n
2
0
1
3
.
He
p
u
rsu
e
d
f
u
rth
e
r
stu
d
i
e
s
a
n
d
o
b
tai
n
e
d
a
m
a
ste
r'
s
d
e
g
re
e
in
e
lec
tri
c
a
l
a
n
d
m
e
c
h
a
n
ica
l
e
n
g
in
e
e
rin
g
,
sp
e
c
ializin
g
in
a
u
to
m
a
ti
o
n
a
n
d
o
p
ti
m
iza
ti
o
n
.
He
wa
s
su
p
p
o
rte
d
b
y
CON
CYTE
C
a
n
d
a
wa
rd
e
d
b
y
th
e
U
n
iv
e
rsi
d
a
d
d
e
P
iu
ra
i
n
2
0
1
6
.
Du
ri
n
g
h
is
a
c
a
d
e
m
ic
jo
u
r
n
e
y
,
h
e
wa
s
a
re
se
a
rc
h
a
ss
istan
t
a
t
th
e
De
p
a
rtme
n
t
o
f
Tec
h
n
o
lo
g
y
a
n
d
In
n
o
v
a
ti
o
n
(DTI)
a
t
S
UPS
I
.
P
re
se
n
tl
y
,
h
e
h
o
l
d
s
th
e
p
o
siti
o
n
o
f
p
ro
fe
ss
o
r
-
re
se
a
rc
h
e
r
a
t
th
e
Un
iv
e
rsid
a
d
Tec
n
o
l
ó
g
ica
d
e
l
P
e
rú
.
He
c
a
n
b
e
c
o
n
tac
ted
b
y
e
-
m
a
il
:
c2
2
3
9
5
@
u
t
p
.
e
d
u
.
p
e
.
Evaluation Warning : The document was created with Spire.PDF for Python.