I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
11
,
No
.
2
,
A
p
r
il
2
0
2
1
,
p
p
.
1
2
8
4
~1
2
9
2
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
1
1
i
2
.
p
p
1
2
8
4
-
1
2
9
2
1
284
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Illu
m
ina
tion
-
inv
a
ria
nt
v
eg
etation
d
etec
tion
f
o
r a v
isi
o
n
sens
o
r
-
ba
sed a
g
ricultural a
pplica
ti
o
ns
K
eun H
a
Cho
i
1
,
So
o
H
y
un
K
i
m
2
1
A
rti
f
icia
l
In
telli
g
e
n
c
e
R&
D Cen
ter,
T
ra
in
in
g
a
n
d
Do
c
tr
in
e
Co
m
m
a
n
d
,
Da
e
jeo
n
,
Re
p
u
b
l
ic o
f
Ko
re
a
2
De
p
a
rtme
n
t
o
f
M
e
c
h
a
n
ica
l
En
g
i
n
e
e
rin
g
,
Ko
re
a
A
d
v
a
n
c
e
d
In
stit
u
t
e
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
,
Re
p
u
b
li
c
o
f
Ko
re
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
r
1
7
,
2
0
2
0
R
ev
i
s
ed
J
u
n
1
0
,
2
0
2
0
A
cc
ep
ted
Sep
2
9
,
2
0
2
0
In
th
is
p
a
p
e
r,
w
e
p
ro
p
o
se
a
n
o
v
e
l
m
e
th
o
d
,
il
l
u
m
in
a
ti
o
n
-
i
n
v
a
rian
t
v
e
g
e
tatio
n
d
e
tec
ti
o
n
(I
V
D),
to
im
p
ro
v
e
m
a
n
y
a
sp
e
c
ts
o
f
a
g
ricu
lt
u
re
f
o
r
v
i
sio
n
-
b
a
se
d
a
u
to
n
o
m
o
u
s
m
a
c
h
in
e
s
o
r
ro
b
o
ts.
T
h
e
p
ro
p
o
se
d
m
e
th
o
d
d
e
riv
e
s
n
e
w
c
o
lo
r
f
e
a
tu
re
f
u
n
c
ti
o
n
s
f
ro
m
si
m
u
lt
a
n
e
o
u
sly
m
o
d
e
li
n
g
th
e
sp
e
c
tral
p
ro
p
e
rti
e
s
o
f
th
e
c
o
lo
r
c
a
m
e
ra
a
n
d
sc
e
n
e
il
lu
m
in
a
ti
o
n
.
A
n
e
x
p
e
rime
n
t
in
w
h
ich
a
n
im
a
g
e
sa
m
p
le
d
a
tas
e
t
w
a
s
a
c
q
u
ired
u
n
d
e
r
n
a
tu
re
il
l
u
m
in
a
ti
o
n
,
i
n
c
lu
d
in
g
v
a
rio
u
s
in
ten
siti
e
s,
w
e
a
th
e
r
c
o
n
d
it
io
n
s,
s
h
a
d
o
w
s
a
n
d
re
f
lec
ti
o
n
s,
w
a
s
p
e
r
f
o
rm
e
d
.
T
h
e
re
su
lt
s
sh
o
w
th
a
t
th
e
p
ro
p
o
se
d
m
e
th
o
d
(I
V
D)
y
ield
s
th
e
h
ig
h
e
st
p
e
rf
o
r
m
a
n
c
e
w
it
h
th
e
lo
w
e
st
e
rro
r
a
n
d
sta
n
d
a
rd
d
e
v
iatio
n
a
n
d
is
su
p
e
rio
r
t
o
s
ix
ty
p
ica
l
m
e
th
o
d
s.
Ou
r
m
e
th
o
d
h
a
s
m
u
lt
ip
le
stre
n
g
th
s,
i
n
c
lu
d
in
g
c
o
m
p
u
tati
o
n
a
l
sim
p
li
c
it
y
a
n
d
u
n
if
o
rm
l
y
h
ig
h
-
a
c
c
u
ra
c
y
ima
g
e
se
g
m
e
n
tatio
n
.
K
ey
w
o
r
d
s
:
Ag
r
icu
ltu
r
al
ap
p
licatio
n
s
C
r
o
p
r
o
w
d
etec
tio
n
I
llu
m
in
a
tio
n
-
i
n
v
ar
ia
n
t
Veg
etatio
n
d
etec
tio
n
Vis
io
n
s
en
s
o
r
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
:
So
o
Hy
u
n
Ki
m
Dep
ar
t
m
en
t o
f
Me
ch
i
n
ca
l E
n
g
in
ee
r
in
g
Ko
r
ea
A
d
v
a
n
ce
d
I
n
s
tit
u
te
o
f
S
cien
ce
an
d
T
ec
h
n
o
lo
g
y
2
9
1
Dae
h
ak
-
r
o
,
Yu
s
u
n
g
-
g
u
,
Dea
j
eo
n
-
s
i,
R
ep
u
b
lic
o
f
Ko
r
ea
E
m
ail:
s
o
o
h
y
u
n
@
k
ais
t.a
c.
k
r
1.
I
NT
RO
D
UCT
I
O
N
I
n
th
e
ca
s
e
o
f
v
i
s
io
n
-
b
ased
ag
r
icu
lt
u
r
al
ap
p
licatio
n
s
y
s
te
m
,
a
cr
u
cial
is
s
u
e
is
to
ac
c
u
r
atel
y
s
e
g
m
en
t
o
n
l
y
t
h
e
v
e
g
etatio
n
p
ar
t
f
r
o
m
its
b
ac
k
g
r
o
u
n
d
i
m
ag
e.
I
n
t
h
i
s
p
r
o
ce
s
s
,
a
m
aj
o
r
ch
allen
g
e
i
s
h
o
w
to
o
v
er
co
m
e
th
e
w
id
e
r
an
g
e
o
f
n
atu
r
al
il
lu
m
i
n
atio
n
co
n
d
itio
n
s
,
w
h
ic
h
s
t
r
o
n
g
l
y
a
f
f
ec
t
t
h
e
cr
o
p
i
m
ag
e
s
in
t
y
p
ical
o
u
td
o
o
r
s
e
t
t
i
n
g
s
b
e
c
a
u
s
e
o
f
s
p
e
c
u
l
a
r
r
e
f
l
e
c
t
i
o
n
s
,
s
h
a
d
o
w
s
o
v
e
r
t
h
e
v
e
g
e
t
a
t
i
o
n
a
n
d
w
e
a
t
h
e
r
c
o
n
d
i
t
i
o
n
s
.
P
r
e
v
i
o
u
s
s
t
u
d
ies
h
a
v
e
b
e
e
n
r
e
s
e
a
r
c
h
e
d
a
v
a
r
i
e
t
y
o
f
m
e
t
h
o
d
s
f
o
r
c
r
o
p
d
e
t
e
c
t
i
o
n
.
A
l
l
o
f
t
h
e
s
e
m
e
t
h
o
d
s
p
e
r
f
o
r
m
e
d
w
e
l
l
i
n
a
s
i
m
p
l
e
e
n
v
i
r
o
n
m
e
n
t
w
i
t
h
n
o
r
m
a
l
i
l
l
u
m
i
n
a
t
i
o
n
a
n
d
s
o
i
l
c
o
n
d
i
t
i
o
n
s
.
P
r
e
v
i
o
u
s
s
t
u
d
i
e
s
a
r
e
c
o
n
s
i
s
t
o
f
t
w
o
b
r
o
a
d
c
a
t
e
g
o
r
i
e
s
[
1
]
.
T
h
e
co
lo
r
in
d
ex
b
ased
ap
p
r
o
ac
h
u
s
ed
co
lo
r
s
p
ac
es
(
R
GB
,
HSV)
to
d
is
ti
n
g
u
is
h
c
r
o
p
s
an
d
b
ac
k
g
r
o
u
n
d
s
t
h
r
o
u
g
h
s
i
m
p
le
f
o
r
m
u
las.
T
h
e
lear
n
in
g
-
b
as
ed
ap
p
r
o
ac
h
u
s
ed
t
h
e
lear
n
i
n
g
m
et
h
o
d
o
f
cr
o
p
tr
ain
i
n
g
s
a
m
p
le
s
to
d
e
m
o
n
s
tr
a
te
ad
ap
tab
ilit
y
to
c
h
an
g
i
n
g
il
l
u
m
in
at
io
n
.
I
n
a
co
lo
r
-
i
n
d
ex
b
ased
ap
p
r
o
ac
h
,
th
e
ex
ce
s
s
g
r
ee
n
in
d
e
x
(
E
x
G)
[
2
]
w
a
s
a
m
et
h
o
d
u
s
in
g
g
r
ee
n
co
l
o
r
co
m
p
o
n
en
t e
x
tr
ac
tio
n
m
o
r
e
i
m
p
o
r
tan
t
f
o
r
g
r
ee
n
cr
o
p
ex
tr
ac
tio
n
.
T
h
e
ex
ce
s
s
g
r
ee
n
-
e
x
ce
s
s
r
ed
in
d
ex
(
E
x
GR
)
[
3
]
to
o
k
ad
v
an
ta
g
e
o
f
th
e
h
ig
h
s
u
cc
ess
r
ate
o
f
g
r
ee
n
cr
o
p
ex
tr
ac
tio
n
b
y
s
u
p
p
r
ess
in
g
r
ed
co
m
p
o
n
en
ts
b
y
s
u
b
tr
ac
ti
n
g
th
e
E
x
R
i
n
d
ex
[
4
]
.
Si
m
ilar
l
y
,
t
h
e
n
o
r
m
alize
d
d
i
f
f
er
en
ce
in
d
e
x
(
NDI
)
[
5
]
u
s
ed
b
o
th
g
r
ee
n
an
d
r
ed
co
lo
r
co
m
p
o
n
e
n
ts
an
d
t
h
en
i
m
p
r
o
v
ed
p
er
f
o
r
m
a
n
ce
t
h
r
o
u
g
h
lo
ca
l
g
r
o
w
th
p
r
o
ce
s
s
es.
T
h
e
co
lo
r
i
n
d
ices
o
f
v
e
g
etatio
n
ex
tr
ac
ti
o
n
(
C
I
VE
)
[
6
]
an
d
v
eg
eta
tio
n
i
n
d
ices
(
VE
G)
[
7
]
u
s
ed
all
t
h
r
ee
co
lo
r
co
m
p
o
n
e
n
ts
,
an
d
ea
ch
R
GB
co
lo
r
to
em
p
h
asize
t
h
e
r
o
le
o
f
th
e
g
r
ee
n
co
m
p
o
n
en
t
to
s
elec
t
th
e
o
p
ti
m
al
ch
a
n
n
e
l
co
m
b
in
a
tio
n
f
o
r
th
e
s
p
ac
e.
T
h
e
r
esu
lt
o
f
th
e
co
m
b
i
n
atio
n
w
a
s
t
h
en
co
n
v
er
ted
i
n
to
a
g
r
a
y
i
m
ag
e.
An
d
i
n
t
h
e
E
x
G,
NDI
,
an
d
C
I
VE
m
et
h
o
d
s
,
cr
o
p
s
eg
m
en
ta
tio
n
w
a
s
o
b
tain
ed
u
s
i
n
g
t
h
e
Ots
u
[
8
]
m
eth
o
d
w
it
h
a
f
i
x
ed
th
r
es
h
o
ld
.
Fo
r
th
e
VE
G
m
eth
o
d
,
th
e
b
in
ar
izatio
n
p
r
o
ce
s
s
is
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:
2
0
8
8
-
8708
I
llu
min
a
tio
n
-
in
v
a
r
ia
n
t v
eg
eta
t
io
n
d
etec
tio
n
(
I
V
D)
fo
r
a
visi
o
n
s
en
s
o
r
-
b
a
s
ed
…
(
K
eu
n
Ha
C
h
o
i
)
1285
p
er
f
o
r
m
ed
b
y
t
h
e
m
ea
n
v
al
u
e.
All
o
f
th
e
ab
o
v
e
co
lo
r
in
d
ex
m
et
h
o
d
s
r
eq
u
ir
ed
a
f
ix
ed
t
h
r
es
h
o
ld
,
b
u
t
t
h
is
f
i
x
ed
th
r
es
h
o
ld
m
et
h
o
d
w
as
d
i
f
f
icu
lt
to
g
en
er
ate
an
ap
p
r
o
p
r
iate
th
r
es
h
o
ld
f
o
r
cr
o
p
ex
tr
ac
tio
n
d
u
e
to
illu
m
i
n
atio
n
ch
an
g
es.
T
h
is
p
r
o
b
lem
r
es
u
lts
in
less
cr
o
p
d
etec
tio
n
b
ec
au
s
e
th
e
g
r
ee
n
ch
a
n
n
el
is
less
p
r
o
n
o
u
n
ce
d
th
a
n
th
e
o
th
er
t
w
o
c
h
an
n
els i
n
a
s
i
n
g
le
i
m
a
g
e.
T
h
ese
m
et
h
o
d
s
ca
n
o
n
l
y
b
e
ap
p
lied
in
li
m
ited
cir
cu
m
s
tan
ce
s
.
I
n
th
e
l
ea
r
n
in
g
-
b
ased
m
et
h
o
d
,
th
er
e
w
er
e
t
w
o
s
tag
e
s
:
tr
ain
in
g
o
f
t
h
e
cr
o
p
co
lo
r
d
ata
an
d
class
i
f
icatio
n
.
I
n
t
h
e
E
A
S
A
m
et
h
o
d
[
9
,
1
0
]
,
th
e
tr
ain
i
n
g
p
r
o
ce
s
s
b
eg
in
s
w
it
h
cl
u
s
ter
i
n
g
an
d
e
n
d
s
w
it
h
a
B
ay
e
s
ian
clas
s
i
f
ier
,
w
h
er
e
t
h
e
clas
s
i
f
icatio
n
p
r
o
ce
s
s
i
s
co
m
p
leted
t
h
r
o
u
g
h
a
lo
o
k
u
p
tab
le.
T
h
e
A
P
-
HI
ap
p
r
o
ac
h
[
1
1
]
w
a
s
b
ased
o
n
t
h
e
ass
u
m
p
tio
n
t
h
at
t
h
e
h
is
to
g
r
a
m
o
f
h
u
e
u
n
d
er
a
ce
r
tain
in
te
n
s
it
y
i
s
s
i
m
ilar
to
a
Gau
s
s
ia
n
d
is
tr
ib
u
tio
n
cu
r
v
e.
T
h
e
tr
ain
in
g
p
r
o
ce
s
s
w
as
to
c
alcu
late
t
h
e
m
ea
n
a
n
d
s
ta
n
d
ar
d
d
ev
iatio
n
o
f
ea
c
h
h
u
e
le
v
el
a
n
d
th
e
n
b
u
ild
a
c
o
r
r
esp
o
n
d
in
g
lo
o
k
u
p
tab
le
(
L
UT
)
.
T
h
e
class
if
icatio
n
p
r
o
ce
s
s
is
p
er
f
o
r
m
ed
b
y
ch
ec
k
i
n
g
th
e
d
is
cr
i
m
i
n
ati
n
g
f
u
n
ctio
n
t
h
r
o
u
g
h
t
h
e
L
UT
.
T
h
e
ar
tif
icial
n
eu
r
al
n
et
w
o
r
k
m
et
h
o
d
[
1
2
]
w
as
u
s
ed
to
class
i
f
y
cr
o
p
s
an
d
b
ac
k
g
r
o
u
n
d
s
t
h
r
o
u
g
h
lear
n
i
n
g
u
s
i
n
g
t
h
e
m
ea
n
s
h
i
f
t
al
g
o
r
it
h
m
an
d
b
ac
k
p
r
o
p
ag
atio
n
ar
tif
icial
n
eu
r
al
n
et
w
o
r
k
(
B
PNN)
.
Gu
o
[
1
3
]
u
s
ed
d
ec
is
io
n
tr
ee
s
an
d
i
m
ag
e
n
o
is
e
r
ed
u
c
tio
n
f
il
ter
s
f
o
r
cr
o
p
ex
tr
ac
tio
n
,
a
n
d
Mo
n
tal
v
o
[
1
4
]
ap
p
lied
a
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM)
f
o
r
cr
o
p
id
en
tif
ic
atio
n
.
B
ai
[
1
5
]
u
s
ed
a
clu
s
ter
in
g
m
et
h
o
d
b
ased
o
n
v
eg
eta
tio
n
s
e
g
m
e
n
tat
io
n
b
ase
d
o
n
p
ar
ticle
s
w
ar
m
o
p
ti
m
izat
i
o
n
(
P
SO)
clu
s
ter
i
n
g
an
d
m
o
r
p
h
o
lo
g
y
m
o
d
eli
n
g
i
n
C
I
E
L
A
B
co
lo
r
s
p
ac
e.
I
n
ad
d
itio
n
,
v
ar
io
u
s
r
esear
ch
e
s
on
cr
o
p
r
o
w
d
etec
tio
n
u
s
i
n
g
v
i
s
io
n
ca
m
er
as a
n
d
i
m
a
g
e
p
r
o
ce
s
s
in
g
h
a
v
e
b
ee
n
co
n
d
u
cted
[
1
6
-
30
]
.
A
ll
t
h
ese
m
et
h
o
d
s
ar
e
ab
le
t
o
ad
ap
t
to
a
ce
r
tain
d
eg
r
ee
o
f
ch
an
g
e
in
li
g
h
ti
n
g
.
Ho
w
e
v
er
,
th
ese
p
er
f
o
r
m
a
n
ce
s
d
ep
en
d
o
n
th
e
s
ize
o
f
th
e
tr
ain
i
n
g
d
ata
to
h
an
d
le
d
if
f
er
en
t
li
g
h
tin
g
ch
ar
ac
te
r
is
tics
.
Si
n
ce
lig
h
ti
n
g
c
h
a
n
g
e
s
al
w
a
y
s
o
cc
u
r
w
it
h
o
u
t
r
u
les
a
n
d
r
eg
u
latio
n
s
,
tr
ain
i
n
g
s
a
m
p
les
ar
e
li
m
ite
d
an
d
class
i
f
icatio
n
r
esu
lt
s
ar
e
n
o
t
g
u
ar
an
teed
,
e
s
p
ec
iall
y
w
h
en
h
ig
h
li
g
h
t
ta
k
es
p
lace
[
1
]
.
T
h
ese
m
et
h
o
d
s
ar
e
n
o
t
r
o
b
u
s
t
to
s
eg
m
e
n
t
v
e
g
etatio
n
f
r
o
m
b
ac
k
g
r
o
u
n
d
w
h
e
n
i
m
a
g
es
co
n
t
ain
s
p
ec
u
lar
r
ef
lectio
n
s
,
s
h
a
d
o
w
ed
ar
ea
s
an
d
illu
m
i
n
atio
n
ch
a
n
g
es.
I
n
t
h
is
p
ap
er
,
w
e
p
r
o
p
o
s
ed
a
n
o
v
e
l
v
e
g
etatio
n
d
etec
tio
n
m
e
th
o
d
f
o
r
v
i
s
io
n
-
b
ased
ag
r
icu
l
tu
r
al
ap
p
licatio
n
s
i
n
ty
p
ica
l
o
u
td
o
o
r
s
ettin
g
s
.
Ou
r
p
r
o
p
o
s
ed
m
eth
o
d
is
in
te
n
d
ed
to
b
e
an
o
b
j
ec
t
s
eg
m
e
n
tatio
n
m
et
h
o
d
th
at
a
u
to
m
at
icall
y
p
r
o
ce
s
s
e
s
i
m
ag
es
r
eg
ar
d
less
o
f
t
h
e
n
a
tu
r
e
o
f
th
e
ill
u
m
i
n
atio
n
co
n
d
itio
n
s
w
i
th
o
u
t a
th
r
es
h
o
ld
ad
j
u
s
t
m
en
t f
o
r
ea
ch
i
m
a
g
e,
an
d
th
e
m
et
h
o
d
ca
n
b
e
ap
p
lied
in
r
ea
l ti
m
e.
2.
RE
S
E
ARCH
M
E
T
H
O
D
2
.
1
.
Co
ns
t
ra
ints o
f
env
iro
n
m
e
nta
l c
ha
ng
es
Vis
io
n
ca
m
er
a
-
b
ased
ag
r
ic
u
lt
u
r
al
ap
p
licatio
n
s
in
p
ad
d
y
f
ie
ld
h
as
a
lo
t
o
f
co
n
s
tr
ain
ts
b
ec
au
s
e
it
is
o
p
er
ated
in
an
o
u
td
o
o
r
en
v
ir
o
n
m
e
n
t
f
o
r
a
lo
n
g
t
i
m
e.
R
ea
s
o
n
s
o
f
th
e
s
e
co
n
s
tr
ain
t
s
clas
s
i
f
y
l
ar
g
el
y
t
w
o
cr
iter
ia
:
illu
m
i
n
atio
n
a
n
d
m
o
r
p
h
o
lo
g
ic
al
v
ar
iatio
n
.
T
h
e
i
m
ag
e
s
o
f
ca
m
er
as
tak
e
n
i
n
o
u
td
o
o
r
en
v
ir
o
n
m
e
n
t
s
ar
e
af
f
ec
ted
b
y
v
ar
io
u
s
il
lu
m
i
n
atio
n
co
n
d
itio
n
s
d
u
e
to
th
e
w
ea
t
h
er
b
ein
g
clea
r
,
clo
u
d
y
,
r
ai
n
y
,
o
r
s
ev
e
r
el
y
c
li
m
a
tic.
Siv
alo
g
e
w
ar
an
[
3
1
]
w
r
o
te
t
h
at
th
i
s
p
r
o
b
le
m
i
s
t
h
at
s
h
ad
o
w
s
an
d
d
if
f
u
s
ed
r
e
f
lectio
n
ca
n
cr
ea
te
a
s
ce
n
e
w
i
th
a
w
id
e
r
a
n
g
e
t
h
at
ca
n
lead
to
s
a
tu
r
atio
n
o
r
u
n
d
er
ex
p
o
s
u
r
e
o
r
h
ig
h
in
ten
s
it
y
o
f
p
ar
ts
o
f
a
s
c
en
e.
E
s
p
ec
iall
y
,
t
h
e
p
ad
d
y
f
ield
i
s
co
n
s
i
s
t
o
f
w
at
er
an
d
m
u
d
d
y
,
t
h
er
ef
o
r
e
t
h
e
s
p
ec
tr
al
co
m
p
o
s
itio
n
o
f
t
h
e
il
lu
m
in
a
n
t
v
ar
ie
s
ar
e
g
en
er
ated
m
o
r
e
s
i
g
n
if
ican
tl
y
.
T
h
is
v
ar
iatio
n
ca
n
o
cc
u
r
b
et
wee
n
s
h
ad
o
w
ar
ea
s
an
d
in
d
ir
ec
t
illu
m
in
a
tio
n
i
n
th
e
s
a
m
e
s
ce
n
e.
E
v
e
n
lar
g
er
v
ar
iat
io
n
s
o
cc
u
r
in
s
ce
n
es
th
at
ar
e
i
n
d
ir
ec
tl
y
ill
u
m
in
ated
at
d
if
f
er
en
t
ti
m
e
s
o
f
th
e
d
a
y
o
r
at
d
if
f
er
en
t
ti
m
es
o
f
t
h
e
d
ay
.
T
h
ese
v
ar
iatio
n
s
m
ak
e
it
v
er
y
d
if
f
ic
u
lt
to
u
s
e
co
lo
r
o
r
ch
r
o
m
a
ticit
y
in
f
o
r
m
atio
n
to
s
e
g
m
en
t
i
n
ter
esti
n
g
o
b
j
ec
ts
w
it
h
i
n
a
s
ce
n
e
.
A
lt
h
o
u
g
h
m
o
d
er
n
ca
m
er
a
d
ev
ices
ca
n
p
er
f
o
r
m
au
to
m
at
ic
i
m
a
g
e
co
r
r
ec
tio
n
th
r
o
u
g
h
a
u
to
m
a
tic
i
m
a
g
e
w
h
ite
b
alan
ce
o
r
en
h
an
ce
m
e
n
t
,
b
u
t
m
o
s
t
ti
m
es
t
h
is
ar
e
lack
i
n
g
i
n
i
n
d
u
s
tr
ial
ca
m
er
as
th
at
r
eq
u
ir
e
d
y
n
a
m
ic
ad
j
u
s
t
m
en
t
o
f
m
o
s
t
ca
m
er
a
s
etti
n
g
s
(
ex
p
o
s
u
r
e
ti
m
e,
au
to
m
at
ic
i
m
ag
e
w
h
ite
b
alan
c
e,
o
r
p
r
e
-
f
ix
ed
b
y
th
e
u
s
er
(
f
o
ca
l
len
g
t
h
,
ir
is
ap
er
tu
r
e)
[
3
1
]
.
Fig
u
r
e
1
s
h
o
w
s
t
h
e
r
esu
lt
s
o
f
cr
o
p
d
etec
tio
n
u
s
i
n
g
Ots
u
,
E
x
G,
E
x
GR
,
C
I
VE
a
n
d
VE
G
m
et
h
o
d
s
o
n
p
ad
d
y
f
i
led
i
m
a
g
e.
T
h
e
r
es
u
lt
s
s
h
o
w
th
a
t
a
lo
t
o
f
i
m
ag
e
n
o
is
e
w
a
s
g
e
n
er
ated
in
t
h
e
cr
o
p
d
etec
tio
n
r
esu
lts
d
u
e
to
v
a
r
io
u
s
ill
u
m
i
n
atio
n
r
ef
lectio
n
s
o
n
t
h
e
f
ield
.
As
s
h
o
w
n
in
Fi
g
u
r
e
1
,
i
f
w
e
tr
y
to
s
eg
m
e
n
t
cr
o
p
p
ar
ts
u
s
i
n
g
t
y
p
ic
al
p
r
ev
io
u
s
m
et
h
o
d
f
r
o
m
d
i
f
f
er
e
n
t
ill
u
m
i
n
atio
n
i
n
ten
s
i
t
y
i
n
a
n
i
m
ag
e,
i
m
a
g
e
s
e
g
m
e
n
tat
io
n
i
s
n
o
t
g
o
o
d
r
esu
lt
b
ec
au
s
e
it
o
b
s
er
v
e
ar
ea
o
f
s
tr
o
n
g
r
ef
lectio
n
a
n
d
s
h
ad
o
w
.
2
.
2
.
I
llu
m
ina
t
io
n inv
a
ria
nt
-
ba
s
ed
v
eg
et
a
t
io
n det
ec
t
i
o
n (
I
VD)
An
i
m
a
g
e
i
s
f
o
r
m
ed
w
h
e
n
li
g
h
t
f
r
o
m
a
n
ill
u
m
in
at
io
n
s
o
u
r
c
e
is
r
e
f
lecte
d
f
r
o
m
v
ar
io
u
s
o
b
j
ec
ts
in
a
s
ce
n
e
i
n
to
an
ar
r
a
y
o
f
p
h
o
to
d
etec
to
r
s
.
As
s
h
o
w
n
i
n
Fi
g
u
r
e
2
,
t
h
e
illu
m
i
n
atio
n
r
esp
o
n
s
e
o
f
an
i
m
a
g
e
s
e
n
s
o
r
,
R
,
in
an
o
u
td
o
o
r
s
ce
n
e
ca
n
t
y
p
ic
all
y
b
e
r
ep
r
esen
t a
s
f
o
llo
w
s
[
3
1
]:
(
)
(
)
x
x
x
R
G
I
S
d
(
1
)
w
h
er
e
G
is
a
g
eo
m
etr
y
f
u
n
c
tio
n
t
h
at
r
ep
r
esen
t
t
h
e
d
ir
ec
tio
n
o
f
th
e
li
g
h
t
s
o
u
r
ce
a
n
d
th
e
d
ir
ec
tio
n
o
f
t
h
e
s
u
r
f
ac
e
n
o
r
m
al,
t
h
e
in
ten
s
it
y
o
f
th
e
il
lu
m
i
n
atio
n
s
o
u
r
ce
is
I
,
th
e
r
ef
lectio
n
co
ef
f
icie
n
t
o
f
t
h
e
o
b
j
ec
ts
is
()
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
2
,
A
p
r
il 2
0
2
1
: 1
2
8
4
-
1292
1286
an
d
th
e
s
p
ec
tr
al
s
e
n
s
it
iv
i
t
y
f
u
n
ctio
n
is
()
S
.
T
h
is
eq
u
atio
n
ca
n
b
e
s
i
m
p
li
f
ied
i
f
it
ca
n
b
e
m
o
d
eled
as
a
Dir
ac
d
elta
f
u
n
c
tio
n
ce
n
ter
ed
o
n
wav
elen
g
t
h
i
,
b
ec
au
s
e
it
i
s
a
s
s
u
m
ed
th
at
t
h
e
s
p
ec
tr
al
s
e
n
s
it
iv
it
y
f
u
n
ct
io
n
i
s
s
u
f
f
icie
n
tl
y
n
ar
r
o
w
.
T
h
er
ef
o
r
e
,
(
1
)
ca
n
b
e
s
im
p
li
f
ied
as f
o
llo
w
s
:
(
)
(
)
x
x
x
i
i
i
R
G
I
S
(
2
)
Fu
r
t
h
er
m
o
r
e,
if
t
h
e
p
h
o
to
d
etec
to
r
is
id
ea
lly
s
e
n
s
iti
v
e
to
lig
h
t
o
n
l
y
at
a
w
a
v
ele
n
g
th
i
,
it
ca
n
b
e
ass
u
m
ed
th
at
(
)
1
i
E
,
w
h
ich
y
ield
s
t
h
e
f
o
llo
w
i
n
g
r
esp
o
n
s
e
f
u
n
ctio
n
:
()
xx
ii
R
G
I
(
3
)
T
ak
in
g
t
h
e
lo
g
ar
ith
m
o
f
b
o
th
s
id
es
o
f
(
3
)
ca
n
b
e
s
ep
ar
ated
.
B
ec
au
s
e
t
h
e
p
h
o
to
d
etec
to
r
r
esp
o
n
s
es
o
f
ea
ch
cr
o
p
an
d
b
ac
k
g
r
o
u
n
d
is
i
n
d
ep
en
d
en
t,
t
h
e
eq
u
atio
n
ca
n
b
e
r
ew
r
it
ten
a
s
f
o
llo
w
s
:
l
o
g
l
o
g
{
}
l
o
g
(
)
c
r
o
p
c
r
o
p
ii
R
G
I
(
4
)
l
o
g
l
o
g
{
}
l
o
g
(
)
b
a
c
k
b
a
c
k
ii
R
G
I
(
5
)
As s
h
o
w
n
i
n
(
5
)
is
s
u
b
tr
ac
ted
f
r
o
m
(
4
)
to
o
b
tain
an
ill
u
m
in
a
n
t
-
i
n
d
ep
en
d
en
t
f
ea
t
u
r
e
f
u
n
ct
io
n
:
l
o
g
l
o
g
l
o
g
(
)
l
o
g
(
)
c
r
o
p
b
a
c
k
c
r
o
p
b
a
c
k
i
i
i
i
RR
(
6
)
As s
h
o
w
n
i
n
(
6
)
ca
n
b
e
r
ep
r
es
en
ted
ac
co
r
d
in
g
to
p
ea
k
s
p
ec
tr
al
r
esp
o
n
s
es e
ac
h
s
en
s
o
r
ch
an
n
el
as
f
o
llo
w
s
:
1
1
1
1
l
o
g
l
o
g
l
o
g
(
)
l
o
g
(
)
c
r
o
p
b
a
c
k
c
r
o
p
b
a
c
k
RR
(
7
)
2
2
2
2
l
o
g
l
o
g
l
o
g
(
)
l
o
g
(
)
c
r
o
p
b
a
c
k
c
r
o
p
b
a
c
k
RR
(
8
)
3
3
3
3
l
o
g
l
o
g
l
o
g
(
)
l
o
g
(
)
c
r
o
p
b
a
c
k
c
r
o
p
b
a
c
k
RR
(
9
)
Fig
u
r
e
1
.
C
r
o
p
d
etec
tio
n
r
esu
lt
s
to
u
tili
ze
Ot
s
u
’
s
,
E
x
G,
E
x
G
R
,
CI
VE
an
d
Ve
g
etati
v
e
VE
G
m
eth
o
d
in
p
ad
d
y
f
ield
W
e
also
w
a
n
t
to
r
e
m
o
v
e
th
e
b
ac
k
g
r
o
u
n
d
in
f
l
u
en
ce
d
u
e
to
s
eg
m
e
n
ti
n
g
o
n
l
y
cr
o
p
s
i
n
t
h
e
i
m
a
g
e.
T
h
e
b
ac
k
g
r
o
u
n
d
o
f
till
a
g
e
is
n
ea
r
l
y
s
o
il
o
r
w
ater
-
s
o
ak
ed
s
o
il
[
3
2
]
;
th
er
ef
o
r
e,
th
e
r
e
f
lectio
n
co
ef
f
icie
n
ts
o
f
th
e
p
ea
k
s
p
ec
tr
al
r
esp
o
n
s
es
f
o
r
ea
ch
s
e
n
s
o
r
ch
a
n
n
el
an
d
r
esp
o
n
s
es
a
r
e
ap
p
r
o
x
im
ate
l
y
t
h
e
s
a
m
e
an
d
ca
n
b
e
r
ep
r
esen
t
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:
2
0
8
8
-
8708
I
llu
min
a
tio
n
-
in
v
a
r
ia
n
t v
eg
eta
t
io
n
d
etec
tio
n
(
I
V
D)
fo
r
a
visi
o
n
s
en
s
o
r
-
b
a
s
ed
…
(
K
eu
n
Ha
C
h
o
i
)
1287
u
s
i
n
g
(
7
-
9
)
.
A
s
s
h
o
w
n
i
n
(
7
)
,
(
8
)
a
n
d
(
9
)
a
r
e
m
u
l
t
i
p
l
i
e
d
b
y
1
1
+
2
+
3
,
1
+
3
1
+
2
+
3
3
1
+
2
+
3
,
r
esp
ec
tiv
el
y
,
to
r
e
m
o
v
e
t
h
e
b
ac
k
g
r
o
u
n
d
ter
m
s
.
T
h
en
,
(
8
)
is
s
u
b
tr
ac
ted
f
r
o
m
(
7
)
an
d
(
9
)
to
y
ield
th
e
f
ea
t
u
r
e
F
:
=
(
1
+
3
1
+
2
+
3
)
2
−
(
1
1
+
2
+
3
)
1
−
(
3
1
+
2
+
3
)
3
=
(1
0
)
T
h
e
f
ea
tu
r
e
F
is
co
n
s
tan
t
a
n
d
a
n
e
w
o
n
e
-
d
i
m
en
s
io
n
al
co
l
o
r
s
p
ac
e
co
n
s
is
tin
g
o
f
t
h
r
ee
r
esp
o
n
s
es
1
2
3
,
,
R
R
R
co
r
r
esp
o
n
d
in
g
to
t
h
e
p
ea
k
s
e
n
s
it
iv
i
ties
at
th
e
o
r
d
er
ed
w
a
v
elen
g
th
1
2
3
,
,
.
T
h
is
f
ea
t
u
r
e
ca
n
b
e
m
ad
e
in
d
ep
en
d
en
t
o
f
b
ac
k
g
r
o
u
n
d
v
a
r
iatio
n
s
s
u
c
h
ch
a
n
g
in
g
ill
u
m
i
n
atio
n
,
r
ef
lectio
n
an
d
s
h
ad
o
w
.
T
h
e
r
ea
s
o
n
f
o
r
th
is
in
d
ep
en
d
en
ce
i
s
t
h
at
th
e
f
ea
t
u
r
e
is
a
f
u
n
c
tio
n
o
f
o
n
l
y
th
e
R
GB
co
lo
r
an
d
r
ef
lectio
n
co
ef
f
icien
t
o
f
th
e
cr
o
p
.
C
o
n
s
eq
u
en
tl
y
,
it
i
s
p
o
s
s
ib
le
t
o
o
b
tain
a
u
n
i
f
o
r
m
l
y
h
i
g
h
-
q
u
alit
y
s
eg
m
e
n
ted
i
m
a
g
e
d
u
r
i
n
g
ti
m
e
s
o
f
ch
a
n
g
i
n
g
illu
m
i
n
atio
n
.
Mo
r
eo
v
er
,
th
i
s
f
ea
tu
r
e
d
ec
r
ea
s
es
t
h
e
d
is
t
u
r
b
an
ce
s
ca
u
s
ed
b
y
s
h
ad
o
w
o
r
r
ef
lectio
n
o
n
a
b
ac
k
g
r
o
u
n
d
.
I
n
t
h
is
s
t
u
d
y
,
a
n
e
w
co
lo
r
s
p
ac
e
i
m
ag
e
b
a
s
ed
o
n
f
ea
tu
r
e
F
i
s
p
r
o
p
o
s
ed
,
an
d
th
e
cr
o
p
i
m
a
g
e
i
s
s
eg
m
e
n
ted
b
y
a
p
p
l
y
in
g
t
h
e
Ot
s
u
m
et
h
o
d
[
8
]
to
th
e
n
e
w
co
lo
r
s
p
ac
e
i
m
ag
e.
I
n
o
r
d
er
to
elim
i
n
ate
n
o
is
e
f
r
o
m
th
e
ac
q
u
ir
ed
i
m
a
g
e,
a
s
ec
o
n
d
m
ed
ian
f
il
ter
w
a
s
ap
p
lied
.
T
h
e
b
in
ar
y
i
m
a
g
e
o
f
th
e
r
ice
r
o
w
ca
n
b
e
d
eter
m
in
ed
b
y
ap
p
l
y
i
n
g
th
e
O
ts
u
m
et
h
o
d
,
w
h
ich
is
o
n
e
o
f
t
h
e
ac
ti
v
e
t
h
r
es
h
o
ld
m
et
h
o
d
s
co
m
m
o
n
l
y
u
s
ed
f
o
r
im
ag
e
s
e
g
m
e
n
tatio
n
.
F
u
r
th
er
m
o
r
e,
s
u
ch
as
in
(
1
1
)
,
s
im
p
le
i
m
ag
e
p
r
o
ce
s
s
in
g
,
ca
n
eli
m
i
n
ate
s
m
a
ll
-
m
a
g
n
it
u
d
e
n
o
is
e
g
e
n
er
ated
b
y
t
h
e
r
e
f
lectio
n
o
f
s
tr
o
n
g
ill
u
m
i
n
atio
n
o
n
t
h
e
w
ater
-
s
o
a
k
ed
s
o
il
s
u
r
f
ac
e.
T
h
is
p
r
o
ce
s
s
d
eter
m
i
n
es
a
b
i
n
ar
y
v
al
u
e
o
f
0
i
n
t
h
e
i
m
a
g
e
p
i
x
els
w
h
e
n
t
h
er
e
is
a
n
o
cc
u
p
ied
ar
ea
o
f
ad
j
ac
en
t p
ix
els.
(
i.e
.
,
(
,
)
)
w
i
th
co
n
n
ec
t
iv
i
t
y
to
ea
ch
p
i
x
el
is
b
elo
w
a
n
ar
b
itra
r
y
t
h
r
es
h
o
ld
(
i.e
.
,
δ)
.
(
,
)
(
,
)
(
,
)
P
0
,
I
f
N
oi
se
e
l
i
m
i
na
t
i
on
P
1
,
othe
r
w
i
se
w
he
r
e
num
be
r
of
pixe
l
s in a
dj
a
c
e
nt
(
,
)
,
P
se
t
of
i
m
a
ge
pi
xe
l
s i
nc
l
ud
i
ng
ar
e
a
ij
ar
e
a
ij
ar
e
a
ij
P
P
p
i
j
P
(
1
1
)
Fig
u
r
e
2
.
C
o
lo
r
im
a
g
e
m
o
d
el
o
f
C
C
D
p
h
o
to
d
etec
to
r
in
f
ar
m
f
ield
3.
RE
SU
L
T
S
A
ND
D
I
SCU
SS
I
O
N
3
.
1
.
I
llu
m
ina
t
io
n
cha
ng
e
T
o
v
er
if
y
th
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
alg
o
r
it
h
m
,
a
n
e
x
p
er
i
m
e
n
t
w
as
p
er
f
o
r
m
ed
to
co
llect
an
i
m
ag
e
s
a
m
p
le
d
ataset
o
f
4
6
i
m
ag
e
s
w
it
h
r
eso
lu
tio
n
6
4
0
x
4
8
0
p
ix
els
s
ep
ar
ated
b
y
1
0
-
m
i
n
u
te
in
ter
v
al
s
b
et
w
ee
n
1
0
:3
0
A
M
a
n
d
6
P
M.
T
h
e
ex
p
er
i
m
en
t
s
ite
w
a
s
a
r
ea
l
p
ad
d
y
i
n
Dae
j
eo
n
,
So
u
th
Ko
r
ea
(
3
6
.
3
7
N,
1
2
7
.
3
6
E
)
.
T
h
e
s
u
n
li
g
h
t
i
s
t
y
p
icall
y
s
tr
o
n
g
d
u
r
in
g
th
i
s
t
i
m
e
o
f
t
h
e
y
ea
r
.
T
h
e
w
ea
t
h
er
co
n
d
itio
n
s
w
er
e
g
e
n
er
all
y
clea
r
b
u
t
s
o
m
eti
m
es
clo
u
d
y
.
T
h
e
ca
p
tu
r
in
g
d
e
v
ice
u
s
ed
w
a
s
a
lo
w
-
co
s
t
co
lo
r
w
eb
-
ca
m
er
a
(
Sa
m
s
u
n
g
®,
SP
C
-
A
8
0
0
M)
.
T
h
e
ca
m
er
a
w
a
s
m
o
u
n
ted
o
n
a
b
r
ac
k
et
ap
p
r
o
x
i
m
atel
y
1
.
5
m
ab
o
v
e
t
h
e
p
ad
d
y
.
I
n
co
m
p
ar
ativ
e
ex
p
er
i
m
en
ts
,
i
m
a
g
es
u
n
d
er
d
if
f
er
en
t
n
a
tu
r
al
lig
h
t
co
n
d
itio
n
s
(
a
to
tal
o
f
4
6
i
m
a
g
es)
w
er
e
ch
o
s
en
an
d
ar
r
an
g
ed
ac
co
r
d
in
g
to
th
e
v
ar
y
in
g
ill
u
m
i
n
atio
n
a
n
d
w
ea
th
er
co
n
d
itio
n
s
.
T
h
e
r
ef
lectio
n
co
ef
f
icie
n
t
s
o
f
th
e
cr
o
p
(
r
ice)
w
er
e
1
(
)
0
.
1
0
,
2
(
)
0
.
2
0
,
3
(
)
0
.
0
7
.
A
lg
o
r
it
h
m
u
s
ed
th
e
Ma
tlab
® p
r
o
g
r
am
(
i
m
a
g
e
p
r
o
ce
s
s
in
g
to
o
lb
o
x
).
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
2
,
A
p
r
il 2
0
2
1
: 1
2
8
4
-
1292
1288
Mo
r
eo
v
er
,
s
ix
o
th
er
co
m
m
o
n
l
y
u
s
ed
alg
o
r
ith
m
s
w
er
e
ap
p
lied
f
o
r
c
o
m
p
ar
is
o
n
.
T
h
e
y
ar
e
th
e
Ots
u
,
E
x
G,
E
x
G
R
,
C
I
VE
,
E
x
R
an
d
VE
G
m
et
h
o
d
s
.
P
r
ev
io
u
s
s
tu
d
ies
h
a
v
e
f
o
c
u
s
ed
o
n
th
e
r
o
le
o
f
th
e
g
r
ee
n
co
m
p
o
n
e
n
t
a
n
d
u
s
ed
a
co
m
b
i
n
atio
n
o
f
ch
a
n
n
els
f
r
o
m
R
G
B
co
lo
r
s
p
ac
e,
as
s
h
o
w
n
in
T
ab
le
1
.
T
h
ese
co
lo
r
f
ea
t
u
r
e
m
et
h
o
d
s
ar
e
b
ased
o
n
t
h
e
ass
u
m
p
tio
n
t
h
at
v
e
g
et
atio
n
an
d
b
ac
k
g
r
o
u
n
d
p
ix
el
s
ca
n
b
e
d
is
ti
n
ctl
y
s
ep
ar
ated
f
r
o
m
ea
c
h
i
m
a
g
e
u
s
in
g
a
p
r
ed
eter
m
i
n
ed
t
h
r
es
h
o
ld
.
T
h
ese
m
et
h
o
d
s
ar
e
n
o
t
p
o
w
er
f
u
l
to
s
e
g
m
e
n
t
v
eg
eta
tio
n
i
n
t
h
e
b
ac
k
g
r
o
u
n
d
i
m
ag
e
if
t
h
e
i
m
a
g
e
co
n
tai
n
s
s
p
ec
u
lar
r
ef
lectio
n
s
,
s
h
ad
o
w
ar
e
as,
an
d
ill
u
m
i
n
atio
n
ch
an
g
es.
I
n
ad
d
itio
n
,
t
h
e
g
r
o
u
n
d
-
tr
u
t
h
i
m
ag
e
s
w
er
e
s
e
g
m
en
ted
m
an
u
all
y
u
s
i
n
g
t
h
e
P
h
o
to
s
h
o
p
s
o
f
t
w
ar
e
p
ac
k
ag
e
(
A
d
o
b
e®)
.
T
o
an
aly
ze
th
e
q
u
an
titat
iv
e
p
er
f
o
r
m
a
n
ce
o
f
p
r
o
p
o
s
ed
m
eth
o
d
,
a
p
er
f
o
r
m
a
n
ce
in
d
ex
to
q
u
an
ti
f
y
th
e
m
i
s
clas
s
i
f
icatio
n
er
r
o
r
o
f
th
e
d
if
f
er
en
t
m
et
h
o
d
s
w
a
s
ap
p
lied
.
I
t is d
ef
in
ed
as f
o
llo
w
s
:
Er
r
o
r
Gr
o
u
n
d
t
r
u
t
h
i
ma
g
e
T
e
s
t
i
ma
g
e
(
1
2
)
A
s
s
h
o
w
n
i
n
(
1
2
)
m
e
a
n
s
s
u
b
t
r
a
c
t
i
n
g
o
n
e
i
m
a
g
e
f
r
o
m
t
h
e
g
r
o
u
n
d
-
t
r
u
t
h
i
m
a
g
e
o
f
t
h
e
s
a
m
e
s
i
z
e
.
F
i
g
u
r
e
3
a
n
d
T
ab
le
1
s
h
o
w
t
h
at
p
r
o
p
o
s
ed
m
et
h
o
d
(
I
VD)
y
ield
s
th
e
h
ig
h
est
p
er
f
o
r
m
a
n
ce
o
f
5
.
8
5
×
10
4
er
r
o
r
p
ix
els
w
it
h
t
h
e
lo
w
es
t
s
ta
n
d
ar
d
d
ev
iatio
n
o
f
0
.
9
7
×
10
3
p
ix
els,
w
h
ic
h
is
b
etter
t
h
an
th
e
o
t
h
er
s
.
I
n
Fi
g
u
r
e
s
3
an
d
4
,
w
e
ca
n
o
b
s
er
v
e
th
at
th
e
I
VD
m
et
h
o
d
is
g
e
n
er
al
l
y
m
o
r
e
ac
c
u
r
ate
t
h
a
n
all
o
f
t
h
e
o
th
er
m
et
h
o
d
s
.
E
s
p
ec
iall
y
i
n
t
h
e
ca
s
e
o
f
lar
g
e
v
ar
iat
io
n
in
ill
u
m
in
atio
n
,
t
h
e
I
VD
m
e
th
o
d
e
x
h
i
b
its
s
u
p
er
io
r
i
m
a
g
e
s
eg
m
e
n
t
atio
n
r
es
u
lt
s
(
i.e
.
,
i
t
u
n
i
f
o
r
m
l
y
s
e
g
m
e
n
t
e
d
p
i
x
e
l
s
o
f
c
r
o
p
l
e
a
f
f
r
o
m
b
a
c
k
g
r
o
u
n
d
)
c
o
m
p
a
r
e
d
w
i
t
h
t
h
e
O
t
s
u
,
E
x
G
R
,
C
I
V
E
a
n
d
E
x
G
m
e
t
h
o
d
s
.
T
ab
le
1
.
P
er
f
o
r
m
a
n
ce
o
f
I
VD
i
n
ter
m
s
o
f
d
etec
tio
n
ac
c
u
r
ac
y
M
e
t
h
o
d
Er
r
o
r
M
e
a
n
(
×
10
4
,
p
i
x
e
l
s)
Er
r
o
r
(
%)
S
.
D
(
×
10
3
,
p
i
x
e
l
s
)
I
V
D
5
.
8
5
1
9
.
1
0
.
9
7
O
t
su
7
.
4
9
2
4
.
4
4
.
6
9
Ex
G
7
.
6
4
2
4
.
9
4
.
8
5
Ex
G
R
1
0
.
8
1
3
5
.
2
3
.
2
5
C
I
V
E
7
.
2
2
2
3
.
5
1
2
.
0
6
Ex
R
7
.
0
4
2
2
.
9
9
.
0
2
V
EG
7
.
3
7
2
3
.
9
5
.
7
4
Fig
u
r
e
3
.
E
x
p
er
i
m
en
ts
f
o
r
illu
m
i
n
atio
n
i
n
v
ar
ian
t
b
ased
r
o
w
d
etec
tio
n
in
p
ad
d
y
f
ield
T
h
e
Ots
u
m
et
h
o
d
d
eter
m
i
n
es
th
e
t
h
r
es
h
o
ld
d
y
n
a
m
ica
ll
y
a
cc
o
r
d
in
g
to
o
n
l
y
t
h
e
g
r
a
y
le
v
el
o
f
a
n
i
m
a
g
e;
co
n
s
eq
u
en
tl
y
,
t
h
e
i
m
ag
e
s
eg
m
en
tatio
n
r
es
u
lt
s
w
er
e
u
n
i
f
o
r
m
an
d
lo
w
-
q
u
alit
y
,
an
d
t
h
e
alg
o
r
ith
m
d
id
n
o
t
r
e
m
o
v
e
p
ar
tial
s
h
ad
o
w
s
o
r
r
e
f
lectio
n
s
.
T
h
e
E
x
G
an
d
VE
G
m
et
h
o
d
s
y
ield
ed
b
l
u
r
r
y
cr
o
p
leaf
ar
ea
s
b
ec
a
u
s
e
th
ese
m
eth
o
d
s
e
m
p
h
asize
o
n
l
y
t
h
e
g
r
ee
n
c
h
an
n
el
a
m
o
n
g
t
h
e
R
GB
c
h
an
n
el
s
.
Mo
r
eo
v
er
,
th
e
E
x
G
R
m
e
th
o
d
id
en
ti
f
ied
v
er
y
l
ittl
e
cr
o
p
le
af
o
v
er
al
l
b
ec
au
s
e
t
h
e
eq
u
at
io
n
ca
n
n
o
t
d
i
s
ti
n
ctl
y
s
e
g
m
e
n
t
cr
o
p
p
ix
el
s
a
n
d
b
ac
k
g
r
o
u
n
d
.
T
h
e
C
I
VE
an
d
E
x
R
m
et
h
o
d
s
w
er
e
o
b
s
er
v
ed
to
h
av
e
a
r
elativ
el
y
n
o
r
m
al
p
er
f
o
r
m
a
n
ce
.
Nev
er
th
e
less
,
th
e
i
m
a
g
e
s
eg
m
en
tatio
n
r
es
u
lts
w
er
e
u
n
i
f
o
r
m
.
T
h
e
p
r
o
p
o
s
ed
m
e
th
o
d
,
th
e
I
V
D
m
et
h
o
d
,
ex
h
ib
its
h
ig
h
ac
c
u
r
ac
y
w
it
h
u
n
i
f
o
r
m
i
m
ag
e
q
u
alit
y
ac
co
r
d
in
g
to
v
ar
y
in
g
ill
u
m
i
n
atio
n
.
0
5
10
15
20
25
30
35
40
45
5
6
7
8
9
10
11
12
x
1
0
4
I
m
age
s
am
ple
num
ber
Abs
olut
e
dif
f
erenc
e
of
im
age
(pix
els
)
O
t
su
E
x
G
E
x
G
R
C
I
V
E
E
x
R
VEG
I
V
D
0
5
10
15
20
25
30
35
40
45
0
2
4
6
8
10
Solar
radiat
ion
(w
/
m
2
,
X10
2
)
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:
2
0
8
8
-
8708
I
llu
min
a
tio
n
-
in
v
a
r
ia
n
t v
eg
eta
t
io
n
d
etec
tio
n
(
I
V
D)
fo
r
a
visi
o
n
s
en
s
o
r
-
b
a
s
ed
…
(
K
eu
n
Ha
C
h
o
i
)
1289
(
a)
(
b
)
(
c)
(
d
)
(
e)
(
f
)
(
g
)
(
h
)
(
i)
Fig
u
r
e
4
.
I
m
a
g
e
s
e
g
m
en
tatio
n
r
esu
lt
s
f
o
r
s
a
m
p
le
i
m
a
g
es c
o
m
p
ar
ed
w
it
h
t
h
e
r
esu
lts
o
f
d
i
f
f
er
en
t
m
e
th
o
d
s
.
T
h
e
im
a
g
es
w
er
e
ac
q
u
ir
ed
in
d
ay
l
ig
h
t
,
(
a)
o
r
ig
in
al,
(
b
)
g
r
o
u
n
d
tr
u
t
h
,
(
c)
p
r
o
p
o
s
ed
m
et
h
o
d
,
(
d
)
o
ts
u
,
(
e)
E
x
G,
(
f
)
E
x
GR
,
(
g
)
C
I
VE
,
(
h
)
E
x
R
,
(
i)
VE
G
3
.
2
.
Wea
t
her
co
nd
it
io
n:
ra
iny
T
h
e
ex
p
er
i
m
e
n
ts
p
er
f
o
r
m
ed
to
v
er
if
y
th
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
cr
o
p
r
o
w
d
etec
t
io
n
u
n
d
er
r
ain
y
co
n
d
itio
n
.
T
h
e
ex
p
er
im
e
n
t
s
it
e
w
as
a
r
ea
l
p
ad
d
y
in
Dae
j
e
o
n
,
So
u
th
Ko
r
ea
(
3
6
.
3
7
N,
1
2
7
.
3
6
E
)
;
am
o
u
n
t
o
f
r
ain
f
al
l
w
as
3
5
.
2
m
m
(
T
h
e
Ko
r
ea
Me
teo
r
o
lo
g
ical
A
d
m
i
n
i
s
tr
atio
n
an
n
o
u
n
ce
d
)
.
T
h
e
ca
m
er
a
w
as
m
o
u
n
ted
o
n
a
b
r
ac
k
et
ap
p
r
o
x
i
m
atel
y
1
.
5
m
a
b
o
v
e
th
e
p
ad
d
y
.
T
h
e
g
r
o
w
t
h
d
a
y
o
f
r
ice
w
as a
b
o
u
t
9
0
d
ay
.
T
h
e
ca
p
tu
r
i
n
g
d
ev
ic
e
u
s
ed
w
as
a
lo
w
-
co
s
t
co
lo
r
web
-
ca
m
er
a
(
Sa
m
s
u
n
g
®,
SP
C
-
A
8
0
0
M)
,
an
d
ca
p
tu
r
ed
th
e
i
m
ag
e
s
a
m
p
les
(
1
5
0
i
m
a
g
es)
d
u
r
i
n
g
a
r
ain
y
.
An
d
ea
ch
s
a
m
p
le
i
m
a
g
es
h
as
b
ee
n
p
h
o
to
g
r
ap
h
ed
f
r
o
m
d
i
f
f
er
en
t
a
n
g
les.
Mo
r
eo
v
er
,
s
ix
o
th
er
co
m
m
o
n
l
y
u
s
ed
alg
o
r
it
h
m
s
w
er
e
al
s
o
ap
p
lied
f
o
r
co
m
p
ar
is
o
n
.
T
h
ey
ar
e
t
h
e
Ot
s
u
,
E
x
G,
E
x
G
R
,
C
I
VE
,
E
x
R
a
n
d
VE
G
m
et
h
o
d
s
.
I
n
ad
d
itio
n
,
t
h
e
g
r
o
u
n
d
-
tr
u
t
h
i
m
a
g
es
w
er
e
s
e
g
m
e
n
ted
m
a
n
u
a
ll
y
u
s
in
g
t
h
e
P
h
o
to
s
h
o
p
s
o
f
t
w
ar
e
p
ac
k
ag
e
(
A
d
o
b
e®)
.
T
o
an
al
y
ze
t
h
e
q
u
an
titati
v
e
p
er
f
o
r
m
an
ce
o
f
p
r
o
p
o
s
ed
m
eth
o
d
as
b
e
f
o
r
e,
a
p
er
f
o
r
m
a
n
ce
i
n
d
ex
to
q
u
a
n
ti
f
y
th
e
m
i
s
clas
s
i
f
icatio
n
er
r
o
r
o
f
th
e
d
if
f
er
en
t
m
et
h
o
d
s
w
as a
p
p
lied
w
it
h
(
1
2
)
.
T
ab
le
2
s
h
o
w
th
at
p
r
o
p
o
s
ed
m
et
h
o
d
(
I
VD)
y
ield
s
t
h
e
h
ig
h
est
p
er
f
o
r
m
a
n
ce
o
f
1
.
7
4
×
10
4
er
r
o
r
p
ix
els
w
it
h
th
e
lo
w
e
s
t
s
ta
n
d
ar
d
d
ev
iatio
n
o
f
4
.
2
8
×
10
3
p
ix
el
s
,
w
h
ic
h
is
b
etter
th
an
t
h
e
o
th
er
s
.
I
n
t
h
e
p
lo
t
o
f
Fi
g
u
r
e
5
an
d
Fi
g
u
r
e
6
,
w
e
ca
n
o
b
s
er
v
e
th
at
t
h
e
I
VD
m
et
h
o
d
is
g
e
n
er
all
y
m
o
r
e
ac
cu
r
ate
t
h
a
n
all
o
f
th
e
o
th
er
m
et
h
o
d
s
.
Sin
ce
a
r
ai
n
y
d
a
y
i
s
n
o
r
m
a
ll
y
c
lo
u
d
y
,
in
s
tead
o
f
t
h
e
il
lu
m
in
a
tio
n
ch
a
n
g
e
is
les
s
,
it
is
lo
w
l
u
m
in
o
u
s
en
v
ir
o
n
m
e
n
t.
T
h
u
s
,
t
h
e
C
I
VE
,
E
x
GR
,
a
n
d
E
x
R
m
et
h
o
d
s
y
i
eld
ed
th
e
i
m
ag
e
s
eg
m
e
n
tati
o
n
r
esu
lt
s
w
er
e
lo
w
-
q
u
alit
y
t
h
at
it
ca
n
n
o
t
d
i
s
ti
n
ct
l
y
s
eg
m
e
n
t
cr
o
p
p
ix
el
s
a
n
d
b
ac
k
g
r
o
u
n
d
.
W
h
er
ea
s
,
t
h
e
E
x
G,
Ot
s
u
a
n
d
VE
G
m
et
h
o
d
s
y
ield
ed
b
lu
r
r
y
cr
o
p
l
ea
f
ar
ea
s
b
ec
a
u
s
e
th
e
s
e
m
et
h
o
d
s
e
m
p
h
asize
o
n
l
y
t
h
e
g
r
ee
n
ch
an
n
el
a
m
o
n
g
th
e
R
GB
ch
a
n
n
els.
E
s
p
ec
iall
y
i
n
ca
s
e
o
f
Ot
s
u
m
eth
o
d
,
it
w
a
s
r
e
m
a
in
ed
t
h
e
s
h
ap
e
o
f
r
ai
n
w
ater
d
r
ip
p
in
g
o
n
b
ac
k
g
r
o
u
n
d
i
m
a
g
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
2
,
A
p
r
il 2
0
2
1
: 1
2
8
4
-
1292
1290
T
ab
le
2
.
P
er
f
o
r
m
a
n
ce
o
f
I
VD
i
n
ter
m
s
o
f
d
etec
tio
n
ac
c
u
r
ac
y
M
e
t
h
o
d
Er
r
o
r
me
a
n
(
×
10
4
,
p
i
x
e
l
s)
Er
r
o
r
(
%)
S
.
D
(
×
10
3
,
p
i
x
e
l
s)
I
V
D
1
.
7
4
5
.
6
4
.
2
8
O
t
su
4
.
7
1
1
5
.
3
7
.
4
7
Ex
G
6
.
2
9
2
0
.
5
7
.
7
4
Ex
G
R
7
.
2
4
2
3
.
6
1
0
.
5
2
C
I
V
E
6
.
8
8
2
2
.
3
9
.
6
2
Ex
R
5
.
5
0
1
7
.
9
1
0
.
0
1
V
EG
1
0
.
5
7
3
4
.
4
8
.
6
7
Fig
u
r
e
5
.
E
x
p
er
i
m
en
tal
r
esu
lts
w
it
h
s
a
m
p
le
i
m
ag
e
t
h
at
w
er
e
ac
q
u
ir
ed
in
r
ain
y
: c
o
m
p
ar
is
o
n
r
esu
lt
s
r
eg
ar
d
in
g
th
e
ab
s
o
lu
te
d
i
f
f
er
en
ce
b
et
w
ee
n
th
e
i
m
a
g
e
an
d
t
h
e
g
r
o
u
n
d
-
tr
u
th
i
m
a
g
e
(
a)
(
b
)
(
c)
(
d
)
(
e)
(
f
)
(
g
)
Fig
u
r
e
6
.
I
m
a
g
e
s
e
g
m
en
tatio
n
r
esu
lt
s
f
o
r
s
a
m
p
le
i
m
a
g
es c
o
m
p
ar
ed
w
it
h
t
h
e
r
esu
lts
o
f
d
i
f
f
er
en
t
m
e
th
o
d
s
.
T
h
e
im
a
g
es
w
er
e
ac
q
u
ir
ed
o
n
a
r
ain
y
d
a
y
,
(
a)
o
r
ig
in
al,
(
b
)
g
r
o
u
n
d
tr
u
t
h
,
(
c)
p
r
o
p
o
s
ed
m
et
h
o
d
,
(
d
)
E
x
G,
(
e
)
E
x
GR
,
(
f
)
C
I
VE
,
(
g
)
VE
G
0
50
100
150
0
2
4
6
8
10
12
14
x
1
0
4
I
m
age
s
am
ple
num
ber
Abs
olut
e
dif
f
erenc
e
of
im
age
(pix
els
)
O
t
s
u
EG
E
x
G
R
C
I
V
E
E
x
R
VEG
I
V
D
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:
2
0
8
8
-
8708
I
llu
min
a
tio
n
-
in
v
a
r
ia
n
t v
eg
eta
t
io
n
d
etec
tio
n
(
I
V
D)
fo
r
a
visi
o
n
s
en
s
o
r
-
b
a
s
ed
…
(
K
eu
n
Ha
C
h
o
i
)
1291
4.
CO
NCLU
SI
O
N
I
n
th
i
s
p
ap
er
,
w
e
p
r
o
p
o
s
ed
a
n
o
v
el
v
e
g
etatio
n
d
etec
tio
n
m
eth
o
d
f
o
r
v
is
io
n
-
b
ased
ag
r
icu
l
tu
r
al
ap
p
licatio
n
s
in
t
y
p
ical
o
u
td
o
o
r
s
ettin
g
s
an
d
v
er
i
f
ied
th
e
s
u
p
er
io
r
p
er
f
o
r
m
a
n
ce
o
f
m
et
h
o
d
in
co
m
p
ar
is
o
n
w
it
h
s
ix
d
if
f
er
en
t
m
et
h
o
d
s
.
O
u
r
m
et
h
o
d
h
a
s
s
o
m
e
s
tr
en
g
t
h
s
,
in
cl
u
d
in
g
lo
w
co
m
p
u
tatio
n
a
l
co
s
t,
co
m
p
u
tatio
n
al
s
i
m
p
lic
it
y
a
n
d
u
n
if
o
r
m
l
y
h
i
g
h
-
ac
c
u
r
ac
y
i
m
a
g
e
s
e
g
m
en
tat
i
o
n
.
I
n
th
e
f
u
t
u
r
e,
it
w
ill
b
e
n
ec
es
s
ar
y
to
ap
p
ly
v
ar
io
u
s
cr
o
p
s
f
o
r
v
e
r
i
f
y
in
g
v
er
s
atile
ap
p
licatio
n
s
o
f
th
e
p
r
o
p
o
s
ed
m
e
th
o
d
.
RE
F
E
R
E
NC
E
S
[1
]
M
e
n
g
n
i
Ye
.
,
Zh
ig
u
o
Ca
o
.
,
Z
h
e
n
g
h
o
n
g
Y
u
.
,
X
ia
o
d
o
n
g
Ba
i,
“
Cr
o
p
f
e
a
tu
re
e
x
trac
ti
o
n
f
ro
m
i
m
a
g
e
s
w
i
th
p
r
o
b
a
b
il
isti
c
su
p
e
rp
ix
e
l
M
a
rk
o
v
ra
n
d
o
m
f
ield
,
”
Co
mp
u
ter
s a
n
d
El
e
c
tro
n
ics
in
A
g
ric
u
lt
u
re
,
v
o
l.
1
1
4
,
p
p
.
2
4
7
-
2
6
0
,
2
0
1
5
.
[2
]
D.
M
.
W
o
e
b
b
e
c
k
e
.
,
G
.
E.
M
e
y
e
r.
,
K.
Vo
n
Ba
rg
e
n
.
,
D
.
A
.
M
o
rten
s
e
n
,
“
Co
lo
r
in
d
ice
s
f
o
r
we
e
d
id
e
n
t
if
ica
ti
o
n
u
n
d
e
r
v
a
rio
u
s so
il
,
re
sid
u
e
,
a
n
d
li
g
h
ti
n
g
c
o
n
d
i
ti
o
n
s,”
T
ra
n
sa
c
ti
o
n
s
o
f
t
h
e
AS
AE
,
v
o
l.
3
8
,
n
o
.
1
,
p
p
.
2
5
9
-
2
6
9
,
1
9
9
5
.
[3
]
Ne
to
.
J.
C
.
,
“
A
Co
m
b
in
e
d
S
tatisti
c
a
l
-
S
o
f
t
Co
m
p
u
ti
n
g
A
p
p
ro
a
c
h
fo
r
Clas
sif
ica
ti
o
n
a
n
d
M
a
p
p
in
g
W
e
e
d
S
p
e
c
ies
in
M
in
im
u
m
-
ti
ll
a
g
e
S
y
ste
m
s,”
P
h
.
D
o
f
T
h
e
sis,
Un
iv
e
rsit
y
o
f
N
e
b
ra
sk
a
,
U.S
.
A
.
,
2
0
0
4
.
[4
]
M
e
y
e
r
G
.
E.
,
Hin
d
m
a
n
T
.
W
.
,
Lak
s
m
i
K.,
“
M
a
c
h
in
e
v
isio
n
d
e
tec
ti
o
n
p
a
ra
m
e
ter
s
f
o
r
p
lan
t
sp
e
c
ies
id
e
n
ti
f
ica
ti
o
n
,
”
Pre
c
isio
n
a
g
ric
u
lt
u
re
a
n
d
B
io
l
o
g
i
c
a
l
Qu
a
li
ty
,
v
o
l
.
3
5
4
3
,
1
9
9
9
.
[5
]
P
e
re
z
A
.
,
L
o
p
e
z
F
.
,
Be
n
ll
o
c
h
J.,
Ch
risten
se
n
S
.
,
“
Co
l
o
u
r
a
n
d
sh
a
p
e
a
n
a
l
y
sis
tec
h
n
iq
u
e
s
f
o
r
w
e
e
d
d
e
tec
ti
o
n
in
c
e
re
a
l
f
ield
s,”
Co
mp
u
ter
s a
n
d
El
e
c
tro
n
i
c
s in
Ag
ric
u
lt
u
re
, v
o
l.
2
5
,
n
o
.
3
,
p
p
.
1
9
7
-
2
1
2
,
2
0
0
0
.
[6
]
Ka
tao
k
a
T
.
,
Ka
n
e
k
o
T
.
,
Ok
a
m
o
to
H.,
Ha
ta
S
.
,
“
Cro
p
g
ro
w
th
e
stim
a
ti
o
n
sy
ste
m
u
sin
g
m
a
c
h
in
e
v
isio
n
,
”
Pro
c
e
e
d
in
g
s
2
0
0
3
IE
EE
/A
S
M
E
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
A
d
v
a
n
c
e
d
In
tell
ig
e
n
t
M
e
c
h
a
tr
o
n
ics
(
AIM
2
0
0
3
)
,
Ko
b
e
,
Ja
p
an
,
v
o
l.
2
,
2
0
0
3
,
pp
.
b
1
0
7
9
-
b
1
0
8
3
.
[7
]
Ha
g
u
e
T
.
,
T
il
lett
N.,
W
h
e
e
l
e
r
H
.
,
“
A
u
to
m
a
ted
c
ro
p
a
n
d
we
e
d
m
o
n
it
o
rin
g
in
w
id
e
ly
sp
a
c
e
d
c
e
re
a
ls,”
Pre
c
isio
n
Ag
ric
u
lt
u
re
,
v
o
l.
7
,
n
o
.
1
,
p
p
.
2
1
-
3
2
,
2
0
0
6
.
[8
]
Otsu
N.,
“
A
th
re
sh
o
ld
se
lec
ti
o
n
m
e
th
o
d
f
ro
m
g
ra
y
-
lev
e
l
h
isto
g
ra
m
s,”
in
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
S
y
ste
ms
,
M
a
n
,
a
n
d
Cy
b
e
rn
e
ti
c
s
,
v
o
l.
9
,
n
o
.
1
,
p
p
.
6
2
-
6
6
,
1
9
7
9
.
[9
]
Ru
iz
-
Ru
iz
G
.
,
G
ó
m
e
z
-
G
il
J.,
Na
v
a
s
-
G
ra
c
ia
L
.
,
“
T
e
stin
g
d
iff
e
r
e
n
t
c
o
lo
r
sp
a
c
e
s
b
a
se
d
o
n
h
u
e
f
o
r
th
e
e
n
v
iro
n
m
e
n
tally
a
d
a
p
t
i
v
e
s
e
g
m
e
n
t
a
t
i
o
n
a
l
g
o
r
i
t
h
m
(
E
A
S
A
)
,
”
C
o
m
p
u
t
e
r
s
a
n
d
E
l
e
c
t
r
o
n
i
c
s
i
n
A
g
r
i
c
u
l
t
u
r
e
,
v
o
l
.
6
8
,
n
o
.
1
,
p
p
.
8
8
-
9
6
,
2
0
0
9
.
[1
0
]
T
ian
L
.
F
.
,
S
lau
g
h
ter
D.
C.
,
“
En
v
iro
n
m
e
n
tall
y
a
d
a
p
ti
v
e
se
g
m
e
n
ta
ti
o
n
a
lg
o
rit
h
m
f
o
r
o
u
td
o
o
r
im
a
g
e
se
g
m
e
n
tatio
n
,
”
Co
mp
u
ter
s
a
n
d
El
e
c
tro
n
ics
in
Ag
ric
u
lt
u
re
, v
o
l.
2
1
,
n
o
.
3
,
p
p
.
1
5
3
-
1
6
8
,
1
9
9
8
.
[1
1
]
Yu
Z.
,
Ca
o
Z.
,
W
u
X
.
,
Ba
i
X.,
Qin
Y.,
Z
h
u
o
W
.
,
X
iao
Y.,
Zh
a
n
g
X
.
,
X
u
e
H.
,
“
A
u
to
m
a
ti
c
i
m
a
g
e
-
b
a
se
d
d
e
tec
ti
o
n
tec
h
n
o
l
o
g
y
f
o
r
t
w
o
c
rit
ica
l
g
ro
w
th
sta
g
e
s
o
f
m
a
ize
:
e
m
e
rg
e
n
c
e
a
n
d
th
re
e
-
lea
f
st
a
g
e
,
”
Ag
ric
u
lt
u
ra
l
a
n
d
Fo
re
st
M
e
teo
ro
l
ogy
,
v
o
l
.
1
7
4
-
1
7
5
,
p
p
.
6
5
-
8
4
,
2
0
13.
[1
2
]
Zh
e
n
g
L
.
,
Zh
a
n
g
J.,
W
a
n
g
Q.,
“
M
e
a
n
-
sh
if
t
-
b
a
se
d
c
o
lo
r
se
g
m
e
n
tatio
n
o
f
im
a
g
e
s
c
o
n
tain
in
g
g
re
e
n
v
e
g
e
tatio
n
,
”
Co
mp
u
ter
s
a
n
d
El
e
c
tro
n
ics
in
Ag
ric
u
lt
u
re
,
v
o
l.
6
5
,
n
o
.
1
,
p
p
.
9
3
-
9
8
,
2
0
0
9
.
[1
3
]
G
u
o
W
.
,
R
a
g
e
U.K.,
Nin
o
m
i
y
a
S
.
,
“
Ill
u
m
in
a
ti
o
n
in
v
a
rian
t
se
g
m
e
n
tatio
n
o
f
v
e
g
e
tatio
n
f
o
r
ti
m
e
se
ries
w
h
e
a
t
i
m
a
g
e
s
b
a
se
d
o
n
d
e
c
isio
n
tree
m
o
d
e
l,
”
C
o
mp
u
ter
s
a
n
d
El
e
c
tro
n
ics
in
Ag
ri
c
u
lt
u
re
, v
o
l.
9
6
,
p
p
.
58
-
6
6
,
2
0
1
3
.
[1
4
]
M
o
n
talv
o
M
.
,
G
u
e
rre
ro
J.
M
.
,
Ro
m
e
o
J.,
Emm
i
L
.
,
G
u
ij
a
rro
M
.
,
P
a
jare
s
G
.
,
“
A
u
to
m
a
ti
c
e
x
p
e
rt
sy
ste
m
f
o
r
w
e
e
d
s
/
c
r
o
p
s
i
d
e
n
t
i
f
i
c
a
t
i
o
n
i
n
i
m
a
g
e
s
f
r
o
m
m
a
i
z
e
f
i
e
l
d
s
,
”
E
x
p
e
r
t
S
y
s
t
e
m
i
n
A
p
p
l
i
c
a
t
i
o
n
,
v
o
l
.
4
0
,
n
o
.
1
,
p
p
.
7
5
-
8
2
,
2
0
1
3
.
[1
5
]
Ba
i
X
.
,
Ca
o
Z.
,
W
a
n
g
Y.,
Yu
Z.
,
Zh
a
n
g
X
.
,
L
i
C.
,
“
Cro
p
se
g
m
e
n
tatio
n
f
ro
m
i
m
a
g
e
s b
y
m
o
rp
h
o
lo
g
y
m
o
d
e
li
n
g
in
th
e
CIE
L
⁄
a
⁄
b
⁄
c
o
l
o
r
sp
a
c
e
,
”
Co
m
p
u
t
e
rs
a
n
d
El
e
c
tro
n
ics
i
n
A
g
ric
u
lt
u
re
, v
o
l.
9
9
,
p
p
.
21
-
3
4
,
2
0
1
3
.
[1
6
]
S
c
h
ick
,
A
.
,
Ba
u
m
l
M
.
,
S
ti
e
f
e
lh
a
g
e
n
R.
,
“
Im
p
ro
v
in
g
f
o
re
g
ro
u
n
d
se
g
m
e
n
tatio
n
w
it
h
p
r
o
b
a
b
i
li
stic
su
p
e
rp
ix
e
l
M
a
rk
o
v
ra
n
d
o
m
f
ield
s,”
2
0
1
2
I
EE
E
C
o
mp
u
ter
S
o
c
iety
C
o
n
fer
e
n
c
e
o
n
Co
m
p
u
ter
V
isio
n
a
n
d
P
a
tt
e
rn
Rec
o
g
n
it
i
o
n
W
o
rk
sh
o
p
s
,
P
r
o
v
id
e
n
c
e
,
RI
,
2
0
1
2
,
p
p
.
2
7
-
31.
[1
7
]
Ka
izu
,
Y.,
a
n
d
Im
o
u
K.
A
,
“
Du
a
l
-
sp
e
c
tral
c
a
m
e
r
a
s
y
ste
m
f
o
r
p
a
d
d
y
ric
e
se
e
d
li
n
g
ro
w
d
e
te
c
ti
o
n
,
”
Co
mp
u
ter
s
a
n
d
El
e
c
tro
n
ics
in
Ag
ric
u
lt
u
re
, v
o
l
.
6
3
,
n
o
.
1
,
p
p
.
49
-
5
6
,
2
0
0
8
.
[1
8
]
He
rv
á
s
-
M
a
rtí
n
e
z
C.
,
G
u
ti
é
rre
z
P
.
A
.
,
P
e
ñ
á
-
Ba
rra
g
á
n
J.
M
.
,
Ju
ra
d
o
-
Ex
p
ó
sit
o
M
.
,
L
ó
p
e
z
-
G
ra
n
a
d
o
s
F
.
,
“
A
lo
g
isti
c
ra
d
ial
b
a
sis
f
u
n
c
ti
o
n
re
g
re
ss
io
n
m
e
th
o
d
f
o
r
d
isc
rim
in
a
ti
o
n
o
f
c
o
v
e
r
c
ro
p
s
in
o
li
v
e
o
rc
h
a
rd
s,”
Exp
e
rt
S
y
ste
m
in
Ap
p
li
c
a
ti
o
n
,
v
o
l.
3
7
,
n
o
.
1
2
,
p
p
.
8
4
3
2
-
8
4
4
4
,
2
0
1
0
.
[1
9
]
G
u
e
rre
ro
J.
M
.
,
G
u
ij
a
rro
M
.
,
M
o
n
talv
o
M
.
,
Ro
m
e
o
J.,
Emm
i
L
.
,
Rib
e
iro
A
.
,
P
a
jare
s
G
.
,
“
A
u
to
m
a
t
ic
e
x
p
e
rt
s
y
ste
m
b
a
se
d
o
n
im
a
g
e
s
f
o
r
a
c
c
u
ra
c
y
c
r
o
p
r
o
w
d
e
tec
ti
o
n
i
n
m
a
ize
f
ield
s,”
Exp
e
rt
S
y
ste
m
wit
h
Ap
p
li
c
a
ti
o
n
,
v
o
l.
4
0
,
n
o
.
2
,
p
p
.
6
5
6
-
6
6
4
,
2
0
1
3
.
[2
0
]
G
é
e
C.
,
Bo
ss
u
J.,
J
o
n
e
s
G
.
,
T
ru
c
h
e
tet
F
.
,
“
Cro
p
/w
e
e
d
d
isc
rim
in
a
ti
o
n
in
p
e
rsp
e
c
ti
v
e
a
g
ro
n
o
m
ic
ima
g
e
s,”
Co
mp
u
ter
s
a
n
d
El
e
c
tro
n
ics
in
A
g
ric
u
lt
u
re
,
v
o
l.
6
0
,
n
o
.
1
,
p
p
.
4
9
-
5
9
,
2
0
0
8
.
[2
1
]
Cru
z
-
Ra
m
ír
e
z
M
.
,
He
rv
á
s
-
M
a
rtí
n
e
z
C.
,
Ju
ra
d
o
-
Ex
p
ó
sito
M
.
,
L
ó
p
e
z
-
G
ra
n
a
d
o
s
F
.
,
“
A
m
u
lt
i
-
o
b
jec
ti
v
e
n
e
u
ra
l
n
e
tw
o
rk
b
a
se
d
m
e
th
o
d
f
o
r
c
o
v
e
r
c
ro
p
i
d
e
n
ti
f
ica
ti
o
n
f
ro
m
re
m
o
te
se
n
se
d
d
a
ta,”
Exp
e
rt
S
y
ste
m
wi
th
Ap
p
li
c
a
ti
o
n
,
v
o
l.
3
9
,
n
o
.
1
1
,
pp.
1
0
0
3
8
-
1
0
0
4
8
,
2
0
1
2
.
[2
2
]
X
a
v
ier
P
.
,
B
u
rg
o
s
-
A
rti
z
z
u
a
,
A
n
g
e
la
R.
,
M
a
r
ia
G
.
,
G
o
n
z
a
lo
P
a
-
jar
e
s,
“
Re
a
l
-
ti
m
e
i
m
a
g
e
p
ro
c
e
ss
in
g
f
o
r
c
ro
p
/w
e
e
d
d
isc
rim
in
a
ti
o
n
i
n
m
a
ize
f
ield
s,”
Co
mp
u
ter
s
a
n
d
El
e
c
tro
n
ics
in
Ag
ri
c
u
lt
u
re
,
v
o
l.
7
5
,
n
o
.
2
,
p
p
.
3
3
7
-
3
4
6
,
2
0
1
1
.
[2
3
]
Ba
k
k
e
r
T
.
,
W
o
u
ters
H.,
V
a
n
A
ss
e
lt
K.,
Bo
n
tse
m
a
J.,
Tan
g
L
.
,
M
ü
ll
e
r
J.,
v
a
n
S
trate
n
G
.
,
“
A
v
i
sio
n
b
a
se
d
r
o
w
d
e
tec
ti
o
n
sy
ste
m
f
o
r
su
g
a
r
b
e
e
t,
”
Co
mp
u
ter
s
a
n
d
El
e
c
tro
n
ics
in
Ag
ric
u
lt
u
re
,
v
o
l.
6
0
,
n
o
.
1
,
p
p
.
8
7
-
9
5
,
2
0
0
8
.
[2
4
]
Ba
jcs
y
R.
,
L
e
e
S
.
W
.
,
Leo
n
a
rd
is
A
.
,
“
D
e
tec
ti
o
n
o
f
d
iff
u
se
a
n
d
sp
e
c
u
lar
in
terf
a
c
e
re
f
le
c
ti
o
n
s
a
n
d
in
t
e
r
-
re
f
l
e
c
ti
o
n
s
b
y
c
o
lo
r
im
a
g
e
se
g
m
e
n
tatio
n
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
C
o
mp
u
ter
V
isio
n
,
v
o
l.
1
7
,
n
o
.
3
,
p
p
.
2
4
1
-
2
7
2
,
1
9
9
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
2
,
A
p
r
il 2
0
2
1
: 1
2
8
4
-
1292
1292
[2
5
]
Ke
u
n
Ha
C
h
o
i,
S
a
n
g
Kw
o
n
Ha
n
,
S
a
n
g
Ho
o
n
Ha
n
,
Kw
a
n
g
-
Ho
P
a
rk
,
Ky
u
n
g
-
S
o
o
Kim
,
S
o
o
h
y
u
n
Kim
,
“
M
o
r
p
h
o
lo
g
y
-
b
a
se
d
g
u
id
a
n
c
e
li
n
e
e
x
trac
ti
o
n
f
o
r
a
n
a
u
to
n
o
m
o
u
s
w
e
e
d
in
g
ro
b
o
t
in
p
a
d
d
y
f
ield
s,”
Co
mp
u
ter
s
a
n
d
El
e
c
tro
n
ics
in
Ag
ric
u
lt
u
re
,
v
o
l.
1
1
3
,
p
p
.
2
6
6
-
2
7
4
,
2
0
1
5
.
[2
6
]
W
o
n
S
u
k
L
e
e
,
a
n
d
A
li
V
a
r
d
a
r,
“
Im
m
a
tu
re
p
e
a
c
h
d
e
tec
ti
o
n
in
c
o
lo
u
r
im
-
a
g
e
s
a
c
q
u
ired
in
n
a
tu
ra
l
il
lu
m
in
a
ti
o
n
c
o
n
d
i
ti
o
n
s u
si
n
g
sta
ti
stica
l
c
las
sifiers
a
n
d
n
e
u
ra
l
n
e
tw
o
rk
,
”
Pre
c
isio
n
A
g
ric
u
lt
u
re
,
v
o
l.
1
5
,
p
p
.
57
-
7
9
,
2
0
1
4
.
[2
7
]
W
e
i
G
u
o
.
,
Ud
a
y
K.
Ra
g
e
.
,
S
e
ish
i
Nin
o
m
i
y
,
“
Ill
u
m
in
a
ti
o
n
i
n
v
a
ri
a
n
t
se
g
m
e
n
tatio
n
o
f
v
e
g
e
tatio
n
fo
r
ti
m
e
se
ries
w
h
e
a
t
i
m
a
g
e
s b
a
se
d
o
n
d
e
c
isio
n
t
re
e
m
o
d
e
l,
”
Co
mp
u
ter
s a
n
d
E
lec
tro
n
ics
in
Ag
ric
u
lt
u
re
,
v
o
l
.
9
6
,
p
p
.
58
-
6
6
,
2
0
1
3
.
[2
8
]
A
lb
e
rto
T
e
ll
a
e
c
h
e
,
X
a
v
ier
P
.
,
Bu
rg
o
s
-
A
rti
z
z
u
,
G
o
n
z
a
lo
P
a
jare
s,
A
n
g
e
la
Rib
e
i
-
ro
,
“
A
v
isio
n
-
ba
se
d
m
e
th
o
d
f
o
r
w
e
e
d
s id
e
n
ti
f
ica
ti
o
n
t
h
ro
u
g
h
t
h
e
Ba
y
e
sia
n
d
e
c
isio
n
th
e
o
ry
,
”
Pa
tt
e
r
n
Rec
o
g
n
it
i
o
n
,
v
o
l.
4
1
,
n
o
.
2
,
p
p
.
521
-
5
3
0
,
2
0
0
8
.
[2
9
]
X
a
v
ier
P
.
,
Bu
rg
o
s
-
A
rti
z
z
u
,
A
n
g
e
la
Rib
e
iro
,
A
lb
e
rto
T
e
ll
a
e
c
h
e
,
G
o
n
z
a
lo
P
a
jare
s
,
Ce
sa
r
F
e
rn
á
n
d
e
z
-
Qu
in
tan
il
l
,
“
A
n
a
l
y
sis
o
f
n
a
tu
r
a
l
i
m
a
g
e
s
p
ro
c
e
ss
in
g
f
o
r
th
e
e
x
tra
c
ti
o
n
o
f
a
g
ric
u
lt
u
ra
l
e
lem
e
n
ts,”
Ima
g
e
a
n
d
Vi
s
io
n
C
o
mp
u
ti
n
g
,
v
o
l.
2
8
,
n
o
.
1
,
p
p
.
1
3
8
-
1
4
9
,
2
0
1
0
.
[3
0
]
Ef
th
im
ia
M
a
v
rid
o
u
,
El
e
n
i
V
r
o
c
h
i
d
o
u
,
G
e
o
rg
e
A
.
P
a
p
a
k
o
sta
s,
T
h
e
o
d
o
re
P
a
c
h
id
is,
V
a
ss
il
is
G
.
Ka
b
u
rl
a
so
s,
“
M
a
c
h
in
e
V
isio
n
S
y
ste
m
s i
n
P
re
c
isio
n
A
g
ricu
lt
u
re
f
o
r
Cro
p
F
a
rm
in
g
,
”
J
o
u
rn
a
l
o
f
Ima
g
in
g
,
v
o
l
.
5
,
n
o
.
1
2
,
p
p
.
89
-
12
2
,
2
0
1
9
.
[3
1
]
S
iv
a
lo
g
e
s
w
a
ra
n
,
Ra
tn
a
sin
g
a
m
,
S
tev
e
Co
ll
in
s
,
“
S
tu
d
y
o
f
th
e
p
h
o
t
o
d
e
tec
to
r
c
h
a
ra
c
teristics
o
f
a
c
a
m
e
ra
f
o
r
c
o
lo
r
c
o
n
sta
n
c
y
in
n
a
tu
ra
l
sc
e
n
e
s,”
J
o
u
rn
a
l
o
f
t
h
e
Op
ti
c
a
l
S
o
c
iety
o
f
Ame
ric
a
, v
o
l.
2
7
,
n
o
.
2
,
p
p
.
2
8
6
-
2
9
4
,
2
0
1
0
.
[3
2
]
K.
H.
S
u
h
,
S
.
R.
S
u
h
,
J.
H.
S
u
n
g
,
“
A
f
u
n
d
a
m
e
n
tal
stu
d
y
o
n
d
e
tec
ti
o
n
o
f
we
e
d
s
in
p
a
d
d
y
f
ield
u
sin
g
sp
e
c
tro
p
h
o
t
o
m
e
tri
c
a
n
a
l
y
sis,”
Ag
r
icu
lt
u
ra
l
M
e
c
h
a
n
iz
a
ti
o
n
in
K
o
re
a
, v
o
l.
2
7
,
p
p
.
1
3
3
-
1
4
2
,
2
0
0
2
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
K
e
u
n
H
a
Cho
i
is
a
P
h
.
D
.
in
t
h
e
De
p
a
rtm
e
n
t
o
f
M
e
c
h
a
n
ica
l
En
g
in
e
e
rin
g
,
Ko
re
a
A
d
v
a
n
c
e
d
In
stit
u
te
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
(K
A
IS
T
).
His
re
se
a
rc
h
in
tere
st
is
v
isio
n
–
b
a
se
d
a
u
to
n
o
m
o
u
s
ro
b
o
t
a
n
d
ro
b
o
t
m
o
ti
o
n
c
o
n
tr
o
l.
S
o
o
H
y
u
n
K
i
m
P
ro
f
e
ss
o
r
a
t
th
e
De
p
a
rtme
n
t
o
f
M
e
c
h
a
n
ica
l
En
g
in
e
e
rin
g
,
Ko
re
a
A
d
v
a
n
c
e
d
In
stit
u
te
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
(K
A
IS
T
).
He
re
c
e
iv
e
d
h
is
P
h
.
D
f
ro
m
I
m
p
e
rial
Co
ll
e
g
e
o
f
L
o
n
d
o
n
i
n
1
9
9
1
.
H
i
s
r
e
s
e
a
r
c
h
i
n
t
e
r
e
s
t
i
s
B
i
o
-
i
n
s
p
i
r
e
d
r
o
b
o
t
,
a
p
p
l
i
e
d
o
p
t
i
c
s
a
n
d
a
u
t
o
n
o
m
o
u
s
r
o
b
o
t
.
Evaluation Warning : The document was created with Spire.PDF for Python.