I
nte
rna
t
io
na
l J
o
urna
l o
f
Adv
a
nces in Applie
d Science
s
(
I
J
AAS)
Vo
l.
1
5
,
No
.
2
,
J
u
n
e
20
2
6
,
p
p
.
451
~
4
6
1
I
SS
N:
2252
-
8
8
1
4
,
DOI
:
1
0
.
1
1
5
9
1
/ijaas
.
v
1
5
.
i
2
.
pp
451
-
4
6
1
451
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
a
s
.
ia
esco
r
e.
co
m
Co
mpa
riso
n of t
h
erma
l and no
n
-
th
erma
l ima
g
es for
tom
a
to
fruit
det
e
ction
Su
lf
a
y
a
nti
F
a
ha
rudd
in Situj
u
1
,
Wa
wa
n F
irg
ia
wa
n
1,
2
,
H
ir
o
no
ri
T
a
k
im
o
t
o
3
1
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
c
s
,
F
a
c
u
l
t
y
o
f
En
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
a
s
S
u
l
a
w
e
s
i
B
a
r
a
t
,
M
a
m
u
j
u
,
I
n
d
o
n
e
s
i
a
2
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
S
t
u
d
y
C
e
n
t
e
r
,
U
n
i
v
e
r
si
t
a
s
S
u
l
a
w
e
s
i
B
a
r
a
t
,
M
a
mu
j
u
,
I
n
d
o
n
e
si
a
3
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
a
n
d
C
o
m
mu
n
i
c
a
t
i
o
n
En
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
a
n
d
S
y
st
e
ms
En
g
i
n
e
e
r
i
n
g
,
O
k
a
y
a
m
a
P
r
e
f
e
c
t
u
r
a
l
U
n
i
v
e
r
si
t
y
,
S
o
j
a
,
Ja
p
a
n
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
27
,
2
0
2
4
R
ev
is
ed
Mar
5
,
2
0
2
6
Acc
ep
ted
Ap
r
22
,
2
0
2
6
F
a
rm
e
rs
u
se
m
a
n
u
a
l
o
b
se
rv
a
ti
o
n
t
o
so
rt,
g
ra
d
e
,
a
n
d
e
stim
a
te
to
m
a
to
p
ro
d
u
c
ti
o
n
re
su
lt
s
t
o
m
e
e
t
m
a
rk
e
t
d
e
m
a
n
d
s.
H
o
we
v
e
r,
t
h
is
m
e
th
o
d
re
q
u
ires
a
lo
t
o
f
e
n
e
r
g
y
a
n
d
ti
m
e
,
m
a
k
i
n
g
it
u
n
s
u
it
a
b
le
f
o
r
larg
e
-
sc
a
le
to
m
a
to
c
u
lt
iv
a
ti
o
n
u
ti
li
z
i
n
g
t
h
e
d
e
tec
ti
o
n
p
ro
c
e
ss
.
T
h
is
st
u
d
y
a
ims
to
d
e
v
e
lo
p
t
h
e
a
u
to
m
a
ti
c
t
o
m
a
to
d
e
tec
ti
o
n
tec
h
n
o
l
o
g
y
in
a
n
in
d
u
strial
e
n
v
iro
n
m
e
n
t
b
a
se
d
o
n
a
c
o
n
v
e
y
o
r
b
e
lt
b
y
u
sin
g
t
h
e
rm
a
l
o
r
n
o
n
-
t
h
e
rm
a
l
ima
g
in
g
a
n
d
y
o
u
o
n
l
y
lo
o
k
o
n
c
e
v
e
rsio
n
8
(
YO
LOv
8
)
.
Th
e
d
a
tas
e
t
c
o
n
sists
o
f
5
7
0
ima
g
e
s
o
b
tain
e
d
fro
m
e
a
c
h
th
e
rm
a
l
a
n
d
n
o
n
-
t
h
e
rm
a
l
c
a
m
e
r
a
a
n
d
h
a
s
u
n
d
e
rg
o
n
e
a
u
g
m
e
n
tatio
n
tec
h
n
iq
u
e
s
to
e
n
rich
t
h
e
d
a
ta
v
a
riety
.
T
h
e
m
o
d
e
l
wa
s
train
e
d
a
n
d
v
a
li
d
a
ted
u
sin
g
6
4
0
×
6
4
0
-
p
ix
e
l
ima
g
e
s
fo
r
4
0
e
p
o
c
h
s.
I
n
th
is
p
a
p
e
r,
we
c
o
n
d
u
c
t
a
c
o
m
p
a
ra
ti
v
e
a
n
a
ly
sis
o
f
th
e
to
m
a
to
d
e
tec
ti
o
n
r
e
su
lt
u
si
n
g
Y
OLOv
8
o
n
th
e
rm
a
l
a
n
d
n
o
n
-
th
e
rm
a
l
ima
g
in
g
.
Th
e
re
su
lt
s
i
n
d
ica
te
th
a
t
th
e
m
o
d
e
l
train
e
d
with
t
h
e
rm
a
l
d
a
ta
sig
n
ifi
c
a
n
t
l
y
o
u
t
p
e
rfo
rm
e
d
t
h
e
n
o
n
-
th
e
rm
a
l
m
o
d
e
l,
a
c
h
iev
in
g
9
9
%
p
re
c
isio
n
,
9
8
%
re
c
a
ll
,
9
8
%
F
1
-
sc
o
re
,
a
n
d
9
9
%
m
e
a
n
a
v
e
ra
g
e
p
re
c
isio
n
(m
AP)
5
0
d
u
r
in
g
v
a
li
d
a
ti
o
n
.
T
h
e
th
e
rm
a
l
m
o
d
e
l
re
c
e
iv
e
d
a
9
9
%
a
c
c
u
ra
c
y
ra
te
d
u
rin
g
v
a
li
d
a
ti
o
n
,
wh
il
e
t
h
e
n
o
n
-
th
e
rm
a
l
m
o
d
e
l
a
tt
a
in
e
d
9
4
%
a
c
c
u
ra
c
y
,
e
x
h
i
b
it
i
n
g
a
sli
g
h
tl
y
p
o
o
re
r
p
e
rfo
rm
a
n
c
e
a
n
d
c
o
m
m
it
ti
n
g
se
v
e
ra
l
m
istak
e
s
in
d
e
tec
ti
o
n
.
Th
e
u
se
o
f
th
e
r
m
a
l
c
a
m
e
ra
s
o
n
m
o
v
i
n
g
a
u
to
m
a
ti
o
n
sy
ste
m
s
h
a
s
d
e
m
o
n
stra
ted
it
s
c
a
p
a
b
il
it
y
a
n
d
e
ffe
c
ti
v
e
n
e
ss
,
m
a
k
i
n
g
it
m
o
re
o
p
ti
m
a
l
f
o
r
a
p
p
li
c
a
ti
o
n
i
n
th
e
a
g
ri
c
u
lt
u
ra
l
i
n
d
u
stry
.
K
ey
w
o
r
d
s
:
Ob
ject
d
etec
tio
n
R
GB
im
ag
e
T
h
er
m
al
im
ag
in
g
T
o
m
ato
Y
o
u
o
n
ly
lo
o
k
o
n
ce
v
er
s
io
n
8
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
:
Su
lf
ay
an
ti Fah
ar
u
d
d
in
Sit
u
ju
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atics,
Facu
lty
o
f
E
n
g
in
ee
r
i
n
g
,
Un
i
v
er
s
itas
Su
lawe
s
i
B
ar
at
Pro
f
.
Dr
.
B
ah
ar
u
d
d
in
L
o
p
a,
SH Str
ee
t,
T
alu
m
u
n
g
,
9
1
4
1
2
Ma
jen
e,
W
est Su
lawe
s
i,
I
n
d
o
n
esia
E
m
ail:
s
u
lf
ay
an
ti@
u
n
s
u
lb
ar
.
a
c.
id
1.
I
NT
RO
D
UCT
I
O
N
T
o
m
ato
p
lan
ts
,
k
n
o
wn
b
y
t
h
eir
L
atin
n
am
e
Lyco
p
ers
ico
n
escu
len
tu
m
Mill,
ar
e
a
n
n
u
al
s
h
r
u
b
s
b
elo
n
g
in
g
to
th
e
So
lan
a
ce
ae
f
am
ily
[
1
]
.
T
o
m
at
o
es
ca
n
b
e
co
n
s
u
m
ed
d
ir
ec
tly
.
Ho
w
ev
er
,
in
I
n
d
o
n
esia,
to
m
ato
es
ar
e
a
f
o
o
d
in
g
r
ed
ien
t
wid
ely
u
s
ed
to
m
ak
e
ty
p
ical
I
n
d
o
n
esian
d
is
h
es,
s
u
ch
as
ch
ili
s
au
ce
,
s
o
u
p
,
an
d
o
th
er
tr
a
d
itio
n
al
f
o
o
d
s
.
I
n
ad
d
itio
n
,
th
e
co
n
te
n
t
o
f
p
r
o
tein
,
c
ar
b
o
h
y
d
r
ates,
f
at,
m
i
n
er
a
ls
,
an
d
v
itam
in
s
t
h
at
ar
e
u
s
ef
u
l
f
o
r
h
ea
lth
also
a
d
d
s
to
th
e
u
tili
ty
o
f
th
is
p
lan
t
[
2
]
.
Fo
o
d
c
o
n
s
u
m
p
tio
n
d
ata
s
h
o
w
s
in
cr
ea
s
ed
to
m
at
o
c
o
n
s
u
m
p
tio
n
f
r
o
m
2
0
1
7
to
2
0
2
1
[
3
]
.
T
h
is
th
e
n
g
av
e
b
ir
th
t
o
ef
f
o
r
ts
to
in
c
r
ea
s
e
to
m
ato
p
r
o
d
u
ctio
n
in
o
r
d
e
r
to
m
ee
t th
e
n
ee
d
s
o
f
th
e
co
m
m
u
n
ity
f
o
r
th
is
co
m
m
o
d
ity
.
T
o
m
ato
cu
ltiv
atio
n
is
ca
r
r
ied
o
u
t
f
r
o
m
p
r
e
-
h
a
r
v
est
to
p
o
s
t
-
h
ar
v
est.
Po
s
t
-
h
ar
v
est
cu
ltiv
atio
n
is
ca
r
r
ied
o
u
t
to
m
ain
tain
th
e
q
u
a
lity
o
f
to
m
ato
es
t
o
b
e
m
a
r
k
eted
b
ec
au
s
e,
d
u
r
in
g
th
e
s
to
r
a
g
e
p
e
r
io
d
,
t
h
er
e
ca
n
b
e
ch
an
g
es
in
co
n
d
itio
n
s
o
r
e
v
e
n
a
d
ec
r
ea
s
e
in
q
u
ality
;
f
o
r
ex
am
p
le,
t
o
m
ato
es
b
ec
o
m
e
o
v
er
r
ip
e
o
r
to
o
s
o
f
t.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
1
5
,
No
.
2
,
J
u
n
e
2
0
2
6
:
4
5
1
-
461
452
T
h
e
q
u
ality
o
f
to
m
ato
es
is
u
s
u
ally
s
o
r
ted
im
m
ed
iately
af
ter
th
e
to
m
ato
es
ar
e
p
ick
ed
b
y
s
elec
tin
g
g
o
o
d
q
u
ality
to
b
e
m
ar
k
eted
an
d
d
is
ca
r
d
i
n
g
ab
n
o
r
m
al
to
m
ato
es.
T
h
e
t
o
m
ato
es
to
b
e
m
a
r
k
eted
will
b
e
s
elec
ted
a
g
ain
th
r
o
u
g
h
g
r
a
d
in
g
(
lev
el
o
f
r
i
p
en
ess
)
b
ased
o
n
co
lo
r
a
n
d
s
ize
f
o
r
s
p
ec
if
ic
m
ar
k
et
p
u
r
p
o
s
es
o
r
co
n
s
u
m
er
p
r
ef
er
en
ce
s
.
T
h
e
p
r
o
ce
s
s
o
f
s
o
r
tin
g
,
g
r
ad
in
g
,
an
d
esti
m
atin
g
to
m
ato
p
r
o
d
u
ctio
n
r
esu
lts
b
y
f
ar
m
er
s
is
ca
r
r
ied
o
u
t
th
r
o
u
g
h
m
an
u
al
o
b
s
er
v
ati
o
n
to
en
s
u
r
e
m
ar
k
et
n
ee
d
s
.
T
h
is
m
eth
o
d
r
eq
u
i
r
es
a
lo
t
o
f
en
er
g
y
a
n
d
tim
e,
s
o
it
is
u
n
s
u
itab
le
f
o
r
lar
g
e
-
s
ca
le
to
m
ato
cu
ltiv
atio
n
[
4
]
.
T
h
er
e
f
o
r
e,
tech
n
o
l
o
g
y
s
u
ch
as
au
to
m
atic
to
m
ato
s
o
r
tin
g
co
n
v
ey
o
r
to
o
ls
ca
n
h
el
p
f
ar
m
er
s
s
o
r
t,
g
r
ad
e,
an
d
co
u
n
t
to
m
ato
es
s
o
th
at
ea
ch
p
r
o
ce
s
s
ca
n
b
e
m
o
r
e
e
f
f
ec
ti
v
e
an
d
ef
f
icien
t.
T
ec
h
n
o
lo
g
y
ca
n
also
r
ed
u
ce
p
o
s
t
-
h
ar
v
est p
r
o
ce
s
s
er
r
o
r
s
ca
u
s
ed
b
y
h
u
m
a
n
s
[
5
]
.
T
h
e
to
m
ato
d
etec
tio
n
an
d
co
u
n
tin
g
m
eth
o
d
u
n
d
e
r
p
in
s
th
e
cr
ea
tio
n
o
f
an
au
to
m
ated
to
m
ato
s
o
r
tin
g
co
n
v
ey
o
r
,
as
o
b
ject
d
etec
tio
n
is
th
e
in
itial
p
h
ase
in
th
e
m
ec
h
an
izatio
n
o
f
th
e
a
g
r
icu
ltu
r
al
s
ec
to
r
,
aim
ed
at
id
en
tify
in
g
tar
g
et
o
b
jects
an
d
ca
teg
o
r
izin
g
th
em
ap
p
r
o
p
r
iat
ely
[
4
]
,
[
6
]
.
T
h
ese
m
eth
o
d
s
h
av
e
u
tili
ze
d
m
an
y
co
m
p
u
ter
v
is
io
n
an
d
d
ee
p
lear
n
in
g
m
eth
o
d
s
b
y
ex
p
lo
r
in
g
im
ag
es
to
d
etec
t
an
d
co
u
n
t
to
m
a
to
es
in
ag
r
icu
ltu
r
al
en
v
ir
o
n
m
en
ts
[
4
]
–
[
1
2
]
.
T
h
e
d
ee
p
lear
n
in
g
m
et
h
o
d
is
u
s
ed
t
o
d
etec
t
o
b
jects
s
u
ch
as
t
o
m
a
to
es
b
ec
a
u
s
e
o
f
its
ab
ilit
y
to
h
an
d
le
th
e
c
o
m
p
lex
i
ty
o
f
th
e
d
etec
ted
o
b
ject
e
n
v
ir
o
n
m
en
t
an
d
v
ar
i
o
u
s
lig
h
tin
g
c
o
n
d
itio
n
s
,
s
u
c
h
as
a
m
as
k
-
r
eg
io
n
-
b
ased
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
(
Ma
s
k
-
R
-
C
NN
)
[
8
]
,
[
1
1
]
Fas
ter
-
R
-
C
N
N
[
9
]
an
d
y
o
u
o
n
ly
lo
o
k
o
n
ce
(
YOL
O
)
[
4
]
–
[
7
]
,
[
1
0
]
,
[
1
3
]
.
YOL
O'
s
d
o
m
in
an
ce
is
in
s
ep
ar
ab
le
f
r
o
m
its
r
o
le,
wh
ich
h
as
b
ee
n
p
r
o
v
e
n
to
d
etec
t
o
b
jects
q
u
ic
k
ly
an
d
ef
f
icie
n
tly
[
1
4
]
.
T
h
es
e
s
tu
d
ies
u
tili
ze
r
ed
,
g
r
ee
n
,
b
lu
e
(
R
GB
)
im
ag
es,
s
u
ch
as:
r
ef
er
en
ce
[
4
]
im
p
r
o
v
ed
th
e
p
er
f
o
r
m
a
n
ce
o
f
YOL
O
v
8
in
th
e
o
n
lin
e
au
t
o
m
ated
m
atu
r
ity
g
r
ad
i
n
g
an
d
co
u
n
tin
g
p
r
o
ce
s
s
b
y
ad
o
p
tin
g
th
e
m
u
lti
-
h
ea
d
s
elf
-
atten
ti
o
n
(
MH
SA
)
atten
tio
n
m
ec
h
a
n
is
m
in
YOL
Ov
8
'
s
b
ac
k
b
o
n
e,
[
5
]
d
ev
el
o
p
ed
a
n
a
u
to
m
atic
to
m
ato
d
etec
tio
n
an
d
class
if
icatio
n
s
y
s
tem
th
at
c
an
id
en
tify
to
m
ato
r
ip
en
ess
in
r
ea
l
tim
e,
[
1
1
]
r
esear
ch
u
tili
ze
d
Ma
s
k
-
R
-
C
NN
to
d
is
tin
g
u
is
h
to
m
ato
es
f
r
o
m
s
tem
s
in
th
e
d
ev
elo
p
m
e
n
t
o
f
a
h
ar
v
esti
n
g
r
o
b
o
t,
[
6
]
co
m
p
a
r
ed
t
h
e
r
e
s
u
lts
o
f
to
m
ato
d
etec
tio
n
an
d
co
u
n
tin
g
u
s
in
g
Y
OL
O
v
4
,
YOL
Ov
4
-
tin
y
,
YO
L
Ov
3
,
an
d
YOL
Ov
3
-
tin
y
,
an
d
[
1
3
]
also
d
e
m
o
n
s
tr
ated
to
m
ato
class
if
icatio
n
r
esu
lts
u
s
in
g
YOL
Ov
8
o
n
to
m
ato
im
ag
e
au
g
m
e
n
tatio
n
d
ata.
Oth
er
r
esear
ch
co
m
b
i
n
ed
R
GB
im
ag
es with
o
th
er
im
ag
e
ty
p
es
to
im
p
r
o
v
e
th
e
p
er
f
o
r
m
a
n
ce
o
f
to
m
ato
d
ete
ctio
n
an
d
co
u
n
tin
g
.
I
n
[
9
]
,
an
im
a
g
e
-
b
ased
ap
p
r
o
ac
h
was
in
tr
o
d
u
ce
d
th
at
u
tili
ze
s
R
GB
an
d
s
p
ec
tr
al
im
ag
es
to
ev
alu
ate
th
e
n
u
m
b
er
o
f
r
ip
e
to
m
ato
es
r
ea
d
y
f
o
r
h
ar
v
est.
I
n
[
7
]
,
c
o
m
b
in
es o
b
je
ct
d
etec
tio
n
with
m
u
ltip
le
o
b
jects tr
ac
k
in
g
an
d
s
p
ec
if
ic
tr
ac
k
i
n
g
r
eg
i
o
n
co
u
n
tin
g
to
en
h
an
ce
to
m
ato
clu
s
ter
co
u
n
tin
g
ab
ilit
y
.
I
n
[
1
0
]
,
ca
r
r
ies
o
u
t
a
tar
g
et
tr
ac
k
in
g
n
etwo
r
k
th
at
ca
n
id
en
tify
an
d
co
u
n
t to
m
at
o
es a
t d
if
f
er
e
n
t g
r
o
wth
s
tag
es
,
wh
ich
is
r
ef
er
r
e
d
to
as YO
L
O
-
D
eep
SOR
T
.
So
m
e
r
esear
ch
ab
o
u
t
o
b
ject
d
etec
tio
n
is
also
ap
p
lied
to
R
GB
im
ag
es
tak
en
u
s
in
g
a
r
eg
u
l
ar
ca
m
er
a
,
an
d
im
ag
es
tak
e
n
v
ia
in
f
r
ar
e
d
[
1
5
]
–
[
1
8
]
.
I
n
[
1
5
]
,
o
f
f
er
s
a
r
ap
id
d
etec
tio
n
an
d
r
ec
o
g
n
it
io
n
m
o
d
el
u
s
in
g
a
YOL
O
m
o
d
el
with
a
m
u
lti
-
s
ca
le
s
el
f
-
atten
tio
n
m
ec
h
an
is
m
,
s
p
ec
if
ically
d
esig
n
ed
f
o
r
s
m
all
r
o
ad
tar
g
ets
in
in
f
r
ar
ed
d
etec
tio
n
co
n
tex
ts
.
I
n
[
1
6
]
,
u
tili
ze
s
b
o
th
th
e
o
r
ig
i
n
al
im
ag
e
an
d
its
co
r
r
esp
o
n
d
in
g
en
co
d
e
d
v
er
s
io
n
,
d
er
iv
ed
th
r
o
u
g
h
a
tex
tu
r
al
d
escr
i
p
to
r
m
eth
o
d
,
ar
e
u
tili
ze
d
as
in
p
u
ts
to
a
d
ee
p
lear
n
in
g
m
o
d
el
th
at
in
co
r
p
o
r
ates
tar
g
et
atten
tio
n
an
d
s
ize
atten
tio
n
m
ec
h
an
is
m
s
f
o
r
o
b
ject
d
etec
tio
n
.
Acc
o
r
d
in
g
to
[
1
7
]
,
a
n
etwo
r
k
u
s
in
g
R
eti
na
N
et
o
n
v
is
ib
le
an
d
th
er
m
al
in
f
r
ar
ed
(
T
I
R
)
ca
m
er
as
f
r
o
m
u
n
m
an
n
e
d
ae
r
ial
v
e
h
icles
(
UAVs
)
to
d
etec
t
an
d
class
if
y
g
r
o
u
n
d
o
b
ject
s
.
W
h
ile,
[
1
8
]
co
n
d
u
cted
a
n
an
a
ly
s
is
o
f
th
e
cu
r
r
en
t
s
tate
o
f
r
e
s
ea
r
ch
o
n
th
e
f
u
s
io
n
o
f
v
is
ib
le
an
d
in
f
r
ar
e
d
im
ag
es
f
o
r
o
b
ject
d
etec
tio
n
.
I
n
f
r
ar
e
d
im
ag
es
in
o
b
ject
d
etec
tio
n
s
h
o
w
f
aster
d
etec
tio
n
ca
p
ab
ilit
ies
in
ch
allen
g
in
g
en
v
ir
o
n
m
e
n
ts
,
s
u
ch
as
lo
w
lig
h
t
in
ten
s
ity
o
r
wh
e
n
d
etec
tio
n
i
s
r
eq
u
ir
ed
f
o
r
s
m
all
o
b
jects
in
th
e
im
ag
e.
Ob
ject
d
etec
tio
n
is
also
d
o
n
e
b
y
u
t
ilizin
g
im
ag
es
o
b
tain
ed
f
r
o
m
a
th
er
m
al
ca
m
er
a
[
1
9
]
–
[
2
2
]
.
I
n
[
1
9
]
,
in
tr
o
d
u
ce
s
a
n
eu
r
al
n
etwo
r
k
m
o
d
el
d
esi
g
n
ed
to
d
etec
t
s
m
all
an
d
tin
y
o
b
jects
u
s
in
g
th
e
v
eh
icle
d
etec
tio
n
in
ae
r
ial
im
ag
er
y
(
VE
DAI
)
d
ataset
[
2
3
]
,
wh
ich
is
th
e
th
er
m
al
im
ag
in
g
ca
p
tu
r
ed
b
y
UAV
s
,
u
tili
zin
g
th
e
YOL
Ov
5
ar
ch
ite
ctu
r
e
en
h
a
n
ce
d
with
a
tr
an
s
f
o
r
m
er
en
co
d
er
at
th
e
f
in
al
s
tag
e.
I
n
[
20]
,
s
u
p
p
o
r
ts
au
to
m
ated
an
im
al
d
etec
tio
n
an
d
class
if
icatio
n
in
th
er
m
al
im
ag
es
b
y
in
t
r
o
d
u
cin
g
a
n
o
v
el
alg
o
r
it
h
m
f
o
r
ex
tr
ac
tin
g
th
e
r
m
al
f
ea
tu
r
es.
Su
b
s
eq
u
en
tly
,
a
th
e
r
m
al
s
ig
n
at
u
r
e
f
o
r
ea
c
h
id
en
tifie
d
o
b
ject
is
co
m
p
u
te
d
u
s
in
g
m
o
r
p
h
o
lo
g
ical
o
p
e
r
atio
n
s
.
I
n
t
h
e
s
tu
d
y
b
y
[
2
1
]
,
a
Fas
ter
-
R
-
C
NN
is
ap
p
lied
t
o
th
e
r
m
al
a
n
d
v
is
u
al
s
p
ec
tr
u
m
im
ag
er
y
o
n
4
-
wh
ee
le
r
,
2
-
wh
ee
ler
,
tr
af
f
ic
lig
h
t
,
an
d
h
u
m
a
n
o
b
jects
to
p
e
r
f
o
r
m
a
co
m
p
ar
ativ
e
ev
alu
atio
n
,
r
ev
ea
lin
g
th
at
t
h
er
m
al
ca
m
e
r
a
im
ag
es
h
av
e
o
u
tp
er
f
o
r
m
e
d
r
esu
lts
co
m
p
ar
ed
to
v
is
ib
le
s
p
ec
tr
u
m
im
ag
es.
I
n
[
2
4
]
,
p
r
o
p
o
s
ed
a
to
m
ato
d
etec
tio
n
m
et
h
o
d
in
a
c
o
m
p
l
ex
n
atu
r
al
e
n
v
ir
o
n
m
en
t
b
ase
d
o
n
th
e
b
ased
o
n
r
esid
u
al
an
d
C
-
SP
P
en
h
an
ce
d
YOL
Ov
4
(
RC
-
YOL
Ov
4
)
,
an
d
r
esu
lted
a
8
8
%
ac
cu
r
ac
y
in
a
n
atu
r
al
en
v
ir
o
n
m
en
t.
Acc
o
r
d
in
g
to
[
2
2
]
,
v
is
ib
le
an
d
th
er
m
al
im
ag
es
,
s
p
ec
if
ically
ca
r
,
p
er
s
o
n
,
b
icy
cle,
an
d
d
o
g
as
th
e
d
ataset
,
an
d
ad
o
p
ts
R
etin
aNe
t
as
th
e
b
aselin
e
m
o
d
el
to
in
teg
r
ate
f
ea
tu
r
es
f
r
o
m
m
u
ltip
l
e
d
ata
s
o
u
r
ce
s
f
o
r
o
b
ject
d
etec
tio
n
.
A
th
er
m
al
ca
m
er
a
is
v
alu
ab
le
f
o
r
d
etec
tin
g
h
ea
t
s
ig
n
atu
r
es,
allo
win
g
th
em
to
wo
r
k
ef
f
ec
tiv
ely
in
lo
w
v
is
ib
ilit
y
co
n
d
itio
n
s
,
s
u
ch
as a
t n
ig
h
t,
wh
e
r
e
co
n
v
e
n
tio
n
al
ca
m
e
r
as h
av
e
d
if
f
icu
lty
.
T
h
e
a
p
p
l
i
c
a
t
i
o
n
o
f
t
h
e
r
m
a
l
i
m
a
g
i
n
g
t
e
c
h
n
o
l
o
g
y
i
n
a
g
r
i
cu
l
t
u
r
e
is
f
e
as
i
b
l
e
d
u
e
t
o
tem
p
e
r
a
t
u
r
e
d
i
f
f
e
r
e
n
t
i
a
ls
t
h
at
f
a
ci
l
i
ta
t
e
o
b
j
e
c
t
d
et
e
c
t
i
o
n
,
w
h
i
c
h
ca
n
s
u
b
s
e
q
u
e
n
t
l
y
b
e
e
m
p
l
o
y
e
d
f
o
r
n
u
m
e
r
o
u
s
r
e
a
s
o
n
s
,
i
n
c
l
u
d
i
n
g
p
r
e
d
i
c
t
i
o
n
a
n
d
i
d
e
n
t
i
f
i
c
at
i
o
n
[
2
5
]
–
[
3
1
]
.
T
h
e
s
e
w
o
r
k
s
i
l
l
u
s
t
r
a
t
e
t
h
e
t
r
e
n
d
o
f
t
h
e
r
m
a
l
u
s
e
i
n
e
d
g
e
c
o
m
p
u
t
i
n
g
f
o
r
f
i
e
l
d
r
o
b
o
t
i
cs
[
2
5
]
,
[
2
9
]
,
l
o
w
e
r
-
c
o
s
t
s
e
n
s
o
r
d
e
p
l
o
y
m
e
n
t
[
2
6
]
,
[
3
1
]
,
a
n
d
c
l
i
m
a
t
e
-
r
es
il
i
e
n
t
a
g
r
i
c
u
l
t
u
r
e
[
2
6
]
–
[
3
0
]
.
S
h
a
l
ash
e
t
a
l
.
[
2
9
]
i
n
d
i
c
at
e
t
h
a
t
ar
t
i
f
i
c
i
al
i
n
te
l
l
i
g
e
n
ce
–
t
h
e
r
m
a
l
im
a
g
i
n
g
i
n
t
e
g
r
a
t
i
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
C
o
mp
a
r
is
o
n
o
f th
erma
l a
n
d
n
o
n
-
th
erma
l ima
g
es fo
r
to
ma
to
…
(
S
u
lfa
ya
n
ti F
a
h
a
r
u
d
d
in
S
it
u
ju
)
453
f
a
c
i
l
it
a
t
es
t
h
e
p
r
o
m
p
t
d
e
t
e
c
t
io
n
o
f
f
l
u
c
t
u
a
t
i
o
n
s
d
u
e
t
o
p
e
s
ts
o
r
d
i
s
e
a
s
es
,
e
n
a
b
l
i
n
g
t
im
e
l
y
t
r
e
a
t
m
e
n
t
a
n
d
m
i
t
i
g
a
ti
o
n
.
M
e
a
n
w
h
i
l
e
,
A
w
a
is
e
t
a
l
.
[
2
6
]
d
e
m
o
n
s
t
r
a
t
e
t
h
a
t
th
e
r
m
a
l
i
m
a
g
i
n
g
m
a
y
d
i
s
c
e
r
n
v
a
r
i
a
t
i
o
n
s
i
n
w
at
e
r
s
t
a
t
u
s
a
n
d
t
h
e
c
r
o
p
w
a
t
e
r
s
t
r
e
s
s
i
n
d
e
x
(
C
W
S
I
)
.
O
n
t
h
e
o
t
h
e
r
h
a
n
d
,
[
2
5
]
i
n
d
i
c
a
t
e
s
t
h
a
t
t
h
e
r
m
al
i
m
a
g
i
n
g
e
n
h
a
n
c
es
f
r
u
i
t
g
r
a
d
i
n
g
p
r
o
c
e
s
s
es
,
e
n
s
u
r
e
s
f
o
o
d
s
a
f
e
t
y
,
a
n
d
r
e
d
u
c
es
p
o
s
t
-
h
a
r
v
e
s
t
l
o
s
s
es
.
A
d
d
it
i
o
n
a
l
l
y
,
t
h
e
r
m
a
l
i
m
a
g
i
n
g
i
s
a
n
e
n
v
i
r
o
n
m
e
n
t
a
l
l
y
s
u
s
t
a
i
n
a
b
le
t
e
c
h
n
o
l
o
g
y
t
h
a
t
g
e
n
e
r
a
t
es
n
o
w
a
s
t
e
o
r
h
a
z
a
r
d
o
u
s
e
m
i
s
s
i
o
n
s
[
3
1
]
.
T
h
e
s
e
s
t
u
d
i
es
i
l
l
u
s
t
r
a
t
e
t
h
e
e
f
f
e
ct
i
v
e
n
es
s
o
f
th
e
r
m
a
l
i
m
a
g
i
n
g
i
n
d
i
s
ti
n
g
u
i
s
h
in
g
b
e
t
w
e
e
n
s
t
r
es
s
e
d
a
n
d
n
o
n
-
s
tr
e
s
s
e
d
p
l
a
n
t
s
a
n
d
i
n
a
c
q
u
i
r
i
n
g
d
e
t
a
i
l
e
d
d
a
t
a
o
n
c
a
n
o
p
y
t
e
m
p
e
r
a
t
u
r
e
.
T
h
i
s
i
n
f
o
r
m
a
t
i
o
n
c
a
n
f
a
c
i
l
i
t
at
e
t
h
e
c
o
m
p
r
e
h
e
n
s
i
o
n
a
n
d
i
n
t
e
r
p
r
e
t
a
ti
o
n
o
f
c
a
n
o
p
y
t
e
m
p
e
r
a
t
u
r
e
[
3
2
]
.
T
h
i
s
m
e
t
h
o
d
p
o
s
s
e
s
s
es
s
i
g
n
i
f
i
c
a
n
t
p
o
t
e
n
ti
a
l
f
o
r
a
p
p
l
i
c
a
t
i
o
n
i
n
t
r
o
p
i
c
al
a
g
r
i
c
u
l
t
u
r
e
,
g
i
v
e
n
t
h
a
t
t
r
o
p
i
c
a
l
r
e
g
i
o
n
s
e
x
p
e
r
i
e
n
c
e
h
i
g
h
t
e
m
p
e
r
a
t
u
r
e
s
a
n
d
i
n
t
e
n
s
e
s
u
n
l
i
g
h
t
[
3
3
]
,
[
3
4
]
.
R
esear
ch
in
[
3
5
]
in
teg
r
ated
th
er
m
al
an
d
v
is
ib
le
lig
h
t
im
ag
e
r
y
with
d
ep
th
d
ata
to
c
r
ea
te
a
s
y
s
tem
f
o
r
th
e
r
em
o
te
d
etec
tio
n
o
f
p
lan
t
s
af
f
licted
b
y
th
e
to
m
ato
p
o
w
d
er
y
m
ild
ew
f
u
n
g
u
s
.
T
h
is
r
esear
ch
u
tili
ze
s
th
e
h
an
d
cr
a
f
ted
f
ea
tu
r
e
m
eth
o
d
f
o
r
f
ea
t
u
r
e
ex
tr
ac
tio
n
an
d
a
s
u
p
p
o
r
t
v
ec
t
o
r
m
ac
h
in
e
(
SVM)
f
o
r
class
if
icatio
n
.
Dee
p
lear
n
in
g
a
d
ap
ted
to
p
r
o
ce
s
s
th
er
m
al
im
a
g
in
g
p
r
o
v
i
d
es
r
o
b
u
s
t
o
b
ject
d
etec
tio
n
,
ev
en
in
co
m
p
lex
en
v
ir
o
n
m
en
ts
.
T
h
u
s
,
th
e
co
m
b
in
atio
n
o
f
th
er
m
al
im
ag
in
g
an
d
d
ee
p
lear
n
in
g
allo
ws
f
o
r
h
ig
h
ac
cu
r
ac
y
in
d
etec
tin
g
an
d
d
is
tin
g
u
is
h
in
g
o
b
jects
b
ased
o
n
te
m
p
er
atu
r
e
[
1
9
]
,
[
2
0
]
.
I
n
[
3
6
]
,
p
r
o
p
o
s
ed
a
m
eth
o
d
f
o
r
t
h
e
class
if
icatio
n
o
f
p
lan
t
an
d
cr
o
p
d
is
ea
s
es
with
a
th
e
r
m
al
ca
m
er
a
an
d
a
C
NN
.
T
h
is
s
tu
d
y
wo
r
k
s
o
n
2
8
p
lan
ts
an
d
6
cr
o
p
d
is
ea
s
e
class
if
icati
o
n
s
.
Pre
v
io
u
s
s
tu
d
ies
s
h
o
w
th
at
R
G
B
im
ag
es
ar
e
u
s
ed
f
o
r
to
m
ato
d
etec
tio
n
,
an
d
in
teg
r
ated
th
er
m
al
te
ch
n
o
lo
g
y
is
esp
ec
ially
u
s
ed
f
o
r
to
m
ato
d
is
ea
s
e
d
etec
tio
n
.
Me
an
wh
ile,
th
is
s
tu
d
y
attem
p
ts
to
d
ev
elo
p
tech
n
o
lo
g
y
f
o
r
d
etec
tin
g
to
m
ato
es o
n
a
m
o
v
in
g
c
o
n
v
ey
o
r
m
ac
h
in
e
u
s
in
g
th
e
YOL
Ov
8
m
o
d
el.
T
h
is
r
esear
ch
in
v
o
lv
ed
c
r
ea
tin
g
a
li
b
r
ar
y
o
f
n
o
n
-
t
h
er
m
al
a
n
d
th
e
r
m
al
im
ag
es
o
f
to
m
ato
es,
im
p
l
em
en
tin
g
YOL
Ov
8
f
o
r
to
m
ato
d
etec
tio
n
in
m
o
v
in
g
co
n
d
itio
n
s
,
d
em
o
n
s
tr
atin
g
th
e
r
eliab
ilit
y
o
f
to
m
ato
d
etec
tio
n
u
s
in
g
a
co
m
b
in
atio
n
o
f
th
er
m
al
tech
n
o
lo
g
y
a
n
d
d
ee
p
lear
n
in
g
,
an
d
p
r
esen
tin
g
a
co
m
p
ar
ativ
e
an
al
y
s
is
o
f
th
e
to
m
ato
d
etec
tio
n
o
u
tco
m
es
u
tili
zin
g
t
h
er
m
al
an
d
n
o
n
-
t
h
er
m
al
im
a
g
i
n
g
.
No
n
-
th
er
m
al
im
ag
es
a
r
e
t
h
e
im
ag
es
o
b
tain
ed
f
r
o
m
a
n
R
GB
ca
m
er
a,
wh
ile
t
h
er
m
al
im
ag
es
ar
e
th
e
im
a
g
es
o
b
tain
ed
f
r
o
m
a
th
e
r
m
al
ca
m
er
a.
T
h
e
YOL
Ov
8
m
o
d
el
is
u
s
ed
to
o
b
tain
d
et
ec
tio
n
ac
cu
r
ac
y
ac
c
o
r
d
in
g
to
in
d
u
s
t
r
ial
co
n
d
itio
n
s
.
T
h
e
r
e
f
o
r
e,
th
is
r
esear
ch
co
n
tr
ib
u
tes
to
d
em
o
n
s
tr
atin
g
th
e
co
m
p
ar
is
o
n
o
f
th
e
to
m
ato
d
etec
tio
n
r
esu
lts
u
s
in
g
YOL
O
v
8
in
n
o
n
-
th
er
m
a
l
im
ag
es
an
d
th
er
m
al
ca
m
er
a
im
ag
es.
Gen
er
ally
,
th
is
s
t
u
d
y
em
p
h
asizes
th
e
d
ev
elo
p
m
en
t
o
f
ad
v
a
n
ce
d
tech
n
o
lo
g
y
to
i
m
p
r
o
v
e
th
e
ac
cu
r
ac
y
an
d
ef
f
icien
cy
o
f
to
m
ato
d
etec
tio
n
in
v
ar
io
u
s
f
ield
co
n
d
itio
n
s
,
s
u
ch
as
f
r
u
it tr
an
s
f
er
m
ac
h
in
es o
r
b
elt
co
n
v
ey
o
r
s
.
2.
P
RO
P
O
SE
D
M
E
T
H
O
D
T
h
is
s
tu
d
y
p
r
o
p
o
s
es
u
s
in
g
th
e
YOL
Ov
8
alg
o
r
ith
m
f
o
r
t
o
m
ato
d
etec
tio
n
,
u
s
in
g
a
th
er
m
al
an
d
non
-
th
e
r
m
al
i
m
a
g
es
d
ataset
to
d
eter
m
in
e
th
e
p
er
f
o
r
m
an
ce
o
f
ea
ch
tech
n
o
lo
g
y
i
n
d
etec
tin
g
m
o
v
in
g
o
b
jects
o
n
a
b
elt
co
n
v
ey
o
r
m
ac
h
in
e.
T
h
e
YOL
Ov
8
m
o
d
el
was
ch
o
s
en
f
o
r
th
is
task
d
u
e
to
its
s
u
p
er
io
r
ity
in
r
ea
l
-
tim
e
o
b
ject
d
etec
tio
n
an
d
its
ef
f
ici
en
cy
in
im
ag
e
p
r
o
ce
s
s
in
g
[
3
7
]
.
YOL
O
d
etec
to
r
is
a
wid
ely
u
s
ed
s
in
g
le
-
s
tag
e
o
b
ject
d
etec
tio
n
n
etwo
r
k
th
a
t
b
alan
ce
s
ac
cu
r
ac
y
an
d
s
p
e
ed
well.
T
h
is
s
tu
d
y
u
s
es
th
e
latest
v
er
s
io
n
o
f
YOL
Ov
8
(
web
r
ef
er
e
n
ce
)
f
o
r
to
m
ato
d
etec
tio
n
.
Mo
s
aic
d
a
ta
au
g
m
e
n
tatio
n
is
u
s
ed
in
Y
OL
Ov
8
.
T
h
is
d
ata
au
g
m
en
tatio
n
m
et
h
o
d
ap
p
lies
s
ev
er
al
au
g
m
en
t
atio
n
m
eth
o
d
s
to
n
ew
tr
ain
in
g
im
ag
es,
s
u
ch
as
f
lip
,
r
o
tatio
n
,
s
ca
lin
g
,
an
d
co
lo
r
ch
an
g
e.
T
h
is
ca
n
im
p
r
o
v
e
th
e
m
o
d
el'
s
a
cc
u
r
ac
y
d
u
r
in
g
th
e
tr
ain
in
g
p
r
o
ce
s
s
co
m
p
ar
ed
to
n
o
t
u
s
in
g
it.
T
h
is
a
u
g
m
en
tati
o
n
aim
s
to
s
im
u
late
v
ar
io
u
s
e
n
v
ir
o
n
m
en
tal
an
d
lig
h
tin
g
c
o
n
d
i
tio
n
s
d
u
r
in
g
th
e
d
etec
tio
n
p
r
o
ce
s
s
,
as su
g
g
ested
in
th
e
s
tu
d
y
[
3
8
]
.
YOL
Ov
8
co
m
p
r
is
es
th
r
ee
p
r
i
m
ar
y
co
m
p
o
n
e
n
ts
:
b
ac
k
b
o
n
e,
n
ec
k
,
an
d
h
ea
d
.
T
h
e
b
ac
k
b
o
n
e
is
task
ed
with
ex
tr
ac
tin
g
v
ar
io
u
s
f
ea
tu
r
es
f
r
o
m
th
e
in
p
u
t.
I
t
o
p
er
ates
b
y
d
iv
id
in
g
f
ea
tu
r
e
m
ap
s
in
to
two
h
alv
es.
T
h
e
Nec
k
f
u
n
ctio
n
in
teg
r
ates
th
e
f
ea
tu
r
es
f
r
o
m
t
h
e
b
ac
k
b
o
n
e.
T
h
e
Hea
d
in
YOL
Ov
8
i
d
en
ti
f
ies
th
e
o
b
ject
b
y
d
ir
ec
tly
p
r
e
d
ictin
g
its
ce
n
ter
.
Fig
u
r
e
1
illu
s
tr
ates th
e
m
ain
ar
ch
itectu
r
e
o
f
YOL
Ov
8
.
3.
M
E
T
H
O
D
T
h
e
m
eth
o
d
in
th
is
r
esear
ch
in
v
o
lv
es
s
ev
er
al
m
ai
n
s
tag
e
s
:
d
ata
co
llectio
n
,
d
ata
p
r
ep
r
o
ce
s
s
in
g
,
in
clu
d
in
g
au
g
m
e
n
tatio
n
,
im
a
g
e
lab
elin
g
,
an
d
s
p
lit
d
ata;
g
en
er
atin
g
a
m
o
d
el;
m
o
d
el
v
alid
atio
n
f
r
o
m
t
h
e
tr
ain
in
g
an
d
test
in
g
p
h
ase
to
p
r
o
d
u
ce
th
e
d
etec
tio
n
r
esu
lts
.
T
h
ese
s
tag
es
ap
p
ly
to
b
o
th
ty
p
es
o
f
im
a
g
es
u
s
ed
,
n
am
ely
n
o
n
-
th
e
r
m
al
an
d
th
er
m
al
im
ag
es.
T
h
e
s
tag
es o
f
th
is
s
tu
d
y
ca
n
b
e
s
ee
n
in
Fig
u
r
e
2
.
3
.
1
.
Da
t
a
a
cquis
it
io
n
Data
ac
q
u
is
itio
n
was
ca
r
r
ied
o
u
t
u
s
in
g
th
er
m
al
an
d
n
o
n
-
th
er
m
al
ca
m
er
as.
Data
wer
e
tak
en
wh
ile
to
m
ato
es
r
an
o
n
a
b
elt
c
o
n
v
ey
o
r
m
ac
h
in
e,
s
im
u
latin
g
in
d
u
s
tr
ial
co
n
d
itio
n
s
.
Data
co
lle
ctio
n
was
in
itially
co
n
d
u
cte
d
b
y
o
p
e
r
atin
g
th
e
co
n
v
ey
o
r
at
a
co
n
tr
o
lled
s
p
ee
d
t
o
en
s
u
r
e
a
co
n
s
is
ten
t
f
lo
w
o
f
to
m
ato
es.
T
h
e
R
GB
an
d
th
er
m
al
ca
m
er
as
wer
e
p
o
s
itio
n
ed
with
a
co
n
s
is
ten
t
d
is
tan
ce
an
d
an
g
le
f
o
r
d
ata
c
o
llectio
n
,
s
p
ec
if
ically
p
er
p
en
d
icu
lar
t
o
th
e
co
n
v
ey
o
r
s
u
r
f
ac
e
f
o
r
d
ata
u
n
if
o
r
m
ity
.
T
h
r
o
u
g
h
o
u
t
th
e
ac
q
u
is
itio
n
p
r
o
c
ess
,
to
m
a
to
es
wer
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
1
5
,
No
.
2
,
J
u
n
e
2
0
2
6
:
4
5
1
-
461
454
r
an
d
o
m
l
y
p
o
s
itio
n
ed
o
n
th
e
c
o
n
v
ey
o
r
,
d
is
p
lay
in
g
to
m
ato
c
o
lo
r
s
,
d
im
en
s
io
n
s
,
an
d
o
r
ien
ta
tio
n
s
.
T
h
e
r
esu
ltan
t
d
ata
co
m
p
r
is
ed
R
GB
an
d
th
er
m
al
im
ag
es
o
f
th
e
to
m
at
o
es,
r
esp
ec
tiv
ely
.
T
h
e
d
ata
wer
e
s
u
b
s
eq
u
en
tly
o
r
g
an
ized
s
y
s
tem
atica
lly
to
en
h
an
ce
th
e
an
n
o
tatio
n
p
r
o
ce
s
s
an
d
an
aly
s
is
th
at
f
o
llo
wed
.
T
h
e
d
ata
co
llectio
n
an
d
test
in
g
s
ce
n
ar
io
s
ca
n
b
e
s
ee
n
in
Fig
u
r
e
3
.
Fig
u
r
e
1
.
T
h
e
YOL
Ov
8
ar
c
h
itectu
r
e
f
o
r
th
er
m
al
a
n
d
n
o
n
-
th
e
r
m
al
im
ag
es o
f
to
m
ato
d
etec
ti
o
n
Fig
u
r
e
2
.
T
h
e
s
tag
es in
th
e
r
es
ea
r
ch
Fig
u
r
e
3
.
Data
co
llectio
n
p
r
o
c
ess
o
n
th
e
co
n
v
e
y
o
r
b
elt
m
ac
h
in
e
D
et
ec
t
ion
us
in
g
non
-
t
her
m
al
D
et
ec
t
ion
us
in
g
non
-
t
her
m
al
D
et
ec
t
ion
us
in
g
non
-
t
her
m
al
D
et
ec
t
ion
us
in
g
non
-
t
her
m
al
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
C
o
mp
a
r
is
o
n
o
f th
erma
l a
n
d
n
o
n
-
th
erma
l ima
g
es fo
r
to
ma
to
…
(
S
u
lfa
ya
n
ti F
a
h
a
r
u
d
d
in
S
it
u
ju
)
455
3
.
1
.
1
.
Ca
m
er
a
s
pecif
ica
t
io
ns
T
a
b
le
1
s
h
o
ws
t
h
e
d
if
f
e
r
e
n
ce
s
in
s
p
ec
i
f
i
ca
ti
o
n
s
b
e
twe
e
n
t
h
e
R
GB
ca
m
e
r
a
f
o
r
n
o
n
-
t
h
e
r
m
al
d
at
a
an
d
th
e
th
e
r
m
al
c
am
e
r
a
f
o
r
th
er
m
a
l
i
m
a
g
i
n
g
d
a
ta
.
T
h
e
M
o
b
I
R
ai
r
th
e
r
m
al
c
am
e
r
a
u
tili
ze
s
a
v
a
n
ad
i
u
m
o
x
i
d
e
(
VO
x
)
m
ic
r
o
b
o
l
o
m
et
e
r
s
e
n
s
o
r
i
n
t
h
e
l
o
n
g
-
w
av
e
i
n
f
r
ar
ed
(
L
W
I
R
)
s
p
e
ct
r
u
m
,
o
f
f
e
r
i
n
g
1
2
0
×
90
-
p
i
x
el
I
R
r
es
o
l
u
ti
o
n
,
a
tem
p
e
r
at
u
r
e
m
e
asu
r
e
m
e
n
t
r
a
n
g
es
f
r
o
m
2
0
°
C
to
1
2
0
°C
,
a
n
d
a
2
5
H
z
f
r
a
m
e
r
ate
f
o
r
p
r
ec
is
e
h
e
at
d
ete
cti
o
n
.
Me
a
n
w
h
il
e,
t
h
e
L
o
g
ite
ch
C
2
7
0
R
GB
ca
m
e
r
a
e
m
p
l
o
y
s
a
C
M
OS
s
e
n
s
o
r
f
o
r
v
is
i
b
l
e
li
g
h
t,
d
e
liv
er
in
g
h
i
g
h
er
H
D
7
2
0
p
(
1
2
8
0
×7
2
0
-
p
ix
el
)
r
es
o
l
u
t
io
n
at
u
p
t
o
3
0
f
p
s
,
t
h
o
u
g
h
it
la
ck
s
a
n
y
th
er
m
a
l
m
e
asu
r
e
m
e
n
t
ca
p
a
b
il
iti
es.
T
ab
le
1
.
C
am
er
a
s
p
ec
if
icatio
n
s
Te
c
h
n
i
c
a
l
p
a
r
a
me
t
e
r
s
M
o
b
I
R
a
i
r
(
t
h
e
r
ma
l
c
a
m
e
r
a
)
Lo
g
i
t
e
c
h
C
2
7
0
(
R
G
B
c
a
m
e
r
a
)
S
e
n
s
o
r
t
y
p
e
s
a
n
d
sp
e
c
t
r
u
m
VO
×
mi
c
r
o
b
o
l
o
m
e
t
e
r
(
l
o
n
g
r
a
n
g
e
i
n
f
r
a
r
e
d
/
LWI
R
)
C
M
O
S
(
v
i
s
i
b
l
e
l
i
g
h
t
/
R
G
B
)
s
e
n
s
o
r
R
e
s
o
l
u
t
i
o
n
1
2
0
×
90
-
p
i
x
e
l
(
I
R
r
e
so
l
u
t
i
o
n
)
H
D
7
2
0
p
(
1
2
8
0
×
7
2
0
-
p
i
x
e
l
)
Te
mp
e
r
a
t
u
r
e
me
a
su
r
e
me
n
t
r
a
n
g
e
2
0
°
C
t
o
1
2
0
°
C
N
o
t
a
p
p
l
i
c
a
b
l
e
F
r
a
me
r
a
t
e
2
5
H
z
U
p
t
o
3
0
f
p
s
3
.
1
.
2
.
I
m
a
g
ing
c
o
nd
it
io
ns
T
h
e
r
esear
ch
was
p
e
r
f
o
r
m
ed
i
n
a
tr
o
p
ical
s
ettin
g
ch
ar
ac
ter
iz
ed
b
y
d
ay
tim
e
tem
p
er
atu
r
es
o
f
3
1
°C
to
34
°C
an
d
r
elativ
e
h
u
m
id
ity
l
ev
els
o
f
7
0
%
to
9
0
%.
I
m
a
g
e
d
ata
f
r
o
m
th
er
m
al
was
ac
q
u
ir
ed
o
u
td
o
o
r
s
u
n
d
er
a
d
ir
ec
t
s
u
n
lig
h
t
en
v
ir
o
n
m
en
t
o
n
s
u
n
n
y
,
r
ain
less
d
ay
s
to
r
ed
u
ce
in
ter
f
er
e
n
ce
f
r
o
m
in
f
r
ar
ed
r
ad
iatio
n
ca
u
s
ed
b
y
wate
r
v
ap
o
r
.
T
h
e
ac
q
u
is
itio
n
p
r
o
ce
s
s
o
cc
u
r
r
e
d
f
r
o
m
9
:3
0
to
1
1
:0
0
AM
to
m
itig
ate
th
e
im
p
ac
t
o
f
in
ten
s
e
s
u
n
r
ad
iatio
n
,
wh
ich
c
o
u
ld
d
is
to
r
t
to
m
ato
tem
p
er
atu
r
e
m
ea
s
u
r
em
en
ts
.
T
h
e
ca
m
er
a
was
p
o
s
i
tio
n
ed
ab
o
v
e
th
e
co
n
v
ey
o
r
,
m
ain
tain
i
n
g
a
f
ix
e
d
d
is
tan
ce
f
r
o
m
th
e
o
b
ject
to
g
u
ar
an
tee
d
ata
co
n
s
is
ten
cy
.
T
h
e
g
ath
er
ed
d
ata
co
m
p
r
is
ed
v
i
d
eo
f
o
o
tag
e
o
f
to
m
ato
es p
o
s
itio
n
ed
o
n
th
e
m
o
v
i
n
g
co
n
v
ey
o
r
.
T
h
e
d
ataset
co
n
s
is
ts
o
f
tw
o
ty
p
es
o
f
im
ag
es,
n
am
el
y
,
im
ag
es
f
r
o
m
th
er
m
al
a
n
d
r
eg
u
lar
(
n
o
n
-
t
h
er
m
al)
.
T
h
er
m
al
im
ag
es
ar
e
u
s
ed
to
o
v
er
c
o
m
e
th
e
ch
allen
g
es
o
f
p
o
o
r
lig
h
tin
g
a
n
d
en
s
u
r
e
c
o
n
s
is
ten
t
d
etec
tio
n
in
v
ar
io
u
s
en
v
ir
o
n
m
en
tal
co
n
d
itio
n
s
,
as
s
tu
d
ies
h
a
v
e
s
h
o
wn
th
at
t
h
e
u
s
e
o
f
th
er
m
al
is
v
er
y
ef
f
ec
tiv
e
in
d
etec
tin
g
o
b
jec
ts
in
lo
w
o
r
co
m
p
lex
li
g
h
tin
g
s
itu
atio
n
s
[
3
9
]
.
Usi
n
g
th
er
m
al
im
a
g
in
g
also
h
elp
s
d
is
tin
g
u
is
h
o
b
jects
with
s
im
ilar
co
l
o
r
s
o
r
tex
tu
r
es
f
r
o
m
th
e
b
ac
k
g
r
o
u
n
d
,
t
h
er
eb
y
im
p
r
o
v
i
n
g
th
e
q
u
ality
o
f
th
e
d
ata
o
b
tain
ed
[
3
5
]
.
T
h
e
r
esu
lts
in
d
i
ca
ted
th
at
th
e
t
h
er
m
al
im
a
g
in
g
co
u
ld
ef
f
ec
tiv
ely
d
is
p
lay
to
m
ato
o
b
jects,
as
th
ey
d
is
ce
r
n
ib
le
th
a
n
o
t
h
er
o
b
jects
in
t
h
e
b
ac
k
g
r
o
u
n
d
.
T
h
is
co
n
d
itio
n
ca
n
s
u
p
p
o
r
t
th
e
d
e
v
e
lo
p
m
en
t
o
f
a
p
lan
t
s
o
r
tin
g
s
y
s
tem
u
s
in
g
an
o
u
td
o
o
r
co
n
v
ey
o
r
,
as in
[
4
0
]
.
3
.
2
.
P
re
pro
ce
s
s
ing
Data
p
r
ep
r
o
ce
s
s
in
g
is
ess
en
ti
al
to
p
r
ep
ar
e
th
e
ac
q
u
ir
e
d
d
a
ta
f
o
r
u
tili
za
tio
n
in
th
e
m
o
d
e
l
tr
ain
in
g
p
r
o
ce
s
s
.
Pre
p
r
o
ce
s
s
in
g
is
im
p
lem
en
ted
o
n
b
o
th
th
e
r
m
al
an
d
n
o
n
-
th
e
r
m
al
d
atasets
.
T
h
e
ac
q
u
ir
ed
v
id
e
o
d
ata
was
ex
tr
ac
ted
in
to
im
ag
e
f
r
am
es
.
Su
b
s
eq
u
en
tly
,
im
ag
e
d
at
a
o
b
tain
ed
f
r
o
m
v
id
eo
s
r
ec
o
r
d
ed
with
th
er
m
al
an
d
non
-
th
e
r
m
al
ca
m
e
r
as
is
lab
eled
o
r
an
n
o
tated
.
Mo
r
eo
v
e
r
,
au
g
m
en
tatio
n
tec
h
n
iq
u
es
a
r
e
em
p
lo
y
ed
to
en
h
an
c
e
th
e
v
ar
iab
ilit
y
o
f
th
e
d
ataset.
E
ac
h
ca
m
er
a
ty
p
e
h
as
5
7
0
im
ag
es
th
at
h
av
e
u
n
d
er
g
o
n
e
an
a
u
g
m
en
tatio
n
p
r
o
ce
s
s
to
en
h
an
ce
d
ata
v
a
r
iab
ilit
y
an
d
im
p
r
o
v
e
m
o
d
el
tr
ain
i
n
g
q
u
ality
.
T
h
e
au
g
m
en
tatio
n
m
eth
o
d
s
en
co
m
p
ass
r
o
tatio
n
,
f
lip
p
in
g
,
s
atu
r
atio
n
,
ex
p
o
s
u
r
e,
an
d
b
lu
r
r
in
g
.
Au
g
m
en
tatio
n
en
h
a
n
ce
s
th
e
m
o
d
el'
s
d
iv
er
s
ity
an
d
im
p
r
o
v
es
its
g
en
er
aliza
t
io
n
t
o
n
o
v
el
d
ata.
T
h
e
f
in
al
s
tag
e
in
v
o
lv
es
p
ar
titi
o
n
in
g
ea
ch
d
ataset
in
to
tr
ain
in
g
a
n
d
v
alid
atio
n
.
T
ab
le
2
p
r
esen
ts
th
e
v
is
u
al
r
ep
r
esen
tatio
n
s
d
e
r
iv
e
d
f
r
o
m
th
e
lab
ellin
g
an
d
a
u
g
m
en
tatio
n
m
eth
o
d
s
.
3
.
3
.
Det
ec
t
io
n a
lg
o
ri
t
hm
T
h
e
YOL
Ov
8
m
o
d
el
f
r
o
m
U
ltra
ly
tics
was
tr
ain
ed
u
s
in
g
a
d
ataset
th
at
h
as
6
4
0
×
640
-
p
i
x
el
im
ag
es
f
r
o
m
n
o
n
-
th
e
r
m
al
an
d
th
er
m
al
im
ag
es
d
ataset
r
esp
ec
tiv
el
y
.
T
h
e
tr
ain
in
g
p
r
o
ce
s
s
in
v
o
l
v
es
f
in
e
-
tu
n
in
g
t
h
e
p
ar
am
eter
s
u
s
in
g
th
e
Ad
am
o
p
tim
izatio
n
alg
o
r
ith
m
,
ef
f
ec
ti
v
el
y
ac
ce
ler
atin
g
c
o
n
v
e
r
g
en
c
e
an
d
r
e
d
u
cin
g
lo
s
s
d
u
r
in
g
tr
ain
in
g
.
Fin
e
-
tu
n
in
g
a
im
s
to
o
p
tim
ize
th
e
m
o
d
el
p
e
r
f
o
r
m
an
ce
to
ac
h
iev
e
th
e
b
est
r
esu
lts
in
d
etec
tin
g
to
m
ato
es
o
n
co
n
v
ey
o
r
b
elt
m
ac
h
in
es.
T
h
e
tr
ain
in
g
p
h
as
e
in
th
is
s
tu
d
y
u
tili
ze
s
th
e
T
esla
T
4
g
r
ap
h
ics
pr
o
ce
s
s
in
g
u
n
it
(
GPU
)
.
I
t
is
ex
ce
llen
t
f
o
r
d
ee
p
lear
n
i
n
g
task
s
s
u
ch
as
im
ag
e
p
r
o
ce
s
s
in
g
with
th
e
YOL
Ov
8
m
o
d
el
a
n
d
o
b
ject
d
etec
tio
n
.
W
ith
1
5
GB
o
f
m
em
o
r
y
an
d
C
UDA
v
er
s
io
n
1
2
.
2
,
th
e
T
esl
a
T
4
is
ex
ce
llen
t
f
o
r
p
r
o
ce
s
s
in
g
lar
g
e
d
atasets
in
i
n
d
u
s
tr
ial
en
v
ir
o
n
m
en
ts
th
at
r
eq
u
ir
e
r
ea
l
-
tim
e
p
r
o
ce
s
s
in
g
.
T
h
ese
s
p
ec
if
icatio
n
s
en
s
u
r
e
f
ast an
d
ac
cu
r
ate
m
o
d
e
l tr
ain
in
g
,
m
ak
in
g
it a
p
p
licab
l
e
in
in
d
u
s
tr
ial
s
itu
atio
n
s
s
u
ch
as a
u
to
m
atic
to
m
ato
s
o
r
tin
g
.
Fo
llo
win
g
4
0
e
p
o
ch
s
o
f
tr
ain
i
n
g
,
a
v
alid
atio
n
p
r
o
ce
s
s
was
co
n
d
u
cted
to
ass
ess
th
e
ef
f
icac
y
a
n
d
p
er
f
o
r
m
an
ce
o
f
th
e
tr
ain
e
d
m
o
d
el
[
4
1
]
,
[
4
2
]
.
3
.
4
.
E
v
a
lua
t
i
o
n m
et
rics
Mo
d
el
test
in
g
is
p
er
f
o
r
m
ed
af
ter
tr
ain
in
g
t
o
ass
ess
th
e
m
o
d
el's
p
er
f
o
r
m
a
n
ce
in
d
etec
tin
g
to
m
ato
es.
E
v
alu
atio
n
is
p
er
f
o
r
m
e
d
u
s
in
g
a
s
ep
ar
ate
test
d
ataset,
wh
ic
h
th
e
m
o
d
el
n
ev
e
r
s
ee
s
d
u
r
in
g
tr
ain
in
g
,
to
e
n
s
u
r
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
1
5
,
No
.
2
,
J
u
n
e
2
0
2
6
:
4
5
1
-
461
456
th
at
th
e
m
o
d
el
ca
n
g
en
er
alize
well
to
n
ew
d
ata.
T
es
t
d
ata
i
n
th
e
f
o
r
m
o
f
a
v
id
e
o
o
f
to
m
ato
es
o
n
a
m
o
v
in
g
co
n
v
ey
o
r
.
T
h
e
m
etr
ics
u
s
ed
to
m
ea
s
u
r
e
m
o
d
el
p
er
f
o
r
m
an
ce
i
n
clu
d
e
p
r
ec
is
io
n
,
r
ec
all,
F1
-
s
c
o
r
e,
m
ea
n
av
er
a
g
e
p
r
ec
is
io
n
(
m
AP)
,
a
n
d
in
ter
s
ec
tio
n
o
v
er
th
e
u
n
io
n
(
I
o
U)
.
Pre
cisi
o
n
an
d
r
ec
all
m
ea
s
u
r
e
th
e
m
o
d
el'
s
ac
cu
r
ac
y
in
d
etec
tin
g
r
elev
a
n
t
o
b
jects,
wh
ile
th
e
p
r
ec
is
io
n
a
n
d
r
ec
all
o
f
th
e
F1
-
s
co
r
e
b
ala
n
ce
[
4
3
]
.
Sp
ec
if
ically
,
p
r
ec
is
io
n
is
a
m
etr
ic
to
m
ea
s
u
r
e
h
o
w
ac
cu
r
ate
t
h
e
m
o
d
el'
s
p
r
ed
ic
tio
n
s
ar
e
b
y
co
m
p
ar
in
g
th
e
co
r
r
ec
t
p
r
ed
ictio
n
s
(
tr
u
e
p
o
s
itiv
e
(
T
P)
)
to
th
e
to
ta
l
p
o
s
itiv
e
p
r
e
d
ictio
n
s
(
TP
+
f
a
ls
e
p
o
s
itiv
e
(
FP
)
)
.
R
ec
all
is
a
m
etr
ic
to
m
ea
s
u
r
e
h
o
w
m
an
y
o
b
jects
th
e
m
o
d
e
l
s
u
cc
ess
f
u
lly
d
etec
t
s
o
u
t
o
f
all
th
e
o
b
jects
p
r
esen
t
(
d
et
ec
ted
an
d
m
is
s
ed
)
.
F1
-
s
co
r
e
is
th
e
h
a
r
m
o
n
ic
m
e
an
o
f
p
r
ec
is
io
n
a
n
d
r
ec
all,
b
a
lan
cin
g
ac
cu
r
ac
y
a
n
d
c
o
m
p
le
ten
ess
.
I
n
ad
d
itio
n
,
m
AP
p
r
o
v
id
es
a
co
m
p
r
eh
e
n
s
iv
e
p
ictu
r
e
o
f
th
e
m
o
d
el'
s
d
etec
tio
n
p
er
f
o
r
m
an
ce
u
n
d
er
v
ar
io
u
s
o
b
ject
o
v
e
r
lap
co
n
d
itio
n
s
.
m
AP
is
th
e
a
v
er
a
g
e
o
f
th
e
av
er
a
g
e
p
r
ec
is
io
n
(
AP)
v
alu
es
f
o
r
all
class
es
an
d
th
e
I
o
U
th
r
esh
o
ld
,
wh
ile
AP
is
ca
lcu
lated
as
th
e
ar
ea
u
n
d
er
th
e
p
r
ec
is
io
n
-
r
e
ca
ll
cu
r
v
e
f
o
r
ea
c
h
class
.
I
o
U
is
a
m
etr
ic
th
at
q
u
an
tifie
s
th
e
o
v
er
la
p
p
in
g
ar
e
a
b
etwe
en
a
p
r
ed
icted
b
o
u
n
d
i
n
g
b
o
x
an
d
a
g
r
o
u
n
d
tr
u
th
b
o
u
n
d
in
g
b
o
x
.
On
a
co
n
v
ey
o
r
,
p
a
r
t
o
f
th
e
to
m
at
o
'
s
s
u
r
f
ac
e
is
co
v
er
ed
,
an
d
th
e
to
m
ato
ca
n
ch
an
g
e
p
o
s
itio
n
d
u
e
to
m
o
v
em
e
n
ts
s
u
ch
a
s
r
o
tatio
n
.
T
h
is
co
n
d
itio
n
r
eq
u
ir
es
v
er
y
p
r
ec
is
e
b
o
u
n
d
in
g
b
o
x
d
etec
tio
n
,
s
o
th
e
m
o
d
el
m
u
s
t
d
o
m
o
r
e
th
a
n
ju
s
t
d
etec
t
th
e
to
m
ato
.
T
h
er
ef
o
r
e,
m
AP
is
n
ec
ess
ar
y
b
ec
au
s
e
it
s
er
v
es
a
cr
u
cial
f
u
n
ctio
n
in
ass
ess
in
g
th
e
p
r
ec
is
io
n
o
f
o
b
ject
lo
ca
lizatio
n
.
T
h
is
m
etr
ic
h
as
also
b
ee
n
wid
ely
u
s
ed
to
d
eter
m
in
e
t
h
e
r
esu
lts
o
f
o
b
ject
d
etec
tio
n
in
th
e
ag
r
icu
ltu
r
al
s
ec
to
r
[
7
]
,
[
9
]
,
[
1
0
]
,
[
1
4
]
.
T
ab
le
2
.
R
ep
r
esen
t im
ag
es f
r
o
m
p
r
ep
r
o
ce
s
s
in
g
N
o
n
-
t
h
e
r
mal
Th
e
r
m
a
l
I
mag
e
l
a
b
e
l
l
i
n
g
I
mag
e
a
u
g
me
n
t
a
t
i
o
n
Ad
d
itio
n
ally
,
in
f
er
en
ce
tim
e
m
ea
s
u
r
es
a
m
o
d
el'
s
tim
e
to
p
r
o
ce
s
s
a
s
in
g
le
im
ag
e
o
r
b
atc
h
o
f
im
a
g
es.
T
h
is
tim
e
is
u
s
u
ally
m
ea
s
u
r
ed
in
m
illi
s
ec
o
n
d
s
(
m
s
)
o
r
f
r
am
es
p
er
s
ec
o
n
d
(
FP
S).
T
h
er
e
is
n
o
f
ix
ed
f
o
r
m
u
la
f
o
r
in
f
er
en
ce
,
b
u
t th
is
m
etr
ic
in
d
icate
s
th
e
m
o
d
el'
s
ab
ilit
y
to
d
etec
t to
m
ato
es e
f
f
ec
tiv
ely
with
in
a
s
y
s
tem
.
=
+
(
1
)
=
+
(
2
)
1
−
=
2
×
x
+
(
3
)
=
1
∑
=
1
(
4
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
C
o
mp
a
r
is
o
n
o
f th
erma
l a
n
d
n
o
n
-
th
erma
l ima
g
es fo
r
to
ma
to
…
(
S
u
lfa
ya
n
ti F
a
h
a
r
u
d
d
in
S
it
u
ju
)
457
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
r
ain
in
g
an
d
v
alid
atio
n
wer
e
co
n
d
u
cted
t
o
co
m
p
ar
e
th
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
YOL
Ov
8
m
o
d
el
in
d
etec
tin
g
to
m
at
o
es
u
s
in
g
th
er
m
al
d
ata
an
d
n
o
n
-
t
h
er
m
al
d
ata.
T
r
ain
in
g
was
co
n
d
u
cted
f
o
r
4
0
ep
o
ch
s
.
T
a
b
le
s
3
an
d
4
p
r
esen
t
th
e
n
o
r
m
alize
d
r
esu
lts
o
f
th
e
co
n
f
u
s
io
n
m
at
r
ix
f
o
r
to
m
ato
d
etec
tio
n
u
tili
zi
n
g
YOL
Ov
8
o
n
th
er
m
al
an
d
n
o
n
-
t
h
er
m
al
d
atas
ets,
r
esp
ec
tiv
ely
.
YOL
Ov
8
ef
f
ec
tiv
ely
id
en
tifie
s
to
m
ato
o
b
je
cts,
p
ar
ticu
lar
ly
in
th
er
m
al
d
atasets
,
with
an
er
r
o
r
r
ate
o
f
u
p
t
o
1
%.
B
o
th
c
o
n
f
u
s
io
n
m
atr
ices
r
ev
ea
l
th
at
ce
r
tain
b
ac
k
g
r
o
u
n
d
s
ar
e
m
is
id
en
tifie
d
as
to
m
at
o
es,
in
d
icatin
g
th
at
YOL
Ov
8
h
as
h
eig
h
ten
ed
s
en
s
itiv
ity
in
d
etec
tin
g
to
m
ato
o
b
jects
ac
r
o
s
s
b
o
th
d
ataset
ty
p
es.
T
h
u
s
,
YOL
Ov
8
d
em
o
n
s
tr
ates
s
u
f
f
icien
t
r
eliab
ilit
y
f
o
r
ap
p
licatio
n
in
to
m
ato
o
b
ject
d
etec
tio
n
with
in
in
d
u
s
tr
ial
s
ettin
g
s
th
at
em
p
lo
y
co
n
v
e
y
o
r
s
.
T
h
e
p
r
im
ar
y
ev
al
u
atio
n
m
ea
s
u
r
es,
s
u
ch
as
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
f
o
r
ea
ch
m
o
d
el,
co
m
e
f
r
o
m
v
alid
atio
n
d
ata.
T
h
e
r
esu
lts
o
f
t
h
e
m
AP5
0
m
etr
ic
wer
e
m
ea
s
u
r
ed
to
ass
ess
th
e
m
o
d
el'
s
ac
cu
r
ac
y
in
d
etec
tin
g
o
b
jects.
I
n
f
er
en
ce
s
wer
e
o
b
t
ain
ed
f
r
o
m
test
in
g
u
s
in
g
v
i
d
eo
s
f
r
o
m
ea
c
h
th
er
m
al
an
d
n
o
n
-
t
h
er
m
al
ca
m
er
a
.
T
ab
le
5
c
o
m
p
iles
th
e
m
etr
ic
ev
alu
atio
n
r
esu
lts
,
wh
ile
Fig
u
r
e
4
s
h
o
ws
th
e
r
es
u
lts
o
f
th
e
c
o
m
p
ar
is
o
n
o
f
th
er
m
al
(
Fig
u
r
e
4
(
a)
)
an
d
n
o
n
-
th
e
r
m
al
(
Fig
u
r
e
4
(
b
)
)
test
in
g
o
n
th
e
test
in
g
d
ataset.
T
ab
le
3
.
No
r
m
alize
d
c
o
n
f
u
s
io
n
m
atr
ix
o
f
to
m
ato
d
etec
tio
n
u
s
in
g
YOL
Ov
8
with
th
er
m
al
i
m
ag
in
g
A
c
t
u
a
l
P
r
e
d
i
c
t
i
o
n
To
ma
t
o
B
a
c
k
g
r
o
u
n
d
To
ma
t
o
0
.
9
9
0
.0
1
B
a
c
k
g
r
o
u
n
d
1
.0
0
0
T
ab
le
4
.
No
r
m
alize
d
co
n
f
u
s
io
n
m
atr
ix
o
f
to
m
ato
d
etec
tio
n
u
s
in
g
YOL
Ov
8
with
n
o
n
-
th
er
m
al
im
ag
in
g
M
e
t
h
o
d
A
c
t
u
a
l
P
r
e
d
i
c
t
i
o
n
To
ma
t
o
B
a
c
k
g
r
o
u
n
d
Y
O
LO
v
8
To
ma
t
o
0
.
9
4
0
.0
6
B
a
c
k
g
r
o
u
n
d
1
.
00
0
T
ab
le
5
.
C
o
m
p
a
r
is
o
n
o
f
th
er
m
al
an
d
n
o
n
-
th
e
r
m
al
test
in
g
r
esu
lts
M
e
t
r
i
c
s
Th
e
r
m
a
l
N
o
n
-
t
h
e
r
ma
l
C
o
m
b
i
n
a
t
i
o
n
(
t
h
e
r
mal
a
n
d
n
o
n
-
t
h
e
r
m
a
l
)
P
r
e
c
i
s
i
o
n
0
.
99
0
.
8
4
0
.
9
0
R
e
c
a
l
l
0
.
9
8
0
.
88
0
.
9
8
F
1
-
sc
o
r
e
0
.
9
8
0.
86
0
.
9
4
M
e
t
r
i
c
s
mA
P
5
0
0
.
9
9
0.
77
0
.
98
I
n
f
e
r
e
n
c
e
2
2
.
0
f
p
s
2
4
.
2
f
p
s
-
(
a)
(
b
)
Fig
u
r
e
4
.
C
o
m
p
a
r
is
o
n
o
f
m
ate
r
ial
co
n
d
itio
n
s
f
o
r
(
a
)
th
er
m
al
with
less
an
d
n
o
r
m
al
am
o
u
n
t
a
n
d
(
b
)
n
o
n
-
th
e
r
m
al
with
less
an
d
n
o
r
m
al
am
o
u
n
t
T
h
e
m
o
d
el
tr
ain
ed
with
th
er
m
al
im
ag
es
r
o
u
tin
ely
o
u
tp
er
f
o
r
m
s
th
e
m
o
d
el
em
p
lo
y
in
g
s
o
lely
non
-
th
e
r
m
al
im
ag
es.
T
h
e
th
er
m
al
m
o
d
el
is
m
o
r
e
p
r
ec
is
e
an
d
h
as
s
tr
o
n
g
e
r
d
etec
tio
n
ca
p
a
b
ilit
ies,
p
ar
ticu
lar
ly
wh
en
it
c
o
m
es
to
id
en
tif
y
in
g
ev
er
y
to
m
ato
o
b
ject
in
t
h
e
im
ag
e,
as
e
v
id
en
ce
d
b
y
its
h
i
g
h
er
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e.
T
h
e
t
h
er
m
al
m
o
d
el'
s
F1
-
s
co
r
e
is
1
4
.
6
%
h
ig
h
er
th
an
th
e
n
o
n
-
th
er
m
al
m
o
d
e
l.
T
h
is
s
u
g
g
ests
th
at
th
e
th
er
m
al
m
o
d
el
is
s
u
b
s
tan
tially
m
o
r
e
s
u
cc
ess
f
u
l
in
d
etec
tio
n
o
v
er
all,
n
o
t
ju
s
t
m
ar
g
in
al
ly
b
etter
.
Utilizin
g
th
e
FP
r
ate
≈
1
−
p
r
ec
is
io
n
ap
p
r
o
ac
h
,
th
e
r
atio
o
f
n
o
n
-
th
er
m
al
to
th
er
m
al
FP
r
ates is
1
6
:1
.
T
h
is
in
d
icate
s
th
at
th
e
th
er
m
al
d
etec
to
r
co
m
m
its
1
6
tim
es
f
ewe
r
er
r
o
r
s
in
id
en
tify
in
g
n
o
n
e
x
is
ten
t
o
b
jects
co
m
p
ar
e
d
to
th
e
non
-
th
e
r
m
al
d
etec
to
r
.
Simu
lta
n
eo
u
s
ly
,
u
tili
zin
g
th
e
f
alse
n
e
g
ativ
e
(
FN)
r
ate
≈
1
−
r
ec
all
m
e
th
o
d
o
lo
g
y
,
th
e
FN
r
ate
r
atio
b
etwe
en
n
o
n
-
t
h
er
m
al
an
d
th
er
m
al
is
6
.
T
h
is
s
h
o
ws
th
at
th
e
T
h
er
m
al
m
o
d
el
o
v
er
lo
o
k
s
s
ix
tim
es
f
ewe
r
th
in
g
s
th
an
th
e
n
o
n
-
th
er
m
al
m
o
d
el,
r
e
n
d
er
i
n
g
it
m
o
r
e
s
en
s
itiv
e
an
d
n
ea
r
ly
c
ap
a
b
le
o
f
d
etec
tin
g
all
o
b
jects.
T
h
e
co
m
p
r
eh
en
s
iv
e
co
m
p
ar
is
o
n
o
f
th
e
r
esu
lts
in
d
icate
s
th
at
th
er
m
al
is
s
ig
n
if
ican
tly
s
u
p
er
io
r
to
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
1
5
,
No
.
2
,
J
u
n
e
2
0
2
6
:
4
5
1
-
461
458
non
-
th
e
r
m
al.
T
h
e
r
elativ
e
m
A
P5
0
d
if
f
er
e
n
ce
o
f
th
er
m
al
to
n
o
n
-
th
e
r
m
al
is
ap
p
r
o
x
im
ately
2
8
%,
r
esu
ltin
g
in
a
m
u
ch
b
etter
o
v
er
all
p
r
ec
is
io
n
-
r
ec
all
cu
r
v
e
in
th
e
th
er
m
al
m
o
d
el
co
m
p
ar
ed
t
o
th
e
n
o
n
-
th
er
m
al
m
o
d
el.
Fig
u
r
e
5
d
is
p
lay
s
th
e
co
m
p
ar
is
o
n
o
f
m
AP
g
r
ap
h
s
d
u
r
i
n
g
t
h
e
tr
ain
i
n
g
p
r
o
ce
s
s
,
s
h
o
win
g
th
e
o
u
tc
o
m
es
o
f
th
e
m
o
d
el
tr
ain
in
g
p
r
o
ce
d
u
r
e
.
T
h
e
tr
ain
i
n
g
r
esu
lts
o
n
th
e
th
er
m
al
d
ataset
s
h
o
w
th
at
th
e
m
o
d
el
co
n
s
is
ten
tly
ac
h
iev
es
a
h
ig
h
m
AP5
0
ac
r
o
s
s
all
tr
ain
i
n
g
e
p
o
ch
s
c
o
m
p
ar
ed
t
o
th
e
n
o
n
-
th
er
m
al
d
ataset.
I
n
t
h
e
f
i
r
s
t
ep
o
ch
,
th
e
m
o
d
el
o
b
tain
ed
a
m
AP5
0
o
f
0
.
9
4
7
1
2
,
b
u
t
th
en
in
cr
ea
s
ed
in
th
e
n
ex
t
ep
o
ch
.
T
h
e
m
o
d
el
co
n
tin
u
ed
to
s
h
o
w
s
ati
s
f
y
in
g
p
er
f
o
r
m
an
ce
t
h
r
o
u
g
h
o
u
t
th
e
tr
ain
in
g
p
r
o
ce
s
s
,
with
m
AP5
0
r
an
g
in
g
f
r
o
m
0
.
9
4
7
1
2
to
0
.
9
9
4
4
.
E
v
en
af
ter
s
ev
er
al
ep
o
ch
s
,
th
er
e
is
n
o
d
i
s
ce
r
n
ib
le
d
ec
lin
e
in
m
AP5
0
v
alu
es'
p
er
f
o
r
m
an
ce
d
u
r
i
n
g
t
h
e
tr
ain
in
g
p
r
o
ce
s
s
.
T
h
er
m
al
n
o
t
o
n
ly
ex
ce
ls
at
a
s
in
g
u
lar
p
o
in
t
b
u
t
also
d
e
m
o
n
s
tr
ates
s
u
p
er
io
r
c
o
n
s
is
ten
cy
a
n
d
p
r
o
x
im
ity
to
th
e
id
ea
l
ac
r
o
s
s
all
ep
o
ch
s
.
T
h
is
in
d
i
c
a
t
e
s
t
h
a
t t
h
e
m
o
d
e
l
h
as
e
f
f
e
c
t
i
v
e
l
y
l
e
a
r
n
e
d
t
o
g
e
n
e
r
a
li
z
e
v
i
s
u
a
l d
a
t
a
p
e
r
t
a
i
n
i
n
g
t
o
t
h
e
o
b
j
e
c
t'
s
t
e
m
p
e
r
at
u
r
e
.
I
n
c
o
n
t
r
a
s
t
,
t
r
ai
n
i
n
g
o
n
n
o
n
-
t
h
e
r
m
a
l
d
a
t
a
s
h
o
w
s
m
o
r
e
s
i
g
n
if
i
c
a
n
t
p
e
r
f
o
r
m
a
n
c
e
f
l
u
c
t
u
a
t
i
o
n
s
t
h
a
n
t
h
e
r
m
a
l
d
at
a
.
I
n
t
h
e
f
i
r
s
t
e
p
o
c
h
,
t
h
e
m
A
P
5
0
v
a
l
u
e
i
s
m
u
c
h
l
o
w
e
r
t
h
a
n
t
h
e
t
h
er
m
a
l
d
a
t
a
.
Fig
u
r
e
5
.
C
o
m
p
a
r
is
o
n
o
f
m
AP g
r
ap
h
s
in
t
h
e
test
in
g
p
r
o
ce
s
s
C
o
m
p
ar
ed
t
o
th
e
th
er
m
al
d
ata
s
et,
th
e
co
m
b
in
atio
n
d
ataset
e
x
h
ib
its
a
s
ig
n
i
f
ican
tly
h
ig
h
er
FP
r
ate
in
its
m
o
d
el,
ap
p
r
o
x
im
ately
te
n
tim
es
g
r
ea
ter
.
T
h
e
r
ate
in
d
icate
s
th
at
th
e
co
m
b
in
atio
n
ex
h
ib
its
a
h
ig
h
er
in
cid
en
ce
o
f
f
alse
d
etec
tio
n
,
y
et
m
ain
tain
s
a
h
ig
h
r
ec
all.
E
ac
h
co
m
b
i
n
atio
n
an
d
th
er
m
al
m
o
d
el
p
r
o
v
id
e
eq
u
iv
alen
t
r
ec
all
v
alu
es,
in
d
ic
atin
g
th
at
b
o
th
ef
f
ec
tiv
ely
id
e
n
tify
n
ea
r
ly
all
o
b
jects.
T
h
e
c
o
m
b
in
atio
n
d
id
n
o
t
y
ield
a
s
ig
n
i
f
ican
t
r
esu
lt
in
s
en
s
itiv
ity
wh
en
co
m
p
ar
ed
t
o
th
e
u
s
e
o
f
th
e
r
m
al
alo
n
e.
T
h
is
also
o
cc
u
r
s
in
m
AP5
0
.
I
n
co
m
p
a
r
is
o
n
to
u
s
in
g
o
n
l
y
n
o
n
-
th
er
m
al
d
ata,
th
e
co
m
b
in
atio
n
o
f
th
er
m
al
a
n
d
n
o
n
-
th
er
m
al
d
ata
y
ield
ed
g
r
ea
ter
p
r
ec
is
io
n
,
r
ec
all,
F1
-
s
co
r
e,
an
d
m
AP5
0
v
alu
es.
T
h
is
d
em
o
n
s
tr
ates
h
o
w
to
m
ato
d
etec
tio
n
p
er
f
o
r
m
an
ce
ca
n
b
e
e
n
h
an
ce
d
b
y
u
s
in
g
th
e
r
m
al
im
a
g
es.
Simu
ltan
eo
u
s
ly
,
th
e
in
f
er
e
n
ce
v
alu
es
f
o
r
b
o
t
h
m
o
d
els,
th
er
m
al
an
d
n
o
n
-
th
er
m
al,
p
r
o
d
u
ce
co
m
m
en
d
a
b
le
r
e
s
u
lts
,
n
o
tab
ly
≥
2
0
f
p
s
,
r
en
d
er
i
n
g
th
em
ap
p
r
o
p
r
iate
f
o
r
r
ea
l
-
tim
e
a
p
p
licatio
n
s
.
T
h
e
th
er
m
al
d
etec
tio
n
ac
cu
r
a
c
y
d
em
o
n
s
tr
ated
s
u
p
er
io
r
r
esu
lt
s
co
m
p
ar
ed
t
o
n
o
n
-
th
er
m
al
ca
m
er
a
d
ata.
T
h
e
th
er
m
al
ca
m
e
r
a
ca
p
tu
r
es
h
ea
t
an
d
g
e
n
er
ates
co
lo
r
wa
v
es
th
at
co
r
r
esp
o
n
d
to
th
e
o
b
ject'
s
tem
p
er
atu
r
e,
allo
win
g
T
o
m
ato
E
d
g
e
t
o
ef
f
e
ctiv
ely
d
etec
t
an
d
p
r
ec
is
ely
d
e
ter
m
in
e
th
e
s
h
ap
e
o
f
th
e
to
m
at
o
,
d
if
f
e
r
en
tiatin
g
it
f
r
o
m
s
u
r
r
o
u
n
d
i
n
g
o
b
jects
as
p
r
ev
i
o
u
s
ly
m
e
n
tio
n
ed
in
[
4
4
]
.
T
h
e
u
tili
za
tio
n
o
f
a
n
o
n
-
th
er
m
al
f
o
r
to
m
ato
d
etec
tio
n
y
ield
ed
in
ad
eq
u
ate
r
esu
lts
d
u
e
to
th
e
o
cc
asio
n
al
b
lu
r
r
in
ess
o
f
m
o
v
i
n
g
to
m
ato
e
s
o
n
th
e
co
n
v
ey
o
r
.
T
h
e
im
ag
e'
s
b
lu
r
r
i
n
ess
lim
its
th
e
a
b
ilit
y
to
id
en
tify
th
e
e
d
g
es
o
f
th
e
to
m
ato
,
r
esu
ltin
g
in
an
i
n
ac
cu
r
ate
r
ep
r
esen
tatio
n
o
f
its
s
h
ap
e.
T
h
is
r
ed
u
ce
d
th
e
m
o
d
el'
s
ab
ilit
y
to
ac
cu
r
ately
id
e
n
tify
to
m
at
o
es.
C
o
n
s
eq
u
en
tly
,
o
u
r
s
tu
d
y
d
e
m
o
n
s
tr
ated
th
at
th
er
m
al
ca
m
er
as
p
o
s
s
ess
b
en
ef
its
in
id
en
tify
in
g
m
o
v
i
n
g
o
b
jects
r
elativ
e
to
non
-
th
e
r
m
al
ca
m
er
as.
H
o
wev
er
,
s
o
m
e
ad
d
itio
n
al
co
n
s
id
er
atio
n
s
m
u
s
t
b
e
ad
d
r
ess
ed
:
th
e
s
tu
d
y
f
o
u
n
d
th
at
th
e
in
f
lu
en
ce
o
f
lig
h
t
cir
cu
m
s
tan
c
es
d
o
es
n
o
t
a
s
ig
n
if
ican
tly
d
if
f
er
en
tiate
th
e
d
etec
tio
n
o
u
tco
m
es
o
f
th
er
m
al
an
d
non
-
th
e
r
m
al
d
ata;
th
e
r
o
u
n
d
n
e
s
s
f
ea
tu
r
e
o
f
th
e
to
m
ato
o
b
ject
is
th
e
p
r
im
ar
y
attr
ib
u
te
t
h
at
d
i
s
tin
g
u
is
h
es
it
f
r
o
m
th
e
b
ac
k
g
r
o
u
n
d
,
th
is
p
er
h
ap
s
lead
in
g
to
th
e
m
is
id
en
tific
atio
n
o
f
o
t
h
er
r
o
u
n
d
o
b
jects
as
to
m
a
to
es;
a
th
er
m
al
ca
m
er
a
ca
n
id
en
tif
y
o
b
jects b
y
th
eir
h
ea
t w
h
en
th
er
e
is
a
n
o
ta
b
le
tem
p
er
atu
r
e
d
is
p
ar
it
y
b
etwe
en
th
e
o
b
ject
an
d
its
s
u
r
r
o
u
n
d
in
g
s
,
wh
ile
R
GB
ca
m
er
as
d
ep
en
d
o
n
am
b
ien
t
li
g
h
t
s
o
p
er
f
o
r
m
an
ce
d
r
o
p
s
s
h
a
r
p
ly
in
d
u
s
k
,
n
ig
h
t,
o
r
s
h
ad
ed
a
r
ea
s
.
T
h
e
an
a
ly
s
is
o
f
th
e
o
b
tain
ed
f
i
n
d
in
g
s
in
d
icate
s
th
e
n
ee
d
to
in
teg
r
ate
th
e
th
er
m
al
ca
m
e
r
a
with
s
en
s
o
r
s
,
ca
m
er
as,
o
r
o
th
e
r
d
ev
ices
as
a
h
y
b
r
i
d
d
etec
tio
n
m
et
h
o
d
s
o
th
at
th
e
th
er
m
al
ca
m
er
a
ca
n
wo
r
k
at
r
o
o
m
tem
p
er
atu
r
e.
No
n
eth
eless
,
th
is
s
tu
d
y
h
as
d
em
o
n
s
tr
ated
th
at
th
e
th
er
m
al
ca
m
er
a
is
ef
f
ec
tiv
e
in
aid
in
g
au
to
m
atic
d
etec
tio
n
s
y
s
tem
s
with
in
in
d
u
s
tr
ial
en
v
ir
o
n
m
e
n
ts
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
C
o
mp
a
r
is
o
n
o
f th
erma
l a
n
d
n
o
n
-
th
erma
l ima
g
es fo
r
to
ma
to
…
(
S
u
lfa
ya
n
ti F
a
h
a
r
u
d
d
in
S
it
u
ju
)
459
5.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
h
as
p
r
esen
ted
th
e
co
m
p
ar
is
o
n
o
f
th
er
m
al
an
d
n
o
n
-
th
e
r
m
al
u
s
in
g
YOL
Ov
8
-
b
ased
f
o
r
o
b
ject
d
etec
tio
n
.
T
h
e
s
y
s
tem
g
r
ea
tly
en
h
a
n
ce
s
to
m
ato
d
e
tec
tio
n
p
er
f
o
r
m
an
ce
.
T
h
e
an
aly
s
i
s
r
esu
lts
s
h
o
w
th
at
th
e
m
o
d
el
tr
ain
e
d
u
s
in
g
th
e
r
m
al
d
ata
h
as
v
er
y
g
o
o
d
c
o
n
s
is
ten
cy
d
u
r
in
g
th
e
tr
ain
in
g
p
r
o
ce
s
s
,
with
o
u
t
ex
p
er
ien
cin
g
a
s
ig
n
if
ican
t d
ec
r
ea
s
e
in
p
er
f
o
r
m
a
n
ce
.
T
h
is
is
ac
h
iev
ed
b
y
ap
p
ly
in
g
a
d
atase
t th
at
h
as u
n
d
e
r
g
o
n
e
au
g
m
en
tatio
n
tech
n
i
q
u
es
an
d
is
d
iv
id
e
d
f
o
r
tr
ain
in
g
,
v
alid
atio
n
,
a
n
d
test
in
g
p
u
r
p
o
s
es.
T
h
is
m
o
d
el
o
u
tp
er
f
o
r
m
ed
t
h
e
o
n
e
tr
ain
e
d
o
n
n
o
n
-
th
er
m
al
ca
m
e
r
a
d
ata
i
n
ter
m
s
o
f
p
r
ec
is
io
n
,
r
ec
all,
F
1
-
s
co
r
e,
an
d
m
AP5
0
v
alu
es.
On
th
e
o
th
er
h
a
n
d
,
th
e
n
o
n
-
th
er
m
al
m
o
d
el
was
u
n
s
tab
le
d
u
r
in
g
th
e
f
ir
s
t
f
ew
ep
o
ch
s
an
d
h
a
d
h
i
g
h
er
p
er
f
o
r
m
an
ce
f
lu
ctu
atio
n
s
an
d
m
AP5
0
f
in
d
in
g
s
.
B
ased
o
n
th
e
co
n
f
u
s
io
n
m
at
r
ix
o
f
th
e
v
alid
atio
n
d
ata,
th
e
th
er
m
al
m
o
d
el
ac
h
ie
v
ed
9
9
%
d
etec
tio
n
p
r
ec
is
io
n
.
I
n
co
n
tr
a
s
t,
th
e
n
o
n
-
th
er
m
al
m
o
d
el
s
h
o
wed
h
ig
h
er
er
r
o
r
s
,
with
s
o
m
e
b
ac
k
g
r
o
u
n
d
ca
s
es
b
ein
g
wr
o
n
g
ly
d
etec
ted
,
s
u
c
h
as
to
m
ato
es,
an
d
v
ice
v
er
s
a.
As
a
r
esu
lt,
th
er
m
al
ca
m
er
as
h
av
e
b
ee
n
s
h
o
wn
to
b
e
m
o
r
e
e
f
f
ec
tiv
e
at
s
u
p
p
o
r
tin
g
th
e
to
m
ato
d
etec
tio
n
s
y
s
tem
.
YOL
Ov
8
h
as
also
d
em
o
n
s
tr
ated
p
r
o
f
icien
cy
in
d
etec
t
in
g
to
m
at
o
item
s
with
an
in
f
e
r
en
ce
r
ate
e
x
ce
ed
in
g
2
0
f
p
s
ac
r
o
s
s
b
o
th
d
ataset
ty
p
es,
in
d
icatin
g
its
c
ap
ab
ilit
y
to
s
p
ec
if
ically
id
e
n
tify
f
ea
tu
r
es
o
f
m
o
v
in
g
o
b
jects.
W
h
en
it
co
m
es
to
in
d
u
s
tr
ial
au
to
m
atio
n
ac
tiv
itie
s
th
at
tak
e
p
lace
af
ter
h
ar
v
est,
s
u
ch
as
th
e
u
s
e
o
f
co
n
v
ey
o
r
b
elts
,
th
is
th
er
m
al
tech
n
o
lo
g
y
ca
n
in
cr
ea
s
e
p
r
ec
is
io
n
an
d
ef
f
icien
cy
.
Fu
t
u
r
e
wo
r
k
is
ex
p
ec
te
d
to
f
o
cu
s
o
n
test
in
g
in
m
o
r
e
co
m
p
lex
en
v
ir
o
n
m
e
n
ts
,
in
clu
d
in
g
s
y
s
tem
in
teg
r
atio
n
f
o
r
r
ea
l
-
tim
e
to
m
ato
s
o
r
tin
g
m
ac
h
in
es.
I
t
m
ig
h
t
b
e
v
alu
ab
le
to
co
n
d
u
ct
ex
p
e
r
im
e
n
ts
th
at
ac
co
u
n
t
f
o
r
p
o
ten
tial
n
o
n
-
tar
g
et
o
b
jects
or
n
e
g
ativ
e
o
b
jects
(
s
u
ch
as
leav
es
o
r
o
th
er
f
r
u
its
o
r
v
eg
e
tab
les
)
o
n
th
e
c
o
n
v
e
y
o
r
b
elt.
I
t
is
d
esira
b
le
to
ev
alu
ate
th
e
r
o
b
u
s
tn
ess
o
f
th
e
m
eth
o
d
i
n
ca
s
es
wh
er
e
o
b
j
ec
ts
o
th
er
th
an
to
m
ato
es
ap
p
ea
r
b
y
m
is
tak
e.
I
n
ad
d
itio
n
,
in
f
er
en
ce
s
p
ee
d
o
p
tim
izatio
n
will
b
e
a
to
p
p
r
i
o
r
ity
s
o
th
at
th
e
s
y
s
tem
ca
n
r
u
n
m
o
r
e
ef
f
icien
tly
an
d
e
f
f
ec
tiv
ely
in
r
ea
l
-
tim
e
ap
p
licatio
n
s
.
I
n
th
e
f
u
tu
r
e,
th
e
in
s
ig
h
ts
g
ain
ed
f
r
o
m
th
e
p
r
o
p
o
s
ed
m
eth
o
d
co
u
ld
c
o
n
tr
ib
u
te
to
th
e
d
e
v
elo
p
m
e
n
t
o
f
a
r
o
b
u
s
t
to
m
ato
d
etec
tio
n
s
y
s
tem
f
o
r
au
to
m
atic
m
o
n
ito
r
i
n
g
o
f
to
m
ato
f
ield
s
b
y
r
o
b
o
ts
,
ca
p
ab
le
o
f
tr
ac
k
in
g
r
ip
en
ess
an
d
f
r
u
it c
o
u
n
t u
n
d
er
v
ar
y
in
g
co
n
d
itio
n
s
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esear
ch
was
f
u
n
d
ed
b
y
t
he
2
0
2
4
r
esear
ch
g
r
a
n
t
s
f
r
o
m
th
e
Dir
ec
t
o
r
ate
o
f
R
esear
ch
,
T
ec
h
n
o
lo
g
y
,
a
n
d
C
o
m
m
u
n
ity
Ser
v
ice
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT
)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Su
lf
ay
an
ti
Fah
ar
u
d
d
in
Sit
u
ju
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
W
awa
n
Firg
iawa
n
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Hir
o
n
o
r
i T
a
k
im
o
to
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
N
T
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
a
v
ailab
l
e
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
au
t
h
o
r
,
[
SFS
]
,
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
T.
Z
e
n
g
,
S
.
Li
,
Q
.
S
o
n
g
,
F
.
Z
h
o
n
g
,
a
n
d
X
.
W
e
i
,
“
Li
g
h
t
w
e
i
g
h
t
t
o
m
a
t
o
r
e
a
l
-
t
i
me
d
e
t
e
c
t
i
o
n
me
t
h
o
d
b
a
s
e
d
o
n
i
m
p
r
o
v
e
d
Y
O
LO
a
n
d
mo
b
i
l
e
d
e
p
l
o
y
me
n
t
,
”
C
o
m
p
u
t
e
rs
a
n
d
El
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
.
2
0
5
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
a
g
.
2
0
2
3
.
1
0
7
6
2
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
1
5
,
No
.
2
,
J
u
n
e
2
0
2
6
:
4
5
1
-
461
460
[
2
]
I
.
R
a
f
a
n
i
a
n
d
F
.
B
.
M
.
D
a
b
u
k
k
e
,
“
T
h
e
p
e
r
f
o
r
ma
n
c
e
a
n
d
d
e
v
e
l
o
p
me
n
t
o
f
I
n
d
o
n
e
si
a
n
t
o
ma
t
o
e
s,
”
a
p
.
f
f
t
c
.
o
r
g
.
t
w
.
2
0
2
4
.
A
c
c
e
sse
d
:
O
c
t
.
1
5
,
2
0
2
4
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
a
p
.
f
f
t
c
.
o
r
g
.
t
w
/
a
r
t
i
c
l
e
/
3
5
2
3
.
[
3
]
G
.
M
.
Y
o
l
a
n
d
a
,
D
.
H
.
D
a
r
w
a
n
t
o
,
a
n
d
M
.
K
.
A
r
d
h
i
,
“
C
o
n
su
m
e
r
s’
a
t
t
i
t
u
d
e
a
n
d
p
r
e
f
e
r
e
n
c
e
t
o
w
a
r
d
f
r
e
sh
t
o
ma
t
o
e
s
i
n
S
p
e
c
i
a
l
R
e
g
i
o
n
o
f
Y
o
g
y
a
k
a
r
t
a
,
I
n
d
o
n
e
s
i
a
,
”
Ag
r
a
r
i
s
,
v
o
l
.
8
,
n
o
.
2
,
p
p
.
1
2
3
–
1
3
8
,
O
c
t
.
2
0
2
2
,
d
o
i
:
1
0
.
1
8
1
9
6
/
a
g
r
a
r
i
s.
v
8
i
2
.
1
2
1
5
0
.
[
4
]
P
.
L
i
,
J.
Z
h
e
n
g
,
P
.
Li
,
H
.
L
o
n
g
,
M
.
Li
,
a
n
d
L.
G
a
o
,
“
T
o
m
a
t
o
ma
t
u
r
i
t
y
d
e
t
e
c
t
i
o
n
a
n
d
c
o
u
n
t
i
n
g
m
o
d
e
l
b
a
se
d
o
n
M
H
S
A
-
Y
O
LO
v
8
,
”
S
e
n
so
rs
,
v
o
l
.
2
3
,
n
o
.
1
5
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
3
1
5
6
7
0
1
.
[
5
]
S
.
R
u
p
a
r
e
l
i
a
,
M
.
Je
t
h
v
a
,
a
n
d
R
.
G
a
j
j
a
r
,
“
R
e
a
l
-
t
i
me
t
o
m
a
t
o
d
e
t
e
c
t
i
o
n
,
c
l
a
ssi
f
i
c
a
t
i
o
n
,
a
n
d
c
o
u
n
t
i
n
g
s
y
s
t
e
m
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
a
n
d
e
mb
e
d
d
e
d
sy
s
t
e
m
s,”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
I
n
t
e
r
n
a
t
i
o
n
a
l
e
-
C
o
n
f
e
re
n
c
e
o
n
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
s
a
n
d
S
i
g
n
a
l
P
ro
c
e
ssi
n
g
,
2
0
2
2
,
p
p
.
5
1
1
–
522
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
16
-
2
1
2
3
-
9
_
3
9
.
[
6
]
V
.
P
r
i
y
a
n
k
a
,
P
.
S
a
n
d
h
y
a
,
a
n
d
V
.
V
a
n
i
,
“
D
e
e
p
l
e
a
r
n
i
n
g
b
a
se
d
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
a
n
d
c
o
u
n
t
i
n
g
i
n
t
o
ma
t
o
f
i
e
l
d
,
”
i
n
AI
P
C
o
n
f
e
re
n
c
e
Pro
c
e
e
d
i
n
g
s
,
2
0
2
4
,
v
o
l
.
2
8
0
2
,
n
o
.
1
,
d
o
i
:
1
0
.
1
0
6
3
/
5
.
0
1
8
2
3
5
8
.
[
7
]
J.
R
o
n
g
,
H
.
Zh
o
u
,
F
.
Z
h
a
n
g
,
T
.
Y
u
a
n
,
a
n
d
P
.
W
a
n
g
,
“
T
o
ma
t
o
c
l
u
s
t
e
r
d
e
t
e
c
t
i
o
n
a
n
d
c
o
u
n
t
i
n
g
u
s
i
n
g
i
m
p
r
o
v
e
d
Y
O
LO
v
5
b
a
se
d
o
n
R
G
B
-
D
f
u
s
i
o
n
,
”
C
o
m
p
u
t
e
rs
a
n
d
El
e
c
t
ro
n
i
c
s
i
n
A
g
r
i
c
u
l
t
u
r
e
,
v
o
l
.
2
0
7
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
a
g
.
2
0
2
3
.
1
0
7
7
4
1
.
[
8
]
M
.
A
f
o
n
s
o
e
t
a
l
.
,
“
T
o
m
a
t
o
f
r
u
i
t
d
e
t
e
c
t
i
o
n
a
n
d
c
o
u
n
t
i
n
g
i
n
g
r
e
e
n
h
o
u
s
e
s
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
,
”
Fro
n
t
i
e
rs
i
n
P
l
a
n
t
S
c
i
e
n
c
e
,
v
o
l
.
1
1
,
p
p
.
1
–
1
2
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
l
s.
2
0
2
0
.
5
7
1
2
9
9
.
[
9
]
I
.
T.
C
h
e
n
a
n
d
H
.
Y
.
L
i
n
,
“
D
e
t
e
c
t
i
o
n
,
c
o
u
n
t
i
n
g
a
n
d
m
a
t
u
r
i
t
y
a
ss
e
ssm
e
n
t
o
f
c
h
e
r
r
y
t
o
ma
t
o
e
s
u
si
n
g
m
u
l
t
i
-
s
p
e
c
t
r
a
l
i
ma
g
e
s
a
n
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
,
”
i
n
VI
S
I
G
RAPP
2
0
2
0
-
Pr
o
c
e
e
d
i
n
g
s o
f
t
h
e
1
5
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
i
n
t
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r V
i
s
i
o
n
,
I
m
a
g
i
n
g
a
n
d
C
o
m
p
u
t
e
r Gr
a
p
h
i
c
s T
h
e
o
ry
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
2
0
2
0
,
v
o
l
.
5
,
p
p
.
7
5
9
–
7
6
6
,
d
o
i
:
1
0
.
5
2
2
0
/
0
0
0
8
8
7
4
9
0
7
5
9
0
7
6
6
.
[
1
0
]
Y
.
G
e
e
t
a
l
.
,
“
Tr
a
c
k
i
n
g
a
n
d
c
o
u
n
t
i
n
g
o
f
t
o
ma
t
o
a
t
d
i
f
f
e
r
e
n
t
g
r
o
w
t
h
p
e
r
i
o
d
u
s
i
n
g
a
n
i
m
p
r
o
v
i
n
g
Y
O
LO
-
d
e
e
p
so
r
t
n
e
t
w
o
r
k
f
o
r
i
n
s
p
e
c
t
i
o
n
r
o
b
o
t
,
”
M
a
c
h
i
n
e
s
,
v
o
l
.
1
0
,
n
o
.
6
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
m
a
c
h
i
n
e
s
1
0
0
6
0
4
8
9
.
[
1
1
]
S
.
H
a
g
g
a
g
,
M
.
V
e
r
e
s,
C
.
T
a
r
r
y
,
a
n
d
M
.
M
o
u
ss
a
,
“
O
b
j
e
c
t
d
e
t
e
c
t
i
o
n
i
n
t
o
mat
o
g
r
e
e
n
h
o
u
ses
:
a
st
u
d
y
o
n
m
o
d
e
l
g
e
n
e
r
a
l
i
z
a
t
i
o
n
,
”
Ag
ri
c
u
l
t
u
r
e
,
v
o
l
.
1
4
,
n
o
.
2
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
a
g
r
i
c
u
l
t
u
r
e
1
4
0
2
0
1
7
3
.
[
1
2
]
M
.
Y
a
q
o
o
b
,
S
.
S
h
a
r
ma
,
a
n
d
P
.
A
g
g
a
r
w
a
l
,
“
I
mag
i
n
g
t
e
c
h
n
i
q
u
e
s
i
n
a
g
r
o
-
i
n
d
u
st
r
y
a
n
d
t
h
e
i
r
a
p
p
l
i
c
a
t
i
o
n
s,
a
r
e
v
i
e
w
,
”
J
o
u
rn
a
l
o
f
F
o
o
d
Me
a
su
r
e
m
e
n
t
a
n
d
C
h
a
ra
c
t
e
ri
z
a
t
i
o
n
,
v
o
l
.
1
5
,
n
o
.
3
,
p
p
.
2
3
2
9
–
2
3
4
3
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
6
9
4
-
0
2
1
-
0
0
8
0
9
-
w.
[
1
3
]
W
.
F
i
r
g
i
a
w
a
n
,
S
u
l
f
a
y
a
n
t
i
,
N
u
r
h
a
l
i
s
a
,
N
.
I
n
a
y
a
h
,
N
.
I
r
i
a
n
s
y
a
h
,
a
n
d
M
a
h
m
u
d
d
i
n
,
“
I
mp
r
o
v
e
d
T
o
m
a
t
o
c
l
a
ssi
f
i
c
a
t
i
o
n
i
n
i
n
d
u
st
r
i
a
l
e
n
v
i
r
o
n
m
e
n
t
u
si
n
g
Y
O
LO
v
8
a
n
d
d
a
t
a
a
u
g
me
n
t
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
2
0
2
4
I
EE
E
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s
a
n
d
I
n
t
e
l
l
i
g
e
n
c
e
S
y
st
e
m
s,
I
o
T
a
I
S
2
0
2
4
,
2
0
2
4
,
p
p
.
2
3
1
–
236
,
d
o
i
:
1
0
.
1
1
0
9
/
I
o
Ta
I
S
6
4
0
1
4
.
2
0
2
4
.
1
0
7
9
9
4
2
4
.
[
1
4
]
R
.
S
a
p
k
o
t
a
,
D
.
A
h
me
d
,
a
n
d
M
.
K
a
r
k
e
e
,
“
C
o
m
p
a
r
i
n
g
Y
O
LO
v
8
a
n
d
m
a
s
k
R
-
C
N
N
f
o
r
i
n
s
t
a
n
c
e
s
e
g
m
e
n
t
a
t
i
o
n
i
n
c
o
m
p
l
e
x
o
r
c
h
a
r
d
e
n
v
i
r
o
n
m
e
n
t
s,
”
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
i
n
Ag
r
i
c
u
l
t
u
re
,
v
o
l
.
1
3
,
p
p
.
8
4
–
9
9
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
i
i
a
.
2
0
2
4
.
0
7
.
0
0
1
.
[
1
5
]
P
.
Li
u
,
Y
.
Z
h
a
n
g
,
G
.
G
u
o
,
a
n
d
J.
D
i
n
g
,
“
En
h
a
n
c
e
d
d
e
t
e
c
t
i
o
n
a
n
d
r
e
c
o
g
n
i
t
i
o
n
o
f
r
o
a
d
o
b
j
e
c
t
s
i
n
i
n
f
r
a
r
e
d
i
m
a
g
i
n
g
u
si
n
g
m
u
l
t
i
-
s
c
a
l
e
sel
f
-
a
t
t
e
n
t
i
o
n
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
4
,
n
o
.
1
6
,
p
p
.
1
–
2
2
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
4
1
6
5
4
0
4
.
[
1
6
]
M
.
P
a
r
h
i
z
k
a
r
,
G
.
K
a
r
a
m
a
l
i
,
a
n
d
B
.
A
.
R
a
v
a
n
,
“
O
b
j
e
c
t
t
r
a
c
k
i
n
g
i
n
i
n
f
r
a
r
e
d
i
ma
g
e
s
u
s
i
n
g
a
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
a
n
d
a
t
a
r
g
e
t
-
at
t
e
n
t
i
o
n
m
e
c
h
a
n
i
sm
,
”
C
o
m
p
l
e
x
a
n
d
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
s
,
v
o
l
.
9
,
n
o
.
2
,
p
p
.
1
4
9
5
–
1
5
0
6
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s4
0
7
4
7
-
0
2
2
-
0
0
8
7
2
-
w.
[
1
7
]
F
.
W
u
,
G
.
Z
h
o
u
,
J.
H
e
,
H
.
Li
,
Y
.
L
i
u
,
a
n
d
G
.
Y
a
n
g
,
“
Ef
f
i
c
i
e
n
t
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
g
r
o
u
n
d
o
b
j
e
c
t
s
f
r
o
m
t
h
e
r
m
a
l
i
n
f
r
a
r
e
d
r
e
m
o
t
e
s
e
n
s
i
n
g
i
ma
g
e
b
a
se
d
o
n
d
e
e
p
l
e
a
r
n
i
n
g
,
”
i
n
P
a
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
a
n
d
C
o
m
p
u
t
e
r
V
i
si
o
n
(
PR
C
V
2
0
2
1
)
,
2
0
2
1
,
p
p
.
1
6
5
–
175
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
0
-
8
8
0
1
3
-
2
_
1
4
.
[
1
8
]
Y
.
S
u
n
,
Y
.
M
e
n
g
,
Q
.
W
a
n
g
,
M
.
T
a
n
g
,
T.
S
h
e
n
,
a
n
d
Q
.
W
a
n
g
,
“
V
i
s
i
b
l
e
a
n
d
i
n
f
r
a
r
e
d
i
m
a
g
e
f
u
si
o
n
f
o
r
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
:
a
s
u
r
v
e
y
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
m
a
g
e
,
V
i
si
o
n
a
n
d
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
s
2
0
2
3
(
I
C
I
VI
S
2
0
2
3
)
,
2
0
2
4
,
p
p
.
2
3
6
–
248
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
97
-
0
8
5
5
-
0
_
2
4
.
[
1
9
]
M
.
D
.
T
u
,
K
.
T
.
L
e
,
a
n
d
M
.
D
.
P
h
u
n
g
,
“
O
b
j
e
c
t
d
e
t
e
c
t
i
o
n
i
n
t
h
e
r
m
a
l
i
m
a
g
e
s
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
u
n
m
a
n
n
e
d
a
e
r
i
a
l
v
e
h
i
c
l
e
s
,
”
i
n
2
0
2
4
I
E
E
E
/
S
I
C
E
I
n
t
e
r
n
a
t
i
o
n
a
l
S
y
m
p
o
s
i
u
m
o
n
S
y
s
t
e
m
I
n
t
e
g
r
a
t
i
o
n
,
S
I
I
2
0
2
4
,
2
0
2
4
,
p
p
.
6
8
7
–
6
9
2
,
d
o
i
:
1
0
.
1
1
0
9
/
S
I
I
5
8
9
5
7
.
2
0
2
4
.
1
0
4
1
7
6
1
1
.
[
2
0
]
P
.
C
h
r
i
st
i
a
n
se
n
,
K
.
A
.
S
t
e
e
n
,
R
.
N
.
J
ø
r
g
e
n
s
e
n
,
a
n
d
H
.
K
a
r
s
t
o
f
t
,
“
A
u
t
o
ma
t
e
d
d
e
t
e
c
t
i
o
n
a
n
d
r
e
c
o
g
n
i
t
i
o
n
o
f
w
i
l
d
l
i
f
e
u
s
i
n
g
t
h
e
r
m
a
l
c
a
mer
a
s,”
S
e
n
s
o
rs
,
v
o
l
.
1
4
,
n
o
.
8
,
p
p
.
1
3
7
7
8
–
1
3
7
9
3
,
2
0
1
4
,
d
o
i
:
1
0
.
3
3
9
0
/
s1
4
0
8
1
3
7
7
8
.
[
2
1
]
U
.
M
i
t
t
a
l
,
S
.
S
r
i
v
a
s
t
a
v
a
,
a
n
d
P
.
C
h
a
w
l
a
,
“
O
b
j
e
c
t
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
f
r
o
m
t
h
e
r
ma
l
i
ma
g
e
s
u
s
i
n
g
r
e
g
i
o
n
b
a
s
e
d
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
,
”
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
5
,
n
o
.
7
,
p
p
.
9
6
1
–
9
7
1
,
2
0
1
9
,
d
o
i
:
1
0
.
3
8
4
4
/
j
c
ss
p
.
2
0
1
9
.
9
6
1
.
9
7
1
.
[
2
2
]
H
.
Z
h
o
u
,
M
.
S
u
n
,
X
.
R
e
n
,
a
n
d
X
.
W
a
n
g
,
“
V
i
si
b
l
e
-
t
h
e
r
ma
l
i
ma
g
e
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
v
i
a
t
h
e
c
o
m
b
i
n
a
t
i
o
n
o
f
i
l
l
u
m
i
n
a
t
i
o
n
c
o
n
d
i
t
i
o
n
s
a
n
d
t
e
m
p
e
r
a
t
u
r
e
i
n
f
o
r
mat
i
o
n
,
”
Re
m
o
t
e
S
e
n
si
n
g
,
v
o
l
.
1
3
,
n
o
.
1
8
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s1
3
1
8
3
6
5
6
.
[
2
3
]
S
.
R
a
z
a
k
a
r
i
v
o
n
y
a
n
d
F
.
Ju
r
i
e
,
“
V
e
h
i
c
l
e
d
e
t
e
c
t
i
o
n
i
n
a
e
r
i
a
l
i
ma
g
e
r
y
:
a
s
mal
l
t
a
r
g
e
t
d
e
t
e
c
t
i
o
n
b
e
n
c
h
m
a
r
k
,
”
J
o
u
r
n
a
l
o
f
V
i
s
u
a
l
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
I
m
a
g
e
Re
p
res
e
n
t
a
t
i
o
n
,
v
o
l
.
3
4
,
p
p
.
1
8
7
–
2
0
3
,
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
v
c
i
r
.
2
0
1
5
.
1
1
.
0
0
2
.
[
2
4
]
Y
.
W
a
n
g
,
Q
.
R
o
n
g
,
a
n
d
C
.
H
u
,
“
R
i
p
e
t
o
ma
t
o
d
e
t
e
c
t
i
o
n
a
l
g
o
r
i
t
h
m
b
a
s
e
d
o
n
i
m
p
r
o
v
e
d
Y
O
LO
v
9
,
”
Pl
a
n
t
s
,
v
o
l
.
1
3
,
n
o
.
2
2
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
p
l
a
n
t
s
1
3
2
2
3
2
5
3
.
[
2
5
]
R
.
S
.
K
a
l
e
a
n
d
S
.
S
h
i
t
o
l
e
,
“
N
o
n
-
d
e
st
r
u
c
t
i
v
e
f
r
u
i
t
q
u
a
l
i
t
y
a
ss
e
ssm
e
n
t
:
a
r
e
v
i
e
w
o
n
e
merg
i
n
g
t
r
e
n
d
s
i
n
t
h
e
r
mal
i
ma
g
i
n
g
t
e
c
h
n
o
l
o
g
y
,
”
J
o
u
rn
a
l
o
f
C
o
m
p
u
t
a
t
i
o
n
a
l
An
a
l
y
si
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
3
,
n
o
.
8
.
p
p
.
3
2
6
–
3
4
2
,
2
0
2
4
.
[
2
6
]
M
.
A
w
a
i
s
e
t
a
l
.
,
“
U
A
V
-
b
a
s
e
d
r
e
mo
t
e
se
n
si
n
g
i
n
p
l
a
n
t
st
r
e
ss
i
m
a
g
i
n
e
u
s
i
n
g
h
i
g
h
-
r
e
s
o
l
u
t
i
o
n
t
h
e
r
ma
l
s
e
n
s
o
r
f
o
r
d
i
g
i
t
a
l
a
g
r
i
c
u
l
t
u
r
e
p
r
a
c
t
i
c
e
s
:
a
m
e
t
a
-
r
e
v
i
e
w
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
n
v
i
ro
n
m
e
n
t
a
l
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
2
0
,
n
o
.
1
,
p
p
.
1
1
3
5
–
1
1
5
2
,
Jan
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
3
7
6
2
-
021
-
0
3
8
0
1
-
5.
[
2
7
]
H
.
S
.
N
d
l
o
v
u
,
J.
O
d
i
n
d
i
,
M
.
S
i
b
a
n
d
a
,
a
n
d
O
.
M
u
t
a
n
g
a
,
“
A
s
y
s
t
e
m
a
t
i
c
r
e
v
i
e
w
o
n
t
h
e
a
p
p
l
i
c
a
t
i
o
n
o
f
U
A
V
-
b
a
se
d
t
h
e
r
m
a
l
r
e
mo
t
e
sen
s
i
n
g
f
o
r
a
s
sess
i
n
g
a
n
d
mo
n
i
t
o
r
i
n
g
c
r
o
p
w
a
t
e
r
s
t
a
t
u
s
i
n
c
r
o
p
f
a
r
mi
n
g
sy
s
t
e
ms
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Re
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
4
5
,
n
o
.
1
5
,
p
p
.
4
9
2
3
–
4
9
6
0
,
A
u
g
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
8
0
/
0
1
4
3
1
1
6
1
.
2
0
2
4
.
2
3
6
8
9
3
3
.
[
2
8
]
R
.
A
.
P
.
H
e
r
n
a
n
d
a
,
H
.
L
e
e
,
J
.
I.
C
h
o
,
G
.
K
i
m
,
B
.
K
.
C
h
o
,
a
n
d
M
.
S
.
K
i
m
,
“
C
u
r
r
e
n
t
t
r
e
n
d
s
i
n
t
h
e
u
s
e
o
f
t
h
e
r
m
a
l
i
m
a
g
e
r
y
i
n
a
s
s
e
s
s
i
n
g
p
l
a
n
t
s
t
r
e
s
s
e
s
:
a
r
e
v
i
e
w
,
”
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
.
2
2
4
,
S
e
p
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
a
g
.
2
0
2
4
.
1
0
9
2
2
7
.
[
2
9
]
O
.
S
h
a
l
a
s
h
e
t
a
l
.
,
“
F
u
si
o
n
o
f
r
o
b
o
t
i
c
s,
A
I
,
a
n
d
t
h
e
r
m
a
l
i
ma
g
i
n
g
t
e
c
h
n
o
l
o
g
i
e
s
f
o
r
i
n
t
e
l
l
i
g
e
n
t
p
r
e
c
i
si
o
n
a
g
r
i
c
u
l
t
u
r
e
s
y
s
t
e
ms,
”
S
e
n
so
rs
,
v
o
l
.
2
5
,
n
o
.
2
2
,
N
o
v
.
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
5
2
2
6
8
4
4
.
[
3
0
]
Z.
Z
h
o
u
,
Y
.
M
a
j
e
e
d
,
G
.
D
.
N
a
r
a
n
j
o
,
a
n
d
E.
M
.
T
.
G
a
m
b
a
c
o
r
t
a
,
“
A
ss
e
ssm
e
n
t
f
o
r
c
r
o
p
w
a
t
e
r
s
t
r
e
ss w
i
t
h
i
n
f
r
a
r
e
d
t
h
e
r
mal
i
ma
g
e
r
y
i
n
p
r
e
c
i
si
o
n
a
g
r
i
c
u
l
t
u
r
e
:
a
r
e
v
i
e
w
a
n
d
f
u
t
u
r
e
p
r
o
sp
e
c
t
s
f
o
r
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
l
i
c
a
t
i
o
n
s,
”
C
o
m
p
u
t
e
rs
a
n
d
El
e
c
t
ro
n
i
c
s
i
n
A
g
ri
c
u
l
t
u
re
,
v
o
l
.
1
8
2
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
a
g
.
2
0
2
1
.
1
0
6
0
1
9
.
[
3
1
]
P
.
P
a
t
h
m
a
n
a
b
a
n
,
B
.
K
.
G
n
a
n
a
v
e
l
,
S
.
S
.
A
n
a
n
d
a
n
,
a
n
d
S
.
S
a
t
h
i
y
a
m
u
r
t
h
y
,
“
A
d
v
a
n
c
i
n
g
p
o
s
t
-
h
a
r
v
e
s
t
f
r
u
i
t
h
a
n
d
l
i
n
g
t
h
r
o
u
g
h
A
I
-
b
a
s
e
d
t
h
e
r
m
a
l
i
m
a
g
i
n
g
:
a
p
p
l
i
c
a
t
i
o
n
s
,
c
h
a
l
l
e
n
g
e
s
,
a
n
d
f
u
t
u
r
e
t
r
e
n
d
s
,
”
D
i
s
c
o
v
e
r
F
o
o
d
,
v
o
l
.
3
,
n
o
.
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
4
1
8
7
-
0
2
3
-
0
0
0
6
8
-
2.
[
3
2
]
I
.
I
smai
l
,
D
.
B
u
d
i
m
a
n
,
a
n
d
Z.
R
.
A
i
d
h
a
,
“
Th
e
s
mart
a
g
r
i
c
u
l
t
u
r
e
b
a
se
d
o
n
r
e
c
o
n
st
r
u
c
t
e
d
t
h
e
r
ma
l
i
m
a
g
e
,
”
J
o
u
rn
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
6
,
n
o
.
0
1
,
p
p
.
8
–
1
3
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
2
5
0
7
7
/
j
i
t
c
e
.
6
.
0
1
.
8
-
1
3
.
2
0
2
2
.
[
3
3
]
M
.
F
.
A
r
a
g
ã
o
e
t
a
l
.
,
“
Ev
a
l
u
a
t
i
o
n
o
f
c
r
o
p
w
a
t
e
r
st
a
t
u
s o
f
m
e
l
o
n
p
l
a
n
t
s
i
n
t
r
o
p
i
c
a
l
sem
i
-
a
r
i
d
c
l
i
m
a
t
e
u
s
i
n
g
t
h
e
r
ma
l
i
ma
g
i
n
g
,
”
Re
v
i
st
a
Bra
s
i
l
e
i
r
a
d
e
E
n
g
e
n
h
a
ri
a
A
g
ri
c
o
l
a
e
Am
b
i
e
n
t
a
l
,
v
o
l
.
2
7
,
n
o
.
6
,
p
p
.
4
4
7
–
4
5
6
,
J
u
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
5
9
0
/
1
8
0
7
-
1
9
2
9
/
A
G
R
I
A
M
B
I
.
V
2
7
N
6
P
4
4
7
-
4
5
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.