I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
15
,
No
.
1
,
Feb
r
u
ar
y
20
25
,
p
p
.
883
~
893
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
1
.
pp
8
8
3
-
8
9
3
883
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Desig
n of a
ro
a
d
ma
rking
vio
la
tion detec
tion sy
stem
a
t
ra
ilwa
y
lev
el cross
ing
s
H
elf
y
Su
s
ila
wa
t
i
1
,
Sifa
Nurpa
dil
la
h
1
,
Wa
hju
Sedio
no
2
,
A
g
un
g
I
hwa
n Nur
din
1
1
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
E
n
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
a
s
G
a
r
u
t
,
G
a
r
u
t
,
I
n
d
o
n
e
si
a
2
D
e
p
a
r
t
me
n
t
o
f
M
e
c
h
a
t
r
o
n
i
c
s
E
n
g
i
n
e
e
r
i
n
g
,
I
n
t
e
r
n
a
t
i
o
n
a
l
I
sl
a
mi
c
U
n
i
v
e
r
si
t
y
M
a
l
a
y
si
a
,
K
u
a
l
a
Lu
m
p
u
r
,
M
a
l
a
y
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
r
5
,
2
0
2
4
R
ev
is
ed
Au
g
1
3
,
2
0
2
4
Acc
ep
ted
Au
g
2
0
,
2
0
2
4
Wh
e
n
a
train
p
a
ss
e
d
th
ro
u
g
h
a
ra
il
wa
y
-
lev
e
l
c
ro
ss
in
g
,
a
c
o
m
m
o
n
p
h
e
n
o
m
e
n
o
n
wa
s
t
h
a
t
m
a
n
y
v
e
h
icle
s
a
tt
e
m
p
ted
t
o
o
v
e
rtak
e
o
th
e
rs
b
y
c
ro
ss
in
g
i
n
to
lan
e
s
d
e
sig
n
a
ted
fo
r
o
n
c
o
m
i
n
g
traffic,
re
su
lt
in
g
i
n
b
o
th
r
o
a
d
s
b
e
c
o
m
in
g
c
o
n
g
e
ste
d
wit
h
m
o
to
r
ize
d
v
e
h
icle
s.
At
th
a
t
ti
m
e
,
n
o
sy
ste
m
wa
s
in
p
lac
e
to
e
n
fo
rc
e
p
e
n
a
lt
ies
f
o
r
v
io
latin
g
r
o
a
d
m
a
rk
in
g
s
a
t
lev
e
l
c
ro
ss
in
g
s.
Th
e
re
fo
re
,
a
sy
ste
m
c
a
p
a
b
le
o
f
d
e
tec
ti
n
g
su
c
h
v
io
lati
o
n
s
wh
e
n
t
ra
in
s
p
a
ss
th
ro
u
g
h
wa
s
n
e
e
d
e
d
.
T
h
e
d
e
sig
n
e
d
sy
ste
m
u
ti
li
z
e
d
a
Ra
sp
b
e
rr
y
P
i
4
,
a
we
b
c
a
m
,
a
n
d
a
n
u
lt
ra
so
n
ic
se
n
s
o
r.
T
h
e
sin
g
le
sh
o
t
d
e
tec
to
r
(
S
S
D)
m
e
th
o
d
wa
s
e
m
p
lo
y
e
d
fo
r
v
e
h
icle
c
las
si
fica
ti
o
n
.
T
h
e
o
p
t
ica
l
c
h
a
ra
c
ter
r
e
c
o
g
n
it
i
o
n
(OCR)
m
e
th
o
d
wa
s
u
se
d
f
o
r
c
h
a
ra
c
ter
re
c
o
g
n
it
io
n
o
n
li
c
e
n
se
p
l
a
tes
.
Th
e
re
se
a
rc
h
in
v
o
l
v
e
d
o
b
jec
t
d
e
tec
ti
o
n
a
t
lev
e
l
c
r
o
ss
in
g
s
u
sin
g
v
a
ri
e
d
o
b
jec
ts
(c
a
rs
a
n
d
m
o
t
o
rc
y
c
les
)
wit
h
li
c
e
n
se
p
late
s
c
a
teg
o
rize
d
in
to
two
ty
p
e
s:
wh
it
e
b
a
c
k
g
ro
u
n
d
p
late
s
wit
h
b
lac
k
n
u
m
b
e
rs
a
n
d
b
lac
k
b
a
c
k
g
r
o
u
n
d
p
late
s
with
wh
it
e
n
u
m
b
e
rs.
Ba
se
d
o
n
t
h
e
re
se
a
rc
h
re
su
lt
s,
tu
rn
in
g
o
n
th
e
we
b
c
a
m
wh
e
n
th
e
b
a
r
o
p
e
n
e
d
a
n
d
c
l
o
se
d
u
si
n
g
a
n
u
lt
ra
so
n
ic
se
n
so
r
g
o
t
a
n
a
v
e
ra
g
e
e
rro
r
o
f
0
.
5
7
3
%
a
n
d
0
.
5
8
2
%
.
Th
e
sy
ste
m
c
o
u
l
d
d
isti
n
g
u
is
h
o
b
jec
ts
wit
h
a
n
a
v
e
ra
g
e
re
c
o
g
n
it
i
o
n
d
e
lay
o
f
0
.
5
5
4
se
c
o
n
d
s
a
n
d
0
.
7
0
2
se
c
o
n
d
s
fo
r
c
a
r
a
n
d
m
o
to
rb
i
k
e
o
b
jec
ts.
Re
g
a
r
d
in
g
n
u
m
b
e
r
p
lat
e
d
e
tec
ti
o
n
,
t
h
e
su
c
c
e
ss
ra
te
o
f
c
h
a
ra
c
ter
re
c
o
g
n
it
i
o
n
sto
o
d
a
t
6
4
.
4
5
%
.
K
ey
w
o
r
d
s
:
Op
tical
ch
ar
ac
ter
r
ec
o
g
n
itio
n
R
ailway
lev
el
cr
o
s
s
in
g
R
asp
b
er
r
y
P
i
R
o
ad
m
ar
k
in
g
s
Sin
g
le
s
h
o
t d
etec
to
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
:
Helf
y
Su
s
ilawati
Dep
ar
tm
en
t o
f
E
lectr
ical
E
n
g
i
n
ee
r
in
g
,
Facu
lty
o
f
E
n
g
in
ee
r
in
g
,
Un
iv
er
s
itas
Gar
u
t
1
3
T
er
u
s
an
R
o
ad
,
T
ar
o
g
o
n
g
K
aler
Su
b
d
is
tr
ic,
Gar
u
t Reg
en
c
y
,
W
est J
av
a,
I
n
d
o
n
esia
E
m
ail: h
elf
y
.
s
u
s
ilawati@
u
n
ig
a.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
R
ailway
tr
an
s
p
o
r
tatio
n
is
a
co
m
m
o
n
ly
u
tili
ze
d
m
o
d
e
o
f
tr
a
n
s
p
o
r
t
in
n
ea
r
l
y
ev
er
y
co
u
n
tr
y
,
in
clu
d
in
g
I
n
d
o
n
esia.
Du
r
in
g
o
p
er
atio
n
s
,
it is
in
ev
itab
le
f
o
r
r
ailway
tr
ac
k
s
to
in
ter
s
ec
t w
i
th
lan
d
tr
an
s
p
o
r
t m
o
d
es,
s
u
ch
as
r
o
ad
s
.
T
h
is
in
ter
s
ec
tio
n
b
etwe
en
a
r
ailway
lin
e
an
d
a
p
u
b
lic
r
o
ad
is
r
ef
er
r
ed
t
o
as
a
r
ailway
cr
o
s
s
in
g
.
A
r
ailway
cr
o
s
s
in
g
is
th
e
p
o
i
n
t
wh
er
e
th
e
r
ailway
in
ter
s
ec
ts
with
th
e
h
ig
h
way
[
1
]
.
I
n
d
o
n
esia
is
o
n
e
o
f
t
h
e
co
u
n
tr
ies
g
r
ap
p
li
n
g
with
s
af
ety
is
s
u
es
at
r
ailway
cr
o
s
s
in
g
s
[
2
]
.
I
n
I
n
d
o
n
esia,
a
co
m
m
o
n
o
c
cu
r
r
en
ce
at
r
ailway
cr
o
s
s
in
g
s
wh
en
tr
ain
s
p
ass
is
th
e
m
o
v
em
e
n
t
o
f
v
eh
icles,
s
u
ch
as
ca
r
s
an
d
m
o
t
o
r
b
ik
es,
th
at
s
h
o
u
ld
b
e
u
s
in
g
o
n
ly
o
n
e
la
n
e.
Ho
wev
er
,
wh
e
n
th
e
tr
ain
p
ass
es,
m
an
y
v
eh
icles
cr
o
s
s
o
v
er
th
e
r
o
ad
m
ar
k
in
g
s
,
r
esu
ltin
g
in
b
o
th
lan
es
b
ec
o
m
in
g
f
u
lly
o
cc
u
p
ie
d
b
y
ca
r
s
an
d
m
o
to
r
b
ik
es.
T
h
is
s
i
tu
atio
n
o
cc
u
r
s
in
b
o
th
d
ir
ec
tio
n
s
o
f
th
e
r
o
ad
,
ca
u
s
in
g
v
e
h
icles
f
r
o
m
o
p
p
o
s
ite
d
ir
ec
tio
n
s
to
f
ac
e
ea
c
h
o
th
er
af
ter
th
e
tr
ain
h
as
p
ass
ed
.
T
h
is
in
ci
d
en
t
is
ex
tr
em
ely
h
az
ar
d
o
u
s
as
it
ca
n
lead
to
ac
cid
en
ts
[
3
]
.
T
h
e
m
ain
o
b
jectiv
e
p
o
in
t
o
f
th
is
wo
r
k
is
t
o
p
r
o
v
i
d
e
war
n
in
g
s
to
d
r
iv
er
s
wh
o
cr
o
s
s
r
o
ad
m
ar
k
i
n
g
b
o
u
n
d
a
r
ies
wh
en
tr
ain
s
p
ass
th
r
o
u
g
h
lev
el
cr
o
s
s
in
g
s
b
y
r
ec
o
r
d
in
g
licen
s
e
p
late
d
ata
in
a
d
ata
b
a
s
e.
T
h
is
d
ata
ca
n
th
en
b
e
u
s
ed
b
y
p
o
lice
as
g
r
o
u
n
d
s
f
o
r
is
s
u
in
g
f
in
es.
T
h
is
r
esear
ch
is
im
p
o
r
tan
t to
en
s
u
r
e
th
at
ca
r
an
d
m
o
to
r
cy
cle
d
r
iv
e
r
s
ad
h
er
e
to
r
eg
u
latio
n
s
at
r
ailway
cr
o
s
s
in
g
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
1
,
Feb
r
u
ar
y
20
25
:
8
8
3
-
893
884
R
esear
ch
h
as
b
ee
n
co
n
d
u
cted
to
p
r
ev
e
n
t
ac
cid
en
ts
at
r
ailwa
y
lev
el
cr
o
s
s
in
g
s
,
o
n
e
m
eth
o
d
o
f
wh
ich
in
v
o
lv
es
ca
lcu
latin
g
th
e
d
is
tan
ce
b
etwe
en
th
e
d
r
iv
er
an
d
th
e
lev
el
cr
o
s
s
in
g
u
s
in
g
ca
m
er
a
im
ag
es
s
to
r
ed
in
th
e
v
eh
icle
[
4
]
.
I
n
ad
d
itio
n
to
ac
cid
en
ts
,
th
is
will
al
s
o
ca
u
s
e
co
n
g
esti
o
n
[
5
]
.
T
h
er
e
a
r
e
n
u
m
er
o
u
s
s
tu
d
ies
o
n
m
o
d
if
icatio
n
s
to
lev
el
cr
o
s
s
in
g
s
aim
ed
at
r
e
d
u
cin
g
ac
cid
e
n
ts
,
in
clu
d
in
g
r
esear
ch
o
n
al
g
o
r
ith
m
s
f
o
r
tr
af
f
i
c
co
n
tr
o
l
at
th
ese
cr
o
s
s
in
g
s
[
6
]
.
An
o
th
er
r
esear
ch
r
ev
o
lv
es
ar
o
u
n
d
m
a
n
ag
in
g
tr
af
f
ic
lig
h
ts
at
r
ailway
-
lev
el
cr
o
s
s
in
g
s
th
r
o
u
g
h
th
e
ap
p
licat
io
n
o
f
c
o
m
p
u
te
r
v
is
io
n
[
7
]
.
A
d
d
itio
n
ally
,
o
th
er
s
tu
d
ies
in
v
e
s
tig
ate
o
b
s
tacle
s
at
r
ailway
-
lev
el
cr
o
s
s
in
g
s
,
d
e
m
o
n
s
tr
atin
g
th
at
t
h
e
d
e
v
elo
p
e
d
s
y
s
tem
ca
n
ef
f
ec
tiv
ely
d
ete
ct
o
b
jects
at
th
ese
cr
o
s
s
in
g
s
an
d
ca
n
b
e
im
p
lem
e
n
ted
in
r
ea
l
-
wo
r
ld
s
ce
n
ar
io
s
[
8
]
.
R
asp
b
er
r
y
Pi
is
u
tili
ze
d
as
a
m
icr
o
co
n
tr
o
ller
in
th
is
r
esear
ch
,
alo
n
g
with
d
ig
it
al
im
ag
e
p
r
o
ce
s
s
in
g
to
id
en
tif
y
o
b
jects
an
d
r
ea
d
t
h
e
n
u
m
b
e
r
p
lates
o
f
ca
r
s
o
r
m
o
to
r
b
ik
es
clo
s
est
to
th
e
d
o
o
r
s
to
p
.
Dig
ital
im
ag
e
p
r
o
ce
s
s
in
g
is
ex
ten
s
iv
ely
e
m
p
lo
y
e
d
i
n
v
ar
io
u
s
d
o
m
ai
n
s
,
in
clu
d
in
g
f
ir
e
-
d
etec
tio
n
a
p
p
li
ca
tio
n
s
[
9
]
,
r
ail
wea
r
d
etec
tio
n
[
1
0
]
,
f
o
r
au
to
n
o
m
o
u
s
v
e
h
ic
les
[
1
1
]
,
an
d
m
an
y
m
o
r
e.
T
h
is
r
esear
ch
d
if
f
er
s
f
r
o
m
p
r
e
v
io
u
s
s
tu
d
ies
b
ec
a
u
s
e
ea
r
lier
r
esear
ch
aim
e
d
to
im
p
r
o
v
e
r
ailway
s
y
s
tem
s
o
r
m
o
n
ito
r
tr
ain
co
n
d
itio
n
s
to
p
r
ev
en
t
ac
cid
e
n
ts
.
C
u
r
r
en
tly
,
th
e
s
y
s
tem
u
s
ed
to
war
n
th
o
s
e
wh
o
v
io
late
r
o
a
d
m
ar
k
in
g
s
at
r
ailway
cr
o
s
s
in
g
s
in
v
o
lv
es
d
ir
ec
t
an
n
o
u
n
ce
m
e
n
t
s
b
y
r
ailway
g
u
ar
d
s
.
Ho
wev
er
,
th
is
ap
p
r
o
ac
h
h
as
p
r
o
v
e
n
in
e
f
f
ec
tiv
e.
T
h
er
e
f
o
r
e,
a
s
y
s
tem
is
n
ee
d
ed
th
at
ca
n
p
r
o
v
id
e
war
n
in
g
s
an
d
d
eter
v
io
latio
n
s
th
r
o
u
g
h
th
e
is
s
u
an
ce
o
f
f
in
es.
Ho
wev
er
,
t
h
is
s
tu
d
y
f
o
cu
s
es
o
n
d
esig
n
in
g
a
s
y
s
tem
aim
e
d
at
p
en
alizin
g
v
e
h
icle
u
s
er
s
wh
o
v
io
late
r
o
ad
m
ar
k
in
g
s
b
y
r
ec
o
r
d
in
g
th
eir
licen
s
e
p
late
n
u
m
b
er
s
.
T
h
is
d
ata
ca
n
t
h
en
b
e
u
s
ed
b
y
p
o
lice
f
o
r
is
s
u
in
g
f
in
es.
2.
M
E
T
H
O
D
2
.
1
.
F
lo
wcha
rt
s
y
s
t
em
Fig
u
r
e
1
d
ep
icts
th
e
o
v
er
all
o
p
er
atio
n
o
f
th
e
s
y
s
tem
,
s
tar
tin
g
with
th
e
in
p
u
t
o
f
a
n
u
ltra
s
o
n
ic
s
en
s
o
r
to
d
eter
m
in
e
th
e
d
is
tan
ce
b
etwe
en
th
e
r
o
ad
s
u
r
f
ac
e
an
d
th
e
r
ailway
cr
o
s
s
in
g
g
ate
wh
en
th
e
g
ate
is
clo
s
in
g
.
T
h
e
u
ltra
s
o
n
ic
s
en
s
o
r
u
s
ed
f
o
r
d
is
t
an
ce
d
etec
tio
n
is
p
o
s
itio
n
ed
at
th
e
m
id
p
o
in
t
o
f
th
e
r
ailway
cr
o
s
s
in
g
g
ate.
I
f
th
e
d
is
tan
ce
v
alu
e
f
r
o
m
th
e
g
ate
to
th
e
r
o
a
d
s
u
r
f
ac
e
is
≥
1
1
0
c
m
an
d
≤
1
4
0
cm
,
th
e
s
en
s
o
r
s
en
d
s
a
s
ig
n
al
to
th
e
R
asp
b
er
r
y
Pi
to
ac
tiv
ate
th
e
web
ca
m
.
T
h
e
we
b
ca
m
ca
p
t
u
r
es
a
v
id
eo
an
d
i
d
en
tifie
s
th
e
d
etec
tio
n
ar
ea
ac
co
r
d
in
g
t
o
th
e
lin
es
o
n
th
e
o
p
p
o
s
ite
lan
e.
Af
ter
war
d
,
th
e
s
y
s
tem
p
er
f
o
r
m
s
v
e
h
icle
o
b
ject
d
etec
tio
n
u
s
in
g
th
e
s
in
g
le
s
h
o
t
d
etec
to
r
m
eth
o
d
to
class
if
y
o
b
jects.
I
n
th
is
s
t
u
d
y
,
o
b
jects
ar
e
class
if
ied
in
to
two
ca
teg
o
r
ies:
m
o
to
r
cy
cles
a
n
d
ca
r
s
.
I
f
th
e
s
y
s
tem
d
etec
ts
an
o
b
ject
ac
co
r
d
i
n
g
to
th
e
s
p
ec
if
ied
class
if
icatio
n
s
,
it
will
p
r
o
d
u
ce
a
war
n
in
g
s
o
u
n
d
o
u
t
p
u
t
th
r
o
u
g
h
a
wir
eless
B
lu
eto
o
th
s
p
ea
k
er
.
Su
b
s
eq
u
e
n
tly
,
af
te
r
1
5
s
ec
o
n
d
s
,
v
e
h
icle
p
lat
e
d
etec
tio
n
will
b
e
c
o
n
d
u
cted
u
s
in
g
th
e
Haa
r
ca
s
ca
d
e
class
if
i
er
m
eth
o
d
,
an
d
th
e
r
esu
ltin
g
d
ata
will
b
e
s
en
t
t
o
th
e
d
atab
ase.
T
h
is
r
esear
ch
u
tili
ze
s
R
asp
b
er
r
y
Pi
as
th
e
m
icr
o
p
r
o
ce
s
s
o
r
,
u
ltra
s
o
n
ic
s
en
s
o
r
s
to
d
etec
t
th
e
d
is
tan
ce
f
r
o
m
th
e
r
o
ad
to
th
e
lev
el
cr
o
s
s
in
g
g
ate,
a
web
ca
m
to
ca
p
tu
r
e
im
ag
es
o
f
v
eh
icles
at
th
e
lev
el
cr
o
s
s
in
g
,
an
d
a
b
u
zz
er
to
p
r
o
v
id
e
war
n
in
g
s
f
o
r
v
eh
icles
th
at
v
io
late.
R
a
s
p
b
er
r
y
Pi
is
al
s
o
em
p
lo
y
ed
f
o
r
v
e
h
icle
class
if
icat
io
n
an
d
f
o
r
id
e
n
tify
in
g
a
n
d
tr
an
s
latin
g
ch
ar
ac
ter
s
o
n
licen
s
e
p
lates
with
in
th
e
d
etec
tio
n
ar
ea
.
T
h
e
s
in
g
le
s
h
o
t
d
etec
to
r
(
SS
D)
m
eth
o
d
is
em
p
lo
y
ed
to
d
etec
t
an
d
class
if
y
v
e
h
icle
o
b
jects,
wh
ile
th
e
o
p
tical
ch
a
r
ac
ter
r
ec
o
g
n
itio
n
(
OC
R
)
m
eth
o
d
is
u
s
ed
to
tr
an
s
late
ch
ar
ac
ter
s
o
n
licen
s
e
p
lates.
A
ca
r
o
r
m
o
t
o
r
b
ik
e
in
p
r
o
x
im
ity
to
a
d
o
o
r
s
to
p
b
u
t n
o
t
with
in
it
s
d
esig
n
ated
la
n
e
in
d
icate
s
th
a
t
it
h
as
c
r
o
s
s
ed
th
e
r
o
a
d
m
ar
k
i
n
g
lim
it.
T
h
er
e
f
o
r
e,
ca
r
s
o
r
m
o
to
r
b
ik
es n
ea
r
th
e
d
o
o
r
s
to
p
will r
ec
eiv
e
a
war
n
in
g
t
h
r
o
u
g
h
a
b
u
zz
er
.
T
wo
m
i
n
u
tes af
ter
th
e
b
u
zz
er
is
ac
tiv
ated
,
th
e
ca
m
e
r
a
will
ca
p
tu
r
e
th
e
v
eh
icle'
s
licen
s
e
p
late
n
u
m
b
e
r
,
wh
ich
will
th
en
b
e
co
n
v
er
ted
in
to
alp
h
an
u
m
e
r
ic
ch
ar
ac
ter
s
.
Su
b
s
eq
u
en
tly
,
th
is
in
f
o
r
m
atio
n
will
b
e
tr
an
s
m
itted
to
a
d
esig
n
ated
web
s
ite
s
er
v
in
g
as
a
d
atab
ase
f
o
r
tr
a
f
f
ic
v
i
o
lato
r
s
wh
o
h
a
v
e
cr
o
s
s
ed
r
o
ad
m
a
r
k
in
g
s
.
T
h
is
s
tu
d
y
o
n
l
y
d
etec
t
s
an
d
class
if
ies
two
o
b
jects,
n
am
ely
ca
r
s
an
d
m
o
to
r
cy
cles.
Ad
d
itio
n
ally
,
th
e
r
esear
ch
o
n
ly
r
ec
o
r
d
s
licen
s
e
p
lates
th
at
v
io
late
r
o
ad
m
ar
k
in
g
s
al
o
n
g
with
th
e
tim
estam
p
o
f
d
ata
ac
q
u
is
itio
n
.
T
h
e
o
wn
er
d
ata
o
f
th
e
d
etec
ted
licen
s
e
p
lates
r
em
ain
s
d
u
m
m
y
d
ata
th
at
h
as n
o
t b
ee
n
in
teg
r
ated
with
g
o
v
er
n
m
en
t li
ce
n
s
e
p
late
d
ata.
2
.
2
.
H
a
rdwa
re
s
y
s
t
em
T
h
e
h
ar
d
war
e
s
y
s
tem
co
m
p
r
is
es
R
a
s
p
b
er
r
y
Pi
as
a
m
icr
o
co
n
tr
o
ller
,
a
web
ca
m
ca
m
er
a
f
o
r
ca
p
tu
r
in
g
im
ag
es,
an
u
ltra
s
o
n
ic
s
en
s
o
r
to
m
ea
s
u
r
e
th
e
d
is
tan
ce
f
r
o
m
t
h
e
cr
o
s
s
in
g
g
ate
to
th
e
r
o
ad
,
a
n
d
a
b
u
zz
er
to
em
it
war
n
in
g
s
o
u
n
d
s
f
o
r
ca
r
s
o
r
m
o
to
r
b
ik
es
v
i
o
latin
g
th
e
r
o
ad
m
ar
k
in
g
s
.
T
o
m
ain
tain
th
e
p
o
wer
,
th
e
web
ca
m
ca
m
er
a
will
ac
tiv
ate
wh
en
th
e
d
is
tan
ce
f
r
o
m
th
e
d
o
o
r
s
tep
to
th
e
r
o
ad
r
ea
c
h
es
1
1
0
to
1
4
0
cm
.
I
f
th
e
d
is
tan
c
e
v
alu
e
f
r
o
m
th
e
d
ev
ice
to
th
e
r
o
ad
is
≥
1
1
0
cm
an
d
≤
1
4
0
cm
,
th
e
s
en
s
o
r
will
s
en
d
a
s
ig
n
al
to
th
e
R
asp
b
er
r
y
Pi
to
tu
r
n
o
n
th
e
web
ca
m
,
an
d
th
e
web
ca
m
will
tak
e
a
v
id
eo
,
t
h
en
d
eter
m
in
e
th
e
d
etec
tio
n
a
r
ea
ac
co
r
d
in
g
to
th
e
lin
e
in
t
h
e
o
p
p
o
s
ite
d
ir
ec
tio
n
.
T
h
e
u
s
e
o
f
R
asp
b
er
r
y
Pi
was
ch
o
s
en
b
ec
au
s
e
R
asp
b
er
r
y
Pi
h
as
b
ee
n
wid
el
y
u
s
ed
in
o
b
ject
r
ec
o
g
n
itio
n
[
1
2
]
an
d
[
1
3
]
.
I
n
ad
d
itio
n
,
R
asp
b
er
r
y
Pi
ca
n
also
b
e
u
s
ed
to
p
er
f
o
r
m
o
b
ject
d
etec
tio
n
in
r
ea
l
-
tim
e
[
1
4
]
.
Fig
u
r
e
2
d
e
p
icts
th
e
elec
tr
o
n
ic
h
ar
d
war
e
s
y
s
tem
d
esig
n
co
m
p
r
is
in
g
R
asp
b
er
r
y
Pi,
a
web
ca
m
ca
m
er
a,
an
u
ltra
s
o
n
ic
s
en
s
o
r
,
an
d
th
e
war
n
in
g
s
o
u
n
d
em
itted
v
ia
a
B
lu
eto
o
th
s
p
ea
k
er
.
Fig
u
r
e
3
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Desig
n
o
f a
r
o
a
d
ma
r
kin
g
vio
l
a
tio
n
d
etec
tio
n
s
ystem
a
t ra
ilw
a
y
leve
l c
r
o
s
s
in
g
s
(
Helfy
S
u
s
ila
w
a
ti
)
885
d
ep
icts
th
e
p
r
o
to
t
y
p
e
o
f
th
e
r
ailway
d
o
o
r
s
to
p
,
co
n
s
tr
u
cted
at
a
s
ca
le
o
f
1
:2
i
n
c
o
m
p
ar
is
o
n
to
th
e
o
r
i
g
in
al
d
o
o
r
s
to
p
.
T
h
e
p
o
s
itio
n
in
g
o
f
th
e
d
ev
ice
alig
n
s
with
th
e
in
i
tial
d
esig
n
,
s
itu
ated
in
th
e
ce
n
ter
o
f
t
h
e
r
ailway
d
o
o
r
s
to
p
p
r
o
t
o
ty
p
e.
Fig
u
r
e
1
.
Flo
wch
ar
t sy
s
tem
Fig
u
r
e
2
.
E
lectr
o
n
ic
s
y
s
tem
d
e
s
ig
n
Fig
u
r
e
3
.
Pro
t
o
ty
p
e
r
ailway
d
o
o
r
cr
o
s
s
in
g
2
.
3
.
O
bje
c
t
cla
s
s
if
ica
t
io
n
Ob
ject
d
etec
tio
n
is
a
cr
u
cial
p
ar
am
eter
in
th
is
r
esear
ch
.
I
f
a
n
o
b
ject
is
d
etec
ted
with
in
th
e
d
etec
tio
n
ar
ea
,
it
s
ig
n
if
ies
a
v
io
latio
n
o
f
r
o
ad
m
ar
k
in
g
s
.
T
h
e
o
b
jects
in
th
is
r
e
s
ea
r
ch
ar
e
ca
teg
o
r
ized
in
to
two
class
if
icatio
n
s
:
ca
r
s
an
d
m
o
to
r
b
ik
es.
T
h
e
m
eth
o
d
em
p
lo
y
e
d
f
o
r
o
b
ject
class
if
icatio
n
is
th
e
SS
D
m
eth
o
d
.
SS
D
was
s
elec
ted
d
u
e
to
its
h
ig
h
ac
cu
r
ac
y
an
d
r
ap
i
d
p
r
o
ce
s
s
in
g
ca
p
a
b
ilit
ies
[
1
5
]
.
Acc
o
r
d
in
g
to
r
esear
ch
,
SS
D
y
ield
s
h
ig
h
er
p
r
ec
is
io
n
co
m
p
ar
ed
to
a
s
u
p
p
o
r
t
v
ec
t
o
r
m
ac
h
in
e
(
SVM)
[
1
6
]
.
I
n
th
e
co
n
d
u
cted
r
esear
ch
,
th
e
p
r
o
ce
s
s
ed
d
ata
co
n
s
is
ted
o
f
1
f
r
am
e
p
e
r
s
ec
o
n
d
(
f
p
s
)
,
wh
e
r
ein
th
e
in
ten
d
ed
r
ea
l
-
tim
e
c
o
n
d
itio
n
d
u
r
i
n
g
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
1
,
Feb
r
u
ar
y
20
25
:
8
8
3
-
893
886
s
tu
d
y
r
e
f
er
s
to
test
in
g
b
ein
g
c
ar
r
ied
o
u
t
in
r
ea
l
-
tim
e
with
in
ac
tu
al
en
v
ir
o
n
m
e
n
tal
s
ettin
g
s
,
r
esu
ltin
g
in
a
d
elay
in
o
b
ject
class
if
icatio
n
tim
in
g
.
T
h
e
in
itial
p
r
o
ce
d
u
r
e
f
o
r
o
b
ject
class
if
icat
io
n
in
v
o
lv
es
c
ap
tu
r
in
g
a
v
id
eo
at
th
e
r
ailway
lev
el
cr
o
s
s
in
g
.
Su
b
s
eq
u
en
tly
,
th
is
v
id
eo
is
s
eg
m
en
ted
in
to
m
u
ltip
le
f
r
am
es.
Fig
u
r
e
4
d
ep
icts
th
e
estab
lis
h
m
en
t
o
f
a
d
etec
tio
n
ar
ea
wh
er
e
v
eh
icles
s
u
r
p
ass
in
g
th
e
r
o
ad
m
a
r
k
in
g
lim
it
ar
e
co
n
s
id
er
ed
f
o
r
class
if
icatio
n
.
On
ce
th
e
d
etec
tio
n
ar
ea
is
d
ef
in
e
d
,
th
e
s
u
b
s
eq
u
en
t step
is
to
class
if
y
th
e
d
etec
ted
o
b
jects.
Ob
ject
class
if
icatio
n
test
in
g
is
co
n
d
u
cte
d
th
r
o
u
g
h
two
a
p
p
r
o
ac
h
es:
f
ir
s
t,
d
ir
ec
tly
at
th
e
r
ailway
cr
o
s
s
in
g
s
ite,
an
d
s
e
co
n
d
,
in
alter
n
ativ
e
lo
ca
tio
n
s
u
tili
zin
g
t
h
e
d
e
v
el
o
p
ed
p
r
o
t
o
ty
p
e.
Dete
ctio
n
a
r
ea
s
in
im
ag
es
u
s
in
g
Py
th
o
n
as
a
p
r
o
g
r
am
m
in
g
lan
g
u
ag
e
a
n
d
u
s
in
g
R
asp
b
er
r
y
Pi OS a
n
d
v
is
u
al
s
tu
d
io
co
d
e
f
o
r
s
o
f
twar
e.
Fig
u
r
e
4
.
Dete
ctio
n
a
r
ea
im
ag
e
2
.
4
.
Vehicle
nu
m
ber
pla
t
e
det
ec
t
io
n
T
h
e
n
u
m
b
er
p
late
o
b
ject
d
etec
tio
n
m
eth
o
d
u
s
es
th
e
Haa
r
C
ascad
e
c
lass
if
ier
to
d
etec
t
letter
s
an
d
n
u
m
b
er
s
o
n
th
e
n
u
m
b
e
r
p
late
u
s
in
g
th
e
OC
R
m
eth
o
d
.
T
h
e
u
s
e
o
f
th
e
Haa
r
ca
s
ca
d
e
clas
s
if
ier
an
d
OC
R
f
o
r
p
late
d
etec
tio
n
h
as
also
b
ee
n
d
o
n
e
i
n
p
r
ev
io
u
s
s
tu
d
ies
[
1
7
]
.
T
h
e
d
if
f
e
r
en
ce
b
etwe
en
th
is
r
esear
ch
an
d
th
e
o
n
e
co
n
d
u
cte
d
is
th
at
af
ter
o
b
ject
d
etec
tio
n
an
d
c
h
ar
ac
ter
r
ec
o
g
n
itio
n
,
th
e
r
esu
lts
o
f
c
h
ar
ac
t
er
r
ec
o
g
n
itio
n
ar
e
s
to
r
ed
in
th
e
d
atab
ase
an
d
d
is
p
lay
ed
o
n
th
e
web
s
ite.
Sen
d
in
g
d
ata
to
t
h
e
d
atab
ase
will
b
e
th
e
b
asis
f
o
r
tick
etin
g
f
o
r
v
i
o
latin
g
r
o
ad
m
ar
k
in
g
s
.
T
h
e
u
s
e
o
f
OC
R
was
ch
o
s
en
b
ec
a
u
s
e
OC
R
is
o
n
e
o
f
th
e
g
o
o
d
m
eth
o
d
s
u
s
ed
f
o
r
ch
ar
ac
ter
r
ec
o
g
n
itio
n
with
f
air
ly
g
o
o
d
ac
cu
r
ac
y
[
1
8
]
.
OC
R
is
wid
ely
u
s
ed
f
o
r
h
a
n
d
wr
itin
g
r
esear
c
h
,
in
clu
d
in
g
f
o
r
r
ec
o
g
n
izin
g
E
n
g
lis
h
h
an
d
wr
itten
tex
t
[
1
9
]
,
Ma
lay
alam
h
a
n
d
wr
itten
te
x
t
[
2
0
]
,
Dev
an
ag
a
r
i
s
cr
ip
t
h
an
d
wr
itin
g
[
2
1
]
,
an
d
m
an
y
m
o
r
e.
OC
R
is
also
u
s
ed
in
r
esear
ch
f
o
r
th
e
d
ig
itizatio
n
o
f
m
ed
ical
r
ec
o
r
d
s
,
wh
er
e
th
e
er
r
o
r
r
esu
lts
o
f
OC
R
r
ea
c
h
ed
6
%,
wh
ic
h
is
lo
wer
th
a
n
u
s
in
g
th
e
Gate
d
-
C
NN
-
B
L
STM
alg
o
r
ith
m
m
eth
o
d
,
wh
ich
is
9
%
[
2
2
]
.
Dete
ctio
n
l
icen
s
e
p
late
u
s
in
g
Py
th
o
n
as
a
p
r
o
g
r
am
m
i
n
g
la
n
g
u
a
g
e
an
d
u
s
in
g
R
asp
b
er
r
y
Pi
OS a
n
d
v
is
u
al
s
tu
d
io
co
d
e
f
o
r
s
o
f
twar
e.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
s
ec
tio
n
d
is
cu
s
s
e
s
th
e
r
ese
ar
ch
r
esu
lts
d
ep
icted
in
f
ig
u
r
e
s
an
d
tab
les.
T
h
is
s
ec
tio
n
will
b
e
d
iv
id
ed
in
to
s
ev
er
al
p
ar
ts
.
T
h
e
f
ir
s
t
p
a
r
t
d
is
cu
s
s
es
th
e
test
in
g
o
f
ea
ch
co
m
p
o
n
en
t
in
d
i
v
id
u
ally
,
f
o
llo
wed
b
y
test
in
g
th
e
en
tire
s
y
s
tem
as
a
wh
o
le.
S
y
s
tem
test
in
g
f
o
r
ea
c
h
co
m
p
o
n
en
t
in
clu
d
es
u
ltra
s
o
n
ic
s
en
s
o
r
test
in
g
,
o
b
ject
d
etec
tio
n
test
in
g
,
licen
s
e
p
late
r
ea
d
in
g
test
in
g
,
an
d
d
ata
tr
an
s
m
is
s
io
n
test
in
g
to
th
e
d
atab
ase
.
3
.
1
.
E
x
perim
ent
ultr
a
s
o
nic sens
o
r
re
a
din
g
o
f
webca
m
co
nd
it
io
ns
T
h
e
d
o
o
r
s
to
p
au
to
m
atica
lly
clo
s
es
u
p
o
n
th
e
ar
r
iv
al
o
f
a
tr
ai
n
s
ch
ed
u
le.
Du
r
in
g
th
e
clo
s
u
r
e
p
r
o
ce
s
s
,
an
u
ltra
s
o
n
ic
s
en
s
o
r
m
ea
s
u
r
es
th
e
d
is
tan
ce
b
etwe
en
th
e
h
e
ig
h
t
o
f
th
e
cr
o
s
s
b
ar
an
d
th
e
r
o
ad
s
u
r
f
ac
e.
I
f
th
e
d
is
tan
ce
f
alls
with
in
th
e
r
an
g
e
o
f
≥
1
1
0
cm
an
d
≤
1
4
0
cm
,
th
e
web
ca
m
ac
tiv
ates,
an
d
th
e
s
y
s
tem
b
ec
o
m
es
o
p
er
atio
n
al.
T
h
e
d
is
tan
ce
≥
1
1
0
cm
an
d
≤
1
4
0
cm
is
ch
o
s
en
b
ased
o
n
th
e
ac
t
u
al
h
eig
h
t
o
f
t
h
e
r
ailway
cr
o
s
s
in
g
g
ate
ab
o
v
e
th
e
g
r
o
u
n
d
(
as
p
er
th
e
p
r
o
to
ty
p
e
co
n
s
tr
u
cte
d
)
,
wh
ich
is
1
1
0
c
m
.
T
h
e
web
ca
m
ac
tiv
atio
n
th
r
esh
o
ld
b
eg
in
s
wh
en
th
e
u
ltra
s
o
n
ic
s
e
n
s
o
r
d
etec
ts
a
d
is
tan
ce
f
r
o
m
t
h
e
g
ate
t
o
th
e
g
r
o
u
n
d
b
elo
w
1
4
0
cm
.
T
h
is
en
s
u
r
es
th
at
b
y
th
e
tim
e
th
e
c
r
o
s
s
in
g
g
ate
is
f
u
lly
clo
s
ed
(
at
a
d
is
tan
ce
o
f
1
1
0
cm
f
r
o
m
th
e
g
r
o
u
n
d
)
,
t
h
e
web
ca
m
is
r
ea
d
y
to
ca
p
tu
r
e
im
ag
es
an
d
p
er
f
o
r
m
d
etec
tio
n
a
n
d
class
if
icatio
n
task
s
.
T
h
is
is
d
o
n
e
s
o
t
h
at
th
e
s
y
s
tem
d
o
es
n
o
t
co
n
tin
u
o
u
s
ly
ac
tiv
ate
th
e
ca
m
er
a.
T
h
e
u
ltra
s
o
n
ic
s
e
n
s
o
r
r
ea
d
in
g
s
ar
e
test
ed
u
n
d
er
clea
r
wea
th
er
co
n
d
itio
n
s
an
d
g
o
o
d
illu
m
in
at
io
n
(
d
u
r
in
g
d
ay
tim
e)
,
allo
win
g
th
e
u
ltra
s
o
n
ic
s
en
s
o
r
t
o
ac
c
u
r
ately
m
ea
s
u
r
e
th
e
d
is
tan
ce
b
etwe
en
th
e
cr
o
s
s
in
g
g
ate
an
d
th
e
g
r
o
u
n
d
.
Ho
wev
er
,
in
ad
v
er
s
e
wea
th
er
co
n
d
iti
o
n
s
s
u
ch
as
r
ain
o
r
in
s
u
f
f
icien
t lig
h
tin
g
,
th
e
r
ea
d
in
g
s
f
r
o
m
th
e
u
ltra
s
o
n
ic
s
en
s
o
r
m
ay
b
ec
o
m
e
less
ac
cu
r
ate.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Desig
n
o
f a
r
o
a
d
ma
r
kin
g
vio
l
a
tio
n
d
etec
tio
n
s
ystem
a
t ra
ilw
a
y
leve
l c
r
o
s
s
in
g
s
(
Helfy
S
u
s
ila
w
a
ti
)
887
T
ab
le
1
p
r
esen
ts
th
e
s
y
s
tem
test
in
g
r
esu
lts
co
m
p
ar
in
g
u
l
tr
aso
n
ic
s
en
s
o
r
r
ea
d
in
g
s
with
web
ca
m
ac
tiv
atio
n
co
n
d
itio
n
s
ac
r
o
s
s
v
ar
y
in
g
d
is
tan
ce
s
f
r
o
m
th
e
lo
w
est
to
th
e
h
ig
h
est
r
a
n
g
e
a
n
d
f
r
o
m
th
e
f
u
r
th
est
to
th
e
clo
s
est
d
is
tan
ce
p
o
s
itio
n
s
.
Fro
m
th
e
d
ata
i
n
T
ab
le
1
,
it
is
o
b
s
er
v
ed
th
at
th
e
we
b
ca
m
ac
tiv
ates
wh
en
th
e
s
en
s
o
r
r
ea
d
in
g
s
r
an
g
e
f
r
o
m
1
0
9
.
8
6
to
1
3
9
.
6
1
cm
an
d
f
r
o
m
1
1
0
.
0
9
to
1
3
8
.
1
5
cm
b
etwe
en
t
h
e
g
ate
an
d
th
e
r
o
ad
s
u
r
f
ac
e.
C
o
n
v
er
s
ely
,
t
h
e
web
c
am
r
em
ain
s
in
ac
tiv
e
wh
en
t
h
e
s
en
s
o
r
r
ea
d
in
g
s
ar
e
b
etwe
en
9
.
9
7
to
1
0
0
.
1
4
c
m
,
1
4
7
.
9
7
to
1
8
9
.
1
4
cm
,
1
0
.
0
7
t
o
1
0
3
.
1
4
cm
,
an
d
1
5
4
.
0
4
to
1
8
9
.
8
8
cm
.
T
h
e
s
en
s
o
r
u
ltra
s
o
n
ic
d
ata
was
cr
o
s
s
-
ch
ec
k
ed
with
ac
tu
al
d
is
tan
ce
s
u
s
in
g
a
r
u
ler
.
T
a
b
le
1
in
d
i
ca
tes
th
at
th
e
av
er
a
g
e
er
r
o
r
o
f
u
ltra
s
o
n
ic
s
en
s
o
r
r
ea
d
in
g
s
is
0
.
5
7
3
% a
n
d
0
.
5
8
2
%.
T
h
e
av
er
ag
e
e
r
r
o
r
in
T
a
b
le
1
is
ca
lcu
lated
u
s
in
g
(
1
)
:
(
%
)
=
|
−
|
∗
100%
(
1
)
T
ab
le
1
.
T
h
e
in
f
lu
e
n
ce
o
f
s
en
s
o
r
r
ea
d
i
n
g
s
o
n
we
b
ca
m
co
n
d
it
io
n
s
f
r
o
m
l
o
w
to
h
ig
h
an
d
f
r
o
m
h
ig
h
t
o
lo
w
d
is
tan
ce
s
S
e
n
s
o
r
r
e
a
d
i
n
g
s
o
n
w
e
b
c
a
m
c
o
n
d
i
t
i
o
n
s fr
o
m
l
o
w
t
o
h
i
g
h
d
i
s
t
a
n
c
e
s
S
e
n
s
o
r
r
e
a
d
i
n
g
s
o
n
w
e
b
c
a
m
c
o
n
d
i
t
i
o
n
s fr
o
m
h
i
g
h
t
o
l
o
w
d
i
s
t
a
n
c
e
s
R
e
f
e
r
e
n
c
e
v
a
l
u
e
met
e
r
(
c
m)
S
e
n
s
o
r
r
e
a
d
i
n
g
r
e
s
u
l
t
(
c
m)
S
e
n
s
o
r
r
e
a
d
i
n
g
e
r
r
o
r
r
a
t
e
(
%)
W
e
b
c
a
m
c
o
n
d
i
t
i
o
n
R
e
f
e
r
e
n
c
e
v
a
l
u
e
s
o
f
t
h
e
m
e
t
e
r
(
c
m)
S
e
n
s
o
r
r
e
a
d
i
n
g
r
e
s
u
l
t
s (c
m)
S
e
n
s
o
r
r
e
a
d
i
n
g
e
r
r
o
r
r
a
t
e
(
%)
W
e
b
c
a
m
c
o
n
d
i
t
i
o
n
10
9
.
9
7
0
.
3
0
Off
1
9
0
1
8
9
.
8
8
0
.
0
6
Off
20
1
9
.
5
8
2
.
1
0
Off
1
8
0
1
7
9
.
9
3
0
.
0
3
Off
30
2
9
.
9
7
0
.
1
0
Off
1
7
0
1
7
0
.
1
6
0
.
0
9
Off
40
4
0
.
1
2
0
.
3
0
Off
1
6
0
1
6
0
.
5
6
0
.
3
5
Off
50
5
0
.
6
1
1
.
2
2
Off
1
5
0
1
5
4
.
0
4
2
.
6
9
Off
60
5
9
.
6
9
0
.
5
1
Off
1
4
0
1
3
8
.
1
5
1
.
3
2
On
70
7
0
.
1
4
0
.
2
0
Off
1
3
0
1
2
9
.
7
5
0
.
1
9
On
80
8
0
.
1
8
0
.
2
2
Off
1
2
0
1
1
9
.
9
6
0
.
0
3
On
90
9
0
.
3
1
0
.
3
4
Off
1
1
0
1
1
0
.
0
9
0
.
0
8
On
1
0
0
1
0
0
.
1
4
0
.
1
4
Off
1
0
0
1
0
3
.
1
4
3
.
1
4
Off
1
1
0
1
0
9
.
8
6
0
.
1
2
On
90
9
0
.
3
1
0
.
3
4
Off
1
2
0
1
1
9
.
7
0
0
.
2
5
On
80
8
0
.
1
8
0
.
2
2
Off
1
3
0
1
2
8
.
9
6
0
.
8
0
On
70
7
0
.
3
1
0
.
4
4
Off
1
4
0
1
3
9
.
6
1
0
.
2
7
On
60
6
0
.
0
9
0
.
1
5
Off
1
5
0
1
4
7
.
9
7
1
.
3
5
Off
50
4
9
.
9
7
0
.
0
6
Off
1
6
0
1
6
0
.
1
4
0
.
0
8
Off
40
4
0
.
1
2
0
.
3
0
Off
1
7
0
1
7
0
.
5
8
0
.
3
4
Off
30
3
0
.
1
4
0
.
4
6
Off
1
8
0
1
7
7
.
9
8
1
.
1
2
Off
20
1
9
.
9
7
0
.
1
5
Off
1
9
0
1
8
9
.
1
4
1
.
1
2
Off
10
1
0
.
0
7
0
.
7
0
Off
A
v
e
r
a
g
e
e
r
r
o
r
(
%)
0
.
5
7
3
A
v
e
r
a
g
e
e
r
r
o
r
(
%)
0
.
5
8
2
3
.
2
.
O
bje
c
t
cla
s
s
if
ica
t
io
n t
esting
T
h
e
im
ag
es
d
er
iv
ed
f
r
o
m
th
e
r
ec
o
r
d
e
d
v
id
e
o
r
esu
lts
ar
e
s
u
b
s
eq
u
en
tly
ca
teg
o
r
ized
i
n
to
tw
o
o
b
jects:
m
o
to
r
b
ik
e
o
b
jects
an
d
ca
r
o
b
jects.
T
esti
n
g
is
co
n
d
u
cted
u
tili
zin
g
a
p
r
ev
io
u
s
ly
d
e
v
elo
p
e
d
p
r
o
to
t
y
p
e,
wh
ich
em
p
lo
y
s
a
d
etec
tio
n
ar
ea
tailo
r
ed
to
th
e
ch
ar
ac
ter
is
tics
o
f
lev
el
cr
o
s
s
in
g
s
.
I
n
Fig
u
r
e
5
,
th
e
g
r
ee
n
lin
e
d
elin
ea
tes
th
e
d
etec
tio
n
ar
ea
,
wh
ile
th
e
b
lu
e
lin
e
r
ep
r
esen
ts
th
e
class
if
icatio
n
o
f
m
o
to
r
b
ik
e
o
b
jects.
I
t
is
ev
id
en
t
f
r
o
m
th
e
f
i
g
u
r
e
th
at
t
h
er
e
ar
e
two
m
o
to
r
cy
cles;
h
o
wev
er
,
th
o
s
e
o
u
ts
id
e
th
e
d
ete
ctio
n
ar
ea
ar
e
n
o
t
class
if
ied
.
Fig
u
r
e
6
illu
s
tr
ate
s
th
e
class
if
icatio
n
o
f
th
e
ca
r
o
b
ject.
T
h
e
d
etec
tio
n
ar
ea
is
in
d
icate
d
b
y
a
g
r
ee
n
lin
e,
wh
ile
th
e
ca
r
class
if
icati
o
n
is
d
en
o
ted
b
y
a
r
ed
lin
e.
T
h
r
o
u
g
h
o
u
t
th
e
d
etec
tio
n
p
r
o
ce
s
s
,
th
e
tim
e
d
elay
n
ec
ess
ar
y
f
o
r
o
b
ject
class
if
icatio
n
is
ass
es
s
ed
.
T
ab
le
2
d
is
p
lay
s
th
e
tim
e
r
eq
u
ir
ed
f
o
r
o
b
ject
class
if
icatio
n
.
T
h
e
av
er
ag
e
tim
e
f
o
r
class
if
y
in
g
m
o
to
r
b
ik
e
o
b
jects
is
0
.
7
0
2
s
ec
o
n
d
s
,
wh
ile
f
o
r
class
if
y
in
g
ca
r
o
b
jects,
it
is
0
.
5
5
4
s
ec
o
n
d
s
.
3
.
3
.
Vehicle
nu
m
ber
pla
t
e
det
ec
t
io
n t
est
T
h
e
d
etec
tio
n
o
f
v
e
h
icle
n
u
m
b
er
p
lates
u
tili
ze
s
th
e
Haa
r
C
ascad
e
c
lass
if
ier
,
wh
ile
ch
ar
ac
te
r
r
ec
o
g
n
itio
n
o
n
t
h
e
n
u
m
b
e
r
p
late
is
ac
h
iev
ed
u
s
in
g
OC
R
.
T
h
e
p
r
o
ce
s
s
o
f
d
etec
tin
g
an
d
r
ec
o
g
n
izin
g
ch
a
r
ac
ter
s
o
n
th
e
n
u
m
b
er
p
late
in
v
o
lv
es
s
ev
er
al
s
tep
s
,
in
clu
d
in
g
cr
o
p
p
in
g
,
g
r
ay
s
ca
le
co
n
v
er
s
io
n
,
r
es
izin
g
,
d
ilatio
n
,
an
d
er
o
s
io
n
.
T
o
f
in
d
o
u
t th
e
s
tar
tin
g
p
er
ce
n
ta
g
e
o
f
s
u
cc
ess
in
ch
ar
ac
ter
r
ec
o
g
n
itio
n
,
we
ca
n
u
s
e
(
2
)
:
Su
cc
ess
(
%)
=
∑
cl
o
s
e
s
t
char
act
er
∑
t
r
ue
char
act
er
∗
100%
(
2
)
T
h
e
o
u
tco
m
es
o
f
th
e
s
y
s
tem
'
s
ch
ar
ac
ter
r
ec
o
g
n
itio
n
s
u
cc
ess
ca
lcu
latio
n
f
o
r
th
e
ch
ar
ac
ter
s
with
in
th
e
n
u
m
b
er
p
late.
T
ab
le
3
d
is
p
la
y
s
th
e
ex
p
er
im
en
t
in
v
o
l
v
ed
i
n
co
n
d
u
ctin
g
5
test
s
u
s
in
g
th
e
s
am
e
n
u
m
b
e
r
p
late
o
b
ject.
I
n
t
h
e
ca
s
e
o
f
th
e
n
u
m
b
er
p
late
with
a
wh
ite
b
ac
k
g
r
o
u
n
d
,
s
ev
er
al
test
s
f
ailed
to
r
ec
o
g
n
ize
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
1
,
Feb
r
u
ar
y
20
25
:
8
8
3
-
893
888
ch
ar
ac
ter
s
o
n
th
e
p
late.
C
o
n
v
er
s
ely
,
with
th
e
b
lack
n
u
m
b
e
r
p
late,
it
was
o
b
s
er
v
ed
t
h
at
all
ch
ar
ac
ter
s
wer
e
s
u
cc
ess
f
u
lly
r
ec
o
g
n
ize
d
.
Ou
t
o
f
th
e
f
iv
e
test
s
co
n
d
u
cte
d
wi
th
th
e
wh
ite
p
late,
o
n
ly
two
te
s
ts
wer
e
s
u
cc
ess
f
u
l
in
ch
ar
ac
ter
r
ec
o
g
n
itio
n
,
wh
er
ea
s
all
test
s
co
n
d
u
cte
d
wi
th
th
e
b
lack
p
late
s
u
cc
ess
f
u
lly
r
ec
o
g
n
ized
th
e
ch
ar
ac
ter
s
.
T
h
e
en
tire
test
in
g
was
co
n
d
u
cted
u
n
d
e
r
clea
r
wea
th
er
co
n
d
itio
n
s
an
d
b
r
ig
h
t
illu
m
in
atio
n
,
s
p
ec
if
ically
d
u
r
in
g
d
ay
lig
h
t h
o
u
r
s
.
Fig
u
r
e
5
.
C
lass
if
icatio
n
o
f
m
o
t
o
r
b
ik
e
o
b
jects
Fig
u
r
e
6
.
C
lass
if
icatio
n
o
f
ca
r
o
b
jects
T
ab
le
2
.
Ob
ject
class
if
icatio
n
tim
e
d
elay
tab
le
Te
st
i
n
g
O
b
j
e
c
t
c
l
a
ssi
f
i
c
a
t
i
o
n
t
i
m
e
M
o
t
o
r
b
i
k
e
C
a
r
s
1
0
.
7
8
0
.
6
5
2
0
.
9
1
0
.
5
7
3
0
.
6
2
0
.
5
6
4
0
.
7
3
0
.
4
7
5
0
.
4
7
0
.
5
2
A
v
e
r
a
g
e
d
e
l
a
y
0
.
7
0
2
0
.
5
5
4
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Desig
n
o
f a
r
o
a
d
ma
r
kin
g
vio
l
a
tio
n
d
etec
tio
n
s
ystem
a
t ra
ilw
a
y
leve
l c
r
o
s
s
in
g
s
(
Helfy
S
u
s
ila
w
a
ti
)
889
Fu
r
th
er
m
o
r
e
,
to
o
b
tain
a
n
u
m
b
er
p
late
th
at
ca
n
b
e
ea
s
ily
d
etec
ted
a
n
d
r
ec
o
g
n
ize
d
,
t
h
e
ca
m
er
a'
s
p
o
s
itio
n
r
elativ
e
to
th
e
n
u
m
b
er
p
late
m
u
s
t
b
e
p
er
p
en
d
ic
u
lar
.
I
f
th
e
n
u
m
b
er
p
late
o
b
tai
n
ed
f
r
o
m
th
e
v
id
e
o
r
esu
lts
is
m
is
alig
n
ed
,
th
is
also
af
f
ec
ts
th
e
c
h
ar
ac
ter
r
ec
o
g
n
itio
n
p
r
o
ce
s
s
o
n
t
h
e
n
u
m
b
er
p
l
ate.
Nu
m
b
er
p
lates
with
b
lack
b
ac
k
g
r
o
u
n
d
s
ar
e
ea
s
ier
to
r
ec
o
g
n
ize
c
h
ar
ac
t
er
s
b
ec
au
s
e
th
ey
alig
n
b
etter
with
th
e
im
a
g
e
p
r
o
ce
s
s
in
g
p
r
o
ce
s
s
,
p
ar
ticu
l
ar
ly
th
e
g
r
a
y
s
ca
le
co
n
v
er
s
io
n
.
W
h
en
g
r
a
y
s
ca
le
co
n
v
er
s
io
n
is
p
er
f
o
r
m
ed
,
ch
ar
ac
ter
s
o
n
b
lack
p
lates
ap
p
ea
r
b
r
ig
h
ter
c
o
m
p
ar
e
d
to
th
o
s
e
o
n
wh
ite
n
u
m
b
e
r
p
lates.
T
h
e
en
tire
test
in
g
was
co
n
d
u
cte
d
u
n
d
er
clea
r
wea
th
e
r
co
n
d
itio
n
s
an
d
b
r
ig
h
t illu
m
in
atio
n
,
s
p
ec
if
ically
d
u
r
in
g
d
ay
li
g
h
t h
o
u
r
s
.
T
ab
le
3
.
Nu
m
b
er
p
late
test
in
g
tab
le
Te
st
i
n
g
t
o
-
O
r
i
g
i
n
a
l
c
h
a
r
a
c
t
e
r
I
mag
e
p
r
o
c
e
ssi
n
g
C
h
a
r
a
c
t
e
r
r
e
c
o
g
n
i
t
i
o
n
r
e
s
u
l
t
P
e
r
c
e
n
t
a
g
e
(
%)
O
b
j
e
c
t
1
C
a
r
(
B
l
a
c
k
P
l
a
t
e
)
1
D
1
1
7
5
N
W
O
1
1
7
5
N
W
8
5
.
1
7
2
O
1
1
7
5
N
W
8
5
.
1
7
3
D
1
1
7
5
N
W
1
0
0
4
D
1
1
7
5
N
W
1
0
0
5
O
1
1
Z
5
N
W
7
1
.
4
2
O
b
j
e
c
t
2
M
o
t
o
r
b
i
k
e
(
W
h
i
t
e
P
l
a
t
e
)
1
Z2
6
6
4
D
B
D
Z2
6
6
4
D
B
I
8
7
.
5
0
2
Z2
6
6
4
D
B
D
1
0
0
3
-
0
4
-
0
5
-
0
O
b
j
e
c
t
3
M
o
t
o
r
b
i
k
e
(
B
l
a
c
k
P
l
a
t
e
)
1
Z4
7
2
4
D
A
Q
Z4
7
2
4
D
A
O
8
7
.
5
0
2
ZL7
2
LD
A
O
6
2
.
5
0
3
ZL7
2
LD
A
G
6
2
.
5
0
4
ZL7
2
LD
A
C
6
2
.
5
0
5
ZL7
2
LD
A
C
6
2
.
5
0
A
v
e
r
a
g
e
p
e
r
c
e
n
t
a
g
e
o
f
s
u
c
c
e
ss (
%)
6
4
.
4
5
I
n
Fig
u
r
e
7
,
it
is
n
o
ted
th
at
b
o
th
class
if
ied
o
b
jects,
n
am
ely
ca
r
s
an
d
m
o
to
r
c
y
cles,
ca
n
b
e
id
en
tifie
d
.
T
h
is
is
ev
id
en
t
f
r
o
m
th
e
d
etec
tio
n
ar
ea
s
o
n
th
e
ca
r
s
an
d
m
o
t
o
r
cy
cles
ex
ce
e
d
in
g
th
e
r
o
a
d
m
ar
k
in
g
b
o
u
n
d
ar
ies.
I
n
b
o
th
in
s
tan
ce
s
wh
er
e
m
o
to
r
cy
cles
v
io
late
th
e
r
o
ad
m
ar
k
in
g
s
,
th
e
f
ir
s
t
d
etec
ted
m
o
to
r
cy
cle
is
th
e
b
lack
-
co
lo
r
ed
o
n
e,
wh
er
e
class
if
icatio
n
d
ata
an
d
licen
s
e
p
late
in
f
o
r
m
atio
n
ar
e
o
b
tain
ed
.
T
h
e
a
d
jace
n
t
m
o
to
r
c
y
cle
o
b
ject
is
d
etec
ted
af
ter
o
b
tain
in
g
th
e
licen
s
e
p
late
o
f
th
e
f
ir
s
t
m
o
to
r
cy
cle
o
b
ject.
I
n
Fig
u
r
e
8
,
it
is
o
b
s
er
v
ed
th
at
th
e
s
y
s
tem
i
s
ca
p
ab
le
o
f
class
if
y
in
g
o
b
jects
an
d
d
eter
m
in
in
g
th
em
as
m
o
to
r
cy
cles.
Ho
wev
er
,
f
o
r
th
e
y
ello
w
-
co
lo
r
e
d
m
o
to
r
c
y
cle,
th
e
ch
ar
ac
ter
s
o
n
th
e
licen
s
e
p
lat
e
ca
n
n
o
t b
e
r
ec
o
g
n
ize
d
d
u
e
to
th
e
p
o
o
r
q
u
ality
o
f
th
e
d
etec
ted
licen
s
e
p
late
im
ag
e.
B
ec
au
s
e
th
e
licen
s
e
p
lat
e
is
n
o
t
alig
n
ed
with
th
e
ca
m
er
a
p
lace
m
en
t,
th
e
s
y
s
tem
ca
n
n
o
t
r
ec
o
g
n
ize
th
e
licen
s
e
p
late
o
n
th
e
ca
r
at
all.
T
h
er
ef
o
r
e,
th
e
an
g
le
o
f
t
h
e
ca
m
er
a
ca
p
tu
r
e
co
n
ce
r
n
in
g
th
e
licen
s
e
p
late
o
n
th
e
o
b
ject
also
n
ee
d
s
to
b
e
c
o
n
s
id
er
ed
.
Up
o
n
d
etec
tio
n
o
f
an
o
b
ject
a
t
a
lev
el
cr
o
s
s
in
g
,
th
e
s
y
s
tem
ac
tiv
ates
a
b
u
zz
e
r
to
war
n
th
e
o
b
ject
n
o
t
to
cr
o
s
s
th
e
r
o
ad
m
ar
k
in
g
s
.
I
f
th
e
o
b
ject
is
s
til
l
d
etec
ted
af
ter
th
e
b
u
zz
er
war
n
i
n
g
,
th
e
s
y
s
tem
p
r
o
ce
ed
s
to
r
ec
o
g
n
ize
th
e
licen
s
e
p
late
ch
ar
ac
ter
s
,
r
ec
o
r
d
in
g
th
em
as
v
i
o
latio
n
r
ec
o
r
d
s
.
R
esear
ch
f
in
d
in
g
s
also
in
d
icate
th
e
s
u
cc
ess
f
u
l
f
u
n
ctio
n
ality
o
f
th
e
b
u
zz
e
r
an
d
d
ata
tr
a
n
s
m
is
s
io
n
to
th
e
d
atab
ase.
Ho
wev
e
r
,
th
er
e
is
a
n
ee
d
f
o
r
im
p
r
o
v
em
e
n
t
in
th
e
c
h
ar
ac
ter
r
ec
o
g
n
itio
n
co
m
p
o
n
en
t
t
o
en
s
u
r
e
r
ec
o
g
n
itio
n
u
n
d
e
r
all
co
n
d
itio
n
s
.
T
h
e
s
y
s
tem
's
p
u
r
p
o
s
e
is
to
p
r
o
v
id
e
war
n
in
g
s
an
d
d
eter
r
e
n
ce
to
r
o
a
d
m
a
r
k
in
g
v
i
o
lato
r
s
at
lev
el
r
ailway
cr
o
s
s
in
g
s
,
an
ar
ea
wh
er
e
ef
f
ec
tiv
e
war
n
in
g
a
n
d
d
eter
r
en
ce
s
y
s
tem
s
ar
e
cu
r
r
e
n
tly
lack
in
g
,
p
ar
ticu
lar
ly
in
I
n
d
o
n
esia.
3
.
4
.
T
esting
s
endin
g
da
t
a
t
o
t
he
da
t
a
ba
s
e
Fo
llo
win
g
th
e
ch
ar
ac
ter
r
ea
d
i
n
g
test
o
n
th
e
n
u
m
b
e
r
p
late,
t
h
e
s
u
b
s
eq
u
en
t
s
tep
in
v
o
lv
es
tr
an
s
m
itti
n
g
th
e
n
u
m
b
e
r
p
late
ch
ar
ac
ter
d
ata
to
th
e
d
atab
ase.
Fig
u
r
e
9
d
ep
icts
an
im
ag
e
o
f
t
h
e
web
s
ite
d
esig
n
ed
f
o
r
r
ec
o
r
d
in
g
v
io
latio
n
s
o
f
r
o
ad
m
ar
k
in
g
s
at
r
ailway
-
lev
el
cr
o
s
s
in
g
s
.
I
m
ag
e
ca
p
tu
r
e
o
cc
u
r
s
wh
en
th
e
s
y
s
te
m
d
etec
ts
a
m
o
to
r
b
ik
e
o
r
ca
r
p
ass
in
g
th
r
o
u
g
h
th
e
r
o
ad
,
f
o
ll
o
wed
b
y
a
war
n
i
n
g
is
s
u
ed
th
r
o
u
g
h
a
B
lu
eto
o
th
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
1
,
Feb
r
u
ar
y
20
25
:
8
8
3
-
893
890
s
p
ea
k
er
to
p
r
o
m
p
t
th
e
v
eh
icl
e
to
s
witch
to
th
e
ap
p
r
o
p
r
iate
lan
e.
Su
b
s
eq
u
en
tly
,
af
ter
a
2
-
m
in
u
te
in
ter
v
al,
a
p
ictu
r
e
is
tak
e
n
o
f
th
e
v
e
h
icle
th
at
v
i
o
lates
th
e
r
o
ad
m
ar
k
in
g
s
at
th
e
f
r
o
n
t.
T
h
is
im
ag
e
is
th
en
tr
an
s
m
itted
t
o
th
e
web
s
ite
alo
n
g
with
th
e
tim
estam
p
o
f
th
e
v
io
latio
n
.
Fig
u
r
e
7
.
Dete
ctio
n
a
n
d
class
if
icatio
n
o
f
o
b
jects
alo
n
g
with
licen
s
e
p
late
r
ea
d
in
g
o
n
th
e
f
ir
s
t
m
o
to
r
cy
cle
o
b
ject
(
b
lac
k
co
lo
r
)
Fig
u
r
e
8
.
I
ll
u
s
tr
ates th
e
d
etec
tio
n
an
d
class
if
icatio
n
o
f
o
b
jects a
lo
n
g
with
th
e
licen
s
e
p
late
r
ea
d
in
g
o
n
th
e
s
ec
o
n
d
m
o
to
r
b
i
k
e
(
h
ig
h
lig
h
ted
in
y
ello
w)
Fig
u
r
e
9
.
W
eb
s
ite
f
o
r
r
ec
o
r
d
in
g
v
io
lato
r
s
o
f
r
o
a
d
m
ar
k
in
g
s
a
t r
ailway
lev
el
cr
o
s
s
in
g
s
3.
5
.
Da
t
a
a
na
ly
s
is
a
nd
dis
c
u
s
s
io
n
T
h
is
r
esear
ch
aim
s
to
p
r
e
v
en
t
tr
af
f
ic
co
n
g
esti
o
n
a
n
d
ac
cid
e
n
ts
wh
en
r
ailway
cr
o
s
s
in
g
g
ate
s
ar
e
o
p
e
n
ca
u
s
ed
b
y
m
o
to
r
is
ts
u
s
in
g
b
o
t
h
s
id
es
o
f
th
e
r
o
ad
.
T
h
e
u
s
e
o
f
b
o
th
s
id
es
f
r
o
m
o
p
p
o
s
ite
d
ir
ec
tio
n
s
ca
n
lead
to
co
n
g
esti
o
n
an
d
p
o
s
e
ac
cid
en
t
r
is
k
s
.
T
h
is
s
tu
d
y
d
esig
n
s
a
s
y
s
tem
to
d
etec
t
v
eh
icles
cr
o
s
s
in
g
r
o
ad
m
ar
k
in
g
b
o
u
n
d
ar
ies
an
d
aler
t
d
r
iv
er
s
t
o
r
ef
r
ain
f
r
o
m
d
o
in
g
s
o
.
I
t
als
o
aim
s
to
d
eter
v
io
latio
n
s
b
y
r
ec
o
r
d
in
g
th
e
lice
n
s
e
p
lates o
f
v
eh
icles th
at
cr
o
s
s
th
e
m
ar
k
in
g
s
wh
ile
tr
ain
s
ar
e
p
ass
in
g
,
wh
ich
ca
n
lead
to
s
u
b
s
e
q
u
en
t le
g
al
ac
tio
n
s
.
T
h
is
r
esear
ch
is
cr
u
cial
as
its
p
r
im
ar
y
g
o
al
is
to
cr
ea
te
a
d
et
er
r
en
t
ef
f
ec
t,
f
o
s
ter
in
g
awa
r
en
ess
am
o
n
g
d
r
iv
e
r
s
n
o
t
to
cr
o
s
s
r
o
ad
m
ar
k
in
g
s
w
h
en
tr
ain
s
a
r
e
p
ass
in
g
.
E
f
f
ec
tiv
e
u
s
e
o
f
ca
p
ab
le
m
icr
o
c
o
n
tr
o
ll
er
s
an
d
o
p
tim
izin
g
th
e
ca
m
er
a
s
y
s
tem
f
o
r
v
ar
io
u
s
co
n
d
itio
n
s
ar
e
k
ey
asp
ec
ts
f
o
r
f
u
tu
r
e
s
y
s
tem
d
e
v
elo
p
m
e
n
t.
Sev
er
al
s
tu
d
ies
h
av
e
b
ee
n
co
n
d
u
cte
d
to
p
r
ev
en
t
ac
cid
e
n
ts
at
r
ailway
cr
o
s
s
in
g
s
,
f
o
cu
s
in
g
o
n
in
f
r
astru
ctu
r
e
d
ev
el
o
p
m
en
t
with
o
u
t
r
aisi
n
g
awa
r
en
ess
am
o
n
g
r
ailway
cr
o
s
s
in
g
u
s
er
s
.
On
e
s
u
ch
s
tu
d
y
in
v
o
lv
es
th
e
d
etec
tio
n
o
f
r
ailway
tr
ac
k
d
am
ag
e
[
2
3
]
,
t
h
e
d
etec
tio
n
o
f
tr
ain
lo
ca
tio
n
[
2
4
]
,
an
d
th
e
m
o
n
ito
r
in
g
o
f
r
ailway
tr
ac
k
s
[
2
5
]
.
T
h
e
u
s
e
o
f
ca
m
er
as
at
r
ailway
cr
o
s
s
in
g
s
is
em
p
lo
y
ed
f
o
r
th
e
d
ec
en
tr
aliza
tio
n
o
f
r
ailway
s
y
s
tem
s
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Desig
n
o
f a
r
o
a
d
ma
r
kin
g
vio
l
a
tio
n
d
etec
tio
n
s
ystem
a
t ra
ilw
a
y
leve
l c
r
o
s
s
in
g
s
(
Helfy
S
u
s
ila
w
a
ti
)
891
wh
er
e
d
ec
e
n
tr
alizin
g
r
ailway
cr
o
s
s
in
g
s
y
s
tem
s
b
ec
o
m
es
a
l
o
n
g
-
ter
m
s
o
lu
tio
n
to
r
ailway
cr
o
s
s
in
g
is
s
u
es
[
2
6
]
.
Pre
v
io
u
s
s
tu
d
ies
h
av
e
f
o
cu
s
ed
o
n
th
e
d
ev
ices
u
s
ed
at
r
ailway
cr
o
s
s
in
g
s
.
Ho
wev
er
,
th
is
r
esear
ch
aim
s
to
cr
ea
t
e
a
d
eter
r
en
t
e
f
f
ec
t,
p
ar
ticu
lar
ly
f
o
r
d
r
iv
er
s
wh
o
v
i
o
late
r
o
a
d
m
ar
k
in
g
s
u
s
in
g
a
web
ca
m
,
to
p
r
ev
e
n
t
ac
cid
en
ts
.
T
h
e
d
eter
r
en
t
e
f
f
ec
t
g
en
er
ate
d
b
y
th
e
s
y
s
tem
b
ec
o
m
es
th
e
s
tr
en
g
th
o
f
th
e
s
y
s
tem
b
ec
au
s
e
o
n
ce
d
r
iv
er
s
a
r
e
d
eter
r
ed
,
t
h
ey
ar
e
less
lik
ely
to
co
m
m
it v
io
latio
n
s
th
at
c
o
u
ld
l
ea
d
to
ac
cid
en
ts
.
T
h
e
u
s
e
o
f
a
web
ca
m
an
d
R
asp
b
er
r
y
Pi
4
in
t
h
e
in
itial
h
y
p
o
th
esis
is
ex
p
ec
ted
to
y
ield
g
o
o
d
r
esu
lts
.
T
h
e
web
ca
m
ca
n
p
r
o
v
id
e
g
o
o
d
r
esu
lts
in
im
ag
e
ac
q
u
is
itio
n
p
r
o
ce
s
s
es
[
2
7
]
,
a
n
d
th
e
R
asp
b
er
r
y
Pi
4
,
as
h
ar
d
war
e,
ca
n
also
b
e
p
r
o
f
ici
en
tly
u
s
ed
in
d
ig
ital
im
ag
e
p
r
o
ce
s
s
in
g
an
d
as
a
co
n
tr
o
l
f
o
r
th
e
o
v
er
all
s
y
s
tem
[
2
8
]
.
H
o
wev
er
,
in
t
h
e
co
n
d
u
c
ted
r
esear
ch
,
th
e
web
ca
m
d
id
n
o
t
f
u
n
cti
o
n
well
b
ec
au
s
e
it
c
an
o
n
ly
b
e
u
s
ed
in
th
e
d
ay
tim
e
u
n
d
er
clea
r
wea
th
er
co
n
d
itio
n
s
.
T
h
e
web
ca
m
f
a
ils
to
p
r
o
d
u
ce
g
o
o
d
im
ag
es
d
u
r
in
g
n
ig
h
ttime
an
d
r
ain
y
co
n
d
itio
n
s
.
Fu
r
th
er
m
o
r
e
,
th
e
u
s
e
o
f
R
asp
b
er
r
y
Pi
4
al
s
o
p
r
o
v
ed
less
p
r
o
f
icien
t,
ev
i
d
en
ce
d
b
y
th
e
jer
k
y
m
o
v
em
en
t
o
f
o
b
jects
d
u
r
in
g
d
etec
tio
n
an
d
class
if
icatio
n
(
n
o
t
s
m
o
o
th
)
.
A
d
r
awb
ac
k
o
f
th
is
r
esear
ch
is
th
e
r
elativ
ely
lo
n
g
d
etec
tio
n
d
el
ay
.
T
h
is
d
elay
m
ay
o
cc
u
r
b
ec
au
s
e
th
e
R
asp
b
er
r
y
Pi
u
til
ized
p
er
f
o
r
m
s
d
u
al
f
u
n
ctio
n
s
,
n
am
ely
p
r
o
ce
s
s
in
g
im
ag
es
o
b
tain
ed
a
n
d
s
im
u
ltan
eo
u
s
ly
c
o
n
tr
o
llin
g
an
d
r
ec
o
r
d
in
g
d
ata
f
o
r
th
e
s
en
s
o
r
.
T
h
e
in
itial
h
y
p
o
th
esi
s
u
s
in
g
th
e
SS
D
m
eth
o
d
s
h
o
wed
p
r
o
m
is
e
in
ac
cu
r
ately
an
aly
zi
n
g
o
b
ject
d
etec
tio
n
,
as
SS
D
ca
n
s
er
v
e
a
s
an
ef
f
ec
tiv
e
an
d
ef
f
icie
n
t
d
e
tectio
n
m
eth
o
d
,
d
em
o
n
s
tr
atin
g
g
o
o
d
p
er
f
o
r
m
an
ce
ac
r
o
s
s
v
ar
io
u
s
d
atasets
[
2
9
]
.
I
n
th
e
co
n
d
u
cted
r
esear
ch
,
it
was
f
o
u
n
d
th
at
th
e
u
s
e
o
f
SS
D
p
er
f
o
r
m
e
d
well
in
d
etec
tin
g
an
d
class
if
y
in
g
o
b
j
ec
ts
s
u
ch
as
ca
r
s
an
d
m
o
to
r
c
y
cles.
T
h
e
h
y
p
o
t
h
esis
r
eg
ar
d
i
n
g
th
e
u
s
e
o
f
OC
R
s
h
o
wed
p
r
o
m
is
in
g
p
er
f
o
r
m
a
n
ce
f
o
r
licen
s
e
p
late
d
etec
tio
n
[
3
0
]
.
Ho
wev
er
,
i
n
th
e
c
o
n
d
u
c
ted
r
esear
ch
,
OC
R
s
till
h
as
s
o
m
e
s
h
o
r
tco
m
in
g
s
,
in
clu
d
in
g
its
in
ab
ilit
y
to
d
is
ti
n
g
u
is
h
b
etwe
en
ch
ar
ac
ter
s
o
r
n
u
m
b
er
s
th
at
h
av
e
s
im
ilar
s
h
ap
es,
s
u
ch
as d
is
tin
g
u
is
h
in
g
b
etwe
en
th
e
n
u
m
b
er
2
an
d
th
e
letter
Z
.
B
ased
o
n
th
e
r
esear
ch
r
esu
lts
,
th
e
u
ltra
s
o
n
ic
s
en
s
o
r
r
ea
d
in
g
s
u
s
ed
as
tr
ig
g
er
s
f
o
r
web
ca
m
co
n
d
itio
n
s
ex
h
ib
ited
lo
w
er
r
o
r
r
ea
d
in
g
s
o
f
0
.
5
7
3
%
an
d
0
.
5
8
2
%.
I
n
th
e
o
b
ject
class
if
icatio
n
tes
ts
,
th
e
s
y
s
tem
s
u
cc
es
s
f
u
lly
class
if
ied
two
d
if
f
er
en
t
o
b
ject
s
:
ca
r
s
an
d
m
o
to
r
cy
cles.
H
o
wev
er
,
b
o
th
class
if
icatio
n
s
ex
p
e
r
ien
ce
d
s
ig
n
if
ica
n
t
d
elay
s
,
s
p
ec
if
ically
0
.
7
0
2
s
e
co
n
d
s
f
o
r
ca
r
s
an
d
0
.
5
5
4
s
e
co
n
d
s
f
o
r
m
o
to
r
cy
cles.
Du
r
i
n
g
test
in
g
with
p
r
e
-
r
ec
o
r
d
e
d
v
i
d
eo
s
,
th
e
o
b
ject
class
if
icatio
n
p
r
o
ce
s
s
d
id
n
o
t
r
u
n
s
m
o
o
th
l
y
;
p
lay
b
ac
k
o
f
th
e
v
id
eo
ca
u
s
ed
d
elay
s
in
m
o
v
em
en
t,
af
f
ec
ti
n
g
th
e
d
e
tectio
n
an
d
class
if
icatio
n
r
esu
l
ts
.
R
eg
ar
d
in
g
v
eh
icle
licen
s
e
p
late
d
etec
tio
n
an
d
r
ea
d
in
g
test
s
f
o
r
v
io
lato
r
s
,
th
e
s
y
s
tem
ac
h
iev
ed
a
s
u
cc
ess
r
ate
o
f
6
4
.
4
5
%.
T
h
e
ac
cu
r
a
cy
o
f
licen
s
e
p
late
r
ea
d
in
g
r
elied
o
n
th
e
OC
R
'
s
ab
ilit
y
to
in
ter
p
r
et
ch
ar
ac
ter
s
.
Du
r
in
g
test
in
g
,
th
e
s
y
s
tem
e
n
co
u
n
ter
e
d
r
ea
d
in
g
er
r
o
r
s
wh
er
e
t
h
e
n
u
m
b
er
7
w
as
m
is
r
ea
d
as
th
e
letter
Z
,
th
e
letter
D
as
th
e
letter
E
,
an
d
th
e
letter
Q
as
th
e
letter
s
O,
G,
o
r
C
.
Ad
d
itio
n
ally
,
th
e
v
e
h
icle'
s
licen
s
e
p
la
te
h
ad
to
b
e
alig
n
e
d
p
a
r
allel
to
th
e
ca
m
e
r
a
f
o
r
ac
cu
r
ate
r
ea
d
in
g
.
Fu
tu
r
e
r
esear
ch
ca
n
f
o
c
u
s
o
n
h
o
w
to
im
p
r
o
v
e
r
ea
d
ab
ilit
y
d
ela
y
s
an
d
in
c
r
ea
s
e
th
e
ac
cu
r
ac
y
o
f
n
u
m
b
er
p
late
r
ea
d
in
g
s
.
4.
CO
NCLU
SI
O
N
T
h
is
r
esear
ch
h
as
s
u
cc
ess
f
u
ll
y
d
esig
n
ed
a
s
y
s
tem
ca
p
ab
le
o
f
d
etec
tin
g
v
e
h
icles
th
at
v
io
late
r
o
ad
m
ar
k
in
g
s
at
r
ailway
cr
o
s
s
in
g
s
.
T
h
e
co
n
d
u
cted
r
esear
ch
h
a
s
s
u
cc
ess
f
u
lly
co
n
tr
o
lled
th
e
ca
m
er
a
co
n
d
itio
n
s
u
s
in
g
u
ltra
s
o
n
ic
s
en
s
o
r
r
ea
d
in
g
s
as
tr
ig
g
er
s
,
b
u
t
OC
R
n
o
t
b
ein
g
o
p
tim
al
in
tr
a
n
s
latin
g
letter
s
an
d
n
u
m
b
e
r
s
o
n
licen
s
e
p
lates.
Fo
r
f
u
r
th
er
r
e
s
ea
r
ch
,
to
r
e
d
u
ce
d
elay
,
th
e
s
y
s
tem
ca
n
b
e
attem
p
te
d
to
s
ep
ar
ate
th
e
co
n
tr
o
l
f
u
n
ctio
n
a
n
d
th
e
r
ec
o
r
d
in
g
f
u
n
ctio
n
u
s
in
g
two
m
icr
o
p
r
o
ce
s
s
o
r
s
,
o
r
it
ca
n
b
e
attem
p
ted
to
r
ep
lace
th
e
m
icr
o
p
r
o
ce
s
s
o
r
b
ein
g
u
s
ed
.
Ad
d
itio
n
ally
,
th
e
ca
m
er
a'
s
p
o
s
itio
n
m
u
s
t
b
e
p
r
ec
is
ely
alig
n
ed
with
th
e
n
u
m
b
er
p
late
to
en
s
u
r
e
p
r
o
p
er
r
ec
o
g
n
i
tio
n
o
f
th
e
ch
ar
ac
ter
s
o
n
th
e
n
u
m
b
er
p
late.
Var
io
u
s
m
eth
o
d
s
ca
n
b
e
em
p
lo
y
e
d
f
o
r
licen
s
e
p
late
c
h
ar
ac
ter
d
etec
tio
n
to
d
eter
m
in
e
wh
ich
ch
ar
ac
ter
r
ec
o
g
n
itio
n
m
eth
o
d
is
m
o
r
e
ac
cu
r
ate.
An
o
th
er
lim
itatio
n
is
th
at
th
e
s
y
s
tem
d
ev
elo
p
ed
in
th
e
cu
r
r
e
n
t
r
esear
ch
d
o
es
n
o
t
in
clu
d
e
m
ea
s
u
r
es
to
s
ec
u
r
e
th
e
d
ata
o
f
licen
s
e
p
lates
s
to
r
e
d
in
th
e
s
y
s
tem
.
T
o
ad
d
r
ess
th
e
s
h
o
r
tco
m
i
n
g
s
o
f
th
is
r
esear
c
h
,
s
ev
er
al
s
tep
s
ca
n
b
e
tak
en
.
On
e
ap
p
r
o
ac
h
is
to
r
ep
lace
o
r
p
o
s
s
ib
ly
ad
d
m
icr
o
co
n
tr
o
ller
s
,
with
o
n
e
d
ed
icate
d
to
im
ag
e
p
r
o
ce
s
s
in
g
an
d
an
o
th
e
r
f
o
r
s
y
s
tem
co
n
tr
o
l.
Ad
d
itio
n
ally
,
co
n
s
id
er
atio
n
c
o
u
ld
b
e
g
iv
e
n
to
u
p
g
r
ad
in
g
th
e
ca
m
er
a
to
en
ab
le
th
e
s
y
s
tem
to
p
e
r
f
o
r
m
d
etec
tio
n
an
d
c
lass
if
icatio
n
u
n
d
er
v
ar
io
u
s
c
o
n
d
itio
n
s
,
s
u
c
h
as
n
ig
h
ttime
o
r
r
ain
y
wea
th
er
.
Fu
tu
r
e
r
esear
c
h
co
u
ld
also
f
o
cu
s
o
n
en
h
an
cin
g
d
ata
s
ec
u
r
ity
m
ea
s
u
r
es
f
o
r
licen
s
e
p
late
d
ata,
s
u
c
h
as
e
n
cr
y
p
tin
g
licen
s
e
p
late
in
f
o
r
m
atio
n
o
r
im
p
r
o
v
in
g
s
y
s
tem
s
ec
u
r
ity
o
v
er
all.
M
o
r
eo
v
e
r
,
ch
allen
g
es
p
o
s
ed
b
y
en
v
ir
o
n
m
en
tal
co
n
d
itio
n
s
an
d
v
ar
y
in
g
l
ig
h
tin
g
le
v
els
n
ee
d
to
b
e
th
o
r
o
u
g
h
ly
in
v
esti
g
ated
an
d
r
eso
lv
e
d
.
ACK
NO
WL
E
DG
E
M
E
NT
S
We
ex
ten
d
our
g
r
atitu
d
e
to
th
e
f
ac
u
lty
o
f
e
n
g
in
ee
r
i
n
g
at
th
e
Un
iv
er
s
ity
o
f
Gar
u
t
f
o
r
th
eir
ass
is
tan
ce
an
d
s
u
p
p
o
r
t,
wh
ich
h
av
e
b
ee
n
in
s
tr
u
m
en
tal
in
c
o
m
p
letin
g
th
is
r
esear
ch
a
n
d
ar
ticles
ef
f
ec
tiv
ely
,
an
d
to
th
e
Dep
ar
tm
en
t
o
f
Me
ch
atr
o
n
ics
I
n
ter
n
atio
n
al
I
s
lam
ic
Un
iv
e
r
s
ity
Ma
lay
s
ia
as
p
ar
t
o
f
th
e
co
llab
o
r
atio
n
in
p
r
ep
ar
in
g
th
is
ar
ticle.
We
als
o
ex
p
r
ess
m
y
ap
p
r
ec
iatio
n
to
th
o
s
e
wh
o
h
av
e
ass
is
ted
,
in
clu
d
in
g
t
h
e
cr
o
s
s
b
ar
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
1
,
Feb
r
u
ar
y
20
25
:
8
8
3
-
893
892
g
u
ar
d
wh
o
g
r
an
ted
p
er
m
is
s
io
n
f
o
r
th
e
v
id
eo
to
b
e
r
ec
o
r
d
ed
d
u
r
in
g
th
e
o
p
er
atio
n
o
f
th
e
cr
o
s
s
b
ar
,
as
well
as
to
m
y
co
lleag
u
es wh
o
h
av
e
co
n
s
i
s
ten
tly
o
f
f
er
ed
th
eir
s
u
p
p
o
r
t.
RE
F
E
R
E
NC
E
S
[
1
]
A
.
I
.
D
a
v
y
d
o
v
,
M
.
M
.
S
o
k
o
l
o
v
,
a
n
d
K
.
I
.
K
o
r
n
i
e
n
k
o
,
“
S
e
ma
n
t
i
c
mo
d
e
l
o
f
i
n
t
e
l
l
i
g
e
n
t
r
a
i
l
w
a
y
c
r
o
ssi
n
g
safe
t
y
ma
n
a
g
e
m
e
n
t
s
y
st
e
m,”
T
ra
n
s
p
o
rt
a
t
i
o
n
Re
s
e
a
r
c
h
Pr
o
c
e
d
i
a
,
v
o
l
.
6
1
,
p
p
.
3
3
3
–
3
3
9
,
J
a
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
t
r
p
r
o
.
2
0
2
2
.
0
1
.
0
5
4
.
[
2
]
S
.
V
e
l
a
n
t
i
a
,
A
.
W
i
d
y
a
n
t
i
,
a
n
d
T
.
Y
u
d
h
i
st
i
r
a
,
“
P
r
e
v
a
l
e
n
c
e
o
f
a
n
d
i
n
t
e
n
t
b
e
h
i
n
d
m
o
t
o
r
c
y
c
l
i
s
t
s’
v
i
o
l
a
t
i
o
n
s
a
t
r
a
i
l
w
a
y
c
r
o
ss
i
n
g
s
i
n
I
n
d
o
n
e
si
a
:
M
o
d
e
l
i
n
g
b
e
h
a
v
i
o
r
a
n
d
l
e
a
r
n
i
n
g
l
e
ss
o
n
s
f
r
o
m
a
d
e
v
e
l
o
p
i
n
g
c
o
u
n
t
r
y
,
”
I
AT
S
S
R
e
se
a
rc
h
,
v
o
l
.
4
8
,
n
o
.
1
,
p
p
.
2
7
–
3
9
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
a
t
ssr
.
2
0
2
4
.
0
1
.
0
0
2
.
[
3
]
R
.
B
r
i
d
g
e
l
a
l
l
a
n
d
D
.
D
.
T
o
l
l
i
v
e
r
,
“
R
a
i
l
r
o
a
d
a
c
c
i
d
e
n
t
a
n
a
l
y
s
i
s
b
y
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
n
a
t
u
r
a
l
l
a
n
g
u
a
g
e
p
r
o
c
e
ss
i
n
g
,
”
J
o
u
r
n
a
l
o
f
Ra
i
l
T
r
a
n
sp
o
rt
P
l
a
n
n
i
n
g
a
n
d
M
a
n
a
g
e
m
e
n
t
,
v
o
l
.
2
9
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
r
t
p
m.
2
0
2
3
.
1
0
0
4
2
9
.
[
4
]
K
.
S
h
i
mu
r
a
,
Y
.
To
m
i
o
k
a
,
a
n
d
Q
.
Zh
a
o
,
“
A
d
i
st
a
n
c
e
e
st
i
ma
t
i
o
n
me
t
h
o
d
t
o
r
a
i
l
w
a
y
c
r
o
ss
i
n
g
u
s
i
n
g
w
a
r
n
i
n
g
si
g
n
s,”
i
n
Pro
c
e
e
d
i
n
g
s
-
2
0
2
1
I
EEE
1
4
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
S
y
m
p
o
si
u
m
o
n
Em
b
e
d
d
e
d
M
u
l
t
i
c
o
re/
M
a
n
y
-
C
o
r
e
S
y
st
e
m
s
-
on
-
C
h
i
p
,
MC
S
o
C
2
0
2
1
,
2
0
2
1
,
p
p
.
1
7
8
–
1
8
1
,
d
o
i
:
1
0
.
1
1
0
9
/
M
C
S
o
C
5
1
1
4
9
.
2
0
2
1
.
0
0
0
3
4
.
[
5
]
F
.
G
u
o
,
Z.
J
i
a
n
g
,
Y
.
W
a
n
g
,
C
.
C
h
e
n
,
a
n
d
Y
.
Q
i
a
n
,
“
D
e
n
se
t
r
a
f
f
i
c
d
e
t
e
c
t
i
o
n
a
t
h
i
g
h
w
a
y
-
r
a
i
l
r
o
a
d
g
r
a
d
e
c
r
o
ssi
n
g
s
,
”
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
I
n
t
e
l
l
i
g
e
n
t
T
r
a
n
s
p
o
rt
a
t
i
o
n
S
y
s
t
e
m
s
,
v
o
l
.
2
3
,
n
o
.
9
,
p
p
.
1
5
4
9
8
–
1
5
5
1
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
TS.2
0
2
2
.
3
1
4
0
9
4
8
.
[
6
]
D
.
V
Ef
a
n
o
v
,
G
.
V
O
sa
d
c
h
i
i
,
a
n
d
V
.
V
K
h
o
r
o
s
h
e
v
,
“
N
e
w
s
t
a
g
e
i
n
safe
t
y
t
r
a
f
f
i
c
c
o
n
t
r
o
l
t
e
c
h
n
o
l
o
g
i
e
s
d
e
v
e
l
o
p
m
e
n
t
:
D
i
g
i
t
a
l
r
a
i
l
r
o
a
d
c
r
o
ssi
n
g
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
2
0
1
9
I
n
t
e
rn
a
t
i
o
n
a
l
R
u
ss
i
a
n
A
u
t
o
m
a
t
i
o
n
C
o
n
f
e
r
e
n
c
e
,
R
u
sA
u
t
o
C
o
n
2
0
1
9
,
2
0
1
9
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
R
U
S
A
U
TO
C
O
N
.
2
0
1
9
.
8
8
6
7
7
0
0
.
[
7
]
F
.
G
u
o
,
Y
.
W
a
n
g
,
a
n
d
Y
.
Q
i
a
n
,
“
C
o
mp
u
t
e
r
v
i
s
i
o
n
-
b
a
se
d
a
p
p
r
o
a
c
h
f
o
r
s
mart
t
r
a
f
f
i
c
c
o
n
d
i
t
i
o
n
a
ss
e
ssm
e
n
t
a
t
t
h
e
r
a
i
l
r
o
a
d
g
r
a
d
e
c
r
o
ssi
n
g
,
”
A
d
v
a
n
c
e
d
En
g
i
n
e
e
ri
n
g
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
5
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
e
i
.
2
0
2
1
.
1
0
1
4
5
6
.
[
8
]
P
.
K
u
d
l
a
c
i
k
a
n
d
T.
E.
W
e
so
l
o
w
s
k
i
,
“
O
b
st
a
c
l
e
d
e
t
e
c
t
i
o
n
a
l
g
o
r
i
t
h
m
f
o
r
r
a
i
l
r
o
a
d
-
r
o
a
d
c
r
o
ss
i
n
g
s
b
a
s
e
d
o
n
v
i
d
e
o
st
r
e
a
m
a
n
a
l
y
si
s,”
Pro
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
2
5
,
p
p
.
1
5
5
2
–
1
5
6
1
,
Ja
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s
.
2
0
2
3
.
1
0
.
1
4
4
.
[
9
]
W
.
X
i
o
n
g
,
“
R
e
se
a
r
c
h
o
n
f
i
r
e
d
e
t
e
c
t
i
o
n
a
n
d
i
m
a
g
e
i
n
f
o
r
ma
t
i
o
n
p
r
o
c
e
ss
i
n
g
sy
st
e
m
b
a
se
d
o
n
i
ma
g
e
p
r
o
c
e
ss
i
n
g
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
2
0
2
0
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
A
d
v
a
n
c
e
i
n
Am
b
i
e
n
t
C
o
m
p
u
t
i
n
g
a
n
d
I
n
t
e
l
l
i
g
e
n
c
e
,
I
C
AA
C
I
2
0
2
0
,
2
0
2
0
,
p
p
.
1
0
6
–
1
0
9
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
A
C
I
5
0
7
3
3
.
2
0
2
0
.
0
0
0
2
7
.
[
1
0
]
J.
Li
,
B
.
M
a
,
a
n
d
H
.
D
o
n
g
,
“
D
e
t
e
c
t
i
o
n
o
f
t
h
e
r
a
i
l
p
r
o
f
i
l
e
w
e
a
r
b
a
se
d
o
n
i
ma
g
e
p
r
o
c
e
ss
i
n
g
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
2
0
2
0
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
P
o
w
e
r,
I
n
t
e
l
l
i
g
e
n
t
C
o
m
p
u
t
i
n
g
a
n
d
S
y
st
e
m
s
,
I
C
PI
C
S
2
0
2
0
,
2
0
2
0
,
p
p
.
5
8
2
–
5
8
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
P
I
C
S
5
0
2
8
7
.
2
0
2
0
.
9
2
0
1
9
5
6
.
[
1
1
]
D
.
M
o
g
a
a
n
d
I
.
F
i
l
i
p
,
“
R
o
l
e
o
f
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
t
e
c
h
n
i
q
u
e
s
i
n
a
c
t
i
v
e
s
a
f
e
t
y
u
si
n
g
i
ma
g
e
p
r
o
c
e
ssi
n
g
f
o
r
a
u
t
o
n
o
m
o
u
s
d
r
i
v
i
n
g
v
e
h
i
c
l
e
s,”
i
n
S
A
C
I
2
0
2
2
-
I
E
EE
1
6
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
S
y
m
p
o
s
i
u
m
o
n
A
p
p
l
i
e
d
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
I
n
f
o
rm
a
t
i
c
s,
Pro
c
e
e
d
i
n
g
s
,
2
0
2
2
,
p
p
.
2
5
3
–
2
5
8
,
d
o
i
:
1
0
.
1
1
0
9
/
S
A
C
I
5
5
6
1
8
.
2
0
2
2
.
9
9
1
9
5
1
3
.
[
1
2
]
C
.
J.
L.
C
h
a
n
,
E
.
J
.
A
.
R
e
y
e
s
,
N
.
B
.
L
i
n
sa
n
g
a
n
,
a
n
d
R
.
A
.
J
u
a
n
a
t
a
s
,
“
R
e
a
l
-
t
i
me
d
e
t
e
c
t
i
o
n
o
f
a
q
u
a
r
i
u
m
f
i
s
h
s
p
e
c
i
e
s
u
s
i
n
g
Y
O
LO
v
4
-
t
i
n
y
o
n
R
a
s
p
b
e
r
r
y
P
i
4
,
”
i
n
4
t
h
I
E
EE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
i
n
E
n
g
i
n
e
e
ri
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
I
I
C
AI
ET
2
0
2
2
,
2
0
2
2
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
I
C
A
I
ET5
5
1
3
9
.
2
0
2
2
.
9
9
3
6
7
9
0
.
[
1
3
]
R
.
Ta
r
u
n
a
n
d
B
.
P
.
Es
t
h
e
r
,
“
R
e
a
l
-
t
i
m
e
r
e
g
i
o
n
a
l
r
o
a
d
si
g
n
d
e
t
e
c
t
i
o
n
a
n
d
i
d
e
n
t
i
f
i
c
a
t
i
o
n
u
s
i
n
g
R
a
s
p
b
e
r
r
y
P
i
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
1
st
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
N
e
t
w
o
r
k
i
n
g
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
s
2
0
2
3
,
I
C
N
W
C
2
0
2
3
,
2
0
2
3
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
N
W
C
5
7
8
5
2
.
2
0
2
3
.
1
0
1
2
7
3
7
0
.
[
1
4
]
M
.
Y
i
l
d
i
r
i
m,
O
.
K
a
r
a
d
u
ma
n
,
a
n
d
H
.
K
u
r
u
m,
“
R
e
a
l
-
t
i
me
i
ma
g
e
a
n
d
v
i
d
e
o
p
r
o
c
e
ss
i
n
g
a
p
p
l
i
c
a
t
i
o
n
s
u
s
i
n
g
R
a
s
p
b
e
r
r
y
P
i
,
”
i
n
1
s
t
I
EE
E
I
n
d
u
st
r
i
a
l
El
e
c
t
r
o
n
i
c
s
S
o
c
i
e
t
y
A
n
n
u
a
l
O
n
-
L
i
n
e
C
o
n
f
e
re
n
c
e
,
2
0
2
2
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
O
N
C
O
N
5
6
9
8
4
.
2
0
2
2
.
1
0
1
2
7
0
3
4
.
[
1
5
]
F
.
A
n
d
i
k
a
a
n
d
Y
.
B
a
n
d
u
n
g
,
“
R
o
a
d
d
a
ma
g
e
c
l
a
ssi
f
i
c
a
t
i
o
n
u
s
i
n
g
S
S
D
M
o
b
i
l
e
n
e
t
w
i
t
h
i
m
a
g
e
e
n
h
a
n
c
e
me
n
t
,
”
i
n
I
C
C
o
S
I
T
E
2
0
2
3
-
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
a
n
d
En
g
i
n
e
e
ri
n
g
:
D
i
g
i
t
a
l
T
r
a
n
s
f
o
rm
a
t
i
o
n
S
t
r
a
t
e
g
y
i
n
Fa
c
i
n
g
t
h
e
VU
C
A
a
n
d
T
U
N
A
Er
a
,
2
0
2
3
,
p
p
.
5
4
0
–
5
4
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
o
S
I
TE5
7
6
4
1
.
2
0
2
3
.
1
0
1
2
7
7
6
3
.
[
1
6
]
A
.
H
e
r
e
d
i
a
a
n
d
G
.
B
a
r
r
o
s
-
G
a
v
i
l
a
n
e
s,
“
C
o
mp
a
r
i
n
g
S
V
M
a
n
d
S
S
D
f
o
r
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
v
e
h
i
c
l
e
s
a
n
d
p
e
d
e
st
r
i
a
n
s
f
o
r
e
d
g
e
c
o
m
p
u
t
i
n
g
,
”
i
n
2
0
1
9
I
EEE
C
o
l
o
m
b
i
a
n
C
o
n
f
e
re
n
c
e
o
n
A
p
p
l
i
c
a
t
i
o
n
s
i
n
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
C
o
l
C
A
C
I
2
0
1
9
-
Pr
o
c
e
e
d
i
n
g
s
,
2
0
1
9
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
C
o
l
C
A
C
I
.
2
0
1
9
.
8
7
8
1
9
8
9
.
[
1
7
]
M
.
R
.
C
.
N
i
l
u
c
k
s
h
i
n
i
a
n
d
M
.
F
.
M
.
F
i
r
d
h
o
u
s,
“
A
u
t
o
ma
t
i
c
n
u
m
b
e
r
p
l
a
t
e
d
e
t
e
c
t
i
o
n
u
si
n
g
H
a
a
r
-
C
a
sc
a
d
e
a
l
g
o
r
i
t
h
m
p
r
o
p
o
se
d
f
o
r
S
r
i
l
a
n
k
a
n
c
o
n
t
e
x
t
,
”
i
n
I
C
A
RC
2
0
2
2
-
2
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
A
d
v
a
n
c
e
d
Re
s
e
a
rc
h
i
n
C
o
m
p
u
t
i
n
g
:
T
o
w
a
rd
s
a
D
i
g
i
t
a
l
l
y
Em
p
o
w
e
r
e
d
S
o
c
i
e
t
y
,
2
0
2
2
,
p
p
.
2
4
8
–
2
5
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
R
C
5
4
4
8
9
.
2
0
2
2
.
9
7
5
3
9
1
5
.
[
1
8
]
M
.
K
r
i
s
h
n
a
m
o
o
r
t
h
i
,
K
.
P
.
S
.
R
a
m
,
M
.
S
a
t
h
y
a
n
,
a
n
d
T
.
V
a
sa
n
t
h
,
“
I
mp
r
o
v
i
n
g
o
p
t
i
c
a
l
c
h
a
r
a
c
t
e
r
r
e
c
o
g
n
i
t
i
o
n
(
O
C
R
)
a
c
c
u
r
a
c
y
u
si
n
g
mu
l
t
i
-
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
(
M
LP)
,
”
i
n
7
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
T
r
e
n
d
s
i
n
El
e
c
t
r
o
n
i
c
s
a
n
d
I
n
f
o
rm
a
t
i
c
s
,
I
C
O
EI
2
0
2
3
-
Pro
c
e
e
d
i
n
g
s
,
2
0
2
3
,
p
p
.
1
6
4
2
–
1
6
4
7
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
O
EI
5
6
7
6
5
.
2
0
2
3
.
1
0
1
2
5
6
0
3
.
[
1
9
]
R
.
P
a
r
t
h
i
b
a
n
,
R
.
Ez
h
i
l
a
r
a
s
i
,
a
n
d
D
.
S
a
r
a
v
a
n
a
n
,
“
O
p
t
i
c
a
l
c
h
a
r
a
c
t
e
r
r
e
c
o
g
n
i
t
i
o
n
f
o
r
En
g
l
i
s
h
h
a
n
d
w
r
i
t
t
e
n
t
e
x
t
u
si
n
g
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
i
n
2
0
2
0
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
y
s
t
e
m
,
C
o
m
p
u
t
a
t
i
o
n
,
A
u
t
o
m
a
t
i
o
n
a
n
d
N
e
t
w
o
rk
i
n
g
,
I
C
S
C
A
N
2
0
2
0
,
2
0
2
0
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
S
C
A
N
4
9
4
2
6
.
2
0
2
0
.
9
2
6
2
3
7
9
.
[
2
0
]
S
.
P
.
S
a
l
i
m,
A
.
J
a
mes
,
a
n
d
C
.
S
a
r
a
v
a
n
a
n
,
“
P
r
o
p
o
se
d
m
e
t
h
o
d
t
o
M
a
l
a
y
a
l
a
m
h
a
n
d
w
r
i
t
t
e
n
c
h
a
r
a
c
t
e
r
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
r
e
s
i
d
u
a
l
n
e
t
w
o
r
k
e
n
h
a
n
c
e
d
b
y
m
u
l
t
i
-
s
c
a
l
e
d
f
e
a
t
u
r
e
s,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
1
st
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
n
o
v
a
t
i
o
n
s
i
n
I
n
f
o
rm
a
t
i
o
n
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
I
C
I
I
C
T
2
0
1
9
,
2
0
1
9
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
I
C
T1
.
2
0
1
9
.
8
7
4
1
4
4
4
.
[
2
1
]
B
.
D
e
ss
a
i
a
n
d
A
.
P
a
t
i
l
,
“
A
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
o
p
t
i
c
a
l
c
h
a
r
a
c
t
e
r
r
e
c
o
g
n
i
t
i
o
n
o
f
h
a
n
d
w
r
i
t
t
e
n
D
e
v
a
n
a
g
a
r
i
scri
p
t
,
”
i
n
2
0
1
9
2
n
d
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
l
l
i
g
e
n
t
C
o
m
p
u
t
i
n
g
,
I
n
s
t
r
u
m
e
n
t
a
t
i
o
n
a
n
d
C
o
n
t
ro
l
T
e
c
h
n
o
l
o
g
i
e
s,
I
C
I
C
I
C
T
2
0
1
9
,
2
0
1
9
,
p
p
.
1
1
6
0
–
1
1
6
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
C
I
C
T4
6
0
0
8
.
2
0
1
9
.
8
9
9
3
3
4
2
.
[
2
2
]
M
.
A
.
Za
r
y
a
b
a
n
d
C
.
R
.
N
g
,
“
O
p
t
i
c
a
l
c
h
a
r
a
c
t
e
r
r
e
c
o
g
n
i
t
i
o
n
f
o
r
me
d
i
c
a
l
r
e
c
o
r
d
s
d
i
g
i
t
i
z
a
t
i
o
n
w
i
t
h
d
e
e
p
l
e
a
r
n
i
n
g
,
”
i
n
P
ro
c
e
e
d
i
n
g
s
-
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
m
a
g
e
P
ro
c
e
ssi
n
g
,
I
C
I
P
,
2
0
2
3
,
p
p
.
3
2
6
0
–
3
2
6
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
P
4
9
3
5
9
.
2
0
2
3
.
1
0
2
2
2
0
3
8
.
[
2
3
]
G
.
H
a
r
i
k
a
,
N
.
S
w
a
t
h
i
,
S
.
M
.
N
i
k
h
i
l
,
C
.
J.
T
e
j
a
,
a
n
d
P
.
K
.
K
u
m
a
r
,
“
A
u
t
o
m
a
t
i
c
r
a
i
l
w
a
y
t
r
a
c
k
c
r
a
c
k
d
e
t
e
c
t
i
o
n
a
n
d
a
l
e
r
t
s
y
st
e
m,”
2
0
2
3
I
n
n
o
v
a
t
i
o
n
s
i
n
Po
w
e
r
a
n
d
Ad
v
a
n
c
e
d
C
o
m
p
u
t
i
n
g
T
e
c
h
n
o
l
o
g
i
e
s,
i
-
PAC
T
2
0
2
3
,
p
p
.
1
–
7
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
-
P
A
C
T5
8
6
4
9
.
2
0
2
3
.
1
0
4
3
4
8
2
2
.
[
2
4
]
K
.
R
.
A
h
me
d
,
M
.
A
.
H
o
ssa
i
n
,
A
.
A
k
t
e
r
,
a
n
d
L
.
A
k
t
h
a
r
,
“
A
se
c
u
r
e
a
u
t
o
m
a
t
e
d
l
e
v
e
l
c
r
o
s
si
n
g
a
n
d
t
r
a
i
n
d
e
t
e
c
t
i
o
n
s
y
st
e
m
f
o
r
B
a
n
g
l
a
d
e
s
h
R
a
i
l
w
a
y
,
”
i
n
2
0
2
2
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
A
d
v
a
n
c
e
m
e
n
t
i
n
El
e
c
t
r
i
c
a
l
a
n
d
E
l
e
c
t
r
o
n
i
c
E
n
g
i
n
e
e
ri
n
g
,
I
C
A
EEE
2
0
2
2
,
2
0
2
2
,
p
p
.
1
–
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
EEE5
4
9
5
7
.
2
0
2
2
.
9
8
3
6
3
6
1
.
[
2
5
]
M
.
Y
i
l
ma
z
e
r
a
n
d
M
.
K
a
r
a
k
o
se
,
“
R
a
i
l
w
a
y
c
o
n
d
i
t
i
o
n
m
o
n
i
t
o
r
i
n
g
a
n
d
f
a
u
l
t
d
e
t
e
c
t
i
o
n
b
a
se
d
o
n
Y
O
LO
v
4
,
”
i
n
2
0
2
2
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
n
o
v
a
t
i
o
n
a
n
d
I
n
t
e
l
l
i
g
e
n
c
e
f
o
r
I
n
f
o
rm
a
t
i
c
s
,
C
o
m
p
u
t
i
n
g
,
a
n
d
T
e
c
h
n
o
l
o
g
i
e
s,
3
I
C
T
2
0
2
2
,
2
0
2
2
,
p
p
.
4
3
9
–
4
4
3
,
d
o
i
:
1
0
.
1
1
0
9
/
3
I
C
T
5
6
5
0
8
.
2
0
2
2
.
9
9
9
0
6
4
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.