I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
8
,
No
.
3
,
J
u
n
e
201
8
,
p
p
.
1522
~
1
5
2
9
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
8
i
3
.
p
p
1
5
2
2
-
1529
1522
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/
jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JE
C
E
Aut
o
no
m
o
us T
ra
f
fic
Sig
na
l Con
trol
u
sing
Decisio
n T
ree
Rit
hes
h R
.
N
.
,
Vig
nes
h R,
A
na
la
M
.
R
.
R
V
C
o
ll
e
g
e
o
f
En
g
in
e
e
rin
g
,
Ba
n
g
a
lo
re
,
In
d
o
n
e
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
1
7
,
2
0
1
7
R
ev
i
s
ed
Dec
2
6
,
2
0
1
7
A
cc
ep
ted
J
an
3
,
2
0
1
8
T
h
e
o
b
jec
ti
v
e
o
f
th
is
p
a
p
e
r
is
to
in
tro
d
u
c
e
a
n
e
f
fe
c
ti
v
e
a
n
d
e
f
f
icie
n
t
w
a
y
o
f
traff
ic
sig
n
a
l
li
g
h
t
c
o
n
tr
o
l
to
o
p
ti
m
iz
e
th
e
traff
ic
sig
n
a
l
d
u
ra
ti
o
n
a
c
ro
ss
e
a
c
h
lan
e
s
a
n
d
th
e
re
b
y
,
to
m
in
i
m
ize
o
r
c
o
m
p
lete
l
y
e
li
m
in
a
te
tra
ff
ic
c
o
n
g
e
stio
n
.
T
h
is
p
a
p
e
r
in
tro
d
u
c
e
s
a
n
e
w
a
p
p
r
o
a
c
h
to
re
so
lv
e
th
e
traff
ic
c
o
n
g
e
stio
n
p
ro
b
lem
a
t
ju
n
c
ti
o
n
s
b
y
m
a
k
in
g
u
se
o
f
d
e
c
isio
n
tree
s.
T
h
e
v
e
h
icle
c
o
u
n
t
in
th
e
re
a
l
ti
m
e
traff
ic
v
id
e
o
is
d
e
ter
m
in
e
d
b
y
I
m
a
g
e
P
ro
c
e
ss
in
g
tec
h
n
iq
u
e
.
T
h
is
in
f
o
rm
a
ti
o
n
is
f
e
d
to
th
e
d
e
c
isio
n
tree
b
a
se
d
o
n
w
h
ich
th
e
d
e
c
isio
n
is
m
a
d
e
re
g
a
rd
in
g
th
e
sta
tu
s
o
f
tr
a
ff
i
c
sig
n
a
l
li
g
h
ts
o
f
e
a
c
h
lan
e
a
t
th
e
ju
n
c
ti
o
n
a
t
a
n
y
g
iv
e
n
in
sta
n
t
o
f
ti
m
e
.
K
ey
w
o
r
d
:
B
ac
k
g
r
o
u
n
d
s
u
b
tr
ac
tio
n
Dec
is
io
n
tr
ee
Ob
j
ec
t
d
etec
tio
n
T
r
af
f
ic
co
n
g
e
s
tio
n
Veh
icle
co
u
n
t
Co
p
y
rig
h
t
©
2
0
1
8
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
An
ala
M
.
R
.
,
Dep
ar
te
m
en
t o
f
C
o
m
p
u
ter
Sci
en
ce
an
d
E
n
g
i
n
ee
r
in
g
,
R
V
C
o
lle
g
e
o
f
E
n
g
i
n
ee
r
in
g
,
R
.
V.
Vid
y
a
n
ik
e
tan
P
o
s
t,
M
y
s
u
r
u
R
o
ad
,
B
en
g
al
u
r
u
–
5
6
0
0
5
9
,
I
n
d
ia.
E
m
ail
:
a
n
ala
m
r
@
r
v
ce
.
ed
u
.
in
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
p
r
im
ar
y
i
n
te
n
s
io
n
o
f
t
h
e
t
r
af
f
ic
s
i
g
n
al
l
ig
h
t
s
is
to
f
ac
ilit
a
te
th
e
tr
an
s
p
o
r
tatio
n
o
r
m
o
v
e
m
en
t o
f
t
h
e
v
eh
ic
les
in
j
u
n
c
tio
n
s
w
it
h
o
u
t
cr
ea
tin
g
a
n
y
ch
ao
s
o
r
ad
v
er
s
el
y
af
f
ec
ti
n
g
t
h
e
n
o
r
m
al
d
a
y
to
d
ay
lif
e
o
f
p
eo
p
le.
E
f
f
icien
t
w
o
r
k
i
n
g
o
f
t
h
e
s
a
m
e
is
an
ess
e
n
tia
l
p
ar
t
f
o
r
s
m
o
o
th
tr
an
s
p
o
r
tatio
n
,
esp
ec
iall
y
i
n
d
en
s
el
y
p
o
p
u
lated
m
etr
o
p
o
litan
citie
s
.
B
u
t
in
to
d
ay
‟
s
ag
e
o
f
g
lo
b
aliza
tio
n
t
h
e
n
u
m
b
er
o
f
v
e
h
icles
s
tep
p
in
g
o
n
to
t
h
e
r
o
ad
h
a
s
elev
ated
b
y
s
i
g
n
i
f
ica
n
t
a
m
o
u
n
t
lead
in
g
to
tr
af
f
ic
co
n
g
esti
o
n
p
r
o
b
lem
.
T
r
af
f
ic
co
n
g
e
s
tio
n
h
as
e
m
er
g
ed
as
o
n
e
o
f
th
e
m
o
s
t
s
er
io
u
s
p
r
o
b
lem
s
f
ac
ed
b
y
m
o
s
t
o
f
th
e
co
u
n
tr
ie
s
to
d
ay
.
I
t
h
as
ad
v
er
s
e
e
f
f
ec
t
o
n
t
h
e
p
h
y
s
ical
a
n
d
m
en
tal
h
ea
l
t
h
o
f
t
h
e
p
eo
p
le,
t
h
e
en
v
ir
o
n
m
e
n
t,
a
n
d
is
o
n
e
o
f
t
h
e
m
ai
n
r
ea
s
o
n
s
f
o
r
t
h
e
ca
u
s
e
o
f
ac
cid
en
t
s
.
All o
f
th
ese
p
r
o
b
lem
s
ca
n
b
e
m
i
n
i
m
ized
a
n
d
i
n
s
o
m
e
ca
s
es
c
o
m
p
lete
l
y
eli
m
i
n
ated
b
y
in
c
o
r
p
o
r
atin
g
th
e
r
ig
h
t
m
et
h
o
d
o
lo
g
y
w
h
ic
h
co
n
tr
o
ls
a
n
d
co
o
r
d
in
ates
f
lo
w
o
f
v
e
h
ic
le
s
o
n
t
h
e
r
o
ad
in
a
n
e
f
f
icie
n
t
m
an
n
er
,
a
n
d
th
er
eb
y
m
ak
e
s
o
p
ti
m
u
m
u
tili
za
tio
n
o
f
ti
m
e
a
n
d
av
ailab
le
s
p
ac
e
f
o
r
v
eh
ic
le
tr
an
s
p
o
r
tatio
n
.
T
h
is
p
ap
er
in
tr
o
d
u
ce
s
a
n
ef
f
icien
t
w
a
y
f
o
r
tr
a
f
f
ic
s
i
g
n
a
l
li
g
h
t
co
n
tr
o
l
u
s
in
g
d
ec
i
s
io
n
tr
ee
s
.
T
h
e
d
ec
is
io
n
tr
ee
m
o
d
eled
h
e
r
e
i
s
m
ai
n
l
y
b
ased
o
n
th
e
n
u
m
b
er
o
f
v
e
h
i
cles
o
n
ea
ch
la
n
e
at
t
h
e
j
u
n
ct
io
n
.
T
h
e
co
u
n
t
o
f
t
h
e
n
u
m
b
er
o
f
v
e
h
icles
ac
r
o
s
s
ea
ch
la
n
e
at
t
h
e
j
u
n
ctio
n
is
o
b
tain
ed
b
y
u
s
i
n
g
I
m
a
g
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
es.
T
h
e
d
ec
is
io
n
r
eg
ar
d
in
g
th
e
s
tat
u
s
(
i.e
.
co
lo
r
)
o
f
th
e
s
i
g
n
al
l
ig
h
ts
ac
r
o
s
s
ea
ch
lan
e
s
o
f
t
h
e
j
u
n
ct
io
n
s
is
m
ad
e
b
ased
o
n
th
e
n
u
m
b
er
o
f
v
e
h
icles
o
n
ea
ch
la
n
es
a
n
d
,
ac
co
r
d
in
g
l
y
t
h
e
s
ta
tu
s
o
f
th
e
s
i
g
n
al
li
g
h
ts
ar
e
ch
a
n
g
ed
i
n
r
ea
l
t
i
m
e
to
ac
h
iev
e
m
a
x
i
m
u
m
th
r
o
u
g
h
p
u
t
i
n
ter
m
s
o
f
n
u
m
b
er
o
f
v
eh
icles
clea
r
i
n
g
/cr
o
s
s
i
n
g
th
e
j
u
n
c
tio
n
,
w
it
h
m
in
i
m
u
m
ch
a
n
ce
s
o
f
tr
a
f
f
ic
j
am
.
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
I
n
telli
g
en
t
tr
an
s
p
o
r
tatio
n
s
y
s
t
e
m
s
(
I
T
S)
m
ai
n
l
y
ai
m
at
p
r
o
v
id
in
g
b
etter
q
u
ali
t
y
o
f
tr
a
f
f
ic
co
n
g
es
tio
n
co
n
tr
o
l.
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
-
8708
A
u
t
o
n
o
mo
u
s
Tr
a
ffic S
ig
n
a
l Co
n
tr
o
l u
s
in
g
Dec
is
io
n
Tr
ee
(
A
n
a
la
M.
R
.
)
1523
T
h
e
w
o
r
ld
h
as see
n
h
u
g
e
ad
v
a
n
ce
m
e
n
t
s
in
I
T
S so
m
e
o
f
t
h
e
m
ar
e
f
o
llo
w
s
:
A
m
eth
o
d
o
lo
g
y
i
n
w
h
ich
t
h
e
s
y
s
te
m
d
etec
ts
an
d
co
n
tr
o
ls
t
h
e
tr
af
f
ic
co
n
g
est
io
n
in
r
ea
l
ti
m
e
b
ased
o
n
th
e
e
x
ten
t
to
w
h
ic
h
co
n
g
esti
o
n
h
as
o
cc
u
r
r
ed
b
y
e
m
p
lo
y
in
g
ac
tiv
e
R
FID
(
g
ate
w
a
y
,
r
o
u
ter
an
d
tag
s
)
an
d
G
SM
tech
n
o
lo
g
y
i
s
d
is
c
u
s
s
ed
in
[
1
]
.
T
h
is
m
et
h
o
d
r
eq
u
ir
es
e
ac
h
v
eh
ic
les
to
h
av
e
R
FID
ta
g
i
n
s
talled
in
th
e
m
a
n
d
b
ased
o
n
th
e
r
elati
v
e
s
p
ee
d
s
o
f
t
h
e
v
eh
icles
th
e
tr
af
f
ic
s
ig
n
al
is
co
n
tr
o
lled
b
y
t
h
e
co
o
r
d
in
at
o
r
s
.
T
h
is
tech
n
iq
u
e
r
eq
u
ir
es
a
h
u
g
e
in
itial
i
n
v
est
m
en
t
f
o
r
s
y
s
te
m
s
et
u
p
an
d
,
d
if
f
icu
l
t
to
i
m
p
le
m
e
n
t
i
n
citie
s
w
it
h
h
i
g
h
co
n
g
e
s
tio
n
p
r
o
b
lem
b
ec
au
s
e
th
e
tr
af
f
ic
c
o
n
g
es
tio
n
at
g
i
v
e
n
s
i
g
n
al
n
o
t
o
n
l
y
a
f
f
ec
ts
th
e
s
i
g
n
al
lig
h
t
s
o
f
th
i
s
j
u
n
c
tio
n
b
u
t
also
i
n
f
l
u
e
n
ce
s
th
e
s
i
g
n
al
lig
h
ts
o
f
p
r
ev
io
u
s
j
u
n
ctio
n
s
.
T
h
er
ef
o
r
e
d
u
e
to
c
h
ai
n
r
ea
ctio
n
,
in
t
h
e
w
o
r
s
t
ca
s
e
a
s
er
ies o
f
s
i
g
n
als ca
n
ex
p
er
ie
n
c
e
a
s
ev
er
e
co
n
g
e
s
tio
n
p
r
o
b
le
m
.
T
h
e
tech
n
iq
u
e
i
n
w
h
ic
h
tr
a
f
f
ic
s
i
g
n
al
co
n
tr
o
l
i
s
d
o
n
e
u
s
i
n
g
i
m
ag
e
p
r
o
ce
s
s
i
n
g
tech
n
iq
u
e
s
i
s
p
r
esen
ted
in
[
2
]
-
[
4
]
.
T
h
e
s
i
m
ilar
it
y
b
et
wee
n
a
r
ef
er
en
ce
i
m
ag
e
o
f
a
r
o
ad
an
d
th
e
r
ea
l
i
m
ag
e
o
f
s
a
m
e
r
o
ad
b
ec
o
m
es
t
h
e
cr
iter
ia
f
o
r
tr
af
f
ic
s
i
g
n
a
l
li
g
h
t
co
n
tr
o
l.
Hig
h
er
t
h
e
s
i
m
il
ar
it
y
lo
w
er
i
s
t
h
e
n
u
m
b
er
o
f
v
eh
icles
a
n
d
v
iz.
P
r
ef
er
en
ce
is
g
i
v
e
n
to
r
o
ad
w
h
ic
h
h
as
least
s
i
m
ilar
it
y
v
a
lu
e.
T
h
is
tech
n
iq
u
e
ta
k
es
in
t
o
ac
co
u
n
t
o
n
l
y
t
h
e
s
i
m
ilar
it
y
v
alu
e
t
h
er
ef
o
r
e
ir
r
es
p
ec
tiv
e
o
f
n
u
m
b
er
o
f
v
eh
ic
les
ac
r
o
s
s
ea
ch
la
n
es
GR
E
E
N
s
i
g
n
al
i
s
g
i
v
en
to
o
n
l
y
th
o
s
e
lan
e
s
w
it
h
least
s
i
m
ilar
i
t
y
v
al
u
e.
T
h
er
e
m
i
g
h
t
o
cc
u
r
a
s
itu
atio
n
in
w
h
ich
o
n
e
la
n
e
h
as
f
e
w
er
n
u
m
b
er
o
f
L
ar
g
e
Mo
to
r
Veh
icle
s
(
L
M
V)
in
w
h
ic
h
t
h
e
s
i
m
ilar
it
y
v
alu
e
is
s
m
al
l
an
d
a
n
o
t
h
er
lan
e
m
i
g
h
t
h
a
v
e
g
r
ea
ter
n
u
m
b
er
o
f
s
m
all
s
ized
v
e
h
icl
es
co
v
er
i
n
g
les
s
ar
ea
ac
r
o
s
s
th
e
r
o
ad
co
m
p
ar
ed
to
t
h
e
r
o
ad
w
i
th
L
MV
t
h
u
s
s
i
m
ilar
it
y
v
al
u
e
w
o
u
ld
b
e
co
m
p
ar
at
iv
el
y
h
i
g
h
.
I
n
th
i
s
ca
s
e
f
o
r
m
er
lan
e
is
g
iv
e
n
GR
E
E
N
s
ig
n
al
an
d
later
ca
s
e
is
g
i
v
e
n
R
E
D
s
ig
n
al
t
h
u
s
f
ai
li
n
g
to
av
o
id
co
n
g
est
io
n
at
t
h
e
d
en
s
el
y
p
o
p
u
lated
r
o
ad
s
.
A
m
et
h
o
d
o
lo
g
y
in
w
h
ic
h
t
h
e
v
eh
ic
le
co
u
n
t
i
s
d
eter
m
in
ed
u
s
in
g
I
m
ag
e
p
r
o
ce
s
s
in
g
tec
h
n
i
q
u
e
an
d
a
lear
n
in
g
m
o
d
el
is
d
esi
g
n
ed
wh
ich
p
r
ed
icts
t
h
e
d
u
r
atio
n
o
f
tr
af
f
ic
s
i
g
n
al
f
o
r
th
e
n
e
x
t
iter
atio
n
b
ased
o
n
th
e
av
ailab
le
d
ata
o
f
c
u
r
r
en
t
iter
a
tio
n
,
is
p
r
ese
n
ted
i
n
[
5
]
.
A
l
s
o
,
[
6
]
an
d
[
7
]
p
r
o
p
o
s
es
alter
n
ativ
e
tec
h
n
iq
u
e
s
to
o
v
er
co
m
e
tr
af
f
ic
co
n
g
est
io
n
a
n
d
tr
af
f
ic
ac
cid
en
t
s
.
3.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
o
lo
g
y
e
n
co
m
p
a
s
s
es t
w
o
m
ai
n
p
h
ase
s
:
a.
Ob
j
ec
t d
etec
tio
n
a
n
d
v
eh
icle
c
o
u
n
ti
n
g
b.
Dec
is
io
n
m
a
k
in
g
u
s
i
n
g
Dec
is
i
o
n
tr
ee
.
E
ac
h
o
f
th
e
s
e
p
h
ase
s
is
e
x
p
lai
n
ed
in
d
etail
i
n
th
e
f
o
llo
w
in
g
s
ec
tio
n
.
3
.
1
.
O
bje
ct
det
ec
t
io
n a
nd
v
ehicle
co
un
t
ing
A
ca
m
er
a
ca
p
ab
le
o
f
ca
p
tu
r
i
n
g
all
t
h
e
la
n
es
at
a
g
i
v
e
n
j
u
n
ctio
n
h
a
s
to
b
e
s
et
u
p
.
T
h
e
p
o
s
itio
n
a
n
d
o
r
ien
tatio
n
o
f
th
i
s
ca
m
er
a
s
h
o
u
ld
b
e
co
n
s
i
s
ten
t
in
g
i
v
i
n
g
th
e
p
r
o
p
er
v
ie
w
o
f
all
th
e
la
n
es.
A
b
ala
n
ce
d
p
icto
r
ial
v
ie
w
o
f
al
l
t
h
e
la
n
es
o
b
tain
ed
f
r
o
m
th
e
ca
m
er
a
h
elp
s
i
n
ac
h
i
ev
in
g
b
etter
r
es
u
lts
f
o
r
d
ec
i
s
io
n
m
a
k
in
g
p
r
o
ce
s
s
.
T
h
is
r
ea
l
ti
m
e
v
id
eo
f
r
o
m
t
h
i
s
ca
m
er
a
is
g
iv
e
n
a
s
i
n
p
u
t
to
th
e
m
icr
o
co
n
tr
o
ller
/
m
icr
o
p
r
o
ce
s
s
o
r
.
T
h
e
I
m
a
g
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
e
f
o
r
o
b
j
ec
t
d
etec
tio
n
an
d
co
u
n
ti
n
g
an
d
,
t
h
e
al
g
o
r
ith
m
f
o
r
d
ec
is
io
n
m
a
k
in
g
i
s
p
r
o
g
r
am
m
ed
in
t
h
e
m
icr
o
p
r
o
ce
s
s
o
r
.
T
h
e
im
a
g
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
e
u
s
ed
h
er
e
f
o
llo
w
s
ex
tr
ac
tio
n
o
f
f
r
a
m
e
s
f
r
o
m
th
e
v
id
eo
,
B
ac
k
g
r
o
u
n
d
s
u
b
tr
ac
tio
n
,
th
r
es
h
o
ld
s
etu
p
,
cr
ea
tin
g
co
n
to
u
r
s
,
b
lo
b
d
etec
tio
n
,
an
d
v
eh
ic
le
co
u
n
ti
n
g
w
h
ich
i
s
m
o
r
e
ac
c
u
r
ate
th
a
n
th
e
o
b
j
ec
t
d
etec
tio
n
t
ec
h
n
iq
u
e
p
r
esen
ted
i
n
[
8
]
an
d
[
9
]
.
T
h
e
ca
p
tu
r
ed
v
id
eo
is
b
r
o
k
en
d
o
w
n
i
n
to
s
e
q
u
en
ce
o
f
f
r
a
m
es,
t
h
e
f
r
a
m
es
ar
e
ex
tr
ac
ted
a
t
a
r
ate
o
f
2
5
f
r
a
m
es/
s
ec
.
T
h
ese
s
eq
u
en
ce
s
o
f
f
r
a
m
es
ar
e
p
r
o
ce
s
s
ed
to
d
etec
t
m
u
ltip
le
m
o
v
i
n
g
o
b
j
ec
ts
(
v
eh
icle
s
)
.
F
o
r
th
e
p
u
r
p
o
s
e
o
f
ex
p
lan
atio
n
,
t
h
e
al
g
o
r
ith
m
i
s
ap
p
lied
f
o
r
a
t
w
o
la
n
e
tr
a
f
f
ic
j
u
n
ctio
n
.
A
t
th
e
b
eg
i
n
n
in
g
o
f
th
i
s
al
g
o
r
ith
m
t
h
e
v
eh
ic
le
co
u
n
t a
cr
o
s
s
all
t
h
e
la
n
es i
s
in
itialized
to
ze
r
o
.
A
v
ir
tu
al
li
n
e
i
s
d
r
a
w
n
ac
r
o
s
s
ea
c
h
lan
es a
t
th
e
j
u
n
ctio
n
to
k
ee
p
tr
a
ck
o
n
th
e
n
u
m
b
er
o
f
v
e
h
icle
s
w
aiti
n
g
to
cr
o
s
s
t
h
e
j
u
n
ctio
n
.
T
h
e
v
ir
tu
al
li
n
e
s
ar
e
co
n
s
id
er
ed
as
th
e
lin
e
o
f
r
e
f
er
en
ce
f
o
r
th
e
m
o
v
e
m
en
t
o
f
t
h
e
v
e
h
icle
s
.
Fig
u
r
e
1
s
h
o
w
s
o
r
ig
i
n
al
i
m
a
g
e
ex
tr
a
cted
f
r
o
m
th
e
v
id
eo
an
d
th
e
i
m
ag
e
w
i
th
v
ir
t
u
al
li
n
e
s
d
r
a
w
s
ac
r
o
s
s
ea
c
h
o
f
t
h
e
lan
es o
f
th
e
j
u
n
ctio
n
.
T
h
e
ex
tr
ac
ted
f
r
a
m
e
s
f
r
o
m
t
h
e
v
id
eo
ar
e
co
n
v
er
ted
in
to
b
i
n
ar
y
b
lac
k
a
n
d
w
h
ite
i
m
a
g
e.
I
t
is
ev
id
e
n
t
f
r
o
m
[
1
0
]
th
at
C
an
n
y
E
d
g
e
d
etec
tio
n
is
th
e
m
o
s
t
e
f
f
icie
n
t
tech
n
iq
u
e
f
o
r
o
b
j
ec
t
ed
g
e
ex
tr
ac
tio
n
,
h
e
n
ce
th
e
s
a
m
e
tec
h
n
iq
u
e
i
s
u
s
ed
h
er
e.
C
o
n
to
u
r
s
ar
e
d
r
a
w
n
f
o
r
th
e
b
i
n
ar
y
i
m
a
g
e
an
d
co
n
v
ex
h
u
lls
ar
e
co
n
s
tr
u
cted
w
it
h
th
e
h
elp
o
f
t
h
ese
co
n
to
u
r
s
an
d
,
f
in
all
y
b
lo
b
s
ar
e
f
o
r
m
ed
.
E
ac
h
o
f
v
al
id
b
lo
b
s
ar
e
a
d
d
ed
to
th
e
lis
t
li
s
t_
b
lo
b
s
.
Fo
r
ea
ch
a
n
d
ev
er
y
b
lo
b
in
t
h
e
lis
t
l
is
t_
b
lo
b
s
,
if
th
e
b
lo
b
h
a
s
cr
o
s
s
ed
t
h
e
v
ir
tu
al
li
n
e
t
h
en
th
e
v
eh
icle
co
u
n
ter
ass
o
ciate
d
w
ith
th
e
co
r
r
esp
o
n
d
in
g
la
n
e
is
i
n
cr
e
m
en
ted
.
T
h
e
b
lo
b
s
m
a
y
b
e
ca
teg
o
r
ized
as
2
-
w
h
ee
ler
o
r
4
-
w
h
ee
ler
b
ased
o
n
th
e
s
ize
a
n
d
asp
ec
t
r
atio
.
A
n
d
also
t
w
o
s
e
p
ar
ate
co
u
n
ter
s
m
a
y
b
e
ass
i
g
n
ed
to
ea
ch
lan
e
at
th
e
j
u
n
ct
io
n
,
o
n
e
to
ac
co
u
n
t
f
o
r
n
u
m
b
er
o
f
t
w
o
w
h
ee
ler
v
e
h
icles
w
a
iti
n
g
to
cr
o
s
s
t
h
e
j
u
n
ctio
n
an
d
t
h
e
o
th
e
r
f
o
r
f
o
u
r
w
h
ee
ler
.
C
r
o
s
s
in
g
t
h
e
lin
e
m
er
el
y
r
e
f
er
s
to
t
h
e
f
ac
t t
h
at
t
h
e
m
id
p
o
in
t o
f
t
h
e
b
lo
b
u
n
d
er
r
ef
er
en
ce
i
s
o
n
o
n
e
s
id
e
o
f
t
h
e
li
n
e
i
n
th
e
p
r
ev
io
u
s
f
r
a
m
e
a
n
d
in
t
h
e
c
u
r
r
en
t
f
r
a
m
e
t
h
e
m
id
p
o
in
t
is
o
n
o
r
h
as
cr
o
s
s
ed
th
e
v
ir
tu
a
l
lin
e.
I
n
Fi
g
u
r
e
2
f
o
r
ea
ch
o
f
th
e
la
n
es
t
w
o
co
u
n
ter
s
a
r
e
m
ai
n
tai
n
ed
r
esp
ec
tiv
el
y
.
O
n
e
f
o
r
th
e
2
w
h
ee
ler
v
eh
ic
le
an
d
t
h
e
o
t
h
er
f
o
r
th
e
4
w
h
ee
ler
v
e
h
icle
as s
h
o
w
n
i
n
t
h
e
to
p
lef
t c
o
r
n
er
f
o
r
lan
e
1
(
L
ef
t la
n
e
i
n
Fi
g
u
r
e
2
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2088
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
8
,
No
.
3
,
J
u
n
e
201
8
:
1
5
2
2
–
1
5
2
9
1524
an
d
b
o
tto
m
r
i
g
h
t
co
r
n
er
f
o
r
lan
e
2
(
B
o
tto
m
la
n
e
in
Fig
u
r
e
2
)
,
in
y
ello
w
co
lo
r
.
I
n
th
e
p
air
o
f
n
u
m
b
er
s
f
o
r
ea
c
h
lan
e,
t
h
e
u
p
p
er
n
u
m
b
er
in
d
icat
es
th
e
n
u
m
b
er
o
f
t
w
o
w
h
ee
ler
v
eh
ic
les
a
n
d
lo
w
er
n
u
m
b
er
in
d
icate
s
th
e
n
u
m
b
e
r
o
f
f
o
u
r
w
h
ee
ler
v
eh
ic
les
w
h
ic
h
h
a
v
e
cr
o
s
s
ed
th
e
v
ir
t
u
al
lin
e.
T
h
e
r
esp
ec
tiv
e
co
u
n
ter
s
ar
e
r
ef
r
es
h
ed
ev
er
y
ti
m
e
th
e
d
ec
is
io
n
i
s
m
ad
e,
i
n
o
r
d
er
to
h
av
e
a
v
al
id
co
u
n
t
f
o
r
th
e
n
ex
t tu
r
n
o
f
d
ec
is
io
n
m
a
k
i
n
g
.
Fig
u
r
e
1
.
E
x
tr
ac
ted
f
r
a
m
e
f
r
o
m
v
id
eo
Fig
u
r
e
2
.
Ou
tp
u
t_
f
r
a
m
e
3
.
2
.
Dec
is
io
n
m
a
k
i
ng
us
ing
deci
s
i
o
n t
re
e
B
asicall
y
d
ec
is
io
n
tr
ee
is
f
o
r
m
ed
b
y
p
o
s
i
n
g
s
er
ie
s
o
f
q
u
est
io
n
s
ab
o
u
t
th
e
ch
ar
ac
ter
i
s
tics
o
r
attr
ib
u
tes
o
f
th
e
i
n
p
u
t r
ec
o
r
d
,
o
n
e
af
ter
t
h
e
o
th
er
.
T
h
e
p
r
o
ce
s
s
s
tar
ts
f
r
o
m
th
e
r
o
o
t n
o
d
e,
th
e
test
co
n
d
itio
n
is
ap
p
lied
to
it
in
a
n
i
n
ter
n
al
n
o
d
e,
an
d
b
ased
o
n
t
h
e
o
u
tco
m
e,
ap
p
r
o
p
r
iate
b
r
an
ch
i
s
f
o
llo
w
ed
.
T
h
is
w
ill
t
ak
e
t
h
e
i
n
p
u
t
eit
h
er
to
th
e
n
e
x
t
in
ter
n
al
n
o
d
e
w
h
er
e
ag
ai
n
a
tes
t
co
n
d
itio
n
i
s
to
b
e
an
s
w
er
ed
,
o
r
th
e
leaf
n
o
d
e
t
h
at
h
as
a
cla
s
s
lab
el
to
w
h
ich
t
h
e
i
n
p
u
t i
s
class
if
ied
to
.
Fig
u
r
e
3
s
h
o
w
s
th
e
d
ec
is
io
n
t
r
ee
.
Fig
u
r
e
3
.
Dec
is
io
n
tr
ee
I
n
Fi
g
u
r
e
3
,
„
i
‟
s
ta
n
d
s
f
o
r
p
r
ef
er
r
ed
lan
es
t
u
r
n
e.
g
.
if
i
=
1
t
h
en
p
r
ef
er
r
ed
la
n
e
i
s
1
,
i.e
.
la
n
e
1
w
ill
b
e
g
iv
e
n
p
r
i
m
e
i
m
p
o
r
tan
ce
o
v
er
o
th
er
lan
e
s
f
o
r
n
ex
t
t
h
r
ee
ti
m
e
s
lo
ts
(
1
ti
m
e
s
lo
t
=3
0
s
ec
s
)
.
„
co
u
n
t
‟
s
tan
d
s
f
o
r
co
u
n
t
o
n
iter
atio
n
,
‟
co
u
n
t
‟
ca
n
b
e
0
,
1
o
r
2
.
E
v
er
y
ti
m
e
th
e
r
o
o
t
n
o
d
e
ch
ec
k
s
if
t
h
e
L
a
n
e
i
‟
s
th
r
ee
iter
atio
n
(
i.e
.
th
r
ee
ti
m
e
s
lo
ts
)
is
co
m
p
leted
,
I
f
co
m
p
leted
t
h
en
n
ex
t
la
n
e
i
s
ch
o
s
e
n
a
s
t
h
e
p
r
e
f
er
r
ed
lan
e
a
n
d
t
h
e
s
tatu
s
o
f
t
h
e
lan
e
f
la
g
is
ch
ec
k
ed
.
E
ls
e,
„
i
‟
i
s
i
n
cr
e
m
e
n
ted
an
d
r
esp
ec
ti
v
e
la
n
e
co
u
n
t
(
la
n
e
co
u
n
t
s
g
iv
e
t
h
e
n
u
m
b
er
o
f
co
n
s
ec
u
tiv
e
ti
m
e
s
th
e
r
esp
ec
ti
v
e
lan
e
w
as
g
i
v
en
g
r
ee
n
s
i
g
n
a
l)
is
in
cr
e
m
e
n
ted
.
I
f
th
e
t
h
r
ee
iter
atio
n
s
ar
e
o
v
er
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
-
8708
A
u
t
o
n
o
mo
u
s
Tr
a
ffic S
ig
n
a
l Co
n
tr
o
l u
s
in
g
Dec
is
io
n
Tr
ee
(
A
n
a
la
M.
R
.
)
1525
an
d
in
all
t
h
e
3
co
n
s
ec
u
tiv
e
i
te
r
atio
n
s
i
f
s
a
m
e
s
et
o
f
la
n
es
ar
e
g
i
v
e
n
g
r
ee
n
s
i
g
n
al
th
e
n
r
esp
e
ctiv
e
la
n
e
f
la
g
s
ar
e
s
et.
A
t
lev
el
2
o
f
lef
t
s
u
b
-
tr
ee
,
s
tat
u
s
f
la
g
a
n
d
Z
i
s
c
h
ec
k
ed
b
ased
co
n
d
itio
n
at
le
v
el
1
.
Af
ter
a
co
u
p
le
o
f
s
i
m
ilar
co
n
d
itio
n
s
th
e
d
ec
is
io
n
is
tak
e
n
at
th
e
lea
v
es.
E
ac
h
lea
f
n
o
d
e
o
f
th
e
tr
ee
m
a
k
es
th
e
d
ec
is
i
o
n
o
n
w
h
ich
o
f
t
h
e
f
o
llo
w
in
g
clas
s
es
d
o
es
th
e
g
iv
e
n
in
p
u
t
(
L
1
3
&
L
2
4
)
b
elo
n
g
s
to
:
C
la
s
s
L1
:
L
an
e
1
is
g
i
v
en
g
r
ee
n
f
o
r
3
0
s
ec
o
n
d
s
an
d
L
a
n
e
2
,
3
an
d
4
ar
e
r
ed
.
C
la
s
s
L2
:
L
an
e
2
is
g
i
v
en
g
r
ee
n
f
o
r
3
0
s
ec
o
n
d
s
an
d
L
a
n
e
3
,
4
an
d
1
ar
e
r
ed
.
C
la
s
s
L3
:
L
an
e
3
is
g
i
v
en
g
r
ee
n
f
o
r
3
0
s
ec
o
n
d
s
an
d
L
a
n
e
4
,
1
an
d
2
ar
e
r
ed
.
C
la
s
s
L4
:
L
an
e
4
is
g
i
v
en
g
r
ee
n
f
o
r
3
0
s
ec
o
n
d
s
an
d
L
a
n
e
1
,
2
an
d
3
ar
e
r
ed
.
C
la
s
s
L1
3
:
L
a
n
e
1
an
d
L
a
n
e
3
ar
e
g
iv
e
n
g
r
ee
n
f
o
r
3
0
s
ec
o
n
d
s
an
d
L
a
n
e
2
an
d
L
a
n
e
4
ar
e
g
i
v
en
r
ed
.
C
la
s
s
L2
4
:
L
a
n
e
2
an
d
L
a
n
e
4
ar
e
g
iv
e
n
g
r
ee
n
f
o
r
3
0
s
ec
o
n
d
s
an
d
L
a
n
e
1
an
d
L
a
n
e
3
ar
e
g
i
v
en
r
ed
.
T
h
e
d
is
cr
im
in
a
n
t
f
u
n
ctio
n
g
(
x
,
y
)
i
s
d
ef
i
n
ed
as f
o
llo
w
s
:
Z
=
g
(
x
,
y
)
=
(
(
y
/
x
)
-
1)
(
1
)
Her
e,
y
i
s
to
tal
n
u
m
b
er
o
f
v
eh
i
cles a
cr
o
s
s
lan
e
2
an
d
4
an
d
,
x
is
to
tal
n
u
m
b
er
o
f
v
eh
icles a
cr
o
s
s
lan
e
1
an
d
3
.
Dec
is
io
n r
ule:
I
f
(
Z
>0
A
ND
Z
<1
0
)
OR
(
Z
<
-
0
.
1
)
T
h
en
d
ec
id
e
GR
E
E
N
s
ig
n
al
f
o
r
lan
e
2
an
d
4
(
i.e
.
d
ec
id
e
L
2
4
)
I
f
(
Z
<0
A
ND
Z
>
-
0
.
1
)
OR
(
Z
>1
0
)
T
h
en
d
ec
id
e
GR
E
E
N
s
ig
n
al
f
o
r
lan
e
1
an
d
3
(
i.e
.
d
ec
id
e
L
1
3
)
Fig
u
r
e
4
.
d
is
cr
i
m
i
n
an
t r
e
g
io
n
Fig
u
r
e
5
.
Z
=
g
(
x
,
y
)
Gr
ap
h
s
h
o
w
n
in
Fi
g
u
r
e
4
is
a
2
D
g
r
ap
h
d
ep
ictin
g
t
h
e
r
eg
io
n
s
R
1
(
g
r
a
y
)
a
n
d
R
2
(
w
h
ite)
,
C
o
u
n
t
o
f
n
u
m
b
er
o
f
v
eh
icles
ac
r
o
s
s
lan
e
1
an
d
3
is
s
h
o
w
n
ac
r
o
s
s
x
-
a
x
is
a
n
d
n
u
m
b
er
o
f
v
eh
icle
s
ac
r
o
s
s
lan
e
2
a
n
d
4
is
s
h
o
w
n
ac
r
o
s
s
y
-
ax
i
s
,
Fig
u
r
e
4
s
h
o
w
s
th
e
p
ict
u
r
izatio
n
as
to
h
o
w
t
h
e
d
if
f
er
en
t
co
m
b
in
atio
n
o
f
v
e
h
icles
co
u
n
t
ar
e
b
if
u
r
ca
ted
as
b
elo
n
g
in
g
t
o
r
eg
io
n
1
an
d
r
eg
io
n
2
r
esp
ec
tiv
el
y
.
Gr
ap
h
s
h
o
w
n
i
n
F
ig
u
r
e
5
p
r
esen
ts
t
h
e
d
is
cr
i
m
i
n
an
t
f
u
n
ctio
n
Z
,
w
it
h
x
an
d
y
a
x
i
s
d
ep
icts
th
e
n
u
m
b
er
o
f
v
e
h
icl
e
s
ac
r
o
s
s
L
1
3
(
=L
1
+L
3
)
an
d
L
2
4
(
=L
2
+L
4
)
r
esp
ec
ti
v
el
y
,
a
n
d
Z
is
alo
n
g
z
a
x
is
.
T
h
e
d
ec
is
io
n
r
u
le
is
ap
p
lied
o
v
er
t
h
e
Z
v
al
u
e
o
b
tain
ed
f
o
r
t
h
e
g
iv
e
n
s
e
t
o
f
in
p
u
ts
,
a
n
d
f
i
n
all
y
d
ec
is
io
n
is
m
ad
e.
T
h
e
alg
o
r
ith
m
f
o
r
Dec
is
io
n
tr
ee
in
au
to
n
o
m
o
u
s
tr
a
f
f
ic
s
i
g
n
a
l
co
n
t
r
o
l is g
i
v
en
b
elo
w
.
1
:
pro
ce
du
re
Ma
in
(
)
2:
i
←
0
//
s
tar
t
w
it
h
lan
e
1
3:
LF
13
←
0
//
L
an
e
f
la
g
f
o
r
lan
e
1
an
d
3
4:
LF
24
←
0
//
L
an
e
f
la
g
f
o
r
lan
e
2
an
d
4
5:
co
u
n
t
←
0
6:
C
1
3
←
0
7:
C
2
4
←
0
8:
w
hil
e
1
do
//
s
tar
t
ev
er
y
90
s
ec
s
9:
if
c
o
un
t
%3
=
0
t
h
e
n
10
:
c
ou
nt
←
c
ou
nt
+
1
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2088
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
8
,
No
.
3
,
J
u
n
e
201
8
:
1
5
2
2
–
1
5
2
9
1526
11
:
if
LF
13
=
1
||
LF
24
=
1
t
h
e
n
12
:
if
LF
13
=
1
t
hen
//
L
1
3
w
as
g
r
ee
n
f
o
r
last
90
s
ec
s
13
:
LF
13
=
0
14
:
C
24
←
C
24
+
1
15
:
ST
A
R
T
_
W
IT
H
_
L
24
16
:
e
l
s
e
//
L
2
4
w
as
g
r
ee
n
f
o
r
last
90
s
ec
s
17
:
LF
24
=
0
18
:
C
13
←
C
13
+
1
19
:
ST
A
R
T
_
W
IT
H
_
L
13
20
:
end
if
21
:
else
22
:
if
D
et
e
r
m
i
n
e
_
G
=
L
24
t
h
e
n
/
/
L
2
4
h
a
s
m
o
r
e
v
e
h
icle
s
23
:
C
24
←
C
24
+
1
24
:
ST
A
R
T
_
W
IT
H
_
L
24
25
:
e
l
s
e
//
L
1
3
h
as
m
o
r
e
v
e
h
icles
26
:
C
13
←
C
13
+
1
27
:
ST
A
R
T
_
W
IT
H
_
L
13
28
:
end
if
29
:
end
if
30
:
else
31
:
c
ou
nt
←
c
ou
nt
+
1
32
:
if
DET
E
R
M
I
N
E
_
G
=
L
13
t
h
e
n
33
:
La
n
e
1
←
La
n
e
3
←
g
r
e
e
n
34
:
C
13
←
C
13
+
1
35
:
C
2
4
=
0
36
:
o
u
tlet
←
2
37
:
w
a
it
30
s
ec
s
38
:
if
C
1
3
=
3
t
hen
39
:
LF
13
=
1
40
:
end
if
41
:
else
42
:
La
n
e
2
←
La
n
e
4
←
g
r
e
e
n
43
:
C
24
←
C
24
+
1
44
:
C
1
3
←
0
45
:
o
u
tlet
←
2
46
:
w
a
it
30
s
ec
s
47
:
if
C
2
4
=
3
t
hen
48
:
LF
24
=
1
49
:
end
if
50
:
end
if
51
:
end
if
52
:
e
n
d
w
h
i
l
e
5
3
:
end
pro
ce
du
re
5
4
:
p
ro
c
e
d
ur
e
D
e
t
e
r
m
i
n
e
_
G
(
)
55
:
LC
24
←
LC
2
+
LC
4
56
:
LC
13
←
LC
1
+
LC
3
57
:
G
←
LC
24
/
L
C
13
−
1
58
:
i
f
G
>
0
&
&
G
<
10
t
h
en
re
t
urn
L
24
59
:
else
re
t
urn
L
13
60
:
end
if
6
1
:
end
pro
ce
du
re
6
2
:
p
ro
c
e
d
ur
e
S
T
A
R
T
_
W
I
T
H
_
L
2
4
(
)
63
:
if
i
=
2
t
h
e
n
64
:
La
n
e
2
←
g
r
e
e
n
65
:
O
ut
le
t
←
3
66
:
el
s
e
if
i
=
4
t
h
e
n
67
:
La
n
e
4
←
g
r
e
e
n
68
:
O
ut
le
t
←
3
69
:
else
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
-
8708
A
u
t
o
n
o
mo
u
s
Tr
a
ffic S
ig
n
a
l Co
n
tr
o
l u
s
in
g
Dec
is
io
n
Tr
ee
(
A
n
a
la
M.
R
.
)
1527
70
:
La
n
e
2
←
La
n
e
4
←
g
r
e
e
n
71
:
O
ut
le
t
←
2
72
:
w
a
it
30
s
ec
s
73
:
end
if
7
4
:
end
pro
ce
du
re
7
5
:
p
ro
c
e
d
ur
e
S
T
A
R
T
_
W
I
T
H
_
L
1
3
(
)
76
:
if
i
=
1
t
h
e
n
77
:
La
n
e
1
←
g
r
e
e
n
78
:
O
ut
le
t
←
3
79
:
el
s
e
if
i
=
3
t
h
e
n
80
:
La
n
e
3
←
g
r
e
e
n
81
:
O
ut
le
t
←
3
82
:
else
83
:
La
n
e
1
←
La
n
e
3
←
g
r
e
e
n
84
:
O
ut
le
t
←
2
85
:
w
a
it
30
s
ec
s
86
:
end
if
8
7
:
end
pro
ce
du
re
I
n
th
i
s
co
n
tex
t,
t
h
e
i
n
p
u
t
to
t
h
e
d
ec
is
io
n
tr
ee
ar
e
th
e
f
ea
t
u
r
es
o
f
4
la
n
es
L
1
,
L
2
,
L
3
an
d
L
4
.
T
h
ese
f
ea
t
u
r
es
i
n
cl
u
d
e
th
e
v
e
h
icle
c
o
u
n
t
o
f
ea
c
h
la
n
e
a
n
d
a
f
lag
ass
o
ciate
d
w
it
h
t
h
e
p
air
o
f
la
n
es
i.e
.
L
F1
3
an
d
L
F2
4
.
T
h
e
f
la
g
v
al
u
e
1
f
o
r
a
p
air
o
f
la
n
e
s
s
p
ec
i
f
ie
s
t
h
at
th
e
y
w
er
e
g
iv
e
n
g
r
ee
n
s
ig
n
al
f
o
r
3
co
n
s
ec
u
ti
v
e
ti
m
e
(
3
0
s
ec
ea
ch
)
.
T
h
e
leaf
n
o
d
es
s
p
ec
if
ie
s
w
h
ich
lan
e
s
s
h
o
u
ld
b
e
g
i
v
en
w
it
h
t
h
e
g
r
ee
n
s
ig
n
al
f
o
r
th
e
n
e
x
t
3
0
s
ec
s
an
d
also
m
ar
k
s
t
h
e
f
lag
s
o
f
th
e
lan
es
i
f
t
h
e
y
w
er
e
g
i
v
e
n
g
r
ee
n
s
i
g
n
als
f
o
r
3
co
n
s
ec
u
t
iv
e
ti
m
es
w
h
ich
is
u
s
ed
a
s
th
e
in
p
u
t to
th
e
n
ex
t iter
atio
n
.
Fig
u
r
e
6
.
3
o
u
tle
t f
o
r
m
at
a
n
d
2
o
u
tlet f
o
r
m
a
t
3
o
u
tlet
fo
r
ma
t
:
I
n
th
is
f
o
r
m
at,
a
s
elec
ted
lan
e
(
s
a
y
L
1
)
allo
w
s
its
v
e
h
icle
s
to
m
o
v
e
i
n
3
d
ir
ec
tio
n
s
i.e
s
tr
aig
h
t
(
alo
n
g
lan
e3
)
,
lef
t
(
alo
n
g
la
n
e2
)
an
d
r
ig
h
t
(
alo
n
g
lan
e4
)
.
2
o
u
tlet
fo
r
ma
t
:
I
n
th
is
f
o
r
m
at,
a
s
elec
ted
lan
e
(
s
a
y
L
1
)
allo
w
s
its
v
e
h
icle
s
to
m
o
v
e
i
n
2
d
ir
ec
tio
n
s
i.e
s
tr
aig
h
t
(
alo
n
g
lan
e3
)
an
d
le
f
t
(
alo
n
g
la
n
e2
)
.
Fig
u
r
e
6
r
ep
r
esen
ts
b
o
th
t
h
ese
f
o
r
m
at
s
.
T
h
e
tr
ee
is
ex
ec
u
ted
o
n
ce
i
n
e
v
er
y
ti
m
e
s
lo
t
(
3
0
s
ec
s
)
.
First
w
e
c
h
ec
k
if
9
0
s
ec
o
n
d
s
(
i.e
t
h
r
ee
3
0
s
ec
ti
m
e
s
lo
ts
)
is
co
m
p
leted
u
s
i
n
g
th
e
co
n
d
itio
n
co
u
n
t%3
=0
.
i
f
it
h
a
s
t
h
e
n
w
e
c
h
ec
k
i
f
a
n
y
p
a
ir
o
f
la
n
es
(
L
1
3
o
r
L
2
4
)
w
er
e
g
i
v
e
n
g
r
ee
n
s
i
g
n
al
f
o
r
9
0
s
ec
s
i.e
.
f
o
r
3
co
n
ti
n
u
o
u
s
s
lo
ts
.
I
f
t
h
at
‟
s
tr
u
e
(
s
a
y
L
1
3
w
a
s
g
r
ee
n
f
o
r
9
0
s
ec
s
)
,
t
h
en
ir
r
esp
ec
tiv
e
o
f
t
h
e
r
esu
lt
o
f
th
e
Z
f
u
n
ctio
n
,
t
h
e
o
t
h
er
t
w
o
la
n
e
s
(
i.e
.
L
2
4
)
ar
e
g
i
v
en
t
h
e
p
r
ef
er
e
n
ce
s
o
as
to
a
v
o
id
s
tar
v
at
io
n
.
I
f
n
o
n
e
o
f
th
e
f
la
g
s
w
er
e
s
et,
t
h
e
f
u
n
ctio
n
Z
is
ca
l
led
to
d
ec
id
e
w
h
ich
o
f
t
h
e
p
air
s
is
to
b
e
g
iv
en
p
r
ef
er
en
ce
f
o
r
th
e
f
ir
s
t
3
0
s
ec
s
(
A
s
s
u
m
e
Z
d
ec
id
es
L
2
4
)
.
So
f
o
r
th
e
f
ir
s
t
3
0
s
ec
s
,
o
n
e
o
f
th
ese
t
w
o
lan
es
(
L
2
o
r
L
4
)
h
as
to
b
e
g
iv
en
g
r
ee
n
s
ig
n
al
w
it
h
3
o
u
tlet
f
o
r
m
at
,
b
ased
o
n
„
i
‟
v
al
u
e
.
T
h
e
lan
e
w
h
ic
h
h
as
it
s
tu
r
n
i
n
t
h
i
s
iter
atio
n
is
s
e
lecte
d
h
er
e.
ie,
if
L
2
is
p
r
ef
er
r
ed
la
n
e
i
n
th
is
iter
atio
n
t
h
en
L
2
i
s
s
elec
t
ed
o
r
if
L
4
h
a
s
its
tu
r
n
t
h
en
L
4
is
s
elec
ted
.
I
f
n
ei
th
er
o
f
t
h
e
m
h
ad
it
s
tu
r
n
,
i.e
L
1
o
r
L
3
h
ad
its
tu
r
n
in
th
e
co
r
r
esp
o
n
d
in
g
iter
atio
n
,
b
u
t
b
ased
o
n
Z
L
2
4
g
o
t
g
r
ee
n
th
e
n
b
o
th
o
f
th
e
m
ar
e
g
iv
e
n
g
r
ee
n
w
i
th
2
o
u
t
let
f
o
r
m
at.
I
n
t
h
e
s
ec
o
n
d
an
d
th
ir
d
ti
m
e
s
lo
ts
o
n
l
y
2
o
u
t
let
f
o
r
m
at
i
s
f
o
llo
w
ed
b
ased
o
n
p
air
o
f
lan
es
c
h
o
s
e
n
b
y
Z
.
I
f
co
u
n
t
%
3
is
n
o
t
0
,
i.e
.
9
0
s
ec
s
is
n
o
t c
o
m
p
leted
,
th
en
t
h
e
p
air
o
f
lan
e
s
is
s
elec
te
d
p
u
r
ely
b
ased
o
n
t
h
e
r
es
u
lt o
f
f
u
n
ctio
n
Z
.
Her
e
i
s
w
h
er
e
w
e
c
h
ec
k
if
a
p
air
is
b
ein
g
g
i
v
e
n
g
r
ee
n
s
ig
n
al
f
o
r
3
co
n
s
ec
u
tiv
e
ti
m
es
o
r
9
0
co
n
s
e
cu
ti
v
e
s
ec
o
n
d
s
an
d
th
er
eb
y
s
et
th
e
co
r
r
esp
o
n
d
in
g
f
la
g
s
to
av
o
id
s
tar
v
atio
n
o
f
t
h
e
o
th
er
p
air
o
f
lan
es.
Fo
r
a
4
l
an
e
s
tr
u
ct
u
r
e
o
f
th
e
d
ec
is
io
n
tr
ee
,
th
e
f
o
llo
w
in
g
m
eth
o
d
o
lo
g
y
is
f
o
llo
w
ed
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2088
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
8
,
No
.
3
,
J
u
n
e
201
8
:
1
5
2
2
–
1
5
2
9
1528
Fo
r
ev
er
y
iter
atio
n
(
i.e
e
v
e
r
y
3
0
s
ec
s
)
L
1
3
(
=
L
1
+
L
3
)
an
d
L
2
4
(
=
L
2
+L
4
)
is
co
m
p
u
ted
.
E
v
er
y
la
n
e
(
I
n
th
is
ca
s
e
4
lan
es)
m
ee
t
in
g
at
th
e
j
u
n
ctio
n
is
g
i
v
e
n
eq
u
al
p
r
io
r
ity
in
R
o
u
n
d
R
o
b
in
f
a
s
h
io
n
,
i.e
ev
er
y
lan
e
b
ec
o
m
e
s
p
r
ef
er
r
ed
la
n
e
(
g
e
ts
3
o
u
tlet
f
o
r
m
at
f
o
r
1
s
t
3
0
s
ec
s
)
w
it
h
i
n
a
m
a
x
i
m
u
m
o
f
1
1
ti
m
e
s
lo
ts
an
d
ir
r
esp
ec
tiv
e
o
f
t
h
e
m
ag
n
it
u
d
e
o
f
co
n
g
esti
o
n
at
th
e
tr
af
f
ic
j
u
n
ctio
n
e
v
er
y
la
n
e
g
et
g
r
ee
n
s
i
g
n
al
(
2
o
u
tlet
f
o
r
m
at)
w
it
h
i
n
a
m
a
x
i
m
u
m
o
f
6
ti
m
e
s
lo
ts
.
Af
ter
ev
er
y
3
iter
atio
n
s
,
a
lan
e
„
i‟
b
ec
o
m
es
p
r
ef
er
r
ed
lan
e
b
ased
o
n
th
e
f
o
llo
w
in
g
r
u
le
i =
(
i %
4
)
+
1
(
2
)
4.
R
E
SU
L
T
S
A
N
D
A
N
A
L
Y
SI
S
T
h
e
alg
o
r
ith
m
i
s
i
m
p
le
m
e
n
te
d
in
C
++
i
n
v
is
u
al
s
tu
d
io
alo
n
g
w
it
h
o
p
en
C
V
o
p
en
s
o
u
r
ce
s
o
f
t
w
ar
e.
T
h
e
v
eh
icle
d
etec
tio
n
an
d
co
u
n
t
in
g
alg
o
r
it
h
m
w
as
ex
ec
u
te
d
f
o
r
2
s
im
u
latio
n
v
id
eo
s
an
d
3
r
ea
l
tim
e
v
id
eo
s
,
ea
ch
f
o
r
a
s
p
an
o
f
6
0
s
ec
o
n
d
s
an
d
th
e
f
o
llo
w
i
n
g
r
esu
l
ts
w
e
r
e
o
b
tain
ed
.
A
ctu
a
l
c
o
u
n
t
c
o
l
u
m
n
i
n
th
e
T
ab
le.
1
s
ig
n
i
f
ies
t
h
e
ac
t
u
al
n
u
m
b
er
o
f
v
e
h
icles
i
n
t
h
e
v
id
eo
th
i
s
co
u
n
t
w
as
o
b
tain
ed
b
y
m
a
n
u
all
y
co
u
n
tin
g
t
h
e
v
eh
ic
les.
C
o
u
n
t
o
b
ta
in
ed
co
l
u
m
n
g
iv
e
s
th
e
n
u
m
b
er
o
f
m
o
v
in
g
v
e
h
icle
s
id
en
ti
f
ied
b
y
th
e
alg
o
r
it
h
m
,
t
h
e
co
r
r
esp
o
n
d
in
g
d
ev
iatio
n
a
n
d
ac
cu
r
ac
y
i
s
m
e
n
tio
n
ed
i
n
th
e
T
ab
le
1
.
T
h
e
i
m
p
le
m
en
ta
tio
n
o
f
th
is
tech
n
iq
u
e
co
n
s
is
ts
o
f
t
w
o
d
i
f
f
er
en
t
p
r
o
g
r
a
m
s
r
u
n
n
in
g
s
i
m
u
lta
n
eo
u
s
l
y
,
o
n
e
p
r
o
g
r
a
m
co
n
s
tit
u
te
s
t
h
e
i
m
a
g
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
e
f
o
r
m
o
v
in
g
v
e
h
icle
d
etec
tio
n
an
d
co
u
n
ti
n
g
an
d
,
th
e
o
th
er
p
r
o
g
r
am
is
f
o
r
m
a
k
i
n
g
d
ec
is
io
n
o
n
s
tatu
s
o
f
tr
af
f
ic
s
i
g
n
a
l
li
g
h
t
b
ased
o
n
d
ec
is
io
n
tr
ee
.
T
h
e
o
u
tp
u
t
o
f
th
e
f
o
r
m
er
p
r
o
g
r
a
m
is
w
r
itte
n
i
n
te
x
t
f
ile
(
in
p
u
t
)
an
d
th
e
later
p
r
o
g
r
a
m
w
h
ich
is
r
u
n
n
in
g
s
i
m
u
lta
n
eo
u
s
l
y
r
ea
d
s
th
i
s
te
x
t
f
ile
(
in
p
u
t
)
an
d
m
ak
e
s
d
ec
is
io
n
o
n
tr
af
f
ic
s
i
g
n
al.
T
h
e
o
u
tp
u
t
o
f
th
e
later
p
r
o
g
r
am
ca
n
b
e
w
r
itte
n
to
a
n
o
th
er
te
x
t
f
ile
o
r
ca
n
b
e
f
ed
to
co
n
tr
o
l
s
w
itc
h
e
s
o
f
tr
af
f
ic
l
ig
h
t
s
.
T
h
e
m
o
d
el
d
esig
n
ed
h
er
e
is
f
o
r
th
e
a
u
to
n
o
m
o
u
s
tr
af
f
ic
co
n
tr
o
l
,
th
u
s
t
h
e
n
u
m
b
er
o
f
v
e
h
icles
ac
r
o
s
s
ea
ch
o
f
th
e
la
n
es
i
s
d
eter
m
i
n
ed
an
d
in
s
tan
tan
eo
u
s
l
y
w
r
i
tten
to
t
h
e
te
x
t
f
i
le
.
T
h
is
f
ile
i
s
r
ea
d
co
n
tin
u
o
u
s
l
y
b
y
d
ec
is
io
n
tr
ee
an
d
co
r
r
esp
o
n
d
in
g
l
y
th
e
s
ta
t
u
s
o
f
th
e
tr
a
f
f
ic
lig
h
ts
is
v
ar
ie
d
b
ased
o
n
th
e
r
ea
l
ti
m
e
s
itu
a
tio
n
o
f
t
h
e
j
u
n
ct
io
n
.
T
ab
le
1
.
R
esu
lt
A
n
al
y
s
is
S
l
.
n
o
A
c
t
u
a
l
c
o
u
n
t
C
o
u
n
t
o
b
t
a
i
n
e
d
D
e
v
i
a
t
i
o
n
A
c
c
u
r
a
c
y
N
a
t
u
r
e
o
f
v
i
d
e
o
1
52
52
0%
1
0
0
%
R
e
a
l
2
1
1
8
92
2
2
%
7
8
%
R
e
a
l
3
72
72
0%
1
0
0
%
S
i
mu
l
a
t
i
o
n
4
51
60
1
7
.
5
0
%
8
2
.
5
0
%
S
i
mu
l
a
t
i
o
n
5
1
0
9
1
0
6
0
.
0
2
%
9
9
.
9
8
%
R
e
a
l
T
h
e
ac
cu
r
ac
y
o
f
th
e
r
es
u
lt i
s
m
ai
n
l
y
d
o
m
in
ated
b
y
q
u
a
lit
y
o
f
th
e
v
id
eo
an
d
th
e
ca
m
er
a
o
r
ien
tatio
n
.
T
h
e
v
ar
iatio
n
o
r
d
if
f
er
en
ce
b
et
w
ee
n
th
e
ac
tu
a
l
v
eh
ic
le
co
u
n
t
an
d
t
h
e
v
e
h
icle
co
u
n
t
o
b
tain
e
d
in
tr
a
f
f
ic
v
id
eo
i
s
attr
ib
u
ted
to
th
e
f
o
llo
w
i
n
g
f
ac
t
o
r
s
:
a.
No
is
e
in
th
e
v
id
eo
-
b
ec
au
s
e
o
f
w
h
ic
h
m
o
s
t
o
f
th
e
in
f
o
r
m
atio
n
i
s
in
co
n
s
is
te
n
t
an
d
o
b
j
ec
t
d
etec
tio
n
b
ec
o
m
e
s
m
o
r
e
d
if
f
ic
u
lt.
A
p
p
l
y
i
n
g
d
en
o
i
s
i
n
g
al
g
o
r
ith
m
to
ea
ch
f
r
a
m
e
in
t
h
e
v
id
eo
ten
d
s
to
b
e
ti
m
e
co
n
s
u
m
i
n
g
an
d
r
es
u
lts
i
n
lo
s
s
o
f
u
s
e
f
u
l i
n
f
o
r
m
atio
n
.
b.
Dis
ta
n
ce
f
ac
to
r
-
w
h
e
n
t
h
e
g
r
o
u
p
o
f
v
e
h
icle
s
ar
e
v
er
y
clo
s
e,
th
e
al
g
o
r
ith
m
co
n
s
id
er
s
it
as
o
n
e
s
i
n
g
le
o
b
j
ec
t
an
d
th
u
s
t
h
e
co
u
n
ti
n
g
ca
n
n
o
t b
e
m
ad
e
1
0
0
% a
cc
u
r
ate.
c.
Qu
alit
y
o
f
t
h
e
v
id
eo
d.
P
lace
m
e
n
t/P
o
s
itio
n
o
f
th
e
ca
m
er
a
w
it
h
r
esp
ec
t to
th
e
cr
o
s
s
r
o
ad
/j
u
n
ctio
n
.
T
ab
le
2
.
Dec
is
io
n
T
r
ee
R
esu
lt
s
T
i
me
st
a
m
p
(
T
S
)
L
a
n
e
1
(
v
e
h
i
c
l
e
c
o
u
n
t
)
L
a
n
e
2
(
v
e
h
i
c
l
e
c
o
u
n
t
)
D
e
c
i
si
o
n
O
u
t
p
u
t
30
1
0
0
50
L1
L
1
g
r
e
e
n
f
o
r
3
0
se
c
s
60
1
2
0
70
L1
L
1
g
r
e
e
n
f
o
r
3
0
se
c
s
90
1
1
0
80
L1
L
1
g
r
e
e
n
f
o
r
3
0
se
c
s
1
2
0
1
3
5
85
L2
L
2
g
r
e
e
n
f
o
r
3
0
se
c
s
1
5
0
1
4
0
10
L1
L
1
g
r
e
e
n
f
o
r
3
0
se
c
s
1
8
0
30
20
L1
L
1
g
r
e
e
n
f
o
r
1
0
se
c
s
2
1
0
5
15
L2
L
2
g
r
e
e
n
f
o
r
3
0
se
c
s
2
4
0
10
1
0
5
L1
L
1
g
r
e
e
n
f
o
r
3
0
se
c
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
-
8708
A
u
t
o
n
o
mo
u
s
Tr
a
ffic S
ig
n
a
l Co
n
tr
o
l u
s
in
g
Dec
is
io
n
Tr
ee
(
A
n
a
la
M.
R
.
)
1529
T
ab
le
2
d
escr
ib
es
th
e
r
es
u
lt
o
f
d
ec
is
io
n
tr
ee
f
o
r
a
j
u
n
ctio
n
with
2
la
n
es.
L
a
n
e
1
is
g
i
v
en
g
r
ee
n
s
i
g
n
al
th
r
ice
ea
ch
w
it
h
ti
m
e
s
lo
t
o
f
3
0
s
ec
o
n
d
s
.
I
n
t
h
e
n
ex
t
t
u
r
n
e
v
en
i
f
L
1
h
a
s
m
o
r
e
n
u
m
b
er
o
f
v
eh
ic
le
t
h
an
L
2
,
s
t
ill
L
2
i
s
s
et
to
g
r
ee
n
t
h
er
eb
y
a
v
o
id
in
g
s
tar
v
atio
n
.
A
t
ti
m
e
s
ta
m
p
2
4
0
th
o
u
g
h
L
2
h
a
s
m
o
r
e
v
e
h
icles
t
h
an
L
1
s
t
ill
L
1
is
g
i
v
en
g
r
ee
n
s
i
g
n
al
i
n
o
r
d
er
to
av
o
id
s
m
all
n
u
m
b
er
o
f
v
eh
ic
les
w
ai
tin
g
f
o
r
a
r
elativ
el
y
lo
n
g
er
d
u
r
atio
n
o
f
ti
m
e.
5.
CO
NCLU
SI
O
N
T
h
e
m
o
d
el
d
esig
n
ed
f
o
r
au
t
o
n
o
m
o
u
s
tr
af
f
ic
s
i
g
n
al
co
n
tr
o
l
is
co
h
er
e
n
t
w
it
h
its
p
u
r
p
o
s
e.
T
h
e
m
et
h
o
d
o
lo
g
y
i
m
p
le
m
e
n
ted
h
er
e
is
co
m
p
letel
y
b
ased
o
n
n
u
m
b
er
o
f
v
e
h
icles
ac
r
o
s
s
ea
c
h
lan
e
s
an
d
,
s
i
n
c
e
tr
af
f
ic
co
n
g
e
s
tio
n
d
ir
ec
tl
y
d
e
p
en
d
s
o
n
n
u
m
b
er
o
f
v
e
h
icle
s
w
aiti
n
g
to
cr
o
s
s
j
u
n
ctio
n
ac
r
o
s
s
ea
ch
la
n
e.
T
h
is
tech
n
iq
u
e
m
i
n
i
m
izes
th
e
tr
af
f
ic
co
n
g
e
s
tio
n
,
a
n
d
i
n
s
o
m
e
ca
s
es
it
is
co
m
p
le
tel
y
eli
m
in
a
te
d
.
T
h
e
s
tatis
tics
o
n
th
e
v
eh
ic
le
co
u
n
t
ca
n
also
b
e
u
s
ed
f
o
r
th
e
i
n
f
r
astru
c
tu
r
al
d
ev
elo
p
m
en
t
s
u
ch
a
s
f
l
y
o
v
e
r
s
,
m
etr
o
etc.
T
h
e
d
ec
is
io
n
tr
ee
d
esig
n
ed
is
a
g
e
n
er
ic
m
o
d
el
an
d
ca
n
b
e
ex
te
n
d
ed
to
an
y
n
u
m
b
er
o
f
la
n
es
b
y
m
ak
i
n
g
ap
p
r
o
p
r
iate
ch
an
g
es
i
n
d
if
f
er
en
t
le
v
els
o
f
t
h
e
d
ec
is
io
n
tr
ee
.
T
h
e
w
o
r
s
t
ca
s
e
s
ce
n
ar
io
is
w
h
e
n
a
s
et
o
f
v
e
h
icles
o
f
a
lan
e
h
a
s
to
w
ait
f
o
r
5
co
n
tin
u
o
u
s
s
lo
ts
o
r
1
5
0
s
ec
s
.
T
h
is
s
ee
m
s
h
i
g
h
l
y
i
m
p
r
ac
tical
i
n
r
ea
lit
y
.
P
eo
p
le
ca
n
‟
t
k
n
o
w
w
h
en
ex
ac
tl
y
th
e
y
w
ill b
e
allo
w
ed
t
o
m
o
v
e
as t
h
e
d
ec
is
io
n
i
s
tak
e
n
at
r
u
n
ti
m
e
at
th
e
e
n
d
o
f
3
0
s
ec
s
o
r
a
s
lo
t.
RE
F
E
R
E
NC
E
S
[1
]
S
iu
li
Ro
y
,
S
o
m
p
ra
k
a
sh
Ba
n
d
y
o
p
a
d
h
y
a
y
,
M
u
n
m
u
n
Da
s,
S
u
v
a
d
i
p
Ba
tab
y
a
l,
S
a
n
k
h
a
d
e
e
p
P
a
l
,
“
Re
a
l
T
ime
T
ra
ff
ic
Co
n
g
e
stio
n
De
tec
ti
o
n
a
n
d
M
a
n
a
g
e
m
e
n
t
u
sin
g
Ac
ti
v
e
RF
ID
a
n
d
G
S
M
T
e
c
h
n
o
lo
g
y
”
,
In
p
ro
c
.
of
th
e
1
0
t
h
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
on
I
n
tel
li
g
e
n
t
T
ra
n
sp
o
rt
S
y
ste
ms
T
e
lec
o
mm
u
n
ica
t
io
n
(
IT
S
T
’1
0
)
.
[2
]
Nila
y
M
o
k
a
sh
i
,
“
In
telli
g
e
n
t
T
ra
ff
ic
S
ig
n
a
l
Co
n
tr
o
l
u
sin
g
Im
a
g
e
P
r
o
c
e
ss
in
g
”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
Res
e
a
rc
h
in
C
o
mp
u
ter
S
c
ien
c
e
a
n
d
M
a
n
a
g
e
me
n
t
S
t
u
d
ies
,
v
o
l
.
3,
n
o
.
10,
2
0
1
5
,
I
S
S
N:
2
3
2
1
-
7
7
8
2
.
[3
]
S
u
sm
it
a
A
.
M
e
sh
ra
m
,
A
.
V
.
M
a
lv
iy
a
,
“
T
ra
ff
ic
S
u
rv
e
il
lan
c
e
b
y
Co
u
n
ti
n
g
a
n
d
Clas
sif
ic
a
ti
o
n
o
f
v
e
h
i
c
les
f
ro
m
v
id
e
o
u
sin
g
Im
a
g
e
p
ro
c
e
ss
in
g
”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
Re
se
a
rc
h
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
M
a
n
a
g
e
me
n
t
S
tu
d
ies
, v
o
l.
1
,
n
o
.
6,
2
0
1
3
,
I
S
S
N:
2
3
2
1
-
7
7
8
2
.
[4
]
M
s.
P
a
ll
a
v
i
c
h
o
u
d
e
k
a
r,
M
s.
b
S
a
y
a
n
ti
Ba
n
e
rjee
,
P
ro
f
M
.
K.
M
u
ju
,
“
Re
a
l
ti
m
e
tra
ff
ic
li
g
h
t
c
o
n
tro
l
u
sin
g
im
a
g
e
p
ro
c
e
ss
in
g
”,
In
d
ia
n
J
o
u
rn
a
l
o
f
C
o
mp
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
,
v
ol
.
2
,
n
o.
1
,
IS
S
N:
0
9
7
6
-
5
1
6
6
,
p
p
.
6
-
1
0
.
[5
]
A
rc
h
it
P
e
sh
a
v
e
,
S
h
a
n
tan
u
Ra
jeN
im
b
a
lk
a
r,
A
ji
n
k
y
a
P
u
a
r,
V
ik
a
s
G
a
rd
a
re
,
A
b
h
ij
e
e
t
Do
d
a
k
e
,
Jiten
d
ra
W
a
y
d
a
n
d
e
,
“
A
Re
v
ie
w
o
n
A
u
to
n
o
m
o
u
s
T
ra
ff
ic
L
ig
h
ts
Co
n
tr
o
l
S
y
ste
m
”,
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
In
n
o
v
a
ti
v
e
Res
e
a
rc
h
in
Co
mp
u
te
r
a
n
d
Co
mm
u
n
ica
ti
o
n
E
n
g
i
n
e
e
rin
g
,
v
o
l.
3,
n
o
.
1
0
,
Oc
to
b
e
r
2
0
1
5
,
pp
.
1
0
0
3
4
-
1
0
0
3
7
.
[6
]
S
u
ti
k
n
o
,
He
lm
ie
A
ri
f
W
ib
a
wa
,
P
rim
a
Yu
su
f
Bu
d
iarto
,
“
Clas
sif
ica
ti
o
n
o
f
Ro
a
d
d
a
m
a
g
e
f
ro
m
d
ig
it
a
l
Im
a
g
e
u
si
n
g
Ba
c
k
p
ro
p
a
g
a
ti
o
n
Ne
u
ra
l
Ne
two
rk
”
,
IAE
S
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Arti
f
icia
l
I
n
telli
g
e
n
c
e
,
v
o
l.
6
,
n
o
.
4
,
De
c
e
m
b
e
r
2
0
1
7
,
IS
S
N:
2
2
5
2
-
8
9
3
8
.
[7
]
Ku
su
m
a
Ku
m
a
ri,
S
a
m
p
a
d
a
S
e
th
i,
Ra
m
a
k
a
n
th
Ku
m
a
r,
Nish
a
n
t
Ku
m
a
r,
A
tu
li
t
S
h
a
n
k
a
r
,
“
Driv
e
r
Dro
w
s
in
e
ss
De
tec
ti
o
n
S
y
ste
m
u
si
n
g
S
e
n
so
rs”
,
IAE
S
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
In
fo
rm
a
t
ics
a
n
d
C
o
mm
u
n
ica
ti
o
n
T
e
c
h
n
o
lo
g
y
,
v
o
l.
6
,
n
o
.
3
.
[8
]
V
a
ru
n
S
h
a
rm
a
,
“
Ob
jec
t
Co
u
n
ti
n
g
u
sin
g
M
ATLA
B”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
S
c
ien
ti
fi
c
&
En
g
in
e
e
rin
g
Res
e
a
rc
h
,
v
o
l.
5
,
n
o
.
3
,
M
a
rc
h
2
0
1
4
.
IS
S
N 2
2
2
9
-
5
5
1
8
.
[9
]
G
a
n
e
sh
R
a
g
h
tate
,
A
b
h
il
a
sh
a
K
T
i
w
a
ri
,
“
M
o
v
in
g
Ob
jec
t
Co
u
n
ti
n
g
in
V
id
e
o
S
ig
n
a
l”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
En
g
i
n
e
e
rin
g
Res
e
a
rc
h
a
n
d
Ge
n
e
r
a
l
S
c
ien
c
e
, v
o
l.
2
,
n
o
.
3
,
2
0
1
4
,
IS
S
N:
2
0
9
1
-
2
7
3
0
.
[1
0
]
Brin
d
a
R.
B,
Na
m
ra
th
a
V
e
n
k
a
tes
h
M
u
rt
h
y
,
B.
M
.
Ra
m
y
a
,
Dr.
V
ij
a
y
a
P
ra
k
a
sh
A
M
,
“
Ed
g
e
d
e
tec
ti
o
n
S
m
a
rt
T
ra
ff
ic
Co
n
tr
o
l”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
In
n
o
v
a
ti
v
e
Res
e
a
rc
h
in
El
e
c
t
ric
a
l,
El
e
c
tro
n
ics
,
In
stru
me
n
t
a
ti
o
n
a
n
d
Co
n
tro
l
En
g
i
n
e
e
rin
g
,
v
o
l.
3
,
n
o
.
1
1
,
2
0
1
5
,
IS
S
N:
2
3
2
1
-
2
0
0
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.