I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
15
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
,
p
p
.
300
~
309
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
1
.
p
p
3
0
0
-
3
0
9
300
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Portab
le
sy
stem
f
o
r re
a
l
-
time
t
ra
f
fi
c vo
lume a
nd spe
ed
estima
tion usin
g
YO
L
O
v
1
0
I
da
B
a
g
us
Sra
d
ha
Na
nd
a
,
M
a
s
ro
no
Yug
iha
rt
im
a
n,
E
k
o
P
rim
a
di H
endri,
I
M
a
de
Su
a
r
t
ik
a
I
n
d
o
n
e
si
a
n
La
n
d
Tr
a
n
s
p
o
r
t
a
t
i
o
n
P
o
l
y
t
e
c
h
n
i
c
-
S
TTD
,
B
e
k
a
si
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
6
,
2
0
2
5
R
ev
is
ed
Oct
2
4
,
2
0
2
5
Acc
ep
ted
J
an
2
2
,
2
0
2
6
Ac
c
u
ra
te
traffic
d
a
ta
is
e
ss
e
n
ti
a
l
fo
r
e
ffe
c
ti
v
e
tran
sp
o
rtati
o
n
p
la
n
n
i
n
g
a
n
d
p
o
li
c
y
m
a
k
in
g
.
Ho
we
v
e
r,
i
n
m
a
n
y
re
g
io
n
s,
e
sp
e
c
ially
th
o
s
e
lac
k
in
g
in
telli
g
e
n
t
i
n
fra
stru
c
tu
re
,
d
a
ta
c
o
ll
e
c
ti
o
n
re
m
a
in
s
d
e
p
e
n
d
e
n
t
o
n
m
a
n
u
a
l
m
e
th
o
d
s
th
a
t
a
re
lab
o
r
-
i
n
ten
si
v
e
,
ti
m
e
-
c
o
n
su
m
in
g
,
a
n
d
su
sc
e
p
ti
b
le
to
h
u
m
a
n
e
rro
r.
Wh
il
e
a
d
v
a
n
c
e
d
sy
ste
m
s
su
c
h
a
s
c
lo
se
d
-
c
ircu
it
tele
v
isio
n
(C
CTV)
a
n
d
a
re
a
traffic
c
o
n
tro
l
sy
ste
m
s
(AT
CS
)
o
ffe
r
a
u
to
m
a
ti
o
n
,
th
e
ir
h
i
g
h
c
o
st
a
n
d
in
fra
stru
c
tu
re
re
q
u
irem
e
n
ts
li
m
it
wid
e
sp
re
a
d
a
d
o
p
ti
o
n
.
T
h
is
stu
d
y
p
ro
p
o
se
s
a
p
o
rtab
le,
lo
w
-
c
o
st,
a
n
d
re
a
l
-
ti
m
e
traffic
m
o
n
it
o
rin
g
sy
ste
m
b
a
se
d
o
n
t
h
e
YO
LOv
1
0
o
b
jec
t
d
e
tec
ti
o
n
a
l
g
o
rit
h
m
.
Th
e
s
y
ste
m
o
p
e
ra
tes
u
si
n
g
o
n
l
y
a
sm
a
rtp
h
o
n
e
-
g
ra
d
e
c
a
m
e
ra
(1
0
8
0
p
,
6
0
f
p
s) an
d
a
sta
n
d
a
rd
lap
t
o
p
,
e
li
m
in
a
ti
n
g
th
e
n
e
e
d
f
o
r
e
x
p
e
n
siv
e
i
n
sta
ll
a
ti
o
n
s.
It
d
e
tec
ts,
c
las
sifies
,
a
n
d
c
o
u
n
ts
v
e
h
icle
s
a
s th
e
y
p
a
ss
th
ro
u
g
h
a
p
re
d
e
fi
n
e
d
re
g
io
n
o
f
i
n
tere
st (
ROI),
a
n
d
a
lso
e
stim
a
tes
th
e
ir
sp
e
e
d
b
a
se
d
o
n
ti
m
e
–
d
istan
c
e
m
e
a
su
re
m
e
n
ts.
F
ield
e
v
a
lu
a
t
io
n
s
u
si
n
g
fiv
e
o
n
e
-
h
o
u
r
u
rb
a
n
traffic
v
i
d
e
o
s
sh
o
we
d
e
x
c
e
ll
e
n
t
a
g
re
e
m
e
n
t
wi
th
m
a
n
u
a
l
c
o
u
n
ts,
a
c
h
iev
in
g
a
m
e
a
n
a
b
s
o
lu
t
e
p
e
rc
e
n
tag
e
e
rr
o
r
(
M
APE
)
o
f
j
u
st
0
.
3
0
%
.
S
p
e
e
d
e
stim
a
ti
o
n
tri
a
ls
c
o
n
d
u
c
ted
o
n
sa
m
p
le
c
li
p
s
a
lso
d
e
m
o
n
stra
ted
c
o
n
siste
n
t
a
n
d
p
lau
si
b
le
re
su
lt
s
.
Th
e
se
fi
n
d
i
n
g
s
h
i
g
h
li
g
h
t
th
e
sy
ste
m
’s
p
o
ten
ti
a
l
a
s
a
sc
a
lab
le
a
n
d
a
c
c
u
ra
te
a
lt
e
rn
a
ti
v
e
fo
r
traffic
m
o
n
it
o
rin
g
i
n
in
fra
stru
c
tu
re
-
li
m
it
e
d
e
n
v
iro
n
m
e
n
ts.
K
ey
w
o
r
d
s
:
Ob
ject
d
etec
tio
n
Po
r
tab
le
s
y
s
tem
R
ea
l
-
tim
e
AI
T
r
af
f
ic
v
o
lu
m
e
Veh
icle
s
p
ee
d
esti
m
atio
n
YOL
Ov
1
0
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
:
I
d
a
B
ag
u
s
Sra
d
h
a
Nan
d
a
I
n
d
o
n
esian
L
an
d
T
r
an
s
p
o
r
tatio
n
Po
ly
tech
n
ic
-
STT
D
8
9
Setu
Hig
h
way
,
B
ek
asi,
I
n
d
o
n
esia
E
m
ail: g
u
s
s
r
ad
h
a@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
Acc
u
r
ate
an
d
tim
ely
tr
a
f
f
ic
d
ata
is
a
cr
itical
co
m
p
o
n
en
t
o
f
m
o
d
er
n
u
r
b
a
n
tr
an
s
p
o
r
tatio
n
p
lan
n
in
g
,
tr
af
f
ic
en
g
in
ee
r
in
g
,
a
n
d
p
o
lic
y
m
ak
in
g
.
Am
o
n
g
v
ar
io
u
s
m
etr
ics,
tr
af
f
ic
v
o
lu
m
e
r
em
ai
n
s
o
n
e
o
f
th
e
m
o
s
t
f
u
n
d
am
e
n
tal,
in
f
l
u
en
cin
g
k
e
y
d
ec
is
io
n
s
r
elate
d
t
o
r
o
ad
ca
p
ac
ity
,
s
ig
n
al
tim
in
g
,
c
o
n
g
esti
o
n
m
itig
atio
n
s
tr
ateg
ies,
an
d
s
af
ety
in
ter
v
en
tio
n
s
[
1
]
.
I
n
m
a
n
y
d
ev
el
o
p
in
g
co
u
n
tr
ies,
h
o
we
v
er
,
tr
af
f
ic
v
o
lu
m
e
d
ata
is
s
till
o
b
tain
ed
th
r
o
u
g
h
m
an
u
al
c
o
u
n
tin
g
m
eth
o
d
s
.
T
h
ese
tec
h
n
i
q
u
es,
wh
ile
s
tr
aig
h
tf
o
r
war
d
,
ar
e
lab
o
r
-
in
ten
s
iv
e,
tim
e
-
co
n
s
u
m
in
g
,
an
d
p
r
o
n
e
to
h
u
m
an
er
r
o
r
[
2
]
.
Sem
i
-
au
to
m
ated
f
r
am
ewo
r
k
s
u
s
in
g
C
C
T
V
-
b
ased
m
u
lti
-
class
v
eh
icle
co
u
n
tin
g
h
av
e
also
b
ee
n
p
r
o
p
o
s
ed
[
3
]
,
y
et
th
eir
d
ep
lo
y
m
e
n
t
r
em
ain
s
d
ep
en
d
e
n
t
o
n
co
s
tly
f
ix
ed
in
f
r
astru
ctu
r
e,
lim
itin
g
ap
p
lica
b
ilit
y
in
r
eso
u
r
ce
-
co
n
s
tr
ain
ed
s
ettin
g
s
.
T
o
ad
d
r
ess
th
ese
lim
itatio
n
s
,
m
an
y
u
r
b
a
n
ar
ea
s
h
av
e
a
d
o
p
t
ed
au
to
m
ate
d
tr
af
f
ic
m
o
n
ito
r
i
n
g
s
y
s
tem
s
s
u
ch
as
clo
s
ed
-
cir
cu
it
telev
i
s
io
n
(
C
C
T
V)
an
d
ar
ea
tr
af
f
ic
co
n
tr
o
l
s
y
s
tem
s
(
AT
C
S)
[
4
]
.
W
h
ile
th
ese
tech
n
o
lo
g
ies
ca
n
b
e
ef
f
ec
tiv
e,
th
eir
im
p
lem
en
tatio
n
o
f
te
n
d
em
an
d
s
s
u
b
s
tan
tial
in
f
r
astru
ctu
r
e,
f
in
an
cial
in
v
estme
n
t,
an
d
s
p
ec
ialized
te
ch
n
ical
k
n
o
wled
g
e
—
f
ac
to
r
s
th
at
ca
n
h
in
d
e
r
ad
o
p
tio
n
in
s
m
aller
m
u
n
icip
alities
o
r
in
f
r
astru
ctu
r
e
-
c
o
n
s
tr
ain
ed
r
eg
io
n
s
.
Alter
n
ativ
e
ap
p
r
o
ac
h
es,
s
u
ch
as
Do
p
p
ler
r
ad
ar
,
p
r
o
v
id
e
lo
w
-
c
o
s
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
P
o
r
ta
b
le
s
ystem
fo
r
r
ea
l
-
time
t
r
a
ffic v
o
lu
me
a
n
d
s
p
ee
d
esti
ma
tio
n
u
s
in
g
…
(
I
d
a
B
a
g
u
s
S
r
a
d
h
a
N
a
n
d
a
)
301
s
en
s
in
g
s
o
lu
tio
n
s
b
u
t
lack
th
e
ab
ilit
y
to
class
if
y
v
e
h
icles
o
r
esti
m
ate
s
p
ee
d
[
5
]
.
T
h
is
h
ig
h
lig
h
ts
th
e
n
ee
d
f
o
r
s
o
lu
tio
n
s
th
at
ar
e
n
o
t
o
n
ly
ac
c
u
r
ate,
b
u
t a
ls
o
c
o
s
t
-
ef
f
ec
tiv
e,
p
o
r
tab
le,
a
n
d
ea
s
y
to
d
ep
lo
y
.
R
ec
en
t
ad
v
an
ce
s
in
ar
tific
i
al
in
tellig
en
ce
(
AI
)
a
n
d
c
o
m
p
u
ter
v
is
io
n
h
av
e
in
tr
o
d
u
ce
d
n
ew
o
p
p
o
r
tu
n
ities
f
o
r
au
to
m
atin
g
tr
af
f
ic
d
ata
c
o
llectio
n
with
o
u
t
r
ely
in
g
o
n
e
x
p
en
s
iv
e
h
ar
d
w
ar
e.
T
h
e
y
o
u
o
n
l
y
lo
o
k
o
n
ce
(
YOL
O)
f
a
m
ily
o
f
o
b
ject
d
etec
tio
n
alg
o
r
ith
m
s
h
as
b
ec
o
m
e
a
lea
d
in
g
f
r
am
e
wo
r
k
f
o
r
r
ea
l
-
tim
e
ap
p
licatio
n
s
d
u
e
to
its
ef
f
icien
cy
an
d
r
o
b
u
s
t
p
er
f
o
r
m
an
ce
[
6
]
.
T
h
e
latest
v
er
s
io
n
,
YOL
Ov
1
0
,
f
u
r
th
e
r
im
p
r
o
v
es
d
etec
tio
n
ac
cu
r
ac
y
an
d
co
m
p
u
tatio
n
al
ef
f
icien
c
y
,
en
a
b
lin
g
d
ep
lo
y
m
en
t
o
n
co
n
s
u
m
er
-
g
r
ad
e
d
e
v
ices
an
d
m
ak
in
g
it we
ll
-
s
u
ited
f
o
r
ed
g
e
-
b
ased
tr
af
f
ic
m
o
n
ito
r
i
n
g
[
7
]
.
Sev
er
al
s
tu
d
ies
h
av
e
ex
p
lo
r
ed
YOL
O
-
b
ased
im
p
lem
en
tatio
n
s
f
o
r
tr
af
f
ic
m
o
n
ito
r
in
g
.
Fo
r
in
s
tan
ce
,
a
m
o
b
ile
ap
p
licatio
n
u
tili
zin
g
YOL
Ov
8
ac
h
iev
ed
9
3
%
ac
cu
r
ac
y
in
v
e
h
icle
d
etec
tio
n
an
d
co
u
n
tin
g
u
s
in
g
a
s
m
ar
tp
h
o
n
e
ca
m
er
a
[
8
]
.
Sim
ilar
ly
,
d
r
o
n
e
-
ass
is
ted
u
r
b
an
m
o
n
ito
r
in
g
with
an
im
p
r
o
v
e
d
YOL
Ov
8
m
o
d
el
d
em
o
n
s
tr
ated
r
o
b
u
s
t
d
etec
tio
n
o
f
v
eh
icles
an
d
p
e
d
estrian
s
in
co
m
p
le
x
tr
af
f
ic
c
o
n
d
itio
n
s
[
9
]
.
W
h
ile
th
ese
s
tu
d
ies
co
n
f
ir
m
th
e
f
ea
s
ib
ilit
y
o
f
p
o
r
tab
le
tr
af
f
ic
an
aly
tics
,
th
ey
ar
e
ty
p
ically
lim
ited
to
s
in
g
le
f
u
n
ctio
n
s
(
s
u
ch
as
co
u
n
tin
g
)
o
r
r
eq
u
ir
e
s
p
ec
ia
lized
p
latf
o
r
m
s
s
u
c
h
as
u
n
m
a
n
n
ed
ae
r
ial
v
eh
icles
(
UAVs
)
.
C
o
m
p
ar
ativ
e
wo
r
k
h
as
also
s
h
o
wn
th
at
YOL
Ov
1
0
co
n
s
is
ten
tly
o
u
tp
er
f
o
r
m
s
Y
OL
Ov
8
in
d
etec
tio
n
r
o
b
u
s
tn
e
s
s
[
1
0
]
.
Me
an
w
h
ile,
r
esear
ch
o
n
v
is
io
n
-
b
ased
v
eh
icle
s
p
ee
d
esti
m
atio
n
co
n
f
ir
m
s
th
at
r
eliab
le
r
esu
lts
ca
n
b
e
ac
h
iev
e
d
th
r
o
u
g
h
ca
m
er
a
-
b
ased
s
y
s
tem
s
[
1
1
]
.
Ho
wev
er
,
m
o
s
t
ex
is
tin
g
ap
p
r
o
ac
h
es
ad
d
r
ess
eith
er
tr
af
f
ic
v
o
lu
m
e
o
r
s
p
ee
d
in
is
o
latio
n
,
r
ath
er
th
a
n
in
teg
r
ati
n
g
b
o
t
h
f
u
n
ctio
n
s
in
a
u
n
if
ied
,
lo
w
-
co
s
t f
r
am
ewo
r
k
.
T
ab
le
1
s
u
m
m
ar
izes
r
ep
r
esen
tativ
e
s
tu
d
ies
in
th
is
d
o
m
ain
,
co
m
p
ar
in
g
th
eir
ap
p
r
o
ac
h
es,
h
ar
d
war
e
r
eq
u
ir
em
e
n
ts
,
ac
cu
r
ac
y
,
co
s
t,
an
d
d
ep
lo
y
m
en
t
co
m
p
lex
ity
.
As
s
h
o
wn
,
ex
is
tin
g
s
o
lu
tio
n
s
eith
er
r
ely
o
n
co
s
tly
in
f
r
astru
ctu
r
e
(
C
C
T
V,
AT
C
S),
r
eq
u
ir
e
s
p
ec
ialized
d
ev
ices
(
r
ad
ar
,
d
r
o
n
es),
o
r
r
em
ain
f
u
n
c
tio
n
ally
lim
ited
t
o
eith
er
v
o
lu
m
e
o
r
s
p
ee
d
esti
m
atio
n
.
T
o
th
e
b
est
o
f
o
u
r
k
n
o
wled
g
e,
n
o
p
r
io
r
wo
r
k
h
as
d
e
m
o
n
s
tr
ated
a
f
u
lly
p
o
r
tab
le,
lo
w
-
co
s
t
s
y
s
tem
ca
p
ab
le
o
f
s
im
u
ltan
eo
u
s
ly
esti
m
atin
g
b
o
th
tr
af
f
ic
v
o
lu
m
e
an
d
v
eh
icle
s
p
ee
d
u
s
in
g
o
n
ly
a
s
m
ar
tp
h
o
n
e
-
g
r
ad
e
ca
m
er
a
an
d
a
lap
to
p
c
o
m
p
u
ter
.
T
h
is
s
tu
d
y
ad
d
r
ess
es
th
at
g
ap
b
y
d
ev
elo
p
in
g
a
n
d
v
alid
atin
g
s
u
ch
a
s
y
s
tem
u
n
d
e
r
r
ea
l
-
wo
r
ld
u
r
b
a
n
tr
af
f
ic
co
n
d
itio
n
s
.
T
h
e
co
n
t
r
ib
u
tio
n
s
o
f
th
is
r
esear
ch
ar
e
th
r
ee
f
o
ld
.
First,
it
p
r
o
p
o
s
es
a
lo
w
-
co
s
t
an
d
p
o
r
tab
le
s
y
s
tem
f
o
r
au
to
m
ated
tr
af
f
ic
v
o
lu
m
e
m
o
n
ito
r
in
g
u
s
in
g
YOL
Ov
1
0
.
Seco
n
d
,
it
in
teg
r
ates
v
eh
icle
s
p
ee
d
esti
m
atio
n
in
to
th
e
s
am
e
r
ea
l
-
tim
e
d
etec
tio
n
f
r
a
m
ewo
r
k
.
T
h
ir
d
,
it
v
alid
ates
th
e
s
y
s
tem
’
s
ac
cu
r
ac
y
ag
ain
s
t
m
an
u
al
co
u
n
tin
g
b
en
ch
m
ar
k
s
u
s
in
g
o
n
e
-
h
o
u
r
t
r
af
f
ic
v
id
e
o
r
ec
o
r
d
in
g
s
f
r
o
m
an
u
r
b
a
n
ar
ter
ial.
B
y
d
e
m
o
n
s
tr
atin
g
f
ea
s
ib
ilit
y
u
n
d
er
n
o
n
-
i
d
ea
l,
r
ea
l
-
wo
r
l
d
c
o
n
d
itio
n
s
,
th
is
s
tu
d
y
co
n
tr
ib
u
t
es
to
th
e
g
r
o
win
g
b
o
d
y
o
f
r
es
ea
r
ch
o
n
ac
ce
s
s
ib
le,
AI
-
d
r
iv
en
tr
an
s
p
o
r
tatio
n
s
o
lu
ti
o
n
s
.
T
ab
le
1
.
C
o
m
p
a
r
ativ
e
o
v
e
r
v
ie
w
o
f
tr
af
f
ic
m
o
n
ito
r
i
n
g
s
y
s
tem
R
e
f
e
r
e
n
c
e
A
p
p
r
o
a
c
h
H
a
r
d
w
a
r
e
/
S
e
t
u
p
A
c
c
u
r
a
c
y
C
o
s
t
/
d
e
p
l
o
y
me
n
t
c
o
m
p
l
e
x
i
t
y
Li
mi
t
a
t
i
o
n
P
e
p
p
a
e
t
a
l
.
[
4
]
,
2
0
2
1
C
C
TV
-
b
a
s
e
d
d
e
t
e
c
t
i
o
n
a
n
d
p
r
e
d
i
c
t
i
o
n
F
i
x
e
d
C
C
TV
+
s
e
r
v
e
r
s
H
i
g
h
H
i
g
h
c
o
s
t
,
c
o
m
p
l
e
x
N
o
t
p
o
r
t
a
b
l
e
N
a
i
d
o
o
e
t
a
l
.
[
5
]
,
2
0
2
5
Lo
w
-
c
o
st
D
o
p
p
l
e
r
r
a
d
a
r
R
a
d
a
r
u
n
i
t
s
R
e
l
i
a
b
l
e
M
o
d
e
r
a
t
e
c
o
st
,
med
i
u
m
se
t
u
p
N
o
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
n
o
sp
e
e
d
C
h
a
r
e
f
e
t
a
l
.
[
8
]
,
2
0
2
5
Y
O
LO
v
8
mo
b
i
l
e
a
p
p
S
martp
h
o
n
e
c
a
m
e
r
a
~
9
3
%
Lo
w
c
o
s
t
,
si
mp
l
e
O
n
l
y
c
o
u
n
t
s
v
e
h
i
c
l
e
s
D
o
u
e
t
a
l
.
[
9
]
,
2
0
2
5
D
r
o
n
e
-
b
a
s
e
d
Y
O
LO
v
8
U
A
V
c
a
mera
H
i
g
h
H
i
g
h
c
o
s
t
,
c
o
m
p
l
e
x
Li
mi
t
e
d
f
l
i
g
h
t
d
u
r
a
t
i
o
n
G
e
e
t
h
a
e
t
a
l
.
[
1
0
]
,
2
0
2
4
Y
O
LO
v
8
v
s
Y
O
LO
v
1
0
b
e
n
c
h
mar
k
D
a
t
a
s
e
t
s,
st
a
n
d
a
r
d
h
a
r
d
w
a
r
e
Y
O
LO
v
1
0
>
Y
O
LO
v
8
Lo
w
(
si
mu
l
a
t
i
o
n
)
N
o
t
a
p
p
l
i
e
d
t
o
t
r
a
f
f
i
c
mo
n
i
t
o
r
i
n
g
M
a
c
k
o
e
t
a
l
.
[
1
1
]
,
2
0
2
5
V
i
si
o
n
-
b
a
s
e
d
sp
e
e
d
e
st
i
ma
t
i
o
n
C
a
mer
a
+
v
i
s
i
o
n
a
l
g
o
r
i
t
h
ms
C
o
n
si
s
t
e
n
t
M
o
d
e
r
a
t
e
S
p
e
e
d
o
n
l
y
,
n
o
v
o
l
u
me
Th
i
s
s
t
u
d
y
P
o
r
t
a
b
l
e
Y
O
LO
v
1
0
sy
st
e
m
S
martp
h
o
n
e
(
1
0
8
0
p
,
60
f
p
s)
+
P
C
(
6
G
b
V
R
A
M
)
V
o
l
u
me
:
M
A
P
E
0
.
3
0
%,
S
p
e
e
d
c
o
n
si
s
t
e
n
t
w
i
t
h
n
o
r
ms
V
e
r
y
l
o
w
c
o
st
,
e
a
s
y
t
o
d
e
p
l
o
y
N
e
e
d
s
v
a
l
i
d
a
t
i
o
n
u
n
d
e
r
a
d
v
e
r
se
w
e
a
t
h
e
r
/
l
o
w
-
l
i
g
h
t
2.
M
E
T
H
O
D
T
h
is
s
ec
tio
n
o
u
tlin
es
th
e
co
m
p
lete
wo
r
k
f
l
o
w
f
o
r
d
e
v
elo
p
in
g
an
d
ev
alu
atin
g
th
e
p
r
o
p
o
s
e
d
p
o
r
tab
le
s
y
s
tem
f
o
r
tr
af
f
ic
v
o
lu
m
e
a
n
d
s
p
ee
d
esti
m
atio
n
b
ased
o
n
Y
OL
Ov
1
0
.
T
h
e
m
eth
o
d
o
lo
g
y
e
n
co
m
p
ass
es
s
y
s
tem
d
esig
n
,
v
eh
icle
d
etec
tio
n
a
n
d
class
if
icatio
n
.
I
t
also
in
clu
d
es
tr
af
f
ic
v
o
lu
m
e
co
m
p
u
tatio
n
,
s
p
ee
d
esti
m
atio
n
,
an
d
s
tatis
tical
v
alid
atio
n
.
2
.
1
.
Sy
s
t
e
m
o
v
er
v
iew
a
nd
t
o
o
ls
T
h
e
p
r
o
p
o
s
ed
s
y
s
tem
is
d
esig
n
ed
f
o
r
d
ep
lo
y
m
en
t
in
lo
w
-
r
e
s
o
u
r
ce
en
v
ir
o
n
m
en
ts
an
d
was
d
ev
elo
p
e
d
u
s
in
g
Py
th
o
n
as
th
e
p
r
im
ar
y
p
r
o
g
r
am
m
in
g
lan
g
u
a
g
e,
s
u
p
p
o
r
ted
b
y
a
s
u
ite
o
f
o
p
e
n
-
s
o
u
r
ce
l
ib
r
ar
ies
to
f
ac
ilit
ate
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
:
300
-
3
0
9
302
o
b
ject
d
etec
tio
n
,
v
id
e
o
p
r
o
ce
s
s
in
g
,
an
d
d
ata
ex
p
o
r
t
[
6
]
.
A
t
its
co
r
e,
th
e
s
y
s
tem
em
p
lo
y
s
YOL
Ov
1
0
f
r
o
m
Ultr
aly
tics
a
s
th
e
m
ain
d
etec
ti
o
n
en
g
in
e.
T
h
is
m
o
d
el
p
r
o
ce
s
s
es e
ac
h
f
r
am
e
o
f
in
p
u
t v
id
eo
t
o
p
er
f
o
r
m
r
ea
l
-
tim
e
o
b
ject
d
etec
tio
n
an
d
class
if
icatio
n
.
YOL
Ov
1
0
h
as
d
em
o
n
s
tr
ated
s
ig
n
if
ican
t
im
p
r
o
v
em
en
ts
o
v
er
p
r
ev
io
u
s
v
er
s
io
n
s
in
ter
m
s
o
f
b
o
t
h
d
e
tectio
n
ac
cu
r
ac
y
an
d
co
m
p
u
t
atio
n
al
ef
f
icien
cy
,
wh
ich
m
a
k
es
it
p
ar
ticu
lar
ly
s
u
itab
le
f
o
r
ed
g
e
co
m
p
u
tin
g
a
n
d
r
ea
l
-
tim
e
p
r
o
ce
s
s
in
g
o
n
s
tan
d
ar
d
h
ar
d
war
e
[
7
]
,
[
1
0
]
.
Fo
r
v
id
e
o
i
n
p
u
t
h
an
d
lin
g
an
d
f
r
a
m
e
p
r
o
ce
s
s
in
g
,
th
e
s
y
s
t
em
u
tili
ze
s
Op
en
C
V
—
o
n
e
o
f
th
e
m
o
s
t
estab
lis
h
ed
lib
r
ar
ies
in
th
e
f
ield
o
f
co
m
p
u
ter
v
is
io
n
.
Op
en
C
V
o
f
f
er
s
r
o
b
u
s
t
f
u
n
ctio
n
alities
f
o
r
im
ag
e
m
an
ip
u
latio
n
a
n
d
h
as
b
ee
n
w
id
ely
ad
o
p
ted
in
r
ea
l
-
tim
e
v
id
eo
an
aly
tics
ap
p
licatio
n
s
[
1
2
]
,
[
1
3
]
.
T
o
s
im
p
lif
y
th
e
im
p
lem
e
n
tatio
n
o
f
r
eg
io
n
o
f
in
te
r
est
(
R
OI
)
lo
g
ic
a
n
d
v
e
h
icle
cr
o
s
s
in
g
d
etec
tio
n
,
th
e
s
y
s
tem
in
teg
r
ates
th
e
cv
zo
n
e
lib
r
ar
y
.
B
u
ilt
u
p
o
n
Op
en
C
V
an
d
Me
d
iaPip
e,
cv
z
o
n
e
p
r
o
v
id
es
h
ig
h
-
lev
el
a
b
s
tr
ac
tio
n
s
th
at
en
a
b
le
r
a
p
id
p
r
o
to
ty
p
in
g
a
n
d
s
tr
ea
m
lin
ed
d
ev
elo
p
m
en
t
o
f
v
is
io
n
-
b
ased
ap
p
licatio
n
s
[
1
4
]
.
T
h
e
s
y
s
tem
’
s
o
u
tp
u
t
is
m
an
a
g
ed
th
r
o
u
g
h
in
teg
r
atio
n
with
x
lwin
g
s
,
a
lib
r
ar
y
th
at
en
ab
le
s
s
ea
m
les
s
in
ter
ac
tio
n
b
etwe
en
Py
th
o
n
a
n
d
Mic
r
o
s
o
f
t
E
x
ce
l.
T
h
is
allo
ws
tr
af
f
ic
v
o
lu
m
e
an
d
s
p
ee
d
esti
m
atio
n
r
esu
lts
to
b
e
ex
p
o
r
ted
au
to
m
atica
lly
in
to
s
p
r
ea
d
s
h
ee
t
f
o
r
m
at
f
o
r
f
u
r
th
er
a
n
aly
s
is
o
r
r
ep
o
r
tin
g
.
x
lwin
g
s
h
as
b
ee
n
p
ar
ticu
lar
ly
u
s
ef
u
l f
o
r
lig
h
tweig
h
t a
p
p
licatio
n
s
th
at
r
eq
u
ir
e
p
r
o
g
r
am
m
atic
E
x
ce
l m
an
ip
u
latio
n
[
1
5
]
.
Sy
s
tem
test
in
g
was
co
n
d
u
cted
u
s
in
g
v
id
e
o
f
o
o
tag
e
r
ec
o
r
d
ed
o
n
Gaja
h
Ma
d
a
s
tr
ee
t
,
Klu
n
g
k
u
n
g
R
eg
en
cy
,
with
a
co
n
s
u
m
e
r
-
g
r
a
d
e
s
m
ar
tp
h
o
n
e
ca
m
e
r
a
ca
p
a
b
l
e
o
f
Fu
ll
HD
(
1
0
8
0
p
)
r
eso
lu
tio
n
at
6
0
f
r
am
es
p
e
r
s
ec
o
n
d
.
T
h
e
ca
m
er
a
was
m
o
u
n
ted
o
n
a
s
tab
le
p
latf
o
r
m
a
p
p
r
o
x
im
ately
5
m
eter
s
ab
o
v
e
g
r
o
u
n
d
lev
el
an
d
5
m
eter
s
f
r
o
m
th
e
r
o
a
d
way
,
w
ith
a
tilt
a
n
g
le
o
f
ab
o
u
t
4
5
°
to
en
s
u
r
e
co
n
s
is
ten
t
co
v
er
ag
e
o
f
th
e
t
r
af
f
ic
s
tr
ea
m
.
All
p
r
o
ce
s
s
in
g
was
ex
ec
u
ted
o
n
a
s
tan
d
ar
d
lap
to
p
eq
u
ip
p
ed
with
a
GPU
with
at
least
4
GB
o
f
VR
AM
,
en
s
u
r
in
g
r
eliab
le
p
er
f
o
r
m
an
ce
wh
ile
m
ain
tain
in
g
p
o
r
tab
ilit
y
f
o
r
f
ield
d
ep
lo
y
m
en
t.
A
s
am
p
le
f
r
am
e
f
r
o
m
th
e
r
ec
o
r
d
e
d
v
id
e
o
is
p
r
esen
ted
in
s
ec
tio
n
3
,
illu
s
tr
atin
g
th
e
ty
p
ic
al
v
is
u
al
in
p
u
t u
s
ed
i
n
th
is
s
tu
d
y
.
T
h
e
o
v
er
all
w
o
r
k
f
lo
w
o
f
t
h
e
s
y
s
te
m
is
ill
u
s
t
r
at
e
d
i
n
Fi
g
u
r
e
1
,
w
h
i
c
h
p
r
es
e
n
ts
t
h
e
s
t
ep
-
by
-
s
t
ep
alg
o
r
it
h
m
ic
f
l
o
w
f
r
o
m
v
i
d
e
o
i
n
p
u
t
t
o
d
at
a
o
u
tp
u
t
.
I
n
a
d
d
iti
o
n
,
Fi
g
u
r
e
2
p
r
ese
n
ts
t
h
e
s
y
s
te
m
ar
ch
ite
ct
u
r
e
d
ia
g
r
a
m
.
I
t
h
ig
h
l
ig
h
ts
t
h
e
i
n
te
r
a
cti
o
n
b
e
twe
en
h
a
r
d
wa
r
e
,
s
o
f
tw
ar
e,
a
n
d
d
ata
f
l
o
w
c
o
m
p
o
n
e
n
ts
i
n
a
m
o
d
u
la
r
s
tr
u
ct
u
r
e
t
o
e
n
s
u
r
e
r
e
p
r
o
d
u
ci
b
i
lit
y
an
d
cl
ar
it
y
o
f
th
e
ex
p
er
im
e
n
ta
l s
et
u
p
f
o
r
p
r
o
p
o
s
e
d
t
r
a
f
f
ic
m
o
n
i
to
r
i
n
g
s
y
s
t
em
.
Fig
u
r
e
1
.
Sy
s
tem
wo
r
k
f
lo
w
f
r
o
m
v
id
e
o
in
p
u
t,
d
etec
tio
n
,
R
OI
-
b
ased
tr
ac
k
i
n
g
,
to
tr
af
f
ic
v
o
l
u
m
e
an
d
s
p
ee
d
esti
m
atio
n
o
u
tp
u
t
Fig
u
r
e
2
.
Sy
s
tem
ar
c
h
itectu
r
e
d
iag
r
am
2
.
2
.
Vehicle
det
ec
t
io
n a
nd
cla
s
s
if
ica
t
io
n
T
h
e
YOL
Ov
1
0
m
o
d
el
was
tr
ain
ed
an
d
co
n
f
ig
u
r
e
d
to
d
etec
t
th
r
ee
ca
teg
o
r
ies
o
f
v
eh
icles
p
er
tin
en
t
to
tr
af
f
ic
en
g
i
n
ee
r
in
g
:
m
o
to
r
c
y
cl
es,
lig
h
t
v
eh
icles,
an
d
h
ea
v
y
v
eh
icles.
C
lass
if
icat
io
n
r
elied
o
n
r
elativ
e
o
b
ject
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
P
o
r
ta
b
le
s
ystem
fo
r
r
ea
l
-
time
t
r
a
ffic v
o
lu
me
a
n
d
s
p
ee
d
esti
ma
tio
n
u
s
in
g
…
(
I
d
a
B
a
g
u
s
S
r
a
d
h
a
N
a
n
d
a
)
303
s
ize
an
d
s
h
ap
e,
alig
n
e
d
with
m
eth
o
d
o
l
o
g
ies
in
p
r
io
r
YOL
O
-
b
ased
tr
af
f
ic
s
tu
d
ies
[
1
6
]
.
E
ac
h
d
etec
ted
v
e
h
icle
was
as
s
ig
n
ed
a
p
ass
en
g
er
ca
r
u
n
it
(
PC
U)
v
alu
e
in
ac
co
r
d
a
n
ce
with
I
n
d
o
n
esian
tr
af
f
ic
s
tan
d
ar
d
s
:
0
.
2
5
f
o
r
m
o
to
r
cy
cles,
1
.
0
0
f
o
r
lig
h
t
v
eh
icles,
an
d
1
.
2
0
f
o
r
h
ea
v
y
v
eh
icles
[
1
7
]
.
T
h
e
ap
p
licati
o
n
o
f
PC
U
v
alu
e
s
f
ac
ilit
ates
th
e
s
tan
d
ar
d
izatio
n
o
f
h
eter
o
g
en
eo
u
s
tr
af
f
ic
f
lo
ws,
a
co
m
m
o
n
p
r
ac
tice
i
n
tr
af
f
ic
en
g
in
ee
r
in
g
t
o
ac
co
u
n
t f
o
r
v
a
r
y
in
g
v
eh
icle
ty
p
es [
1
8
]
.
T
h
e
ass
ig
n
ed
PC
U
v
alu
es a
r
e
s
u
m
m
ar
ized
in
T
ab
le
2
.
R
eg
ar
d
in
g
d
etec
tio
n
r
eliab
ilit
y
u
n
d
e
r
r
ea
l
-
wo
r
ld
co
n
d
itio
n
s
,
t
h
e
s
y
s
tem
ad
o
p
ts
a
l
o
g
ic
co
m
p
ar
ab
le
to
h
u
m
an
s
u
r
v
ey
o
r
s
.
Veh
icles
ar
e
o
n
ly
co
u
n
ted
wh
e
n
th
ei
r
ce
n
tr
o
id
s
f
u
lly
cr
o
s
s
th
e
R
OI
,
w
h
ich
p
r
e
v
en
ts
d
o
u
b
l
e
co
u
n
tin
g
d
u
r
in
g
p
ar
tial
o
cc
lu
s
io
n
s
o
r
o
v
er
lap
s
.
I
n
ca
s
es
o
f
c
o
m
p
lete
o
cc
lu
s
io
n
wh
er
e
a
v
e
h
icle
is
n
o
t
v
is
ib
le
to
eith
er
th
e
h
u
m
a
n
ey
e
o
r
th
e
ca
m
er
a,
th
e
s
y
s
tem
lik
e
a
m
an
u
al
s
u
r
v
e
y
ca
n
n
o
t
r
ec
o
r
d
th
e
o
b
ject.
Ho
wev
e
r
,
wh
en
o
n
l
y
a
p
o
r
tio
n
o
f
t
h
e
v
eh
icle
r
em
ain
s
v
is
ib
le,
th
e
Y
OL
Ov
1
0
m
o
d
el
is
s
till
ca
p
ab
le
o
f
d
etec
tin
g
an
d
class
if
y
in
g
th
e
o
b
ject
b
ased
o
n
tr
ain
ed
f
ea
tu
r
es.
L
i
g
h
t
i
n
g
c
o
n
d
i
t
i
o
n
s
a
r
e
m
a
n
a
g
e
d
i
n
s
i
m
il
a
r
w
a
y
.
A
u
t
o
m
a
t
i
c
ex
p
o
s
u
r
e
s
e
t
ti
n
g
s
o
f
c
a
m
e
r
a
a
r
e
g
e
n
e
r
a
l
l
y
s
u
f
f
i
c
i
e
n
t
t
o
e
n
s
u
r
e
t
h
a
t
v
e
h
ic
l
e
s
r
e
m
ai
n
v
i
s
i
b
l
e
f
o
r
d
e
t
e
cti
o
n
.
A
s
l
o
n
g
a
s
t
h
e
s
h
a
p
e
o
f
t
h
e
o
b
j
e
c
t
r
e
m
a
i
n
s
d
i
s
c
e
r
n
i
b
l
e
,
t
h
e
s
y
s
t
e
m
p
e
r
f
o
r
m
s
r
e
li
a
b
l
y
.
H
o
w
e
v
e
r
,
i
n
e
x
t
r
e
m
e
l
o
w
-
l
i
g
h
t
o
r
g
l
a
r
e
c
o
n
d
i
ti
o
n
s
w
h
e
r
e
o
b
j
e
ct
c
o
n
t
o
u
r
s
b
e
c
o
m
e
i
n
d
i
s
t
i
n
ct
,
d
e
te
c
t
i
o
n
a
c
c
u
r
a
c
y
d
e
c
r
e
a
s
e
s
.
I
n
s
u
c
h
c
a
s
e
s
,
m
a
n
u
a
l
a
d
j
u
s
t
m
e
n
t
o
f
c
a
m
e
r
a
e
x
p
o
s
u
r
e
o
r
t
h
e
u
s
e
o
f
c
a
m
e
r
as
w
it
h
s
u
p
e
r
i
o
r
l
o
w
-
l
i
g
h
t
s
e
n
s
i
t
i
v
i
t
y
w
o
u
ld
b
e
r
e
q
u
i
r
e
d
t
o
m
a
i
n
t
a
i
n
o
p
t
im
a
l
p
e
r
f
o
r
m
a
n
c
e
.
T
ab
le
2
.
PC
U
eq
u
iv
alen
ce
ta
b
le
V
e
h
i
c
l
e
t
y
p
e
P
C
U
v
a
l
u
e
M
o
t
o
r
c
y
c
l
e
0
.
2
5
Li
g
h
t
v
e
h
i
c
l
e
1
.
0
0
H
e
a
v
y
v
e
h
i
c
l
e
1
.
2
0
2
.
3
.
Vo
lu
m
e
lo
g
g
ing
m
ec
ha
n
is
m
T
o
alig
n
with
s
tan
d
ar
d
tr
af
f
i
c
s
u
r
v
ey
p
r
ac
tices,
th
e
p
r
o
p
o
s
ed
s
y
s
tem
was
co
n
f
ig
u
r
ed
to
r
ec
o
r
d
v
eh
icle
d
ata
in
1
5
-
m
in
u
te
in
t
er
v
als,
a
co
n
v
en
tio
n
wid
ely
a
d
o
p
ted
in
tr
af
f
ic
en
g
i
n
ee
r
in
g
to
ca
p
tu
r
e
tem
p
o
r
al
v
ar
iatio
n
s
in
tr
a
f
f
ic
f
lo
w
[
1
9
]
.
T
h
is
in
ter
v
al
n
o
t
o
n
ly
p
r
o
v
i
d
es
s
u
f
f
icien
t
g
r
an
u
lar
ity
f
o
r
a
n
aly
zin
g
s
h
o
r
t
-
ter
m
f
lu
ctu
atio
n
s
b
u
t
also
f
ac
ilit
ate
s
ag
g
r
eg
atio
n
in
to
h
o
u
r
ly
o
r
d
aily
v
o
lu
m
es
f
o
r
b
r
o
a
d
er
p
lan
n
in
g
p
u
r
p
o
s
es.
Fo
r
in
s
tan
ce
,
lar
g
e
-
s
ca
le
s
en
s
o
r
n
etwo
r
k
s
an
d
h
ig
h
-
r
eso
lu
tio
n
t
r
af
f
ic
co
n
tr
o
l
d
ata
s
tr
ea
m
s
h
a
v
e
d
em
o
n
s
tr
ated
t
h
e
ef
f
ec
tiv
en
ess
o
f
1
5
-
m
in
u
te
in
ter
v
al
lo
g
g
in
g
in
r
ev
ea
lin
g
d
etailed
u
r
b
an
tr
af
f
ic
d
y
n
a
m
ics
[
2
0
]
,
an
d
s
im
ilar
in
ter
v
al
co
n
v
en
tio
n
s
ar
e
u
s
ed
i
n
s
tu
d
ies o
f
tr
af
f
ic
ch
ar
ac
ter
is
tics
an
d
p
lan
n
in
g
[
1
9
]
,
[
2
1
]
.
I
n
p
r
ac
tice,
ev
e
r
y
v
eh
icle
c
r
o
s
s
in
g
th
e
R
OI
is
d
etec
ted
,
c
lass
if
ied
,
an
d
ass
ig
n
ed
a
PC
U
v
alu
e
to
s
tan
d
ar
d
ize
h
eter
o
g
e
n
eo
u
s
tr
a
f
f
ic
s
tr
ea
m
s
.
T
h
e
ac
cu
m
u
lated
d
ata
with
in
ea
ch
in
ter
v
al
ar
e
th
en
au
to
m
atica
lly
ex
p
o
r
ted
to
Mic
r
o
s
o
f
t
E
x
ce
l
v
ia
th
e
x
lwin
g
s
lib
r
ar
y
.
T
h
e
ex
p
o
r
ted
d
ataset
in
clu
d
es
v
eh
icl
e
co
u
n
ts
p
er
class
,
PC
U
-
eq
u
iv
alen
t to
tals
,
an
d
tim
estam
p
s
,
th
er
eb
y
m
ai
n
tain
in
g
a
s
tr
u
ctu
r
ed
an
d
a
n
aly
za
b
le
r
ec
o
r
d
.
T
h
is
au
to
m
ated
lo
g
g
in
g
m
ec
h
an
is
m
m
ir
r
o
r
s
th
e
s
tr
u
ctu
r
e
o
f
m
an
u
al
tr
a
f
f
ic
s
u
r
v
ey
s
wh
ile
e
lim
in
atin
g
th
e
p
o
ten
tial
f
o
r
h
u
m
a
n
er
r
o
r
.
B
y
p
r
eser
v
in
g
co
m
p
atib
ilit
y
with
co
n
v
en
tio
n
al
f
o
r
m
ats
u
s
ed
in
tr
an
s
p
o
r
tatio
n
p
lan
n
in
g
,
th
e
s
y
s
tem
en
ab
les
d
ir
ec
t
v
alid
atio
n
ag
ain
s
t
m
an
u
al
co
u
n
tin
g
m
et
h
o
d
s
.
I
t
also
s
u
p
p
o
r
ts
in
teg
r
atio
n
with
estab
lis
h
ed
tr
af
f
ic
an
aly
s
is
f
r
am
ewo
r
k
s
—
in
clu
d
in
g
a
p
p
r
o
ac
h
es
th
at
co
m
b
in
e
au
to
m
ated
co
u
n
ter
s
with
cr
o
wd
s
o
u
r
ce
d
tr
af
f
ic
d
ata
f
o
r
i
m
p
r
o
v
e
d
v
o
lu
m
e
-
d
elay
m
o
d
el
in
g
[
2
2
]
.
2
.
4
.
Sp
ee
d
estim
a
t
io
n
m
o
du
le
T
h
e
s
p
ee
d
esti
m
atio
n
m
o
d
u
le
was
d
ev
elo
p
ed
to
o
p
er
ate
d
ir
e
ctly
o
n
v
id
eo
f
r
am
es
with
o
u
t
r
ely
in
g
o
n
ex
ter
n
al
s
en
s
o
r
s
s
u
ch
as
GP
S
o
r
r
ad
ar
.
Veh
icle
m
o
tio
n
was
q
u
an
tifie
d
b
y
tr
ac
k
in
g
t
h
e
ce
n
tr
o
id
o
f
ea
c
h
d
etec
ted
o
b
ject
ac
r
o
s
s
co
n
s
ec
u
tiv
e
f
r
am
es.
T
h
e
d
is
p
lace
m
en
t
in
p
ix
els
was
ca
lcu
lated
u
s
in
g
th
e
E
u
clid
ea
n
d
is
tan
ce
[
2
3
]
as in
(
1
)
.
∆
=
√
(
+
∆
−
)
2
+
(
+
∆
−
)
2
(
1
)
W
h
er
e
(
,
)
an
d
(
+
∆
,
+
∆
)
r
ep
r
esen
t
th
e
ce
n
tr
o
id
co
o
r
d
in
ates
o
f
a
v
eh
icle
at
f
r
am
e
an
d
at
a
lat
er
f
r
am
e
+
∆
.
I
n
th
is
s
tu
d
y
,
∆
=
60
,
co
r
r
esp
o
n
d
in
g
to
a
o
n
e
-
s
ec
o
n
d
i
n
ter
v
al
at
6
0
f
p
s
.
T
h
is
one
-
s
ec
o
n
d
win
d
o
w
e
n
s
u
r
ed
th
at
d
is
p
lace
m
en
ts
wer
e
s
u
f
f
i
cien
tly
lar
g
e
to
m
itig
ate
p
ix
e
l
-
lev
el
n
o
is
e
wh
ile
m
ain
tain
in
g
r
ea
l
-
tim
e
r
esp
o
n
s
i
v
en
ess
.
T
o
co
n
v
er
t
p
i
x
el
d
is
p
lace
m
en
t
in
to
r
ea
l
-
wo
r
ld
d
is
tan
ce
,
a
s
ca
le
f
ac
to
r
(
/
)
was
d
er
iv
ed
f
r
o
m
a
g
r
o
u
n
d
r
ef
er
en
ce
v
is
ib
le
in
th
e
v
id
eo
f
r
am
e,
s
u
ch
as
lan
e
wid
th
o
r
r
o
ad
m
ar
k
in
g
o
f
k
n
o
w
n
p
h
y
s
ical
len
g
th
as in
(
2
)
.
=
(
2
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
:
300
-
3
0
9
304
T
h
e
ac
tu
al
tr
av
eled
d
is
tan
ce
in
m
eter
s
was th
en
ca
lcu
lated
as
(
3
)
.
=
∆
×
(
3
)
Giv
en
th
e
tim
e
in
ter
v
al
∆
=
∆
,
th
e
v
eh
icle’
s
s
p
ee
d
was c
o
m
p
u
ted
as
(
4
)
.
/
=
∆
,
/
ℎ
=
/
×
3
,
6
(
4
)
Sin
ce
∆
=
1
u
n
d
er
th
e
60
-
f
p
s
co
n
f
ig
u
r
atio
n
,
th
e
co
m
p
u
tatio
n
s
im
p
l
if
ied
to
(
5
)
.
/
ℎ
=
×
3
,
6
(
5
)
T
h
e
o
v
er
all
lo
g
ic
o
f
th
e
s
p
ee
d
esti
m
atio
n
p
r
o
ce
s
s
is
illu
s
tr
ated
in
Fig
u
r
e
3
.
T
h
e
s
y
s
tem
b
eg
in
s
b
y
d
etec
tin
g
v
eh
icles
an
d
ex
tr
ac
tin
g
th
eir
ce
n
tr
o
id
s
.
E
ac
h
v
e
h
icle
is
as
s
ig
n
ed
a
u
n
iq
u
e
tr
a
ck
in
g
I
D,
wh
ich
is
m
o
n
ito
r
ed
ac
r
o
s
s
co
n
s
ec
u
tiv
e
f
r
am
es.
On
ce
th
e
in
ter
v
al
o
f
∆
=
60
f
r
am
es
is
r
ea
c
h
ed
,
t
h
e
ce
n
tr
o
id
d
is
p
lace
m
en
t
is
co
m
p
u
ted
u
s
in
g
(
1
)
.
T
h
is
p
i
x
el
d
is
p
lace
m
e
n
t
is
th
en
co
n
v
er
ted
in
t
o
r
ea
l
d
is
tan
ce
u
s
in
g
th
e
s
ca
le
f
ac
to
r
(
2
)
an
d
(
3
)
,
f
o
llo
w
ed
b
y
s
p
ee
d
ca
lcu
latio
n
(
4
)
an
d
(
5
)
.
Fin
ally
,
th
e
esti
m
ated
s
p
ee
d
is
r
ec
o
r
d
ed
f
o
r
ea
ch
v
eh
icle
I
D.
Fig
u
r
e
3
.
Flo
wch
ar
t
s
p
ee
d
esti
m
atio
n
m
o
d
u
le
2
.
5
.
Acc
ura
cy
ev
a
lua
t
i
o
n
T
h
e
ac
cu
r
ac
y
o
f
t
h
e
p
r
o
p
o
s
ed
s
y
s
tem
was
ev
alu
ated
b
y
co
m
p
ar
in
g
its
o
u
t
p
u
ts
with
m
an
u
al
tr
af
f
ic
co
u
n
ts
,
wh
ich
s
er
v
e
d
as
th
e
g
r
o
u
n
d
tr
u
th
.
T
h
r
ee
p
r
im
ar
y
in
d
i
ca
to
r
s
wer
e
u
s
ed
:
p
r
ec
is
io
n
,
r
e
ca
ll,
an
d
F1
-
s
co
r
e,
wh
ich
ar
e
wid
ely
ap
p
lied
in
co
m
p
u
ter
v
is
io
n
a
n
d
tr
af
f
ic
m
o
n
ito
r
in
g
s
tu
d
ies
to
ass
es
s
class
if
icatio
n
an
d
d
etec
tio
n
p
er
f
o
r
m
a
n
ce
[
2
4
]
.
P
r
ec
is
io
n
(
)
m
ea
s
u
r
es
th
e
p
r
o
p
o
r
tio
n
o
f
co
r
r
ec
tly
i
d
en
tifie
d
v
eh
icles
am
o
n
g
all
d
etec
tio
n
s
,
r
ec
all
(
)
q
u
a
n
tifie
s
th
e
p
r
o
p
o
r
tio
n
o
f
co
r
r
ec
tly
d
etec
ted
v
eh
icles
r
elativ
e
to
th
e
to
tal
n
u
m
b
er
o
f
v
eh
icles
p
r
esen
t,
an
d
th
e
F1
-
s
co
r
e
r
e
p
r
esen
ts
th
e
h
ar
m
o
n
ic
m
ea
n
o
f
p
r
ec
is
io
n
an
d
r
ec
all,
p
r
o
v
id
i
n
g
a
b
alan
ce
d
p
er
f
o
r
m
an
ce
m
etr
ic
as in
(
6
)
.
=
+
,
=
+
,
1
=
2
×
×
+
(
6
)
W
h
er
e
is
tr
u
e
p
o
s
itiv
es
(
v
eh
i
cles
co
r
r
ec
tly
d
etec
ted
)
,
is
f
alse
p
o
s
itiv
es
(
in
co
r
r
ec
t
d
etec
ti
o
n
s
)
,
an
d
is
f
alse n
eg
ativ
es (
m
is
s
ed
d
etec
tio
n
s
)
.
T
o
ev
alu
ate
tr
af
f
ic
v
o
lu
m
e
esti
m
atio
n
,
th
e
m
ea
n
ab
s
o
lu
te
p
e
r
ce
n
tag
e
er
r
o
r
(
MA
PE)
was e
m
p
lo
y
ed
to
m
ea
s
u
r
e
th
e
r
elativ
e
d
ev
iatio
n
o
f
th
e
au
t
o
m
ated
s
y
s
tem
f
r
o
m
th
e
m
an
u
al
g
r
o
u
n
d
tr
u
th
as in
(
7
)
.
=
1
∑
|
−
|
×
100%
=
1
(
7
)
W
h
er
e
r
ep
r
esen
ts
th
e
m
an
u
al
(
g
r
o
u
n
d
tr
u
th
)
c
o
u
n
t a
n
d
th
e
a
u
to
m
atic
co
u
n
t f
o
r
s
am
p
le
i [
2
5
]
.
T
o
p
r
o
v
i
d
e
s
t
at
is
t
i
ca
l
r
i
g
o
r
,
a
9
5
%
c
o
n
f
i
d
e
n
c
e
i
n
t
e
r
v
a
l
(
)
w
a
s
c
a
l
c
u
la
t
e
d
f
o
r
t
h
e
e
r
r
o
r
v
a
l
u
e
s
t
o
q
u
a
n
t
i
f
y
u
n
c
e
r
t
a
i
n
t
y
[
2
6
]
.
T
h
e
w
a
s
d
e
r
i
v
e
d
u
s
i
n
g
t
h
e
s
t
a
n
d
a
r
d
e
r
r
o
r
(
)
a
c
r
o
s
s
t
h
e
f
i
v
e
v
i
d
e
o
s
am
p
l
e
s
as
(
8
)
.
=
√
,
95
%
=
Ē
±
0
.
025
,
−
1
×
(
8
)
W
h
er
e
is
s
tan
d
ar
d
d
ev
iatio
n
o
f
th
e
er
r
o
r
s
,
n
is
th
e
n
u
m
b
er
o
f
s
am
p
les,
Ē
is
th
e
m
ea
n
er
r
o
r
(
e.
g
.
,
MA
PE)
,
an
d
0
.
025
,
−
1
is
th
e
cr
itical
v
alu
e
f
r
o
m
t
h
e
s
tu
d
en
t’
s
t
-
d
is
tr
ib
u
tio
n
f
o
r
a
two
-
tailed
9
5
% c
o
n
f
id
en
ce
l
ev
el.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
P
o
r
ta
b
le
s
ystem
fo
r
r
ea
l
-
time
t
r
a
ffic v
o
lu
me
a
n
d
s
p
ee
d
esti
ma
tio
n
u
s
in
g
…
(
I
d
a
B
a
g
u
s
S
r
a
d
h
a
N
a
n
d
a
)
305
All
co
m
p
u
tatio
n
s
wer
e
p
er
f
o
r
m
ed
u
s
in
g
th
e
p
ai
r
ed
d
ataset
o
f
m
an
u
al
an
d
au
to
m
atic
co
u
n
ts
ac
r
o
s
s
f
iv
e
o
b
s
er
v
atio
n
s
am
p
les,
en
s
u
r
in
g
co
n
s
is
ten
cy
with
s
tan
d
ar
d
p
r
a
ctice
s
in
tr
af
f
ic
en
g
i
n
ee
r
in
g
a
n
d
c
o
m
p
u
te
r
v
is
io
n
b
en
ch
m
ar
k
in
g
[
2
7
]
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
T
ra
f
f
ic
v
o
lum
e
estim
a
t
i
o
n
T
h
e
d
ev
elo
p
ed
s
y
s
tem
was
ev
alu
ated
u
s
in
g
f
i
v
e
o
n
e
-
h
o
u
r
v
id
eo
r
ec
o
r
d
i
n
g
s
ca
p
tu
r
e
d
at
a
f
ix
ed
lo
ca
tio
n
alo
n
g
Gaja
h
Ma
d
a
s
tr
ee
t
,
Klu
n
g
k
u
n
g
R
eg
en
c
y
.
E
ac
h
v
id
e
o
r
e
f
lecte
d
r
ea
l
-
wo
r
l
d
tr
af
f
ic
co
n
d
itio
n
s
o
v
er
d
if
f
er
e
n
t
p
er
i
o
d
s
o
f
th
e
d
ay
.
Dete
ctio
n
a
n
d
class
if
icatio
n
wer
e
p
er
f
o
r
m
ed
u
s
in
g
YOL
Ov
1
0
,
ca
te
g
o
r
izin
g
v
eh
icles in
to
m
o
to
r
cy
cles (
M
C
)
,
lig
h
t v
eh
icles (
L
V)
,
a
n
d
h
e
av
y
v
e
h
icles (
HV)
.
Fig
u
r
e
4
illu
s
tr
ates
th
e
s
y
s
t
em
in
ter
f
ac
e
d
u
r
i
n
g
r
ea
l
-
tim
e
tr
af
f
ic
v
o
lu
m
e
esti
m
atio
n
.
Dete
cted
v
eh
icles
ar
e
en
clo
s
ed
with
in
b
o
u
n
d
in
g
b
o
x
es
lab
eled
b
y
class
an
d
co
n
f
id
en
ce
s
co
r
e
an
d
tr
ac
k
ed
as
th
ey
p
ass
th
r
o
u
g
h
th
e
R
OI
.
T
h
e
cu
m
u
l
ativ
e
class
-
b
ased
tr
af
f
ic
co
u
n
ts
ap
p
ea
r
i
n
th
e
to
p
-
lef
t
co
r
n
er
,
p
r
o
v
id
i
n
g
d
ir
ec
t
v
is
u
al
v
alid
atio
n
o
f
d
etec
ti
o
n
,
tr
ac
k
in
g
,
an
d
co
u
n
tin
g
p
er
f
o
r
m
an
ce
ad
d
r
ess
in
g
r
e
v
iewe
r
r
eq
u
ests
f
o
r
o
p
er
atio
n
al
clar
ity
.
Fig
u
r
e
4
.
Sy
s
tem
d
is
p
lay
f
o
r
tr
af
f
ic
v
o
lu
m
e
au
to
m
atic
c
o
u
n
t
Ma
n
u
al
v
e
h
icle
co
u
n
ts
wer
e
c
o
n
d
u
cte
d
b
y
tr
ai
n
ed
s
u
r
v
ey
o
r
s
u
s
in
g
s
tan
d
ar
d
tr
af
f
ic
s
u
r
v
e
y
p
r
ac
tices,
s
er
v
in
g
as
g
r
o
u
n
d
tr
u
th
f
o
r
b
en
ch
m
ar
k
in
g
.
T
ab
les
3
an
d
4
p
r
esen
t
th
e
r
esu
lts
o
f
m
a
n
u
al
an
d
a
u
to
m
ated
co
u
n
ts
,
r
esp
ec
tiv
ely
,
in
clu
d
i
n
g
u
n
it
co
u
n
ts
an
d
e
q
u
iv
al
en
t
PC
U.
T
o
q
u
a
n
tify
ac
cu
r
ac
y
ac
r
o
s
s
v
e
h
icle
ca
teg
o
r
ies,
T
ab
le
5
s
u
m
m
ar
iz
es
p
r
ec
is
io
n
,
r
ec
all,
F1
-
s
co
r
e,
MA
PE
(
%),
an
d
9
5
%
co
n
f
i
d
en
ce
in
ter
v
als
f
o
r
ea
ch
class
.
Me
tr
ics we
r
e
ca
lcu
lated
b
y
ag
g
r
eg
atin
g
d
ata
ac
r
o
s
s
all
f
iv
e
s
am
p
les.
T
ab
le
3
.
T
r
a
f
f
ic
v
o
lu
m
e
f
r
o
m
m
an
u
al
co
u
n
t
S
a
mp
l
e
Li
g
h
t
v
e
h
i
c
l
e
H
e
a
v
y
v
e
h
i
c
l
e
M
o
t
o
r
c
y
c
l
e
Tr
a
f
f
i
c
v
o
l
u
me
U
n
i
t
s
P
C
U
U
n
i
t
s
P
C
U
U
n
i
t
s
P
C
U
1
1
8
6
1
8
6
65
78
1
,
6
7
6
4
1
9
6
8
3
.
00
2
85
85
85
1
0
2
1
,
2
8
0
3
2
0
5
0
7
.
00
3
1
1
0
1
1
0
72
86
.
4
1
,
2
7
8
3
1
9
.
5
5
1
5
.
90
4
2
3
0
2
2
8
91
1
0
9
.
2
2
,
2
0
1
5
5
0
.
25
8
8
7
.
45
5
2
3
1
2
3
1
1
2
0
1
4
4
1
,
7
2
8
4
3
4
.
5
8
0
9
.
50
T
ab
le
4
.
T
r
a
f
f
ic
v
o
lu
m
e
f
r
o
m
au
to
m
atic
co
u
n
t
S
a
mp
l
e
Li
g
h
t
v
e
h
i
c
l
e
H
e
a
v
y
v
e
h
i
c
l
e
M
o
t
o
r
c
y
c
l
e
Tr
a
f
f
i
c
v
o
l
u
me
U
n
i
t
s
P
C
U
U
n
i
t
s
P
C
U
U
n
i
t
s
P
C
U
1
1
9
2
1
9
2
65
78
1
,
6
5
0
4
1
2
.
5
6
8
2
.
5
0
2
90
90
87
1
0
4
.
4
1
,
2
6
0
3
1
5
5
0
9
.
4
0
3
1
2
0
1
2
0
71
8
5
.
2
1
,
2
5
3
3
1
3
.
2
5
5
1
8
.
4
5
4
2
4
1
2
4
1
92
1
1
0
.
4
2
,
1
6
4
5
4
1
8
9
2
.
4
0
5
2
3
9
2
3
9
1
1
8
1
4
1
.
6
1
,
7
1
0
4
2
7
.
5
8
0
8
.
1
0
T
ab
le
5
.
Per
f
o
r
m
an
ce
m
etr
ics o
f
au
to
m
atic
tr
a
f
f
ic
v
o
lu
m
e
es
tim
atio
n
b
y
v
eh
icle
ty
p
e
V
e
h
i
c
l
e
t
y
p
e
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
S
c
o
r
e
M
A
P
E
(
%)
9
5
%
C
I
(
M
A
P
E)
Li
g
h
t
v
e
h
i
c
l
e
(
LV
)
0
.
9
5
5
1
.
0
0
0
0
.
9
7
7
5
.
2
9
3
.
8
8
-
6
.
7
0
H
e
a
v
y
v
e
h
i
c
l
e
(
H
V
)
0
.
9
9
3
0
.
9
9
3
0
.
9
9
3
1
.
3
0
0
.
6
2
-
1
.
9
8
M
o
t
o
r
c
y
c
l
e
(
M
C
)
1
.
0
0
0
0
.
9
8
5
0
.
9
9
2
1
.
5
6
0
.
9
1
-
2
.
2
1
O
v
e
r
a
l
l
(
m
i
c
ro
-
a
v
g
)
0
.
9
9
5
0
.
9
8
6
0
.
9
9
1
0
.
9
2
0
.
4
7
-
1
.
3
7
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
:
300
-
3
0
9
306
T
h
ese
r
esu
lts
d
em
o
n
s
tr
ate
h
ig
h
ac
cu
r
ac
y
ac
r
o
s
s
all
v
eh
icle
ca
teg
o
r
ies.
L
ig
h
t
v
eh
icles
s
h
o
w
s
lig
h
tly
h
ig
h
er
p
r
o
p
o
r
tio
n
al
er
r
o
r
,
lik
ely
d
u
e
to
class
h
eter
o
g
en
eit
y
.
Ov
er
all
MA
PE
r
em
ain
s
u
n
d
er
1
%
with
a
tig
h
t
co
n
f
id
en
ce
in
ter
v
al,
in
d
icatin
g
co
n
s
is
ten
t
s
y
s
tem
p
er
f
o
r
m
a
n
ce
.
T
h
ese
o
u
tco
m
es
alig
n
w
ith
em
er
g
in
g
s
m
ar
t
tr
af
f
ic
s
y
s
tem
s
r
ep
o
r
tin
g
s
u
b
-
5
% M
APE
as a
cc
ep
tab
le
f
o
r
u
r
b
an
d
e
p
lo
y
m
e
n
t [
4
]
.
L
astl
y
,
a
s
tati
s
tical
test
o
f
t
h
e
m
ea
n
v
o
lu
m
e
d
if
f
er
e
n
ce
b
etwe
en
m
an
u
al
an
d
au
t
o
m
a
ted
co
u
n
ts
r
etu
r
n
ed
a
9
5
%
C
I
o
f
d
if
f
e
r
en
ce
in
clu
d
in
g
ze
r
o
(
e.
g
.
,
–
3
.
7
to
+0
.
3
PC
U)
.
T
h
is
co
n
f
ir
m
s
n
o
s
tatis
tically
s
ig
n
if
ican
t
b
ias
b
etwe
en
m
et
h
o
d
s
.
T
ak
e
n
to
g
eth
er
,
th
ese
f
in
d
in
g
s
v
ali
d
ate
th
e
p
r
o
p
o
s
ed
YOL
Ov
1
0
-
b
ased
s
y
s
tem
as
a
r
eliab
le,
co
s
t
-
ef
f
e
ctiv
e
alter
n
ativ
e
to
tr
ad
itio
n
al
s
en
s
o
r
-
b
ased
tr
a
f
f
ic
m
o
n
ito
r
i
n
g
co
n
s
is
ten
t
with
tr
en
d
s
in
em
er
g
in
g
AI
-
p
o
wer
e
d
I
T
S d
ep
lo
y
m
en
ts
[
2
8
]
,
[
2
9
]
.
3
.
2
.
Sp
ee
d
estim
a
t
io
n
t
ria
ls
T
h
e
s
y
s
tem
’
s
s
p
ee
d
esti
m
atio
n
m
o
d
u
le
was
e
v
alu
ated
u
s
in
g
th
e
s
am
e
s
et
o
f
f
iv
e
v
id
eo
r
ec
o
r
d
in
g
s
em
p
lo
y
ed
in
tr
af
f
ic
v
o
lu
m
e
a
n
aly
s
is
.
As
d
etailed
in
s
ec
tio
n
2
.
5
,
v
e
h
icle
s
p
ee
d
was
d
er
i
v
ed
b
y
tr
ac
k
i
n
g
th
e
ce
n
tr
o
id
d
is
p
lace
m
en
t
o
f
ea
ch
d
etec
ted
o
b
ject
o
v
er
a
o
n
e
-
s
ec
o
n
d
in
ter
v
al
(
eq
u
i
v
alen
t
to
6
0
f
r
am
es
at
6
0
f
p
s
)
.
T
h
e
p
ix
el
d
is
p
lace
m
en
t
was
th
en
co
n
v
er
ted
i
n
to
r
ea
l
-
wo
r
l
d
d
is
tan
ce
u
s
in
g
a
s
ca
lin
g
f
a
cto
r
b
ased
o
n
th
e
k
n
o
wn
len
g
t
h
o
f
lan
e
m
ar
k
e
r
s
with
in
th
e
R
OI
,
an
d
th
e
r
esu
lti
n
g
v
alu
e
was
co
n
v
er
ted
in
to
k
ilo
m
eter
s
p
er
h
o
u
r
b
y
m
u
ltip
ly
i
n
g
with
3
.
6
.
Fig
u
r
e
5
p
r
esen
ts
an
e
x
em
p
l
ar
y
s
y
s
tem
o
u
t
p
u
t,
wh
e
r
e
ea
ch
d
etec
ted
v
eh
icle
is
an
n
o
ta
ted
with
a
b
o
u
n
d
in
g
b
o
x
,
class
lab
el,
co
n
f
id
en
ce
s
co
r
e,
an
d
r
ea
l
-
tim
e
esti
m
ated
s
p
ee
d
.
T
h
is
v
is
u
al
o
v
er
lay
u
n
d
e
r
s
co
r
es
th
e
s
y
s
tem
’
s
in
teg
r
ated
ca
p
ab
ilit
y
f
o
r
s
im
u
ltan
eo
u
s
d
etec
tio
n
,
class
if
icatio
n
,
an
d
s
p
ee
d
esti
m
atio
n
.
T
h
e
av
er
ag
e
esti
m
ated
s
p
ee
d
s
o
b
tain
ed
ac
r
o
s
s
th
e
f
iv
e
s
am
p
les ar
e
s
u
m
m
ar
ized
in
T
a
b
le
6
.
Fig
u
r
e
5
.
Sy
s
tem
d
is
p
lay
f
o
r
s
p
ee
d
esti
m
atio
n
T
ab
le
6
.
E
x
am
p
le
av
e
r
ag
e
s
p
e
ed
b
y
v
eh
icle
ty
p
e
(
tr
ial
d
ata
)
V
e
h
i
c
l
e
t
y
p
e
S
p
e
e
d
(
k
m/
h
)
9
5
%
C
I
(
k
m/
h
)
M
o
t
o
r
c
y
c
l
e
33
.
95
32
.
8
-
35
.
1
Li
g
h
t
v
e
h
i
c
l
e
35
.
32
34
.
1
-
36
.
6
H
e
a
v
y
v
e
h
i
c
l
e
28
.
20
27
.
0
-
29
.
4
T
h
ese
esti
m
ates
alig
n
with
ty
p
ical
u
r
b
an
tr
af
f
ic
b
eh
av
io
r
,
w
h
er
e
m
o
to
r
cy
cles
an
d
lig
h
t
v
e
h
icles
ten
d
to
m
o
v
e
f
aster
th
an
h
ea
v
y
v
e
h
icles,
d
u
e
to
th
eir
en
h
an
ce
d
m
an
eu
v
er
a
b
ilit
y
an
d
lo
wer
w
eig
h
t.
T
h
is
p
atter
n
is
in
lin
e
with
f
in
d
i
n
g
s
f
r
o
m
o
th
er
v
is
io
n
-
b
ased
s
p
ee
d
esti
m
atio
n
s
tu
d
ies
[
3
0
]
.
E
r
r
o
r
r
o
b
u
s
tn
ess
was
as
s
es
s
ed
v
ia
r
ep
ea
ted
s
p
ee
d
iter
atio
n
s
,
y
ield
in
g
a
MA
PE
b
elo
w
ap
p
r
o
x
i
m
ately
2
%,
co
n
f
ir
m
in
g
th
at
e
s
tim
ated
s
p
ee
d
s
lie
with
in
ac
ce
p
tab
le
er
r
o
r
m
ar
g
in
s
(
ty
p
ically
u
n
d
e
r
5
%)
as
r
ep
o
r
ted
in
p
r
io
r
liter
atu
r
e
[
1
1
]
.
T
h
e
n
a
r
r
o
w
co
n
f
id
en
ce
in
ter
v
als
f
u
r
th
er
in
d
icate
co
n
s
is
ten
t
p
er
f
o
r
m
an
ce
ac
r
o
s
s
m
u
ltip
le
s
am
p
l
es.
T
h
ese
f
in
d
in
g
s
d
em
o
n
s
tr
ate
th
at
th
e
s
y
s
tem
p
r
o
v
id
es
r
eliab
le
s
p
ee
d
esti
m
atio
n
in
ad
d
itio
n
to
v
o
lu
m
e
m
ea
s
u
r
em
en
t.
B
y
lev
er
ag
in
g
a
s
in
g
le
ca
m
er
a
a
n
d
s
tan
d
ar
d
h
a
r
d
war
e,
it
o
f
f
e
r
s
a
p
r
o
m
is
in
g
,
co
s
t
-
ef
f
ec
tiv
e
ap
p
r
o
ac
h
f
o
r
s
m
ar
t
tr
af
f
ic
m
o
n
ito
r
in
g
s
y
s
tem
s
—
p
ar
ticu
lar
ly
s
u
ited
f
o
r
lo
w
-
r
eso
u
r
ce
o
r
in
f
r
astru
ctu
r
e
-
lim
ited
co
n
tex
ts
.
3
.
3
.
Dis
cus
s
io
n
T
h
e
p
r
o
p
o
s
ed
YOL
Ov
1
0
-
b
a
s
ed
s
y
s
tem
d
eliv
er
s
s
tr
o
n
g
p
er
f
o
r
m
an
ce
.
T
r
af
f
ic
v
o
lu
m
e
MA
PE
co
n
s
is
ten
tly
u
n
d
e
r
2
%
with
n
ar
r
o
w
9
5
%
co
n
f
id
en
ce
in
ter
v
als,
an
d
r
ea
lis
tic
s
p
ee
d
esti
m
ates
—
m
o
to
r
cy
cles
at
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
P
o
r
ta
b
le
s
ystem
fo
r
r
ea
l
-
time
t
r
a
ffic v
o
lu
me
a
n
d
s
p
ee
d
esti
ma
tio
n
u
s
in
g
…
(
I
d
a
B
a
g
u
s
S
r
a
d
h
a
N
a
n
d
a
)
307
~3
4
k
m
/h
,
lig
h
t
v
eh
icles
~3
5
k
m
/h
,
h
ea
v
y
v
eh
icles
~2
8
k
m
/h
.
T
h
ese
r
esu
lts
alig
n
with
estab
lis
h
ed
p
er
f
o
r
m
an
ce
b
en
c
h
m
ar
k
s
f
o
r
v
id
eo
-
b
ased
tr
af
f
ic
m
o
n
ito
r
in
g
s
y
s
tem
s
,
wh
ich
r
ep
o
r
t
ac
ce
p
tab
le
MA
PE
th
r
esh
o
ld
s
b
elo
w
5
% in
f
ield
d
ep
lo
y
m
en
ts
[
2
9
]
,
[
3
1
]
.
I
n
ter
m
s
o
f
p
r
ac
tical
d
e
p
lo
y
m
en
t,
th
e
ca
m
e
r
a
-
b
ased
s
o
lu
tio
n
o
f
f
e
r
s
s
ig
n
if
ican
t
ad
v
an
t
ag
es
o
v
er
tr
ad
itio
n
al
m
eth
o
d
s
.
R
ad
ar
s
y
s
tem
s
p
r
o
v
id
e
h
ig
h
ac
cu
r
ac
y
b
u
t
ar
e
co
s
tly
an
d
less
f
lex
ib
le;
lo
o
p
d
etec
to
r
s
ar
e
in
tr
u
s
iv
e
an
d
r
e
q
u
ir
e
r
o
ad
m
o
d
if
icatio
n
[
3
2
]
,
[
3
3
]
.
Fo
r
ex
am
p
le,
r
a
d
ar
-
b
ased
d
etec
to
r
s
s
u
ch
as
W
av
etr
o
n
ix
Sm
ar
tSen
s
o
r
HD
r
ep
o
r
t
v
o
lu
m
e
ac
cu
r
ac
y
with
in
1
.
6
%
an
d
s
p
ee
d
er
r
o
r
s
b
elo
w
1
m
p
h
,
wh
ile
co
m
p
ar
ativ
e
s
tu
d
ies
f
o
u
n
d
r
ad
a
r
an
d
iC
o
n
e
s
en
s
o
r
s
p
r
o
d
u
ce
d
s
p
ee
d
er
r
o
r
s
o
f
1
.
4
%
–
1
.
5
%
a
n
d
v
o
lu
m
e
e
r
r
o
r
s
o
f
7
.
8
%
–
8
.
6
%
ag
ain
s
t
p
n
eu
m
atic
r
o
a
d
tu
b
es
[
2
9
]
.
T
h
ese
b
e
n
ch
m
a
r
k
s
in
d
ic
ate
th
at
th
e
ac
c
u
r
ac
y
ac
h
iev
e
d
b
y
o
u
r
s
y
s
tem
is
co
m
p
ar
ab
le
to
estab
lis
h
ed
s
en
s
in
g
tech
n
o
lo
g
ies.
I
m
p
o
r
ta
n
tly
,
th
e
p
r
o
p
o
s
ed
s
o
lu
tio
n
r
em
ain
s
lo
w
-
co
s
t,
non
-
in
t
r
u
s
iv
e,
an
d
p
o
r
tab
le,
m
ak
in
g
it
esp
ec
ially
s
u
itab
le
f
o
r
d
ev
el
o
p
in
g
r
eg
io
n
s
wh
er
e
d
ep
lo
y
m
e
n
t
b
u
d
g
ets
an
d
in
f
r
astru
ctu
r
e
m
o
d
if
icatio
n
s
ar
e
co
n
s
tr
ain
ed
.
T
h
e
s
y
s
tem
n
ev
er
th
eless
f
ac
es
ch
allen
g
es
in
m
u
lti
-
lan
e
co
n
d
itio
n
s
,
n
ig
h
ttime
o
p
er
atio
n
,
an
d
ad
v
er
s
e
wea
th
er
.
As
with
m
o
s
t
ca
m
er
a
-
b
ased
s
o
lu
tio
n
s
,
o
cc
lu
s
io
n
an
d
p
o
o
r
illu
m
i
n
atio
n
m
a
y
r
ed
u
ce
d
etec
tio
n
r
o
b
u
s
tn
ess
.
E
n
h
an
ce
m
en
ts
s
u
ch
as
m
u
lti
-
ca
m
er
a
f
u
s
io
n
,
ad
ap
tiv
e
illu
m
in
atio
n
,
o
r
i
m
ag
e
en
h
an
ce
m
e
n
t
tech
n
iq
u
es
co
u
ld
h
elp
o
v
er
co
m
e
th
ese
lim
itatio
n
s
.
Ad
d
itio
n
ally
,
th
e
ar
ch
itectu
r
e
s
u
p
p
o
r
t
s
ed
g
e
d
ep
lo
y
m
en
t,
wh
er
e
lo
ca
l
p
r
o
ce
s
s
in
g
r
ed
u
c
es
b
an
d
wid
th
a
n
d
laten
cy
,
en
ab
lin
g
in
teg
r
atio
n
with
in
ter
n
et
o
f
th
in
g
s
(
I
o
T
)
f
r
am
ewo
r
k
s
a
n
d
ad
ap
tiv
e
tr
af
f
ic
co
n
tr
o
l
p
latf
o
r
m
s
[
3
4
]
,
[
3
5
]
.
Fu
tu
r
e
wo
r
k
s
h
o
u
ld
a
d
d
r
e
s
s
s
ca
lab
ilit
y
ac
r
o
s
s
d
iv
er
s
e
r
o
ad
en
v
ir
o
n
m
e
n
ts
an
d
ex
p
lo
r
e
tig
h
ter
i
n
teg
r
atio
n
with
in
tellig
en
t tr
an
s
p
o
r
t sy
s
tem
s
.
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
p
r
esen
ted
a
p
o
r
tab
le,
lo
w
-
co
s
t,
an
d
n
o
n
-
in
tr
u
s
iv
e
YOL
Ov
1
0
-
b
ased
s
y
s
tem
f
o
r
r
ea
l
-
tim
e
tr
af
f
ic
m
o
n
ito
r
in
g
,
ca
p
ab
le
o
f
esti
m
atin
g
b
o
th
tr
af
f
ic
v
o
lu
m
e
a
n
d
v
eh
icle
s
p
ee
d
w
ith
h
ig
h
ac
cu
r
ac
y
.
Valid
atio
n
ag
ain
s
t
m
an
u
al
g
r
o
u
n
d
tr
u
th
s
h
o
wed
ex
ce
llen
t
ag
r
ee
m
en
t,
with
a
MA
PE
b
elo
w
2
%
a
n
d
d
etec
tio
n
m
etr
ics
(
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e)
c
o
n
s
is
ten
tly
ab
o
v
e
0
.
9
7
,
wh
ile
s
p
ee
d
esti
m
atio
n
r
esu
lts
alig
n
ed
with
r
ea
lis
tic
r
o
ad
way
co
n
d
itio
n
s
.
T
h
e
f
r
am
ew
o
r
k
o
p
er
ates
e
f
f
ec
tiv
ely
u
s
in
g
c
o
n
s
u
m
er
-
g
r
ad
e
ca
m
er
as
an
d
s
tan
d
ar
d
co
m
p
u
tin
g
h
ar
d
war
e,
m
ak
in
g
it
p
r
ac
tical
f
o
r
d
e
p
lo
y
m
en
t
in
r
eso
u
r
ce
-
c
o
n
s
tr
a
in
ed
en
v
ir
o
n
m
en
ts
.
Alth
o
u
g
h
ch
allen
g
es
r
em
ain
in
h
an
d
lin
g
m
u
lti
-
lan
e
tr
af
f
ic,
n
ig
h
t
-
tim
e
o
p
e
r
atio
n
,
an
d
ad
v
er
s
e
wea
th
er
,
th
is
wo
r
k
d
em
o
n
s
tr
ates
th
e
f
ea
s
ib
ilit
y
o
f
v
is
io
n
-
b
ased
d
ee
p
lear
n
in
g
as
a
s
ca
lab
le
alter
n
ativ
e
to
in
tr
u
s
iv
e
tr
af
f
ic
co
u
n
ter
s
,
h
ig
h
lig
h
tin
g
its
p
o
te
n
tial
in
teg
r
atio
n
in
to
f
u
t
u
r
e
i
n
tellig
en
t
tr
an
s
p
o
r
tatio
n
s
y
s
tem
s
an
d
r
ein
f
o
r
cin
g
its
co
n
tr
ib
u
tio
n
as a
n
o
v
el,
f
ield
-
d
ep
lo
y
a
b
le
s
o
lu
tio
n
f
o
r
m
o
d
er
n
tr
af
f
ic
an
al
y
tics
.
ACK
NO
WL
E
DG
M
E
N
T
S
T
h
e
au
th
o
r
s
wo
u
ld
lik
e
to
t
h
an
k
th
e
Dep
a
r
tm
en
t
o
f
T
r
a
n
s
p
o
r
tatio
n
o
f
Klu
n
g
k
u
n
g
R
eg
en
cy
f
o
r
f
ac
ilit
atin
g
th
e
d
ata
co
llectio
n
p
r
o
ce
s
s
,
an
d
I
n
d
o
n
esian
L
an
d
T
r
an
s
p
o
r
tatio
n
Po
ly
tech
n
ic
-
STT
D,
B
ek
asi,
f
o
r
th
eir
ac
ad
em
ic
s
u
p
p
o
r
t d
u
r
in
g
th
is
s
tu
d
y
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
s
tu
d
y
was
s
u
p
p
o
r
ted
b
y
I
n
d
o
n
esian
L
an
d
T
r
an
s
p
o
r
tatio
n
Po
ly
tech
n
ic
-
STT
D
’
s
in
s
titu
tio
n
al
r
esear
ch
f
u
n
d
in
g
.
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
I
d
a
B
ag
u
s
Sra
d
h
a
N
an
d
a
✓
✓
✓
✓
✓
✓
✓
✓
✓
Ma
s
r
o
n
o
Yu
g
i
h
ar
tim
an
✓
✓
✓
✓
✓
✓
✓
✓
✓
E
k
o
Prim
ad
i H
en
d
r
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
I
Ma
d
e
Su
ar
tik
a
✓
✓
✓
✓
✓
✓
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
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
:
300
-
3
0
9
308
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
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
ataset
u
s
ed
in
th
is
s
tu
d
y
is
av
ailab
le
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
a
u
th
o
r
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
X
.
Y
a
n
,
Y
.
Z
h
a
o
,
a
n
d
H
.
X
.
L
i
u
,
“
A
p
r
o
b
a
b
i
l
i
st
i
c
m
o
d
e
l
f
o
r
mi
ss
i
n
g
t
r
a
f
f
i
c
v
o
l
u
me
r
e
c
o
n
s
t
r
u
c
t
i
o
n
b
a
se
d
o
n
d
a
t
a
f
u
si
o
n
,
”
a
rXi
v
:
2
1
0
5
.
0
2
7
7
7
,
M
a
y
2
0
2
1
.
[
2
]
J.
P
a
ľ
o
,
J.
C
a
b
a
n
,
M
.
K
i
k
t
o
v
á
,
a
n
d
Ľ.
Č
e
r
n
i
c
k
ý
,
“
Th
e
c
o
m
p
a
r
i
s
o
n
o
f
a
u
t
o
m
a
t
i
c
t
r
a
f
f
i
c
c
o
u
n
t
i
n
g
a
n
d
ma
n
u
a
l
t
r
a
f
f
i
c
c
o
u
n
t
i
n
g
,
”
I
O
P
C
o
n
f
e
re
n
c
e
S
e
r
i
e
s:
Ma
t
e
r
i
a
l
s
S
c
i
e
n
c
e
a
n
d
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
7
1
0
,
n
o
.
1
,
D
e
c
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
5
7
-
8
9
9
X
/
7
1
0
/
1
/
0
1
2
0
4
1
.
[
3
]
K.
-
H
.
N
.
B
u
i
,
H
.
Y
i
,
a
n
d
J.
C
h
o
,
“
A
mu
l
t
i
-
c
l
a
ss
m
u
l
t
i
-
m
o
v
e
me
n
t
v
e
h
i
c
l
e
c
o
u
n
t
i
n
g
f
r
a
mew
o
r
k
f
o
r
t
r
a
f
f
i
c
a
n
a
l
y
si
s
i
n
c
o
m
p
l
e
x
a
r
e
a
s
u
si
n
g
C
C
TV
s
y
s
t
e
ms
,
”
En
e
rg
i
e
s
,
v
o
l
.
1
3
,
n
o
.
8
,
A
p
r
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
3
0
8
2
0
3
6
.
[
4
]
M
.
V
.
P
e
p
p
a
e
t
a
l
.
,
“
To
w
a
r
d
s
a
n
e
n
d
-
to
-
e
n
d
f
r
a
mew
o
r
k
o
f
C
C
TV
-
b
a
s
e
d
u
r
b
a
n
t
r
a
f
f
i
c
v
o
l
u
me
d
e
t
e
c
t
i
o
n
a
n
d
p
r
e
d
i
c
t
i
o
n
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
1
,
n
o
.
2
,
Ja
n
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
1
0
2
0
6
2
9
.
[
5
]
M
.
N
a
i
d
o
o
,
S
.
P
a
i
n
e
,
A
.
K
.
M
i
sh
r
a
,
a
n
d
M
.
Y
.
A
.
G
a
f
f
a
r
,
“
R
e
l
i
a
b
l
e
t
r
a
f
f
i
c
mo
n
i
t
o
r
i
n
g
u
s
i
n
g
l
o
w
-
c
o
st
d
o
p
p
l
e
r
r
a
d
a
r
u
n
i
t
s,
”
i
n
2
0
2
4
I
n
t
e
r
n
a
t
i
o
n
a
l
Ra
d
a
r
C
o
n
f
e
re
n
c
e
(
RA
D
AR)
,
O
c
t
.
2
0
2
4
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
R
A
D
A
R
5
8
4
3
6
.
2
0
2
4
.
1
0
9
9
3
6
4
7
.
[
6
]
J.
T
e
r
v
e
n
,
D
.
-
M
.
C
.
-
Es
p
a
r
z
a
,
a
n
d
J.
-
A
.
R
.
-
G
o
n
z
á
l
e
z
,
“
A
c
o
m
p
r
e
h
e
n
si
v
e
r
e
v
i
e
w
o
f
y
o
l
o
a
r
c
h
i
t
e
c
t
u
r
e
s
i
n
c
o
mp
u
t
e
r
v
i
si
o
n
:
f
r
o
m
y
o
l
o
v
1
t
o
y
o
l
o
v
8
a
n
d
y
o
l
o
-
n
a
s,
”
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
a
n
d
K
n
o
w
l
e
d
g
e
E
x
t
ra
c
t
i
o
n
,
v
o
l
.
5
,
n
o
.
4
,
p
p
.
1
6
8
0
–
1
7
1
6
,
N
o
v
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
ma
k
e
5
0
4
0
0
8
3
.
[
7
]
A
.
W
a
n
g
e
t
a
l
.
,
“
Y
O
LO
v
1
0
:
r
e
a
l
-
t
i
me
e
n
d
-
to
-
e
n
d
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
,
”
a
rXi
v
:
2
4
0
5
.
1
4
4
5
8
,
O
c
t
.
2
0
2
4
.
[
8
]
A
.
C
h
a
r
e
f
,
Z
.
J
a
r
i
r
,
a
n
d
M
.
Q
u
a
f
a
f
o
u
,
“
M
o
b
i
l
e
a
p
p
l
i
c
a
t
i
o
n
u
t
i
l
i
z
i
n
g
y
o
l
o
v
8
f
o
r
r
e
a
l
-
t
i
me
u
r
b
a
n
t
r
a
f
f
i
c
d
a
t
a
c
o
l
l
e
c
t
i
o
n
,
”
E
3
S
W
e
b
o
f
C
o
n
f
e
re
n
c
e
s
,
v
o
l
.
6
0
1
,
Ja
n
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
5
1
/
e
3
s
c
o
n
f
/
2
0
2
5
6
0
1
0
0
0
7
7
.
[
9
]
H
.
D
o
u
,
S
.
C
h
e
n
,
F
.
X
u
,
Y
.
Li
u
,
a
n
d
H
.
Z
h
a
o
,
“
A
n
a
l
y
si
s
o
f
v
e
h
i
c
l
e
a
n
d
p
e
d
e
s
t
r
i
a
n
d
e
t
e
c
t
i
o
n
e
f
f
e
c
t
s
o
f
i
m
p
r
o
v
e
d
Y
O
LO
v
8
m
o
d
e
l
i
n
d
r
o
n
e
-
a
ssi
st
e
d
u
r
b
a
n
t
r
a
f
f
i
c
mo
n
i
t
o
r
i
n
g
s
y
st
e
m,”
PLO
S
O
N
E
,
v
o
l
.
2
0
,
n
o
.
3
,
M
a
r
.
2
0
2
5
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
3
1
4
8
1
7
.
[
1
0
]
A
.
S
.
G
e
e
t
h
a
,
M
.
A
.
R
.
A
l
i
f
,
M
.
H
u
s
sai
n
,
a
n
d
P
.
A
l
l
e
n
,
“
C
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
s
i
s
o
f
Y
O
LO
v
8
a
n
d
Y
O
LO
v
1
0
i
n
v
e
h
i
c
l
e
d
e
t
e
c
t
i
o
n
:
p
e
r
f
o
r
m
a
n
c
e
me
t
r
i
c
s
a
n
d
mo
d
e
l
e
f
f
i
c
a
c
y
,
”
V
e
h
i
c
l
e
s
,
v
o
l
.
6
,
n
o
.
3
,
p
p
.
1
3
6
4
–
1
3
8
2
,
A
u
g
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
v
e
h
i
c
l
e
s6
0
3
0
0
6
5
.
[
1
1
]
A
.
M
a
c
k
o
,
L.
G
a
j
d
o
še
c
h
,
a
n
d
V
.
K
o
c
u
r
,
“
Ef
f
i
c
i
e
n
t
v
i
s
i
o
n
-
b
a
se
d
v
e
h
i
c
l
e
s
p
e
e
d
e
s
t
i
m
a
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
Re
a
l
-
T
i
m
e
I
m
a
g
e
Pro
c
e
ssi
n
g
,
v
o
l
.
2
2
,
n
o
.
3
,
J
u
n
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
5
5
4
-
025
-
0
1
7
0
4
-
z.
[
1
2
]
A
.
B
u
s
t
a
m
a
n
t
e
,
L.
M
.
B
e
l
mo
n
t
e
,
R
.
M
o
r
a
l
e
s,
A
.
P
e
r
e
i
r
a
,
a
n
d
A
.
F
.
-
C
a
b
a
l
l
e
r
o
,
“
V
i
d
e
o
p
r
o
c
e
ssi
n
g
f
r
o
m
a
v
i
r
t
u
a
l
u
n
ma
n
n
e
d
a
e
r
i
a
l
v
e
h
i
c
l
e
:
c
o
m
p
a
r
i
n
g
t
w
o
a
p
p
r
o
a
c
h
e
s
t
o
u
si
n
g
o
p
e
n
c
v
i
n
u
n
i
t
y
,
”
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
2
,
n
o
.
1
2
,
J
u
n
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
2
1
2
5
9
5
8
.
[
1
3
]
O
p
e
n
C
V
,
“
G
e
t
t
i
n
g
st
a
r
t
e
d
w
i
t
h
v
i
d
e
o
s,
”
O
p
e
n
S
o
u
rc
e
C
o
m
p
u
t
e
r
V
i
s
i
o
n
.
A
c
c
e
ss
e
d
:
M
a
y
3
,
2
0
2
5
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
d
o
c
s.
o
p
e
n
c
v
.
o
r
g
/
4
.
x
/
d
d
/
d
4
3
/
t
u
t
o
r
i
a
l
_
p
y
_
v
i
d
e
o
_
d
i
s
p
l
a
y
.
h
t
m
l
[
1
4
]
C
V
Zo
n
e
“
c
v
z
o
n
e
:
c
o
m
p
u
t
e
r
v
i
si
o
n
p
a
c
k
a
g
e
f
o
r
O
p
e
n
C
V
a
n
d
me
d
i
a
p
i
p
e
,
”
G
i
t
H
u
b
.
A
c
c
e
sse
d
:
M
a
y
3
,
2
0
2
5
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
g
i
t
h
u
b
.
c
o
m/
c
v
z
o
n
e
/
c
v
z
o
n
e
[
1
5
]
F
.
Z
u
ms
t
e
i
n
,
P
y
t
h
o
n
f
o
r
Ex
c
e
l
:
a
m
o
d
e
rn
e
n
v
i
ro
n
m
e
n
t
f
o
r
a
u
t
o
m
a
t
i
o
n
a
n
d
d
a
t
a
a
n
a
l
y
s
i
s
.
S
e
b
a
st
o
p
o
l
,
C
A
,
U
S
A
:
O
’
R
e
i
l
l
y
M
e
d
i
a
,
I
n
c
.
,
2
0
2
1
.
[
1
6
]
M
.
L.
A
l
i
a
n
d
Z.
Z
h
a
n
g
,
“
T
h
e
Y
O
L
O
f
r
a
mew
o
r
k
:
a
c
o
m
p
r
e
h
e
n
si
v
e
r
e
v
i
e
w
o
f
e
v
o
l
u
t
i
o
n
,
a
p
p
l
i
c
a
t
i
o
n
s
,
a
n
d
b
e
n
c
h
m
a
r
k
s
i
n
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
,
”
C
o
m
p
u
t
e
rs
,
v
o
l
.
13
,
n
o
.
12
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
c
o
m
p
u
t
e
r
s
1
3
1
2
0
3
3
6
.
[
1
7
]
M
.
Z
u
d
h
y
,
I
.
D
.
S
t
u
d
e
n
t
,
T.
S
u
mi
,
a
n
d
A
.
M
u
n
a
w
a
r
,
“
I
mp
l
e
me
n
t
a
t
i
o
n
o
f
t
h
e
1
9
9
7
I
n
d
o
n
e
s
i
a
n
h
i
g
h
w
a
y
c
a
p
a
c
i
t
y
ma
n
u
a
l
(
M
K
JI
)
v
o
l
u
me
d
e
l
a
y
f
u
n
c
t
i
o
n
(
i
n
I
n
d
o
n
e
s
i
a
n
c
o
n
t
e
x
t
)
,
”
J
o
u
r
n
a
l
o
f
t
h
e
E
a
st
e
rn
A
si
a
S
o
c
i
e
t
y
f
o
r
T
ra
n
s
p
o
r
t
a
t
i
o
n
S
t
u
d
i
e
s
,
v
o
l
.
8
,
p
p
.
3
5
0
–
3
6
0
,
2
0
1
0
.
[
1
8
]
J.
-
D
.
W
u
,
B
.
-
Y
.
C
h
e
n
,
W
.
-
J
.
S
h
y
r
,
a
n
d
F
.
-
Y
.
S
h
i
h
,
“
V
e
h
i
c
l
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
n
d
c
o
u
n
t
i
n
g
sy
s
t
e
m
u
si
n
g
Y
O
LO
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
t
e
c
h
n
o
l
o
g
y
,
”
T
ra
i
t
e
m
e
n
t
d
u
S
i
g
n
a
l
,
v
o
l
.
3
8
,
n
o
.
4
,
p
p
.
1
0
8
7
–
1
0
9
3
,
A
u
g
.
2
0
2
1
,
d
o
i
:
1
0
.
1
8
2
8
0
/
t
s.
3
8
0
4
1
9
.
[
1
9
]
S
.
F
u
,
H
.
S
h
i
,
S
.
L
i
a
n
g
,
X
.
W
a
n
g
,
a
n
d
B
.
R
a
n
,
“
A
n
a
l
y
t
i
c
a
l
o
p
t
i
mi
z
e
d
t
r
a
f
f
i
c
f
l
o
w
r
e
c
o
v
e
r
y
f
o
r
l
a
r
g
e
-
sca
l
e
u
r
b
a
n
t
r
a
n
s
p
o
r
t
a
t
i
o
n
n
e
t
w
o
r
k
,
”
a
r
Xi
v
:
2
4
0
9
.
0
3
9
0
6
,
2
0
2
4
.
[
2
0
]
Y
.
L
i
,
Q
.
Z
h
a
o
,
a
n
d
M
.
W
a
n
g
,
“
H
i
g
h
-
r
e
so
l
u
t
i
o
n
t
r
a
f
f
i
c
f
l
o
w
d
a
t
a
f
r
o
m
t
h
e
u
r
b
a
n
t
r
a
f
f
i
c
c
o
n
t
r
o
l
s
y
st
e
m
i
n
g
l
a
s
g
o
w
,
”
S
c
i
e
n
t
i
f
i
c
D
a
t
a
,
v
o
l
.
1
2
,
n
o
.
1
,
F
e
b
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
7
-
0
2
5
-
0
4
4
9
4
-
y.
[
2
1
]
S
.
C
h
a
u
h
a
n
,
S
.
D
a
v
e
,
J.
S
h
a
h
,
a
n
d
A
.
K
e
d
i
a
,
“
A
sses
si
n
g
t
r
a
f
f
i
c
c
h
a
r
a
c
t
e
r
i
s
t
i
c
s
f
o
r
safe
p
e
d
e
s
t
r
i
a
n
c
r
o
ssi
n
g
s:
d
e
v
e
l
o
p
i
n
g
w
a
r
r
a
n
t
s
f
o
r
su
s
t
a
i
n
a
b
l
e
u
r
b
a
n
s
a
f
e
t
y
,
”
S
u
s
t
a
i
n
a
b
i
l
i
t
y
,
v
o
l
.
1
6
,
n
o
.
1
0
,
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
su
1
6
1
0
4
1
8
2
.
[
2
2
]
G
.
C
a
s
e
y
,
B
.
Z
h
a
o
,
K
.
K
u
mar,
a
n
d
K
.
S
o
g
a
,
“
C
o
n
t
e
x
t
-
sp
e
c
i
f
i
c
v
o
l
u
me
–
d
e
l
a
y
c
u
r
v
e
s
b
y
c
o
m
b
i
n
i
n
g
c
r
o
w
d
-
s
o
u
r
c
e
d
t
r
a
f
f
i
c
d
a
t
a
w
i
t
h
a
u
t
o
m
a
t
e
d
t
r
a
f
f
i
c
c
o
u
n
t
e
r
s
:
a
c
a
se
s
t
u
d
y
f
o
r
L
o
n
d
o
n
,
”
D
a
t
a
-
C
e
n
t
ri
c
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
7
/
d
c
e
.
2
0
2
0
.
1
8
.
[
2
3
]
H
.
Li
a
n
e
t
a
l
.
,
“
V
e
h
i
c
l
e
sp
e
e
d
m
e
a
s
u
r
e
me
n
t
me
t
h
o
d
u
si
n
g
m
o
n
o
c
u
l
a
r
c
a
meras,
”
S
c
i
e
n
t
i
f
i
c
R
e
p
o
r
t
s
,
v
o
l
.
1
5
,
n
o
.
1
,
J
a
n
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
025
-
8
7
0
7
7
-
6.
[
2
4
]
R
.
Y
a
c
o
u
b
y
a
n
d
D
.
A
x
m
a
n
,
“
P
r
o
b
a
b
i
l
i
st
i
c
e
x
t
e
n
si
o
n
o
f
p
r
e
c
i
s
i
o
n
,
r
e
c
a
l
l
,
a
n
d
F
1
sc
o
r
e
f
o
r
mo
r
e
t
h
o
r
o
u
g
h
e
v
a
l
u
a
t
i
o
n
o
f
c
l
a
ss
i
f
i
c
a
t
i
o
n
m
o
d
e
l
s
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
F
i
rst
Wo
r
k
sh
o
p
o
n
Ev
a
l
u
a
t
i
o
n
a
n
d
C
o
m
p
a
ri
s
o
n
o
f
N
L
P
S
y
st
e
m
s
,
S
t
r
o
u
d
s
b
u
r
g
,
P
A
,
U
S
A
:
A
sso
c
i
a
t
i
o
n
f
o
r
C
o
m
p
u
t
a
t
i
o
n
a
l
Li
n
g
u
i
s
t
i
c
s,
2
0
2
0
,
p
p
.
7
9
–
91
,
d
o
i
:
1
0
.
1
8
6
5
3
/
v
1
/
2
0
2
0
.
e
v
a
l
4
n
l
p
-
1
.
9
.
[
2
5
]
H
.
H
.
E
l
mo
u
sa
l
a
mi
,
“
C
o
mp
a
r
i
s
o
n
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
f
o
r
p
r
o
j
e
c
t
c
o
n
c
e
p
t
u
a
l
c
o
s
t
p
r
e
d
i
c
t
i
o
n
:
a
c
a
se
s
t
u
d
y
a
n
d
c
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
si
s
,
”
I
E
EE
T
r
a
n
sa
c
t
i
o
n
s
o
n
E
n
g
i
n
e
e
r
i
n
g
M
a
n
a
g
e
m
e
n
t
,
v
o
l
.
6
8
,
n
o
.
1
,
p
p
.
1
8
3
–
1
9
6
,
F
e
b
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
TE
M
.
2
0
2
0
.
2
9
7
2
0
7
8
.
[
2
6
]
P
.
D
.
R
o
s
t
r
o
n
,
T
.
F
e
a
r
n
,
a
n
d
M
.
H
.
R
a
mse
y
,
“
C
o
n
f
i
d
e
n
c
e
i
n
t
e
r
v
a
l
s
f
o
r
r
o
b
u
st
e
st
i
ma
t
e
s
o
f
m
e
a
s
u
r
e
me
n
t
u
n
c
e
r
t
a
i
n
t
y
,
”
Ac
c
r
e
d
i
t
a
t
i
o
n
a
n
d
Q
u
a
l
i
t
y
As
su
r
a
n
c
e
,
v
o
l
.
2
5
,
n
o
.
2
,
p
p
.
1
0
7
–
1
1
9
,
A
p
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s0
0
7
6
9
-
0
1
9
-
0
1
4
1
7
-
4.
[
2
7
]
K
.
H
.
K
.
M
a
n
g
u
r
i
a
n
d
A
.
A
.
M
o
h
a
m
med
,
“
A
r
e
v
i
e
w
o
f
c
o
mp
u
t
e
r
v
i
s
i
o
n
–
b
a
se
d
t
r
a
f
f
i
c
c
o
n
t
r
o
l
l
i
n
g
a
n
d
mo
n
i
t
o
r
i
n
g
,
”
U
H
D
J
o
u
rn
a
l
o
f
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
7
,
n
o
.
2
,
p
p
.
6
–
1
5
,
A
u
g
.
2
0
2
3
,
d
o
i
:
1
0
.
2
1
9
2
8
/
u
h
d
j
st
.
v
7
n
2
y
2
0
2
3
.
p
p
6
-
1
5
.
[
2
8
]
S
.
K
.
A
b
b
a
s
e
t
a
l
.
,
“
V
i
s
i
o
n
b
a
se
d
i
n
t
e
l
l
i
g
e
n
t
t
r
a
f
f
i
c
l
i
g
h
t
ma
n
a
g
e
m
e
n
t
sy
st
e
m
u
s
i
n
g
f
a
s
t
e
r
r
‐
c
n
n
,
”
C
AAI
T
ra
n
s
a
c
t
i
o
n
s
o
n
I
n
t
e
l
l
i
g
e
n
c
e
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
9
,
n
o
.
4
,
p
p
.
9
3
2
–
9
4
7
,
A
u
g
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
4
9
/
c
i
t
2
.
1
2
3
0
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
P
o
r
ta
b
le
s
ystem
fo
r
r
ea
l
-
time
t
r
a
ffic v
o
lu
me
a
n
d
s
p
ee
d
esti
ma
tio
n
u
s
in
g
…
(
I
d
a
B
a
g
u
s
S
r
a
d
h
a
N
a
n
d
a
)
309
[
2
9
]
A
.
K
a
l
a
š
o
v
á
,
P
.
F
a
b
i
a
n
,
K
.
Č
u
l
í
k
,
a
n
d
L
.
Š
k
o
r
v
á
n
k
o
v
á
,
“
C
o
m
p
a
r
i
s
o
n
o
f
t
h
e
a
c
c
u
r
a
c
y
o
f
t
r
a
f
f
i
c
f
l
o
w
i
n
t
e
n
si
t
y
a
n
d
s
p
e
e
d
mea
s
u
r
e
me
n
t
u
s
i
n
g
a
c
a
mer
a
s
y
st
e
m a
n
d
me
a
s
u
r
i
n
g
d
e
v
i
c
e
s
su
c
h
a
s
s
i
e
r
z
e
g
a
a
n
d
s
d
r
o
n
a
c
o
n
g
e
st
e
d
r
o
a
d
,
”
V
e
h
i
c
l
e
s
,
v
o
l
.
7
,
n
o
.
2
,
Ju
n
.
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
v
e
h
i
c
l
e
s
7
0
2
0
0
5
9
.
[
3
0
]
X
.
C
.
V
u
o
n
g
,
R
.
-
F
.
M
ou
,
a
n
d
T.
T
.
V
u
, “V
e
h
i
c
l
e
t
r
a
c
k
i
n
g
a
n
d
sp
e
e
d
e
s
t
i
m
a
t
i
o
n
u
n
d
e
r
mi
x
e
d
t
r
a
f
f
i
c
c
o
n
d
i
t
i
o
n
s
u
s
i
n
g
Y
O
LO
v
4
a
n
d
so
r
t
:
a
c
a
s
e
s
t
u
d
y
o
f
h
a
n
o
i
,
”
T
ra
n
s
p
o
r
t
Pr
o
b
l
e
m
s
,
v
o
l
.
1
7
,
n
o
.
4
,
p
p
.
1
7
–
2
6
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
2
0
8
5
8
/
t
p
.
2
0
2
2
.
1
7
.
4
.
0
2
.
[
3
1
]
A
.
A
.
K
a
s
h
y
a
p
,
S
.
R
a
v
i
r
a
j
,
A
.
D
e
v
a
r
a
k
o
n
d
a
,
S
.
R
.
N
a
y
a
k
K
,
S
.
K
V
,
a
n
d
S
.
J.
B
h
a
t
,
“
Tr
a
f
f
i
c
f
l
o
w
p
r
e
d
i
c
t
i
o
n
mo
d
e
l
s
–
a
r
e
v
i
e
w
o
f
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
,
”
C
o
g
e
n
t
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
9
,
n
o
.
1
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
8
0
/
2
3
3
1
1
9
1
6
.
2
0
2
1
.
2
0
1
0
5
1
0
.
[
3
2
]
X
.
Z
h
o
u
,
R
.
K
e
,
H
.
Y
a
n
g
,
a
n
d
C
.
Li
u
,
“
W
h
e
n
i
n
t
e
l
l
i
g
e
n
t
t
r
a
n
sp
o
r
t
a
t
i
o
n
s
y
s
t
e
ms
se
n
si
n
g
m
e
e
t
s
e
d
g
e
c
o
m
p
u
t
i
n
g
:
v
i
s
i
o
n
a
n
d
c
h
a
l
l
e
n
g
e
s,”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
1
,
n
o
.
2
0
,
O
c
t
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
1
2
0
9
6
8
0
.
[
3
3
]
M
.
P
e
y
ma
n
,
P
.
J.
C
o
p
a
d
o
,
R
.
D
.
T
o
r
d
e
c
i
l
l
a
,
L
.
d
o
C
.
M
a
r
t
i
n
s,
F
.
X
h
a
f
a
,
a
n
d
A
.
A
.
J
u
a
n
,
“
E
d
g
e
c
o
m
p
u
t
i
n
g
a
n
d
I
o
T
a
n
a
l
y
t
i
c
s
f
o
r
a
g
i
l
e
o
p
t
i
m
i
z
a
t
i
o
n
i
n
i
n
t
e
l
l
i
g
e
n
t
t
r
a
n
s
p
o
r
t
a
t
i
o
n
s
y
st
e
ms,
”
E
n
e
r
g
i
e
s
,
v
o
l
.
1
4
,
n
o
.
1
9
,
O
c
t
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
4
1
9
6
3
0
9
.
[
3
4
]
C
.
G
h
e
o
r
g
h
e
a
n
d
A
.
S
o
i
c
a
,
“
R
e
v
o
l
u
t
i
o
n
i
z
i
n
g
u
r
b
a
n
m
o
b
i
l
i
t
y
:
a
sy
s
t
e
m
a
t
i
c
r
e
v
i
e
w
o
f
AI
,
I
o
T
,
a
n
d
p
r
e
d
i
c
t
i
v
e
a
n
a
l
y
t
i
c
s
i
n
a
d
a
p
t
i
v
e
t
r
a
f
f
i
c
c
o
n
t
r
o
l
s
y
st
e
ms f
o
r
r
o
a
d
n
e
t
w
o
r
k
s,”
El
e
c
t
ro
n
i
c
s
,
v
o
l
.
1
4
,
n
o
.
4
,
F
e
b
.
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
1
4
0
4
0
7
1
9
.
[
3
5
]
T.
A
f
r
i
n
,
N
.
Y
o
d
o
,
A
.
D
e
y
,
a
n
d
L.
G
.
A
r
a
g
o
n
,
“
A
d
v
a
n
c
e
me
n
t
s
i
n
UAV
-
e
n
a
b
l
e
d
i
n
t
e
l
l
i
g
e
n
t
t
r
a
n
s
p
o
r
t
a
t
i
o
n
sy
s
t
e
m
s
:
a
t
h
r
e
e
-
l
a
y
e
r
e
d
f
r
a
mew
o
r
k
a
n
d
f
u
t
u
r
e
d
i
r
e
c
t
i
o
n
s,
”
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
4
,
n
o
.
2
0
,
O
c
t
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
4
2
0
9
4
5
5
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ida
Ba
g
u
s S
r
a
d
h
a
Na
n
d
a
is a t
ra
n
sp
o
rtati
o
n
p
ra
c
ti
ti
o
n
e
r
a
n
d
re
se
a
rc
h
e
r
c
u
rre
n
tl
y
wo
rk
i
n
g
a
t
th
e
De
p
a
rtme
n
t
o
f
Tr
a
n
sp
o
rtati
o
n
o
f
Kl
u
n
g
k
u
n
g
Re
g
e
n
c
y
,
I
n
d
o
n
e
sia
.
He
h
o
l
d
s
a
d
ip
l
o
m
a
a
n
d
a
b
a
c
h
e
lo
r
d
e
g
re
e
fro
m
th
e
I
n
d
o
n
e
sia
n
Lan
d
Tran
s
p
o
rtatio
n
P
o
l
y
tec
h
n
ic
-
S
T
TD
.
His
re
se
a
rc
h
fo
c
u
se
s
o
n
th
e
a
p
p
l
i
c
a
ti
o
n
o
f
tec
h
n
o
lo
g
y
i
n
tran
sp
o
rta
ti
o
n
s
y
ste
m
s,
p
a
rti
c
u
larly
in
imp
ro
v
i
n
g
sa
fe
ty
a
n
d
traffic
e
ffici
e
n
c
y
t
h
ro
u
g
h
sm
a
rt
i
n
fra
stru
c
tu
re
.
He
h
a
s
p
u
b
li
sh
e
d
re
se
a
rc
h
in
F
o
r
u
m
M
e
k
a
n
i
k
a
ti
tl
e
d
"
De
si
g
n
o
f
a
n
Am
iab
le
P
e
li
c
a
n
(Am
a
n
)
c
ro
ss
in
g
b
a
se
d
o
n
IOS
a
rd
u
in
o
n
a
n
o
:
a
c
a
se
stu
d
y
o
n
Ba
su
k
i
Ra
h
m
a
t
s
tree
t"
.
His
a
c
a
d
e
m
ic
p
ro
fil
e
is
a
v
a
il
a
b
le
o
n
G
o
o
g
le S
c
h
o
lar.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
g
u
ss
ra
d
h
a
@g
m
a
il
.
c
o
m
.
Ma
sr
o
n
o
Yu
g
ih
a
r
tim
a
n
is
a
lec
tu
re
r
a
t
t
h
e
In
d
o
n
e
sia
n
La
n
d
Tran
s
p
o
rtati
o
n
P
o
ly
tec
h
n
ic
-
S
T
TD.
He
h
o
l
d
s
a
d
o
c
to
r
in
Eco
n
o
m
ic
S
c
ien
c
e
fr
o
m
P
a
d
jad
jara
n
Un
iv
e
rsity
a
n
d
a
m
a
ste
r’s d
e
g
re
e
in
Tran
sp
o
rtati
o
n
P
lan
n
i
n
g
a
n
d
E
n
g
in
e
e
rin
g
fro
m
I
TS
th
e
Un
i
v
e
rsity
o
f
Lee
d
s
,
Un
it
e
d
Kin
g
d
o
m
.
He
p
re
v
io
u
sly
se
rv
e
d
a
s
h
e
a
d
o
f
t
h
e
Ce
n
ter
fo
r
Re
se
a
rc
h
a
n
d
De
v
e
lo
p
m
e
n
t
o
f
Lan
d
a
n
d
Ra
il
wa
y
Tran
sp
o
rt
a
n
d
a
s
d
irec
to
r
o
f
ra
il
wa
y
sa
fe
ty
a
t
th
e
M
in
istry
o
f
Tran
sp
o
rtati
o
n
,
In
d
o
n
e
sia
.
His
re
se
a
rc
h
fo
c
u
se
s
o
n
in
telli
g
e
n
t
tran
sp
o
rtati
o
n
sy
ste
m
s,
c
o
n
g
e
sti
o
n
p
rici
n
g
,
a
n
d
su
sta
i
n
a
b
le
u
r
b
a
n
m
o
b
i
li
ty
.
He
h
a
s
p
u
b
li
sh
e
d
in
se
v
e
ra
l
re
p
u
tab
le
in
tern
a
ti
o
n
a
l
j
o
u
r
n
a
ls,
in
c
lu
d
i
n
g
S
u
sta
in
a
b
i
li
ty
(
M
DPI)
a
n
d
JRC
P
ITB.
His
a
c
a
d
e
m
ic
p
ro
fil
e
is
a
v
a
il
a
b
le o
n
G
o
o
g
le
S
c
h
o
lar.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
y
h
a
rti
m
a
n
.
y
h
@
g
m
a
il
.
c
o
m
.
Ek
o
Prim
a
d
i
H
e
n
d
r
i
is a stati
stics
lec
tu
re
r
a
t
th
e
In
d
o
n
e
sia
n
Lan
d
Tran
s
p
o
rtati
o
n
P
o
ly
tec
h
n
ic
-
S
T
TD
,
Be
k
a
si,
In
d
o
n
e
sia
.
He
e
a
rn
e
d
h
is
u
n
d
e
rg
ra
d
u
a
te
d
e
g
re
e
fro
m
Un
iv
e
rsitas
G
a
d
jah
M
a
d
a
a
n
d
h
is
M
a
ste
r
o
f
S
c
ien
c
e
in
S
tatisti
c
s
fro
m
IP
B
Un
iv
e
rsit
y
.
His
a
c
a
d
e
m
ic
a
n
d
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
a
p
p
li
e
d
sta
ti
stics
,
d
a
ta
m
o
d
e
li
n
g
,
a
n
d
sta
ti
stica
l
a
p
p
li
c
a
ti
o
n
s
in
tran
sp
o
rtati
o
n
s
y
ste
m
s.
He
h
a
s
c
o
n
tri
b
u
te
d
to
se
v
e
ra
l
re
se
a
rc
h
p
u
b
li
c
a
ti
o
n
s
i
n
n
a
ti
o
n
a
l
a
n
d
in
tern
a
ti
o
n
a
l
j
o
u
r
n
a
ls
a
n
d
a
c
ti
v
e
ly
su
p
p
o
rts
d
a
ta
-
d
ri
v
e
n
a
p
p
ro
a
c
h
e
s
in
tran
s
p
o
rt
p
o
l
icy
a
n
d
p
lan
n
in
g
.
His
a
c
a
d
e
m
ic
p
ro
fil
e
is
a
v
a
il
a
b
le
o
n
G
o
o
g
le
S
c
h
o
lar.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
e
k
o
.
p
r
ima
d
i@p
t
d
istt
d
.
a
c
.
id
.
I
Ma
d
e
S
u
a
r
ti
k
a
is
a
lec
tu
re
r
a
t
th
e
I
n
d
o
n
e
sia
n
Lan
d
Tran
sp
o
rt
a
ti
o
n
P
o
l
y
tec
h
n
ic
-
S
TT
D
a
n
d
h
e
a
d
o
f
t
h
e
m
a
ste
r’s
p
ro
g
ra
m
in
Ap
p
li
e
d
M
a
r
k
e
ti
n
g
I
n
n
o
v
a
ti
o
n
a
n
d
Tec
h
n
o
l
o
g
y
.
He
h
a
s
se
rv
e
d
in
v
a
rio
u
s
k
e
y
p
o
siti
o
n
s
i
n
c
lu
d
in
g
Dire
c
to
r
o
f
P
KTJ
Teg
a
l,
He
a
d
o
f
P
lan
n
in
g
a
n
d
Co
o
p
e
ra
ti
o
n
a
t
th
e
M
in
ist
ry
o
f
Tran
sp
o
rtatio
n
,
a
n
d
Tran
sp
o
rtati
o
n
Attac
h
é
a
t
th
e
In
d
o
n
e
sia
n
Emb
a
ss
y
in
T
h
e
Ha
g
u
e
.
He
h
o
ld
s
a
m
a
ste
r’s
d
e
g
re
e
in
Tran
sp
o
rt
fro
m
t
h
e
Un
iv
e
rsity
o
f
Ne
w
S
o
u
t
h
Wale
s,
Au
stra
li
a
,
a
n
d
is
c
u
rre
n
tl
y
p
u
rs
u
in
g
a
d
o
c
t
o
ra
l
p
ro
g
ra
m
in
Lea
d
e
rsh
ip
a
n
d
I
n
n
o
v
a
ti
o
n
P
o
li
c
y
a
t
Un
iv
e
rsitas
G
a
d
jah
M
a
d
a
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
tran
sp
o
rtati
o
n
p
o
li
c
y
,
r
o
a
d
sa
fe
ty
,
a
n
d
in
n
o
v
a
ti
o
n
i
n
tran
sp
o
rt
a
ti
o
n
sy
ste
m
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
a
d
e
.
su
a
rti
k
a
@p
td
istt
d
.
a
c
.
id
.
Evaluation Warning : The document was created with Spire.PDF for Python.