I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
3
8
,
No
.
2
,
Ma
y
20
2
5
,
p
p
.
997
~
1
0
0
9
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
8
.
i
2
.
pp
997
-
1
0
0
9
997
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
M
ulti
-
ca
mera
mu
lti
-
perso
n
trackin
g
with
DeepS
O
R
T a
nd
M
y
SQ
L
Sh
a
s
ha
nk
H
o
ra
k
o
dig
e
R
a
g
h
a
v
endra
1
,
Ya
s
ha
s
v
i So
ra
pa
lli
1
,
Neha
s
hri P
o
o
j
a
r
S
.
V
.
1
,
H
rit
hik
M
a
dd
ira
la
1
,
Ra
m
a
k
a
nth
K
um
a
r
P
.
1
,
Azr
a
Na
s
re
en
1
,
Nee
t
a
T
riv
edi
2
,
Ash
i
s
h Ag
a
rwa
l
2
,
Sree
la
k
s
hm
i
K.
1
1
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
R
V
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
,
B
a
n
g
a
l
o
r
e
,
I
n
d
i
a
2
I
n
f
e
r
i
g
e
n
c
e
Q
u
o
t
i
e
n
t
P
r
i
v
a
t
e
Li
m
i
t
e
d
,
B
a
n
g
a
l
o
r
e
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ap
r
21
,
2
0
2
4
R
ev
is
ed
Oct
31
,
202
4
Acc
ep
ted
No
v
11
,
2
0
2
4
M
u
lt
i
-
c
a
m
e
ra
m
u
lt
i
-
o
b
jec
t
trac
k
i
n
g
re
fe
rs
to
t
h
e
p
ro
c
e
ss
o
f
sim
u
lt
a
n
e
o
u
sl
y
trac
k
in
g
n
u
m
e
ro
u
s
o
b
jec
ts
u
sin
g
a
n
e
two
r
k
o
f
c
o
n
n
e
c
ted
c
a
m
e
ra
s.
Co
n
stru
c
ti
n
g
a
n
a
c
c
u
ra
te
d
e
p
ictio
n
o
f
a
n
o
b
jec
t
’
s
m
o
v
e
m
e
n
ts
re
q
u
ires
th
e
a
n
a
ly
sis
o
f
v
id
e
o
d
a
ta
fr
o
m
m
a
n
y
c
a
m
e
ra
f
e
e
d
s,
d
e
tec
ti
o
n
o
f
it
e
m
s
o
f
in
tere
st,
a
n
d
t
h
e
ir
a
ss
o
c
iatio
n
a
c
ro
ss
v
a
rio
u
s
c
a
m
e
ra
p
e
rsp
e
c
ti
v
e
s.
T
h
e
o
b
je
c
ti
v
e
is
to
a
c
c
u
ra
tely
e
stim
a
te
th
e
traje
c
to
ries
o
f
th
e
o
b
jec
ts
a
s
th
e
y
n
a
v
i
g
a
te
th
ro
u
g
h
a
m
o
n
it
o
re
d
a
re
a
.
It
h
a
s
se
v
e
ra
l
u
se
s,
in
c
l
u
d
i
n
g
su
r
v
e
il
lan
c
e
,
ro
b
o
t
ics
,
se
lf
-
d
riv
i
n
g
c
a
rs,
a
n
d
a
u
g
m
e
n
ted
re
a
li
ty
.
T
h
e
c
u
rre
n
t
v
e
rsio
n
o
f
a
n
o
b
jec
t
trac
k
in
g
a
lg
o
rit
h
m
,
De
e
p
S
ORT
,
d
o
e
sn
’
t
a
c
c
o
u
n
t
fo
r
e
rro
rs
c
a
u
se
d
b
y
o
c
c
lu
sio
n
o
r
imp
lem
e
n
tatio
n
o
f
m
u
lt
ip
le
c
a
m
e
ra
s.
In
t
h
is
p
a
p
e
r,
De
e
p
S
ORT
h
a
s
b
e
e
n
e
x
t
e
n
d
e
d
b
y
i
n
t
r
o
d
u
c
i
n
g
n
e
w
s
t
a
t
e
s
t
o
i
m
p
r
o
v
e
t
h
e
t
r
a
c
k
i
n
g
p
e
r
f
o
r
m
a
n
c
e
i
n
s
c
e
n
a
r
i
o
s
w
h
e
re
o
b
j
e
c
t
s
a
r
e
o
c
c
l
u
d
e
d
i
n
t
h
e
p
r
e
s
e
n
c
e
o
f
m
u
l
t
i
p
l
e
c
a
m
e
r
a
s
.
T
h
e
c
o
m
m
u
n
i
c
a
t
i
o
n
o
f
t
r
a
c
k
i
n
f
o
r
m
a
t
i
o
n
a
c
r
o
ss
m
u
l
t
i
p
l
e
c
a
m
e
r
a
s
i
s
a
c
h
i
e
v
e
d
w
i
t
h
t
h
e
h
e
l
p
o
f
a
d
a
t
a
b
a
s
e
.
T
h
e
s
u
g
g
e
s
t
e
d
s
y
s
t
e
m
p
e
r
f
o
r
m
s
b
e
t
t
e
r
i
n
s
i
t
u
a
t
i
o
n
s
w
h
e
r
e
o
b
j
e
c
t
s
a
re
o
c
c
lu
d
e
d
,
w
h
e
t
h
e
r
d
u
e
t
o
o
b
j
e
c
t
o
c
c
l
u
s
i
o
n
s
o
r
p
e
rso
n
o
c
c
lu
sio
n
s.
K
ey
w
o
r
d
s
:
Dee
p
SOR
T
Kalm
an
f
ilter
Ob
ject
Occ
lu
d
ed
Occ
lu
d
in
g
Occ
lu
s
io
n
h
an
d
lin
g
Per
s
o
n
Occ
lu
d
ed
YOL
Ov
4
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
:
Azr
a
Nasr
ee
n
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
in
ee
r
in
g
,
R
V
C
o
lleg
e
o
f
E
n
g
in
ee
r
i
n
g
B
an
g
alo
r
e
-
5
9
,
I
n
d
ia
E
m
ail: a
zr
an
asre
en
@
r
v
ce
.
ed
u
.
in
1.
I
NT
RO
D
UCT
I
O
N
R
ec
en
t
y
ea
r
s
h
av
e
s
ee
n
s
ig
n
if
i
ca
n
t
ad
v
an
ce
m
e
n
ts
in
co
m
p
u
t
er
v
is
io
n
,
p
ar
ticu
la
r
ly
in
o
b
ject
d
etec
tio
n
an
d
tr
ac
k
in
g
,
wh
ich
ar
e
v
ital
f
o
r
ap
p
licatio
n
s
s
u
ch
as
s
u
r
v
eillan
ce
,
au
to
n
o
m
o
u
s
v
eh
icles,
v
id
eo
an
aly
tics
,
an
d
h
u
m
an
-
c
o
m
p
u
ter
in
te
r
ac
tio
n
.
I
n
d
ee
p
lear
n
in
g
,
tr
ac
k
in
g
i
n
v
o
lv
es
p
r
ed
ictin
g
th
e
o
b
ject
p
o
s
i
tio
n
s
ac
r
o
s
s
v
id
e
o
s
u
s
in
g
s
p
atial
[
1
]
an
d
tem
p
o
r
al
[
2
]
attr
i
b
u
tes.
T
h
e
d
etec
tio
n
m
o
d
u
le,
em
p
lo
y
in
g
tec
h
n
iq
u
e
s
s
u
ch
as
YOL
Ov
4
,
lo
ca
tes
o
b
jects,
wh
ile
th
e
m
o
tio
n
p
r
e
d
ictio
n
m
o
d
u
le
f
o
r
ec
asts
f
u
tu
r
e
tr
ajec
to
r
ies
b
ased
o
n
p
ast
b
eh
av
i
o
u
r
.
C
o
m
b
in
in
g
th
ese
m
o
d
u
les
e
n
a
b
les
th
e
tr
ac
k
in
g
s
y
s
tem
t
o
f
o
l
lo
w
an
d
an
ticip
ate
o
b
ject
m
o
v
em
en
t,
p
r
o
v
i
d
in
g
a
co
m
p
r
eh
e
n
s
iv
e
u
n
d
er
s
tan
d
in
g
o
f
s
p
atial
an
d
tem
p
o
r
al
d
y
n
am
ics
[
3
]
.
T
h
e
p
r
o
ce
s
s
co
m
p
r
is
es
two
s
tag
es:
d
etec
tio
n
a
n
d
tr
ac
k
in
g
.
Y
OL
Ov
4
id
en
tifie
s
o
b
jects
in
th
e
d
etec
tio
n
s
tag
e,
an
d
Dee
p
SOR
T
[
4
]
,
an
ex
ten
s
io
n
o
f
th
e
SOR
T
[
5
]
alg
o
r
ith
m
,
is
u
s
ed
f
o
r
tr
ac
k
i
n
g
.
D
ee
p
SOR
T
in
teg
r
ates
d
ee
p
lear
n
in
g
tech
n
iq
u
es,
in
cl
u
d
in
g
Kalm
an
f
ilt
er
s
f
o
r
m
o
ti
o
n
p
r
ed
ictio
n
an
d
f
r
am
e
-
by
-
f
r
am
e
d
ata
ass
o
ciatio
n
u
s
in
g
th
e
Hu
n
g
a
r
ian
m
eth
o
d
[
6
]
.
An
ap
p
ea
r
an
ce
d
escr
ip
t
o
r
,
e
x
tr
ac
ted
t
h
r
o
u
g
h
C
NNs,
m
in
im
is
es
id
en
tity
s
witch
es
b
y
en
co
d
in
g
u
n
iq
u
e
v
is
u
al
ch
ar
ac
ter
is
tics
.
T
h
i
s
in
teg
r
ated
ap
p
r
o
ac
h
en
s
u
r
es
ef
f
icien
t
tr
ac
k
in
g
,
ac
cu
r
ate
co
n
tin
u
ity
,
an
d
a
r
o
b
u
s
t so
lu
tio
n
f
o
r
m
u
ltip
le
o
b
ject
tr
ac
k
in
g
(
MO
T
)
task
s
[
7
]
.
Desp
ite
th
ese
ad
v
an
ce
m
en
ts
,
o
b
ject
tr
ac
k
in
g
in
m
u
lti
-
ca
m
er
a
en
v
ir
o
n
m
en
ts
p
r
esen
ts
s
ig
n
if
ican
t
ch
al
len
g
es.
On
e
m
ajo
r
is
s
u
e
is
o
cc
lu
s
io
n
[
8
]
,
wh
er
e
o
b
jects
m
a
y
b
e
p
ar
tially
o
r
co
m
p
letely
h
id
d
en
f
r
o
m
v
iew,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
2
,
May
20
2
5
:
9
9
7
-
1
0
0
9
998
co
m
p
licatin
g
t
h
e
tr
ac
k
i
n
g
p
r
o
ce
s
s
.
C
u
r
r
en
t
tr
ac
k
in
g
s
y
s
tem
s
o
f
ten
s
tr
u
g
g
le
with
m
ain
tain
in
g
o
b
ject
id
en
titi
es
an
d
c
o
n
tin
u
ity
in
th
e
p
r
esen
ce
o
f
o
cc
lu
s
io
n
s
o
r
wh
en
o
b
jects
m
o
v
e
ac
r
o
s
s
o
v
er
lap
p
in
g
ca
m
er
a
v
iews.
T
h
is
ch
allen
g
e
is
f
u
r
th
er
co
m
p
o
u
n
d
ed
in
m
u
lti
-
ca
m
er
a
s
etu
p
s
wh
er
e
s
y
n
ch
r
o
n
is
atio
n
an
d
d
ata
in
teg
r
atio
n
a
r
e
cr
u
cial
f
o
r
ac
cu
r
ate
tr
ac
k
in
g
.
Var
io
u
s
ex
ten
s
io
n
s
an
d
ad
ju
s
t
m
en
ts
h
av
e
b
ee
n
p
r
o
p
o
s
ed
in
r
ec
en
t
r
esear
c
h
to
en
h
an
ce
tr
ac
k
in
g
ac
c
u
r
ac
y
;
h
o
wev
er
,
m
an
y
o
f
th
ese
tec
h
n
iq
u
es
a
r
e
s
till
u
n
ab
le
t
o
h
an
d
le
co
m
p
licated
r
ea
l
-
wo
r
ld
s
itu
atio
n
s
wh
er
e
c
am
er
as
h
av
e
o
v
er
lap
p
i
n
g
f
iel
d
s
o
f
v
is
io
n
o
r
o
b
jects
ar
e
c
o
n
s
tan
tly
o
b
s
cu
r
ed
.
Ad
d
r
ess
in
g
th
ese
p
r
o
b
lem
s
r
e
q
u
ir
es
in
n
o
v
ativ
e
s
o
lu
tio
n
s
to
en
h
an
ce
th
e
r
o
b
u
s
tn
ess
o
f
tr
ac
k
in
g
alg
o
r
ith
m
s
,
p
ar
ticu
lar
ly
in
c
o
m
p
lex
s
ce
n
ar
io
s
.
T
h
is
s
tu
d
y
p
r
o
p
o
s
es
a
n
o
v
el
s
tr
ateg
y
to
ad
d
r
ess
ex
ten
d
e
d
o
cc
lu
s
io
n
,
r
ed
u
ce
id
en
tity
s
witch
es,
an
d
in
tr
o
d
u
ce
a
d
ata
b
ase
s
y
s
tem
f
o
r
s
ea
m
less
tr
ac
k
in
f
o
r
m
atio
n
tr
an
s
f
er
b
etwe
en
ca
m
er
as.
T
h
is
ap
p
r
o
ac
h
m
ain
tain
s
a
u
n
iq
u
e
I
D
f
o
r
a
p
er
s
o
n
ac
r
o
s
s
ca
m
er
as
ev
en
in
ch
allen
g
in
g
s
ce
n
ar
io
s
.
B
y
co
m
b
in
in
g
th
ese
m
eth
o
d
o
lo
g
ies,
th
is
s
tu
d
y
co
n
tr
ib
u
tes to
ad
v
a
n
cin
g
tr
ac
k
in
g
tech
n
o
lo
g
y
an
d
en
h
an
cin
g
p
er
f
o
r
m
a
n
ce
in
co
m
p
lex
s
ce
n
ar
io
s
.
T
h
e
p
a
p
er
is
s
tr
u
ctu
r
ed
as
f
o
ll
o
ws:
s
ec
tio
n
2
,
Dee
p
SOR
T
e
n
h
an
ce
m
e
n
t,
d
is
cu
s
s
es
im
p
r
o
v
em
en
ts
to
th
e
Dee
p
SOR
T
alg
o
r
ith
m
[
9
]
,
f
o
cu
s
in
g
o
n
o
cc
lu
s
i
o
n
h
an
d
li
n
g
,
o
v
er
lap
m
an
a
g
em
en
t
b
etw
ee
n
ca
m
er
a
v
iews,
an
d
id
en
tity
p
r
eser
v
atio
n
.
Sectio
n
3
,
ex
p
e
r
im
en
tal
s
etu
p
,
d
et
ails
th
e
eq
u
ip
m
en
t
an
d
to
o
ls
u
s
ed
,
alo
n
g
with
th
e
m
u
lti
-
ca
m
er
a
v
id
e
o
f
ee
d
s
p
ec
i
f
icatio
n
s
.
Sectio
n
4
,
d
ata
s
elec
tio
n
,
ex
p
lain
s
th
e
cr
iter
ia
f
o
r
d
ata
in
clu
s
io
n
an
d
p
r
o
v
id
es
an
o
v
er
v
iew
o
f
s
in
g
le
an
d
m
u
lti
-
ca
m
er
a
f
o
o
tag
e
s
ce
n
ar
io
s
.
Sectio
n
5
,
m
o
d
if
icatio
n
s
,
o
u
tlin
es
en
h
an
ce
m
e
n
ts
m
ad
e
to
Dee
p
SOR
T
,
in
clu
d
in
g
n
ew
v
ar
iab
les,
f
ea
tu
r
es,
an
d
th
e
d
atab
ase
s
etu
p
f
o
r
m
u
lti
-
ca
m
e
r
a
tr
ac
k
in
g
.
Sectio
n
6
,
im
p
lem
e
n
tatio
n
,
d
escr
ib
es
s
in
g
le
a
n
d
m
u
lti
-
ca
m
er
a
tr
ac
k
in
g
p
r
o
ce
d
u
r
es,
em
p
h
asizin
g
o
cc
lu
s
io
n
h
an
d
li
n
g
an
d
d
atab
ase
m
an
ag
em
en
t.
Sectio
n
7
,
r
esu
lts
an
d
d
is
cu
s
s
io
n
,
p
r
esen
ts
em
p
ir
ical
r
esu
lts
d
em
o
n
s
tr
atin
g
th
e
e
f
f
ec
tiv
en
e
s
s
o
f
th
e
p
r
o
p
o
s
ed
e
n
h
an
ce
m
en
ts
,
d
is
cu
s
s
in
g
th
eir
im
p
ac
t
in
s
in
g
le
an
d
m
u
lti
-
ca
m
er
a
en
v
ir
o
n
m
e
n
ts
,
alo
n
g
with
s
y
s
tem
lim
itatio
n
s
.
F
in
ally
,
s
ec
tio
n
8
,
c
o
n
clu
s
io
n
,
s
u
m
m
ar
izes
k
ey
co
n
tr
ib
u
tio
n
s
an
d
s
u
g
g
ests
d
ir
ec
tio
n
s
f
o
r
f
u
tu
r
e
r
esear
ch
.
2.
DE
E
P
SO
RT
E
NH
ANC
E
M
E
NT
T
h
e
Dee
p
SOR
T
co
d
e
was
m
o
d
if
ied
to
r
ed
u
ce
i
d
en
tity
m
i
s
m
atch
es
[
1
0
]
in
ca
s
es
o
f
o
c
clu
s
io
n
b
y
p
er
f
o
r
m
in
g
a
v
ar
iety
o
f
task
s
s
u
ch
as
s
to
p
p
in
g
v
is
u
al
f
ea
tu
r
e
u
p
d
ates
an
d
th
e
ad
d
itio
n
o
f
n
e
w
tr
ac
k
s
tates.
T
h
ese
en
h
an
ce
m
e
n
ts
in
clu
d
e
th
e
f
o
ll
o
win
g
:
2
.
1
.
O
cc
lus
io
n ha
nd
li
ng
I
n
th
e
co
n
te
x
t
o
f
o
cc
l
u
s
io
n
h
an
d
lin
g
[
1
1
]
in
a
s
in
g
le
-
ca
m
er
a
s
ce
n
ar
io
,
it
is
ess
en
tial
to
ad
d
r
ess
s
itu
atio
n
s
wh
er
e
o
n
e
p
e
r
s
o
n
i
s
d
ir
ec
tly
b
eh
in
d
an
o
t
h
er
p
e
r
s
o
n
,
th
at
is
,
m
u
ltip
le
p
eo
p
le
a
r
e
with
in
th
e
s
am
e
b
o
u
n
d
in
g
b
o
x
.
T
h
is
is
d
o
n
e
to
p
r
ev
en
t
u
n
wa
n
ted
v
is
u
al
f
ea
tu
r
e
u
p
d
ates
th
at
c
an
lea
d
to
co
n
f
u
s
io
n
a
n
d
id
en
tity
ex
ch
an
g
es a
m
o
n
g
i
n
d
iv
id
u
als.
I
n
s
tead
,
s
p
ec
if
ic
m
ea
s
u
r
es we
r
e
im
p
lem
en
ted
t
o
en
s
u
r
e
ac
cu
r
ate
tr
ac
k
in
g
.
2
.
1
.
1
.
P
a
rt
i
a
l a
nd
co
m
plet
e
o
v
er
la
p det
ec
t
io
n
T
h
e
in
ter
s
ec
tio
n
o
v
e
r
u
n
io
n
(
I
OU)
m
etr
ic
[
1
2
]
is
f
r
eq
u
e
n
tly
u
s
ed
to
d
eter
m
in
e
wh
e
n
p
ar
tial
o
r
co
m
p
lete
o
v
e
r
lap
tak
es
p
lace
b
etwe
en
two
tr
ac
k
s
[
1
3
]
.
T
h
e
am
o
u
n
t
o
f
o
v
er
lap
b
etwe
en
tw
o
b
o
u
n
d
in
g
b
o
x
es is
m
ea
s
u
r
ed
b
y
I
OU.
I
f
th
e
I
OU
v
al
u
e
b
etwe
en
two
m
atc
h
ed
tr
ac
k
s
is
g
r
ea
ter
th
an
th
e
I
OU
th
r
esh
o
ld
(
0
.
0
0
1
)
,
th
en
it
is
a
p
ar
tial
o
v
er
lap
.
I
f
th
e
I
OU
v
alu
e
b
etwe
en
a
m
atch
e
d
an
d
an
u
n
m
atch
ed
tr
ac
k
is
g
r
ea
ter
th
an
th
e
I
OU
th
r
esh
o
ld
,
th
e
n
it is
a
co
m
p
lete
o
v
er
lap
.
2
.
1
.
2
.
Sto
pp
ing
a
pp
ea
ra
nce
f
ea
t
ure
up
da
t
es
I
n
ca
s
e
o
f
th
e
two
a
b
o
v
e
c
o
n
d
i
tio
n
s
b
ein
g
tr
u
e
,
th
e
tr
ac
k
.
u
p
d
ate(
)
f
u
n
ctio
n
is
m
o
d
if
ied
t
o
o
n
ly
u
p
d
ate
th
e
m
o
v
em
e
n
t f
ea
tu
r
es o
f
th
e
p
ar
ticu
lar
tr
ac
k
an
d
n
o
t th
e
a
p
p
ea
r
an
ce
f
ea
t
u
r
es
[
1
4
]
.
2
.
1
.
3
.
Av
o
idi
ng
identit
y
m
is
m
a
t
ches
T
h
e
tr
ac
k
er
r
ed
u
ce
s
th
e
p
o
s
s
ib
ilit
y
o
f
in
ac
cu
r
ate
id
en
tity
m
is
m
atch
es
b
y
f
o
r
g
o
in
g
a
p
p
ea
r
a
n
ce
f
ea
tu
r
e
u
p
d
ates
d
u
r
i
n
g
o
cc
lu
s
io
n
.
T
h
is
is
b
ec
au
s
e
wh
en
n
u
m
er
o
u
s
p
eo
p
le
ar
e
p
r
esen
t
in
th
e
s
am
e
b
o
u
n
d
in
g
b
o
x
,
ap
p
ea
r
an
ce
f
ea
tu
r
es
th
at
s
er
v
e
to
d
is
tin
g
u
is
h
b
etwe
en
i
n
d
iv
id
u
als
m
ay
b
ec
o
m
e
in
a
cc
u
r
ate
o
r
u
n
clea
r
.
T
h
e
tr
ac
k
er
ca
n
p
r
eser
v
e
ea
ch
p
er
s
o
n
’
s
tr
ac
k
a
n
d
r
e
d
u
ce
th
e
l
ik
elih
o
o
d
o
f
id
e
n
tity
ex
ch
a
n
g
e
s
b
y
g
iv
in
g
p
r
io
r
ity
to
m
ain
tain
in
g
t
h
e
Kalm
an
[
1
5
]
m
o
v
em
e
n
t a
ttrib
u
tes.
3.
E
XP
E
R
I
M
E
N
T
A
L
SE
T
UP
T
o
co
n
d
u
ct
o
u
r
r
esear
ch
,
we
h
ad
to
f
ir
s
t
ca
p
tu
r
e
a
s
er
ies
o
f
s
in
g
le
-
ca
m
er
a
f
o
o
ta
g
e
an
d
m
u
lti
-
ca
m
er
a
f
o
o
tag
e.
T
h
ese
v
id
eo
s
we
r
e
r
e
co
r
d
ed
at
a
s
ig
n
if
ican
t
h
eig
h
t a
n
d
d
is
tan
ce
to
allo
w
th
e
ca
m
er
a
f
ee
d
to
b
e
a
b
le
to
ca
p
tu
r
e
a
wid
e
en
o
u
g
h
ar
ea
.
T
h
ese
v
id
eo
s
wer
e
th
en
d
o
wn
lo
ad
ed
in
to
o
u
r
lap
t
o
p
s
f
o
r
p
r
o
c
ess
in
g
v
ia
o
u
r
co
d
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Mu
lti
-
ca
mera
mu
lti
-
p
ers
o
n
tr
a
ck
in
g
w
ith
Dee
p
S
OR
T a
n
d
MyS
QL
(
S
h
a
s
h
a
n
k
Ho
r
a
ko
d
ig
e
R
a
g
h
a
ve
n
d
r
a
)
999
to
d
eter
m
in
e
th
e
ac
cu
r
ac
y
an
d
co
n
s
is
ten
cy
o
f
th
e
co
d
e.
T
h
e
y
also
allo
wed
u
s
to
ca
p
tu
r
e
u
n
k
n
o
wn
e
d
g
e
ca
s
es
an
d
h
el
p
m
o
d
if
y
th
e
c
o
d
e
t
o
b
e
tter
f
it
th
em
.
W
e
h
ad
v
id
eo
f
ee
d
s
f
o
r
s
in
g
le
-
ca
m
er
a
an
d
m
u
lti
-
ca
m
er
a
s
itu
atio
n
s
.
B
o
th
th
ese
ca
s
es we
r
e
h
an
d
led
d
if
f
er
en
tly
b
y
im
p
lem
en
tin
g
d
if
f
e
r
en
t m
eth
o
d
o
lo
g
ies.
3
.
1
.
I
ns
t
rum
ent
s
us
ed
T
ab
le
1
h
as
th
e
s
p
ec
if
icatio
n
s
o
f
th
e
ca
m
er
a
u
s
ed
f
o
r
s
in
g
le
-
ca
m
er
a
v
id
eo
f
ee
d
.
T
h
ese
v
id
eo
s
wer
e
ca
p
tu
r
ed
f
r
o
m
a
h
eig
h
t
o
f
3
s
t
o
r
ies.
T
ab
le
2
h
as
t
h
e
s
p
ec
if
ic
atio
n
s
o
f
th
e
ca
m
er
a
u
s
ed
f
o
r
m
u
lti
-
ca
m
er
a
v
i
d
eo
f
ee
d
.
T
wo
o
f
s
u
ch
ca
m
e
r
as
wer
e
in
s
talled
at
a
h
ei
g
h
t
o
f
4
s
to
r
ies
with
s
o
m
e
o
v
e
r
lap
b
etwe
e
n
th
e
two
r
ec
o
r
d
in
g
f
ield
s
.
T
ab
le
1
.
Sam
s
u
n
g
Gala
x
y
M3
1
s
s
p
ec
if
icatio
n
s
S
p
e
c
i
f
i
c
a
t
i
o
n
D
e
t
a
i
l
s
D
e
v
i
c
e
S
a
msu
n
g
G
a
l
a
x
y
M
3
1
s
M
a
i
n
c
a
m
e
r
a
Tr
i
p
l
e
:
64
M
P
,
f
/
1
.
8
,
2
6
mm
(
w
i
d
e
)
,
1
/
1
.
7
3
”
,
0
.
8
µ
m,
P
D
A
F
1
2
M
P
,
f
/
2
.
2
,
1
2
3
°
(
u
l
t
r
a
w
i
d
e
)
5
M
P
,
f
/
2
.
4
,
(
m
a
c
r
o
)
5
M
P
,
f
/
2
.
4
,
(
d
e
p
t
h
)
64
M
P
,
f
/
1
.
8
,
2
6
mm
(
w
i
d
e
)
,
1
/
1
.
7
3
”
,
0
.
8
µ
m,
P
D
A
F
F
e
a
t
u
r
e
s
LED
f
l
a
s
h
,
p
a
n
o
r
a
ma,
H
D
R
V
i
d
e
o
r
e
c
o
r
d
i
n
g
r
e
so
l
u
t
i
o
n
UHD
4K
(
3
8
4
0
×
2
1
6
0
)
@
3
0
f
p
s
T
ab
le
2
.
C
P PLU
S we
ath
er
p
r
o
o
f
o
u
t
d
o
o
r
s
ec
u
r
ity
ca
m
er
a
s
p
ec
if
icatio
n
s
S
p
e
c
i
f
i
c
a
t
i
o
n
D
e
t
a
i
l
s
M
o
d
e
l
C
P
P
LU
S
w
e
a
t
h
e
r
p
r
o
o
f
o
u
t
d
o
o
r
Ty
p
e
W
i
r
e
d
b
u
l
l
e
t
s
e
c
u
r
i
t
y
c
a
m
e
r
a
R
e
s
o
l
u
t
i
o
n
2
.
4
MP
Le
n
s
3
.
6
M
M
f
o
r
w
i
d
e
a
n
g
l
e
R
e
c
o
r
d
i
n
g
1
0
8
0
P
f
u
l
l
HD
F
e
a
t
u
r
e
s
D
i
g
i
t
a
l
w
i
d
e
d
y
n
a
mi
c
r
a
n
g
e
(D
-
W
D
R
)
3
.
2
.
M
ea
s
urem
ent
f
o
r
m
ulti
-
ca
m
er
a
v
ideo
f
ee
d
T
wo
ca
m
er
as
(
C
AM
1
an
d
C
AM
2
)
h
a
v
e
b
ee
n
s
et
u
p
p
o
in
tin
g
f
r
o
m
a
h
eig
h
t to
war
d
s
a
f
ield
.
T
h
e
f
ee
d
s
o
f
b
o
th
ca
m
er
as
h
a
v
e
a
r
eso
lu
tio
n
o
f
1
9
2
0
×
1
0
8
0
.
C
AM
1
ca
p
tu
r
es
th
e
lef
t
ar
ea
,
wh
er
ea
s
C
AM
2
ca
p
tu
r
es
th
e
r
ig
h
t.
B
o
th
ca
m
er
as
h
av
e
an
o
v
er
lap
p
in
g
r
eg
io
n
in
th
e
m
id
d
l
e.
A
lar
g
e
p
ar
t
o
f
th
e
f
ee
d
b
esi
d
e
th
e
o
v
er
lap
p
in
g
r
eg
io
n
h
as
b
ee
n
u
s
ed
as
th
e
‘
wr
itin
g
r
eg
io
n
’
.
W
h
en
e
v
er
a
t
r
ac
k
en
ter
s
th
is
‘
w
r
itin
g
r
e
g
io
n
’
,
its
f
ea
tu
r
es
a
r
e
wr
itten
in
to
th
e
d
atab
ase,
wh
ich
ar
e
im
m
ed
iately
r
ea
d
a
n
d
s
to
r
ed
b
y
th
e
o
th
e
r
ca
m
er
a.
T
h
e
o
v
er
lap
lin
e
f
o
r
C
AM
1
ex
ten
d
s
f
r
o
m
co
o
r
d
in
ates
(
1
6
0
0
,
0
)
to
(
2
0
0
0
,
1
4
4
0
)
,
an
d
f
o
r
C
AM
2
,
f
r
o
m
(
1
2
0
0
,
0
)
to
(
6
0
0
,
1
4
4
0
)
.
T
h
e
wr
itin
g
r
ef
e
r
en
ce
lin
e
is
d
ef
in
ed
f
o
r
C
AM
1
as
(
1
9
0
0
,
0
)
to
(
1
9
0
0
,
1
4
4
0
)
an
d
f
o
r
C
AM
2
as
(
7
0
0
,
0
)
to
(
7
0
0
,
1
4
4
0
)
,
m
ar
k
in
g
th
e
b
o
u
n
d
ar
ies o
f
th
is
r
eg
io
n
f
o
r
b
o
th
c
am
er
as.
4.
DATA S
E
L
E
C
T
I
O
N
B
ef
o
r
e
h
ea
d
in
g
i
n
to
th
e
m
o
d
if
icatio
n
s
m
ad
e
to
th
e
ex
is
tin
g
Dee
p
SOR
T
alg
o
r
ith
m
,
we
h
ad
to
o
b
tain
s
o
m
e
f
o
o
tag
e
f
o
r
b
o
th
s
in
g
le
c
am
er
a
an
d
m
u
lti ca
m
er
a
tr
ac
k
i
n
g
p
u
r
p
o
s
es.
4
.
1
.
Da
t
a
s
elec
t
io
n c
rit
er
ia
B
elo
w
is
th
e
s
elec
tio
n
cr
iter
ia
we
h
ad
in
p
lace
wh
ile
co
llectin
g
f
o
o
tag
e
f
o
r
test
in
g
.
4
.
1
.
1
.
Acc
ept
a
ble
−
T
h
e
p
e
o
p
l
e
i
n
t
h
e
v
i
d
e
o
f
e
e
d
a
r
e
o
c
c
l
u
d
e
d
:
t
h
is
is
o
n
e
o
f
t
h
e
tw
o
m
a
i
n
p
r
o
b
l
e
m
s
w
e
t
a
c
k
l
e
d
in
o
u
r
r
e
s
e
a
r
c
h
.
−
T
h
e
p
eo
p
le
in
th
e
v
id
eo
f
ee
d
walk
/r
u
n
at
v
a
r
y
in
g
s
p
ee
d
s
an
d
in
d
if
f
er
en
t
d
ir
ec
tio
n
s
:
t
h
ese
s
ce
n
ar
io
s
wer
e
r
eq
u
ir
ed
in
o
r
d
er
to
test
th
e
ac
cu
r
ac
y
o
f
o
u
r
m
o
d
if
icatio
n
s
.
−
An
y
n
u
m
b
er
o
f
p
eo
p
le
i
n
th
e
v
id
eo
f
ee
d
:
a
s
lo
n
g
as
th
e
p
eo
p
le
in
th
e
f
ee
d
a
r
e
d
etec
tab
le
th
r
o
u
g
h
o
u
t
th
e
v
id
eo
,
th
is
d
ata
is
ac
ce
p
tab
le
a
n
d
with
in
s
co
p
e
o
f
o
u
r
r
esear
c
h
.
4
.
1
.
2
.
O
ut
o
f
s
co
pe
−
T
h
e
m
ain
o
b
ject
o
f
tr
ac
k
in
g
is
n
o
t
a
p
er
s
o
n
:
t
h
ese
m
o
d
if
ica
tio
n
s
m
ad
e
to
th
e
Dee
p
SOR
T
alg
o
r
ith
m
h
av
e
o
n
ly
b
ee
n
test
ed
o
n
p
eo
p
le
(
o
b
ject=
p
er
s
o
n
)
.
As
we
co
u
ld
cr
ea
te
as
m
an
y
s
ce
n
ar
io
s
f
o
r
test
i
n
g
b
y
m
o
v
in
g
in
d
if
f
er
en
t
d
ir
ec
tio
n
s
at
will,
th
i
s
d
ec
is
io
n
was m
ad
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
2
,
May
20
2
5
:
9
9
7
-
1
0
0
9
1000
−
T
h
e
p
e
o
p
le
i
n
th
e
f
ee
d
m
u
s
t
b
e
d
etec
tab
le:
t
h
is
r
esear
ch
o
n
l
y
f
o
cu
s
s
es
o
n
im
p
r
o
v
in
g
th
e
tr
ac
k
in
g
a
b
ilit
y
o
f
Dee
p
SOR
T
.
T
h
er
ef
o
r
e,
it is
an
in
h
er
en
t r
e
q
u
ir
em
e
n
t th
at
all
s
u
b
jects m
u
s
t b
e
d
etec
tab
le.
No
m
o
d
if
icatio
n
s
wer
e
m
ad
e
to
YOL
Ov
4
,
th
e
d
etec
tio
n
al
g
o
r
ith
m
u
s
ed
in
th
is
r
esear
ch
.
4
.
2
.
Sin
g
le
-
ca
m
er
a
a
nd
m
ulti
-
ca
m
er
a
f
o
o
t
a
g
e
det
a
ils
A
to
tal
o
f
s
ev
en
s
ce
n
ar
io
s
f
o
r
s
in
g
le
-
ca
m
er
a
e
n
v
ir
o
n
m
en
ts
an
d
ten
s
ce
n
ar
io
s
f
o
r
m
u
l
ti
-
ca
m
er
a
en
v
ir
o
n
m
en
ts
wer
e
ca
r
ef
u
lly
d
esig
n
ed
,
r
ec
o
r
d
ed
,
an
d
u
s
ed
as
in
p
u
t
d
ata
f
o
r
th
e
Dee
p
SOR
T
tr
ac
k
in
g
alg
o
r
ith
m
.
T
ab
le
3
p
r
esen
ts
th
e
d
etailed
d
escr
ip
tio
n
s
o
f
th
e
s
itu
a
tio
n
s
o
b
s
er
v
ed
in
th
e
s
in
g
le
-
ca
m
er
a
s
etu
p
s
,
alo
n
g
with
th
e
tr
ac
k
in
g
o
u
tco
m
es
u
s
in
g
th
e
o
r
ig
in
al
Dee
p
SOR
T
alg
o
r
ith
m
.
I
m
p
r
o
v
e
m
en
ts
m
ad
e
to
t
h
ese
in
itial
r
esu
lts
,
lev
er
ag
in
g
t
h
e
en
h
a
n
ce
d
v
er
s
io
n
o
f
Dee
p
SOR
T
,
ar
e
d
is
cu
s
s
ed
in
s
u
b
s
eq
u
e
n
t sectio
n
s
.
T
h
e
m
u
lti
-
cam
er
a
f
o
o
ta
g
e,
ca
p
tu
r
ed
u
s
in
g
two
s
y
n
c
h
r
o
n
ize
d
ca
m
er
as,
was
d
esig
n
ed
t
o
e
n
co
m
p
ass
a
wid
e
r
an
g
e
o
f
s
ce
n
ar
io
s
,
r
ef
l
ec
tin
g
r
ea
l
-
wo
r
ld
c
o
m
p
lex
itie
s
s
u
ch
as
o
cc
lu
s
io
n
s
,
cr
o
s
s
o
v
er
s
,
an
d
d
ir
ec
tio
n
al
ch
an
g
es.
T
h
ese
s
ce
n
ar
i
o
s
s
im
u
late
co
n
d
itio
n
s
o
f
ten
e
n
co
u
n
ter
ed
in
s
u
r
v
eillan
ce
an
d
tr
ac
k
in
g
ap
p
licatio
n
s
,
en
s
u
r
in
g
th
at
b
o
th
th
e
r
o
b
u
s
tn
ess
an
d
ad
ap
tab
ilit
y
o
f
th
e
tr
ac
k
in
g
alg
o
r
ith
m
wer
e
th
o
r
o
u
g
h
ly
ev
alu
ated
.
A
d
etailed
ac
co
u
n
t
o
f
th
e
s
ce
n
ar
io
d
escr
ip
tio
n
s
,
al
o
n
g
with
t
h
e
r
esu
lts
o
b
tain
ed
u
s
in
g
th
e
e
n
h
an
ce
d
Dee
p
SOR
T
al
g
o
r
ith
m
,
is
also
p
r
o
v
i
d
ed
i
n
later
s
ec
tio
n
s
.
T
h
is
co
m
b
in
atio
n
o
f
s
in
g
le
an
d
m
u
lti
-
c
am
er
a
test
s
en
s
u
r
es
co
m
p
r
eh
e
n
s
iv
e
v
alid
atio
n
o
f
t
h
e
im
p
r
o
v
e
m
en
ts
m
ad
e
to
Dee
p
SOR
T
,
d
em
o
n
s
tr
atin
g
its
c
ap
ab
ilit
y
to
h
an
d
l
e
d
iv
er
s
e
tr
ac
k
in
g
ch
allen
g
es e
f
f
ec
tiv
ely
.
T
ab
le
3
.
Sin
g
le
-
ca
m
er
a
f
o
o
tag
e
an
d
r
esu
lt d
etails o
n
o
r
ig
in
al
Dee
p
SOR
T
Ev
e
n
t
N
o
.
S
i
t
u
a
t
i
o
n
d
e
scri
p
t
i
o
n
O
u
t
p
u
t
1
Tw
o
p
e
o
p
l
e
w
a
l
k
i
n
o
p
p
o
si
t
e
d
i
r
e
c
t
i
o
n
s a
n
d
c
r
o
ss
o
v
e
r
I
D
s 1
a
n
d
2
a
ssi
g
n
e
d
;
o
n
c
r
o
ss
o
v
e
r
,
I
D
1
b
e
c
o
m
e
s
3
,
I
D
2
b
e
c
o
m
e
s
1
.
2
Tw
o
p
e
o
p
l
e
w
a
l
k
t
o
w
a
r
d
s
e
a
c
h
o
t
h
e
r
,
t
a
l
k
,
a
n
d
w
a
l
k
o
f
f
.
I
D
s 1
a
n
d
2
sw
i
t
c
h
b
r
i
e
f
l
y
a
f
t
e
r
o
c
c
l
u
s
i
o
n
;
P
e
r
so
n
1
g
e
t
s
n
e
w
I
D
3
p
o
st
-
i
n
t
e
r
a
c
t
i
o
n
.
3
Tw
o
p
e
o
p
l
e
w
a
l
k
o
f
f
a
t
a
c
u
t
e
a
n
g
l
e
s,
r
e
t
u
r
n
,
a
n
d
c
r
o
ss
o
v
e
r
.
I
D
2
d
i
s
a
p
p
e
a
r
s t
e
m
p
o
r
a
r
i
l
y
,
b
u
t
i
s
c
o
r
r
e
c
t
l
y
re
-
a
ssi
g
n
e
d
l
a
t
e
r
.
4
O
n
e
p
e
r
s
o
n
w
a
l
k
s
,
a
n
o
t
h
e
r
r
u
n
s i
n
o
p
p
o
s
i
t
e
d
i
r
e
c
t
i
o
n
s
D
u
r
i
n
g
c
r
o
ss
o
v
e
r
,
I
D
2
d
i
sa
p
p
e
a
r
s
b
r
i
e
f
l
y
a
n
d
i
s
r
e
-
i
d
e
n
t
i
f
i
e
d
.
5
Tw
o
p
e
o
p
l
e
w
a
l
k
i
n
o
p
p
o
si
t
e
d
i
r
e
c
t
i
o
n
s a
n
d
t
u
r
n
r
i
g
h
t
o
n
c
r
o
ss
o
v
e
r
.
I
D
1
d
i
s
a
p
p
e
a
r
s;
P
e
r
so
n
1
t
a
k
e
s
I
D
2
,
P
e
r
so
n
2
g
e
t
s
n
e
w
I
D
3
.
6
Tw
o
p
e
o
p
l
e
w
a
l
k
a
t
a
n
a
c
u
t
e
a
n
g
l
e
;
o
n
e
d
i
st
a
n
t
p
e
r
s
o
n
r
e
ma
i
n
s st
a
t
i
o
n
a
r
y
.
I
D
s 1
a
n
d
2
sw
i
t
c
h
d
u
r
i
n
g
c
r
o
sso
v
e
r
a
n
d
sw
i
t
c
h
b
a
c
k
sh
o
r
t
l
y
a
f
t
e
r
.
7
Tw
o
p
e
o
p
l
e
w
a
l
k
p
e
r
p
e
n
d
i
c
u
l
a
r
l
y
a
n
d
c
r
o
ss
o
v
e
r
.
ID
1
d
i
s
a
p
p
e
a
r
s
b
r
i
e
f
l
y
b
u
t
is
c
o
r
r
e
c
t
l
y
re
-
i
d
e
n
t
i
f
i
e
d
.
5.
M
O
DIFI
CAT
I
O
NS
T
h
e
o
r
ig
in
al
Dee
p
SOR
T
alg
o
r
ith
m
,
th
o
u
g
h
ac
cu
r
ate,
co
u
ld
n
o
t
ac
co
u
n
t
f
o
r
o
cc
lu
s
io
n
s
.
T
h
is
p
r
o
p
o
s
ed
s
o
lu
tio
n
h
an
d
les o
cc
lu
s
io
n
s
wh
ile
also
m
ak
in
g
th
e
alg
o
r
ith
m
s
u
itab
le
f
o
r
m
u
lti
-
ca
m
er
a
tr
ac
k
in
g
[
1
6
]
,
[
1
7
]
.
5
.
1
.
New
ly
intr
o
du
ce
d v
a
ria
bles
a
nd
f
ea
t
ures:
s
ing
le
ca
m
er
a
t
ra
c
k
ing
I
n
ca
s
e
o
f
o
cc
l
u
s
io
n
,
th
e
I
D
s
g
iv
en
to
th
e
tr
ac
k
s
wer
e
a
lm
o
s
t
n
ev
er
m
ain
tain
ed
,
in
th
e
o
r
i
g
in
al
Dee
p
SOR
T
.
T
o
im
p
r
o
v
e
th
is
,
we
h
av
e
in
cr
ea
s
ed
th
e
n
u
m
b
er
o
f
tr
ac
k
s
tates
b
ein
g
co
n
s
id
er
ed
an
d
ad
d
e
d
ad
d
itio
n
al
m
etad
ata
f
o
r
b
etter
u
n
d
er
s
tan
d
i
n
g
o
f
tr
ac
k
s
ass
ig
n
ed
/ch
an
g
e
d
.
5
.
1
.
1
.
Addi
t
io
na
l t
ra
ck
s
t
a
t
es
Fo
u
r
n
ew
ad
d
itio
n
al
s
tates
w
er
e
ad
d
ed
alo
n
g
with
th
e
a
v
a
ilab
le
Dee
p
SOR
T
s
tates
o
f
‘
T
en
tativ
e
’
,
‘
C
o
n
f
ir
m
ed
’
,
an
d
‘
D
elete
d
’
.
T
h
e
n
ew
s
tates a
r
e:
a.
I
n
ac
tiv
e
s
tate:
if
a
d
etec
tio
n
ass
o
ciate
d
with
a
‘
C
o
n
f
ir
m
ed
’
tr
ac
k
h
as
n
o
t
b
ee
n
d
etec
ted
ag
ai
n
f
o
r
o
v
er
‘
m
a
x
ag
e
’
n
u
m
b
er
o
f
f
r
am
es
(
d
ef
au
l
t
o
f
6
0
)
,
th
en
its
s
tate
ch
an
g
es
to
‘
I
n
ac
tiv
e
’
o
r
else
it
will
s
tay
as
‘
C
o
n
f
ir
m
ed
’
.
I
n
ca
s
e
o
f
th
e
o
r
ig
in
al
alo
g
r
ith
m
,
s
u
ch
tr
ac
k
s
wo
u
ld
h
av
e
b
e
en
d
elete
d
.
T
o
im
p
lem
en
t
th
is
,
a
t
r
ac
k
is
s
et
to
‘
I
n
ac
tiv
e
’
if
its
tim
e
s
in
ce
u
p
d
ate
(
r
ef
er
‘
Data
b
ase
s
etu
p
an
d
ad
d
itio
n
s
to
c
o
d
e
’
)
is
g
r
ea
ter
th
an
m
ax
ag
e.
T
h
e
in
ac
tiv
e
s
tate
s
h
o
u
ld
b
e
tr
ea
ted
lik
e
th
e
co
n
f
ir
m
ed
s
tate
an
d
b
e
i
n
clu
d
ed
in
tr
ac
k
m
atc
h
in
g
.
b.
Occ
lu
d
in
g
s
tate:
if
a
tr
ac
k
m
o
v
es
in
f
r
o
n
t o
f
an
o
t
h
er
tr
ac
k
,
p
r
ev
en
tin
g
th
e
latter
tr
ac
k
f
r
o
m
b
ein
g
d
etec
ted
,
th
en
th
e
f
o
r
m
er
t
r
ac
k
is
s
et
to
‘
Occ
lu
d
in
g
’
.
T
h
e
v
al
u
e
o
f
o
v
er
lap
b
etwe
en
th
e
b
o
u
n
d
in
g
b
o
x
o
f
th
e
in
v
o
lv
ed
tr
ac
k
s
is
u
s
ed
as
a
th
r
esh
o
ld
f
o
r
s
ettin
g
a
tr
ac
k
t
o
‘
Occ
lu
d
in
g
’
.
I
f
it
is
g
r
ea
te
r
th
an
ze
r
o
f
o
r
a
n
y
o
f
t
h
e
u
n
m
atch
ed
tr
ac
k
s
,
t
h
e
s
tate
is
ch
an
g
ed
to
‘
Occ
lu
d
in
g
’
.
On
ce
th
is
v
alu
e
is
ze
r
o
ag
ain
,
th
e
s
tate
is
ch
an
g
ed
to
‘
C
o
n
f
ir
m
ed
’
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Mu
lti
-
ca
mera
mu
lti
-
p
ers
o
n
tr
a
ck
in
g
w
ith
Dee
p
S
OR
T a
n
d
MyS
QL
(
S
h
a
s
h
a
n
k
Ho
r
a
ko
d
ig
e
R
a
g
h
a
ve
n
d
r
a
)
1001
c.
P
er
s
o
n
O
cc
lu
d
ed
s
tate:
if
a
tr
a
ck
is
h
id
d
en
f
r
o
m
th
e
ca
m
e
r
a
b
ec
au
s
e
o
f
an
o
th
e
r
tr
ac
k
,
th
en
its
s
tate
i
s
s
et
to
‘
P
er
s
o
n
Occ
lu
d
ed
’
.
T
h
e
v
alu
e
o
f
o
v
er
lap
b
etwe
en
th
is
tr
ac
k
an
d
all
o
t
h
er
m
atch
e
d
tr
ac
k
ed
is
d
eter
m
in
ed
.
I
f
th
is
v
alu
e
is
g
r
ea
ter
th
an
0
,
th
en
th
e
tr
ac
k
is
u
n
m
atc
h
ed
with
a
‘
P
er
s
o
n
Occ
lu
d
ed
’
s
tate
an
d
s
tay
s
th
e
s
am
e
u
n
til
it
is
m
atch
ed
a
g
ai
n
.
O
n
ce
th
is
tr
ac
k
is
n
o
lo
n
g
er
h
id
d
en
a
n
d
d
etec
ted
,
its
s
tate
is
ch
an
g
ed
to
‘
C
o
n
f
ir
m
ed
’
.
I
f
t
h
is
o
cc
lu
s
io
n
last
s
f
o
r
m
o
r
e
th
an
m
ax
a
g
e
f
r
am
es th
en
th
is
tr
ac
k
is
m
o
v
e
d
to
‘
I
n
ac
tiv
e
’
.
d.
O
b
ject
O
cc
lu
d
ed
s
tate:
if
a
tr
ac
k
is
h
id
d
e
n
f
r
o
m
th
e
ca
m
e
r
a
b
y
a
s
tatic
o
b
ject,
th
en
its
s
tate
is
s
et
to
‘
O
b
jectOc
clu
d
ed
’
.
Ag
ain
,
t
h
e
v
alu
e
o
f
o
v
er
la
p
b
etwe
en
th
is
tr
ac
k
an
d
all
o
th
er
m
atch
ed
tr
ac
k
ed
is
d
eter
m
in
ed
.
I
f
th
is
v
alu
e
is
g
r
ea
ter
th
an
0
,
th
en
th
e
tr
ac
k
is
u
n
m
atch
ed
with
a
‘
O
b
jectOc
c
lu
d
ed
’
s
tate
an
d
s
tay
s
th
e
s
am
e
u
n
til
it
is
m
atch
ed
ag
ain
.
I
f
t
h
is
o
cc
lu
s
io
n
last
s
f
o
r
m
o
r
e
th
an
m
ax
ag
e
f
r
am
es
th
en
th
is
tr
ac
k
is
m
o
v
ed
to
‘
I
n
ac
tiv
e
’
.
5
.
1
.
2
.
O
t
her
a
dd
ed
f
ea
t
ures
I
n
ad
d
itio
n
to
th
e
n
ew
v
a
r
iab
les,
th
e
u
p
d
ated
Dee
p
SOR
T
alg
o
r
ith
m
h
as
a
co
u
p
le
n
ew
lo
g
ics
in
tr
o
d
u
ce
d
.
T
h
ese
in
clu
s
io
n
s
ar
e
u
s
ef
u
l in
m
ai
n
tain
g
th
e
I
D
o
f
th
e
tr
ac
k
d
u
r
in
g
o
cc
lu
s
io
n
.
a.
Occ
p
air
s
:
a
tr
ac
k
in
th
e
o
cc
lu
d
in
g
s
tate
r
em
ai
n
s
as
s
u
ch
u
n
til
it
n
o
lo
n
g
e
r
o
v
er
lap
s
with
an
y
tr
ac
k
s
p
r
e
d
icted
b
o
x
.
Su
p
p
o
s
e,
i
f
tr
ac
k
A
o
cc
lu
d
es
tr
ac
k
B
f
o
r
a
lo
n
g
e
n
o
u
g
h
tim
e,
tr
ac
k
B
’
s
p
r
e
d
icted
b
o
x
co
u
ld
m
o
v
e
o
u
t
o
f
th
e
o
v
er
lap
ca
u
s
in
g
tr
ac
k
A
to
r
e
g
ain
its
co
n
f
ir
m
ed
s
tate.
T
h
is
lead
s
t
o
tr
ac
k
A
b
ei
n
g
u
p
d
ated
with
in
co
r
r
ec
t
f
ea
tu
r
es
as
th
e
two
d
etec
tio
n
s
ar
e
s
till
o
v
e
r
lap
p
in
g
.
T
o
h
a
n
d
le
th
is
,
‘
Occ
p
air
s
’
wer
e
in
tr
o
d
u
ce
d
.
T
h
e
‘
Occ
p
air
s
’
v
ar
iab
le
is
a
l
is
t
o
f
p
air
s
in
wh
ich
ea
ch
p
ai
r
is
o
f
th
e
f
o
r
m
(
Occ
lu
d
in
g
I
D
,
Occ
lu
d
ed
I
D)
.
I
t is u
s
ed
to
m
ain
tain
th
e
tr
ac
k
s
tates d
u
r
in
g
lo
n
g
p
er
io
d
s
o
f
o
cc
lu
s
io
n
.
I
t is u
s
ed
to
ass
ig
n
‘
Occ
lu
d
in
g
’
a
n
d
‘
P
er
s
o
n
Occ
lu
d
ed
’
s
tates
b
ef
o
r
e
th
e
o
v
er
lap
ch
ec
k
.
E
v
e
r
y
tim
e
an
o
cc
lu
s
io
n
o
cc
u
r
s
,
th
eir
r
e
s
p
ec
tiv
e
I
Ds
ar
e
ad
d
ed
to
th
is
lis
t,
an
d
o
n
ly
wh
en
th
e
tr
ac
k
with
th
e
Occ
lu
d
ed
I
D
is
m
atch
ed
ag
ain
,
th
e
p
air
i
s
r
em
o
v
ed
f
r
o
m
th
e
lis
t.
b.
T
wo
alp
h
ab
et
g
en
er
ato
r
:
alo
n
g
with
th
e
tr
ac
k
I
D,
ea
ch
tr
ac
k
h
as
a
u
n
iq
u
e
2
-
alp
h
a
b
et
co
d
e
g
en
er
ated
b
y
a
2
-
alp
h
ab
et
g
en
e
r
atio
n
lo
g
ic.
E
v
er
y
tim
e
a
n
ew
tr
ac
k
is
in
it
ialis
ed
,
th
e
g
en
er
at
o
r
co
d
e
r
u
n
s
an
d
ass
ig
n
s
a
lex
ical
v
alu
e
to
it.
T
h
is
alo
n
g
with
th
e
tr
ac
k
id
s
er
v
es to
d
is
tin
g
u
is
h
b
etwe
en
t
r
ac
k
s
.
5
.
2
.
Da
t
a
ba
s
e
s
et
up
a
nd
a
dd
it
io
ns
t
o
co
de:
m
ulti
-
c
a
m
er
a
t
ra
ck
ing
I
n
o
r
d
er
to
e
x
ten
d
t
h
e
s
in
g
le
ca
m
er
a
tr
ac
k
in
g
ca
p
ab
ilit
y
to
m
u
lti
ca
m
er
a
tr
ac
k
in
g
,
it
is
n
ec
ess
ar
y
to
r
etain
in
f
o
r
m
atio
n
ab
o
u
t
th
e
tr
ac
k
s
an
d
co
m
m
u
n
icate
th
is
b
etwe
en
th
e
ca
m
er
as.
T
h
is
r
eq
u
ir
es
a
d
atab
ase
to
s
to
r
e
th
e
co
m
m
u
n
icatio
n
d
etails.
5
.
2
.
1
.
Select
io
n o
f
da
t
a
ba
s
e
B
ef
o
r
e
ch
o
o
s
in
g
a
d
atab
ase,
a
n
ex
p
er
im
e
n
t
was
p
er
f
o
r
m
ed
o
v
er
a
v
i
d
eo
co
n
tain
in
g
1
0
,
0
0
0
f
r
am
es
to
d
eter
m
in
e
th
e
r
ea
d
/wr
ite
tim
e
s
o
f
two
d
atab
ases
,
My
SQL
a
n
d
Mo
n
g
o
DB
.
T
h
e
r
ea
d
/wr
ite
tim
es
m
en
tio
n
ed
in
T
ab
le
4
,
ar
e
t
h
e
tim
es
tak
en
t
o
r
ea
d
a
n
d
wr
ite
a
s
in
g
le
f
ea
t
u
r
e
v
ec
to
r
r
esp
ec
tiv
ely
f
r
o
m
an
d
to
th
e
d
atab
ase.
E
ac
h
f
ea
tu
r
e
v
ec
to
r
co
n
s
is
ts
o
f
1
2
8
v
alu
es.
B
ased
o
n
th
e
r
e
ad
/wr
ite
tim
es
o
b
tain
ed
o
v
er
th
e
1
0
,
0
0
0
f
r
am
es,
v
ar
io
u
s
s
tatis
tical
v
alu
es
in
clu
d
in
g
m
in
im
u
m
,
m
a
x
im
u
m
,
av
er
ag
e,
v
ar
ian
ce
,
an
d
s
tan
d
ar
d
d
e
v
iatio
n
wer
e
ca
lcu
lated
.
T
ab
le
4
.
Per
f
o
r
m
an
ce
m
etr
ics f
o
r
1
0
,
0
0
0
f
r
a
m
es
M
e
t
r
i
c
s
M
y
S
Q
L(
W
)
M
y
S
Q
L(
R
)
M
o
n
g
o
D
B
(
W
)
M
o
n
g
o
D
B
(
R
)
M
i
n
1
.
1
1
4
9
ms
0
.
3
3
8
1
ms
a
p
p
r
o
x
.
0s
a
p
p
r
o
x
.
0s
M
a
x
4
3
.
7
8
7
4
ms
2
.
9
9
0
8
ms
2
0
1
.
6
7
7
ms
3
5
.
3
3
6
ms
M
e
a
n
2
.
2
4
1
0
ms
0
.
8
2
6
4
ms
1
.
5
3
6
1
ms
0
.
6
3
9
ms
V
a
r
s
0
.
0
0
9
3
ms
0
.
0
0
0
6
ms
0
.
0
0
9
9
ms
0
.
0
0
0
4
ms
S
t
d
.
D
0
.
0
9
6
3
ms
0
.
0
2
4
6
ms
0
.
0
9
9
8
ms
0
.
0
1
9
8
ms
5
.
2
.
2
.
Schem
a
T
h
e
s
tr
u
ctu
r
e
o
r
b
lu
e
p
r
in
t th
at
s
p
ec
if
ies h
o
w
d
ata
is
ar
r
an
g
ed
,
k
ep
t,
an
d
ac
ce
s
s
ed
with
in
a
d
atab
ase
is
r
ef
er
r
ed
t
o
as
a
d
atab
ase
s
ch
e
m
a.
I
t
s
p
ec
if
ies
th
e
tab
les,
f
ield
s
,
r
elatio
n
s
h
ip
s
,
co
n
s
tr
ain
ts
,
a
n
d
o
th
e
r
elem
en
ts
o
f
th
e
d
atab
ase
’
s
lo
g
ical
an
d
p
h
y
s
ical
lay
o
u
t.
T
ab
le
5
r
ep
r
esen
ts
th
e
s
ch
em
a
o
f
th
e
two
f
ea
tu
r
e
tab
les
an
d
th
e
s
h
ar
ed
tab
le.
I
t a
ls
o
p
r
o
v
i
d
es th
e
attr
ib
u
tes o
f
th
e
tab
les.
I
n
o
u
r
My
SQL
d
atab
ase,
th
r
ee
d
if
f
er
en
t ta
b
les ar
e
m
ain
tain
e
d
:
f
ea
tu
r
e
T
ab
le
1
:
c
o
n
s
is
ts
o
f
th
e
tr
ac
k
f
ea
tu
r
es wr
itten
b
y
C
AM
1
.
T
h
e
tab
le
is
r
ea
d
b
y
C
AM
2
.
f
ea
tu
r
e
T
ab
le
2
:
c
o
n
s
is
ts
o
f
th
e
tr
ac
k
f
ea
tu
r
es wr
itten
b
y
C
AM
2
.
T
h
e
tab
le
is
r
ea
d
b
y
C
AM
1
.
s
h
ar
ed
tab
le:
u
s
ed
f
o
r
allo
win
g
co
m
m
u
n
icatio
n
to
tak
e
p
lace
b
etwe
en
b
o
t
h
C
AM
1
an
d
C
AM
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
2
,
May
20
2
5
:
9
9
7
-
1
0
0
9
1002
T
ab
le
5
.
Data
b
ase
tab
le
attr
ib
u
tes
Ta
b
l
e
n
a
me
A
t
t
r
i
b
u
t
e
D
a
t
a
t
y
p
e
D
e
t
a
i
l
s
F
e
a
t
u
r
e
t
a
b
l
e
id
i
n
t
3
2
S
p
e
c
i
f
i
e
s t
h
e
t
r
a
c
k
I
D
.
st
a
t
e
i
n
t
3
2
S
p
e
c
i
f
i
e
s t
h
e
st
a
t
e
o
f
t
h
e
t
r
a
c
k
(
Te
n
t
a
t
i
v
e
=
1
a
n
d
C
o
n
f
i
r
me
d
=
2
)
f
e
a
t
u
r
e
s
V
a
r
c
h
a
r
(
3
0
0
0
)
A
p
p
e
a
r
a
n
c
e
v
e
c
t
o
r
(
A
r
r
a
y
of
1
2
8
v
a
l
u
e
s)
f
r
a
me
n
u
m
i
n
t
3
2
F
r
a
me
n
u
m
b
e
r
h
i
t
s
i
n
t
3
2
N
u
mb
e
r
o
f
t
i
mes
t
h
e
t
r
a
c
k
h
a
s
u
n
d
e
r
g
o
n
e
a
me
a
su
r
e
me
n
t
u
p
d
a
t
e
mea
n
V
a
r
c
h
a
r
(
3
0
0
0
)
8
-
d
i
me
n
si
o
n
a
l
me
a
n
v
e
c
t
o
r
c
o
v
a
r
i
a
n
c
e
V
a
r
c
h
a
r
(
3
0
0
0
)
8
×
8
-
d
i
me
n
si
o
n
a
l
c
o
v
a
r
i
a
n
c
e
m
a
t
r
i
x
t
r
a
c
k
s
t
r
V
a
r
c
h
a
r
(
2
)
R
a
n
d
o
m
2
-
a
l
p
h
a
b
e
t
st
r
i
n
g
a
ssi
g
n
e
d
to
t
h
e
t
r
a
c
k
a
g
e
i
n
t
3
2
To
t
a
l
n
u
m
b
e
r
of
f
r
a
mes
si
n
c
e
t
h
e
f
i
r
s
t
o
c
c
u
r
r
e
n
c
e
of
t
h
e
t
r
a
c
k
o
c
c
id
i
n
t
3
2
Th
e
ID
of
t
h
e
t
r
a
c
k
b
e
i
n
g
o
c
c
l
u
d
e
d
by
t
h
i
s
t
r
a
c
S
h
a
r
e
d
t
a
b
l
e
id
i
n
t
8
S
e
t
t
o
1
.
U
se
d
o
n
l
y
f
o
r
r
e
a
d
i
n
g
/
w
r
i
t
i
n
g
p
u
r
p
o
ses
n
e
x
t
i
d
V
a
r
c
h
a
r
(
2
)
U
sed
t
o
a
ss
i
g
n
t
r
a
c
k
I
D
s,
i
n
c
r
e
me
n
t
e
d
(
+
1
)
b
y
e
i
t
h
e
r
c
a
mera
w
h
e
n
a
c
o
mm
1
i
n
t
8
I
n
i
t
i
a
l
i
s
e
d
t
o
0
.
S
e
t
t
o
t
h
e
n
u
m
b
e
r
o
f
p
e
o
p
l
e
i
n
t
h
e
w
r
i
t
i
n
g
r
e
g
i
o
n
b
y
C
A
M
1
d
u
r
i
n
g
i
t
s
w
r
i
t
e
o
p
e
r
a
t
i
o
n
.
R
e
se
t
t
o
0
b
y
C
A
M
2
a
f
t
e
r
r
e
a
d
i
n
g
e
v
e
r
y
r
o
w
i
n
f
e
a
t
u
r
e
Ta
b
l
e
1
.
c
o
mm
2
i
n
t
8
I
n
i
t
i
a
l
i
s
e
d
t
o
0
.
S
e
t
t
o
t
h
e
n
u
m
b
e
r
o
f
p
e
o
p
l
e
i
n
t
h
e
w
r
i
t
i
n
g
r
e
g
i
o
n
b
y
C
A
M
2
d
u
r
i
n
g
i
t
s
w
r
i
t
e
o
p
e
r
a
t
i
o
n
.
R
e
se
t
t
o
0
b
y
C
A
M
1
a
f
t
e
r
r
e
a
d
i
n
g
e
v
e
r
y
r
o
w
i
n
f
e
a
t
u
r
e
Ta
b
l
e
2
.
6.
I
M
P
L
E
M
E
NT
A
T
I
O
N
T
h
e
Dee
p
SOR
T
alg
o
r
ith
m
,
b
a
s
ed
o
n
th
e
SOR
T
[
1
8
]
ar
ch
itec
tu
r
e,
h
as
r
ec
eiv
e
d
s
ig
n
if
ican
t
r
ec
o
g
n
itio
n
f
o
r
its
ca
p
ac
ity
t
o
tr
ac
k
o
b
jec
ts
in
v
id
eo
s
eq
u
en
ce
s
.
I
ts
ab
il
ity
to
in
co
r
p
o
r
ate
ap
p
ea
r
an
ce
f
ea
tu
r
es
as
well
as
m
o
tio
n
d
ata
m
a
k
es
it
id
ea
l
f
o
r
co
m
p
lex
tr
ac
k
i
n
g
s
ce
n
ar
io
s
i
n
v
o
lv
in
g
m
an
y
c
am
er
as
an
d
o
cc
lu
s
io
n
s
.
Pre
v
io
u
s
r
esear
ch
h
as
s
h
o
wn
th
at
Dee
p
SOR
T
is
u
s
ef
u
l
in
a
v
ar
iety
o
f
tr
ac
k
in
g
ap
p
licatio
n
s
.
Fo
r
ex
a
m
p
le,
r
esear
ch
h
as
s
h
o
wn
th
at
Dee
p
SOR
T
o
u
tp
e
r
f
o
r
m
s
c
o
m
m
o
n
tr
ac
k
in
g
ap
p
r
o
ac
h
es
b
y
r
etain
in
g
id
e
n
tity
c
o
n
s
is
ten
cy
,
r
eg
ar
d
less
o
f
d
if
f
ic
u
l
t sit
u
atio
n
s
.
Ou
r
m
eth
o
d
o
lo
g
y
’
s
r
esu
lts
ar
e
esp
ec
ially
im
p
o
r
tan
t
in
r
ea
l
-
wo
r
ld
ap
p
licatio
n
s
lik
e
s
u
r
v
eil
lan
ce
[
1
9
]
,
[
2
0
]
,
r
o
b
o
tics
[
2
1
]
,
an
d
s
ec
u
r
i
ty
[
2
2
]
,
[
2
3
]
,
wh
er
e
co
n
tin
u
o
u
s
tr
ac
k
in
g
ac
r
o
s
s
m
an
y
ca
m
er
a
f
ee
d
s
is
ess
en
tial.
T
h
e
en
h
a
n
ce
m
en
ts
p
r
o
v
id
e
p
r
ac
tical
b
en
ef
its
b
y
in
cr
ea
s
in
g
t
h
e
r
eliab
ilit
y
an
d
p
r
ec
is
io
n
o
f
tr
ac
k
in
g
s
y
s
tem
s
in
ch
allen
g
in
g
s
ce
n
a
r
io
s
.
6
.
1
.
P
r
o
ce
du
re
o
f
im
ple
m
ent
a
t
io
n f
o
r
s
ing
le
-
ca
m
er
a
t
ra
c
k
ing
T
h
e
p
r
o
ce
d
u
r
e
f
o
r
s
in
g
le
-
ca
m
er
a
tr
ac
k
in
g
lar
g
ely
f
o
llo
ws
th
e
o
r
ig
in
al
Dee
p
SOR
T
alg
o
r
ith
m
,
with
m
o
d
if
icatio
n
s
in
tr
o
d
u
ce
d
to
im
p
r
o
v
e
ac
cu
r
ac
y
,
p
ar
ticu
l
ar
ly
d
u
r
in
g
o
cc
lu
s
io
n
s
.
6
.
1
.
1
.
I
nitia
lis
a
t
io
n
T
h
e
n
ec
ess
ar
y
lib
r
ar
ies
an
d
d
ep
en
d
e
n
cies
f
o
r
Dee
p
SOR
T
an
d
YOL
O
[
2
4
]
(
o
r
a
n
y
o
th
er
o
b
ject
d
etec
to
r
)
ar
e
lo
ad
ed
at
th
e
s
tar
t.
T
h
e
YOL
O
d
etec
to
r
i
s
in
itialized
to
d
etec
t
o
b
ject
s
in
v
id
eo
f
r
am
es.
Ad
d
itio
n
ally
,
th
e
Dee
p
SOR
T
tr
ac
k
er
is
in
itialized
with
s
p
e
cif
ic
co
n
f
ig
u
r
ati
o
n
s
,
s
u
ch
as
s
ettin
g
th
e
m
ax
ag
e
p
ar
a
m
eter
to
6
0
f
r
am
es a
n
d
c
o
n
f
ig
u
r
i
n
g
th
e
I
OU
th
r
esh
o
ld
f
o
r
o
v
er
la
p
d
etec
tio
n
(
e.
g
.
,
0
.
0
0
1
)
.
6
.
1
.
2
.
T
ra
ck
ing
wit
h o
cc
lus
io
n ha
nd
li
ng
Fo
r
ev
er
y
f
r
am
e
in
th
e
v
id
eo
s
tr
ea
m
,
th
e
YOL
O
d
etec
to
r
is
u
s
ed
to
d
etec
t
o
b
jects,
p
r
o
v
id
i
n
g
b
o
u
n
d
in
g
b
o
x
es
an
d
d
etec
tio
n
co
n
f
id
en
c
es.
T
h
ese
d
etec
tio
n
s
ar
e
f
ed
i
n
to
th
e
Dee
p
SOR
T
tr
ac
k
er
.
Fo
r
e
ac
h
d
etec
ted
o
b
ject
,
th
e
I
OU
is
ca
lcu
lated
b
etwe
e
n
th
e
c
u
r
r
e
n
t
d
etec
tio
n
an
d
a
ll
ac
tiv
e
tr
ac
k
s
.
B
ased
o
n
th
e
I
OU
an
d
f
ea
tu
r
e
s
im
ilar
ity
,
d
etec
tio
n
s
ar
e
ass
ig
n
ed
to
tr
ac
k
s
.
I
f
a
d
etec
tio
n
m
at
ch
es
a
tr
a
ck
,
th
e
tr
ac
k
’
s
p
o
s
itio
n
is
u
p
d
ated
u
s
in
g
Kalm
an
f
ilter
p
r
ed
ictio
n
s
.
W
h
en
th
e
I
OU
in
d
icate
s
p
ar
ti
al
o
r
co
m
p
lete
o
v
er
lap
with
an
o
th
er
tr
ac
k
,
th
e
tr
ac
k
s
tate
i
s
u
p
d
ated
to
eith
er
‘
Occ
lu
d
in
g
’
o
r
‘
P
er
s
o
n
Occ
lu
d
ed
’
,
a
n
d
t
h
e
p
air
o
f
tr
ac
k
s
is
a
d
d
ed
to
th
e
‘
Occ
p
air
s
’
lis
t.
At
th
is
p
o
in
t,
a
p
p
ea
r
an
ce
f
ea
tu
r
e
u
p
d
ates
f
o
r
th
e
tr
ac
k
a
r
e
s
u
s
p
en
d
e
d
t
o
p
r
ev
en
t
id
en
ti
ty
m
is
m
atch
es.
I
f
a
d
etec
tio
n
d
o
es
n
o
t
m
atch
an
y
tr
ac
k
,
a
n
ew
tr
ac
k
is
in
itialized
,
ass
ig
n
ed
a
u
n
iq
u
e
I
D,
a
n
d
g
iv
en
a
r
a
n
d
o
m
two
-
alp
h
a
b
et
co
d
e.
Fo
r
ea
ch
tr
ac
k
,
th
e
s
y
s
tem
c
h
e
ck
s
if
th
e
tim
e
s
in
ce
u
p
d
ate
e
x
ce
ed
s
m
ax
ag
e.
I
f
it
d
o
es,
th
e
tr
ac
k
’
s
s
tate
ch
an
g
es
to
‘
I
n
ac
tiv
e
’
an
d
is
a
d
d
ed
to
th
e
p
o
o
l
o
f
t
r
ac
k
s
av
ailab
le
f
o
r
f
u
t
u
r
e
m
atch
in
g
.
I
f
an
‘
I
n
ac
tiv
e
’
tr
ac
k
f
in
d
s
a
m
atch
in
g
d
etec
tio
n
,
its
s
tate
is
r
e
s
to
r
ed
to
‘
C
o
n
f
ir
m
ed
’
.
T
r
ac
k
s
o
cc
lu
d
ed
b
y
s
tatic
o
b
jects
f
o
r
m
o
r
e
th
a
n
m
ax
ag
e
f
r
am
es a
ls
o
s
witch
to
‘
I
n
ac
tiv
e
’
.
6
.
1
.
3
.
H
a
nd
lin
g
t
ra
c
k
s
t
a
t
es
T
r
ac
k
s
in
th
e
‘
Occ
lu
d
in
g
’
s
ta
te
r
ev
er
t
to
‘
C
o
n
f
ir
m
ed
’
o
n
ce
th
ey
n
o
lo
n
g
e
r
o
v
er
la
p
,
an
d
th
e
p
air
is
r
em
o
v
ed
f
r
o
m
t
h
e
‘
Occ
p
air
s
’
lis
t.
Similar
ly
,
f
o
r
tr
ac
k
s
in
th
e
‘
p
er
s
o
n
Occ
lu
d
e
d
’
s
tate,
if
th
e
o
cc
lu
d
in
g
tr
ac
k
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Mu
lti
-
ca
mera
mu
lti
-
p
ers
o
n
tr
a
ck
in
g
w
ith
Dee
p
S
OR
T a
n
d
MyS
QL
(
S
h
a
s
h
a
n
k
Ho
r
a
ko
d
ig
e
R
a
g
h
a
ve
n
d
r
a
)
1003
m
o
v
es
an
d
th
e
o
cc
lu
d
e
d
tr
ac
k
i
s
d
etec
ted
ag
ain
,
th
e
s
tate
ch
an
g
es
to
‘
C
o
n
f
ir
m
ed
’
,
an
d
th
e
p
a
ir
is
r
e
m
o
v
e
d
f
r
o
m
th
e
lis
t.
I
f
o
cc
lu
s
io
n
p
er
s
is
ts
b
ey
o
n
d
m
ax
a
g
e
f
r
am
es,
th
e
tr
ac
k
b
ec
o
m
es
‘
I
n
ac
tiv
e
’
.
T
r
ac
k
s
in
t
h
e
‘
O
b
jectOc
clu
d
ed
’
s
tate
ch
an
g
e
to
‘
C
o
n
f
ir
m
e
d
’
wh
en
d
etec
ted
ag
ain
b
u
t
tr
an
s
itio
n
to
‘
I
n
ac
tiv
e
’
if
o
cc
lu
s
io
n
ex
ce
ed
s
m
ax
ag
e
f
r
am
es.
6
.
1
.
4
.
O
utput
T
h
e
f
in
al
o
u
t
p
u
t
co
n
s
is
ts
o
f
v
i
d
eo
f
r
am
es
with
o
v
e
r
laid
b
o
u
n
d
in
g
b
o
x
es
an
d
tr
ac
k
I
d
s
[
2
5
]
.
Op
tio
n
ally
,
d
etailed
lo
g
s
o
f
tr
ac
k
in
f
o
r
m
at
io
n
an
d
s
tates c
an
b
e
g
en
er
ate
d
f
o
r
a
n
aly
s
is
.
6
.
2
.
P
r
o
ce
du
re
o
f
im
ple
m
ent
a
t
io
n f
o
r
m
ulti
-
ca
m
er
a
t
ra
c
k
ing
T
o
s
u
p
p
o
r
t
m
u
lti
-
ca
m
er
a
tr
ac
k
in
g
,
ad
d
itio
n
al
ch
an
g
es
ar
e
im
p
lem
en
ted
alo
n
g
s
id
e
th
e
m
o
d
i
f
ied
s
in
g
le
-
ca
m
er
a
alg
o
r
ith
m
.
6
.
2
.
1
.
I
nitia
lis
a
t
io
n
L
ib
r
ar
ies
an
d
d
ep
e
n
d
en
cies
f
o
r
Dee
p
SOR
T
an
d
YOL
O
(
o
r
o
th
er
o
b
ject
d
etec
to
r
s
)
ar
e
lo
ad
ed
.
YOL
O
is
in
itialized
f
o
r
ea
ch
ca
m
er
a
to
d
etec
t
o
b
jects
in
th
ei
r
r
es
p
ec
tiv
e
f
r
a
m
es.
A
s
ep
ar
ate
D
ee
p
SOR
T
tr
ac
k
er
is
in
itialized
f
o
r
ea
ch
c
am
er
a,
with
th
e
m
ax
ag
e
p
ar
am
eter
s
et
to
6
0
f
r
am
es
a
n
d
an
I
OU
th
r
esh
o
ld
o
f
0
.
0
0
1
.
A
s
h
ar
ed
d
atab
ase
en
v
ir
o
n
m
en
t
is
also
estab
lis
h
ed
to
f
ac
ilit
ate
co
m
m
u
n
icatio
n
b
etwe
e
n
th
e
ca
m
er
as,
a
n
d
p
o
ly
g
o
n
r
e
g
io
n
s
ar
e
d
ef
in
ed
to
av
o
id
o
v
er
lap
.
6
.
2
.
2
.
Writ
ing
t
o
da
t
a
ba
s
e
I
n
th
e
tr
ac
k
.
u
p
d
ate(
)
f
u
n
ctio
n
o
f
ea
ch
ca
m
er
a,
t
h
e
s
y
s
tem
ch
ec
k
s
if
th
e
tr
ac
k
is
n
o
n
-
ten
tati
v
e
an
d
h
as
v
alid
f
ea
tu
r
es.
I
f
th
e
tr
ac
k
lie
s
with
in
th
e
s
p
ec
if
ied
p
o
ly
g
o
n
r
eg
io
n
,
its
f
ea
tu
r
es
ar
e
wr
itten
to
th
e
d
atab
ase
’
s
f
ea
tu
r
e
tab
le.
Ad
d
itio
n
ally
,
th
e
n
ex
t
I
D
is
f
etch
ed
f
r
o
m
th
e
s
h
ar
ed
tab
le
to
m
ain
tain
u
n
i
q
u
e
I
D
ass
ig
n
m
en
ts
ac
r
o
s
s
ca
m
er
as.
T
h
e
co
m
m
1
an
d
co
m
m
2
v
alu
es
ar
e
u
p
d
ate
d
b
ased
o
n
th
e
n
u
m
b
e
r
o
f
tr
a
ck
s
in
th
e
p
o
ly
g
o
n
r
eg
io
n
f
o
r
ea
c
h
ca
m
er
a.
6
.
2
.
3
.
Rea
din
g
f
ro
m
da
t
a
ba
s
e
I
n
th
e
tr
ac
k
er
.
u
p
d
ate(
)
f
u
n
ctio
n
,
ea
ch
ca
m
er
a
u
s
es
th
e
co
m
m
v
alu
e
to
d
eter
m
in
e
h
o
w
m
a
n
y
tr
ac
k
s
to
r
ea
d
f
r
o
m
th
e
f
ea
tu
r
e
tab
le.
T
h
e
s
y
s
tem
r
etr
iev
es
tr
ac
k
s
o
r
d
er
ed
b
y
f
r
am
e
n
u
m
b
er
(
in
d
escen
d
in
g
o
r
d
er
)
to
en
s
u
r
e
th
e
m
o
s
t
r
ec
en
t
d
ata
is
ac
ce
s
s
ed
.
Fo
r
ea
ch
r
etr
ie
v
ed
t
r
ac
k
,
if
th
e
tr
ac
k
I
D
ex
is
ts
lo
ca
l
ly
,
its
f
ea
tu
r
es,
h
its
,
an
d
ag
e
a
r
e
u
p
d
ated
.
I
f
th
e
tr
a
ck
is
n
ew,
it is
ad
d
ed
to
th
e
lo
ca
l tr
ac
k
o
b
ject
lis
t.
6
.
2
.
4
.
Co
mm
un
ica
t
io
n bet
wee
n c
a
m
er
a
s
C
o
m
m
u
n
icatio
n
b
etwe
e
n
ca
m
er
as
is
m
an
ag
ed
th
r
o
u
g
h
th
e
c
o
m
m
1
a
n
d
c
o
m
m
2
v
alu
es.
I
f
co
m
m
1
is
g
r
ea
ter
t
h
an
0
,
ca
m
er
a
2
r
ea
d
s
f
r
o
m
ca
m
er
a
1
’
s
f
ea
tu
r
e
tab
le,
an
d
v
ice
v
er
s
a
if
c
o
m
m
2
is
g
r
ea
ter
th
an
0
.
I
n
t
h
e
tr
ac
k
.
u
p
d
ate(
)
f
u
n
ctio
n
,
d
ata
f
r
o
m
o
th
e
r
ca
m
er
as
is
u
s
ed
to
u
p
d
ate
o
r
cr
ea
t
e
n
ew
t
r
ac
k
s
as
n
ee
d
ed
.
T
h
e
c
o
m
m
v
alu
es a
r
e
also
u
p
d
ated
to
e
n
s
u
r
e
s
m
o
o
th
co
m
m
u
n
icatio
n
a
n
d
d
ata
co
n
s
is
ten
cy
.
6
.
2
.
5
.
O
utput
T
h
e
v
id
eo
o
u
tp
u
t
f
r
o
m
ea
ch
c
am
er
a
d
is
p
lay
s
b
o
u
n
d
in
g
b
o
x
es
an
d
tr
ac
k
I
Ds.
T
r
ac
k
in
f
o
r
m
atio
n
an
d
s
tates
ar
e
lo
g
g
ed
f
o
r
f
u
r
th
er
a
n
aly
s
is
.
T
h
is
lo
g
g
in
g
o
f
tr
ac
k
s
tates
allo
w
s
f
o
r
d
etailed
ex
a
m
in
taio
n
o
f
o
b
ject
m
o
v
em
en
t
an
d
tr
ac
k
in
g
ac
cu
r
ac
y
o
v
er
tim
e.
As
a
r
esu
lt,
a
co
m
p
r
eh
e
n
s
iv
e
v
iew
o
f
m
u
lti
-
ca
m
er
a
tr
ac
k
in
g
p
er
f
o
r
m
an
ce
is
p
r
o
v
id
ed
.
7.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
s
tu
d
y
in
v
esti
g
ated
t
h
e
ca
p
ab
ilit
ies
o
f
an
en
h
an
ce
d
Dee
p
SOR
T
alg
o
r
ith
m
f
o
r
m
u
lti
-
o
b
jec
t
tr
ac
k
in
g
in
d
y
n
am
ic
en
v
i
r
o
n
m
e
n
ts
.
W
h
ile
ea
r
lier
s
tu
d
ies
h
av
e
ex
p
lo
r
ed
v
ar
io
u
s
tr
ac
k
in
g
m
eth
o
d
s
,
th
ey
h
av
e
n
o
t
ex
p
licitly
ad
d
r
ess
ed
th
e
in
f
lu
en
ce
o
f
co
n
tin
u
o
u
s
id
en
tity
m
ain
ten
an
ce
d
u
r
in
g
o
cc
l
u
s
io
n
s
,
a
cr
itical
f
ac
to
r
in
r
ea
l
-
wo
r
ld
ap
p
licatio
n
s
.
T
h
e
m
eth
o
d
f
o
llo
we
d
in
th
is
p
ap
er
d
em
o
n
s
tr
ated
th
e
ca
p
ab
ili
ty
to
ac
cu
r
ately
i
d
en
tify
i
n
d
iv
i
d
u
als
an
d
co
n
s
is
ten
tly
ass
ig
n
th
em
th
e
s
am
e
I
Ds,
ev
en
af
te
r
p
er
io
d
s
o
f
o
cc
lu
s
io
n
.
W
e
f
o
u
n
d
th
at
th
e
e
n
h
an
ce
d
Dee
p
SOR
T
alg
o
r
ith
m
c
o
r
r
elate
s
with
im
p
r
o
v
ed
tr
ac
k
in
g
ac
cu
r
ac
y
,
as
e
v
id
en
ce
d
b
y
h
ig
h
e
r
ac
cu
r
ac
y
p
er
ce
n
tag
es
ac
r
o
s
s
v
ar
io
u
s
v
id
e
o
s
eq
u
en
ce
s
.
T
h
i
s
im
p
r
o
v
em
e
n
t
is
lar
g
ely
attr
ib
u
ted
to
th
e
en
h
a
n
ce
d
Dee
p
SOR
T
’
s
ab
ilit
y
to
m
ain
tain
o
r
ig
i
n
al
I
Ds
o
f
i
n
d
iv
i
d
u
als
d
u
r
in
g
o
cc
l
u
s
io
n
s
b
y
s
u
s
p
en
d
in
g
ap
p
ea
r
an
ce
u
p
d
ates,
t
h
er
eb
y
r
ed
u
cin
g
t
h
e
lik
elih
o
o
d
o
f
in
co
r
r
ec
t
I
D
ass
ig
n
m
en
ts
.
T
h
e
u
s
e
o
f
My
SQL
t
o
f
ac
ilit
ate
th
e
co
m
m
u
n
icatio
n
o
f
tr
ac
k
f
ea
tu
r
es
in
o
r
d
er
to
r
ec
o
g
n
ize
o
b
jects
ac
r
o
s
s
m
u
ltip
le
ca
m
er
as
is
an
o
th
er
k
ey
in
n
o
v
atio
n
o
f
th
is
s
tu
d
y
’
s
ap
p
r
o
ac
h
.
T
h
ese
in
n
o
-
v
atio
n
s
n
o
t
o
n
l
y
i
m
p
r
o
v
e
th
e
f
id
elity
o
f
i
n
d
iv
id
u
al
tr
ac
k
in
g
in
co
m
p
lex
s
ce
n
ar
i
o
s
b
u
t
also
s
et
a
n
ew
b
en
ch
m
ar
k
f
o
r
f
u
tu
r
e
r
esear
c
h
in
th
e
f
ield
o
f
m
u
lti
-
ca
m
er
a
m
u
lti
-
o
b
ject
tr
ac
k
in
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
2
,
May
20
2
5
:
9
9
7
-
1
0
0
9
1004
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
u
n
iq
u
el
y
r
ep
r
esen
ts
ea
ch
p
er
s
o
n
’
s
tr
a
ck
s
tate
at
e
v
er
y
s
in
g
le
f
r
am
e,
a
f
ea
t
u
r
e
th
at
was
n
o
t
p
r
esen
t
in
o
th
er
r
elate
d
s
tu
d
ies.
T
h
is
f
r
am
e
-
by
-
f
r
am
e
r
ep
r
esen
tatio
n
allo
ws
f
o
r
co
n
tin
u
o
u
s
an
d
d
etailed
tr
ac
k
in
g
o
f
in
d
iv
id
u
al
s
,
p
r
o
v
id
in
g
a
r
ich
er
d
ataset
a
n
d
en
a
b
lin
g
m
o
r
e
g
r
a
n
u
lar
a
n
aly
s
is
.
Un
lik
e
o
th
er
m
eth
o
d
s
th
at
m
ay
s
k
ip
f
r
am
e
s
o
r
p
r
o
v
id
e
i
n
co
m
p
lete
d
ata,
th
is
ap
p
r
o
ac
h
e
n
s
u
r
es
th
at
n
o
in
f
o
r
m
atio
n
is
lo
s
t
b
etwe
en
f
r
am
es,
th
e
r
eb
y
e
n
h
a
n
cin
g
th
e
ac
c
u
r
ac
y
a
n
d
c
o
m
p
l
eten
ess
o
f
th
e
tr
ac
k
in
g
s
y
s
tem
.
7
.
1
.
Sin
g
le
ca
m
e
ra
re
s
ults
T
h
e
en
h
a
n
ce
d
Dee
p
SOR
T
alg
o
r
ith
m
c
o
n
s
is
ten
tly
d
em
o
n
s
tr
ates
s
u
p
er
io
r
ac
c
u
r
ac
y
c
o
m
p
ar
ed
to
t
h
e
o
r
ig
in
al,
as
e
v
id
en
ce
d
b
y
h
i
g
h
er
ac
cu
r
ac
y
p
e
r
ce
n
tag
es
ac
r
o
s
s
all
v
id
eo
s
eq
u
en
ce
s
.
T
h
is
im
p
r
o
v
em
en
t
is
lar
g
ely
d
u
e
to
th
e
en
h
an
ce
d
Dee
p
SO
R
T
’
s
ab
ilit
y
to
m
ain
tain
t
h
e
o
r
ig
in
al
I
D
o
f
in
d
iv
id
u
als
ev
en
af
ter
o
cc
lu
s
io
n
s
,
p
r
o
v
id
i
n
g
m
o
r
e
r
eliab
le
tr
ac
k
i
n
g
in
co
m
p
lex
s
ce
n
ar
io
s
.
Fig
u
r
e
1
illu
s
tr
ates
th
e
co
m
p
ar
ativ
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
o
r
ig
in
al
a
n
d
en
h
a
n
ce
d
Dee
p
SOR
T
alg
o
r
ith
m
s
ac
r
o
s
s
th
e
s
ev
en
v
id
e
o
s
eq
u
en
ce
s
.
T
h
e
lin
e
g
r
ap
h
s
h
o
ws
ac
cu
r
ac
y
p
er
ce
n
tag
es
ca
lcu
lated
b
ased
o
n
th
e
p
r
o
p
o
r
tio
n
o
f
f
r
am
es
with
co
r
r
ec
t
I
D
ass
ig
n
m
en
ts
r
elativ
e
to
th
e
to
tal
n
u
m
b
er
o
f
f
r
am
es in
ea
ch
s
in
g
le
-
ca
m
er
a
v
id
e
o
.
Fig
u
r
e
2
co
m
p
ar
es
I
D
ass
ig
n
m
en
t
b
y
th
e
o
r
i
g
in
al
Dee
p
SOR
T
an
d
th
e
p
r
o
p
o
s
ed
e
n
h
an
c
e
d
Dee
p
SOR
T
b
ef
o
r
e
a
n
d
af
ter
o
cc
lu
s
io
n
.
Fig
u
r
es
2
(
a)
an
d
2
(
b
)
s
h
o
w
th
e
o
r
i
g
in
al
Dee
p
SOR
T
’
s
p
er
f
o
r
m
an
ce
b
ef
o
r
e
a
n
d
af
ter
o
cc
lu
s
io
n
,
wh
ile
Fig
u
r
es
2
(
c
)
a
n
d
2
(
d
)
r
ep
r
esen
t
th
e
e
n
h
an
ce
d
Dee
p
SOR
T
’
s
r
esu
lts
.
T
h
e
co
r
r
ec
t
I
D
ass
ig
n
m
en
t
in
Fig
u
r
es
2
(
c)
an
d
2
(
d
)
is
th
e
r
esu
lt
o
f
s
to
p
p
in
g
v
is
u
al
f
ea
tu
r
e
u
p
d
ates
in
ca
s
es
o
f
p
ar
tial
o
r
co
m
p
lete
o
v
er
lap
o
f
tr
ac
k
s
to
p
r
eser
v
e
p
r
o
p
e
r
tr
ac
k
f
ea
tu
r
es.
Fig
u
r
e
1
.
Acc
u
r
ac
y
c
o
m
p
ar
is
o
n
b
etwe
en
o
r
ig
in
al
an
d
en
h
a
n
c
ed
Dee
p
SOR
T
f
o
r
s
in
g
le
ca
m
e
r
a
v
id
eo
(
a)
(
b
)
(
c)
(
d
)
Fig
u
r
e
2
.
I
D
ass
ig
n
m
e
n
t u
s
in
g
;
(
a)
o
r
ig
i
n
al
Dee
p
SOR
T
b
ef
o
r
e
o
cc
lu
s
io
n
an
d
(
b
)
af
ter
o
cc
lu
s
io
n
,
an
d
u
s
in
g
th
e
(
c)
p
r
o
p
o
s
ed
en
h
a
n
ce
d
De
ep
SOR
T
b
ef
o
r
e
o
cc
lu
s
io
n
an
d
(
d
)
af
te
r
o
cc
lu
s
io
n
T
h
e
tr
an
s
itio
n
co
n
d
itio
n
s
b
etwe
en
two
s
tates
o
f
a
tr
ac
k
,
o
b
tain
ed
as
a
r
esu
lt
o
f
im
p
lem
en
tin
g
th
e
en
h
an
ce
d
Dee
p
SOR
T
alg
o
r
ith
m
,
ar
e
d
etailed
in
T
ab
le
6
.
T
h
e
r
o
w
h
ea
d
er
s
r
ep
r
esen
t
th
e
s
tate
o
f
a
tr
ac
k
in
th
e
cu
r
r
en
t
f
r
am
e,
an
d
th
e
c
o
lu
m
n
h
ea
d
er
s
r
e
p
r
esen
t
th
e
s
tate
o
f
t
h
e
tr
ac
k
in
th
e
n
e
x
t
f
r
a
m
e.
T
h
e
ce
lls
r
ep
r
ese
n
t
th
e
co
n
d
itio
n
s
n
ec
ess
ar
y
f
o
r
a
tr
ac
k
to
ch
a
n
g
e
f
r
o
m
o
n
e
s
tate
to
an
o
th
er
.
T
h
e
p
ar
am
eter
s
u
s
ed
in
t
h
e
D
ee
p
SOR
T
alg
o
r
ith
m
in
clu
d
e
‘
n
in
it,
’
wh
ic
h
s
p
ec
if
ies
th
at
a
d
etec
tio
n
m
u
s
t
b
e
co
n
tin
u
o
u
s
ly
d
etec
ted
f
o
r
th
e
f
ir
s
t
th
r
ee
co
n
s
ec
u
tiv
e
f
r
am
es
b
ef
o
r
e
b
ein
g
elig
ib
le
f
o
r
tr
ac
k
ass
ig
n
m
en
t.
T
h
e
‘
m
ax
ag
e
’
v
ar
ia
b
le
in
d
icate
s
th
e
m
ax
im
u
m
n
u
m
b
er
o
f
f
r
am
es
a
tr
ac
k
ca
n
g
o
u
n
d
et
ec
ted
b
ef
o
r
e
b
ein
g
m
ar
k
ed
f
o
r
d
eletio
n
,
s
et
to
6
0
f
r
am
es
in
th
is
im
p
lem
en
tatio
n
;
h
o
wev
er
,
it
tr
an
s
itio
n
s
to
an
‘
I
n
ac
tiv
e
’
s
tate
r
ath
er
th
an
a
‘
Dele
ted
’
s
tate
as
in
th
e
o
r
ig
i
n
al
v
e
r
s
io
n
.
A
d
d
itio
n
ally
,
‘
tim
e
s
in
ce
u
p
d
ate
’
tr
ac
k
s
h
o
w
lo
n
g
a
d
etec
tio
n
h
as r
em
ain
ed
u
n
d
etec
ted
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Mu
lti
-
ca
mera
mu
lti
-
p
ers
o
n
tr
a
ck
in
g
w
ith
Dee
p
S
OR
T a
n
d
MyS
QL
(
S
h
a
s
h
a
n
k
Ho
r
a
ko
d
ig
e
R
a
g
h
a
ve
n
d
r
a
)
1005
T
ab
le
6
.
State
m
atr
ix
C
u
r
r
e
n
t
N
e
x
t
f
r
a
me
F
r
a
me
s
t
a
t
e
n
a
m
e
Te
n
t
a
t
i
v
e
C
o
n
f
i
r
me
d
I
n
a
c
t
i
v
e
D
e
l
e
t
e
d
O
c
c
l
u
d
i
n
g
P
e
r
so
n
-
O
c
c
l
u
d
e
d
O
b
j
e
c
t
-
O
c
c
l
u
d
e
d
Te
n
t
a
t
i
v
e
-
D
e
t
e
c
t
e
d
a
n
d
t
r
a
c
k
e
d
f
o
r
n
_
i
n
i
t
D
e
t
e
c
t
e
d
a
n
d
t
r
a
c
k
e
d
f
o
r
l
e
ss
t
h
a
n
n
_
i
n
i
t
-
-
-
C
o
n
f
i
r
me
d
-
-
O
u
t
o
f
scree
n
f
o
r
ma
x
a
g
e
W
h
e
n
i
t
o
c
c
l
u
d
e
s
a
n
o
t
h
e
r
p
e
r
s
o
n
O
c
c
l
u
d
e
d
b
y
a
n
o
t
h
e
r
p
e
r
s
o
n
O
c
c
l
u
d
e
d
b
y
a
s
t
a
t
i
c
o
b
j
e
c
t
I
n
a
c
t
i
v
e
-
B
a
c
k
t
o
scree
n
a
f
t
e
r
g
o
i
n
g
o
u
t
f
o
r
g
r
e
a
t
e
r
t
h
a
n
max
_
a
g
e
D
e
l
e
t
e
d
i
f
t
i
m
e
si
n
c
e
u
p
d
a
t
e
g
r
e
a
t
e
r
t
h
a
n
1
0
0
0
I
f
t
h
e
t
r
a
c
k
o
c
c
l
u
d
e
s s
o
me
o
n
e
a
s s
o
o
n
a
s i
t
b
e
c
o
m
e
s a
c
t
i
v
e
-
-
D
e
l
e
t
e
d
-
-
-
-
-
-
-
O
c
c
l
u
d
i
n
g
N
o
l
o
n
g
e
r
o
c
c
l
u
d
i
n
g
a
n
o
t
h
e
r
p
e
r
s
o
n
-
-
-
S
w
a
p
b
e
t
w
e
e
n
Tr
a
c
k
I
D
s d
u
r
i
n
g
p
e
r
s
o
n
o
c
c
l
u
s
i
o
n
G
o
e
s
b
e
h
i
n
d
st
a
t
i
c
o
b
j
e
c
t
d
u
r
i
n
g
p
e
r
s
o
n
o
c
c
l
u
si
o
n
-
P
e
r
so
n
O
c
c
l
u
d
e
d
N
o
l
o
n
g
e
r
o
c
c
l
u
d
e
d
b
y
a
n
o
t
h
e
r
p
e
r
s
o
n
O
c
c
l
u
d
e
d
b
y
a
p
e
r
so
n
f
o
r
mo
r
e
t
h
a
n
max
a
g
e
S
w
a
p
b
e
t
w
e
e
n
Tr
a
c
k
I
D
s
d
u
r
i
n
g
p
e
r
s
o
n
o
c
c
l
u
si
o
n
-
-
G
o
e
s
b
e
h
i
n
d
st
a
t
i
c
o
b
j
e
c
t
d
u
r
i
n
g
p
e
r
s
o
n
o
c
c
l
u
si
o
n
-
O
b
j
e
c
t
O
c
c
l
u
d
e
d
N
o
l
o
n
g
e
r
o
c
c
l
u
d
e
d
b
y
a
s
t
a
t
i
c
o
b
j
e
c
t
O
c
c
l
u
d
e
d
b
y
a
st
a
t
i
c
o
b
j
e
c
t
f
o
r
mo
r
e
t
h
a
n
max
a
g
e
-
-
M
o
v
e
s fr
o
m
b
e
h
i
n
d
a
st
a
t
i
c
o
b
j
e
c
t
t
o
b
e
h
i
n
d
a
p
e
r
s
o
n
-
-
7
.
2
.
M
ulti
-
ca
m
er
a
re
s
ults
I
n
th
is
s
ec
tio
n
,
we
p
r
esen
t
th
e
r
esu
lts
o
b
tain
ed
f
r
o
m
th
e
m
u
l
ti
-
ca
m
er
a
tr
ac
k
in
g
s
y
s
tem
,
em
p
h
asizin
g
th
e
s
itu
atio
n
s
r
ec
o
r
d
ed
an
d
th
e
ir
r
esp
ec
tiv
e
o
u
tp
u
ts
.
T
ab
le
7
d
etails
v
ar
io
u
s
s
ce
n
ar
io
s
ca
p
tu
r
ed
b
y
th
e
ca
m
e
r
as.
T
h
e
h
i
g
h
er
I
Ds
(
g
r
ea
ter
th
an
2
)
in
th
e
r
esu
lts
ca
n
b
e
attr
ib
u
ted
to
m
is
s
in
g
d
etec
tio
n
s
at
th
e
b
e
g
in
n
in
g
o
f
th
e
o
b
s
er
v
atio
n
p
er
io
d
,
wh
ich
lea
d
s
to
th
e
cr
ea
tio
n
an
d
m
ain
ten
an
ce
o
f
th
ese
h
ig
h
er
I
D
v
alu
es
.
Fig
u
r
e
3
illu
s
tr
ate
th
e
o
u
t
p
u
ts
ca
p
tu
r
e
d
d
u
r
n
g
E
v
en
t
5
(
as
d
escr
ib
ed
in
T
ab
le
7
)
.
T
h
ese
F
ig
u
r
es
3
(
a)
an
d
3
(
b
)
s
h
o
wca
s
e
th
e
r
ea
l
-
tim
e
tr
ac
k
in
g
r
esu
lts
f
r
o
m
b
o
t
h
ca
m
er
as,
h
ig
h
lig
h
tin
g
h
o
w
Per
s
o
n
1
(
with
I
D
3
(
o
x
)
)
an
d
Per
s
o
n
2
(
with
I
D
2
(
d
u
)
)
a
r
e
ass
ig
n
ed
a
n
d
m
ain
tain
ed
th
e
ir
r
esp
ec
tiv
e
I
Ds
wh
ile
tr
a
n
s
itio
n
in
g
f
r
o
m
C
AM
1
to
C
AM
2
in
a
s
im
u
ltan
eo
u
s
h
o
r
izo
n
tal
m
o
v
em
en
t.
T
ab
le
7
.
Mu
lti
-
ca
m
e
r
a
r
esu
lt d
etails
Ev
e
n
t
N
o
.
S
i
t
u
a
t
i
o
n
d
e
scri
p
t
i
o
n
O
u
t
p
u
t
1
P
e
r
so
n
A
w
a
l
k
s
h
o
r
i
z
o
n
t
a
l
l
y
f
r
o
m
C
A
M
1
t
o
C
A
M
2
C
A
M
1
:
I
D
1
(
g
j
)
m
a
i
n
t
a
i
n
e
d
;
C
A
M
2
:
S
a
me
I
D
1
(
g
j
)
.
2
P
e
r
so
n
A
w
a
l
k
s
h
o
r
i
z
o
n
t
a
l
l
y
f
r
o
m
C
A
M
2
t
o
C
A
M
1
C
A
M
1
:
I
D
1
(
h
v
)
m
a
i
n
t
a
i
n
e
d
;
C
A
M
2
:
S
a
me
I
D
1
(
h
v
)
.
3
P
e
r
so
n
A
w
a
l
k
s
d
i
a
g
o
n
a
l
l
y
f
r
o
m
t
o
p
-
l
e
f
t
C
A
M
1
t
o
b
o
t
t
o
m
-
r
i
g
h
t
C
A
M
2
.
C
A
M
1
:
I
D
4
(
w
k
)
mai
n
t
a
i
n
e
d
;
C
A
M
2
:
S
a
me
I
D
4
(
w
k
)
.
4
P
e
r
so
n
A
w
a
l
k
s
d
i
a
g
o
n
a
l
l
y
f
r
o
m
b
o
t
t
o
m
-
r
i
g
h
t
C
A
M
2
t
o
t
o
p
-
l
e
f
t
C
A
M
1
.
C
A
M
1
:
I
D
1
(
mz) mai
n
t
a
i
n
e
d
;
C
A
M
2
:
S
a
me
I
D
1
(
mz).
5
P
e
r
so
n
s A a
n
d
B
m
o
v
e
h
o
r
i
z
o
n
t
a
l
l
y
f
r
o
m
C
A
M
1
t
o
C
A
M
2
.
C
A
M
1
:
I
D
s 3
(
o
x
)
,
2
(
d
u
)
;
C
A
M
2
:
S
a
me
I
D
s.
6
P
e
r
so
n
s A a
n
d
B
m
o
v
e
h
o
r
i
z
o
n
t
a
l
l
y
f
r
o
m
C
A
M
2
t
o
C
A
M
1
C
A
M
2
:
I
D
s 1
(
p
m)
,
2
(
c
l
)
;
C
A
M
1
:
S
a
me
I
D
s
7
P
e
r
so
n
A
w
a
l
k
s
f
r
o
m
C
A
M
1
t
o
C
A
M
2
;
P
e
r
so
n
B
f
o
l
l
o
w
s
a
f
t
e
r
C
A
M
1
:
A
g
e
t
s
I
D
1
(
p
f
)
;
C
A
M
2
:
B
g
e
t
s I
D
2
(
u
s)
a
f
t
e
r
A
e
x
i
t
s
8
P
e
r
so
n
A
w
a
l
k
s
f
r
o
m
C
A
M
2
t
o
C
A
M
1
;
P
e
r
so
n
B
f
o
l
l
o
w
s
a
f
t
e
r
C
A
M
2
:
A
g
e
t
s
I
D
1
(
o
i
)
;
C
A
M
1
:
B
g
e
t
s I
D
2
(
w
y
)
a
f
t
e
r
A
e
x
i
t
s
9
P
e
r
so
n
s A a
n
d
B
w
a
l
k
d
i
a
g
o
n
a
l
l
y
t
o
w
a
r
d
s
o
p
p
o
si
t
e
c
o
r
n
e
r
s
C
A
M
1
:
A
g
e
t
s
I
D
4
(
y
r
)
;
C
A
M
2
:
B
g
e
t
s I
D
1
(
y
x
)
10
P
e
r
so
n
A
o
c
c
l
u
d
e
s
P
e
r
s
o
n
B,
b
o
t
h
m
o
v
e
to
C
A
M
1
,
t
h
e
n
s
p
l
i
t
C
A
M
2
:
I
D
s
1
(
o
a
)
,
2
(
o
w
)
.
A
o
c
c
l
u
d
e
s
B,
w
h
o
g
o
e
s
i
n
a
c
t
i
v
e
a
f
t
e
r
6
0
f
r
a
mes
.
C
A
M
1
:
A
n
e
w
d
e
t
e
c
t
i
o
n
b
o
x
m
e
r
g
e
s
t
h
e
m
i
n
t
o
I
D
8
(
l
r
)
.
I
D
s 1
(
o
a
)
,
2
(
o
w
)
r
e
st
o
r
e
d
a
f
t
e
r
s
p
l
i
t
t
i
n
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
2
,
May
20
2
5
:
9
9
7
-
1
0
0
9
1006
(
a)
(
b
)
Fig
u
r
e
3
.
Ou
t
p
u
ts
f
o
r
e
v
en
t 5
(
d
escr
ib
ed
in
T
a
b
le
7
)
;
(
a
)
f
r
o
m
C
AM
1
an
d
(
b
)
C
AM
2
s
h
o
win
g
tr
ac
k
in
g
r
esu
lts
an
d
I
D
ass
ig
n
m
en
t
7
.
3
.
Ca
v
ea
t
s
a
nd
lim
it
a
t
io
ns
W
h
ile
th
e
p
r
o
p
o
s
ed
m
eth
o
d
a
d
v
an
ce
s
m
u
lti
-
o
b
ject
tr
ac
k
in
g
,
s
ev
er
al
lim
itatio
n
s
wer
e
en
co
u
n
ter
ed
i
n
th
e
s
tu
d
y
,
h
i
g
h
lig
h
tin
g
ar
ea
s
f
o
r
p
o
te
n
tial r
ef
in
em
e
n
t a
n
d
f
u
t
u
r
e
r
esear
ch
:
−
I
n
co
r
r
ec
t
a
s
s
ig
n
m
en
t
o
f
‘
O
b
j
ec
tOcc
lu
d
ed
’
:
a
p
er
s
o
n
m
ay
b
e
m
is
class
if
ied
a
s
‘
O
b
jectO
cc
lu
d
ed
’
d
u
e
to
d
etec
tio
n
lap
s
es o
r
m
o
v
in
g
o
b
j
ec
t o
cc
lu
s
i
o
n
s
,
ca
u
s
in
g
in
c
o
r
r
e
ct
ass
u
m
p
tio
n
s
o
f
s
tatic
o
cc
lu
s
io
n
.
−
I
n
co
r
r
ec
t
a
s
s
ig
n
m
en
t
o
f
‘
Occ
l
u
d
in
g
’
:
t
h
e
s
y
s
tem
d
eter
m
i
n
es
o
cc
lu
s
io
n
u
s
in
g
I
OU
b
ased
o
n
b
o
u
n
d
in
g
b
o
x
o
v
er
lap
.
Ho
wev
e
r
,
it
m
ay
lab
el
a
p
er
s
o
n
as
‘
Occ
lu
d
in
g
’
ev
en
wh
en
th
e
o
b
ject
ca
u
s
in
g
th
e
o
v
er
lap
is
h
id
d
en
,
r
esu
ltin
g
in
in
ac
cu
r
ate
tr
ac
k
in
g
s
tatu
s
es.
−
Ov
er
lap
r
eg
io
n
d
ilem
m
a:
wh
en
a
p
er
s
o
n
en
ter
s
th
e
o
v
er
la
p
r
eg
io
n
b
etwe
en
two
ca
m
er
as
with
o
u
t
p
r
io
r
d
etec
tio
n
,
th
e
y
m
ig
h
t
b
e
ass
ig
n
ed
d
if
f
er
e
n
t
I
Ds
in
ea
ch
v
iew
d
u
e
to
th
e
lack
o
f
d
atab
ase
i
n
f
o
r
m
atio
n
,
u
n
d
er
-
s
co
r
in
g
th
e
n
ee
d
f
o
r
b
etter
i
d
e
n
tity
tr
ac
k
in
g
ac
r
o
s
s
ca
m
er
as.
−
No
t
en
ter
in
g
wr
itin
g
p
o
ly
g
o
n
:
if
a
p
er
s
o
n
ex
its
ca
m
er
a
1
with
o
u
t
e
n
ter
in
g
th
e
d
esig
n
ated
wr
itin
g
p
o
l
y
g
o
n
,
th
eir
f
ea
tu
r
es
wo
n
’
t
b
e
r
ec
o
r
d
e
d
.
I
f
th
ey
later
a
p
p
ea
r
in
ca
m
er
a
2
,
t
h
ey
will
r
ec
eiv
e
a
d
if
f
e
r
en
t
I
D,
illu
s
tr
atin
g
th
e
s
y
s
tem
’
s
r
elian
ce
o
n
p
o
ly
g
o
n
r
eg
i
o
n
s
f
o
r
f
ea
tu
r
e
r
eg
is
tr
atio
n
.
8.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
p
r
esen
ts
k
e
y
en
h
a
n
ce
m
en
ts
to
th
e
Dee
p
SOR
T
alg
o
r
ith
m
,
e
n
ab
lin
g
th
e
m
ai
n
ten
an
ce
o
f
in
d
iv
id
u
al
I
Ds
ev
en
af
te
r
o
cc
l
u
s
io
n
s
,
a
ch
allen
g
e
in
ea
r
lier
i
m
p
lem
en
tatio
n
s
.
T
h
e
m
et
h
o
d
was
test
ed
o
n
b
o
th
s
in
g
le
-
an
d
m
u
lti
-
ca
m
er
a
v
id
e
o
s
,
ac
h
iev
in
g
co
n
s
is
ten
t
id
en
tity
tr
ac
k
in
g
ac
r
o
s
s
ca
m
er
as.
A
n
o
v
el
asp
ec
t
o
f
th
is
r
esear
ch
is
th
e
u
s
e
o
f
a
My
S
QL
d
atab
ase
f
o
r
s
h
ar
in
g
ap
p
e
ar
an
ce
f
ea
tu
r
es
ac
r
o
s
s
ca
m
er
as,
m
ar
k
in
g
th
e
f
ir
s
t
attem
p
t
at
s
u
ch
an
ap
p
r
o
ac
h
.
F
o
u
r
n
ew
s
tates
-
Occ
lu
d
in
g
,
P
er
s
o
n
Occ
lu
d
ed
,
O
b
jectOc
clu
d
e
d
,
an
d
I
n
ac
tiv
e
-
wer
e
in
tr
o
d
u
ce
d
,
p
r
o
v
id
i
n
g
a
m
o
r
e
co
m
p
r
eh
e
n
s
iv
e
f
r
am
ew
o
r
k
f
o
r
tr
ac
k
in
g
a
n
d
en
c
o
u
r
a
g
in
g
f
u
r
t
h
er
r
esear
ch
.
Evaluation Warning : The document was created with Spire.PDF for Python.