I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
9
,
No
.
4
,
A
u
g
u
s
t
201
9
,
p
p
.
2
7
1
5
~
2
7
2
4
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
9
i
4
.
p
p
2
7
1
5
-
2724
2715
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/
jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JE
C
E
Si
m
pl
ified
video
s
urv
eilla
nce f
ra
m
e
w
o
rk
f
o
r dyna
m
ic
object
detec
tion unde
r c
ha
lleng
ing
enviro
n
m
e
nt
M
a
dh
u Cha
nd
ra
G
1
,
Sree
ra
m
a
Red
dy
G
.
M
2
1
,2
De
p
a
rtm
e
n
t
o
f
El
e
c
tro
n
ics
&
Co
m
m
u
n
ica
ti
o
n
E
n
g
in
e
e
rin
g
,
C
By
re
g
o
w
d
a
In
stit
u
te o
f
T
e
c
h
n
o
lo
g
y
,
In
d
ia
1
De
p
a
rtme
n
t
o
f
El
e
c
tro
n
ics
&
Co
m
m
u
n
ica
ti
o
n
En
g
in
e
e
rin
g
,
V
isv
e
sv
a
ra
y
a
Tec
h
n
o
lo
g
ica
l
Un
iv
e
rsity
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
l 1
8
,
2
0
1
8
R
ev
i
s
ed
Ma
r
1
1
,
2
0
1
9
A
cc
ep
ted
Ma
r
1
8
,
2
0
1
9
A
n
e
ffe
c
ti
v
e
v
id
e
o
su
rv
e
il
lan
c
e
s
y
ste
m
is
h
ig
h
ly
e
ss
e
n
ti
a
l
in
o
r
d
e
r
to
e
n
su
re
c
o
n
stru
c
ti
n
g
b
e
tt
e
r
f
o
rm
o
f
v
id
e
o
a
n
a
ly
ti
c
s.
Ex
isti
n
g
re
v
ie
w
o
f
li
tera
tu
re
s
p
e
rtain
in
g
to
v
i
d
e
o
a
n
a
ly
ti
c
s
a
re
f
o
u
n
d
to
d
irec
tl
y
im
p
le
m
e
n
t
a
lg
o
rit
h
m
s
o
n
th
e
to
p
o
f
th
e
v
id
e
o
f
il
e
w
it
h
o
u
t
m
u
c
h
e
m
p
h
a
sis
o
n
f
o
ll
o
w
in
g
p
ro
b
lem
s
i.
e
.
i)
d
y
n
a
m
ic
o
rien
tatio
n
o
f
su
b
je
c
t,
ii
)p
o
o
r
il
l
u
m
in
a
ti
o
n
c
o
n
d
i
ti
o
n
,
ii
i)
id
e
n
ti
f
ica
ti
o
n
a
n
d
c
las
sif
ica
ti
o
n
o
f
su
b
jec
ts,
a
n
d
iv
)
f
a
ste
r
re
sp
o
n
se
ti
m
e
.
T
h
e
re
f
o
re
,
th
e
p
ro
p
o
se
d
sy
ste
m
im
p
le
m
e
n
ts
a
n
a
n
a
l
y
ti
c
a
l
c
o
n
c
e
p
t
th
a
t
u
se
s
d
e
p
th
-
im
a
g
e
o
f
th
e
v
id
e
o
f
e
e
d
a
l
o
n
g
w
it
h
th
e
o
rig
in
a
l
c
o
lo
re
d
v
id
e
o
f
e
e
d
to
a
p
p
ly
a
n
a
lg
o
rit
h
m
f
o
r
e
x
trac
ti
n
g
sig
n
i
f
ica
n
t
in
f
o
r
m
a
ti
o
n
a
b
o
u
t
t
h
e
m
o
ti
o
n
b
lo
b
o
f
th
e
d
y
n
a
m
ic
su
b
jec
ts.
I
m
p
lem
e
n
ted
in
M
ATLA
B,
th
e
stu
d
y
o
u
tco
m
e
sh
o
w
s
th
a
t
it
is
c
a
p
a
b
le
o
f
a
d
d
re
ss
in
g
a
ll
th
e
a
b
o
v
e
m
e
n
ti
o
n
e
d
p
ro
b
lem
s
a
ss
o
c
iate
d
w
it
h
e
x
isti
n
g
re
s
e
a
rc
h
tren
d
s
o
n
v
id
e
o
a
n
a
ly
ti
c
s
b
y
u
si
n
g
a
v
e
r
y
sim
p
le
a
n
d
n
o
n
-
it
e
ra
ti
v
e
p
ro
c
e
ss
o
f
i
m
p
le
m
e
n
tatio
n
.
T
h
e
a
p
p
li
c
a
b
i
li
ty
o
f
th
e
p
ro
p
o
se
d
sy
ste
m
in
p
ra
c
ti
c
a
l
w
o
rld
is t
h
e
re
b
y
p
ro
v
e
n
.
K
ey
w
o
r
d
s
:
Mo
b
ile
Ob
j
ec
t
T
r
ac
k
in
g
Mo
tio
n
B
lo
b
Ob
j
ec
t I
d
en
tif
icat
io
n
Vid
eo
A
n
a
l
y
tic
s
Vid
eo
Su
r
v
eilla
n
ce
Co
p
y
rig
h
t
©
2
0
1
9
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Ma
d
h
u
C
h
a
n
d
r
a
G
R
esear
ch
Sch
o
lar
,
Dep
ar
t
m
e
n
t
o
f
E
lectr
o
n
ics
&
C
o
m
m
u
n
icat
io
n
E
n
g
in
ee
r
i
n
g
,
C
B
y
r
eg
o
w
d
a
I
n
s
t
itu
te
o
f
T
ec
h
n
o
lo
g
y
,
Ko
lar
,
Vis
v
e
s
v
ar
a
y
a
T
ec
h
n
o
lo
g
ical
Un
i
v
er
s
it
y
,
B
elag
a
v
i,
I
n
d
ia
E
m
ail:
m
ad
h
u
.
g
u
r
u
1
9
8
4
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
No
w
ad
a
y
s
,
s
ec
u
r
it
y
s
y
s
te
m
s
f
o
r
r
esid
en
tial,
b
an
k
s
,
m
al
ls
,
etc.
,
is
n
ec
es
s
ar
y
d
u
e
to
in
cr
e
ased
cr
i
m
e
r
ate
ar
o
u
n
d
u
s
.
T
h
u
s
,
v
id
eo
s
u
r
v
eilla
n
ce
i
s
w
id
el
y
co
n
s
id
er
ed
in
r
ec
e
n
t
p
ast
w
h
ich
o
f
f
er
s
v
id
eo
f
o
o
tag
e
s
,
r
ec
o
r
d
s
to
f
in
d
o
u
t
th
e
cr
i
m
i
n
al
o
r
u
n
u
s
u
al
ac
ti
v
it
y
i
n
th
at
p
ar
ticu
lar
ar
ea
.
R
ec
en
t
ad
v
an
c
e
m
en
t
in
co
m
p
u
ter
v
is
io
n
to
o
ls
s
u
c
h
a
s
s
en
s
o
r
tech
n
o
lo
g
y
,
s
to
r
ag
e
ca
p
ac
it
y
a
n
d
h
i
g
h
r
eso
l
u
tio
n
d
is
p
la
y
s
h
av
e
m
ad
e
s
u
p
er
io
r
p
r
o
g
r
ess
in
v
id
eo
s
u
r
v
eil
lan
c
e
s
y
s
te
m
s
.
T
h
is
ad
v
an
ce
m
e
n
t
in
s
u
r
v
eilla
n
ce
s
y
s
te
m
s
in
c
o
r
p
o
r
ates
a
v
id
eo
an
al
y
tics
m
ec
h
a
n
is
m
th
a
t
m
e
ets
t
h
e
s
p
ec
if
ic
clas
s
i
f
icatio
n
o
f
o
b
j
ec
ts
f
r
o
m
t
h
e
i
m
ag
e
s
eq
u
en
ce
s
b
ased
o
n
u
s
er
’
s
r
eq
u
ir
e
m
en
ts
[
1
]
.
Vid
eo
an
al
y
tic
s
r
ef
er
s
to
t
h
e
ab
i
lit
y
o
f
a
u
to
n
o
m
o
u
s
u
n
d
er
s
ta
n
d
in
g
o
f
o
b
j
ec
ts
o
r
r
elev
an
t
ev
e
n
ts
f
r
o
m
t
h
e
v
i
s
u
al
d
a
ta
f
r
a
m
e
f
o
r
d
if
f
er
e
n
t
p
u
r
p
o
s
es
w
it
h
o
u
t
a
n
y
h
u
m
a
n
i
n
v
o
lv
e
m
e
n
t.
Fu
r
t
h
er
m
o
r
e,
it
is
co
llab
o
r
atio
n
o
f
co
m
p
u
ter
v
i
s
io
n
,
i
m
a
g
i
n
g
tec
h
n
iq
u
e,
m
ac
h
i
n
e
in
telli
g
en
ce
a
n
d
an
al
y
tics
co
n
ce
p
t
w
h
ic
h
d
etec
t
s
t
h
e
te
m
p
o
r
al
a
n
d
s
p
atial
e
v
e
n
ts
o
f
v
is
u
al
d
ata
s
tr
ea
m
s
a
n
d
g
e
n
er
ates
s
p
ec
if
ic
an
d
r
elev
an
t
p
atter
n
s
[
2
]
.
T
h
e
p
o
ten
tial
o
f
v
id
eo
an
al
y
tic
s
ap
p
licatio
n
ca
n
b
e
r
ea
lize
th
r
o
u
g
h
th
at
it
b
ec
a
m
e
an
ess
e
n
tial
p
ar
t
o
f
t
h
e
v
ar
io
u
s
o
r
g
an
izat
io
n
s
s
u
c
h
as
m
ed
ical,
g
o
v
er
n
m
e
n
t
a
n
d
p
r
iv
ate
s
ec
to
r
s
[
3
]
.
I
t
p
lay
s
v
er
y
ef
f
ec
tiv
e
r
o
le
in
t
h
e
f
ield
o
f
s
u
r
v
eilla
n
ce
f
o
r
s
ec
u
r
it
y
,
cr
im
e
i
n
v
esti
g
atio
n
,
r
etail,
m
ar
k
et,
m
ilit
ar
y
,
au
to
m
o
b
iles
,
tr
a
f
f
ic
co
n
tr
o
lli
n
g
,
etc.
w
it
h
w
id
e
s
co
p
e
o
f
o
b
j
ec
t
d
etec
tio
n
,
o
b
j
ec
tio
n
r
ec
o
g
n
itio
n
,
o
b
j
ec
t
tr
ac
k
in
g
a
n
d
e
v
en
t
e
x
tr
ac
tio
n
f
r
o
m
t
h
e
i
m
a
g
e
as
w
ell
a
s
v
id
eo
s
ce
n
es
[
4
]
.
T
h
e
d
etec
ti
o
n
an
d
r
ec
o
g
n
it
io
n
p
r
o
ce
s
s
in
v
id
eo
an
al
y
tic
s
i
n
v
o
lv
es
s
ev
er
al
p
r
o
ce
d
u
r
es
f
r
o
m
i
m
a
g
e
p
r
o
ce
s
s
in
g
lev
el
to
i
n
ter
p
r
etatio
n
o
f
t
h
e
v
id
eo
s
ce
n
e
w
h
ic
h
i
s
i
m
p
o
s
s
ib
le
f
o
r
th
e
h
u
m
a
n
o
p
er
ato
r
s
to
m
a
n
u
all
y
e
x
ec
u
te
th
i
s
p
r
o
ce
s
s
[
5
]
.
T
h
e
o
b
s
er
v
ati
o
n
,
f
ea
t
u
r
e
ex
tr
ac
tio
n
an
d
class
i
f
icatio
n
o
f
ev
en
t
s
u
s
es
v
ar
io
u
s
ad
v
an
ce
t
ec
h
n
iq
u
es
s
u
c
h
as
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
4
,
A
u
g
u
s
t
201
9
:
2
7
1
5
-
2724
2716
m
ac
h
in
e
lear
n
i
n
g
,
d
ee
p
lear
n
i
n
g
,
n
e
u
r
al
n
e
t
w
o
r
k
s
a
n
d
d
ata
an
al
y
tics
u
s
ed
f
o
r
t
h
e
f
ea
tu
r
e
class
i
f
icat
io
n
a
n
d
k
n
o
w
led
g
e
d
is
co
v
er
y
.
Mo
r
eo
v
er
,
it
h
as
b
ee
n
s
ee
n
t
h
at
m
a
n
y
e
x
i
s
ti
n
g
r
esear
ch
e
s
h
a
v
e
ca
r
r
ied
to
w
ar
d
s
in
t
h
e
d
o
m
ai
n
o
f
v
id
eo
an
al
y
tics
w
i
th
th
e
ir
ad
v
a
n
ta
g
es
a
n
d
li
m
it
atio
n
s
[
6
-
8
]
.
A
l
s
o
,
v
ar
io
u
s
a
n
d
d
if
f
er
en
t
e
x
is
tin
g
w
o
r
k
o
f
v
id
eo
an
al
y
tic
s
f
o
r
o
b
j
ec
t
an
d
ev
en
t
d
etec
tio
n
ar
e
d
i
s
cu
s
s
ed
in
r
e
v
ie
w
o
f
l
iter
atu
r
e
s
ec
t
io
n
.
Ho
w
ev
er
,
o
n
e
s
id
e
v
id
eo
an
al
y
tic
s
o
p
en
s
g
r
ea
t
o
p
p
o
r
tu
n
ities
an
d
p
r
o
m
is
e
s
f
o
r
th
e
in
d
i
v
id
u
a
l
o
r
g
an
izatio
n
s
i
n
ter
m
s
o
f
h
ig
h
er
s
ec
u
r
it
y
,
a
u
t
h
en
t
icatio
n
,
lo
s
s
p
r
ev
e
n
tio
n
a
n
d
h
i
g
h
er
b
u
s
i
n
es
s
v
al
u
e
[
9
]
.
On
o
t
h
er
h
a
n
d
s
id
e
it
f
ac
e
s
s
o
m
e
t
y
p
ical
ch
al
len
g
es
t
h
at
it
is
f
ac
e
d
ata
m
a
n
a
g
e
m
e
n
t
p
r
o
b
lem
,
i
n
ef
f
ic
ien
t
f
o
r
d
etec
ti
n
g
co
m
p
lex
e
v
e
n
ts
s
u
c
h
a
s
f
ac
e
d
etec
tio
n
i
n
cr
o
w
ed
,
d
etec
tio
n
o
f
m
o
v
in
g
o
b
j
ec
ts
in
r
ea
l
-
t
i
m
e,
e
v
e
n
t
d
etec
tio
n
i
n
d
i
f
f
er
en
t
w
ea
t
h
er
co
n
d
itio
n
s
an
d
en
v
ir
o
n
m
e
n
ts
,
etc
[
1
0
]
.
So
th
er
e
is
an
i
m
m
e
n
s
e
r
eq
u
ir
e
m
en
t
o
f
s
u
c
h
ef
f
ec
ti
v
e
to
o
ls
an
d
m
ec
h
a
n
is
m
th
at
r
esear
ch
e
s
h
a
v
e
to
i
n
tr
o
d
u
ce
w
ith
t
h
e
e
x
p
lo
s
iv
e
g
r
o
w
i
n
g
o
f
th
e
s
e
r
ea
l
d
ata’
s
an
d
s
m
ar
t
s
u
r
v
eilla
n
ce
s
y
s
te
m
s
in
o
r
d
er
p
r
o
v
id
e
f
u
ll
s
ec
u
r
it
y
a
n
d
b
u
s
i
n
ess
g
a
in
.
T
h
er
ef
o
r
e,
th
e
p
r
ese
n
t
p
ap
er
in
tr
o
d
u
ce
s
“a
m
o
d
el
t
h
at
u
s
es
s
i
m
p
li
f
ied
ap
p
r
o
ac
h
u
s
in
g
m
o
tio
n
b
lo
b
a
n
d
i
m
a
g
e
d
ep
th
in
o
r
d
er
to
s
o
lv
e
th
e
p
r
o
b
le
m
o
f
d
y
n
a
m
ic
s
u
b
j
ec
t
id
en
ti
f
icatio
n
”.
Sectio
n
2
d
is
c
u
s
s
e
s
ab
o
u
t
a
lg
o
r
ith
m
i
m
p
le
m
en
tatio
n
f
o
llo
w
ed
b
y
d
i
s
cu
s
s
io
n
o
f
r
esu
lt a
n
al
y
s
i
s
in
Sectio
n
3
.
Fin
all
y
,
th
e
co
n
clu
s
i
v
e
r
e
m
ar
k
s
ar
e
p
r
o
v
id
ed
in
Sectio
n
4
.
T
h
is
s
ec
tio
n
d
i
s
cu
s
s
es
ab
o
u
t
t
h
e
ex
is
ti
n
g
r
esear
ch
w
o
r
k
s
t
h
at
ca
r
r
ied
in
th
e
d
i
v
is
io
n
o
f
v
id
eo
d
ata
an
al
y
tics
.
T
h
e
p
r
ev
io
u
s
w
o
r
k
s
o
f
Ma
d
h
u
C
h
an
d
r
a
an
d
R
e
d
d
y
p
r
esen
ted
a)
co
n
ce
p
tu
al
as
w
e
ll
as
r
esear
c
h
o
v
er
v
ie
w
o
n
v
id
eo
a
n
al
y
tical
m
o
d
eli
n
g
[
1
1
]
,
b
)
an
an
al
y
tica
l
f
r
a
m
e
w
o
r
k
[
1
2
]
to
f
u
l
f
ill
th
e
r
esear
ch
g
ap
f
o
u
n
d
in
[
1
1
]
b
y
u
s
i
n
g
d
ictio
n
ar
y
b
ased
ap
p
r
o
ac
h
an
d
u
n
s
u
p
er
v
is
ed
lear
n
i
n
g
(
Us
L
)
ap
p
r
o
ac
h
a
n
d
c)
i
n
[
1
3
]
m
u
lti
v
ar
iate
an
al
y
s
is
an
d
U
s
L
is
u
s
ed
to
id
en
tify
t
h
e
co
n
te
x
t
u
al
o
u
tlier
.
T
h
e
w
o
r
k
o
f
p
r
ab
h
a
k
ar
an
e
t
al.
[
8
]
h
av
e,
d
i
s
cu
s
s
ed
b
o
th
p
o
ten
tial
a
n
d
is
s
u
es
o
f
v
id
eo
a
n
al
y
tics
in
v
ar
io
u
s
a
s
p
ec
ts
.
I
n
th
e
s
t
u
d
y
o
f
[
1
4
]
Asl
a
m
an
d
c
u
r
r
y
h
av
e
ap
p
lied
d
ee
p
lear
n
in
g
t
ec
h
n
iq
u
e
f
o
r
ev
en
t
d
etec
tio
n
f
o
r
t
h
e
r
ea
l
-
ti
m
e
d
at
a
g
e
n
er
ated
f
r
o
m
th
e
m
u
lt
i
m
e
d
ia’
s
i
n
ter
n
et
o
f
t
h
in
g
s
.
T
h
e
w
o
r
k
ca
r
r
ied
o
u
t
b
y
B
allas
et
al.
[
1
5
]
h
av
e
in
v
est
i
g
ated
th
e
ca
p
ab
ilit
ie
s
o
f
v
id
eo
p
r
o
ce
s
s
in
g
b
ased
o
n
f
r
a
m
e
o
f
I
o
T
in
f
r
astr
u
ctu
r
e
b
y
u
s
i
n
g
li
g
h
t g
ate
w
a
y
n
o
d
es f
o
r
cr
o
w
d
m
o
n
ito
r
in
g
an
d
ev
e
n
t d
etec
tio
n
.
I
m
b
ala
n
ce
d
ata
cl
ass
i
f
icatio
n
al
w
a
y
s
s
ee
m
s
as
ch
a
llen
g
i
n
g
is
s
u
e
i
n
th
e
d
ata
an
al
y
tics
.
So
,
Ya
n
g
et
al.
[
1
6
]
h
av
e
d
esig
n
ed
a
ef
f
ici
en
t
f
r
a
m
e
w
o
r
k
f
o
r
m
u
lti
m
ed
ia
a
n
al
y
s
is
.
T
h
e
p
r
esen
ted
f
r
a
m
e
w
o
r
k
u
s
e
s
s
tatis
t
ical
d
ata
an
a
l
y
s
is
alg
o
r
it
h
m
f
o
r
f
ea
tu
r
e
s
elec
tio
n
an
d
class
i
f
icat
io
n
.
Sh
ao
et
al.
[
1
7
]
h
av
e
p
r
o
p
o
s
ed
an
in
telli
g
en
t
ap
p
r
o
ac
h
f
o
r
ev
en
t
d
etec
tio
n
f
r
o
m
s
u
r
v
ei
llan
ce
s
y
s
te
m
.
I
n
th
is
a
u
t
h
o
r
h
a
v
e
u
tili
ze
s
s
m
ar
t
m
o
n
ito
r
i
n
g
s
y
s
te
m
t
h
at
h
av
e
av
ailab
il
it
y
to
g
e
n
er
ate
alar
m
f
o
r
ab
n
o
r
m
a
l
ev
en
t
s
a
n
d
also
h
av
e
m
a
x
i
m
u
m
s
to
r
ag
e
ca
p
ab
ilit
y
,
h
i
g
h
er
i
n
f
o
r
m
atio
n
r
etr
ie
v
al
p
r
o
p
er
t
y
.
I
n
[
1
8
]
Di
m
itrio
u
s
et
al.
h
av
e
p
r
esen
ted
m
o
d
u
lar
s
u
r
v
eilla
n
ce
m
o
d
el
b
ased
o
n
e
m
b
ed
d
ed
co
m
p
u
ti
n
g
tec
h
n
iq
u
e
f
o
r
e
f
f
icien
t
v
id
eo
an
al
y
tics
s
o
l
u
tio
n
f
o
r
d
etec
tin
g
m
i
n
o
r
cr
i
m
es.
Ma
et
al.
[
1
9
]
h
av
e
p
r
esen
ted
o
p
ti
m
al
s
to
r
a
g
e
ap
p
r
o
ac
h
b
ase
d
o
n
k
e
y
-
i
n
d
ex
in
g
to
ex
tr
ac
t
t
h
e
u
s
e
f
u
l
co
n
te
n
t
i
n
ef
f
icie
n
t
w
a
y
.
T
h
e
ex
p
er
i
m
e
n
tal
o
u
tco
m
e
o
f
p
r
esen
ted
s
t
u
d
y
s
h
o
w
s
t
h
at
it
ac
h
ie
v
es
g
o
o
d
p
er
f
o
r
m
a
n
ce
f
o
r
ex
to
r
tio
n
o
f
in
f
o
r
m
atio
n
f
r
o
m
s
u
r
v
eill
an
ce
v
id
eo
co
n
te
n
t.
B
r
in
to
n
et
al.
[
2
0
]
h
av
e
s
t
u
d
i
ed
th
e
p
er
f
o
r
m
an
ce
o
f
s
t
u
d
en
t
b
eh
av
io
r
o
f
w
atc
h
i
n
g
-
v
id
eo
an
d
f
o
r
m
u
lated
a
n
o
v
el
e
v
en
t d
etec
tio
n
f
r
a
m
e
wo
r
k
b
ased
o
n
s
eq
u
en
ce
s
o
f
n
u
m
b
er
o
f
e
v
e
n
t r
o
u
n
d
a
n
d
b
eh
av
io
r
o
f
p
o
s
itio
n
s
.
P
h
a
m
et
al.
[
2
1
]
h
av
e
p
r
ese
n
te
d
a
n
o
v
el
m
o
d
el
f
o
r
m
i
ti
g
ati
n
g
th
e
p
r
o
b
le
m
o
cc
u
r
s
in
b
ac
k
g
r
o
u
n
d
p
o
s
e
d
etec
tio
n
in
s
u
r
v
eilla
n
ce
s
y
s
te
m
s
.
B
ased
o
n
th
eo
r
etica
l
an
al
y
s
i
s
o
f
lo
ca
l
ch
an
g
es
a
n
d
w
i
n
d
n
o
is
e,
th
e
au
th
o
r
h
av
e
co
n
s
tr
u
cted
e
v
en
t
d
etec
ti
o
n
f
r
a
m
e
w
o
r
k
w
h
ich
u
ti
lizes
o
p
tim
izatio
n
alg
o
r
it
h
m
to
r
ed
u
ce
t
h
e
co
m
p
l
e
x
it
y
o
cc
u
r
s
in
e
v
e
n
t
d
etec
ti
n
g
.
I
n
[
2
2
]
,
th
e
au
t
h
o
r
h
as
u
s
ed
co
m
b
in
ed
ap
p
r
o
ac
h
o
f
s
w
a
r
m
in
telli
g
en
ce
a
n
d
h
is
to
g
r
a
m
o
f
o
r
ien
ted
g
r
ad
ien
ts
f
o
r
e
v
en
t
d
etec
t
in
g
i
n
t
h
e
cr
o
w
d
ed
s
u
r
r
o
u
n
d
in
g
s
.
T
h
e
w
o
r
k
ca
r
r
ied
o
u
t
b
y
C
h
e
n
g
et
al.
[
2
3
]
,
h
av
e
d
ev
elo
p
ed
a
v
is
u
al
an
al
y
tic
s
s
u
p
p
o
r
tiv
e
an
al
y
tics
f
o
r
ev
en
t
d
etec
tio
n
in
s
u
r
v
eil
lan
c
e
s
y
s
te
m
s
.
Si
m
ilar
l
y
t
h
e
A
b
d
u
ll
ah
et
al.
[
2
4
]
h
av
e
u
s
ed
clo
u
d
tech
n
o
lo
g
y
an
d
GP
U
clu
s
ter
f
o
r
d
etec
tin
g
tr
a
f
f
ic
p
atter
n
f
r
o
m
th
e
r
ec
o
r
d
ed
v
id
eo
s
tr
ea
m
s
.
Me
g
h
d
ad
i
et
al.
[
2
5
]
h
av
e
d
esig
n
ed
a
v
id
e
o
an
al
y
t
ics
f
r
a
m
e
w
o
r
k
f
o
r
de
tectin
g
ev
e
n
t
in
m
o
v
in
g
v
i
d
eo
s
.
T
h
e
o
n
l
y
li
m
ita
tio
n
o
f
th
e
p
r
ese
n
ted
ap
p
r
o
ac
h
is
t
h
a
t
it
is
i
n
ef
f
icie
n
t
to
d
etec
t e
v
en
t
s
in
cr
o
w
d
ed
ac
ti
v
it
y
.
Sen
s
t
et
a
l.
[
2
6
]
h
av
e
d
ev
elo
p
ed
ar
ch
itectu
r
e
f
o
r
p
r
o
v
id
in
g
s
ec
u
r
it
y
a
n
d
p
r
iv
ac
y
to
s
u
p
p
o
r
t
v
id
eo
o
p
er
ato
r
s
w
h
ic
h
w
o
r
k
s
i
n
s
u
r
v
eilla
n
ce
s
y
s
te
m
.
T
h
e
ad
v
an
t
ag
e
o
f
p
r
o
p
o
s
ed
s
y
s
te
m
is
t
h
at
it
u
s
e
s
au
to
m
ated
ca
lib
r
ated
ca
m
er
as
it
d
is
p
la
y
d
etec
ted
ev
en
ts
a
n
d
o
b
j
ec
t
ex
tr
ac
tio
n
in
3
D
v
ie
w
.
T
h
e
w
o
r
k
o
f
T
ah
ir
et
al.
[
2
7
]
h
av
e
u
s
ed
g
en
er
al
p
u
r
p
o
s
e
g
r
ap
h
ical
p
r
o
ce
s
s
in
g
u
n
it
i
m
p
le
m
en
ted
w
it
h
C
UD
A
m
o
d
el
f
o
r
v
id
eo
an
aly
tics
f
o
r
in
tr
u
s
io
n
d
etec
tio
n
.
Si
m
ilar
l
y
,
th
e
w
o
r
k
o
f
C
o
n
te
et
al.
[
2
8
]
h
av
e
p
r
ese
n
ted
au
d
io
an
a
l
y
t
ics
f
r
a
m
e
w
o
r
k
f
o
r
an
o
m
al
y
d
etec
tio
n
i
n
a
u
d
io
d
ata
an
d
M
u
eller
et
al.
[
2
9
]
h
a
v
e
p
r
esen
ted
v
i
d
eo
an
al
y
tic
f
r
a
m
e
w
o
r
k
f
o
r
a
n
o
m
al
y
d
etec
tio
n
i
n
u
n
s
tr
u
ct
u
r
ed
v
id
e
o
s
tr
ea
m
s
.
I
n
[
3
0
]
Ki
m
et
al.
h
av
e
d
esi
g
n
ed
a
n
al
y
tics
m
o
d
e
l
f
o
r
tr
ac
k
in
g
a
n
d
d
etec
tin
g
m
u
lti
-
o
b
j
ec
t
f
r
o
m
t
h
e
v
id
eo
s
tr
ea
m
s
.
T
h
e
p
r
esen
ted
m
o
d
el
is
i
m
p
le
m
e
n
ted
w
i
th
FP
G
A
p
lat
f
o
r
m
w
h
ic
h
ac
h
ie
v
e
s
co
s
t e
f
f
ec
ti
v
e
p
er
f
o
r
m
a
n
ce
s
f
o
r
r
ea
l
-
ti
m
e
m
o
n
ito
r
in
g
i
n
r
e
m
o
te
ce
n
ter
s
.
Gu
ler
et
al.
[
3
1
]
p
r
esen
ted
a
n
an
al
y
tics
m
o
d
el
i
n
w
h
ich
th
e
y
h
a
v
e
u
s
ed
g
r
ap
h
ical
p
r
o
ce
s
s
i
n
g
u
n
it
f
o
r
v
id
eo
d
ata
an
al
y
tics
i
n
r
ea
l
-
t
i
m
e
s
u
r
v
eilla
n
ce
s
y
s
te
m
.
I
n
C
an
d
a
m
o
et
al.
[
3
2
]
h
av
e
ca
r
r
ied
a
s
u
r
v
e
y
tas
k
o
n
h
u
m
a
n
p
o
s
e
r
ec
o
g
n
itio
n
tech
n
iq
u
es
a
n
d
th
e
y
f
o
u
n
d
th
at
th
er
e
is
a
m
o
r
e
n
ee
d
o
f
i
m
p
r
o
v
e
m
en
t
i
n
r
ec
o
g
n
itio
n
an
d
an
al
y
tics
alg
o
r
it
h
m
.
P
ar
s
o
la
et
al.
[
3
3
]
h
av
e
p
r
esen
ted
a
n
e
w
m
et
h
o
d
f
o
r
ex
ec
u
ti
n
g
p
o
s
t
ev
en
t
s
t
u
d
y
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
S
imp
lifi
ed
vid
eo
s
u
r
ve
illa
n
ce
f
r
a
mewo
r
k
fo
r
d
yn
a
mic
…
(
Ma
d
h
u
C
h
a
n
d
r
a
G
)
2717
s
to
r
ed
s
u
r
v
eilla
n
ce
v
id
eo
d
ata.
T
h
e
m
ai
n
ai
m
o
f
t
h
is
al
g
o
r
ith
m
is
g
ath
er
s
v
id
eo
d
ata
in
t
o
th
e
HDFS
w
h
ic
h
ca
p
ab
ly
r
ec
o
g
n
izes
t
h
e
ar
ea
o
f
d
ata
f
r
o
m
HD
FS
b
asis
o
n
t
h
e
ti
m
e
o
f
a
m
o
u
n
t
o
f
ev
e
n
t
an
d
ac
co
m
p
li
s
h
f
u
r
th
er
ex
ec
u
t
io
n
.
Fak
h
ar
et
al.
[
3
4
]
h
av
e
ill
u
s
tr
ated
a
c
h
ea
p
er
s
u
b
s
t
it
u
te
o
f
a
tr
an
s
p
o
r
tab
le
co
m
m
u
n
it
y
v
id
eo
s
u
r
v
eilla
n
ce
tech
n
iq
u
e
w
h
ic
h
ex
ec
u
te
s
o
n
R
a
s
p
b
er
r
y
P
i 3
u
s
in
g
Op
en
-
C
V.
T
h
e
n
ex
t
s
ec
tio
n
d
is
c
u
s
s
es
ab
o
u
t
th
e
r
esear
ch
p
r
o
b
lem
s
th
a
t
h
as
ev
o
l
v
ed
af
ter
r
ea
d
in
g
th
e
ex
is
ti
n
g
ap
p
r
o
ac
h
es f
o
llo
w
ed
b
y
b
r
ief
d
is
cu
s
s
io
n
o
f
p
r
o
p
o
s
ed
s
o
lu
tio
n
to
ad
d
r
ess
s
u
c
h
p
r
o
b
lem
s
.
T
h
e
s
ig
n
i
f
ica
n
t r
esear
c
h
p
r
o
b
l
e
m
s
ar
e
as
f
o
llo
w
s
:
a.
E
x
is
ti
n
g
s
t
u
d
ies
to
w
ar
d
s
v
id
eo
an
al
y
tics
ar
e
f
o
u
n
d
to
less
e
m
p
h
a
s
ize
o
n
r
ea
l
-
ti
m
e
co
n
s
t
r
ain
ts
s
u
r
f
ac
ed
n
atu
r
al
l
y
o
n
v
id
eo
s
u
r
v
eilla
n
c
e
s
y
s
te
m
.
b.
L
o
w
ill
u
m
i
n
atio
n
co
n
d
itio
n
as
w
ell
as
v
ar
iab
le
ill
u
m
i
n
atio
n
co
n
d
itio
n
h
a
s
n
o
t
b
ee
n
f
o
u
n
d
to
b
e
a
d
d
r
ess
ed
in
ex
i
s
ti
n
g
r
esear
ch
w
o
r
k
i
n
v
i
d
eo
an
al
y
tics
.
c.
D
y
n
a
m
ic
an
d
r
a
n
d
o
m
m
o
b
ilit
y
o
f
a
s
u
b
j
ec
t a
l
w
a
y
s
p
o
s
es
a
p
r
o
b
lem
o
f
eit
h
er
p
ar
tial o
cc
lu
s
io
n
o
r
co
m
p
let
e
o
cc
lu
s
io
n
t
h
at
ar
e
f
o
u
n
d
n
o
t to
b
e
ad
d
r
ess
ed
in
ex
i
s
ti
n
g
s
y
s
te
m
.
d.
Utilizatio
n
o
f
s
i
m
p
le
an
d
co
m
p
u
tatio
n
all
y
e
f
f
icien
t
ap
p
r
o
ac
h
is
n
o
t
f
o
u
n
d
m
u
c
h
to
b
e
em
p
h
asized
in
a
n
y
o
f
th
e
e
x
is
ti
n
g
r
esear
ch
o
n
v
id
eo
an
al
y
tic
s
.
T
h
er
ef
o
r
e,
th
e
p
r
o
b
lem
s
tate
m
en
t
o
f
th
e
p
r
o
p
o
s
ed
s
tu
d
y
ca
n
b
e
s
tated
as
“
De
v
elo
p
in
g
a
s
i
m
p
le
v
id
eo
an
al
y
tical
f
r
a
m
e
w
o
r
k
t
h
at
is
ca
p
ab
le
o
f
ex
tr
ac
tin
g
p
r
ec
i
s
e
in
f
o
r
m
atio
n
o
f
t
h
e
d
y
n
a
m
ic
s
u
b
j
ec
t
u
n
d
er
ch
alle
n
g
i
n
g
en
v
ir
o
n
m
e
n
t”.
T
h
e
n
ex
t
s
ec
tio
n
o
u
tli
n
es t
h
e
s
o
l
u
tio
n
o
f
th
i
s
p
r
o
b
lem
.
T
h
e
p
r
im
e
p
u
r
p
o
s
e
o
f
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
is
to
d
e
v
elo
p
a
s
i
m
p
le
a
n
d
y
et
n
o
v
el
f
r
a
m
e
w
o
r
k
o
f
v
id
eo
s
u
r
v
eilla
n
ce
s
y
s
te
m
th
at
i
s
ca
p
ab
le
o
f
p
er
f
o
r
m
in
g
id
en
t
if
i
ca
tio
n
o
f
d
y
n
a
m
ic
s
u
b
j
ec
ts
in
r
an
d
o
m
m
o
tio
n
.
T
h
e
co
r
e
id
ea
o
f
p
r
o
p
o
s
ed
im
p
le
m
en
ta
tio
n
i
s
to
o
f
f
er
a
f
a
s
t
er
r
esp
o
n
s
e
ti
m
e
w
i
th
r
esp
ec
t
to
m
o
v
e
m
e
n
t
o
f
t
h
e
s
u
b
j
ec
t
an
d
h
e
n
ce
tar
g
et
s
f
o
r
s
i
m
p
le
co
m
p
u
tatio
n
a
l
ap
p
r
o
ac
h
.
T
h
e
s
tu
d
y
i
s
ca
r
r
ied
o
u
t
u
s
i
n
g
a
n
al
y
tical
r
esear
ch
m
et
h
o
d
o
lo
g
y
a
n
d
its
s
ch
e
m
e
is
p
icto
r
iall
y
p
r
esen
te
d
in
Fig
u
r
e.
1
Fig
u
r
e
1
.
A
d
o
p
ted
s
ch
e
m
a
o
f
p
r
o
p
o
s
ed
m
et
h
o
d
o
lo
g
y
Fas
ter
r
esp
o
n
s
e
ti
m
e
i
n
o
f
f
er
in
g
t
h
e
id
en
tific
atio
n
o
f
t
h
e
d
y
n
a
m
ic
m
o
b
ili
t
y
o
f
t
h
e
s
u
b
j
ec
t
is
o
n
l
y
p
o
s
s
ib
le
if
t
h
e
i
m
p
le
m
en
ta
tio
n
ad
o
p
ts
ce
r
tai
n
s
c
h
e
m
e
w
h
er
e
p
o
ten
tial
i
n
f
o
r
m
atio
n
ab
o
u
t
th
e
d
y
n
a
m
ic
f
r
a
m
es
o
f
th
e
v
id
eo
is
co
n
s
id
er
ed
.
I
n
o
r
d
er
to
f
ac
ilit
ate
s
u
c
h
f
o
r
m
o
f
i
m
p
le
m
e
n
tat
io
n
,
t
h
e
p
r
o
p
o
s
e
d
s
y
s
te
m
i
n
tr
o
d
u
ce
s
an
al
g
o
r
ith
m
f
o
r
r
ea
d
i
n
g
t
h
e
in
p
u
t
v
id
eo
f
ee
d
u
n
li
k
e
an
y
co
n
v
e
n
tio
n
al
s
y
s
te
m
.
I
t
tak
e
s
t
h
e
i
n
p
u
t
o
f
b
o
th
co
lo
r
ed
v
id
eo
f
ee
d
as
w
ell
as
a
d
ep
th
v
id
eo
f
ee
d
(
t
h
at
i
s
p
r
io
r
y
ex
tr
ac
ted
f
r
o
m
t
h
e
co
lo
r
ed
v
id
eo
f
ee
d
)
in
o
r
d
er
to
o
f
f
er
a
n
e
x
tr
ac
ted
v
id
eo
f
e
ed
as
an
o
u
tp
u
t.
T
h
i
s
o
u
tp
u
t
i
s
n
o
w
f
ed
to
t
h
e
s
ec
o
n
d
b
lo
ck
o
f
i
m
p
le
m
e
n
tat
io
n
i.e
.
alg
o
r
ith
m
f
o
r
o
b
tain
in
g
d
ep
th
an
d
f
r
eq
u
en
c
y
i
n
f
o
r
m
atio
n
f
r
o
m
th
e
b
lo
b
i
m
a
g
e.
C
o
n
v
e
r
tio
n
o
f
t
h
e
co
lo
r
ed
to
b
in
ar
ized
f
r
a
m
es
s
i
g
n
i
f
ica
n
t
a
s
s
i
s
ts
in
o
f
f
er
i
n
g
p
o
ten
ti
al
in
f
o
r
m
at
io
n
o
f
a
n
y
s
p
ec
i
f
ic
p
atter
n
s
o
f
th
e
d
y
n
a
m
ic
s
u
b
j
ec
t.
Usag
e
o
f
m
o
tio
n
b
lo
b
p
r
in
cip
le
as
s
is
ts
in
ad
d
r
ess
in
g
t
h
e
p
r
o
b
lem
s
o
f
p
ar
tial
o
r
co
m
p
lete
o
cc
lu
s
io
n
o
f
th
e
s
u
b
j
ec
ts
d
u
r
i
n
g
t
h
e
r
an
d
o
m
m
o
v
e
m
e
n
t
as
t
h
e
b
in
ar
izati
o
n
h
as
o
f
f
er
ed
b
etter
d
if
f
er
e
n
tiatio
n
ca
p
ab
ilit
y
o
f
f
o
r
eg
r
o
u
n
d
an
d
s
tatic
o
r
m
o
v
i
n
g
b
ac
k
g
r
o
u
n
d
s
u
b
j
ec
t.
Fu
r
t
h
er
,
th
e
f
i
n
al
al
g
o
r
ith
m
f
o
r
d
y
n
a
m
ic
s
u
b
j
ec
t
id
en
ti
f
icatio
n
tak
e
s
t
h
e
in
p
u
t
o
f
id
en
tifie
d
m
o
tio
n
b
lo
b
an
d
d
ep
th
i
m
a
g
e
th
a
t
af
ter
p
r
o
ce
s
s
in
g
lead
s
to
g
en
er
atio
n
o
f
d
ep
th
in
f
o
r
m
at
i
o
n
,
f
r
eq
u
e
n
c
y
in
f
o
r
m
at
io
n
,
as
w
el
l
as
s
eg
m
e
n
ted
d
ep
th
.
A
l
l
th
ese
in
f
o
r
m
a
tio
n
j
o
in
tl
y
as
s
is
t
s
i
n
e
x
p
lo
r
in
g
all
th
e
p
o
ten
tial
p
o
in
t
s
r
ep
r
esen
t
in
g
a
s
p
ec
i
f
ic
tar
g
et
v
er
y
m
u
c
h
d
is
cr
etel
y
a
n
d
is
f
o
u
n
d
h
i
g
h
l
y
s
u
itab
le
ev
e
n
in
lo
w
il
lu
m
i
n
atio
n
co
n
d
itio
n
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
a
ls
o
o
f
f
er
s
h
i
g
h
l
y
r
ed
u
ce
s
n
o
n
-
iter
ati
v
e
alg
o
r
ith
m
p
r
o
ce
s
s
in
g
s
tep
s
th
a
t
r
esu
lt
s
in
f
a
s
ter
p
r
o
ce
s
s
in
g
ti
m
e
i
n
s
y
n
c
h
r
o
n
o
u
s
w
it
h
t
h
e
h
i
g
h
er
p
r
ec
is
io
n
o
f
id
en
t
if
ica
tio
n
.
T
h
e
n
ex
t
s
ec
tio
n
d
is
c
u
s
s
es
ab
o
u
t
th
e
ap
p
r
o
ac
h
es
u
s
ed
f
o
r
al
g
o
r
ith
m
i
m
p
le
m
en
ta
tio
n
f
o
llo
w
ed
b
y
o
u
tco
m
e
a
n
al
y
s
i
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
4
,
A
u
g
u
s
t
201
9
:
2
7
1
5
-
2724
2718
2.
AL
G
O
RO
T
H
M
I
M
P
L
E
M
E
NT
A
T
I
O
N
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
is
m
ea
n
t
f
o
r
d
esig
n
i
n
g
a
s
i
m
p
le
a
n
d
ef
f
ec
ti
v
e
s
ch
e
m
e
o
f
d
y
n
a
m
ic
s
u
b
j
ec
t
id
en
ti
f
icatio
n
f
o
r
as
s
is
ti
n
g
i
n
v
id
eo
an
al
y
tics
.
T
h
e
d
esi
g
n
is
ca
r
r
ied
o
u
t
in
s
u
c
h
a
w
a
y
t
h
a
t
h
i
g
h
er
p
r
ec
is
io
n
is
r
etain
ed
d
u
r
i
n
g
th
e
co
m
p
lete
p
r
o
ce
s
s
o
f
co
u
n
tin
g
th
e
n
u
m
b
er
o
f
s
u
b
j
ec
ts
m
o
v
in
g
d
y
n
a
m
icall
y
i
n
lo
w
illu
m
i
n
atio
n
ar
ea
.
T
h
e
alg
o
r
it
h
m
is
s
p
ec
i
f
icall
y
d
esi
g
n
to
ass
is
ts
i
n
o
f
f
er
i
n
g
ac
c
u
r
ate
in
f
o
r
m
atio
n
o
f
e
v
er
y
v
id
eo
an
al
y
t
ical
p
r
o
ce
s
s
.
T
h
is
s
ec
tio
n
d
is
cu
s
s
e
s
ab
o
u
t
d
if
f
e
r
en
t
s
et
o
f
s
eq
u
e
n
tial
al
g
o
r
ith
m
s
t
h
at
en
s
u
r
e
th
e
p
er
f
ec
t o
p
er
atio
n
o
f
ex
tr
ac
tin
g
in
f
o
r
m
atio
n
o
f
n
u
m
b
er
o
f
s
u
b
j
ec
ts
f
o
r
a
g
iv
e
n
d
y
n
a
m
ic
v
id
e
o
f
ee
d
.
2
.
1
.
Alg
o
rit
h
m
f
o
r
re
a
din
g
t
he
inp
ut
v
ideo
f
ee
d
T
h
is
alg
o
r
it
h
m
i
s
r
esp
o
n
s
ib
le
f
o
r
tak
in
g
th
e
i
n
p
u
t
o
f
th
e
v
id
eo
in
o
r
d
er
to
f
u
r
th
er
f
ac
il
itat
e
in
v
id
eo
p
r
o
ce
s
s
in
g
.
U
n
li
k
e
t
h
e
co
n
v
e
n
tio
n
al
v
id
eo
p
r
o
ce
s
s
in
g
s
tep
s
,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
co
n
s
id
er
s
d
ep
th
in
f
o
r
m
atio
n
o
f
th
e
r
elate
d
in
p
u
t
v
id
eo
f
o
r
en
h
a
n
ci
n
g
t
h
e
p
r
ec
is
io
n
o
f
s
u
b
j
ec
t
i
d
en
tif
icat
io
n
in
m
u
c
h
b
etter
w
a
y
.
A
clo
s
er
lo
o
k
in
to
th
e
a
u
to
-
f
o
c
u
s
ca
p
ab
ilit
y
o
f
a
n
y
d
i
g
ital
ca
m
er
a
w
il
l
ex
p
lai
n
th
e
e
f
f
ec
ti
v
e
u
tili
za
tio
n
o
f
d
ep
th
in
f
o
r
m
atio
n
f
o
r
a
g
iv
e
n
s
ce
n
e.
B
asicall
y
,
d
ep
th
i
n
f
o
r
m
atio
n
o
f
an
i
m
ag
e
o
f
f
e
r
s
in
f
o
r
m
a
tio
n
o
f
th
e
z
-
in
f
o
r
m
at
io
n
o
f
t
h
e
tar
g
e
t
ed
s
u
b
j
ec
t
co
r
r
esp
o
n
d
in
g
to
t
h
e
r
ea
l
w
o
r
ld
th
at
s
i
g
n
i
f
ican
tl
y
in
cr
ea
s
es
ac
c
u
r
ac
y
o
f
co
u
n
ti
n
g
th
e
s
u
b
j
ec
ts
esp
ec
iall
y
i
n
ca
s
e
o
f
p
ar
tial
o
r
f
u
ll
o
cc
lu
s
io
n
.
T
h
e
d
is
tan
ce
o
f
a
s
u
b
j
ec
t
ca
n
b
e
r
ep
r
esen
ted
b
y
t
h
e
i
m
ag
e
in
t
en
s
it
y
f
r
o
m
a
s
p
ec
if
ic
v
ie
w
p
o
in
t.
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
m
a
k
es
u
s
e
o
f
t
h
i
s
co
n
ce
p
t in
o
r
d
er
to
b
o
o
s
t u
p
th
e
ac
cu
r
ac
y
i
n
id
en
ti
f
icatio
n
.
T
h
e
alg
o
r
it
h
m
ic
s
tep
s
ar
e
as s
h
o
w
n
as b
elo
w
.
Alg
o
rit
h
m
f
o
r
re
a
din
g
t
he
in
pu
t
v
ideo
f
ee
d
I
np
ut
:
f
o
,
f
d
,
s
f
,
e
f
O
utput
:
d
1
/d
2
Sta
rt
1
.
in
it
f
o
,
f
d
,
s
f
,
e
f
2
.
F
o
r
i=
s
f
:
e
f
3
.
d
1
→r
ea
d
(
f
c
)
i
4
.
d
2
→r
ea
d
(
f
d
)
i
5
.
E
nd
E
nd
T
h
e
ab
o
v
e
alg
o
r
ith
m
s
h
o
w
s
t
h
at
it
tak
e
s
t
h
e
i
n
p
u
t
o
f
f
o
(
f
r
a
m
e
o
f
v
id
eo
)
an
d
f
d
(
f
r
a
m
e
o
f
d
ep
t
h
v
id
eo
)
th
at
a
f
ter
p
r
o
ce
s
s
i
n
g
y
ield
s
an
d
o
u
tp
u
t
o
f
d
1
/d
2
(
ex
tr
ac
ted
v
id
eo
f
ee
d
s
f
o
r
s
t
u
d
y
)
.
A
p
ar
t
f
r
o
m
t
h
i
s
in
p
u
t,
t
h
e
alg
o
r
it
h
m
p
er
f
o
r
m
s
co
m
p
lete
a
n
al
y
s
i
s
o
n
t
h
e
b
asis
o
f
th
e
f
r
a
m
e
le
n
g
t
h
s
p
ec
i
f
ied
to
it
in
th
e
f
o
r
m
o
f
s
tar
t
f
r
a
m
e
s
f
an
d
en
d
f
r
a
m
e
ef
(
L
i
n
e
-
1
)
.
On
l
y
f
o
r
th
e
s
elec
t
ed
f
r
a
m
es
(
L
i
n
e
-
2
)
,
th
e
alg
o
r
it
h
m
co
n
s
tr
u
c
ts
t
w
o
m
atr
i
x
d
1
an
d
d
2
th
at
is
u
s
ed
f
o
r
r
e
-
p
o
s
iti
n
g
f
r
a
m
e
in
f
o
r
m
a
t
io
n
co
r
r
esp
o
n
d
in
g
to
o
r
ig
i
n
al
f
r
a
m
e
f
o
an
d
d
ep
th
f
r
a
m
e
f
d
.
B
o
th
th
ese
m
atr
i
x
w
i
ll b
e
s
u
b
j
ec
ted
f
o
r
f
u
r
th
er
p
r
o
ce
s
s
i
n
g
h
e
n
ce
f
o
r
w
ar
d
.
2
.
2
.
Alg
o
rit
h
m
f
o
r
identif
y
ing
m
o
t
io
n blo
b
T
h
e
u
s
ag
e
o
f
B
in
ar
y
L
ar
g
e
O
b
j
ec
t
o
r
B
L
OB
h
as
alr
ea
d
y
b
ee
n
p
r
o
v
en
to
o
f
f
er
b
etter
f
o
r
m
o
f
d
is
cr
ete
in
f
o
r
m
atio
n
ab
o
u
t
th
e
s
tr
u
ct
u
r
e
o
f
a
g
iv
e
n
i
m
a
g
e.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
u
tili
ze
s
th
e
b
lo
b
in
o
r
d
er
to
an
al
y
ze
all
th
e
s
et
o
f
co
n
s
id
er
ed
f
r
a
m
es
(
f
r
o
m
s
f
to
s
e)
.
I
t
also
as
s
i
s
ts
i
n
i
s
o
lati
n
g
th
e
o
b
j
ec
ts
f
r
o
m
t
h
e
g
i
v
en
b
i
n
ar
y
i
m
a
g
e
th
at
ass
is
t
s
in
in
cr
ea
s
in
g
ac
cu
r
ac
y
o
f
id
en
ti
f
ica
tio
n
o
f
tar
g
et
s
u
b
j
ec
t
f
o
r
a
g
iv
en
s
ce
n
e.
T
h
e
p
r
o
ce
s
s
o
f
ex
tr
ac
tio
n
o
f
b
lo
b
f
r
o
m
t
h
e
g
i
v
en
v
id
eo
f
ee
d
is
s
h
o
w
n
i
n
al
g
o
r
ith
m
ic
s
tep
s
b
elo
w
:
Alg
o
rit
h
m
f
o
r
I
de
ntif
y
ing
M
o
t
io
n B
lo
b
I
np
ut
: d
1
/d
2
O
utput
: b
in
Img
Sta
rt
1
.
ac
ce
p
t d
1
/d
2
2
.
[
I
c
I
d
]
→r
ea
d
(
d
1
d
2
)
3
.
I
d
→
ϕ
(I
d
)
4
.
If
I
d
>D
m
in
&
&
I
d
<D
m
ax
5
.
f
lag
b
in
Img
6
.
b
in
Img
→θ
1
(
b
in
Img
)
7
.
b
in
Img
→
θ
2
(
b
in
Img
)
8
.
E
nd
9
.
Flag
b
in
Img
E
nd
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
S
imp
lifi
ed
vid
eo
s
u
r
ve
illa
n
ce
f
r
a
mewo
r
k
fo
r
d
yn
a
mic
…
(
Ma
d
h
u
C
h
a
n
d
r
a
G
)
2719
T
h
e
o
u
tp
u
t
o
f
th
e
p
r
io
r
alg
o
r
ith
m
is
b
a
s
icall
y
co
n
s
id
er
ed
as
an
i
n
p
u
t
f
o
r
t
h
is
al
g
o
r
it
h
m
i.e
.
d
1
an
d
d
2
(
L
in
e
-
1
)
.
T
h
e
alg
o
r
ith
m
ex
tr
a
cts
th
e
d
ig
itized
in
f
o
r
m
at
io
n
o
f
b
o
th
o
r
ig
in
al
f
r
a
m
e
(
d
1
)
as
w
ell
as
d
ep
th
f
r
a
m
e
(
d
2
)
in
o
r
d
er
to
o
b
tain
t
w
o
m
atr
ix
i.e
.
co
lo
r
o
f
an
i
m
a
g
e
I
c
an
d
d
ep
th
o
f
an
i
m
a
g
e
I
d
(
L
in
e
-
2
)
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
t
h
a
n
ap
p
lies
a
t
w
o
-
d
i
m
en
s
io
n
al
m
ed
ia
n
f
il
ter
ϕ
(
L
in
e
-
3
)
o
v
er
th
e
d
ep
th
o
f
an
i
m
a
g
e
I
d
.
T
h
is
o
p
e
r
atio
n
lead
s
to
th
e
f
u
r
t
h
er
p
r
o
ce
s
s
ed
in
f
o
r
m
a
tio
n
o
f
th
e
d
ep
th
i
m
ag
e
i.e
.
I
d
w
h
er
e
ea
ch
p
ix
e
ls
r
e
tain
s
th
e
m
ed
ia
n
v
alu
e
in
th
e
f
o
r
m
o
f
3
x
3
m
atr
ix
ar
o
u
n
d
th
e
co
r
r
esp
o
n
d
in
g
p
ix
el
i
n
t
h
e
i
n
p
u
t
i
m
a
g
e.
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
also
u
s
e
s
a
m
i
n
i
m
u
m
a
n
d
m
a
x
i
m
u
m
d
ep
th
v
al
u
e
D
m
i
n
a
n
d
D
m
a
x
to
en
s
u
r
e
th
at
th
e
co
n
s
id
er
ed
im
a
g
e
d
ep
t
h
m
atr
i
x
s
h
o
u
ld
r
etai
n
o
n
l
y
t
h
e
p
ix
el
i
n
f
o
r
m
atio
n
w
i
th
th
e
s
co
p
e
o
f
[
D
m
i
n
D
m
a
x
]
(
L
i
n
e
-
4
)
.
T
h
e
n
e
w
ele
m
e
n
t
s
o
f
th
e
m
atr
ix
s
atis
f
y
i
n
g
t
h
e
c
o
n
d
itio
n
in
L
i
n
e
-
4
is
r
etain
e
d
in
a
te
m
p
o
r
ar
y
m
atr
i
x
(
L
i
n
e
-
5
)
th
at
is
f
u
r
th
er
s
u
b
j
ec
ted
to
b
in
ar
y
m
o
r
p
h
o
l
o
g
ical
o
p
er
atio
n
t
h
at
i
n
it
iate
s
w
it
h
er
o
s
io
n
a
n
d
en
d
s
at
d
ilatio
n
o
p
er
atio
n
.
T
h
e
f
u
n
ctio
n
θ1
r
ep
r
esen
t
s
s
u
c
h
m
o
r
p
h
o
lo
g
ical
f
u
n
ctio
n
.
T
h
e
o
b
tai
n
ed
m
o
r
p
h
ed
b
in
ar
y
i
m
a
g
e
b
in
I
m
g
(
L
in
e
-
7
)
is
n
o
w
s
u
b
j
ec
ted
to
f
i
n
e
-
t
u
n
i
n
g
p
r
o
ce
s
s
w
h
er
e
t
h
e
s
m
al
ler
ele
m
e
n
t
s
in
t
h
e
m
atr
ix
ar
e
eli
m
in
a
ted
.
T
h
is
s
tep
o
f
f
er
s
t
h
e
f
in
a
l
l
y
id
en
ti
f
ied
m
o
tio
n
b
lo
b
o
f
th
e
g
i
v
en
v
id
eo
f
ee
d
(
L
in
e
-
9
)
in
th
e
f
o
r
m
o
f
a
b
in
ar
y
i
m
a
g
e
b
in
I
m
g
as a
n
o
u
tp
u
t.
2
.
3
Alg
o
rit
hm
f
o
r
o
bta
ini
ng
depth
a
nd
f
re
qu
e
ncy
info
r
m
a
t
io
n f
ro
m
t
he
b
lo
b i
m
a
g
e
Af
ter
t
h
e
m
o
t
io
n
b
lo
b
in
f
o
r
m
atio
n
is
o
b
tai
n
ed
,
th
e
al
g
o
r
ith
m
is
n
o
w
r
ea
d
y
to
p
er
f
o
r
m
d
is
cr
etiza
tio
n
o
f
th
e
d
o
m
i
n
an
t
p
i
x
el
g
r
o
u
p
.
Ho
w
e
v
er
,
th
er
e
is
a
s
li
g
h
t
c
h
a
llen
g
e
in
d
o
in
g
s
o
as
th
e
m
o
t
i
o
n
b
lo
b
in
f
o
r
m
atio
n
o
b
tain
ed
d
o
n
o
t
co
n
tain
a
n
y
f
o
r
m
o
f
in
d
e
x
i
n
g
o
r
lab
eli
n
g
o
f
th
e
d
o
m
in
a
n
t
b
lo
ck
o
f
p
ix
els.
T
h
er
ef
o
r
e,
th
i
s
alg
o
r
ith
m
as
s
is
t
s
i
n
ex
tr
ac
ti
n
g
p
r
ec
is
e
in
f
o
r
m
a
tio
n
o
f
d
ep
th
u
s
i
n
g
lab
elin
g
co
n
ce
p
t
s
o
th
a
t
s
eg
m
en
tatio
n
ca
n
b
e
ca
r
r
ied
o
u
t in
p
r
ec
is
e
m
a
n
n
er
.
T
h
e
alg
o
r
ith
m
ic
s
tep
s
ar
e
as sh
o
w
n
b
elo
w
:
Alg
o
rit
h
m
f
o
r
o
bta
ini
ng
dep
t
h a
nd
f
re
qu
ency
info
r
m
a
t
io
n f
ro
m
t
he
blo
b i
m
a
g
e
I
np
ut
: b
i
n
Img
(
id
en
ti
f
ied
m
o
t
io
n
b
lo
b
)
O
utput
:
x
(
d
ep
th
)
,
y
(
f
r
eq
u
en
c
y
)
,
D
(
s
e
g
m
en
ted
d
ep
th
)
Sta
rt
1
.
[
L
c]
→
θ
3
(
b
in
Img
)
θ
3
is
b
w
lab
el
2
.
F
o
r
i=1
:c
3
.
If
L
=
=i
4
.
o
b
tain
O
5
.
b
=d
o
u
b
le
(
I
d
(
O)
)
6
.
[
x
y
]
→
h
(
b
,
ar
g
m
in
(
b
)
:ar
g
m
ax
(
b
)
)
7
.
E
nd
8
.
D→I
d
(
b
in
Img
)
E
nd
T
h
e
alg
o
r
ith
m
ta
k
es
t
h
e
i
n
p
u
t
o
f
b
in
I
m
g
(
id
en
ti
f
ied
m
o
t
io
n
b
lo
b
)
o
b
tain
ed
f
r
o
m
p
r
e
v
io
u
s
al
g
o
r
ith
m
p
r
o
ce
s
s
in
g
o
u
tp
u
t
t
h
at
a
f
ter
p
r
o
ce
s
s
in
g
y
ield
s
x
(
d
ep
th
i
n
f
o
r
m
atio
n
)
,
y
(
f
r
eq
u
e
n
c
y
in
f
o
r
m
atio
n
)
,
an
d
D
(
s
eg
m
en
ted
d
ep
th
)
.
T
h
e
f
ir
s
t
s
tep
o
f
th
is
al
g
o
r
ith
m
is
to
c
o
n
s
tr
u
ct
a
m
atr
ix
L
i
n
s
u
c
h
a
w
a
y
t
h
at
it
s
h
o
u
ld
co
r
r
esp
o
n
d
to
th
e
s
ize
o
f
th
e
b
in
ar
y
m
o
tio
n
b
lo
b
b
in
I
m
g
.
T
h
e
m
atr
ix
L
co
n
s
i
s
ts
o
f
i
n
d
ex
o
r
lab
els
f
o
r
all
t
h
e
co
m
p
o
n
e
n
t
s
th
at
ar
e
co
n
n
ec
t
ed
alto
g
eth
er
in
th
e
b
i
n
ar
y
m
o
tio
n
b
lo
b
o
f
v
id
eo
f
ee
d
(
L
i
n
e
-
1
)
.
A
n
ex
p
lic
it
f
u
n
ctio
n
θ3
is
ap
p
lied
w
it
h
a
n
i
n
p
u
t
ar
g
u
m
e
n
t
o
f
b
i
n
ar
y
m
o
tio
n
b
lo
b
b
in
I
m
g
(
L
i
n
e
-
1
)
in
o
r
d
er
to
y
ie
ld
a
m
atr
i
x
L
w
it
h
n
u
m
b
er
o
f
ele
m
en
ts
a
s
c.
Fo
r
all
th
e
e
le
m
e
n
ts
c
(
L
i
n
e
-
2
)
,
th
e
al
g
o
r
ith
m
co
n
s
tr
u
ct
s
a
f
u
n
ctio
n
(
L
in
e
-
3)
t
h
at
e
n
s
u
r
es
e
x
tr
ac
ti
o
n
o
f
o
n
l
y
th
o
s
e
o
b
j
ec
ts
L
w
h
ic
h
is
d
i
m
e
n
s
i
o
n
all
y
s
a
m
e
as
1
to
c
(
L
in
e
-
4
)
.
T
h
e
r
ev
is
ed
v
er
s
io
n
o
f
a
d
ep
t
h
i
m
a
g
e
I
d
is
n
o
w
f
o
r
m
ed
w
h
er
e
th
e
ele
m
en
t
s
o
f
th
e
m
atr
i
x
is
n
o
w
ch
a
n
g
ed
to
o
b
tain
ed
v
alu
e
s
o
f
o
b
j
ec
t
O
f
o
llo
w
ed
b
y
f
i
n
e
-
tu
n
i
n
g
w
i
t
h
d
o
u
b
le
p
r
ec
is
io
n
(
L
in
e
-
5
)
.
T
h
e
n
e
x
t
p
ar
t
o
f
th
e
alg
o
r
ith
m
i
m
p
le
m
e
n
ts
a
f
u
n
ctio
n
h
(
x
)
to
ap
p
l
y
i
m
a
g
e
h
is
to
g
r
a
m
co
n
s
id
er
in
g
t
w
o
i
n
p
u
t
ar
g
u
m
en
t
s
i.e
.
o
b
tain
ed
v
alu
e
o
f
b
f
r
o
m
p
r
io
r
s
et
i.e
.
L
in
e
-
4
an
d
m
i
n
i
m
u
m
a
n
d
m
a
x
i
m
u
m
s
c
o
p
e
o
f
b
(
L
in
e
-
6
)
.
T
h
e
i
m
p
le
m
e
n
ta
t
io
n
f
i
n
all
y
r
e
s
u
lt
i
n
f
o
r
m
atio
n
o
f
d
ep
t
h
i
n
f
o
r
m
at
io
n
x
a
n
d
f
r
eq
u
en
c
y
i
n
f
o
r
m
at
io
n
y
i
n
o
r
d
er
to
f
u
r
t
h
er
r
ed
ef
in
e
th
e
m
o
tio
n
b
lo
b
im
ag
e
o
f
t
h
e
s
u
b
j
ec
ts
f
o
r
a
g
iv
en
v
id
eo
f
ee
d
.
T
h
e
f
u
r
th
er
s
tep
af
ter
it
is
tar
g
eted
f
o
r
s
eg
m
e
n
tatio
n
o
p
er
atio
n
.
Fo
r
s
eg
m
en
tat
io
n
,
th
e
alg
o
r
ith
m
s
u
b
s
tit
u
te
s
th
e
p
r
io
r
elem
e
n
t
s
o
f
th
e
d
ep
th
i
m
a
g
e
I
d
to
n
e
w
ele
m
en
ts
o
f
t
h
e
b
in
ar
y
m
o
t
io
n
b
lo
b
b
in
I
m
g
(
L
i
n
e
-
8
)
.
Fu
r
t
h
er
f
i
n
e
-
t
u
n
in
g
w
i
th
p
r
ec
is
io
n
(
u
n
s
i
g
n
ed
i
n
teg
er
o
f
8
b
its
)
w
ill
m
ak
e
t
h
e
s
e
g
m
e
n
te
d
d
ep
th
m
o
r
e
o
b
v
io
u
s
f
o
r
d
is
p
la
y
.
2
.
4
.
Alg
o
rit
h
m
f
o
r
dy
na
m
ic
s
ub
j
ec
t
identif
ica
t
io
n
T
h
is
is
t
h
e
f
in
a
l
al
g
o
r
ith
m
t
h
at
is
r
esp
o
n
s
ib
le
f
o
r
p
er
f
o
r
m
i
n
g
th
e
id
en
ti
f
icatio
n
o
f
th
e
s
u
b
j
ec
ts
in
r
an
d
o
m
a
n
d
d
y
n
a
m
ic
m
o
tio
n
.
T
h
e
m
ai
n
id
ea
o
f
th
i
s
al
g
o
r
i
th
m
i
s
to
p
er
f
o
r
m
a
p
r
ec
is
e
i
d
en
tific
atio
n
o
f
th
e
s
u
b
j
ec
ts
in
p
r
esen
ce
o
f
lo
w
ill
u
m
in
at
io
n
p
o
in
t
in
o
r
d
er
to
en
s
u
r
e
th
at
s
u
c
h
f
o
r
m
o
f
d
y
n
a
m
ic
in
f
o
r
m
atio
n
ca
n
b
e
ca
p
tu
r
ed
in
lo
w
li
g
h
t
ar
ea
s
.
B
asicall
y
,
th
e
co
n
te
x
t
o
f
lo
w
li
g
h
t
in
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
w
ill
m
ea
n
an
ar
ea
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
4
,
A
u
g
u
s
t
201
9
:
2
7
1
5
-
2724
2720
w
h
er
e
th
er
e
is
n
o
s
u
n
l
ig
h
t
an
d
n
u
m
b
er
s
o
f
s
o
u
r
ce
s
o
f
lig
h
te
n
i
n
g
ar
e
v
er
y
less
with
les
s
er
in
te
n
s
it
y
.
Hen
ce
,
m
aj
o
r
it
y
o
f
t
h
e
ex
i
s
ti
n
g
ap
p
licatio
n
w
ill
te
n
d
to
f
ail
ev
en
i
n
id
en
ti
f
y
i
n
g
t
h
e
s
u
b
j
ec
ts
an
d
th
e
tas
k
co
u
ld
b
e
m
o
r
e
ch
alle
n
g
i
n
g
i
f
t
h
e
s
u
b
j
ec
ts
ar
e
m
o
v
i
n
g
i
n
ar
b
itra
r
y
m
an
n
er
.
He
n
ce
,
th
i
s
al
g
o
r
ith
m
o
f
f
er
s
s
o
m
e
s
i
m
p
le
an
d
ea
s
ier
alter
n
ati
v
e
to
ca
r
r
y
o
u
t th
i
s
tas
k
.
T
h
e
s
tep
s
o
f
th
e
alg
o
r
ith
m
ar
e
as f
o
llo
w
s
:
Alg
o
rit
h
m
f
o
r
Dy
na
m
ic
Su
b
j
ec
t
I
dentif
ica
t
io
n
I
np
ut
: I
d
(
d
ep
th
i
m
ag
e)
,
O
utput
: P
er
s
o
n
id
en
ti
f
icatio
n
Sta
rt
1
.
co
l→ar
b
(
n
)
2
.
F
o
r
i=1
:n
3
.
c(
n
,
:)
→[
m
]
4
.
E
nd
5
.
[
L
c]
→
θ
3
(
b
in
Img
)
6
.
F
o
r
i=1
:c
7
.
If
L
=
=i
8
.
o
b
tain
O
9
.
s
=ρ(d
o
u
b
le
(
I
d
(
O)
)
)
1
0
.
If
s
≤
p
p
=1
5
in
L
-
246
1
1
.
b
b
→1
|
|
P
(
b
b
o
x
)
1
2
.
zs→[μ
(
x
ts
)
μ
(
y
t
s
)
μ
(
I
d
(
O)
)
]
1
3
.
E
ls
e
1
4
.
cp
→ψ(
b
in
Img
)
L
-
256
1
5
.
If
cp
≠
0
1
6
.
{
P
1
P
2
}→r
p
(
O1
O2
)
1
7
.
b
b
o
x
→(
b
b
o
x
1
b
b
o
x
2
)
1
8
.
E
ls
e
1
9
.
zs→[μ
(
x
ts
)
μ
(
y
ts
)
μ
(
I
d
(
lo
g
(
O)
)
)
]
2
0
.
F
o
r
i=
1
:ar
g
m
ax
(
b
w
o
p
)
2
1
.
m
a
s
k
→b
w
o
p
==
i
2
2
.
Flag
id
en
ti
f
ied
p
er
s
o
n
2
3
.
E
nd
2
4
.
E
nd
2
4
.
E
nd
En
d
T
h
e
alg
o
r
ith
m
co
n
s
tr
u
cts
a
r
an
d
o
m
m
atr
ix
co
l
(
L
i
n
e
-
1
)
b
ased
o
n
s
o
m
e
r
a
n
d
o
m
n
u
m
b
er
s
.
Fo
r
a
s
p
ec
if
ic
s
et
o
f
r
an
d
o
m
n
u
m
b
er
s
,
th
e
alg
o
r
it
h
m
co
n
s
tr
u
cts
d
i
f
f
er
en
t
f
o
r
m
s
o
f
co
lo
r
ed
m
atr
i
x
w
it
h
r
o
w
r
an
g
e
[
1
n
]
an
d
co
n
s
id
er
i
n
g
all
t
h
e
c
o
lu
m
n
s
to
g
en
er
ate
ar
r
a
y
o
f
m
n
u
m
b
er
o
f
u
n
iq
u
e
b
in
ar
y
el
e
m
e
n
ts
(
L
i
n
e
-
3
)
.
T
h
e
lab
elin
g
f
u
n
c
tio
n
θ3
i
s
ap
p
lied
o
n
b
in
ar
y
m
o
tio
n
b
lo
b
b
in
I
m
g
i
n
o
r
d
er
to
o
b
tain
L
an
d
c
(
L
i
n
e
-
5
)
.
Fo
r
all
th
e
v
al
u
es
o
f
co
u
n
t
c
o
f
n
e
w
m
atr
ix
L
(
L
i
n
e
-
6
)
,
th
e
alg
o
r
ith
m
ex
tr
ac
t
s
th
e
o
b
j
ec
t
i
n
f
o
r
m
atio
n
(
L
in
e
-
8
)
f
o
llo
w
ed
b
y
f
in
all
y
ap
p
l
y
i
n
g
s
tan
d
ar
d
d
ev
iatio
n
o
v
er
d
o
u
b
le
p
r
ec
is
io
n
o
f
b
in
I
m
a
g
e
(
L
i
n
e
-
9
)
.
I
f
th
e
s
ta
n
d
ar
d
d
ev
iatio
n
s
is
f
o
u
n
d
to
b
e
less
th
an
s
o
m
e
s
p
ec
i
f
ic
li
m
it
p
th
an
p
r
o
p
o
s
ed
s
y
s
te
m
ap
p
lies
r
e
g
io
n
p
r
o
p
er
ties
o
n
o
b
j
ec
t
O
u
s
in
g
b
o
u
n
d
i
n
g
b
o
x
b
b
o
x
a
n
d
s
to
r
e
t
h
e
r
es
u
lta
n
t
el
e
m
en
ts
in
m
atr
i
x
P
(
L
i
n
e
-
1
1
)
.
A
co
n
ca
te
n
atio
n
i
s
p
er
f
o
r
m
ed
b
et
w
ee
n
a
u
n
it
v
al
u
e
an
d
s
elec
ted
r
eg
io
n
P
in
o
r
d
er
to
g
en
er
ate
a
m
atr
i
x
b
b
(
L
i
n
e
-
1
1
)
.
Fi
n
all
y
a
m
atr
i
x
zs
is
co
n
s
tr
u
cted
t
h
at
ta
k
es
t
h
r
ee
d
if
f
er
en
t
ele
m
en
ts
i.
e.
m
ea
n
v
alu
e
μ
o
f
x
ts
,
y
t
x
,
an
d
I
d
,
w
h
er
e
x
ts
a
n
d
y
ts
ar
e
ex
tr
ac
ted
i
n
f
o
r
m
atio
n
o
f
o
b
j
ec
t O
(
L
in
e
-
1
2
)
.
Ho
w
e
v
er
,
if
t
h
e
v
al
u
e
o
f
s
i
s
f
o
u
n
d
m
o
r
e
th
an
th
e
s
p
ec
if
ic
v
alu
e
o
f
p
t
h
an
it
ap
p
lies
a
n
u
n
iq
u
e
f
u
n
c
tio
n
ψ
co
n
s
id
er
i
n
g
i
n
p
u
t
ar
g
u
m
e
n
ts
o
f
o
b
j
ec
t
O.
I
f
t
h
e
v
a
lu
e
o
f
cp
is
f
o
u
n
d
to
b
e
n
o
n
-
ze
r
o
(
L
i
n
e
-
1
5
)
th
an
O1
an
d
O2
in
f
o
r
m
a
tio
n
’
s
ar
e
o
b
tain
ed
.
A
ll
th
e
v
al
u
e
s
o
f
I
d
th
at
is
m
o
r
e
th
an
o
b
tain
ed
cp
is
tr
ea
ted
as
O1
o
r
else
its
O2
(
L
in
e
-
1
6
)
.
T
h
e
alg
o
r
it
h
m
ap
p
lies
r
eg
io
n
p
r
o
p
er
ties
r
p
to
b
o
th
O1
an
d
O2
in
o
r
d
e
r
to
o
b
tain
P
1
an
d
P2
an
d
th
er
eb
y
t
h
e
b
o
u
n
d
i
n
g
b
o
x
is
cr
ea
ted
(
L
i
n
e
-
1
7
)
.
T
h
e
alg
o
r
ith
m
f
i
n
all
y
co
n
s
tr
u
cts
an
d
u
p
d
ate
s
th
e
m
atr
i
x
zs
b
y
ap
p
l
y
i
n
g
lo
g
ical
o
p
er
atio
n
o
n
o
b
j
ec
t
a
s
an
ele
m
e
n
t
o
f
I
d
(
L
in
e
-
1
9
)
.
Fo
r
all
th
e
v
a
lu
e
s
o
f
m
a
x
i
m
u
m
v
al
u
e
o
f
in
d
e
x
o
f
a
n
o
b
j
ec
t
b
w
o
p
(
L
i
n
e
-
2
0
)
,
th
e
alg
o
r
it
h
m
co
n
s
tr
u
ct
s
a
m
a
s
k
o
n
l
y
f
o
r
th
e
ele
m
e
n
ts
o
f
b
w
o
p
m
atc
h
i
n
g
with
i (
L
in
e
-
2
0
)
.
T
h
er
ef
o
r
e,
th
e
i
m
p
licatio
n
o
f
th
i
s
al
g
o
r
ith
m
r
e
s
u
lts
in
a
p
r
ec
is
e
s
elec
tio
n
o
f
t
h
e
d
y
n
a
m
i
c
s
u
b
j
ec
t
s
w
it
h
h
i
g
h
er
d
eg
r
ee
o
f
ac
cu
r
ac
y
.
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
i
s
h
ig
h
l
y
p
r
o
g
r
es
s
i
v
e
i
n
it
s
o
p
er
atio
n
a
n
d
h
e
n
ce
t
h
er
e
ar
e
less
er
c
h
an
ce
s
o
f
s
tale
in
f
o
r
m
at
io
n
s
y
n
c
h
r
o
n
izatio
n
w
it
h
t
h
e
d
y
n
a
m
ic
m
o
b
ilit
y
o
f
th
e
s
u
b
j
ec
t.
T
h
e
n
ex
t
s
ec
tio
n
b
r
ief
s
o
f
t
h
e
o
b
tain
ed
r
esu
lt
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
S
imp
lifi
ed
vid
eo
s
u
r
ve
illa
n
ce
f
r
a
mewo
r
k
fo
r
d
yn
a
mic
…
(
Ma
d
h
u
C
h
a
n
d
r
a
G
)
2721
3.
RE
SU
L
T
S
ANA
L
YS
I
S
T
h
is
s
ec
tio
n
b
r
ief
s
ab
o
u
t
th
e
o
u
tco
m
es
o
b
tain
ed
f
r
o
m
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
.
T
h
e
an
al
y
s
i
s
h
as
b
ee
n
ca
r
r
ied
o
u
t
ex
p
er
i
m
en
ta
ll
y
.
Fo
r
th
is
p
u
r
p
o
s
e,
th
r
ee
s
u
b
j
ec
ts
w
er
e
ch
o
s
en
a
n
d
th
e
o
b
s
er
v
at
i
o
n
h
as
b
ee
n
ca
r
r
ied
o
u
t
f
o
r
r
an
d
o
m
m
o
v
e
m
e
n
t
o
f
th
e
s
u
b
j
ec
ts
.
Fo
r
th
is
ex
p
er
i
m
en
t,
a
lo
w
-
li
g
h
t
co
n
d
itio
n
h
as
b
ee
n
s
et
u
p
in
a
r
o
o
m
in
s
u
c
h
a
w
a
y
t
h
at
p
ar
t
o
f
th
e
r
o
o
m
is
lo
w
li
g
h
t
an
d
p
ar
t
o
f
th
e
r
o
o
m
is
h
av
in
g
m
ed
i
u
m
li
g
h
t
n
in
g
co
n
d
itio
n
.
Dig
ital
ca
m
er
a
h
as
b
ee
n
u
s
ed
f
o
r
ca
p
tu
r
in
g
t
h
e
r
an
d
o
m
v
id
eo
f
ee
d
s
i
n
r
ea
l
-
ti
m
e
w
it
h
th
e
s
ize
o
f
ea
ch
f
r
a
m
es
co
m
es
u
n
d
er
th
e
r
an
g
e
o
f
m
i
n
i
m
u
m
5
0
0
0
-
9
0
0
0
MB.
T
h
e
d
im
e
n
s
io
n
o
f
t
h
e
f
r
a
m
e
is
r
etain
ed
u
n
i
f
o
r
m
l
y
s
a
m
e
a
s
6
4
0
x
4
8
0
w
it
h
a
f
r
a
m
e
-
r
ates
o
f
3
0
f
r
a
m
es
p
er
s
ec
o
n
d
,
d
ata
b
it
r
ate
o
f
7
9
8
1
k
ilo
b
y
tes
p
er
s
ec
o
n
d
an
d
to
tal
b
it
r
ate
o
f
7
9
8
1
k
ilo
b
y
tes
p
er
s
ec
o
n
d
.
T
h
e
s
cr
ip
tin
g
o
f
th
e
p
r
o
p
o
s
ed
s
tu
d
y
h
a
s
b
ee
n
ca
r
r
ied
o
u
t u
s
in
g
M
A
T
L
A
B
.
T
h
e
ab
o
v
e
an
al
y
s
is
is
ca
r
r
ied
o
u
t
co
n
s
id
er
in
g
t
h
e
p
r
esen
ce
o
f
s
in
g
le,
d
o
u
b
le,
an
d
tr
ip
le
s
s
u
b
j
ec
ts
w
it
h
d
y
n
a
m
ic
a
n
d
u
n
s
cr
ip
ted
m
o
v
e
m
e
n
ts
.
T
h
e
p
r
o
p
o
s
ed
s
tu
d
y
to
o
k
t
h
e
co
lo
r
e
d
v
id
eo
clip
as
in
p
u
t
a
s
w
ell
as
it
also
e
x
tr
ac
ts
t
h
e
co
r
r
esp
o
n
d
in
g
d
ep
th
f
r
a
m
es
th
a
t
ar
e
es
s
e
n
tiall
y
m
ea
n
t
f
o
r
a
p
r
ec
is
e
id
en
ti
f
icatio
n
o
f
all
th
e
d
y
n
a
m
icall
y
m
o
v
i
n
g
s
u
b
j
ec
ts
f
o
r
th
e
co
n
s
id
er
ed
v
id
eo
f
ee
d
.
T
h
e
co
m
p
lete
f
ee
d
w
a
s
ca
p
tu
r
ed
w
it
h
i
n
a
d
ela
y
les
s
th
a
n
0
.
0
0
8
6
5
5
1
s
ec
o
n
d
s
,
w
h
ich
is
q
u
ite
i
n
ac
ce
p
tab
le
li
m
its
a
n
d
s
u
it
s
w
el
l
w
i
th
an
y
f
o
r
m
o
f
v
id
eo
s
u
r
v
eilla
n
ce
m
o
n
ito
r
in
g
s
y
s
te
m
.
A
p
ar
t
f
r
o
m
t
h
is
,
t
h
e
a
m
o
u
n
ts
o
f
t
h
e
in
f
o
r
m
at
io
n
ex
tr
ac
ted
f
r
o
m
all
t
h
e
ab
o
v
e
i
m
a
g
es
ar
e
also
q
u
ite
s
i
g
n
if
ic
an
t
a
s
w
e
ll
a
s
p
r
ec
is
e
th
a
t
i
s
q
u
ite
n
ec
e
s
s
ar
y
i
n
o
r
d
er
to
p
er
f
o
r
m
an
y
o
p
er
atio
n
s
o
f
v
id
eo
an
al
y
tics
.
T
ab
le
1
also
s
h
o
w
s
th
at
p
r
o
p
o
s
ed
s
y
s
te
m
o
f
f
er
s
a
clea
r
cu
t
id
en
t
if
icatio
n
ca
p
ab
ilit
y
f
o
r
an
y
n
u
m
b
er
o
f
s
u
b
j
ec
ts
ev
e
n
w
h
e
n
th
e
s
u
b
j
ec
ts
ar
e
s
ee
n
in
p
ar
tial
o
r
co
m
p
lete
o
cc
l
u
s
io
n
.
Us
ag
e
o
f
d
ep
th
i
m
a
g
e
h
as p
r
o
v
en
s
ig
n
i
f
ica
n
t b
en
e
f
it
s
in
o
f
f
er
in
g
p
o
ten
tial i
n
f
o
r
m
ati
o
n
in
t
h
e
f
o
r
m
s
o
f
f
r
eq
u
e
n
c
y
.
T
ab
le
1
.
Vis
u
al
o
u
tco
m
e
s
o
f
p
r
o
p
o
s
ed
s
tu
d
y
Sin
g
le
S
u
b
j
ec
t
Do
u
b
le
Su
b
j
ec
t
T
r
i
p
le
Su
b
j
ec
ts
R
GB
Fra
m
e
Dep
th
Fra
m
e
I
d
n
etif
ied
Mo
tio
n
B
lo
b
Fin
al
d
etec
tio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
4
,
A
u
g
u
s
t
201
9
:
2
7
1
5
-
2724
2722
Fig
u
r
e
2
h
ig
h
li
g
h
ts
t
h
e
f
r
eq
u
e
n
c
y
i
n
f
o
r
m
atio
n
o
f
th
e
i
m
a
g
e
w
it
h
r
esp
ec
t
to
in
cr
ea
s
i
n
g
d
e
p
th
v
al
u
e.
T
h
e
g
r
ap
h
ical
o
u
tco
m
e
s
h
o
w
s
th
at
a
d
is
cr
ete
s
et
o
f
i
n
f
o
r
m
ati
o
n
ca
n
b
e
o
b
tain
ed
u
s
i
n
g
p
r
o
p
o
s
ed
s
y
s
te
m
.
(
a)
(
b
)
(
c)
Fig
u
r
e
2
.
Gr
ap
h
ical
Ou
tco
m
es
o
f
Sa
m
p
le
Mo
tio
n
B
lo
b
,
(
a)
B
lo
b
f
o
r
s
in
g
le
s
u
b
j
ec
t
,
(
b
)
B
lo
b
f
o
r
d
o
u
b
le
s
u
b
j
ec
t
,
(
c)
B
lo
b
f
o
r
s
in
g
le
s
u
b
j
ec
t
4.
CO
NCLU
SI
O
N
T
h
is
p
ap
er
d
is
cu
s
s
es
ab
o
u
t
a
s
i
m
p
le
f
r
a
m
e
w
o
r
k
th
at
e
m
p
h
asize
o
n
th
e
o
b
tai
n
in
g
m
ax
i
m
u
m
s
et
o
f
in
f
o
r
m
atio
n
o
f
th
e
o
b
j
ec
ts
w
it
h
in
a
v
id
eo
f
ee
d
.
T
h
e
p
r
o
p
o
s
e
d
s
tu
d
y
is
also
ca
p
ab
le
o
f
id
en
tify
i
n
g
th
e
d
y
n
a
m
i
c
s
u
b
j
ec
ts
i
n
p
o
o
r
illu
m
i
n
atio
n
co
n
d
itio
n
a
n
d
w
it
h
r
a
n
d
o
m
m
o
b
ilit
y
p
atter
n
.
T
h
e
co
n
tr
ib
u
ti
o
n
o
f
th
e
p
r
o
p
o
s
ed
s
tu
d
y
ar
e
as
f
o
llo
w
:
i)
t
h
e
p
r
o
p
o
s
ed
s
tu
d
y
i
n
tr
o
d
u
ce
s
a
v
e
r
y
s
i
m
p
le
ap
p
r
o
ac
h
o
f
v
id
eo
s
u
r
v
eilla
n
ce
s
y
s
te
m
w
it
h
o
u
t
in
v
o
lv
i
n
g
an
y
f
o
r
m
o
f
co
m
p
lex
o
r
iter
ativ
e
s
y
s
te
m
,
ii)
th
e
p
r
o
p
o
s
ed
s
tu
d
y
h
a
r
n
ess
t
h
e
p
o
ten
tial
in
f
o
r
m
atio
n
o
b
tain
ed
b
y
i
n
teg
r
atin
g
d
ep
th
i
m
a
g
e
f
o
r
b
etter
s
eg
m
e
n
tatio
n
p
r
o
ce
s
s
i
n
h
i
g
h
l
y
s
i
m
p
ler
p
r
o
ce
s
s
,
iii)
th
e
r
esp
o
n
s
e
r
ate
o
f
t
h
e
d
e
tectio
n
h
as
ex
tr
e
m
el
y
le
s
s
er
d
ela
y
o
f
0
.
0
0
8
6
5
5
1
s
ec
o
n
d
s
co
m
p
ar
ed
to
r
ea
l
-
ti
m
e
f
ee
d
h
i
g
h
li
g
h
t
in
g
it
s
ap
p
licab
i
lit
y
o
n
r
ea
l
-
w
o
r
ld
ap
p
licatio
n
s
an
d
s
y
s
te
m
,
a
n
d
iv
)
t
h
e
r
u
n
-
ti
m
e
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
i
s
0
.
1
1
6
2
1
s
ec
o
n
d
s
ass
ess
ed
o
n
co
r
e
-
i3
p
r
o
ce
s
s
o
r
to
s
h
o
w
t
h
at
it
o
f
f
er
s
s
ig
n
i
f
ica
n
tl
y
f
a
s
ter
co
m
p
u
tatio
n
al
p
r
o
ce
s
s
in
g
ti
m
e
.
RE
F
E
R
E
NC
E
S
[1
]
G
a
n
d
o
m
i
A
,
Ha
id
e
r
M
.
“
Be
y
o
n
d
th
e
h
y
p
e
:
Big
d
a
ta
c
o
n
c
e
p
ts
,
m
e
th
o
d
s,
a
n
d
a
n
a
ly
ti
c
s
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
In
fo
rm
a
t
io
n
M
a
n
a
g
e
me
n
t
.
A
p
r
1
;
3
5
(
2
):1
3
7
-
44.
2
0
1
5
.
[2
]
L
ip
to
n
A
J,
V
e
n
e
ti
a
n
e
r
P
L
,
Ha
e
rin
g
N,
Bre
w
e
r
P
C,
Yin
W
,
Zh
a
n
g
Z,
Yu
L
,
Hu
Y,
M
y
e
rs
GW
,
Ch
o
sa
k
A
J,
Cu
tt
in
g
RA
,
“
in
v
e
n
to
rs
,
”
V
i
d
e
o
a
n
a
ly
ti
c
s
f
o
r
re
tail
b
u
sin
e
ss
p
ro
c
e
ss
m
o
n
it
o
rin
g
.
Un
it
e
d
S
tate
s
p
a
ten
t
US
9
,
1
5
8
,
9
7
5
.
Oc
t
1
3
2
0
1
5
.
[3
]
Bv
a
n
Re
st JH.
“
S
u
rv
e
il
lan
c
e
u
se
c
a
se
s:
f
o
c
u
s o
n
v
id
e
o
a
n
a
ly
ti
c
s,
”
Eu
ro
p
e
a
n
Co
m
m
is
sio
n
;
2
0
1
5
.
[4
]
Ch
a
m
b
e
rs
C
A
,
G
a
g
v
a
n
i
N,
Ro
b
e
rtso
n
P
,
S
h
e
p
ro
HE,
“
i
n
v
e
n
to
rs;
C
e
rn
iu
m
Co
rp
,
a
ss
ig
n
e
e
S
y
ste
m
s
a
n
d
m
e
th
o
d
s
f
o
r
a
n
a
ly
sis
o
f
v
id
e
o
c
o
n
ten
t,
e
v
e
n
t
n
o
ti
f
ica
ti
o
n
,
a
n
d
v
id
e
o
c
o
n
ten
t
p
r
o
v
isio
n
,
”
U
n
i
ted
S
tate
s
p
a
ten
t
U
S
8
,
2
0
4
,
2
7
3
.
Ju
n
19.
2
0
1
2
.
[5
]
S
.
Ojh
a
a
n
d
S
.
S
a
k
h
a
re
,
“
Im
a
g
e
p
ro
c
e
ss
in
g
tec
h
n
i
q
u
e
s
f
o
r
o
b
j
e
c
t
trac
k
in
g
in
v
id
e
o
su
rv
e
il
lan
c
e
-
A
su
rv
e
y
,
”
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
Per
v
a
siv
e
Co
mp
u
ti
n
g
(
ICPC)
,
P
u
n
e
,
2
0
1
5
,
p
p
.
1
-
6
.
2
0
1
5
.
[6
]
W
.
F
a
n
g
,
T
.
Zh
a
n
g
,
C.
Zh
a
o
,
D
.
B.
S
o
o
m
ro
,
R.
T
a
j
a
n
d
H.
Hu
,
“
Ba
c
k
g
ro
u
n
d
S
u
b
trac
ti
o
n
B
a
se
d
o
n
Ra
n
d
o
m
S
u
p
e
r
p
ix
e
ls Un
d
e
r
M
u
lt
i
p
le S
c
a
les
f
o
r
V
id
e
o
A
n
a
l
y
ti
c
s,”
in
IEE
E
A
c
c
e
ss
,
v
o
l.
6
,
p
p
.
3
3
3
7
6
-
3
3
3
8
6
,
2
0
1
8
.
[7
]
H.
L
iu
,
S
.
Ch
e
n
a
n
d
N.
Ku
b
o
ta,
“
In
telli
g
e
n
t
V
i
d
e
o
S
y
ste
m
s
a
n
d
A
n
a
l
y
ti
c
s:
A
S
u
rv
e
y
,
”
in
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
In
d
u
stria
l
I
n
f
o
rm
a
ti
c
s
,
v
o
l.
9
,
n
o
.
3
,
p
p
.
1
2
2
2
-
1
2
3
3
,
A
u
g
.
2
0
1
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
S
imp
lifi
ed
vid
eo
s
u
r
ve
illa
n
ce
f
r
a
mewo
r
k
fo
r
d
yn
a
mic
…
(
Ma
d
h
u
C
h
a
n
d
r
a
G
)
2723
[8
]
B.
P
ra
b
h
a
k
a
ra
n
,
Y.
G
.
Ji
a
n
g
,
H.
Ka
lv
a
a
n
d
S
.
F
.
Ch
a
n
g
,
“
Ed
it
o
rial
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
M
u
lt
i
m
e
d
ia
S
p
e
c
ial
S
e
c
ti
o
n
o
n
V
i
d
e
o
A
n
a
ly
ti
c
s:
Ch
a
ll
e
n
g
e
s
,
A
l
g
o
rit
h
m
s,
a
n
d
A
p
p
li
c
a
ti
o
n
s,”
in
IEE
E
T
ra
n
s
a
c
ti
o
n
s
o
n
M
u
lt
ime
d
i
a
,
v
o
l
.
2
0
,
n
o
.
5
,
p
p
.
1
0
3
7
-
1
0
3
7
,
M
a
y
2
0
1
8
.
[9
]
C.
M
e
h
r
o
t
ra
,
N.
C
h
it
ra
n
s
h
a
n
d
A
.
S
in
g
h
,
“
S
c
o
p
e
a
n
d
c
h
a
ll
e
n
g
e
s
o
f
v
isu
a
l
a
n
a
ly
ti
c
s:
A
su
rv
e
y
,
”
In
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
Co
m
p
u
ti
n
g
,
Co
m
mu
n
ica
t
io
n
a
n
d
Au
t
o
ma
ti
o
n
(
ICCCA)
,
G
re
a
t
e
r
No
id
a
,
2
0
1
7
,
p
p
.
1
2
2
9
-
1
2
3
4
.
2
0
1
7
.
[1
0
]
X
iao
g
a
n
g
W
a
n
g
,
“
De
e
p
L
e
a
rn
in
g
in
Ob
jec
t
Re
c
o
g
n
it
io
n
,
De
tec
ti
o
n
,
a
n
d
S
e
g
m
e
n
tatio
n
,
”
N
o
w
P
u
b
li
s
h
e
rs,
2
0
1
6
[1
1
]
M
a
d
h
u
Ch
a
n
d
ra
,
G
.
,
a
n
d
G
.
M
.
S
re
e
ra
m
a
Re
d
d
y
,
“
In
sig
h
ts
to
V
i
d
e
o
A
n
a
l
y
ti
c
M
o
d
e
ll
in
g
A
p
p
ro
a
c
h
w
it
h
F
u
tu
r
e
L
in
e
o
f
Re
se
a
rc
h
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
m
p
u
ter
A
p
p
l
ica
ti
o
n
s
,
Vo
l.
1
4
7
,
N
o
.
7
,
2
0
1
6
.
[1
2
]
M
a
d
h
u
Ch
a
n
d
ra
,
G
.
,
a
n
d
G
.
M
.
S
re
e
ra
m
a
Re
d
d
y
,
“
A
n
a
l
y
ti
c
a
l
F
ra
m
e
w
o
r
k
f
o
r
Id
e
n
ti
f
ica
ti
o
n
o
f
Ou
tl
iers
f
o
r
Un
sc
rip
ted
V
i
d
e
o
,
”
CIC
2
0
1
6
,
In
t
e
rn
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Co
mp
u
ter
S
c
ien
c
e
a
n
d
In
f
o
rm
a
ti
o
n
S
e
c
u
rity
,
V
o
l
.
1
4
,
2
0
1
6
[1
3
]
M
a
d
h
u
Ch
a
n
d
ra
,
G
.
,
a
n
d
G
.
M
.
S
re
e
ra
m
a
Re
d
d
y
,
“
F
ra
m
e
wo
rk
f
o
r
Co
n
tex
tu
a
l
O
u
tl
ier
I
d
e
n
ti
f
ica
ti
o
n
u
sin
g
M
u
lt
iv
a
riate
A
n
a
l
y
sis
a
p
p
ro
a
c
h
a
n
d
Un
s
u
p
e
rv
ise
d
L
e
a
rn
in
g
,
”
In
t
e
rn
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
Co
m
p
u
ter
En
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
V
o
l.
8
,
No
.
2
,
p
p
.
1
0
9
2
-
1
1
0
1
,
2
0
1
8
.
[1
4
]
A
.
A
sla
m
a
n
d
E.
Cu
rry
,
“
T
o
w
a
rd
s
a
G
e
n
e
ra
li
z
e
d
A
p
p
ro
a
c
h
f
o
r
De
e
p
Ne
u
ra
l
Ne
tw
o
rk
Ba
se
d
Ev
e
n
t
P
r
o
c
e
ss
in
g
f
o
r
th
e
In
ter
n
e
t
o
f
M
u
l
ti
m
e
d
ia T
h
in
g
s
,
”
in
IE
EE
Acc
e
ss
,
v
o
l.
6
,
p
p
.
2
5
5
7
3
-
2
5
5
8
7
,
2
0
1
8
.
[1
5
]
C.
Ba
il
a
s,
M
.
M
a
rsd
e
n
,
D.
Z
h
a
n
g
,
N.
E.
O'
Co
n
n
o
r
a
n
d
S
.
L
it
tl
e
,
“
P
e
rf
o
rm
a
n
c
e
o
f
v
id
e
o
p
ro
c
e
ss
in
g
a
t
th
e
e
d
g
e
f
o
r
c
ro
w
d
-
m
o
n
it
o
ri
n
g
a
p
p
l
ica
ti
o
n
s,”
IEE
E
4
th
W
o
rl
d
F
o
ru
m
o
n
In
ter
n
e
t
o
f
T
h
in
g
s
(
W
F
-
Io
T
)
,
S
i
n
g
a
p
o
re
,
p
p
.
4
8
2
-
4
8
7
.
2
0
1
8
.
[1
6
]
Y.
Ya
n
g
,
S
.
P
o
u
y
a
n
f
a
r,
H.
T
ian
,
M
.
C
h
e
n
,
S
.
C.
Ch
e
n
a
n
d
M
.
L
.
S
h
y
u
,
“
IF
-
M
CA
:
I
m
p
o
rtan
c
e
F
a
c
to
r
-
Ba
se
d
M
u
lt
i
p
le
Co
rre
sp
o
n
d
e
n
c
e
A
n
a
l
y
s
is
f
o
r
M
u
lt
im
e
d
ia
D
a
ta
A
n
a
l
y
ti
c
s
,
”
in
IEE
E
T
r
a
n
sa
c
ti
o
n
s
o
n
M
u
lt
i
me
d
ia
,
v
o
l.
2
0
,
n
o
.
4
,
p
p
.
1
0
2
4
-
1
0
3
2
,
A
p
ril
2
0
1
8
.
[1
7
]
Z.
S
h
a
o
,
J.
Ca
i
a
n
d
Z.
W
a
n
g
,
“
S
m
a
rt
M
o
n
i
to
ri
n
g
Ca
m
e
r
a
s
Driv
e
n
In
telli
g
e
n
t
P
ro
c
e
ss
in
g
t
o
B
ig
S
u
r
v
e
il
lan
c
e
V
id
e
o
Da
ta,” in
IEE
E
T
ra
n
s
a
c
ti
o
n
s o
n
B
ig
Da
t
a
,
v
o
l.
4
,
n
o
.
1
,
p
p
.
1
0
5
-
1
1
6
,
M
a
rc
h
1
2
0
1
8
.
[1
8
]
N.
Dim
it
rio
u
e
t
a
l.
,
“
A
n
In
teg
ra
ted
F
ra
m
e
w
o
rk
f
o
r
th
e
T
i
m
e
l
y
D
e
tec
ti
o
n
o
f
P
e
tt
y
Cri
m
e
s,”
Eu
ro
p
e
a
n
In
telli
g
e
n
c
e
a
n
d
S
e
c
u
rity I
n
fo
rm
a
ti
c
s Co
n
fer
e
n
c
e
(
EIS
IC)
,
A
th
e
n
s,
2
0
1
7
,
p
p
.
2
4
-
31.
2
0
1
7
.
[1
9
]
S
.
M
a
,
X
.
C
h
e
n
,
Z
.
L
i,
a
n
d
Y.
Ya
n
g
,
“
Re
se
a
rc
h
A
rti
c
le
A
Re
tri
e
v
a
l
Op
ti
m
ize
d
S
u
rv
e
il
lan
c
e
V
id
e
o
S
to
ra
g
e
S
y
st
e
m
f
o
r
Ca
m
p
u
s A
p
p
li
c
a
ti
o
n
S
c
e
n
a
rio
s
,
”
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
E
n
g
i
n
e
e
rin
g
,
p
p
.
1
0
,
2
0
1
8
[2
0
]
C.
G
.
Brin
to
n
,
S
.
B
u
c
c
a
p
at
n
a
m
,
M
.
C
h
ian
g
a
n
d
H.
V
.
P
o
o
r,
“
M
in
i
n
g
M
OO
C
Cli
c
k
stre
a
m
s:
V
id
e
o
-
W
a
tch
in
g
Be
h
a
v
io
r
v
s.
In
-
V
id
e
o
Qu
iz
P
e
rf
o
rm
a
n
c
e
,
”
in
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
S
i
g
n
a
l
Pro
c
e
ss
in
g
,
v
o
l.
6
4
,
n
o
.
1
4
,
p
p
.
3
6
7
7
-
3
6
9
2
,
J
u
ly
1
5
,
1
5
2
0
1
6
.
[2
1
]
D.
S
.
P
h
a
m
,
O.
A
ra
n
d
jelo
v
ić
a
n
d
S
.
V
e
n
k
a
tes
h
,
“
De
tec
ti
o
n
o
f
D
y
n
a
m
ic
Ba
c
k
g
ro
u
n
d
Du
e
to
S
w
a
y
i
n
g
M
o
v
e
m
e
n
ts
F
ro
m
M
o
ti
o
n
F
e
a
tu
re
s,”
i
n
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Ima
g
e
Pro
c
e
ss
in
g
,
v
o
l.
2
4
,
n
o
.
1
,
p
p
.
3
3
2
-
3
4
4
,
Ja
n
.
2
0
1
5
.
[2
2
]
V
.
Ka
lt
sa
,
A
.
Brias
so
u
li
,
I
.
Ko
m
p
a
tsiaris,
L
.
J.
Ha
d
ji
l
e
o
n
ti
a
d
is
a
n
d
M
.
G
.
S
tri
n
tzis,
“
S
w
a
rm
I
n
telli
g
e
n
c
e
f
o
r
De
tec
ti
n
g
In
tere
stin
g
Ev
e
n
ts
in
C
ro
w
d
e
d
En
v
iro
n
m
e
n
ts,”
in
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Ima
g
e
Pro
c
e
ss
in
g
,
v
o
l.
2
4
,
n
o
.
7
,
p
p
.
2
1
5
3
-
2
1
6
6
,
Ju
ly
2
0
1
5
.
[2
3
]
Y.
Ch
e
n
g
,
L
.
Br
o
w
n
,
Q.
F
a
n
,
R
.
F
e
ris,
S
.
P
a
n
k
a
n
ti
a
n
d
T
.
Z
h
a
n
g
,
“
Risk
W
h
e
e
l:
In
tera
c
ti
v
e
v
isu
a
l
a
n
a
ly
ti
c
s
f
o
r
su
rv
e
il
lan
c
e
e
v
e
n
t
d
e
tec
ti
o
n
,
”
IEE
E
In
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
M
u
lt
ime
d
i
a
a
n
d
Exp
o
(
ICM
E)
,
Ch
e
n
g
d
u
,
p
p
.
1
-
6.
2
0
1
4
.
[2
4
]
T
.
A
b
d
u
ll
a
h
,
A
.
A
n
ju
m
,
M
.
F
.
T
a
riq
,
Y
.
Ba
lt
a
c
i
a
n
d
N
.
A
n
to
n
o
p
o
u
lo
s,
“
T
ra
ff
ic
M
o
n
it
o
r
in
g
Us
in
g
Vid
e
o
A
n
a
ly
ti
c
s
in
Cl
o
u
d
s,”
IEE
E/
ACM
7
th
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Ut
il
it
y
a
n
d
Clo
u
d
C
o
mp
u
ti
n
g
,
L
o
n
d
o
n
,
p
p
.
3
9
-
4
8
.
2
0
1
4
.
[2
5
]
A
.
H.
M
e
g
h
d
a
d
i
a
n
d
P
.
Ira
n
i,
“
In
tera
c
ti
v
e
Ex
p
lo
ra
ti
o
n
o
f
S
u
rv
e
il
la
n
c
e
V
i
d
e
o
th
r
o
u
g
h
A
c
ti
o
n
S
h
o
t
S
u
m
m
a
riz
a
ti
o
n
a
n
d
T
ra
jec
to
r
y
V
isu
a
li
z
a
ti
o
n
,
”
i
n
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Vi
su
a
li
z
a
ti
o
n
a
n
d
Co
m
p
u
ter
Gr
a
p
h
ics
,
v
o
l.
1
9
,
n
o
.
1
2
,
p
p
.
2
1
1
9
-
2
1
2
8
,
De
c
.
2
0
1
3
.
[2
6
]
T
.
S
e
n
st,
V
.
Ei
se
lein
,
A
.
B
a
d
ii
,
M
.
E
in
ig
,
I.
Ke
ll
e
r
a
n
d
T
.
S
i
k
o
ra
,
“
A
d
e
c
e
n
tralize
d
p
riv
a
c
y
-
se
n
siti
v
e
v
id
e
o
su
rv
e
il
lan
c
e
f
ra
m
e
w
o
rk
,
”
1
8
th
In
t
e
rn
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Di
g
i
t
a
l
S
ig
n
a
l
Pro
c
e
ss
in
g
(
DS
P)
,
F
ira
,
p
p
.
1
-
6.
2
0
1
3
.
[2
7
]
S
.
M
.
T
a
h
ir,
On
g
P
e
n
g
S
h
e
n
,
L
e
e
Ch
in
Ya
n
g
a
n
d
E.
K.
Ka
ru
p
p
ia
h
,
“
Im
p
le
m
e
n
tatio
n
o
f
in
tru
si
o
n
d
e
tec
ti
o
n
sy
ste
m
in
CUD
A
f
o
r
r
e
a
l
-
ti
m
e
m
u
lt
i
-
n
o
d
e
stre
a
m
in
g
,
”
IEE
E
Co
n
fer
e
n
c
e
o
n
S
y
ste
ms
,
Pro
c
e
ss
&
Co
n
tro
l
(
ICS
PC
)
,
Ku
a
la
L
u
m
p
u
r
,
p
p
.
9
7
-
1
0
2
.
2
0
1
3
.
[2
8
]
D.
Co
n
te,
P
.
F
o
g
g
ia,
G
.
P
e
rc
a
n
n
e
ll
a
,
A
.
S
a
g
g
e
s
e
a
n
d
M
.
V
e
n
t
o
,
“
A
n
En
se
m
b
le
o
f
R
e
jec
ti
n
g
Clas
sif
ier
s
f
o
r
A
n
o
m
a
l
y
De
tec
ti
o
n
o
f
A
u
d
io
Ev
e
n
ts,”
IEE
E
Nin
th
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Ad
v
a
n
c
e
d
Vi
d
e
o
a
n
d
S
ig
n
a
l
-
B
a
se
d
S
u
rv
e
il
la
n
c
e
,
Be
ij
in
g
,
p
p
.
7
6
-
8
1
.
2
0
1
2
.
[2
9
]
S
.
Kim
,
B.
j.
L
e
e
,
J.
w
.
Je
o
n
g
a
n
d
M
.
j
.
L
e
e
,
“
M
u
lt
i
-
o
b
jec
t
trac
k
in
g
c
o
p
ro
c
e
ss
o
r
f
o
r
m
u
lt
i
-
ch
a
n
n
e
l
e
m
b
e
d
d
e
d
DV
R
s
y
ste
m
s,”
in
IEE
E
T
ra
n
s
a
c
ti
o
n
s o
n
Co
n
su
me
r E
lec
tro
n
ics
,
v
o
l.
5
8
,
n
o
.
4
,
p
p
.
1
3
6
6
-
1
3
7
4
,
N
o
v
e
m
b
e
r
2
0
1
2
.
[3
0
]
M.
M
u
e
ll
e
r,
P
.
Ka
ra
se
v
,
I.
Ko
l
e
so
v
a
n
d
A
.
Tan
n
e
n
b
a
u
m
,
“
A
v
id
e
o
a
n
a
ly
ti
c
s
f
ra
m
e
w
o
rk
f
o
r
a
m
o
rp
h
o
u
s
a
n
d
u
n
stru
c
t
u
re
d
a
n
o
m
a
l
y
d
e
te
c
ti
o
n
,
”
1
8
t
h
IEE
E
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Ima
g
e
Pro
c
e
ss
in
g
,
Bru
s
se
ls,
2
0
1
1
,
p
p
.
2
9
4
5
-
2
9
4
8
.
2
0
1
1
.
[3
1
]
G
u
ler
P
,
Em
e
k
siz
D,
T
e
m
ize
l
A
,
T
e
k
e
M
,
T
e
m
i
z
e
l
T
T
.
“
R
e
a
l
-
ti
m
e
m
u
lt
i
-
c
a
m
e
r
a
v
id
e
o
a
n
a
ly
ti
c
s
s
y
ste
m
o
n
G
P
U”
J
o
u
rn
a
l
o
f
Rea
l
-
T
ime
Ima
g
e
Pro
c
e
ss
in
g
.
M
a
r
1
;1
1
(3
)
:4
5
7
-
72.
2
0
1
6
.
[3
2
]
J.
Ca
n
d
a
m
o
,
M
.
S
h
re
v
e
,
D.
B.
Go
ld
g
o
f
,
D.
B.
S
a
p
p
e
r
a
n
d
R.
Ka
stu
ri,
“
Un
d
e
rsta
n
d
in
g
T
ra
n
sit
S
c
e
n
e
s:
A
S
u
rv
e
y
o
n
Hu
m
a
n
B
e
h
a
v
io
r
-
Re
c
o
g
n
it
io
n
A
lg
o
rit
h
m
s,”
in
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
In
telli
g
e
n
t
T
r
a
n
sp
o
rta
ti
o
n
S
y
ste
ms
,
v
o
l.
1
1
,
n
o
.
1
,
p
p
.
2
0
6
-
2
2
4
,
M
a
rc
h
2
0
1
0
.
[3
3
]
J.
P
a
rso
la,
D.
G
a
n
g
o
d
k
a
r,
A
.
M
it
tal,
“
P
o
st
Ev
e
n
t
In
v
e
stig
a
ti
o
n
o
f
M
u
lt
i
-
stre
a
m
V
id
e
o
Da
ta
Util
izin
g
Ha
d
o
o
p
Clu
ste
r
,
”
In
te
rn
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
i
n
e
e
rin
g
(
IJ
ECE
),
v
o
l.
8
(
6
)
,
p
p
.
5
0
8
9
-
8
0
9
7
,
2
0
1
8
.
[3
4
]
S
.
F
a
k
h
a
r
A
.
G
,
A
.
F
a
u
z
a
n
K,
M
.
S
a
a
d
H,
R.
Aff
e
n
d
i
H,
K.
H.
F
e
n
,
“
De
v
e
lo
p
m
e
n
t
o
f
a
P
o
rtab
le
Co
m
m
u
n
it
y
V
id
e
o
S
u
rv
e
il
lan
c
e
S
y
ste
m
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
Co
m
p
u
ter
E
n
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
9
,
n
o
.
3
,
2
0
1
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
4
,
A
u
g
u
s
t
201
9
:
2
7
1
5
-
2724
2724
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
M
a
d
h
u
C
h
a
n
d
r
a
G
,
P
u
rsu
in
g
Do
c
to
ra
l
De
g
re
e
in
th
e
d
o
m
a
in
o
f
I
m
a
g
e
a
n
d
V
id
e
o
p
r
o
c
e
ss
in
g
f
ro
m
V
isv
e
sv
a
ra
y
a
T
e
c
h
n
o
lo
g
ica
l
Un
i
v
e
rsit
y
(V
T
U),
Be
lag
a
v
i.
Re
c
e
i
v
e
d
th
e
B.
E
a
n
d
M
.
T
e
c
h
De
g
re
e
f
ro
m
V
T
U,
Be
lag
a
v
i,
In
d
ia
in
2
0
0
6
a
n
d
2
0
0
8
,
re
sp
e
c
ti
v
e
l
y
.
P
re
s
e
n
tl
y
h
e
is
w
o
rk
in
g
a
s
As
sista
n
t
p
ro
f
e
ss
o
r
in
th
e
De
p
t.
o
f
El
e
c
tr
o
n
ics
a
n
d
Co
m
m
u
n
ica
ti
o
n
E
n
g
in
e
e
rin
g
a
t
R
L
JI
T
,
Do
d
d
a
b
a
ll
a
p
u
r.
He
is
h
a
v
in
g
to
tal
tea
c
h
in
g
e
x
p
e
rien
c
e
o
f
1
0
y
e
a
rs
a
n
d
a
lso
su
c
c
e
ss
f
u
ll
y
g
u
id
e
d
m
a
n
y
U
G
P
ro
jec
ts
a
n
d
a
lso
p
a
rti
c
i
p
a
ted
v
a
rio
u
s
w
o
rk
sh
o
p
s
a
n
d
f
a
c
u
lt
y
d
e
v
e
lo
p
m
e
n
t
p
ro
g
ra
m
m
e
.
He
is
a
m
e
m
b
e
r
o
f
IEE
E,
M
I
E,
a
n
d
IET
E.
S
r
e
e
r
a
m
a
R
e
d
d
y
G
M
,
P
r
o
f
e
ss
o
r
&
P
rin
c
i
p
a
l
o
f
El
e
c
tro
n
ics
a
n
d
Co
m
m
u
n
ica
ti
o
n
En
g
i
n
e
e
rin
g
,
C
B
y
re
g
o
w
d
a
In
stit
u
te
o
f
T
e
c
h
n
o
l
o
g
y
-
Ko
lar,
In
d
ia.
Re
c
e
i
v
e
d
P
h
.
D
in
M
icr
o
El
e
c
tro
n
ics
/
V
L
S
I
De
sig
n
f
ro
m
De
p
t.
o
f
El
e
c
tro
n
ics
a
n
d
Co
m
m
u
n
ica
ti
o
n
En
g
i
n
e
e
rin
g
,
JN
T
U,
A
n
d
h
ra
P
ra
d
e
sh
,
in
2
0
0
9
a
n
d
M
E
f
ro
m
UV
CE
Ba
n
g
a
lo
re
in
th
e
y
e
a
r
1
9
9
8
.
He
h
a
s
2
6
y
e
a
rs
o
f
t
e
a
c
h
in
g
a
n
d
9
y
e
a
rs
o
f
re
se
a
rc
h
e
x
p
e
rien
c
e
a
n
d
p
u
b
li
s
h
e
d
a
ro
u
n
d
3
0
p
lu
s
i
n
n
a
ti
o
n
a
l
a
n
d
in
tern
a
ti
o
n
a
l
jo
u
rn
a
ls
a
n
d
c
o
n
f
e
re
n
c
e
s.
Co
n
d
u
c
ted
2
5
v
a
ri
o
u
s
w
o
rk
sh
o
p
s
a
n
d
h
a
n
d
s
o
n
s
k
il
ls
a
c
ti
v
it
ies
f
o
r
b
o
th
sta
f
f
a
n
d
stu
d
e
n
ts.
He
h
a
s
i
n
it
iate
d
v
a
rio
u
s
a
c
ti
v
it
ies
a
s
P
ri
n
c
ip
a
l
i
n
p
re
v
io
u
s
c
o
ll
e
g
e
s
a
n
d
re
c
e
iv
e
d
v
a
rio
u
s
f
u
n
d
s f
ro
m
lea
d
in
g
o
rg
a
n
iza
ti
o
n
s.
Evaluation Warning : The document was created with Spire.PDF for Python.