I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Ro
bo
t
ics a
nd
Aut
o
m
a
t
io
n
(
I
J
RA)
Vo
l.
1
4
,
No
.
1
,
Ma
r
ch
20
2
5
,
p
p
.
93
~
102
I
SS
N:
2722
-
2
5
8
6
,
DOI
:
1
0
.
1
1
5
9
1
/i
jr
a
.
v
1
4
i
1
.
pp
93
-
1
0
2
93
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
r
a
.
ia
esco
r
e.
co
m
Perf
o
rma
nce
co
m
pa
riso
n of optica
l
f
lo
w and
ba
ckg
ro
und
subtra
ction a
nd
d
iscrete
wa
v
elet tr
a
nsfo
rm
metho
ds
for mo
v
ing
o
bject
s
M
o
nik
a
Sh
a
rm
a
1
,
K
uld
ee
p Sin
g
h K
a
s
wa
n
1
,
Dileep
K
um
a
r
Ya
da
v
2
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
,
G
a
l
g
o
t
i
a
’
s U
n
i
v
e
r
s
i
t
y
,
G
r
e
a
t
e
r
N
o
i
d
a
,
I
n
d
i
a
2
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
,
S
C
S
E
T,
B
e
n
n
e
t
t
U
n
i
v
e
r
si
t
y
,
G
r
e
a
t
e
r
N
o
i
d
a
,
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
J
u
l 1
9
,
2
0
2
4
R
ev
is
ed
Oct
2
7
,
2
0
2
4
Acc
ep
ted
No
v
1
9
,
2
0
2
4
S
e
lf
-
d
riv
in
g
c
a
rs
a
n
d
o
t
h
e
r
a
u
to
n
o
m
o
u
s
v
e
h
icle
s
re
ly
o
n
sy
ste
m
s
th
a
t
c
a
n
re
c
o
g
n
ize
a
n
d
f
o
ll
o
w
o
b
jec
ts.
Th
e
wa
y
s
h
e
lp
p
e
o
p
le
m
a
k
e
sa
fe
d
e
c
isio
n
s
a
n
d
n
a
v
ig
a
te
b
y
sh
o
win
g
t
h
in
g
s
li
k
e
p
e
o
p
le,
c
a
rs,
o
b
sta
c
les
,
a
n
d
traffic
li
g
h
ts
.
Co
m
p
u
ter
v
isi
o
n
a
lg
o
rit
h
m
s
e
n
c
o
m
p
a
ss
b
o
th
o
b
jec
t
d
e
tec
ti
o
n
a
n
d
trac
k
i
n
g
.
Diffe
re
n
t
m
e
th
o
d
s
a
re
sp
e
c
ifi
c
a
ll
y
d
e
v
e
lo
p
e
d
fo
r
p
ictu
re
o
r
v
i
d
e
o
a
n
a
ly
sis
n
o
t
o
n
ly
to
id
e
n
ti
fy
it
e
m
s
with
i
n
t
h
e
v
is
u
a
l
c
o
n
ten
t
b
u
t
a
lso
to
a
c
c
u
ra
tely
d
e
term
in
e
th
e
ir
p
re
c
ise
lo
c
a
ti
o
n
s.
Th
is
c
a
n
o
p
e
ra
te
in
d
e
p
e
n
d
e
n
t
ly
a
s
a
n
a
lg
o
rit
h
m
o
r
a
s
a
c
o
n
stit
u
e
n
t
o
f
a
n
it
e
m
-
trac
k
in
g
sy
ste
m
.
Ob
jec
t
trac
k
in
g
a
lg
o
rit
h
m
s
c
a
n
b
e
u
se
d
to
fo
ll
o
w
o
b
jec
ts
o
v
e
r
v
i
d
e
o
fra
m
e
s,
p
r
o
v
i
d
in
g
a
c
o
n
tras
ti
n
g
a
p
p
ro
a
c
h
.
T
h
e
re
se
a
rc
h
a
rti
c
le
fo
c
u
se
s
o
n
t
h
e
m
a
th
e
m
a
ti
c
a
l
m
o
d
e
l
sim
u
lati
o
n
o
f
o
p
ti
c
a
l
fl
o
w,
b
a
c
k
g
ro
u
n
d
su
b
trac
ti
o
n
,
a
n
d
d
isc
re
te
wa
v
e
let
tran
sfo
rm
(DWT
)
m
e
th
o
d
s
fo
r
m
o
v
in
g
o
b
jec
ts.
Th
e
p
e
rfo
rm
a
n
c
e
e
v
a
lu
a
ti
o
n
o
f
th
e
m
e
t
h
o
d
s
is
d
o
n
e
b
a
se
d
o
n
sim
u
lati
o
n
re
sp
o
n
se
ti
m
e
,
a
c
c
u
ra
c
y
,
se
n
siti
v
it
y
,
a
n
d
sp
e
c
ifi
c
it
y
d
o
e
se
v
e
ra
l
ima
g
e
s
in
d
iffere
n
t
e
n
v
iro
n
m
e
n
ts.
Th
e
DWT
h
a
s
s
h
o
wn
o
p
ti
m
a
l
b
e
h
a
v
i
o
r
i
n
ter
m
s
o
f
th
e
re
sp
o
n
se
ti
m
e
o
f
0
.
2
7
se
c
o
n
d
s,
a
c
c
u
ra
c
y
o
f
9
5
.
3
4
%
,
se
lec
ti
v
it
y
o
f
9
5
.
9
6
%
,
a
n
d
sp
e
c
ifi
c
it
y
o
f
9
4
.
6
8
%
.
K
ey
w
o
r
d
s
:
Dis
cr
ete
wav
elet
tr
an
s
f
o
r
m
I
m
ag
e
s
u
b
tr
ac
tio
n
Mo
v
in
g
o
b
jects
Op
tical
m
o
d
elin
g
Sig
n
al
d
etec
tio
n
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
:
Mo
n
ik
a
Sh
ar
m
a
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
,
Galg
o
tia’
s
Un
iv
er
s
ity
Gr
ea
ter
No
id
a,
NC
R
,
I
n
d
ia
E
m
ail: m
o
n
ik
ash
ar
m
a
.
cse@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
Ob
ject
d
etec
tio
n
is
a
tech
n
i
q
u
e
u
s
ed
in
c
o
m
p
u
te
r
v
is
io
n
to
id
en
tify
an
d
lo
ca
te
item
s
in
b
o
th
v
id
e
o
an
d
s
till
im
ag
es.
Ob
ject
d
etec
tio
n
alg
o
r
ith
m
s
ty
p
ically
r
el
y
o
n
m
ac
h
in
e
lear
n
i
n
g
o
r
d
ee
p
l
ea
r
n
in
g
tec
h
n
iq
u
es
to
o
b
tain
m
ea
n
in
g
f
u
l
f
in
d
in
g
s
.
Hu
m
an
s
ca
n
q
u
ick
ly
id
en
t
if
y
an
d
f
in
d
o
b
jects
o
f
in
ter
e
s
t
wh
en
th
ey
v
iew
v
is
u
al
m
ater
ial
[
1
]
.
Ob
ject
d
etec
tio
n
s
ee
k
s
to
r
ep
licate
th
is
lev
el
o
f
co
g
n
itiv
e
ab
ilit
y
in
a
co
m
p
u
tatio
n
al
f
r
am
ewo
r
k
.
Var
io
u
s
d
is
cip
lin
es
ar
e
cu
r
r
en
tly
allo
ca
tin
g
r
e
s
o
u
r
ce
s
to
th
e
in
v
esti
g
atio
n
o
f
au
to
m
ated
v
i
d
eo
s
u
r
v
eillan
ce
.
Ad
v
an
ce
m
e
n
ts
in
m
o
d
er
n
tech
n
o
lo
g
y
h
a
v
e
r
ea
ch
ed
a
s
tag
e
wh
er
e
it
is
ec
o
n
o
m
ically
ad
v
an
tag
e
o
u
s
to
i
n
s
tall
ca
m
er
as
in
a
ce
r
tain
lo
ca
tio
n
an
d
ca
p
tu
r
e
v
id
eo
f
o
o
tag
e,
r
ath
er
th
an
em
p
lo
y
in
g
in
d
iv
id
u
als
to
co
n
s
tan
tly
ex
a
m
in
e
th
e
r
ec
o
r
d
ed
f
o
o
tag
e
[
2
]
.
Nu
m
er
o
u
s
en
ter
p
r
is
es
h
av
e
alr
ea
d
y
in
s
talled
s
ec
u
r
ity
ca
m
er
as,
ca
p
ab
le
o
f
ca
p
tu
r
in
g
f
o
o
tag
e
th
at
ca
n
b
e
s
to
r
ed
o
n
tap
e,
s
u
b
ject
to
b
e
in
g
o
v
e
r
wr
itten
o
r
s
to
r
ed
in
a
v
id
eo
ar
ch
iv
e.
Su
b
s
eq
u
en
tly
,
d
etec
tiv
es
ca
n
s
cr
u
tin
ize
th
e
r
ec
o
r
d
ed
v
i
d
eo
m
ater
ial
to
ascer
tain
th
e
s
eq
u
en
ce
o
f
ev
e
n
ts
in
th
e
o
cc
u
r
r
en
ce
o
f
a
cr
im
in
al
ac
t
[
3
]
,
s
u
ch
as
a
r
o
b
b
er
y
in
a
s
to
r
e
o
r
th
e
p
ilfe
r
in
g
o
f
a
v
alu
ab
le
a
u
to
m
o
b
ile.
Ho
wev
er
,
th
e
n
,
it
is
ev
id
e
n
tly
b
e
y
o
n
d
th
e
p
o
in
t
o
f
p
r
ev
e
n
tio
n
o
r
in
ter
v
e
n
tio
n
.
T
o
m
itig
ate
th
e
o
cc
u
r
r
e
n
ce
o
f
th
ese
s
itu
atio
n
s
,
we
ca
n
im
p
lem
en
t
co
n
tin
u
o
u
s
m
o
n
ito
r
in
g
an
d
an
aly
s
is
o
f
v
id
e
o
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
2
5
8
6
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
1
4
,
No
.
1
,
Ma
r
ch
20
2
5
:
93
-
1
0
2
94
s
u
r
v
eillan
ce
s
y
s
tem
s
.
I
n
th
is
m
an
n
er
,
if
s
ec
u
r
ity
ag
e
n
ts
id
e
n
tify
an
o
n
g
o
i
n
g
r
o
b
b
er
y
o
r
s
o
m
eo
n
e
ex
h
i
b
itin
g
s
u
s
p
icio
u
s
b
eh
av
io
r
i
n
th
e
p
ar
k
in
g
lo
t,
t
h
ey
ca
n
p
r
o
m
p
tly
in
t
er
v
en
e
to
a
v
er
t c
r
im
i
n
al
ac
tiv
ity
.
Vid
eo
-
b
ased
s
u
r
v
eillan
ce
s
y
s
t
em
s
[
4
]
allo
w
f
o
r
th
e
m
o
n
ito
r
in
g
o
f
m
an
y
s
ce
n
es.
Vid
eo
s
tr
ea
m
s
ca
n
b
e
u
tili
ze
d
to
ex
tr
ac
t
in
f
o
r
m
atio
n
th
at
ca
p
tu
r
es
o
u
r
atten
tio
n
in
v
ar
io
u
s
ap
p
licatio
n
s
,
s
u
ch
as
s
ec
u
r
ity
,
en
ter
tain
m
en
t,
s
af
ety
,
an
d
ef
f
icien
cy
en
h
a
n
ce
m
en
t.
T
ask
Vid
eo
s
u
r
v
eillan
ce
is
u
tili
z
ed
in
th
e
f
ield
o
f
r
ec
o
g
n
itio
n
.
R
ec
o
g
n
izin
g
ev
e
n
ts
f
r
o
m
an
a
r
ea
o
f
i
n
ter
est
h
as
n
u
m
er
o
u
s
p
o
s
s
ib
le
ap
p
licatio
n
s
,
in
clu
d
in
g
b
u
t
n
o
t
lim
ited
to
tr
af
f
ic
an
aly
s
is
[
5
]
,
tr
ac
k
in
g
lim
ited
v
eh
icle
m
o
v
em
en
ts
,
a
n
d
a
n
aly
zin
g
m
u
lt
i
-
o
b
ject
in
ter
ac
tio
n
.
C
o
m
p
ar
ed
t
o
th
e
n
ee
d
f
o
r
co
n
tin
u
o
u
s
h
u
m
a
n
s
u
p
er
v
is
io
n
,
it
h
elp
s
s
o
lv
e
s
ev
er
al
p
r
o
b
le
m
s
.
T
h
e
f
ir
s
t
cr
u
cial
s
tep
in
th
is
ap
p
r
o
ac
h
is
to
d
eter
m
in
e
wh
eth
er
v
id
e
o
s
am
p
les
in
clu
d
e
m
o
tio
n
.
T
h
e
ap
p
r
o
a
ch
m
u
s
t
n
o
t
o
n
ly
b
e
f
r
ee
f
r
o
m
n
o
is
e,
b
u
t
it
m
u
s
t
al
s
o
s
eg
m
en
t
th
e
v
id
e
o
s
tr
ea
m
to
elim
in
ate
th
e
p
r
esen
ce
o
f
m
o
v
in
g
o
b
jects.
T
h
e
p
r
esen
ce
o
f
r
a
p
id
v
a
r
iatio
n
s
in
lig
h
t
in
ten
s
ity
,
s
u
ch
as
th
o
s
e
ca
u
s
ed
b
y
a
lig
h
t
s
witch
,
p
o
s
es
a
s
u
b
s
tan
tial
ch
allen
g
e
f
o
r
d
etec
tin
g
m
o
v
in
g
o
b
jects.
I
f
th
e
alg
o
r
ith
m
f
ail
s
to
co
p
e
with
v
ar
iatio
n
s
in
li
g
h
tin
g
an
d
ca
m
e
r
a
m
o
v
em
en
t,
it
will
r
esu
lt
in
th
e
in
clu
s
io
n
o
f
b
ac
k
g
r
o
u
n
d
n
o
i
s
e
in
th
e
f
in
al
o
u
tp
u
t
[
6
]
.
T
h
e
p
r
o
b
lem
wo
u
ld
b
e
wo
r
s
en
ed
b
y
d
y
n
am
ic
b
ac
k
g
r
o
u
n
d
s
,
wh
ic
h
wo
u
ld
en
ab
le
o
b
jects
to
m
o
v
e
ar
o
u
n
d
.
W
ea
th
er
v
ar
iatio
n
s
an
d
s
way
in
g
tr
ee
s
m
ay
cr
ea
te
in
a
cc
u
r
ate
r
esu
lts
d
u
r
in
g
t
h
e
d
et
ec
tin
g
s
tep
.
Alter
atio
n
s
in
s
ce
n
er
y
in
tr
o
d
u
ce
a
n
ad
d
itio
n
al
le
v
el
o
f
d
if
f
icu
lty
.
R
eg
ar
d
less
o
f
wh
eth
er
o
n
e
is
asleep
o
r
awa
k
e,
a
m
o
v
in
g
ite
m
h
as
t
h
e
p
o
ten
tial
to
m
o
m
en
tar
ily
h
alt
an
d
g
r
ad
u
ally
b
len
d
in
to
th
e
s
u
r
r
o
u
n
d
in
g
en
v
ir
o
n
m
en
t.
A
m
o
tio
n
d
ete
ctio
n
s
y
s
tem
s
h
o
u
ld
p
o
s
s
ess
th
e
ca
p
ab
ilit
y
to
ef
f
ec
t
iv
ely
n
av
ig
ate
t
h
r
o
u
g
h
th
ese
v
ar
io
u
s
h
u
r
d
les
[
7
]
.
T
h
e
v
id
e
o
s
u
r
v
eillan
ce
s
y
s
te
m
co
m
m
en
ce
s
[
8
]
with
t
h
e
d
etec
tio
n
o
f
m
o
tio
n
a
n
d
o
b
jec
ts
.
Mo
tio
n
d
etec
tio
n
in
v
o
l
v
es
th
e
p
r
o
ce
s
s
o
f
s
ep
ar
atin
g
t
h
e
ar
ea
s
o
f
a
n
im
ag
e
th
at
co
n
tain
m
o
v
in
g
o
b
jects
f
r
o
m
th
e
r
est
o
f
th
e
im
ag
e
.
B
ac
k
g
r
o
u
n
d
m
o
d
elin
g
a
n
d
m
o
tio
n
s
eg
m
e
n
tatio
n
ar
e
co
m
m
o
n
l
y
em
p
l
o
y
ed
in
t
h
e
task
o
f
d
etec
tin
g
m
o
tio
n
a
n
d
id
en
tify
in
g
o
b
jects.
I
n
an
im
ag
e
s
eq
u
en
ce
,
th
e
o
b
jectiv
e
o
f
m
o
tio
n
s
eg
m
en
tatio
n
is
to
id
en
tify
th
e
s
ec
tio
n
s
o
r
ar
ea
s
th
at
co
r
r
esp
o
n
d
to
m
o
v
i
n
g
o
b
je
cts,
s
u
ch
as
au
to
m
o
b
iles
,
b
ir
d
s
,
h
u
m
an
s
,
an
im
als,
an
d
s
o
o
n
[
9
]
.
W
h
en
m
o
tio
n
i
s
id
en
tifie
d
in
a
s
p
ec
if
ic
ar
ea
o
r
r
e
g
io
n
,
it
is
n
ec
ess
ar
y
to
s
t
u
d
y
t
h
ese
d
etec
ted
r
eg
io
n
s
f
o
r
f
u
r
th
er
p
r
o
ce
d
u
r
es su
ch
as
o
b
ject
tr
ac
k
in
g
an
d
b
e
h
av
io
r
a
n
aly
s
is
.
Fo
llo
win
g
th
e
p
r
o
ce
s
s
o
f
m
o
tio
n
an
d
o
b
ject
id
en
tific
atio
n
,
th
e
v
id
eo
s
u
r
v
eillan
ce
s
y
s
tem
ty
p
ically
tr
ac
es
th
e
m
o
v
em
en
t
o
f
o
b
jects
f
r
o
m
o
n
e
f
r
am
e
to
th
e
n
ex
t
in
a
s
eq
u
en
ce
o
f
im
ag
es.
B
eh
av
io
r
an
aly
s
is
en
tail
s
th
e
ex
am
in
atio
n
an
d
id
en
tific
atio
n
o
f
m
o
tio
n
p
atter
n
s
,
th
e
d
escr
ip
tio
n
o
f
ac
tio
n
s
,
an
d
t
h
e
r
elatio
n
s
h
ip
s
b
etwe
en
th
in
g
s
.
2.
RE
L
AT
E
D
WO
RK
Au
to
m
ated
ca
r
s
m
u
s
t
b
e
a
b
l
e
to
ac
ce
s
s
ac
cu
r
ate,
r
ea
l
-
ti
m
e
d
ata
o
n
th
e
s
tate
o
f
o
b
je
cts
in
th
eir
im
m
ed
iate
s
u
r
r
o
u
n
d
in
g
s
if
we
ar
e
to
g
u
ar
a
n
tee
s
af
e
d
r
iv
i
n
g
.
Ob
ject
o
cc
lu
s
io
n
,
clu
tter
in
ter
f
er
en
ce
,
a
n
d
a
lim
ited
s
en
s
o
r
-
d
etec
tin
g
ca
p
ab
ilit
y
p
r
o
d
u
ce
f
alse
alar
m
s
an
d
m
is
s
ed
o
b
ject
d
etec
tio
n
[
1
0
]
.
T
h
u
s
,
it
is
d
if
f
icu
lt
to
g
u
ar
a
n
tee
tr
ac
k
in
g
s
tab
ilit
y
an
d
s
tate
p
r
e
d
ictio
n
in
co
m
p
le
x
tr
af
f
ic
co
n
d
itio
n
s
.
B
ac
k
g
r
o
u
n
d
s
u
b
tr
ac
tio
n
[
1
1
]
r
eq
u
ir
es
a
tr
ain
in
g
s
eq
u
en
ce
d
ev
o
id
o
f
o
b
jects
to
co
n
s
tr
u
ct
a
b
ac
k
g
r
o
u
n
d
m
o
d
el,
in
co
n
tr
ast
to
o
b
ject
d
etec
to
r
s
,
wh
ich
r
eq
u
ir
e
in
s
ta
n
ce
s
th
at
h
av
e
b
ee
n
ex
p
licitly
tag
g
ed
to
tr
ai
n
a
b
in
a
r
y
class
if
ier
.
An
im
p
o
r
tan
t
s
tep
to
war
d
an
aly
tical
au
to
m
a
tio
n
is
o
b
ject
r
ec
o
g
n
itio
n
with
o
u
t
a
d
is
tin
ct
tr
ain
in
g
p
h
ase.
Attem
p
ts
to
s
o
lv
e
th
is
p
r
o
b
lem
b
y
an
aly
zin
g
m
o
tio
n
d
ata
h
av
e
b
ee
n
m
a
d
e.
A
p
o
p
u
lar
m
eth
o
d
f
o
r
d
etec
ti
n
g
m
o
v
in
g
o
b
jects
is
d
is
cr
im
in
ativ
e
m
o
d
elin
g
(
DM
)
,
wh
ich
s
ee
k
s
to
im
p
r
o
v
e
p
er
f
o
r
m
a
n
ce
in
f
o
r
eg
r
o
u
n
d
-
b
ac
k
g
r
o
u
n
d
s
ep
ar
atio
n
u
s
in
g
d
is
cr
im
in
ativ
e
f
ea
tu
r
es
an
d
well
-
d
esig
n
e
d
class
if
ier
s
[
1
2
]
.
B
ec
au
s
e
class
s
ep
ar
ab
ilit
y
is
ty
p
ically
p
o
o
r
in
ca
m
o
u
f
lag
ed
lo
ca
tio
n
s
,
DM
m
ay
f
ail
wh
en
co
n
f
r
o
n
ted
wit
h
th
e
ca
m
o
u
f
lag
e
p
r
o
b
lem
.
T
o
d
etec
t
f
o
r
eg
r
o
u
n
d
p
ix
els
th
at
h
av
e
b
ee
n
ca
m
o
u
f
l
ag
ed
,
we
p
r
esen
t
a
n
o
v
el
ap
p
r
o
ac
h
in
t
h
is
wo
r
k
:
ca
m
o
u
f
la
g
e
m
o
d
elin
g
(
C
M)
.
B
ec
au
s
e
o
f
th
e
two
-
p
ar
t
n
atu
r
e
o
f
ca
m
o
u
f
lag
e,
we
m
u
s
t r
ep
r
e
s
en
t b
o
th
th
e
f
o
r
eg
r
o
u
n
d
a
n
d
t
h
e
b
ac
k
d
r
o
p
.
An
in
n
o
v
ativ
e
f
r
am
ewo
r
k
t
h
at
in
co
r
p
o
r
ates
in
f
o
r
m
atio
n
a
b
o
u
t
co
lo
r
an
d
tex
t
u
r
e
h
as
b
ee
n
d
ev
elo
p
e
d
f
o
r
b
ac
k
d
r
o
p
m
o
d
eli
n
g
[
1
3
]
.
T
h
e
f
o
r
e
g
r
o
u
n
d
ch
o
ice
eq
u
atio
n
in
t
h
is
f
r
am
ewo
r
k
is
c
o
m
p
o
s
ed
o
f
th
r
ee
co
m
p
o
n
en
ts
:
th
e
lef
t
s
ec
tio
n
i
s
f
o
r
th
e
in
teg
r
atio
n
o
f
th
e
t
wo
p
ar
ts
,
th
e
r
ig
h
t
p
o
r
tio
n
is
f
o
r
th
e
in
f
o
r
m
atio
n
ab
o
u
t th
e
tex
tu
r
e
,
an
d
th
e
th
ir
d
p
ar
t is f
o
r
th
e
in
f
o
r
m
atio
n
a
b
o
u
t th
e
co
lo
r
.
T
h
e
u
s
e
o
f
th
is
s
tr
u
ctu
r
e
allo
ws y
o
u
to
tak
e
ad
v
an
tag
e
o
f
th
e
p
o
w
er
o
f
co
lo
r
an
d
tex
tu
r
e
wh
ile
av
o
id
in
g
th
e
d
o
wn
s
id
es
ass
o
c
iated
with
th
em
.
T
o
ac
ce
ler
ate
th
e
m
o
d
elin
g
o
f
th
e
b
ac
k
g
r
o
u
n
d
ev
e
n
m
o
r
e,
we
r
ec
o
m
m
en
d
u
s
in
g
a
b
lo
ck
-
b
ase
d
tech
n
iq
u
e.
T
o
b
e
m
o
r
e
s
p
ec
if
ic,
te
x
tu
r
e
in
f
o
r
m
a
tio
n
m
o
d
elin
g
is
d
is
tin
ct
f
r
o
m
th
e
tr
ad
itio
n
al
m
u
lti
-
h
is
to
g
r
a
m
m
o
d
el
f
o
r
b
lo
ck
-
b
ased
b
ac
k
g
r
o
u
n
d
m
o
d
elin
g
in
th
at
it
cr
ea
tes
a
s
in
g
le
h
is
to
g
r
am
m
o
d
el
f
o
r
ea
ch
b
lo
ck
.
T
h
is
m
o
d
el
co
n
tai
n
s
b
in
s
th
at
in
d
icate
th
e
o
cc
u
r
r
en
ce
p
r
o
b
ab
ilit
ies
o
f
v
a
r
io
u
s
p
atter
n
s
.
B
ased
o
n
t
h
is
p
r
o
ce
s
s
,
th
e
d
o
m
in
an
t
b
ac
k
g
r
o
u
n
d
p
atter
n
s
ar
e
s
elec
ted
to
d
eter
m
i
n
e
th
e
b
ac
k
g
r
o
u
n
d
lik
elih
o
o
d
o
f
u
p
co
m
in
g
b
lo
ck
s
.
A
n
o
v
e
l
m
eth
o
d
b
ased
o
n
f
u
zz
y
co
lo
r
d
if
f
er
en
ce
h
is
to
g
r
am
(
FC
DH)
h
as
b
ee
n
s
u
g
g
ested
to
in
co
r
p
o
r
ate
f
u
zz
y
c
-
m
ea
n
s
(
FC
M)
clu
s
ter
in
g
[
1
4
]
.
T
h
e
u
tili
za
tio
n
o
f
th
e
FC
M
clu
s
ter
in
g
tec
h
n
iq
u
e
in
C
DH
m
itig
ates
th
e
im
p
ac
t
o
f
in
ten
s
ity
v
ar
iatio
n
r
esu
ltin
g
f
r
o
m
f
ak
e
m
o
tio
n
o
r
c
h
an
g
es
in
b
ac
k
g
r
o
u
n
d
illu
m
in
atio
n
,
wh
il
e
also
r
ed
u
cin
g
th
e
s
u
b
s
tan
tial
co
m
p
lex
ity
o
f
th
e
co
m
p
u
tatio
n
'
s
h
is
to
g
r
am
b
in
s
.
T
h
e
s
u
g
g
ested
ap
p
r
o
ac
h
was
test
ed
u
s
in
g
v
ar
io
u
s
p
u
b
licly
ac
ce
s
s
ib
le
v
id
e
o
s
eq
u
en
ce
s
f
ea
tu
r
in
g
c
o
m
p
lex
s
ce
n
ar
io
s
.
T
h
e
m
eth
o
d
is
s
u
g
g
ested
b
ased
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
I
SS
N:
2722
-
2
5
8
6
P
erfo
r
ma
n
ce
co
mp
a
r
is
o
n
o
f o
p
tica
l flo
w
a
n
d
b
a
ck
g
r
o
u
n
d
s
u
b
tr
a
ctio
n
…
(
Mo
n
ika
S
h
a
r
ma
)
95
ex
tr
ac
tin
g
m
o
v
in
g
o
b
jects
f
r
o
m
a
f
r
am
e
s
eq
u
en
ce
,
h
en
ce
n
eith
er
h
u
m
an
in
ter
ac
tio
n
in
t
h
e
f
o
r
m
o
f
em
p
ir
ical
th
r
esh
o
ld
tu
n
in
g
,
n
o
r
b
ac
k
g
r
o
u
n
d
m
o
d
elin
g
with
wh
ich
o
th
er
s
y
s
tem
s
ar
e
b
u
ilt
ar
e
n
ec
ess
ar
y
[
1
5
]
.
T
h
e
s
u
g
g
ested
ap
p
r
o
ac
h
r
en
ts
o
u
t
m
o
v
in
g
o
b
jects
to
b
e
ex
tr
ac
te
d
with
o
u
t
u
s
in
g
an
y
o
f
th
em
.
T
h
e
s
alien
cy
m
ap
o
f
th
e
cu
r
r
en
t
f
r
am
e
with
co
m
p
le
te
r
eso
lu
tio
n
is
cr
ea
ted
b
y
u
s
e
o
f
th
e
co
n
s
tan
t sy
m
m
etr
ic
d
if
f
er
en
ce
b
etwe
en
th
e
f
r
am
es
ad
jace
n
t
to
th
e
p
r
esen
t
f
r
am
e.
Salien
cy
v
ar
iab
les
o
n
th
is
m
a
p
h
elp
t
o
h
i
g
h
lig
h
t
m
o
v
in
g
item
s
wh
ile
also
h
id
in
g
th
e
b
ac
k
d
r
o
p
.
An
im
ag
e
d
escr
ip
to
r
an
d
n
o
n
lin
ea
r
class
if
icatio
n
tech
n
iq
u
e
f
o
r
o
p
tical
f
lo
w
o
r
ien
tatio
n
an
d
a
h
is
to
g
r
am
-
b
ased
m
eth
o
d
h
av
e
b
ee
n
u
s
ed
to
ch
ar
ac
ter
ize
m
o
tio
n
i
n
f
o
r
m
atio
n
in
ea
c
h
v
id
eo
f
r
am
e
[
1
6
]
.
T
h
e
n
o
n
lin
ea
r
o
n
e
-
class
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
class
if
icatio
n
ap
p
r
o
ac
h
in
itially
lear
n
s
f
r
o
m
tr
ain
i
n
g
f
r
am
e
b
eh
av
io
r
t
o
id
en
tify
u
n
u
s
u
al
e
v
en
ts
in
th
e
cu
r
r
en
t
f
r
am
e.
T
h
e
o
p
tical
f
lo
w
ap
p
r
o
ac
h
b
eg
in
s
with
a
Gau
s
s
ian
f
ilter
to
r
em
o
v
e
n
o
is
e
f
r
o
m
e
ac
h
f
r
a
m
e
[
1
7
]
.
Nex
t,
it
ca
lc
u
lates
th
e
o
p
tical
f
lo
w
f
o
r
th
e
p
r
esen
t
f
r
am
e
th
e
p
r
ev
io
u
s
f
r
am
e
th
e
cu
r
r
e
n
t
f
r
am
e,
an
d
t
h
e
f
o
r
th
co
m
i
n
g
f
r
am
e.
Me
r
g
in
g
th
e
two
o
p
tica
l
f
lo
w
co
n
s
titu
en
ts
y
ield
s
th
e
g
r
o
s
s
o
p
tical
f
lo
w.
An
ad
ap
tiv
e
th
r
esh
o
ld
in
g
p
o
s
t
-
p
r
o
ce
s
s
in
g
p
h
ase
r
em
o
v
es
d
is
tr
ac
tin
g
f
o
r
eg
r
o
u
n
d
co
m
p
o
n
en
ts
.
Mo
r
p
h
o
l
o
g
ical
t
ec
h
n
iq
u
es
a
r
e
th
e
n
u
s
ed
to
th
e
eq
u
alize
d
o
u
t
p
u
t
t
o
lo
ca
te
m
o
v
in
g
item
s
.
T
h
e
m
eth
o
d
o
l
o
g
y
was
im
p
lem
en
te
d
,
d
ep
lo
y
ed
,
an
d
ev
alu
ated
o
n
n
u
m
er
o
u
s
au
th
en
tic
v
id
eo
d
at
asets
[
1
8
]
.
T
h
e
2
D
d
is
cr
ete
wav
elet
tr
an
s
f
o
r
m
(
D
W
T
)
an
d
v
ar
ian
ce
ap
p
r
o
ac
h
wer
e
u
s
ed
f
o
r
o
b
ject
d
etec
tio
n
an
d
tr
ac
k
i
n
g
[
1
9
]
.
An
ex
am
in
atio
n
o
f
th
e
p
r
o
p
o
s
ed
v
ar
ian
ce
-
b
ased
m
eth
o
d
f
o
r
o
b
ject
d
etec
tio
n
an
d
lo
ca
lizat
io
n
in
co
m
p
a
r
is
o
n
to
th
e
wid
ely
u
tili
ze
d
m
ea
n
-
s
h
if
t
m
eth
o
d
r
ev
ea
ls
th
at
th
e
l
atter
is
s
lo
wer
,
lead
in
g
to
s
lo
wer
item
d
etec
tio
n
o
v
er
all.
T
o
wr
ap
th
in
g
s
u
p
,
t
h
is
an
aly
s
is
h
elp
s
d
etec
t
an
d
tr
ac
k
m
o
v
in
g
o
b
jects
b
y
u
s
in
g
o
n
ly
t
h
e
b
an
d
p
ass
co
m
p
o
n
en
ts
o
f
th
e
2
D
-
DW
T
o
u
tp
u
ts
.
T
h
e
Dau
b
ec
h
ies
co
m
p
lex
wav
elet
t
r
an
s
f
o
r
m
is
well
-
s
u
ited
f
o
r
tr
ac
k
in
g
b
ec
au
s
e
o
f
its
ap
p
r
o
x
im
ate
s
h
if
t
-
in
v
ar
ian
ce
p
r
o
p
er
ty
.
T
h
e
r
ec
o
m
m
en
d
e
d
m
eth
o
d
ca
n
p
er
f
o
r
m
o
b
ject
s
eg
m
en
tatio
n
f
r
o
m
s
ce
n
es
[
2
0
]
.
Fo
llo
win
g
t
h
e
in
itial
s
eg
m
en
tatio
n
o
f
th
e
f
ir
s
t
f
r
am
e,
ac
h
iev
ed
th
r
o
u
g
h
th
e
co
m
p
u
tatio
n
o
f
m
u
ltis
ca
le
co
r
r
elatio
n
o
f
th
e
im
a
g
in
ar
y
co
m
p
o
n
en
t
o
f
co
m
p
le
x
wav
e
let
co
ef
f
icien
ts
,
th
e
s
u
b
s
eq
u
en
t
f
r
am
es
tr
ac
k
th
e
o
b
ject
b
y
ca
lcu
latin
g
th
e
en
e
r
g
y
o
f
th
e
co
m
p
le
x
wav
elet
co
ef
f
icien
ts
ass
ig
n
ed
to
th
e
o
b
ject'
s
r
eg
io
n
a
n
d
co
m
p
ar
in
g
it
to
th
e
en
er
g
y
o
f
th
e
s
u
r
r
o
u
n
d
in
g
r
e
g
io
n
.
T
h
e
r
esear
ch
g
a
p
is
in
th
e
id
en
tific
atio
n
o
f
s
u
itab
le
m
et
h
o
d
s
f
o
r
s
p
ec
if
ic
o
b
ject
d
ete
ctio
n
p
r
o
b
lem
s
.
O
p
tical
f
lo
w
p
r
o
v
id
es
th
e
m
o
s
t
ac
cu
r
ate
an
d
d
etailed
m
o
tio
n
d
ata,
b
u
t
it
is
also
th
e
m
o
s
t
co
m
p
u
tatio
n
ally
ex
p
en
s
iv
e.
B
ac
k
g
r
o
u
n
d
s
u
b
tr
ac
tio
n
u
s
u
ally
wo
r
k
s
well
wh
e
n
u
s
e
d
in
r
ea
l
-
tim
e
s
ce
n
ar
io
s
with
well
-
m
ain
tain
ed
b
ac
k
d
r
o
p
m
o
d
els.
T
o
en
s
u
r
e
its
ef
f
icac
y
in
m
o
tio
n
d
etec
tio
n
,
ad
d
itio
n
al
p
r
o
ce
s
s
in
g
m
ay
b
e
n
ec
ess
ar
y
af
ter
u
s
in
g
t
h
e
DW
T
,
wh
ich
p
r
o
v
id
es
a
u
n
iq
u
e
t
y
p
e
o
f
in
f
o
r
m
atio
n
.
3.
M
E
T
H
O
DS
I
d
en
tific
atio
n
a
n
d
tr
ac
k
i
n
g
o
b
j
ec
ts
th
at
ar
e
in
m
o
tio
n
i
n
p
h
o
t
o
s
o
r
v
id
e
o
s
is
a
f
u
n
d
am
e
n
tal
task
in
th
e
f
ield
o
f
co
m
p
u
ter
v
is
io
n
.
T
h
is
task
h
as
a
wid
e
r
an
g
e
o
f
a
p
p
licatio
n
s
,
in
clu
d
in
g
s
u
r
v
eillan
ce
,
au
to
n
o
m
o
u
s
d
r
iv
in
g
,
an
d
h
u
m
a
n
-
co
m
p
u
te
r
in
ter
ac
tio
n
.
Var
io
u
s
m
eth
o
d
o
lo
g
ies
an
d
s
tr
ateg
ies
ar
e
em
p
lo
y
ed
f
o
r
th
e
d
etec
tio
n
o
f
m
o
v
in
g
o
b
jects.
B
elo
w
ar
e
m
an
y
f
r
e
q
u
en
tly
e
m
p
lo
y
ed
tec
h
n
iq
u
es.
T
h
e
co
m
m
o
n
s
tep
s
f
o
r
o
b
ject
d
etec
tio
n
ar
e
g
i
v
en
in
Fig
u
r
e
1
.
Fig
u
r
e
1
.
Step
s
in
o
b
ject
d
etec
tio
n
in
im
ag
e
a
n
d
v
id
eo
C
o
m
p
u
ter
v
is
io
n
ca
n
d
etec
t
o
b
jects
in
v
id
eo
o
r
s
till
im
ag
es.
Pre
p
r
o
ce
s
s
in
g
th
e
im
ag
e
b
ef
o
r
e
f
ee
d
in
g
it
to
an
o
b
ject
d
etec
tio
n
m
o
d
el
is
p
o
s
s
ib
le.
Scalin
g
o
r
n
o
r
m
al
izin
g
p
ix
el
v
al
u
es
m
ay
b
e
n
ee
d
ed
to
m
ee
t
m
o
d
el
in
p
u
t
r
e
q
u
ir
em
e
n
ts
.
Ma
th
em
at
ical
m
o
d
els
h
elp
o
b
ject
d
etec
ti
o
n
m
o
d
els
ex
tr
ac
t
f
ea
t
u
r
es.
T
h
ese
n
etwo
r
k
s
lear
n
h
ier
ar
ch
ical
ch
ar
ac
ter
is
tics
f
r
o
m
p
h
o
to
s
to
d
is
tin
g
u
is
h
th
in
g
s
.
L
o
ca
lizin
g
o
b
jects
in
an
im
ag
e
is
as
cr
u
cial
as
I
n
p
u
t
I
m
ag
e
Ob
j
ec
t
r
ec
o
g
n
itio
n
I
m
ag
e
C
lass
if
icatio
n
Ob
j
ec
t
L
o
ca
lizatio
n
Ob
j
ec
t
Dete
ctio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
2
5
8
6
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
1
4
,
No
.
1
,
Ma
r
ch
20
2
5
:
93
-
1
0
2
96
ca
teg
o
r
izin
g
th
e
m
f
o
r
o
b
ject
d
etec
tio
n
.
Pre
d
ictin
g
b
o
u
n
d
in
g
b
o
x
es
th
at
s
ec
u
r
ely
c
o
n
tain
item
s
o
f
in
ter
est
is
co
m
m
o
n
.
T
h
e
m
o
d
el
class
if
ies
all
o
b
s
er
v
ab
le
elem
en
ts
af
ter
o
b
ject
lo
ca
lizatio
n
.
Po
s
t
-
p
r
o
c
ess
in
g
is
d
o
n
e
af
ter
ca
teg
o
r
izatio
n
r
e
f
in
es r
esu
lts
.
3
.
1
.
B
a
c
k
g
ro
un
d
s
ub
t
ra
ct
io
n
On
e
o
f
th
e
m
o
s
t
u
s
ed
an
d
tim
e
-
test
ed
m
eth
o
d
s
f
o
r
f
in
d
i
n
g
m
o
v
in
g
o
b
jects
in
m
o
v
ies
o
r
p
ictu
r
e
s
eq
u
en
ce
s
is
b
ac
k
g
r
o
u
n
d
r
e
m
o
v
al.
Sep
ar
atin
g
th
e
m
o
v
i
n
g
f
o
r
eg
r
o
u
n
d
item
s
f
r
o
m
th
e
s
till
b
ac
k
g
r
o
u
n
d
is
th
e
f
u
n
d
am
e
n
tal
p
r
in
cip
le
o
f
b
ac
k
g
r
o
u
n
d
s
u
b
tr
ac
tio
n
[
2
1
]
.
B
ac
k
g
r
o
u
n
d
s
tatics
p
r
esu
p
p
o
s
es
th
a
t
th
e
b
ac
k
g
r
o
u
n
d
is
alwa
y
s
ch
an
g
in
g
at
a
s
lo
w
p
ac
e.
Fo
r
ex
am
p
le,
th
is
co
u
ld
b
e
a
s
tatic
v
iew
f
r
o
m
a
s
u
r
v
eillan
ce
ca
m
er
a
s
h
o
win
g
a
d
eser
ted
co
r
r
id
o
r
.
C
h
an
g
es
t
o
th
e
b
ac
k
d
r
o
p
o
v
er
tim
e
ar
e
co
n
s
id
er
ed
b
y
th
e
d
y
n
a
m
ic
b
a
ck
g
r
o
u
n
d
.
Su
ch
as
in
n
atu
r
al
s
ettin
g
s
wh
er
e
th
e
s
u
n
,
clo
u
d
s
,
an
d
s
h
ad
o
ws
all
p
lay
a
r
o
le
in
cr
ea
tin
g
v
ar
y
in
g
d
eg
r
ee
s
o
f
illu
m
in
atio
n
.
I
n
th
is
ty
p
e
o
f
m
o
d
el,
ea
ch
p
ix
el
i
n
th
e
b
ac
k
g
r
o
u
n
d
is
r
ep
r
esen
ted
b
y
a
s
tatis
tical
m
o
d
el.
T
h
ese
m
o
d
els
ca
n
b
e
co
d
eb
o
o
k
m
o
d
els
o
r
n
o
n
-
p
ar
am
etr
ic
m
o
d
el
s
.
T
h
e
in
itializatio
n
o
f
th
e
b
a
ck
g
r
o
u
n
d
m
o
d
el
is
d
o
n
e
u
s
in
g
th
e
in
itial
f
r
am
es
o
f
th
e
f
ilm
o
r
s
er
ies.
Fo
r
d
y
n
am
ic
b
ac
k
g
r
o
u
n
d
s
to
ad
ju
s
t
to
s
m
all
b
u
t
n
o
ticea
b
le
ch
an
g
es
in
th
e
s
ce
n
e,
th
e
b
ac
k
d
r
o
p
m
o
d
el
is
r
ef
r
esh
ed
p
er
i
o
d
ically
.
T
o
f
in
d
ar
ea
s
o
r
p
ix
el
s
th
at
ar
e
d
r
asti
ca
lly
d
if
f
er
en
t
f
r
o
m
th
e
b
ac
k
d
r
o
p
,
th
e
b
ac
k
g
r
o
u
n
d
m
o
d
el
is
co
m
p
ar
e
d
with
ea
c
h
n
ew
f
r
am
e.
T
u
n
in
g
th
e
b
ac
k
g
r
o
u
n
d
m
o
d
el
s
ettin
g
s
is
cr
u
cial
f
o
r
o
p
tim
al
p
er
f
o
r
m
an
ce
in
d
iv
e
r
s
e
s
ce
n
ar
io
s
.
E
x
am
p
les
o
f
th
ese
p
ar
am
eter
s
ar
e
th
e
th
r
esh
o
ld
f
o
r
f
o
r
e
g
r
o
u
n
d
d
etec
tio
n
an
d
th
e
lear
n
in
g
r
ate
f
o
r
m
o
d
el
u
p
d
ates.
R
ea
l
-
tim
e
p
r
o
ce
s
s
in
g
o
f
h
ig
h
-
r
eso
lu
tio
n
v
id
eo
f
ee
d
s
ca
n
b
e
d
if
f
icu
lt
d
u
e
to
c
o
m
p
u
tatio
n
ally
e
x
p
en
s
iv
e
b
ac
k
g
r
o
u
n
d
s
u
b
tr
ac
tio
n
p
r
o
ce
d
u
r
es.
Mu
lti
-
m
o
d
al
a
p
p
r
o
ac
h
es
u
s
e
d
ep
th
a
n
d
co
l
o
r
ed
d
ata
t
o
im
p
r
o
v
e
b
a
ck
g
r
o
u
n
d
m
o
d
els.
A
co
m
m
o
n
m
eth
o
d
f
o
r
d
etec
t
in
g
m
o
v
in
g
o
b
jects
u
s
in
g
b
ac
k
g
r
o
u
n
d
s
u
b
tr
ac
tio
n
is
to
co
m
p
ar
e
ea
ch
p
ix
el
in
th
e
cu
r
r
en
t f
r
am
e
o
f
t
h
e
v
id
eo
s
er
ies with
a
m
o
d
el
o
f
th
e
b
ac
k
g
r
o
u
n
d
.
T
h
e
f
u
n
d
am
e
n
tal
id
ea
s
an
d
eq
u
atio
n
s
o
f
b
ac
k
g
r
o
u
n
d
s
u
b
tr
ac
tio
n
ar
e
p
r
esen
ted
h
er
e.
T
h
e
in
itializatio
n
o
f
th
e
b
ac
k
g
r
o
u
n
d
m
o
d
el
I
b
(
,
,
t)
f
o
r
p
ix
el
(
,
)
at
tim
e
t
t
is
ac
co
m
p
lis
h
ed
b
y
u
tili
zin
g
t
h
e
in
itial
f
r
am
es
o
f
th
e
v
id
eo
s
er
ies.
T
h
is
ca
n
b
e
d
o
n
e
with
s
im
p
le
av
er
ag
in
g
as we
ll a
s
m
o
r
e
ad
v
an
ce
d
m
eth
o
d
s
lik
e
g
au
s
s
ian
m
ix
tu
r
e
m
o
d
els
(
GM
M)
.
(
,
,
)
=
(
1
−
)
(
,
,
−
1
)
+
.
(
,
,
)
(
1
)
(
,
,
)
d
en
o
tes
th
e
b
ac
k
g
r
o
u
n
d
m
o
d
el,
(
,
,
)
d
en
o
tes
th
e
co
l
o
r
in
te
n
s
ity
o
f
th
e
im
ag
e
(
x
,
y
)
in
th
e
‘
t’
f
r
am
e
o
r
cu
r
r
e
n
t f
r
am
e
,
an
d
k
is
th
e
lear
n
in
g
r
ate
(
0
<
k
<
1
)
.
T
h
e
cu
r
r
e
n
t
f
r
am
e'
s
ab
s
o
lu
te
d
if
f
er
en
ce
(
o
r
o
t
h
er
m
etr
ics
lik
e
s
q
u
ar
ed
d
i
f
f
er
en
ce
)
f
r
o
m
t
h
e
p
r
ev
io
u
s
f
r
am
e
ca
n
b
e
u
s
ed
to
id
en
tify
item
s
in
th
e
f
o
r
e
g
r
o
u
n
d
(
(
,
,
)
.
(
,
,
)
=
|
(
,
,
)
−
(
,
,
)
|
(
2
)
T
h
e
r
esu
lts
im
ag
e
af
ter
th
r
esh
o
ld
co
m
p
ar
is
o
n
is
g
iv
en
as.
I
t
is
u
s
ed
to
class
if
y
th
at
im
ag
e
b
elo
n
g
s
to
th
e
b
ac
k
g
r
o
u
n
d
r
eg
i
o
n
o
r
f
o
r
eg
r
o
u
n
d
r
e
g
io
n
.
(
,
,
)
=
{
1
if
(
,
,
)
>
0
if
(
,
,
)
<
(
3
)
T
o
elim
in
ate
n
o
is
e
m
o
r
p
h
o
lo
g
ical
o
p
er
atio
n
s
s
u
ch
as
er
o
s
io
n
an
d
d
ilatio
n
ca
n
b
e
a
p
p
lie
d
to
g
et
th
e
m
ask
ed
im
ag
e.
T
h
e
lear
n
in
g
r
ate
α
is
m
o
d
if
ied
v
ia
ad
a
p
tiv
e
a
p
p
r
o
ac
h
es
ac
co
r
d
in
g
to
th
e
s
ize
o
f
th
e
p
ix
el
d
if
f
er
en
ce
s
to
ac
co
m
m
o
d
ate
d
if
f
e
r
en
t le
v
e
ls
o
f
s
ce
n
e
d
y
n
a
m
ics
3
.
2
.
O
ptic
a
l
f
lo
w
m
et
ho
d
R
ec
en
t
ad
v
an
ce
m
en
ts
in
co
m
p
u
ter
v
is
io
n
r
esear
ch
h
av
e
en
ab
led
r
o
b
o
ts
to
s
en
s
e
th
eir
s
u
r
r
o
u
n
d
in
g
s
th
r
o
u
g
h
tech
n
iq
u
es su
ch
as se
m
an
tic
s
eg
m
en
tatio
n
,
wh
ich
cl
ass
if
ies
p
ix
els b
ased
o
n
th
eir
m
ea
n
in
g
,
an
d
o
b
ject
id
en
tific
atio
n
,
wh
ich
id
en
tifie
s
in
s
tan
ce
s
o
f
a
ce
r
tain
o
b
ject
c
lass
[
2
2
]
.
Ho
wev
er
,
m
an
y
o
f
t
h
ese
alg
o
r
ith
m
s
d
o
n
o
t
co
n
s
id
er
th
e
tim
e
in
f
o
r
m
atio
n
(
t)
wh
en
p
r
o
ce
s
s
in
g
r
ea
l
-
tim
e
v
id
eo
in
p
u
t.
I
n
s
tead
,
th
ey
s
o
lely
f
o
cu
s
o
n
an
aly
zin
g
th
e
r
elatio
n
s
h
ip
s
b
e
twee
n
o
b
jects
in
s
id
e
th
e
s
am
e
f
r
am
e
(
x
,
y
)
.
Fo
r
ea
c
h
r
u
n
,
th
ey
co
n
s
id
er
ea
c
h
f
r
am
e
as
a
n
in
d
i
v
id
u
al
im
a
g
e
an
d
r
ea
s
s
ess
it
ac
co
r
d
in
g
ly
.
T
o
id
en
tif
y
ar
ea
s
o
f
m
o
tio
n
i
n
a
p
ictu
r
e,
o
p
tical
f
lo
w
m
eth
o
d
s
lo
o
k
at
th
e
v
ec
to
r
s
o
f
a
m
o
v
i
n
g
o
b
ject'
s
m
o
tio
n
ac
r
o
s
s
tim
e
[
2
3
]
.
T
h
e
o
p
t
ical
f
lo
w
h
as
b
ee
n
em
p
lo
y
ed
b
y
m
an
y
r
esear
ch
e
r
s
.
I
n
v
id
eo
s
eq
u
e
n
ce
s
,
o
b
ject
s
ca
n
b
e
d
etec
ted
u
s
in
g
th
e
o
p
tical
f
lo
w
m
eth
o
d
ev
en
wh
en
t
h
e
ca
m
er
a
is
in
m
o
tio
n
.
T
h
is
th
e
o
r
y
is
d
er
i
v
ed
f
r
o
m
th
e
co
n
s
en
s
u
s
o
f
o
p
tical
s
ig
n
al
p
r
o
ce
s
s
in
g
.
(
,
,
)
=
(
+
∆
,
+
∆
,
+
∆
)
(
4
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
I
SS
N:
2722
-
2
5
8
6
P
erfo
r
ma
n
ce
co
mp
a
r
is
o
n
o
f o
p
tica
l flo
w
a
n
d
b
a
ck
g
r
o
u
n
d
s
u
b
tr
a
ctio
n
…
(
Mo
n
ika
S
h
a
r
ma
)
97
(
+
∆
,
+
∆
,
+
∆
)
=
(
,
,
)
+
∆
+
∆
+
∆
+
⋯
ℎ
(
5
)
B
y
ex
clu
d
in
g
h
ig
h
e
r
-
o
r
d
er
ter
m
s
,
th
e
eq
u
atio
n
is
s
im
p
lifie
d
in
f
o
r
m
s
o
f
(
6
)
to
(
9
)
.
∆
+
∆
+
∆
=
0
(
6
)
(
∆
∆
)
+
(
∆
∆
)
+
(
∆
∆
)
=
0
(
7
)
+
+
=
0
(
8
)
+
=
−
(
9
)
V
px
,
V
py
,
an
d
V
pt
d
en
o
te
th
e
v
elo
city
o
r
o
p
tical
f
lo
w
v
ec
to
r
s
,
I
px
,
I
py,
an
d
I
py
s
h
o
w
th
e
v
ar
ian
ts
o
f
th
e
im
ag
e
in
ten
s
ities
at
a
co
o
r
d
in
ate
in
t
h
e
f
o
r
m
o
f
d
er
iv
ativ
es
f
o
r
th
e
im
ag
e
I
m
(
x
,
y
,
t)
.
B
y
em
p
l
o
y
i
n
g
th
e
ap
p
r
o
ac
h
o
f
th
r
esh
o
ld
in
g
to
d
er
iv
e
th
e
m
o
tio
n
v
ec
to
r
f
o
r
o
b
ject
d
et
ec
tio
n
.
T
h
e
m
ag
n
itu
d
e
o
f
t
h
e
m
o
tio
n
v
ec
to
r
is
p
r
esen
ted
as
(
1
0
)
.
=
√
2
+
2
(
1
0
)
Op
tical
f
lo
w
v
ec
to
r
s
,
in
th
ei
r
m
o
s
t
f
u
n
d
am
en
tal
f
o
r
m
,
p
r
o
v
id
e
i
n
p
u
t
t
o
a
lar
g
e
v
ar
i
ety
o
f
h
ig
h
er
-
lev
el
o
p
er
atio
n
s
th
at
n
ee
d
s
ce
n
e
aw
ar
en
ess
o
f
v
i
d
eo
s
eq
u
en
ce
s
.
T
h
ese
ac
tiv
ities
ar
e
n
ec
ess
ar
y
f
o
r
p
r
o
p
er
o
p
er
atio
n
.
T
h
e
o
p
tical
f
lo
w
m
eth
o
d
en
s
u
r
es
o
b
ject
v
elo
city
ac
r
o
s
s
co
n
s
ec
u
tiv
e
f
r
am
es
u
s
in
g
th
e
ap
p
ar
en
t
m
o
tio
n
o
f
b
r
ig
h
tn
ess
p
atter
n
s
in
a
p
ictu
r
e
.
3
.
3
.
DWT
t
ra
ns
f
o
rm
T
h
e
ab
ilit
y
o
f
th
e
DW
T
to
ca
p
tu
r
e
s
ig
n
als
at
m
an
y
r
eso
lu
tio
n
s
an
d
ac
cu
r
ately
lo
ca
lize
th
em
in
th
e
tim
e
-
f
r
eq
u
e
n
cy
d
o
m
ain
m
a
k
e
s
it
a
cr
u
cial
to
o
l
f
o
r
o
b
ject
d
etec
tio
n
an
d
t
r
ac
k
in
g
.
W
h
en
an
aly
zin
g
d
ata
at
m
u
ltip
le
r
eso
lu
tio
n
s
,
th
e
DW
T
is
u
s
ed
to
b
r
ea
k
d
o
wn
a
n
in
p
u
t
s
ig
n
al
in
t
o
v
ar
i
o
u
s
f
r
e
q
u
en
cy
b
an
d
s
.
E
ac
h
f
r
eq
u
e
n
cy
b
an
d
co
r
r
esp
o
n
d
s
t
o
a
s
p
ec
if
ic
s
ca
le.
T
h
is
en
ab
les
th
e
s
im
u
ltan
eo
u
s
ex
am
in
atio
n
o
f
m
an
y
lev
els
o
f
s
ig
n
als
u
tili
zin
g
o
b
ject
d
etec
tio
n
tech
n
iq
u
es.
T
h
is
en
ab
les
th
e
ef
f
ec
tiv
e
r
etr
ie
v
al
o
f
c
h
ar
ac
ter
is
tics
(
s
u
ch
as
s
h
ap
es,
p
atter
n
s
,
an
d
b
o
u
n
d
ar
i
es)
at
d
if
f
er
en
t
lev
els,
wh
ic
h
i
s
b
en
ef
icial
i
n
th
e
id
e
n
tific
atio
n
a
n
d
m
o
n
it
o
r
in
g
o
f
o
b
jects.
T
h
e
ef
f
icien
t
im
p
l
em
en
tatio
n
o
f
DW
T
en
ab
les
it
to
h
an
d
le
la
r
g
e
am
o
u
n
ts
o
f
d
ata
in
r
ea
l
-
tim
e
ap
p
licatio
n
s
[
2
4
]
.
I
t
is
cr
u
cial
f
o
r
tr
ac
k
in
g
a
n
d
o
b
ject
d
etec
t
io
n
s
y
s
tem
s
to
o
p
er
ate
in
d
y
n
am
ic
en
v
ir
o
n
m
en
ts
an
d
r
e
q
u
ir
e
r
ap
i
d
d
ec
is
io
n
-
m
a
k
in
g
.
T
h
e
DW
T
is
a
v
alu
a
b
le
t
o
o
l
to
esti
m
ate
m
o
tio
n
b
etwe
e
n
f
r
a
m
es
in
a
v
i
d
eo
s
er
ies.
E
v
alu
atin
g
th
e
wav
elet
co
ef
f
icien
ts
ac
r
o
s
s
f
r
am
es
en
ab
les
th
e
esti
m
atio
n
o
f
m
o
tio
n
v
ec
to
r
s
,
wh
ich
is
cr
u
cial
f
o
r
o
b
ject
tr
ac
k
i
n
g
ac
r
o
s
s
tim
e.
T
h
e
DW
T
)
is
a
m
ath
em
atica
l
tech
n
iq
u
e
u
s
ed
to
p
r
o
ce
s
s
an
d
an
aly
ze
d
ata,
esp
ec
ially
p
h
o
to
s
[
2
5
]
.
T
h
e
DW
T
d
iv
id
es
an
im
a
g
e
i
n
to
s
ep
ar
ate
f
r
eq
u
e
n
cy
co
m
p
o
n
en
ts
th
at
d
if
f
er
in
s
ca
le,
en
ab
lin
g
th
e
ex
am
in
atio
n
o
f
s
ev
er
al
r
eso
lu
tio
n
s
[
2
6
]
.
T
h
e
f
o
r
war
d
2
D
DW
T
o
f
an
I
m
ag
e
I
m
(
x
,
y
)
is
d
ec
o
m
p
o
s
ed
with
d
im
en
s
io
n
s
×
in
to
lo
w
-
f
r
e
q
u
en
c
y
a
p
p
r
o
x
im
atio
n
co
ef
f
icien
ts
an
d
h
i
g
h
-
f
r
e
q
u
en
c
y
d
etail
co
ef
f
icien
ts
at
v
a
r
io
u
s
s
ca
les.
T
h
e
im
ag
e
is
d
ec
o
m
p
o
s
ed
in
L
L
,
L
H,
HL
,
an
d
HH
f
r
eq
u
e
n
cy
b
an
d
s
[
2
7
]
.
T
h
e
m
ath
em
atica
l e
q
u
atio
n
s
f
o
r
th
e
s
am
e
to
p
r
esen
t 2
D
-
DW
T
ar
e
g
iv
en
as
f
o
llo
ws.
−
Ap
p
r
o
x
im
atio
n
co
e
f
f
icien
t e
q
u
atio
n
=
∑
∑
ℎ
[
]
.
ℎ
[
]
.
[
2
,
2
]
/
2
−
1
=
0
/
2
−
1
=
0
(
1
1
)
−
Ho
r
izo
n
tal
elem
en
t c
o
ef
f
icien
t
eq
u
atio
n
=
∑
∑
ℎ
[
]
.
ℎ
[
]
.
[
2
,
2
+
1
]
/
2
−
1
=
0
/
2
−
1
=
0
(
1
2
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
2
5
8
6
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
1
4
,
No
.
1
,
Ma
r
ch
20
2
5
:
93
-
1
0
2
98
−
Ver
tical
elem
en
t c
o
ef
f
icien
t e
q
u
atio
n
=
∑
∑
ℎ
[
]
.
ℎ
[
]
.
[
2
+
1
,
2
]
/
2
−
1
=
0
/
2
−
1
=
0
(
1
3
)
−
Diag
o
n
al
elem
en
t
co
e
f
f
icien
t
eq
u
atio
n
=
∑
∑
ℎ
[
]
.
ℎ
[
]
.
[
2
+
1
,
2
+
1
]
/
2
−
1
=
0
/
2
−
1
=
0
(
1
4
)
Fig
u
r
e
2
p
r
esen
ts
th
e
DW
T
im
ag
e
d
ec
o
m
p
o
s
itio
n
a
n
d
le
v
e
l
p
r
o
ce
s
s
in
g
.
Ap
p
ly
in
g
f
ilter
s
in
b
o
th
th
e
h
o
r
izo
n
tal
an
d
v
e
r
tical
ax
es
s
ep
ar
ates
[
2
8
]
t
h
e
im
a
g
e
in
t
o
d
if
f
er
en
t
f
r
eq
u
en
cy
co
m
p
o
n
e
n
t
s
in
a
2
-
lev
el
DW
T
d
ec
o
m
p
o
s
itio
n
.
T
h
e
d
ec
o
m
p
o
s
itio
n
p
r
o
ce
s
s
p
r
o
d
u
ce
s
d
etail
co
ef
f
icien
ts
th
at
ca
p
tu
r
e
h
ig
h
-
f
r
e
q
u
en
c
y
in
f
o
r
m
atio
n
in
th
e
h
o
r
izo
n
tal,
v
er
tical,
a
n
d
d
iag
o
n
al
d
im
e
n
s
io
n
s
,
as
well
as
ap
p
r
o
x
im
a
tio
n
co
e
f
f
icien
ts
at
v
ar
io
u
s
r
eso
lu
tio
n
s
(
lev
els)
[
2
9
]
.
Ob
ject
d
etec
tio
n
a
n
d
tr
ac
k
in
g
,
co
m
p
r
ess
io
n
,
an
d
d
en
o
is
i
n
g
ar
e
ju
s
t
a
f
ew
o
f
th
e
m
an
y
im
a
g
e
-
p
r
o
ce
s
s
in
g
ap
p
licatio
n
s
th
at
b
en
ef
it f
r
o
m
th
i
s
m
u
lti
-
r
eso
lu
tio
n
r
ep
r
esen
tatio
n
[
3
0
]
.
Fig
u
r
e
2
.
DW
T
im
ag
e
d
ec
o
m
p
o
s
itio
n
an
d
lev
el
p
r
o
ce
s
s
in
g
4.
RE
SU
L
T
S
AND
D
I
SCU
SS
I
O
N
W
e
u
s
ed
MA
T
L
AB
2
0
2
3
to
a
n
aly
ze
th
e
im
ag
e'
s
r
esp
o
n
s
e
ti
m
e.
T
ab
le
1
p
r
o
v
id
es
th
e
s
p
ec
if
ics
o
f
th
e
r
esp
o
n
s
e
tim
es
r
eq
u
ir
ed
b
y
t
h
ese
s
im
u
latio
n
s
o
f
all
alg
o
r
ith
m
s
.
I
n
T
a
b
le
2
,
th
e
o
u
tco
m
es
o
f
t
h
e
alg
o
r
ith
m
'
s
s
im
u
latio
n
r
u
n
o
n
t
h
e
au
th
o
r
'
s
ca
m
er
a'
s
r
an
d
o
m
s
till
im
ag
es
an
d
m
o
v
in
g
v
id
eo
.
MA
T
L
AB
s
im
p
lifie
s
th
e
u
tili
za
tio
n
o
f
GPU
ac
ce
ler
ati
o
n
f
o
r
co
m
p
u
tatio
n
ally
in
ten
s
iv
e
task
s
,
s
u
ch
as
d
ee
p
lea
r
n
in
g
-
b
ased
o
b
ject
d
etec
tio
n
.
Utilizin
g
GPUs
in
p
r
o
ce
s
s
in
g
,
as
o
p
p
o
s
ed
to
r
ely
in
g
s
o
lely
o
n
C
PUs
,
ca
n
g
r
ea
tly
r
ed
u
ce
r
esp
o
n
s
e
tim
es,
h
en
ce
en
ab
lin
g
f
aster
i
n
f
er
en
ce
s
p
ee
d
s
.
T
h
e
r
esp
o
n
s
e
tim
e
o
f
MA
T
L
AB
o
b
ject
d
etec
tio
n
m
eth
o
d
s
is
cr
u
cial
f
o
r
ac
h
ie
v
in
g
r
ea
l
-
ti
m
e
p
er
f
o
r
m
a
n
ce
in
v
ar
io
u
s
ap
p
licatio
n
s
,
o
p
tim
izin
g
alg
o
r
ith
m
s
elec
tio
n
a
n
d
im
p
lem
en
tatio
n
,
lev
er
a
g
in
g
h
ar
d
war
e
ca
p
a
b
ilit
ies,
f
ac
ili
tatin
g
iter
ativ
e
d
ev
elo
p
m
e
n
t,
en
h
an
cin
g
u
s
er
ex
p
er
ien
ce
,
a
n
d
id
en
tif
y
in
g
o
p
tim
izatio
n
o
p
p
o
r
tu
n
ities
.
Ob
j
ec
t
d
etec
tio
n
s
y
s
tem
s
ca
n
m
ee
t
th
e
p
er
f
o
r
m
a
n
ce
r
eq
u
ir
em
e
n
ts
o
f
th
eir
in
ten
d
e
d
ap
p
licatio
n
s
wh
en
th
ey
ef
f
ec
tiv
ely
m
an
ag
e
r
esp
o
n
s
e
tim
e.
T
ab
le
1
p
r
esen
ts
th
e
s
im
u
latio
n
r
esp
o
n
s
e
tim
e
o
f
th
e
d
if
f
er
en
t a
l
g
o
r
ith
m
s
u
s
ed
f
o
r
o
b
ject
d
etec
tio
n
.
I
n
d
etec
tin
g
an
d
tr
ac
k
in
g
m
o
v
in
g
o
b
jects,
th
e
th
r
ee
p
r
im
ar
y
m
etr
ics
th
at
s
h
ed
lig
h
t
o
n
t
h
e
s
y
s
tem
'
s
ef
f
icien
cy
,
d
e
p
en
d
a
b
ilit
y
,
an
d
r
esil
ien
ce
in
d
if
f
er
en
t
r
ea
l
-
wo
r
ld
co
n
tex
ts
ar
e
s
p
ec
if
ici
ty
,
s
en
s
itiv
ity
,
an
d
ac
cu
r
ac
y
.
T
h
e
ac
cu
r
ac
y
with
wh
ich
th
e
s
y
s
tem
ca
n
i
d
en
tify
wh
ich
p
ix
els
o
r
r
e
g
io
n
s
b
el
o
n
g
to
m
o
v
i
n
g
o
b
jects
Evaluation Warning : The document was created with Spire.PDF for Python.
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
I
SS
N:
2722
-
2
5
8
6
P
erfo
r
ma
n
ce
co
mp
a
r
is
o
n
o
f o
p
tica
l flo
w
a
n
d
b
a
ck
g
r
o
u
n
d
s
u
b
tr
a
ctio
n
…
(
Mo
n
ika
S
h
a
r
ma
)
99
o
r
th
e
b
ac
k
d
r
o
p
is
r
ef
lecte
d
i
n
th
is
m
etr
ic.
T
h
e
s
en
s
itiv
ity
,
r
ec
all,
o
r
tr
u
e
p
o
s
itiv
e
r
ate
is
a
m
ea
s
u
r
e
o
f
h
o
w
well
th
e
s
y
s
tem
d
etec
ts
r
ea
l
p
o
s
itiv
es
o
r
m
o
v
in
g
o
b
jects.
A
s
y
s
tem
with
a
h
ig
h
s
en
s
itiv
ity
will
b
e
ab
le
to
p
ick
u
p
o
n
m
o
s
t
m
o
v
in
g
item
s
in
th
e
s
ce
n
e,
r
ed
u
cin
g
th
e
li
k
elih
o
o
d
t
h
at
an
y
th
i
n
g
cr
u
cial
wo
u
ld
g
o
u
n
n
o
ticed
.
I
m
p
o
r
ta
n
t
f
ield
s
th
at
r
ely
o
n
it
in
clu
d
e
au
to
m
ate
d
d
r
iv
in
g
an
d
s
u
r
v
eillan
ce
,
wh
er
e
th
e
ab
ilit
y
to
r
ec
o
g
n
ize
an
y
m
o
v
in
g
o
b
ject
is
p
ar
am
o
u
n
t.
T
h
e
s
en
s
itiv
ity
o
f
a
s
y
s
tem
is
d
ef
in
ed
as
th
e
p
er
ce
n
tag
e
o
f
r
ea
l
n
eg
ativ
es
(
i.e
.
,
non
-
m
o
v
in
g
b
ac
k
g
r
o
u
n
d
)
th
at
ar
e
p
r
o
p
er
ly
d
etec
ted
as n
eg
ati
v
es.
T
ab
le
1
.
C
o
m
p
a
r
is
o
n
o
f
th
e
r
e
s
p
o
n
s
e
tim
e
f
o
r
d
etec
tio
n
M
e
t
h
o
d
d
e
scr
i
p
t
i
o
n
R
e
s
p
o
n
se
t
i
me
i
n
M
A
TLA
B
(
se
c
o
n
d
s
)
D
W
T
O
p
t
i
c
a
l
m
e
t
h
o
d
B
a
c
k
g
r
o
u
n
d
su
b
t
r
a
c
t
i
o
n
O
b
j
e
c
t
d
e
t
e
c
t
i
o
n
I
mag
e
/
V
i
d
e
o
-
1
0
.
2
5
0
.
3
1
0
.
4
5
O
b
j
e
c
t
d
e
t
e
c
t
i
o
n
I
mag
e
/
V
i
d
e
o
-
2
0
.
2
4
0
.
3
3
0
.
4
4
O
b
j
e
c
t
d
e
t
e
c
t
i
o
n
I
mag
e
/
V
i
d
e
o
-
3
0
.
3
0
0
.
3
9
0
.
4
7
O
b
j
e
c
t
d
e
t
e
c
t
i
o
n
I
mag
e
/
V
i
d
e
o
-
4
0
.
2
3
0
.
2
9
0
.
3
5
O
b
j
e
c
t
d
e
t
e
c
t
i
o
n
I
mag
e
/
V
i
d
e
o
-
5
0
.
3
1
0
.
3
5
0
.
4
0
T
h
e
im
p
o
r
ta
n
ce
o
f
a
s
y
s
tem
'
s
ab
ilit
y
to
ac
cu
r
ately
d
etec
t
m
o
tio
n
as
o
p
p
o
s
ed
to
n
o
n
-
m
o
tio
n
is
h
ig
h
lig
h
ted
b
y
t
h
e
f
ac
t
th
at
a
h
ig
h
s
p
ec
if
icity
is
cr
u
cial
in
r
ed
u
cin
g
t
h
e
o
cc
u
r
r
en
ce
o
f
f
alse
alar
m
s
an
d
f
alse
p
o
s
itiv
es.
I
t
k
ee
p
s
th
in
g
s
r
eliab
le
an
d
c
u
ts
d
o
wn
o
n
n
ee
d
less
p
r
o
ce
s
s
in
g
o
r
n
o
tific
atio
n
s
b
y
m
ak
i
n
g
s
u
r
e
t
h
e
s
y
s
tem
ca
n
tell
m
o
v
in
g
o
b
ject
s
ap
ar
t
f
r
o
m
a
s
tatio
n
ar
y
b
ac
k
g
r
o
u
n
d
.
T
ab
le
2
p
r
esen
ts
th
e
esti
m
ated
v
alu
es
o
f
all
th
e
d
is
cu
s
s
ed
m
eth
o
d
s
an
d
th
e
co
r
r
esp
o
n
d
in
g
co
m
p
ar
ativ
e
p
er
f
o
r
m
an
ce
c
u
r
v
e
f
o
r
th
e
d
etec
tio
n
alg
o
r
ith
m
s
is
s
h
o
wn
in
Fig
u
r
e
3
.
T
ab
le
3
p
r
esen
ts
th
e
s
im
u
lated
im
ag
es
an
d
r
esu
lts
f
o
r
d
if
f
er
e
n
t im
ag
e
s
.
T
ab
le
2
.
C
o
m
p
a
r
ativ
e
p
er
f
o
r
m
an
ce
v
alu
es
M
e
t
h
o
d
TP
TN
FP
FN
A
c
c
u
r
a
c
y
(
%)
S
e
n
s
i
t
i
v
i
t
y
(
%)
S
p
e
c
i
f
i
c
i
t
y
(
%)
D
W
T
95
89
5
4
9
5
.
3
4
9
5
.
9
6
9
4
.
6
8
O
p
t
i
c
a
l
92
85
5
6
9
4
.
1
5
9
3
.
8
8
9
4
.
4
4
B
a
c
k
g
r
o
u
n
d
su
b
t
r
a
c
t
i
o
n
90
80
6
10
9
1
.
4
9
0
.
0
0
9
3
.
0
2
Fig
u
r
e
3
.
C
o
m
p
a
r
ativ
e
p
e
r
f
o
r
m
an
ce
cu
r
v
e
f
o
r
th
e
d
etec
tio
n
alg
o
r
ith
m
s
87
88
89
90
91
92
93
94
95
96
97
DWT
O
p
ti
c
al
Ba
c
k
g
ro
u
n
d
S
u
b
tr
ac
ti
o
n
%
Uti
l
i
zati
o
n
M
eth
o
d
Per
f
or
man
ce Estim
atio
n
A
c
c
u
racy(
%
)
S
e
n
s
i
ti
vit
y (
%
)
S
p
e
c
i
ficit
y (
%
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
2
5
8
6
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
1
4
,
No
.
1
,
Ma
r
ch
20
2
5
:
93
-
1
0
2
100
T
ab
le
3
.
Simu
latio
n
o
u
tco
m
e
o
f
th
e
d
i
f
f
er
en
t sam
p
le
d
im
ag
e
o
b
ject/v
id
eo
S
.
N
o
I
n
p
u
t
o
r
i
g
i
n
a
l
A
f
t
e
r
a
p
p
l
y
i
n
g
t
h
e
D
W
T
a
l
g
o
r
i
t
h
m
I
mag
e
o
b
j
e
c
t
/
V
i
d
e
o
-
1
I
mag
e
o
b
j
e
c
t
/
V
i
d
e
o
-
2
I
mag
e
o
b
j
e
c
t
/
V
i
d
e
o
-
3
I
mag
e
o
b
j
e
c
t
/
V
i
d
e
o
-
4
I
mag
e
o
b
j
e
c
t
/
V
i
d
e
o
-
5
5.
CO
NCLU
SI
O
N
I
t
is
p
o
s
s
ib
le
to
co
m
p
ar
e
s
ev
er
al
m
eth
o
d
s
,
tu
n
e
p
ar
am
et
er
s
,
an
d
v
e
r
if
y
th
at
t
h
e
s
y
s
tem
s
atis
f
ies
o
p
er
atio
n
al
r
e
q
u
ir
em
e
n
ts
with
th
e
h
elp
o
f
MA
T
L
AB
's
p
er
f
o
r
m
a
n
ce
ev
alu
atio
n
an
d
v
alid
atio
n
to
o
ls
.
T
h
e
ev
alu
atio
n
is
d
o
n
e
f
o
r
th
e
o
p
t
ical
f
lo
w
m
eth
o
d
s
,
b
ac
k
g
r
o
u
n
d
s
u
b
tr
ac
tio
n
m
eth
o
d
s
,
an
d
D
W
T
p
r
o
ce
s
s
in
g
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
I
SS
N:
2722
-
2
5
8
6
P
erfo
r
ma
n
ce
co
mp
a
r
is
o
n
o
f o
p
tica
l flo
w
a
n
d
b
a
ck
g
r
o
u
n
d
s
u
b
tr
a
ctio
n
…
(
Mo
n
ika
S
h
a
r
ma
)
101
m
o
v
in
g
o
b
jects
d
etec
tio
n
.
T
h
e
s
im
u
latio
n
is
ca
r
r
ied
o
u
t
in
s
ev
er
al
en
v
ir
o
n
m
en
ts
in
clu
d
i
n
g
r
ain
y
an
d
h
az
y
en
v
ir
o
n
m
en
ts
.
T
h
e
p
r
im
ar
y
a
d
v
an
tag
es
o
f
th
e
DW
T
f
o
r
o
b
ject
d
etec
tio
n
ar
e
its
ca
p
ac
ity
to
ca
p
tu
r
e
ess
en
tial
in
f
o
r
m
atio
n
,
its
r
o
b
u
s
tn
ess
ag
ain
s
t
n
o
is
e,
its
co
m
p
ac
t
r
e
p
r
esen
tatio
n
,
an
d
its
m
u
lti
-
r
eso
lu
tio
n
an
aly
s
is
.
C
o
n
s
eq
u
en
tly
,
it
s
er
v
es
as
a
v
er
y
ef
f
ec
tiv
e
in
s
tr
u
m
en
t,
p
ar
ti
cu
lar
ly
wh
en
co
n
v
en
tio
n
al
p
r
o
ce
d
u
r
es
m
a
y
p
o
s
e
ch
allen
g
es
o
r
wh
en
o
b
tain
i
n
g
s
p
ec
if
ic
attr
ib
u
tes
is
es
s
en
tial.
T
h
e
s
im
u
latio
n
wo
r
k
o
f
th
e
DW
T
m
eth
o
d
h
as
s
h
o
wn
a
m
in
im
u
m
laten
cy
o
f
0
.
2
3
s
ec
o
n
d
s
th
en
o
p
tical
f
lo
w
o
f
0
.
2
9
s
ec
o
n
d
s
an
d
0
.
3
5
s
ec
o
n
d
s
f
o
r
b
ac
k
g
r
o
u
n
d
s
u
b
tr
ac
tio
n
m
et
h
o
d
s
.
T
h
e
s
am
e
ty
p
e
o
f
b
e
h
av
io
r
is
an
aly
ze
d
f
o
r
o
th
er
ca
s
es
also
.
T
h
e
ac
cu
r
ac
y
o
f
th
e
DW
T
,
o
p
tical,
an
d
b
ac
k
g
r
o
u
n
d
s
u
b
tr
ac
tio
n
m
eth
o
d
s
is
9
5
.
3
4
%
,
9
4
.
1
5
%,
an
d
9
1
.
4
0
%
.
T
h
e
s
en
s
itiv
ity
o
f
th
e
DW
T
,
o
p
tical,
an
d
b
ac
k
g
r
o
u
n
d
s
u
b
tr
a
ctio
n
m
eth
o
d
s
is
9
5
.
9
6
%,
9
3
.
8
8
%,
an
d
9
0
.
0
0
%
.
T
h
e
s
p
ec
if
icity
o
f
th
e
DW
T
,
o
p
tical,
an
d
b
ac
k
g
r
o
u
n
d
s
u
b
tr
ac
tio
n
m
et
h
o
d
s
is
9
4
.
6
8
%,
9
4
.
4
4
%,
an
d
9
3
.
0
3
%
.
W
h
en
it
co
m
es
to
d
etec
tin
g
m
o
v
in
g
o
b
jects
in
i
m
ag
es
an
d
v
id
e
o
s
,
th
e
DW
T
m
eth
o
d
h
as
co
n
tin
u
o
u
s
ly
p
r
o
v
en
to
b
e
t
h
e
o
p
tim
al
ch
o
ice
in
ter
m
s
o
f
b
o
t
h
h
ar
d
w
ar
e
an
d
s
o
f
twar
e
.
RE
F
E
R
E
NC
E
S
[
1
]
A
.
C
a
v
a
l
l
a
r
o
,
O
.
S
t
e
i
g
e
r
,
a
n
d
T.
E
b
r
a
h
i
m
i
,
“
Tr
a
c
k
i
n
g
v
i
d
e
o
o
b
j
e
c
t
s
i
n
c
l
u
t
t
e
r
e
d
b
a
c
k
g
r
o
u
n
d
,
”
I
EEE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
C
i
rc
u
i
t
s
a
n
d
S
y
s
t
e
m
s
f
o
r
V
i
d
e
o
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
5
,
n
o
.
4
,
p
p
.
5
7
5
–
5
8
4
,
2
0
0
5
,
d
o
i
:
1
0
.
1
1
0
9
/
TC
S
V
T
.
2
0
0
5
.
8
4
4
4
4
7
.
[
2
]
A
.
M
u
k
h
t
a
r
,
L.
X
i
a
,
a
n
d
T
.
B
.
T
a
n
g
,
“
V
e
h
i
c
l
e
d
e
t
e
c
t
i
o
n
t
e
c
h
n
i
q
u
e
s
f
o
r
c
o
l
l
i
si
o
n
a
v
o
i
d
a
n
c
e
s
y
st
e
ms:
a
r
e
v
i
e
w
,
”
I
E
EE
T
r
a
n
sa
c
t
i
o
n
s
o
n
I
n
t
e
l
l
i
g
e
n
t
T
r
a
n
s
p
o
rt
a
t
i
o
n
S
y
st
e
m
s
,
v
o
l
.
1
5
,
n
o
.
5
,
p
p
.
2
3
1
8
–
2
3
3
8
,
2
0
1
5
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
TS.2
0
1
5
.
2
4
0
9
1
0
9
.
[
3
]
S
.
H
a
ss
a
n
,
G
.
M
u
j
t
a
b
a
,
A
.
R
a
j
p
u
t
,
a
n
d
N
.
F
a
t
i
ma
,
“
M
u
l
t
i
-
o
b
j
e
c
t
t
r
a
c
k
i
n
g
:
a
s
y
st
e
ma
t
i
c
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
,
”
M
u
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
8
3
,
n
o
.
1
4
,
p
p
.
4
3
4
3
9
–
4
3
4
9
2
,
O
c
t
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
4
2
-
023
-
1
7
2
9
7
-
3.
[
4
]
Z.
Zo
u
,
K
.
C
h
e
n
,
Z
.
S
h
i
,
Y
.
G
u
o
,
a
n
d
J.
Y
e
,
“
O
b
j
e
c
t
d
e
t
e
c
t
i
o
n
i
n
2
0
y
e
a
r
s
:
a
s
u
r
v
e
y
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
I
E
E
E
,
2
0
2
3
,
v
o
l
.
1
1
1
,
n
o
.
3
,
p
p
.
2
5
7
–
2
7
6
,
d
o
i
:
1
0
.
1
1
0
9
/
JP
R
O
C
.
2
0
2
3
.
3
2
3
8
5
2
4
.
[
5
]
D
.
K
.
P
r
a
sa
d
,
D
.
R
a
j
a
n
,
L
.
R
a
c
h
m
a
w
a
t
i
,
E
.
R
a
j
a
b
a
l
l
y
,
a
n
d
C
.
Q
u
e
k
,
“
V
i
d
e
o
p
r
o
c
e
ss
i
n
g
f
r
o
m
e
l
e
c
t
r
o
-
o
p
t
i
c
a
l
s
e
n
s
o
r
s
f
o
r
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
a
n
d
t
r
a
c
k
i
n
g
i
n
a
m
a
r
i
t
i
me
e
n
v
i
r
o
n
m
e
n
t
:
a
s
u
r
v
e
y
,
”
I
E
EE
T
ra
n
s
a
c
t
i
o
n
s
o
n
I
n
t
e
l
l
i
g
e
n
t
T
r
a
n
sp
o
rt
a
t
i
o
n
S
y
s
t
e
m
s
,
v
o
l
.
1
8
,
n
o
.
8
,
p
p
.
1
9
9
3
–
2
0
1
6
,
A
u
g
.
2
0
1
7
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
TS.2
0
1
6
.
2
6
3
4
5
8
0
.
[
6
]
H
.
Zh
u
,
H
.
W
e
i
,
B
.
L
i
,
X
.
Y
u
a
n
,
a
n
d
N
.
K
e
h
t
a
r
n
a
v
a
z
,
“
A
c
o
m
p
r
e
h
e
n
s
i
v
e
su
r
v
e
y
o
f
v
i
d
e
o
d
a
t
a
se
t
s
f
o
r
b
a
c
k
g
r
o
u
n
d
s
u
b
t
r
a
c
t
i
o
n
,
”
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
0
,
n
o
.
2
1
,
N
o
v
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
0
2
1
7
8
3
4
.
[
7
]
A
.
K
u
mar
,
“
T
e
x
t
e
x
t
r
a
c
t
i
o
n
a
n
d
r
e
c
o
g
n
i
t
i
o
n
f
r
o
m
a
n
i
ma
g
e
u
s
i
n
g
i
ma
g
e
p
r
o
c
e
ssi
n
g
i
n
M
A
TLA
B
,
”
i
n
C
o
n
f
e
re
n
c
e
o
n
A
d
v
a
n
c
e
s
i
n
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
C
o
n
t
r
o
l
S
y
st
e
m
s
2
0
1
3
(
C
AC
2
S
2
0
1
3
)
,
2
0
1
3
,
v
o
l
.
2
0
1
3
,
p
p
.
4
2
9
–
4
3
5
.
[
8
]
M
.
S
h
a
r
m
a
,
K
.
S
.
K
a
sw
a
n
,
a
n
d
D
.
K
.
Y
a
d
a
v
,
“
M
o
v
i
n
g
o
b
j
e
c
t
s
d
e
t
e
c
t
i
o
n
b
a
se
d
o
n
h
i
s
t
o
g
r
a
m
o
f
o
r
i
e
n
t
e
d
g
r
a
d
i
e
n
t
a
l
g
o
r
i
t
h
m
c
h
i
p
f
o
r
h
a
z
y
e
n
v
i
r
o
n
m
e
n
t
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
R
e
c
o
n
f
i
g
u
r
a
b
l
e
a
n
d
Em
b
e
d
d
e
d
S
y
st
e
m
s
,
v
o
l
.
1
3
,
n
o
.
3
,
p
p
.
6
0
4
–
6
1
5
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
r
e
s.
v
1
3
.
i
3
.
p
p
6
0
4
-
6
1
5
.
[
9
]
B
.
M
i
r
z
a
e
i
,
H
.
N
e
z
a
m
a
b
a
d
i
-
p
o
u
r
,
A
.
R
a
o
o
f
,
a
n
d
R
.
D
e
r
a
k
h
s
h
a
n
i
,
“
S
m
a
l
l
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
a
n
d
t
r
a
c
k
i
n
g
:
a
c
o
m
p
r
e
h
e
n
s
i
v
e
r
e
v
i
e
w
,
”
S
e
n
so
rs
,
v
o
l
.
2
3
,
n
o
.
1
5
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
3
1
5
6
8
8
7
.
[
1
0
]
J.
B
a
i
,
S
.
Li
,
L.
H
u
a
n
g
,
a
n
d
H
.
C
h
e
n
,
“
R
o
b
u
s
t
d
e
t
e
c
t
i
o
n
a
n
d
t
r
a
c
k
i
n
g
me
t
h
o
d
f
o
r
m
o
v
i
n
g
o
b
j
e
c
t
b
a
s
e
d
o
n
r
a
d
a
r
a
n
d
c
a
mer
a
d
a
t
a
f
u
si
o
n
,
”
I
E
EE
S
e
n
s
o
rs
J
o
u
r
n
a
l
,
v
o
l
.
2
1
,
n
o
.
9
,
p
p
.
1
0
7
6
1
–
1
0
7
7
4
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
JS
EN
.
2
0
2
1
.
3
0
4
9
4
4
9
.
[
1
1
]
X
.
Zh
o
u
,
C
.
Y
a
n
g
,
a
n
d
W
.
Y
u
,
“
M
o
v
i
n
g
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
b
y
d
e
t
e
c
t
i
n
g
c
o
n
t
i
g
u
o
u
s
o
u
t
l
i
e
r
s
i
n
t
h
e
l
o
w
-
r
a
n
k
r
e
p
r
e
s
e
n
t
a
t
i
o
n
,
”
I
E
E
E
T
ra
n
s
a
c
t
i
o
n
s
o
n
P
a
t
t
e
r
n
A
n
a
l
y
si
s
a
n
d
Ma
c
h
i
n
e
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
3
5
,
n
o
.
3
,
p
p
.
5
9
7
–
6
1
0
,
2
0
1
3
.
[
1
2
]
X
.
Z
h
a
n
g
,
C
.
Zh
u
,
S
.
W
a
n
g
,
Y
.
L
i
u
,
a
n
d
M
.
Y
e
,
“
A
B
a
y
e
s
i
a
n
a
p
p
r
o
a
c
h
t
o
c
a
mo
u
f
l
a
g
e
d
m
o
v
i
n
g
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
,
”
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
C
i
r
c
u
i
t
s
a
n
d
S
y
s
t
e
m
s
f
o
r
Vi
d
e
o
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
2
7
,
n
o
.
9
,
p
p
.
2
0
0
1
–
2
0
1
3
,
2
0
1
7
,
d
o
i
:
1
0
.
1
1
0
9
/
T
C
S
V
T.
2
0
1
6
.
2
5
5
5
7
1
9
.
[
1
3
]
H
.
H
a
n
,
J
.
Zh
u
,
S
.
Li
a
o
,
Z.
Le
i
,
a
n
d
S
.
Z.
Li
,
“
M
o
v
i
n
g
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
r
e
v
i
s
i
t
e
d
:
S
p
e
e
d
a
n
d
r
o
b
u
st
n
e
ss,”
I
E
EE
T
ra
n
s
a
c
t
i
o
n
s
o
n
C
i
rc
u
i
t
s
a
n
d
S
y
st
e
m
s
f
o
r
Vi
d
e
o
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
2
5
,
n
o
.
6
,
p
p
.
9
1
0
–
9
2
1
,
2
0
1
5
,
d
o
i
:
1
0
.
1
1
0
9
/
TC
S
V
T
.
2
0
1
4
.
2
3
6
7
3
7
1
.
[
1
4
]
D
.
K
.
P
a
n
d
a
a
n
d
S
.
M
e
h
e
r
,
“
D
e
t
e
c
t
i
o
n
o
f
m
o
v
i
n
g
o
b
j
e
c
t
s
u
si
n
g
f
u
z
z
y
c
o
l
o
r
d
i
f
f
e
r
e
n
c
e
h
i
st
o
g
r
a
m
b
a
s
e
d
b
a
c
k
g
r
o
u
n
d
s
u
b
t
r
a
c
t
i
o
n
,
”
I
EEE
S
i
g
n
a
l
Pr
o
c
e
ssi
n
g
L
e
t
t
e
rs
,
v
o
l
.
2
3
,
n
o
.
1
,
p
p
.
4
5
–
4
9
,
2
0
1
6
,
d
o
i
:
1
0
.
1
1
0
9
/
LSP
.
2
0
1
5
.
2
4
9
8
8
3
9
.
[
1
5
]
Z.
W
a
n
g
,
K
.
Li
a
o
,
J.
X
i
o
n
g
,
a
n
d
Q
.
Zh
a
n
g
,
“
M
o
v
i
n
g
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
b
a
s
e
d
o
n
t
e
m
p
o
r
a
l
i
n
f
o
r
ma
t
i
o
n
,
”
I
EE
E
S
i
g
n
a
l
Pr
o
c
e
ssi
n
g
L
e
t
t
e
rs
,
v
o
l
.
2
1
,
n
o
.
1
1
,
p
p
.
1
4
0
3
–
1
4
0
7
,
2
0
1
4
,
d
o
i
:
1
0
.
1
1
0
9
/
LSP
.
2
0
1
4
.
2
3
3
8
0
5
6
.
[
1
6
]
T.
W
a
n
g
a
n
d
H
.
S
n
o
u
ss
i
,
“
D
e
t
e
c
t
i
o
n
o
f
a
b
n
o
r
mal
v
i
s
u
a
l
e
v
e
n
t
s
v
i
a
g
l
o
b
a
l
o
p
t
i
c
a
l
f
l
o
w
o
r
i
e
n
t
a
t
i
o
n
h
i
st
o
g
r
a
m,
”
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
I
n
f
o
rm
a
t
i
o
n
Fo
r
e
n
si
c
s a
n
d
S
e
c
u
r
i
t
y
,
v
o
l
.
9
,
n
o
.
6
,
p
p
.
9
8
8
–
9
9
8
,
2
0
1
4
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
F
S
.
2
0
1
4
.
2
3
1
5
9
7
1
.
[
1
7
]
S
.
S
.
S
e
n
g
a
r
a
n
d
S
.
M
u
k
h
o
p
a
d
h
y
a
y
,
“
D
e
t
e
c
t
i
o
n
o
f
m
o
v
i
n
g
o
b
j
e
c
t
s
b
a
s
e
d
o
n
e
n
h
a
n
c
e
me
n
t
o
f
o
p
t
i
c
a
l
f
l
o
w
,
”
O
p
t
i
k
,
v
o
l
.
1
4
5
,
p
p
.
1
3
0
–
1
4
1
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
l
e
o
.
2
0
1
7
.
0
7
.
0
4
0
.
[
1
8
]
J.
H
a
r
i
y
o
n
o
,
V
.
D
.
H
o
a
n
g
,
a
n
d
K
.
H
.
Jo
,
“
M
o
v
i
n
g
o
b
j
e
c
t
l
o
c
a
l
i
z
a
t
i
o
n
u
si
n
g
o
p
t
i
c
a
l
f
l
o
w
f
o
r
p
e
d
e
s
t
r
i
a
n
d
e
t
e
c
t
i
o
n
f
r
o
m
a
mo
v
i
n
g
v
e
h
i
c
l
e
,
”
S
c
i
e
n
t
i
f
i
c
W
o
rl
d
J
o
u
r
n
a
l
,
v
o
l
.
2
0
1
4
,
2
0
1
4
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
1
4
/
1
9
6
4
1
5
.
[
1
9
]
P
.
P
.
G
a
n
g
a
l
,
V
.
R
.
S
a
t
p
u
t
e
,
K
.
D
.
K
u
l
a
t
,
a
n
d
A
.
G
.
K
e
s
k
a
r
,
“
O
b
j
e
c
t
d
e
t
e
c
t
i
o
n
a
n
d
t
r
a
c
k
i
n
g
u
si
n
g
2
D
—
D
W
T
a
n
d
v
a
r
i
a
n
c
e
met
h
o
d
,
”
i
n
2
0
1
4
S
t
u
d
e
n
t
s C
o
n
f
e
re
n
c
e
o
n
En
g
i
n
e
e
ri
n
g
a
n
d
S
y
st
e
m
s
,
M
a
y
2
0
1
4
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
S
C
ES
.
2
0
1
4
.
6
8
8
0
1
2
3
.
[
2
0
]
Y
.
W
u
,
X
.
H
e
,
a
n
d
T.
Q
.
N
g
u
y
e
n
,
“
M
o
v
i
n
g
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
w
i
t
h
a
f
r
e
e
l
y
m
o
v
i
n
g
c
a
mer
a
v
i
a
b
a
c
k
g
r
o
u
n
d
m
o
t
i
o
n
s
u
b
t
r
a
c
t
i
o
n
,
”
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
C
i
rc
u
i
t
s
a
n
d
S
y
s
t
e
m
s
f
o
r
Vi
d
e
o
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
2
7
,
n
o
.
2
,
p
p
.
2
3
6
–
2
4
8
,
F
e
b
.
2
0
1
7
,
d
o
i
:
1
0
.
1
1
0
9
/
T
C
S
V
T.
2
0
1
5
.
2
4
9
3
4
9
9
.
[
2
1
]
R
.
K
a
l
s
o
t
r
a
a
n
d
S
.
A
r
o
r
a
,
“
A
c
o
m
p
r
e
h
e
n
s
i
v
e
su
r
v
e
y
o
f
v
i
d
e
o
d
a
t
a
se
t
s
f
o
r
b
a
c
k
g
r
o
u
n
d
su
b
t
r
a
c
t
i
o
n
,
”
I
EE
E
Ac
c
e
ss
,
v
o
l
.
7
,
p
p
.
5
9
1
4
3
–
5
9
1
7
1
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
1
4
9
6
1
.
[
2
2
]
A
.
Ta
l
u
k
d
e
r
a
n
d
L
.
M
a
t
t
h
i
e
s,
“
R
e
a
l
-
t
i
me
d
e
t
e
c
t
i
o
n
o
f
mo
v
i
n
g
o
b
j
e
c
t
s
f
r
o
m
mo
v
i
n
g
v
e
h
i
c
l
e
s
u
s
i
n
g
d
e
n
se
st
e
r
e
o
a
n
d
o
p
t
i
c
a
l
f
l
o
w
,
”
i
n
2
0
0
4
I
EE
E/
R
S
J
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
t
e
l
l
i
g
e
n
t
Ro
b
o
t
s
a
n
d
S
y
s
t
e
m
s
(
I
RO
S
)
,
2
0
0
4
,
v
o
l
.
4
,
p
p
.
3
7
1
8
–
3
7
2
5
,
d
o
i
:
1
0
.
1
1
0
9
/
i
r
o
s.
2
0
0
4
.
1
3
8
9
9
9
3
.
[
2
3
]
K
.
K
a
l
e
,
S
.
P
a
w
a
r
,
a
n
d
P
.
D
h
u
l
e
k
a
r
,
“
M
o
v
i
n
g
o
b
j
e
c
t
t
r
a
c
k
i
n
g
u
s
i
n
g
o
p
t
i
c
a
l
f
l
o
w
a
n
d
mo
t
i
o
n
v
e
c
t
o
r
e
st
i
ma
t
i
o
n
,
”
i
n
2
0
1
5
4
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
R
e
l
i
a
b
i
l
i
t
y
,
I
n
f
o
c
o
m
T
e
c
h
n
o
l
o
g
i
e
s
a
n
d
O
p
t
i
m
i
za
t
i
o
n
(
I
C
RI
T
O
)
(
T
ren
d
s
a
n
d
Fu
t
u
r
e
D
i
rec
t
i
o
n
s)
,
S
e
p
.
2
0
1
5
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
R
I
TO
.
2
0
1
5
.
7
3
5
9
3
2
3
.
[
2
4
]
A
.
K
u
m
a
r
,
“
S
t
u
d
y
a
n
d
a
n
a
l
y
s
i
s
o
f
d
i
f
f
e
r
e
n
t
s
e
g
me
n
t
a
t
i
o
n
m
e
t
h
o
d
s
f
o
r
b
r
a
i
n
t
u
m
o
r
M
R
I
a
p
p
l
i
c
a
t
i
o
n
,
”
M
u
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
8
2
,
n
o
.
5
,
p
p
.
7
1
1
7
–
7
1
3
9
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
1
0
4
2
-
0
2
2
-
1
3
6
3
6
-
y.
[
2
5
]
A
.
G
o
e
l
,
A
.
K
.
G
o
e
l
,
a
n
d
A
.
K
u
m
a
r
,
“
P
e
r
f
o
r
ma
n
c
e
a
n
a
l
y
s
i
s
o
f
m
u
l
t
i
p
l
e
i
n
p
u
t
si
n
g
l
e
l
a
y
e
r
n
e
u
r
a
l
n
e
t
w
o
r
k
h
a
r
d
w
a
r
e
c
h
i
p
,
”
Mu
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
8
2
,
n
o
.
1
8
,
p
p
.
2
8
2
1
3
–
2
8
2
3
4
,
Ju
l
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
1
0
4
2
-
0
2
3
-
1
4
6
2
7
-
3.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
2
5
8
6
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
1
4
,
No
.
1
,
Ma
r
ch
20
2
5
:
93
-
1
0
2
102
[
2
6
]
A
.
K
u
mar,
P
.
R
a
s
t
o
g
i
,
a
n
d
P
.
S
r
i
v
a
s
t
a
v
a
,
“
D
e
si
g
n
a
n
d
F
P
G
A
i
m
p
l
e
me
n
t
a
t
i
o
n
o
f
D
W
T,
i
ma
g
e
t
e
x
t
e
x
t
r
a
c
t
i
o
n
t
e
c
h
n
i
q
u
e
,
”
Pro
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
5
7
,
p
p
.
1
0
1
5
–
1
0
2
5
,
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s
.
2
0
1
5
.
0
7
.
5
1
2
.
[
2
7
]
A
.
S
.
R
a
w
a
t
,
A
.
R
a
n
a
,
A
.
K
u
mar,
a
n
d
A
.
B
a
g
w
a
r
i
,
“
A
p
p
l
i
c
a
t
i
o
n
o
f
m
u
l
t
i
l
a
y
e
r
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
i
n
t
h
e
d
i
a
g
n
o
s
i
s
s
y
st
e
m
:
A
sy
st
e
ma
t
i
c
r
e
v
i
e
w
,
”
I
AE
S
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
(
I
J
-
AI
)
,
v
o
l
.
7
,
n
o
.
3
,
p
.
1
3
8
,
A
u
g
.
2
0
1
8
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
a
i
.
v
7
.
i
3
.
p
p
1
3
8
-
1
4
2
.
[
2
8
]
A
.
G
o
e
l
,
A
.
K
.
G
o
e
l
,
a
n
d
A
.
K
u
mar
,
“
Th
e
r
o
l
e
o
f
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
a
n
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
i
n
u
t
i
l
i
z
i
n
g
s
p
a
t
i
a
l
i
n
f
o
r
ma
t
i
o
n
,
”
S
p
a
t
i
a
l
I
n
f
o
rm
a
t
i
o
n
R
e
se
a
rc
h
,
v
o
l
.
3
1
,
n
o
.
3
,
p
p
.
2
7
5
–
2
8
5
,
J
u
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
1
3
2
4
-
0
2
2
-
0
0
4
9
4
-
x.
[
2
9
]
A
.
D
e
v
r
a
r
i
a
n
d
A
.
K
u
mar,
“
T
u
r
b
o
e
n
c
o
d
e
r
a
n
d
d
e
c
o
d
e
r
c
h
i
p
d
e
s
i
g
n
a
n
d
F
P
G
A
d
e
v
i
c
e
a
n
a
l
y
si
s
f
o
r
c
o
mm
u
n
i
c
a
t
i
o
n
sy
s
t
e
m
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
R
e
c
o
n
f
i
g
u
r
a
b
l
e
a
n
d
Em
b
e
d
d
e
d
S
y
s
t
e
m
s
,
v
o
l
.
1
2
,
n
o
.
2
,
p
p
.
1
7
4
–
1
8
5
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
r
e
s.
v
1
2
.
i
2
.
p
p
1
7
4
-
1
8
5
.
[
3
0
]
S
.
D
h
y
a
n
i
,
A
.
K
u
mar,
a
n
d
S
.
C
h
o
u
d
h
u
r
y
,
“
A
n
a
l
y
si
s
o
f
EC
G
-
b
a
s
e
d
a
r
r
h
y
t
h
m
i
a
d
e
t
e
c
t
i
o
n
s
y
st
e
m
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
Me
t
h
o
d
s
X
,
v
o
l
.
1
0
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
me
x
.
2
0
2
3
.
1
0
2
1
9
5
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Mo
n
ik
a
S
h
a
r
m
a
is
c
u
rre
n
t
ly
wo
rk
i
n
g
a
s
a
re
se
a
rc
h
sc
h
o
lar
in
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
in
e
e
rin
g
a
t
G
a
lg
o
ti
a
s
Un
iv
e
rsity
,
No
id
a
,
NCR,
In
d
ia.
S
h
e
h
a
s
a
n
M
.
Tec
h
.
i
n
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
i
n
e
e
rin
g
a
n
d
a
B.
Tec
h
.
i
n
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
in
e
e
rin
g
in
2
0
1
2
a
n
d
2
0
0
9
re
sp
e
c
ti
v
e
ly
.
S
h
e
h
a
s
p
u
b
li
sh
e
d
m
o
re
t
h
a
n
2
0
re
se
a
rc
h
p
a
p
e
rs
a
n
d
b
o
o
k
c
h
a
p
ters
.
S
h
e
i
s
wo
rk
i
n
g
a
s
a
lec
t
u
re
r
a
t
G
o
v
e
rn
m
e
n
t
G
irl
s
P
o
l
y
tec
h
n
ic
Co
ll
e
g
e
,
Da
u
ra
la,
M
e
e
ru
t,
u
n
d
e
r
th
e
Uttar
P
ra
d
e
sh
Tec
h
n
ica
l
De
p
a
rtme
n
t,
In
d
ia.
S
h
e
is
h
a
v
i
n
g
e
x
p
e
rien
c
e
o
f
1
4
y
e
a
rs.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
m
o
n
ik
a
sh
a
rm
a
.
c
se
@g
m
a
il
.
c
o
m
.
K
u
ld
e
e
p
S
in
g
h
K
a
sw
a
n
is p
re
se
n
tl
y
wo
r
k
in
g
in
t
h
e
S
c
h
o
o
l
o
f
C
o
m
p
u
ti
n
g
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
,
a
t
G
a
lg
o
ti
a
s
Un
iv
e
rsity
,
Uttar P
ra
d
e
sh
,
In
d
ia.
His
c
o
n
tri
b
u
ti
o
n
s fo
c
u
s
o
n
BCI
,
c
y
b
o
r
g
,
a
n
d
d
a
ta
sc
ien
c
e
.
His
Ac
a
d
e
m
ic
d
e
g
re
e
s
a
n
d
th
irt
e
e
n
y
e
a
rs
o
f
e
x
p
e
rien
c
e
wo
rk
i
n
g
wit
h
g
lo
b
a
l
Un
iv
e
rsiti
e
s
li
k
e
Am
it
y
Un
iv
e
rsit
y
,
No
i
d
a
,
G
a
u
tam
Bu
d
d
h
a
Un
iv
e
rsity
,
G
re
a
ter
No
id
a
,
a
n
d
P
DM
Un
i
v
e
rsity
,
Ba
h
a
d
u
r
g
a
rh
,
h
a
v
e
m
a
d
e
h
im
m
o
re
re
c
e
p
ti
v
e
a
n
d
p
ro
m
i
n
e
n
t
i
n
h
is
d
o
m
a
in
.
He
re
c
e
iv
e
d
a
d
o
c
to
ra
te
in
c
o
m
p
u
ter
sc
ien
c
e
fro
m
Ba
n
a
sth
a
li
Vid
y
a
p
it
h
,
Ra
jas
th
a
n
.
He
re
c
e
iv
e
d
a
Do
c
to
r
o
f
En
g
in
e
e
r
in
g
(D.
En
g
g
.
)
fro
m
Da
n
a
Bra
in
He
a
lt
h
In
stit
u
te,
Ira
n
.
He
h
a
s
o
b
tai
n
e
d
a
m
a
ste
r’s
d
e
g
re
e
in
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
i
n
e
e
rin
g
fro
m
Ch
o
u
d
h
a
r
y
De
v
i
La
l
Un
iv
e
rsity
,
S
irsa
(Ha
ry
a
n
a
).
He
h
a
s
su
p
e
r
v
ise
d
m
a
n
y
UG
a
n
d
P
G
p
ro
jec
ts
o
f
e
n
g
i
n
e
e
rin
g
stu
d
e
n
ts.
He
h
a
s
su
p
e
rv
ise
d
3
P
h
.
D.
g
ra
d
u
a
tes
a
n
d
p
re
se
n
tl
y
su
p
e
r
v
isin
g
4
P
h
.
D.
st
u
d
e
n
ts.
He
is
a
lso
a
m
e
m
b
e
r
o
f
IEE
E,
Co
m
p
u
ter
S
c
ien
c
e
Tea
c
h
e
r
As
so
c
iatio
n
(CS
TA),
Ne
w
Yo
rk
,
USA
,
th
e
In
tern
a
ti
o
n
a
l
As
so
c
iatio
n
o
f
En
g
i
n
e
e
rs
(IAENG
),
Ho
n
g
Ko
n
g
,
In
tern
a
ti
o
n
a
l
As
so
c
iatio
n
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
I
n
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
(IACSIT
),
USA,
p
ro
f
e
ss
io
n
a
l
m
e
m
b
e
r
a
ss
o
c
iatio
n
o
f
c
o
m
p
u
ti
n
g
m
a
c
h
in
e
ry
,
USA.
He
h
a
s
p
u
b
li
sh
e
d
9
b
o
o
k
s
a
n
d
4
0
b
o
o
k
c
h
a
p
ters
a
t
n
a
ti
o
n
a
l/
in
ter
n
a
ti
o
n
a
l
le
v
e
l.
He
h
a
s
a
n
u
m
b
e
r
o
f
p
u
b
li
c
a
ti
o
n
s
a
lso
in
i
n
tern
a
ti
o
n
a
l/
n
a
ti
o
n
a
l
jo
u
r
n
a
l
a
n
d
c
o
n
fe
re
n
c
e
s.
He
is
a
n
e
d
i
to
r/a
u
th
o
r,
a
n
d
re
v
iew
e
d
it
o
r
o
f
jo
u
rn
a
ls
a
n
d
b
o
o
k
s
wit
h
IEE
E,
Wi
ley
,
S
p
ri
n
g
e
r,
IG
I,
a
n
d
Riv
e
r.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
k
a
sw
a
n
k
u
l
d
e
e
p
@g
m
a
il
.
c
o
m
.
Dilee
p
K
u
m
a
r
Y
a
d
a
v
re
c
e
iv
e
d
a
n
e
n
g
in
e
e
rin
g
d
e
g
re
e
(B.
Tec
h
.
in
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
i
n
e
e
rin
g
)
fro
m
Uttar
P
ra
d
e
sh
Tec
h
n
ica
l
Un
i
v
e
rsity
,
Lu
c
k
n
o
w,
UP,
I
n
d
ia
i
n
2
0
0
6
a
n
d
m
a
ste
r’s
d
e
g
re
e
(M
.
Tec
h
.
in
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
tec
h
n
o
l
o
g
y
)
fro
m
t
h
e
S
c
h
o
o
l
o
f
Co
m
p
u
ter
a
n
d
S
y
ste
m
s
S
c
ien
c
e
s,
Ja
wa
h
a
rlal
Ne
h
ru
Un
iv
e
rsity
,
Ne
w
De
lh
i,
In
d
ia
in
2
0
1
1
.
Dr
.
Ya
d
a
v
e
a
rn
e
d
a
P
h
.
D.
(c
o
m
p
u
ter
sc
ien
c
e
a
n
d
tec
h
n
o
lo
g
y
)
d
e
g
re
e
fro
m
th
e
S
c
h
o
o
l
o
f
Co
m
p
u
te
r
a
n
d
S
y
ste
m
s
S
c
ien
c
e
s,
Ja
wa
h
a
rl
a
l
Ne
h
ru
Un
iv
e
rsit
y
Ne
w
De
lh
i,
In
d
ia
i
n
2
0
1
6
.
He
is
a
S
u
n
Ce
rti
fied
Ja
v
a
P
ro
g
ra
m
m
e
r.
He
i
s
th
e
a
u
th
o
r
o
f
6
5
re
se
a
rc
h
p
u
b
l
ica
ti
o
n
s
,
in
c
l
u
d
i
n
g
p
a
te
n
t
s
,
jo
u
r
n
a
l
s
(S
CI/S
CI
E/
S
COPUS
)
,
a
n
d
n
a
ti
o
n
a
l/
i
n
tern
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s
.
He
h
a
s
a
lso
a
u
t
h
o
re
d
b
o
o
k
s
a
n
d
m
a
n
y
b
o
o
k
c
h
a
p
ters
fo
r
in
tern
a
ti
o
n
a
ll
y
re
p
u
ted
p
u
b
li
sh
e
rs.
His
p
rima
ry
re
se
a
rc
h
in
tere
sts
a
re
i
n
ima
g
e
p
r
o
c
e
ss
in
g
,
c
o
m
p
u
ter
v
isio
n
,
a
n
d
b
lo
c
k
c
h
a
in
se
c
u
rit
y
u
sin
g
a
rti
ficia
l
in
telli
g
e
n
c
e
a
n
d
m
a
c
h
in
e
lea
rn
in
g
o
v
e
r
d
y
n
a
m
ic d
a
ta.
Dr.
Ya
d
a
v
su
p
e
rv
ise
d
v
a
ri
o
u
s stu
d
e
n
ts
o
f
m
a
ste
r’s
d
e
g
re
e
s
a
n
d
P
h
.
D.
Dr.
Ya
d
a
v
is
a
lso
a
ss
o
c
iate
d
wit
h
m
a
n
y
i
n
tern
a
ti
o
n
a
l
j
o
u
r
n
a
ls
a
s
a
ss
o
c
iate
e
d
it
o
r,
m
e
m
b
e
r,
In
t
.
e
d
it
o
rial
b
o
a
r
d
m
e
m
b
e
r
,
e
tc.
He
h
a
s
m
o
re
th
a
n
1
2
y
e
a
rs
o
f
wo
rk
i
n
g
e
x
p
e
rien
c
e
in
in
d
u
str
y
a
s
we
ll
a
s
a
c
a
d
e
m
i
a
.
Dr.
Ya
d
a
v
is
th
e
re
c
ip
ien
t
o
f
v
a
ri
o
u
s
a
wa
rd
s
fro
m
n
a
ti
o
n
a
l
a
n
d
in
ter
n
a
ti
o
n
a
l
o
rg
a
n
iza
ti
o
n
s
i
n
re
se
a
rc
h
.
He
is
a
lso
su
p
e
rv
isin
g
m
a
n
y
n
a
ti
o
n
a
l
a
n
d
in
tern
a
ti
o
n
a
l
stu
d
e
n
ts
to
p
u
rsu
e
th
e
ir
re
se
a
rc
h
wo
rk
.
Cu
rre
n
t
ly
,
Dr.
Ya
d
a
v
i
s
wo
rk
i
n
g
a
s
a
n
a
ss
o
c
iate
p
ro
fe
ss
o
r
in
t
h
e
De
p
a
rtme
n
t
o
f
CS
E,
S
CS
ET
,
Be
n
n
e
tt
Un
i
v
e
rsity
,
G
re
a
ter No
id
a
,
In
d
ia.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
d
il
e
e
p
2
5
2
0
0
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.