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.
11
,
No
.
1
, M
a
r
ch
20
22
,
p
p
.
1
~
9
I
SS
N:
2722
-
2
5
8
6
,
DOI
:
1
0
.
1
1
5
9
1
/i
jr
a
.
v
11
i
1
.
pp
1
-
9
1
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
r
a
.
ia
esco
r
e.
co
m
A sma
rt
do
o
r p
ro
toty
pe wi
th
a
f
a
c
e
rec
o
g
nition ca
pa
bility
I
v
a
n Sury
a
H
uto
m
o
1
,
H
a
nd
y
Wica
k
s
o
no
2
1
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
a
n
d
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
,
C
o
l
l
e
g
e
o
f
E
l
e
c
t
r
i
c
a
l
a
n
d
C
o
mp
u
t
e
r
E
n
g
i
n
e
e
r
i
n
g
,
N
a
t
i
o
n
a
l
C
h
i
a
o
T
u
n
g
U
n
i
v
e
r
s
i
t
y
,
H
si
n
c
h
u
,
Ta
i
w
a
n
2
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
I
n
d
u
st
r
i
a
l
Te
c
h
n
o
l
o
g
y
,
P
e
t
r
a
C
h
r
i
st
i
a
n
U
n
i
v
e
r
si
t
y
,
S
u
r
a
b
a
y
a
,
I
n
d
o
n
e
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
2
9
,
2
0
2
0
R
ev
is
ed
Ma
y
1
7
,
2
0
2
1
Acc
ep
ted
J
u
l 2
3
,
2
0
2
1
Th
is
re
se
a
rc
h
a
ime
d
to
in
teg
ra
te
a
fa
c
e
re
c
o
g
n
it
io
n
c
a
p
a
b
il
it
y
i
n
a
s
m
a
rt
d
o
o
r
p
ro
t
o
ty
p
e
.
By
u
si
n
g
a
c
a
m
e
ra
-
b
a
se
d
fa
c
e
re
c
o
g
n
it
io
n
,
t
h
e
h
o
u
se
o
wn
e
r
d
o
e
s
n
o
t
n
e
e
d
t
o
m
a
k
e
p
h
y
sic
a
l
c
o
n
tac
t
to
o
p
e
n
th
e
d
o
o
r.
Av
o
id
p
h
y
sic
a
l
c
o
n
tac
t
is
imp
o
rtan
t
d
u
e
t
o
t
h
e
c
o
ro
n
a
v
iru
s
d
ise
a
se
2
0
1
9
(COV
ID1
9
)
p
a
n
d
e
m
ic.
Ra
sp
b
e
rry
P
i
3
B
wa
s
u
se
d
a
s
t
h
e
m
a
in
c
o
n
tro
ll
e
r,
wh
il
e
a
se
rv
o
m
o
to
r
wa
s
u
ti
li
z
e
d
a
s
a
l
o
c
k
i
n
g
d
o
o
r
a
c
tu
a
t
o
r.
Th
e
p
ro
g
ra
m
wa
s
d
e
v
e
lo
p
e
d
u
sin
g
N
o
d
e
-
RED
,
Bly
n
k
,
a
n
d
m
e
ss
a
g
e
q
u
e
u
e
tele
m
e
try
tran
sp
o
rt
(
M
QT
T
)
p
latfo
rm
s
wh
ich
a
re
v
e
ry
p
o
we
rfu
l
f
o
r
d
e
v
e
lo
p
i
n
g
i
n
tern
e
t
o
f
t
h
in
g
s
(Io
T)
d
e
v
ice
s.
All
o
f
t
h
e
p
r
o
g
ra
m
s
we
re
c
o
d
e
d
u
si
n
g
P
y
t
h
o
n
.
Ha
a
r
c
a
sc
a
d
e
a
n
d
lo
c
a
l
b
in
a
ry
p
a
tt
e
rn
h
isto
g
ra
m
m
e
th
o
d
s
we
re
i
m
p
lem
e
n
ted
o
n
t
h
e
fa
c
e
re
c
o
g
n
it
i
o
n
sta
g
e
.
G
o
o
g
le
As
sista
n
t
in
t
e
g
ra
ti
o
n
wa
s
d
o
n
e
b
y
u
sin
g
D
ialo
g
flo
w
a
n
d
F
ireb
a
se
a
s
G
o
o
g
le
Clo
u
d
se
rv
ice
s.
In
teg
ra
ti
o
n
o
f
fa
c
e
re
c
o
g
n
it
io
n
a
n
d
th
e
s
m
a
rt
d
o
o
r
wa
s
su
c
c
e
ss
fu
l.
Th
e
sm
a
rt
d
o
o
r
wa
s
u
n
l
o
c
k
e
d
if
fa
c
e
s
we
re
re
c
o
g
n
ize
d
(a
v
e
ra
g
e
th
re
sh
o
ld
=
6
0
%
).
If
a
fa
c
e
wa
s
n
o
t
re
c
o
g
n
ize
d
,
a
n
e
m
a
il
n
o
ti
fica
ti
o
n
c
o
n
tain
i
n
g
a
fa
c
e
ima
g
e
is
se
n
t
t
o
th
e
h
o
u
se
o
w
n
e
r.
T
h
e
G
o
o
g
le
As
sista
n
t
c
o
u
ld
h
a
n
d
le
u
se
r
re
q
u
e
sts
su
c
c
e
ss
fu
ll
y
wit
h
a
su
c
c
e
ss
ra
te
o
f
9
2
.
8
%
fr
o
m
1
4
7
tri
a
ls
.
K
ey
w
o
r
d
s
:
Dig
ital a
s
s
i
s
tan
t
Face
d
etec
tio
n
Face
r
ec
o
g
n
itio
n
R
asp
b
er
r
y
Sm
ar
t d
o
o
r
l
o
ck
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
I
v
an
Su
r
y
a
Hu
to
m
o
Dep
ar
tm
en
t o
f
E
lectr
ical
E
n
g
i
n
ee
r
in
g
a
n
d
C
o
m
p
u
ter
Scien
c
e,
C
o
lleg
e
o
f
E
lectr
ical
an
d
C
o
m
p
u
ter
E
n
g
in
ee
r
in
g
,
Natio
n
al
C
h
iao
T
u
n
g
Un
i
v
er
s
ity
No
.
1
0
0
1
,
Dax
u
e
R
d
,
E
ast Dis
tr
ict,
Hsi
n
ch
u
C
ity
,
T
aiwa
n
3
0
0
1
0
E
m
ail: h
u
to
m
o
iv
an
.
eic0
8
g
@
n
ctu
.
ed
u
.
tw
1.
I
NT
RO
D
UCT
I
O
N
I
m
p
lem
en
tatio
n
o
f
in
ter
n
et
o
f
th
in
g
s
(
I
o
T
)
f
o
r
s
m
ar
t
h
o
m
e
n
o
wad
ay
s
is
f
o
c
u
s
ed
o
n
ac
ce
s
s
ib
ilit
y
an
d
s
ec
u
r
ity
s
y
s
tem
s
[
1
]
,
[
2
]
.
I
n
th
e
p
ast,
p
eo
p
le
u
s
ed
a
m
ec
h
an
ic
d
o
o
r
with
a
k
ey
an
d
p
ad
l
o
ck
,
wh
er
e
th
e
d
o
o
r
m
u
s
t
b
e
o
p
en
ed
with
a
p
h
y
s
ical
k
ey
[
3
]
.
T
h
is
s
y
s
tem
is
n
o
t
s
o
s
ec
u
r
e
b
ec
a
u
s
e
an
y
o
n
e
w
h
o
h
as
th
e
k
ey
ca
n
en
ter
th
e
d
o
o
r
.
A
h
o
u
s
e
o
wn
er
also
m
u
s
t b
r
in
g
a
p
h
y
s
ical
k
ey
with
h
im
s
o
h
e
co
u
ld
o
p
e
n
t
h
e
d
o
o
r
.
R
ec
en
tly
,
elec
tr
o
n
ic
e
.
g
.
,
ab
s
tr
ac
t
n
ea
r
f
ield
co
m
m
u
n
icatio
n
(
NFC
)
an
d
b
io
m
etr
ic
au
t
h
en
ticatio
n
tech
n
iq
u
es
ar
e
ap
p
lied
to
o
p
e
n
a
d
o
o
r
.
B
io
m
etr
ic
m
eth
o
d
s
ar
e
th
e
u
s
e
o
f
b
i
o
lo
g
ical
ch
a
r
ac
ter
is
tics
o
f
liv
in
g
th
in
g
s
th
at
ar
e
u
n
iq
u
e
an
d
n
o
t
id
en
tical
to
o
n
e
an
o
t
h
er
f
o
r
s
ec
u
r
ity
p
u
r
p
o
s
es
[
4
]
.
B
io
m
etr
i
c
m
eth
o
d
s
th
at
a
r
e
wid
ely
ap
p
lied
in
th
e
s
m
ar
t
d
o
o
r
ar
e
f
in
g
er
p
r
in
t.
T
h
e
in
teg
r
atio
n
o
f
f
ac
e
r
ec
o
g
n
itio
n
an
d
v
o
ice
r
ec
o
g
n
itio
n
with
th
e
s
m
ar
t d
o
o
r
is
co
n
s
id
er
ed
to
b
e
m
o
r
e
ef
f
icien
t a
n
d
th
e
m
o
s
t n
atu
r
al
o
n
e
th
an
p
r
ev
io
u
s
m
eth
o
d
s
[
5
]
.
B
y
u
s
in
g
a
ca
m
er
a
-
b
ased
f
ac
e
r
ec
o
g
n
itio
n
,
th
e
h
o
u
s
e
o
wn
er
d
o
es
n
o
t
n
ee
d
to
m
ak
e
p
h
y
s
ical
co
n
tac
t
to
o
p
e
n
th
e
d
o
o
r
b
ec
au
s
e
it
will
o
p
en
au
t
o
m
atica
lly
wh
en
an
a
u
th
o
r
ita
tiv
e
f
ac
e
is
r
ec
o
g
n
ized
.
Du
e
to
th
e
co
r
o
n
av
ir
u
s
d
is
ea
s
e
2
0
1
9
(
C
OVI
D
1
9
)
p
a
n
d
em
ic,
it
is
r
ea
lly
im
p
o
r
tan
t
to
u
s
e
a
b
io
m
etr
ics
s
o
lu
tio
n
th
at
d
o
es
n
o
t
n
ee
d
p
h
y
s
ical
co
n
tact.
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
.
11
,
No
.
1
,
M
a
r
ch
20
22
:
1
-
9
2
Pre
v
io
u
s
r
esear
ch
,
L
im
et
a
l.
[
6
]
d
ev
elo
p
ed
a
f
ac
e
r
ec
o
g
n
itio
n
m
eth
o
d
f
o
r
th
e
d
o
o
r
,
b
u
t
it
is
n
o
t
ap
p
lied
to
an
y
p
h
y
s
ical
d
o
o
r
k
ey
,
in
s
tead
,
th
ey
u
s
e
a
m
ag
n
etic
d
o
o
r
lo
ck
,
s
o
it
is
s
till
n
o
t
ap
p
licab
le
to
all
k
in
d
s
o
f
d
o
o
r
s
.
He
also
s
till
u
s
es
a
lap
to
p
as
th
e
c
o
n
tr
o
ller
wh
ich
m
ak
es
h
is
s
y
s
tem
less
p
o
r
tab
le
an
d
d
id
n
o
t
d
ev
elo
p
a
n
y
n
o
tific
atio
n
s
y
s
tem
wh
en
th
er
e
is
an
u
n
k
n
o
wn
p
er
s
o
n
th
at
tr
ies to
o
p
en
th
e
d
o
o
r
.
T
o
o
v
e
r
co
m
e
t
h
o
s
e
d
is
ad
v
an
t
ag
es
f
r
o
m
p
r
ev
i
o
u
s
r
esu
lts
,
we
eq
u
ip
a
s
m
ar
t
d
o
o
r
p
r
o
to
ty
p
e
with
f
ac
e
r
ec
o
g
n
itio
n
t
h
at
ca
n
ap
p
licab
l
e
to
n
ea
r
ly
all
k
in
d
s
o
f
d
o
o
r
s
.
W
e
also
ad
d
a
n
atu
r
al
u
s
er
in
ter
f
ac
e
s
o
u
s
er
s
ca
n
“talk
”
to
a
d
o
o
r
.
A
n
o
tific
atio
n
s
y
s
tem
is
also
p
r
o
v
id
ed
,
Go
o
g
le
Ass
is
tan
t
s
er
v
ice
is
u
s
ed
to
p
r
o
v
id
e
clea
r
er
in
f
o
r
m
atio
n
ab
o
u
t
th
e
d
o
o
r
c
o
n
d
itio
n
.
B
y
in
teg
r
atin
g
s
m
ar
t
d
o
o
r
lo
ck
with
f
ac
e
r
ec
o
g
n
itio
n
an
d
Go
o
g
le
Ass
i
s
tan
t,
u
s
er
s
ar
e
ex
p
ec
ted
t
o
h
av
e
a
m
o
r
e
e
f
f
icien
t,
s
af
e,
a
n
d
in
ter
ac
tiv
e
way
to
u
n
lo
ck
in
g
th
e
d
o
o
r
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
e
R
asp
b
er
r
y
Pi
3
B
is
u
s
ed
as
th
e
m
ain
c
o
n
tr
o
ller
o
f
th
e
s
m
ar
t
d
o
o
r
as
s
h
o
wn
in
Fig
u
r
e
1
.
T
h
is
in
clu
d
es
h
an
d
lin
g
im
ag
e
p
r
o
c
ess
in
g
.
R
asp
b
er
r
y
Pi
ca
m
er
a
V2
is
u
s
ed
to
ca
p
tu
r
e
th
e
im
a
g
e
wh
ich
th
en
is
f
ed
to
Haa
r
ca
s
ca
d
e
as
t
h
e
f
ac
e
d
etec
tio
n
alg
o
r
ith
m
[
7
]
.
I
f
a
f
a
ce
is
d
etec
ted
,
th
e
lo
ca
l
b
in
ar
y
p
atter
n
h
is
to
g
r
am
alg
o
r
ith
m
is
th
en
u
tili
ze
d
to
r
ec
o
g
n
ize
wh
o
s
e
f
ac
e
is
in
th
at
im
ag
e.
W
e
im
p
lem
en
t
t
h
e
al
g
o
r
ith
m
u
s
in
g
o
p
en
C
V
lib
r
ar
ies in
Py
th
o
n
[
8
]
.
Af
ter
th
e
im
a
g
e
p
r
o
ce
s
s
in
g
s
t
ep
is
d
o
n
e,
d
ata
is
th
en
f
ed
to
No
d
e
-
R
ed
w
h
ich
will
s
en
d
it
to
a
s
er
v
o
m
o
to
r
.
T
h
is
m
o
to
r
co
n
tr
o
ls
th
e
d
o
o
r
l
o
ck
.
No
d
e
-
R
ED
will
also
s
en
d
d
ata
to
Fire
b
ase
an
d
th
e
B
ly
n
k
ap
p
licatio
n
o
n
s
m
ar
tp
h
o
n
es
s
o
th
e
h
o
u
s
e
o
w
n
er
co
u
ld
g
et
n
o
tific
atio
n
s
.
Dialo
g
f
lo
w
th
en
r
etr
iev
es
d
ata
f
r
o
m
Fire
b
ase
an
d
f
o
r
war
d
s
it
to
Go
o
g
le
Ass
is
tan
t.
A
u
s
er
ca
n
co
n
d
u
ct
tr
ai
n
in
g
p
h
r
ases
th
at
ar
e
u
s
ed
to
tr
ig
g
er
Go
o
g
le
Ass
is
tan
t
[
9
]
.
R
a
s
p
b
er
r
y
Pi
3
is
also
u
s
ed
to
co
n
tr
o
l
th
e
s
p
ea
k
er
an
d
m
icr
o
p
h
o
n
e
with
Go
o
g
le
AI
Y
Vo
ice
Kit.
Fig
u
r
e
1
.
Ov
e
r
all
s
y
s
tem
d
esig
n
2
.
1
.
H
a
a
r
c
a
s
ca
de
a
nd
lo
ca
l
bin
a
ry
pa
t
t
er
n his
t
o
g
ra
m
a
s
f
a
ce
det
ec
t
io
n a
nd
f
a
ce
r
ec
o
g
nitio
n a
lg
o
rit
hm
Haa
r
ca
s
ca
d
e
alg
o
r
ith
m
is
u
s
ed
f
o
r
th
e
f
ac
e
d
etec
tio
n
p
r
o
c
ess
.
I
n
g
en
er
al,
th
e
Haar
lik
e
f
ea
tu
r
e
is
u
s
ed
to
d
etec
t
o
b
jects
in
d
ig
it
al
im
ag
es.
T
h
e
ter
m
Haa
r
s
h
o
ws
a
m
ath
em
atica
l
f
u
n
ctio
n
(
Haa
r
wav
elet
)
i
n
th
e
f
o
r
m
o
f
a
b
o
x
,
t
h
e
p
r
i
n
cip
le
is
th
e
s
am
e
as
in
th
e
Fo
u
r
ier
f
u
n
ctio
n
[
1
0
]
.
At
f
ir
s
t,
im
a
g
e
p
r
o
ce
s
s
in
g
is
o
n
ly
b
y
lo
o
k
in
g
at
th
e
r
ed
,
g
r
ee
n
,
b
lu
e
(
R
GB
)
v
alu
e
o
f
ea
ch
p
ix
el,
b
u
t
t
h
is
m
eth
o
d
f
o
u
n
d
alr
ea
d
y
in
e
f
f
ec
tiv
e
[
1
1
]
,
[
1
2
]
.
Vio
la
an
d
J
o
n
es th
en
d
e
v
elo
p
ed
it so
th
at
Haa
r
lik
e
f
ea
t
u
r
es we
r
e
f
o
r
m
ed
[
1
3
]
.
Face
r
ec
o
g
n
itio
n
is
th
e
n
ex
t
s
tep
af
ter
f
ac
e
d
etec
tio
n
.
A
f
ac
e
ca
n
b
e
d
etec
ted
th
r
o
u
g
h
p
h
o
to
s
an
d
v
id
eo
s
.
B
y
u
tili
zin
g
th
e
tr
ain
in
g
r
esu
lts
f
r
o
m
Haa
r
ca
s
ca
d
e,
th
e
r
esu
lts
o
f
th
is
p
r
o
ce
s
s
ar
e
co
m
b
in
ed
with
th
e
im
ag
e
m
atch
in
g
p
r
o
ce
s
s
with
th
e
lo
ca
l
b
in
a
r
y
p
a
tter
n
h
is
to
g
r
am
(
L
B
PH)
alg
o
r
ith
m
[
1
4
]
.
W
ith
th
is
m
eth
o
d
,
p
h
o
to
s
th
at
h
av
e
b
ee
n
lear
n
ed
will
b
e
m
atch
ed
with
th
e
d
et
ec
tio
n
r
esu
lts
f
r
o
m
s
tr
ea
m
in
g
ca
m
er
as.
W
h
er
e
in
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
A
s
ma
r
t d
o
o
r
p
r
o
to
typ
e
w
ith
a
fa
ce
r
ec
o
g
n
itio
n
c
a
p
a
b
ilit
y
(
I
va
n
S
u
r
ya
Hu
to
mo
)
3
th
e
latter
,
s
o
m
e
im
ag
es
in
th
e
d
atab
ase
ar
e
th
en
m
atch
ed
with
u
tili
zin
g
h
is
to
g
r
am
v
alu
es
th
at
h
av
e
b
ee
n
ex
tr
ac
ted
f
r
o
m
th
e
im
a
g
e
b
y
u
tili
zin
g
th
e
L
B
PH.
T
o
m
atch
th
e
o
wn
e
r
'
s
f
ac
e,
an
eq
u
atio
n
is
u
s
ed
to
g
et
th
e
ap
p
r
o
ac
h
o
f
th
e
h
is
to
g
r
a
m
v
alu
e
wh
ich
is
th
en
u
s
ed
as
a
p
r
ed
ictiv
e
v
alu
e
to
id
en
tify
th
e
o
wn
er
o
f
th
e
f
ac
e
[
1
5
]
.
T
h
er
e
f
o
r
e,
t
h
e
alg
o
r
ith
m
o
u
tp
u
t
is
f
r
o
m
th
e
im
ag
e
with
th
e
clo
s
est
h
is
to
g
r
am
.
T
h
e
alg
o
r
ith
m
m
u
s
t
also
r
etu
r
n
th
e
ca
lc
u
lated
d
is
tan
ce
,
wh
ich
ca
n
b
e
u
s
ed
as
a
m
ea
s
u
r
e
o
f
co
n
f
id
e
n
ce
v
alu
e
[
1
6
]
.
T
h
r
esh
o
ld
v
alu
es
an
d
c
o
n
f
id
e
n
ce
ca
n
th
en
b
e
u
s
ed
au
to
m
atica
lly
to
esti
m
ate
wh
eth
er
th
e
alg
o
r
ith
m
h
as
r
ec
o
g
n
ized
t
h
e
im
ag
e
co
r
r
ec
tly
.
I
f
th
e
c
o
n
f
id
e
n
ce
v
alu
e
is
lo
wer
th
an
th
e
th
r
esh
o
ld
,
th
e
alg
o
r
ith
m
h
a
s
s
u
cc
ee
d
ed
in
r
ec
o
g
n
izin
g
th
e
im
ag
e.
2
.
2
.
H
a
rdwa
re
des
ig
n
Pre
v
io
u
s
r
esear
ch
u
s
ed
lap
t
o
p
s
as
th
e
m
ain
p
r
o
ce
s
s
o
r
o
f
f
a
ce
im
ag
es
wh
ich
wer
e
less
p
o
r
tab
le
an
d
less
f
lex
ib
le
wh
en
o
p
er
ated
p
e
r
m
an
en
tly
[
6
]
.
I
n
th
at
s
tu
d
y
,
it
was r
ec
o
m
m
en
d
ed
to
r
ep
lace
t
h
e
lap
to
p
p
latf
o
r
m
with
a
s
m
aller
m
icr
o
co
n
tr
o
ller
th
at
ca
n
b
e
a
p
p
lied
t
o
v
ar
io
u
s
s
y
s
tem
s
,
n
am
ely
R
asp
b
er
r
y
P
i.
R
asp
b
er
r
y
Pi
is
a
s
m
all,
les
s
ex
p
en
s
iv
e,
p
o
wer
f
u
l,
an
d
r
o
b
u
s
t
m
icr
o
co
n
t
r
o
lle
r
[
1
7
]
.
W
e
u
s
e
a
R
asp
b
er
r
y
Pi
3
B
b
ec
au
s
e
it
is
ca
p
ab
le
to
d
o
f
ac
e
r
ec
o
g
n
itio
n
,
co
m
p
atib
le
with
Go
o
g
le
AI
Y
Vo
ice
Kit,
an
d
h
as
an
ea
s
y
g
r
ap
h
ical
u
s
er
in
ter
f
ac
e
(
GUI
)
with
a
R
asp
b
ian
o
p
e
r
atin
g
s
y
s
tem
th
at
c
an
b
e
ex
p
an
d
e
d
with
v
a
r
io
u
s
p
latf
o
r
m
s
s
u
ch
as
Op
en
C
V,
No
d
e
-
R
ED
,
m
ess
a
g
e
q
u
eu
e
telem
etr
y
tr
an
s
p
o
r
t
(
MQ
T
T
)
,
an
d
s
o
o
n
[
1
8
]
,
[
1
9
]
.
W
e
s
h
o
w
o
u
r
h
ar
d
war
e
d
iag
r
am
in
Fi
g
u
r
e
2
.
A
p
o
wer
b
a
n
k
5
V
2
A
n
u
m
b
er
1
,
is
u
s
ed
t
o
s
u
p
p
ly
R
asp
b
e
r
r
y
Pi
a
n
d
th
e
s
er
v
o
m
o
to
r
n
u
m
b
e
r
9
.
Fig
u
r
e
2
.
Har
d
war
e
d
esig
n
d
ia
g
r
am
R
asp
b
er
r
y
Pi
ca
m
er
a
V2
n
u
m
b
er
3
is
u
s
ed
f
o
r
f
ac
e
r
ec
o
g
n
iti
o
n
[
1
4
]
.
Vo
ice
h
a
r
d
war
e
attac
h
ed
o
n
t
o
p
(
HAT
)
n
u
m
b
e
r
4
w
ill
b
e
in
s
talled
o
n
to
p
o
f
R
asp
b
er
r
y
Pi
3
B
wh
ich
is
d
esig
n
ed
as
HA
T
.
Fu
r
th
er
m
o
r
e,
th
e
m
icr
o
p
h
o
n
e
Nu
m
b
e
r
7
,
s
p
ea
k
er
s
Nu
m
b
er
5
,
an
d
th
e
ar
c
ad
e
b
u
tto
n
n
u
m
b
er
6
will
b
e
co
n
n
ec
ted
to
th
e
R
asp
b
er
r
y
Pi
3
B
v
ia
HAT
.
W
h
ile
th
e
HAT
in
s
talled
o
n
th
e
R
asp
b
er
r
y
Pi
3
,
g
e
n
er
al
p
u
r
p
o
s
e
in
p
u
t
o
u
tp
u
t
(
GPI
O)
o
n
th
e
R
asp
b
er
r
y
Pi
3
B
ca
n
n
o
t
b
e
ac
ce
s
s
ed
d
ir
ec
tly
,
s
o
ac
ce
s
s
in
g
GPI
O
ca
n
b
e
d
o
n
e
th
r
o
u
g
h
Vo
ice
HAT
[
2
0
]
.
GPI
O
Vo
ice
HAT
is
co
n
n
ec
ted
to
Ar
d
u
in
o
n
u
m
b
er
8
a
n
d
p
ass
iv
e
in
f
r
ar
ed
s
en
s
o
r
(
PIR
s
en
s
o
r
)
n
u
m
b
er
1
0
.
W
e
u
s
e
Ar
d
u
in
o
to
o
v
er
co
m
e
th
e
jitt
er
o
n
th
e
s
er
v
o
m
o
to
r
n
u
m
b
er
9
.
J
itter
is
an
u
n
s
tab
le
s
er
v
o
m
o
v
em
en
t
c
au
s
ed
b
y
a
b
ad
p
u
ls
e
-
wid
th
m
o
d
u
latio
n
(
PW
M)
s
ig
n
al
[
2
1
]
.
R
asp
b
er
r
y
Pi
3
B
will
o
n
ly
p
er
f
o
r
m
d
ig
ital tr
ig
g
er
in
g
o
n
Ar
d
u
in
o
an
d
s
u
b
s
eq
u
en
tly
Ar
d
u
in
o
wh
i
ch
will e
m
it
PW
M
s
ig
n
als
to
c
h
an
g
e
s
er
v
o
an
g
les
[
2
2
]
.
PIR
s
en
s
o
r
is
u
s
ed
to
d
e
tect
a
p
er
s
o
n
in
f
r
o
n
t
o
f
t
h
e
d
o
o
r
,
s
o
th
e
f
ac
e
r
ec
o
g
n
itio
n
c
an
b
e
s
tar
ted
.
T
h
is
m
eth
o
d
ca
n
s
av
e
m
em
o
r
y
r
e
s
o
u
r
ce
u
s
ag
e
a
n
d
p
r
ev
en
t
te
m
p
er
atu
r
e
r
aisi
n
g
in
R
asp
b
er
r
y
Pi
3
B
.
T
h
e
lim
it
s
witch
n
u
m
b
er
1
1
is
in
s
talled
o
n
th
e
d
o
o
r
f
r
am
e
to
f
in
d
o
u
t
wh
eth
er
th
e
d
o
o
r
is
clo
s
ed
o
r
n
o
t.
W
h
en
th
e
d
o
o
r
is
clo
s
ed
,
th
e
s
er
v
o
will lo
ck
t
h
e
d
o
o
r
.
T
h
e
s
m
ar
t d
o
o
r
p
r
o
to
t
y
p
e
ca
n
b
e
s
ee
n
in
Fig
u
r
e
3
.
2
.
3
.
So
f
t
wa
re
des
ig
n
T
h
e
m
ec
h
an
is
m
o
f
o
u
r
s
m
ar
t
d
o
o
r
is
s
h
o
wn
in
Fig
u
r
e
4
.
W
h
en
th
e
s
m
ar
t
d
o
o
r
is
in
itiated
in
itially
,
if
th
e
u
s
er
d
o
es
n
o
t
p
r
ess
a
b
u
tt
o
n
to
ad
d
f
ac
e
d
ata,
th
e
s
y
s
tem
will
d
etec
t
a
p
er
s
o
n
’
s
ex
is
ten
ce
in
f
r
o
n
t
o
f
th
e
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
.
11
,
No
.
1
,
M
a
r
ch
20
22
:
1
-
9
4
d
o
o
r
.
I
f
th
er
e
is
a
p
er
s
o
n
,
th
e
ca
m
er
a
will
ca
p
tu
r
e
an
d
tr
y
t
o
r
ec
o
g
n
ize
h
is
f
ac
e.
I
f
it
is
r
ec
o
g
n
ized
,
th
e
d
o
o
r
will
b
e
u
n
lo
c
k
ed
,
th
en
t
h
e
d
o
o
r
s
tatu
s
an
d
th
e
f
ac
e
r
ec
o
g
n
itio
n
d
ata
ar
e
u
p
lo
ad
e
d
to
Fire
b
ase
s
o
th
at
th
e
Go
o
g
le
Ass
is
tan
t
ca
n
r
ea
d
th
e
m
th
r
o
u
g
h
Fire
b
ase
.
T
h
e
s
y
s
tem
th
en
s
en
d
s
an
e
-
m
ail
to
th
e
h
o
u
s
e
o
w
n
e
r
.
T
h
e
au
th
en
ticated
p
er
s
o
n
ca
n
o
p
en
th
e
d
o
o
r
.
A
lim
it
s
witch
is
u
s
ed
to
d
etec
t
th
e
d
o
o
r
s
tatu
s
.
I
f
th
e
d
o
o
r
is
clo
s
ed
,
th
e
s
er
v
o
will
r
o
tate
to
l
o
ck
t
h
e
d
o
o
r
.
Ho
wev
e
r
,
if
th
e
f
ac
e
is
n
o
t
r
ec
o
g
n
ized
,
th
e
d
o
o
r
c
an
n
o
t
b
e
u
n
lo
c
k
ed
.
Attem
p
ts
to
ac
ce
s
s
th
e
d
o
o
r
a
r
e
r
ec
o
r
d
e
d
in
Fire
b
ase
an
d
a
n
o
tific
atio
n
em
ail
is
s
en
t
to
th
e
h
o
u
s
e
o
wn
e
r
to
in
f
o
r
m
t
h
ese
attem
p
ts
.
I
f
th
e
h
o
m
eo
w
n
er
wan
ts
to
ad
d
n
ew
f
ac
e
d
ata,
h
e
m
u
s
t
p
r
ess
th
e
ca
p
tu
r
e
b
u
tto
n
an
d
th
e
n
en
ter
th
e
n
u
m
b
er
th
at
r
ep
r
esen
ts
th
e
o
w
n
er
'
s
i
d
en
tity
(
ID
)
,
th
e
n
t
h
e
ca
m
er
a
will
tak
e
3
0
f
ac
e
s
am
p
le
s
.
B
ec
au
s
e
tr
ain
in
g
d
o
esn
’
t
n
ee
d
a
ca
m
er
a
lik
e
a
ca
p
tu
r
e
an
d
r
ec
o
g
n
itio
n
p
r
o
ce
s
s
,
th
e
p
r
o
ce
s
s
is
s
ep
ar
ate
f
r
o
m
th
e
m
ain
p
r
o
ce
s
s
.
T
h
e
s
o
f
twar
e
d
iag
r
am
b
lo
c
k
o
f
th
e
s
m
ar
t d
o
o
r
ca
n
b
e
s
ee
n
in
Fig
u
r
e
5
.
T
h
e
wh
o
le
s
y
s
tem
is
co
n
n
ec
ted
to
No
d
e
R
E
D
.
No
d
e
-
R
E
D
p
r
o
v
id
es
m
ess
ag
e
in
f
o
r
m
atio
n
r
ec
eiv
ed
f
r
o
m
th
e
f
ac
e
r
ec
o
g
n
itio
n
p
r
o
g
r
am
t
h
r
o
u
g
h
MQ
T
T
b
r
o
k
er
to
ce
r
tain
p
ath
s
in
f
ir
eb
ase
[
2
3
]
.
Fire
b
ase
t
h
en
will
co
m
m
u
n
icate
with
Dialo
g
f
lo
w
wh
ich
is
in
teg
r
ated
with
th
e
Go
o
g
le
Ass
is
tan
t
s
er
v
ice
o
n
th
e
u
s
er
'
s
s
m
ar
tp
h
o
n
e
[
2
4
]
.
No
d
e
-
R
E
D
co
m
m
u
n
icat
es
with
th
e
B
ly
n
k
u
s
in
g
a
v
ir
t
u
al
p
in
[
2
5
]
.
I
f
B
ly
n
k
o
r
d
er
s
t
o
lo
ck
th
e
d
o
o
r
,
it
w
ill
g
iv
e
a
m
ess
ag
e
o
n
an
MQ
T
T
to
p
ic
s
o
th
at
No
d
e
-
R
E
D
ca
n
co
n
tr
o
l
th
e
s
er
v
o
.
A
f
ac
e
r
ec
o
g
n
itio
n
p
r
o
g
r
am
ex
ch
an
g
es
d
ata
with
No
d
e
-
R
E
D
v
ia
MQ
T
T
b
r
o
k
e
r
s
.
Af
ter
th
e
f
ac
e
ca
p
tu
r
e
is
d
o
n
e,
3
0
im
a
g
es
o
f
o
n
e
f
ac
e
ar
e
cr
ea
ted
an
d
f
e
d
to
th
e
tr
ain
in
g
p
r
o
ce
s
s
u
s
in
g
L
B
PH
to
m
ak
e
a
p
atter
n
h
is
to
g
r
am
f
o
r
ea
ch
f
ac
e.
I
f
a
f
ac
e
is
r
ec
o
g
n
ized
,
th
en
th
e
n
am
e
at
ce
r
tain
Fire
b
ase’
s
in
d
ex
is
r
et
r
iev
ed
.
T
h
e
n
am
e
is
co
n
v
er
te
d
to
a
s
o
u
n
d
f
ile
b
y
Go
o
g
le
T
T
S lib
r
ar
y
[
2
6
]
.
Fig
u
r
e
3
.
Sm
ar
t
d
o
o
r
ass
em
b
led
m
in
iatu
r
e
Fig
u
r
e
4
.
Gen
e
r
al
s
o
f
twar
e
f
lo
wch
ar
t o
f
th
e
s
m
ar
t d
o
o
r
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
A
s
ma
r
t d
o
o
r
p
r
o
to
typ
e
w
ith
a
fa
ce
r
ec
o
g
n
itio
n
c
a
p
a
b
ilit
y
(
I
va
n
S
u
r
ya
Hu
to
mo
)
5
Fig
u
r
e
5
.
So
f
twar
e
r
elatio
n
s
h
i
p
b
lo
ck
d
iag
r
am
o
f
s
m
ar
t
d
o
o
r
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
I
n
th
is
ch
ap
ter
,
we
co
n
d
u
ct
e
x
p
er
im
en
ts
to
f
in
d
t
h
e
b
est
ca
m
er
a
d
is
tan
ce
an
d
alg
o
r
ith
m
p
ar
am
eter
s
(
m
in
n
eig
h
b
o
r
an
d
s
ca
le
f
ac
to
r
)
.
An
o
t
h
er
e
x
p
er
im
e
n
t
is
d
o
n
e
to
f
in
d
th
e
a
v
er
ag
e
co
n
f
id
en
ce
th
r
esh
o
ld
in
th
e
f
ac
e
r
ec
o
g
n
itio
n
p
r
o
ce
s
s
.
3
.
1
.
Va
r
y
ing
ca
m
er
a
dis
t
a
nc
e
B
ased
o
n
th
e
e
x
p
er
im
en
t,
th
e
d
is
tan
ce
o
f
th
e
ca
m
er
a
af
f
ec
ts
th
e
r
eso
lu
tio
n
o
f
th
e
p
r
o
d
u
ce
d
d
ataset.
T
h
is
d
ataset
r
eso
lu
tio
n
af
f
ec
ts
tr
ain
in
g
tim
e,
ac
cu
r
ac
y
,
a
n
d
f
ac
e
r
ec
o
g
n
itio
n
tim
e
as
T
ab
le
1
.
T
h
e
T
ab
le
1
s
h
o
ws
th
at
th
e
cl
o
s
er
th
e
f
ac
e
d
i
s
tan
ce
to
th
e
ca
m
er
a,
th
e
h
ig
h
e
r
th
e
r
eso
lu
tio
n
o
f
th
e
d
ataset.
I
f
t
h
e
d
ata
r
eso
lu
tio
n
is
g
ettin
g
h
ig
h
er
,
th
e
tr
ain
in
g
tim
e
r
e
q
u
ir
e
d
is
lo
n
g
e
r
,
b
u
t
th
e
ac
cu
r
ac
y
o
f
f
ac
ial
r
ec
o
g
n
itio
n
in
cr
ea
s
es
to
5
5
.
0
3
%,
an
d
th
e
f
ac
e
r
ec
o
g
n
itio
n
tim
e
is
f
aster
to
2
.
4
9
s
(
c
o
m
p
a
r
ed
t
o
th
e
d
ataset
with
s
m
aller
r
eso
lu
tio
n
)
.
T
h
e
h
i
g
h
-
r
eso
lu
ti
o
n
d
ataset
en
ab
les
L
B
PH
to
m
ap
h
is
to
g
r
am
s
with
m
o
r
e
d
etail,
s
o
it
ca
n
im
p
r
o
v
e
ac
cu
r
ac
y
.
Fr
o
m
th
e
a
b
o
v
e
test
s
,
th
e
b
est d
is
tan
ce
is
3
0
cm
.
T
ab
le
1
.
C
o
m
p
a
r
is
o
n
o
f
v
ar
io
u
s
ca
m
er
a
d
is
tan
ce
s
Fa
c
e
d
i
st
a
n
c
e
t
o
c
a
mera
D
a
t
a
s
e
t
r
e
so
l
u
t
i
o
n
Tr
a
i
n
i
n
g
t
i
me
A
c
c
u
r
a
c
y
F
a
c
e
r
e
c
o
g
n
i
t
i
o
n
t
i
m
e
4
5
c
m
1
9
1
x
1
9
1
p
x
3
.
6
5
s
4
2
.
2
0
%
3
.
0
3
1
s
3
0
c
m
3
2
0
x
3
2
0
p
x
9
.
4
5
s
5
5
.
3
0
%
2
.
4
9
s
3
.
2
.
Va
r
y
ing
t
he
m
in
neig
hb
o
r
a
nd
s
ca
le
f
a
ct
o
r
pa
ra
m
e
t
e
rs
E
x
p
er
im
en
ts
a
r
e
d
o
n
e
to
f
i
n
d
th
e
m
o
s
t
o
p
tim
al
s
ca
le
f
ac
t
o
r
an
d
m
i
n
n
ei
g
h
b
o
r
p
ar
am
et
er
s
wh
ich
p
r
o
d
u
ce
d
th
e
b
est
ac
cu
r
ac
y
a
n
d
th
e
f
astes
t
f
ac
e
r
ec
o
g
n
itio
n
t
im
e.
Av
er
ag
e
ac
cu
r
ac
y
an
d
ti
m
e
wer
e
tak
e
n
f
r
o
m
1
0
x
f
ac
e
r
ec
o
g
n
itio
n
ex
p
er
im
en
ts
.
I
n
th
e
f
ir
s
t
test
,
th
e
m
in
n
eig
h
b
o
r
v
al
u
e
is
f
ix
ed
with
a
v
alu
e
o
f
3
an
d
t
h
e
s
ca
le
f
ac
to
r
v
alu
e
is
ch
an
g
ed
.
Af
ter
th
e
m
o
s
t
o
p
tim
al
s
ca
le
f
ac
to
r
v
alu
e
is
f
o
u
n
d
,
th
e
s
ca
le
f
ac
to
r
v
alu
e
is
f
ix
ed
an
d
th
e
m
i
n
n
eig
h
b
o
r
v
a
lu
e
is
ch
an
g
ed
.
B
ased
o
n
th
e
m
o
s
t o
p
tim
al
p
ar
am
eter
s
im
u
latio
n
f
o
r
s
ca
le
f
ac
to
r
is
1
.
5
as T
ab
le
2
a
n
d
f
o
r
th
e
m
in
n
eig
h
b
o
r
is
2
as T
a
b
le
3
.
At
s
ca
le
f
ac
to
r
1
.
1
,
t
h
e
av
e
r
ag
e
tim
e
h
as
th
e
wo
r
s
t
n
u
m
b
er
o
f
6
.
1
2
s
.
as
T
ab
le
2
.
T
h
is
is
b
e
ca
u
s
e
th
e
r
ed
u
ctio
n
p
r
o
ce
s
s
to
m
atch
th
e
d
ataset
is
n
o
t
lar
g
e
e
n
o
u
g
h
s
o
th
at
th
e
r
ed
u
ctio
n
o
cc
u
r
s
r
ep
ea
ted
ly
a
n
d
r
eq
u
ir
es
a
lo
n
g
er
tim
e
to
m
atc
h
th
e
d
ataset.
On
i
n
cr
ea
s
in
g
e
ac
h
v
alu
e,
th
e
tim
e
p
r
o
d
u
ce
d
is
f
aster
an
d
at
1
.
5
h
as
th
e
b
es
t
v
alu
e.
I
n
th
e
s
ca
le
f
ac
to
r
,
t
h
e
f
ac
e
r
ec
o
g
n
itio
n
s
c
ale
f
ac
to
r
p
r
o
ce
s
s
h
as
in
cr
ea
s
e
d
tim
e
b
ec
a
u
s
e
th
e
r
esu
ltin
g
r
ed
u
ctio
n
v
alu
e
is
to
o
lar
g
e
s
o
it is
u
n
a
b
le
to
m
atch
th
e
d
ataset.
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
.
11
,
No
.
1
,
M
a
r
ch
20
22
:
1
-
9
6
T
ab
le
2
.
C
o
m
p
a
r
is
o
n
o
f
v
ar
io
u
s
s
ca
le
f
ac
to
r
v
alu
es
sca
l
e
f
a
c
t
o
r
M
i
n
n
e
i
g
h
b
o
r
A
c
c
u
r
a
c
y
a
v
e
r
a
g
e
(
%)
Ti
me
a
v
e
r
a
g
e
(
s)
1
3
Er
r
o
r
1
.
1
3
4
6
.
9
3
6
.
1
2
2
7
1
.
2
3
4
1
.
7
6
3
.
9
7
3
1
.
3
3
5
0
.
9
7
3
.
1
1
1
1
.
4
3
4
4
.
0
8
2
.
4
2
3
1
.
5
3
5
8
.
3
9
2
.
0
5
9
1
.
6
3
3
1
.
5
3
7
2
.
2
0
4
1
.
7
3
5
5
.
5
2
2
.
3
8
1
.
8
3
2
6
.
2
9
5
.
4
5
8
1
.
9
3
Er
r
o
r
T
ab
le
3
.
C
o
m
p
a
r
is
o
n
o
f
v
ar
io
u
s
m
in
n
eig
h
b
o
r
v
alu
es
S
c
a
l
e
f
a
c
t
o
r
M
i
n
n
e
i
g
h
b
o
r
A
c
c
u
r
a
c
y
a
v
e
r
a
g
e
(
%)
Ti
me
a
c
c
u
r
a
c
y
(
s)
1
.
5
1
4
2
.
0
3
2
2
.
0
4
8
4
1
.
5
2
6
2
.
0
4
2
.
0
9
3
1
.
5
3
5
9
.
0
6
2
.
0
8
1
1
.
5
4
5
1
.
7
1
2
.
1
1
8
1
.
5
5
4
7
.
8
2
7
2
.
0
8
7
4
1
.
5
6
5
7
.
1
2
2
.
1
0
5
1
.
5
7
5
8
.
1
1
2
.
0
2
4
1
.
5
8
5
0
.
7
1
2
.
0
7
9
1
.
5
9
4
6
.
1
8
2
.
1
7
1
1
.
5
10
5
8
.
4
7
6
.
0
3
7
B
ased
o
n
s
im
u
latio
n
r
esu
lts
as
s
h
o
wn
in
T
ab
le
3
,
th
e
b
est
m
i
n
n
eig
h
b
o
r
v
alu
e
is
2
,
wh
er
e
t
h
e
av
er
ag
e
f
ac
e
r
ec
o
g
n
itio
n
ac
cu
r
ac
y
ca
n
r
ea
ch
6
2
.
0
4
%
with
an
av
er
a
g
e
tim
e
o
f
2
.
1
s
.
Min
n
eig
h
b
o
r
d
o
es
n
o
t
af
f
ec
t
th
e
ac
cu
r
ac
y
an
d
s
p
ee
d
o
f
f
ac
e
r
ec
o
g
n
itio
n
.
T
h
is
h
ap
p
en
s
b
ec
au
s
e
th
e
f
ac
e
is
clo
s
e
to
th
e
ca
m
er
a
(
3
0
cm
)
an
d
th
e
f
ac
e
h
as
f
illed
th
e
en
tire
ca
m
er
a
f
r
am
e
s
o
t
h
at
th
e
p
o
s
s
ib
ilit
y
o
f
a
f
alse
p
o
s
itiv
e
is
v
er
y
s
m
al
l
an
d
d
o
es
n
o
t
af
f
ec
t
ac
cu
r
ac
y
.
Ho
wev
er
,
with
th
e
s
m
aller
m
in
n
eig
h
b
o
r
v
alu
e,
th
e
tim
e
to
r
ec
o
g
n
ize
f
ac
es
is
f
aster
ev
en
th
o
u
g
h
it
d
o
es
n
o
t
ch
an
g
e
s
ig
n
i
f
ican
tly
T
a
b
le
3
,
th
is
is
b
ec
au
s
e
wh
en
m
i
n
n
eig
h
b
o
r
is
s
m
aller
,
th
e
s
y
s
tem
will b
e
m
o
r
e
s
en
s
itiv
e
in
r
ec
o
g
n
izin
g
f
ac
es so
th
at
t
h
e
tim
e
to
r
ec
o
g
n
ize
f
ac
es is
f
aster
.
3
.
3
.
F
ind
ing
a
v
er
a
g
e
co
nfide
nce
a
s
a
t
hresh
o
ld f
o
r
un
lo
ck
ing
s
m
a
rt
do
o
rs
T
h
is
test
a
im
s
to
d
eter
m
in
e
th
e
ab
ilit
y
o
f
th
e
s
y
s
tem
to
r
ec
o
g
n
ize
f
ac
es.
I
n
th
is
test
,
th
e
d
ataset
o
n
ly
co
n
s
is
ts
o
f
3
r
eg
is
ter
ed
r
esp
o
n
d
en
ts
,
wh
ile
an
o
th
er
r
esp
o
n
d
en
t
will
n
o
t
b
e
r
e
g
is
ter
ed
in
th
e
d
ataset
an
d
th
e
s
y
s
tem
s
h
o
u
ld
n
o
t
b
e
g
iv
e
n
au
th
o
r
ity
to
o
p
en
t
h
e
d
o
o
r
lo
c
k
(
n
o
t r
ec
o
g
n
ized
)
,
s
ee
T
ab
le
4
f
o
r
th
e
d
etail.
Fro
m
th
e
ab
o
v
e
e
x
p
er
im
e
n
ts
,
it
was
f
o
u
n
d
th
at
all
f
ac
es
ar
e
r
ec
o
g
n
ized
.
I
n
t
h
e
f
i
r
s
t
test
,
J
is
ch
ak
was
n
o
t
ca
p
tu
r
e
d
in
th
e
d
ataset,
b
u
t
h
is
f
ac
e
was
r
ec
o
g
n
ized
as
Mic
h
ae
l
(
4
4
.
1
8
%),
wh
ile
Mic
h
ae
l'
s
o
r
ig
in
al
f
ac
e
h
as
7
3
.
6
3
%
co
n
f
id
en
ce
.
I
n
th
e
s
ec
o
n
d
o
n
e,
th
e
f
ac
es
o
f
Ga
v
r
iel
an
d
J
is
ch
ak
b
o
th
wer
e
id
en
tifie
d
as
Mic
h
ae
l
with
f
alse
co
n
f
id
en
ce
-
5
5
.
3
4
%
an
d
5
0
.
6
1
%
-
v
e
r
s
u
s
Mic
h
ae
l's
o
r
ig
in
al
f
ac
e
(
7
0
.
7
1
%).
I
n
th
e
th
ir
d
test
,
o
n
ly
I
v
an
'
s
f
ac
e
was
ca
p
tu
r
ed
in
th
e
d
ataset,
h
o
wev
er
,
th
e
f
ac
es o
f
Mic
h
ae
l,
Gav
r
iel,
an
d
J
is
ch
ak
wer
e
id
en
tifie
d
as
I
v
an
with
f
alse c
o
n
f
id
en
ce
-
5
0
.
7
8
%,
5
3
.
4
1
%,
an
d
5
1
.
5
7
% w
h
ile
I
v
an
'
s
f
ac
e
h
ad
tr
u
e
co
n
f
id
en
ce
o
f
6
2
.
5
9
%.
T
h
r
o
u
g
h
th
e
th
r
ee
test
s
,
ea
ch
tr
u
e
co
n
f
id
en
ce
an
d
f
alse
c
o
n
f
id
en
ce
wer
e
ca
lcu
lated
o
n
av
er
ag
e
a
n
d
p
r
o
d
u
ce
d
av
er
a
g
e
f
alse
co
n
f
id
e
n
ce
o
f
5
0
.
9
8
%
an
d
t
r
u
e
co
n
f
id
en
ce
o
f
6
7
.
1
9
%.
Fro
m
th
ese
r
esu
lts
,
to
p
r
ev
en
t
an
u
n
k
n
o
w
n
f
ac
e
f
r
o
m
o
p
en
in
g
a
lo
c
k
ed
d
o
o
r
,
we
d
eter
m
in
e
th
e
co
n
f
id
e
n
ce
th
r
esh
o
ld
to
o
p
en
a
d
o
o
r
m
u
s
t
b
e
ab
o
v
e
5
0
.
9
8
%
(
we
d
eter
m
i
n
e
th
at
th
e
av
er
a
g
e
co
n
f
id
en
ce
to
o
p
en
t
h
e
d
o
o
r
is
6
0
%).
Fig
u
r
e
6
s
h
o
ws
th
at
th
e
o
r
ig
in
al
f
ac
e
th
at
was
id
en
tifi
ed
as
I
v
an
with
an
av
er
a
g
e
c
o
n
f
id
en
ce
o
f
u
p
to
7
0
%,
an
d
th
e
u
n
k
n
o
wn
f
ac
e
r
ec
o
g
n
ized
as I
v
an
with
a
m
u
c
h
lo
wer
av
e
r
ag
e
co
n
f
id
en
ce
(
3
3
%).
Fro
m
all
th
e
e
x
p
er
im
e
n
ts
we
g
o
t
th
e
t
h
r
esh
o
ld
o
f
f
ac
e
r
ec
o
g
n
itio
n
at
6
0
%.
T
h
is
th
r
esh
o
l
d
ac
tu
ally
co
u
ld
b
e
im
p
r
o
v
e
d
u
p
to
m
o
r
e
th
an
9
0
%
if
we
u
s
e
n
eu
r
al
n
etwo
r
k
m
eth
o
d
s
s
u
ch
as
f
ac
e
n
et
.
Face
n
et
is
k
n
o
wn
as
th
e
s
tate
o
f
th
e
ar
t n
eu
r
al
n
etwo
r
k
f
o
r
f
ac
e
r
ec
o
g
n
i
tio
n
[
2
7
]
.
Sin
ce
we
in
teg
r
ate
t
h
is
o
n
R
asp
b
er
r
y
Pi
3
B
with
s
o
m
an
y
p
r
o
ce
s
s
es
s
u
ch
as
MQ
T
T
an
d
No
d
e
-
R
E
D,
it
is
n
o
t
p
o
s
s
ib
le
to
u
s
e
n
e
u
r
al
n
etwo
r
k
s
d
u
e
to
p
er
f
o
r
m
an
ce
lim
itatio
n
is
s
u
es,
h
en
ce
we
ju
s
t u
s
e
L
B
PH
(
m
a
ch
in
e
lear
n
in
g
m
eth
o
d
)
t
o
r
ec
o
g
n
ize
t
h
e
f
ac
e
.
I
t
is
p
o
s
s
ib
le
to
in
cr
ea
s
e
th
e
p
er
f
o
r
m
an
ce
o
f
f
ac
e
r
ec
o
g
n
itio
n
if
we
u
s
e
n
eu
r
al
s
tick
p
r
o
ce
s
s
o
r
as
a
n
eu
r
al
p
r
o
ce
s
s
in
g
h
elp
er
o
r
u
s
e
a
m
o
r
e
p
o
wer
f
u
l
R
asp
b
er
r
y
Pi
s
er
ies
s
u
ch
as
R
asp
b
er
r
y
Pi
4
th
at
alr
ea
d
y
h
as
6
4
B
it
p
r
o
ce
s
s
o
r
ar
ch
itectu
r
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
A
s
ma
r
t d
o
o
r
p
r
o
to
typ
e
w
ith
a
fa
ce
r
ec
o
g
n
itio
n
c
a
p
a
b
ilit
y
(
I
va
n
S
u
r
ya
Hu
to
mo
)
7
T
ab
le
4
.
T
h
e
u
n
k
n
o
w
n
d
ataset
to
f
in
d
u
n
lo
c
k
in
g
th
r
esh
o
ld
D
a
t
a
s
e
t
r
e
g
i
st
e
r
e
d
f
a
c
e
N
a
mes
A
c
c
u
r
a
c
y
a
v
e
r
a
g
e
(
%)
Ti
me
a
c
c
u
r
a
c
y
(
s)
I
v
a
n
,
M
i
c
h
a
e
l
,
G
a
v
r
i
e
l
l
e
I
v
a
n
6
5
.
3
4
3
.
8
7
6
M
i
c
h
a
e
l
7
3
.
6
3
3
.
9
7
2
G
a
v
r
i
e
l
6
7
.
4
8
4
.
0
4
7
Ji
sc
h
a
k
4
4
.
1
8
5
.
2
5
2
I
v
a
n
,
M
i
c
h
a
e
l
I
v
a
n
6
3
.
3
9
3
.
4
7
4
M
i
c
h
a
e
l
7
0
.
7
1
1
3
.
4
7
7
G
a
v
r
i
e
l
5
5
.
3
4
3
.
4
9
6
Ji
sc
h
a
k
5
0
.
6
1
3
.
3
8
8
I
v
a
n
I
v
a
n
6
2
.
5
9
2
.
6
4
2
M
i
c
h
a
e
l
5
0
.
7
8
3
.
1
7
1
G
a
v
r
i
e
l
5
3
.
4
1
3
.
0
1
9
Ji
sc
h
a
k
5
1
.
5
7
2
.
9
8
3
F
a
l
se
c
o
n
f
i
d
e
n
c
e
a
v
e
r
a
g
e
5
0
.
9
8
Tr
u
e
c
o
n
f
i
d
e
n
c
e
a
v
e
r
a
g
e
6
7
.
1
9
Fig
u
r
e
6
.
Dif
f
e
r
en
ce
s
in
av
e
r
a
g
e
co
n
f
i
d
en
ce
in
k
n
o
w
n
d
atas
ets (
lef
t)
an
d
u
n
k
n
o
wn
d
ataset
s
(
r
ig
h
t)
3
.
4
.
G
o
o
g
le
a
s
s
is
t
a
nt
inte
g
ra
t
io
n e
x
perim
ent
s
Sev
er
al
ex
p
er
im
en
ts
ar
e
also
ca
r
r
ied
o
u
t
to
test
th
e
s
u
cc
ess
r
ate
o
f
Go
o
g
le
Ass
is
tan
t
in
r
es
p
o
n
d
in
g
to
o
r
d
er
s
f
r
o
m
u
s
er
s
.
T
h
e
s
u
cc
ess
r
ate
ca
n
b
e
s
ee
n
in
th
e
s
es
s
i
o
n
f
lo
w
f
r
o
m
Dialo
g
f
l
o
w
as
s
h
o
wn
in
Fig
u
r
e
7
.
B
ased
o
n
th
e
s
ess
io
n
f
lo
w
F
ig
u
r
e
7
,
f
r
o
m
1
4
7
e
x
p
er
im
e
n
ts
co
n
d
u
cted
,
t
h
e
s
u
cc
ess
r
ate
r
ea
ch
ed
9
3
.
2
%.
Go
o
g
le
Ass
is
tan
t
'
s
f
ailu
r
e
to
r
ec
o
g
n
ize
u
s
er
s
p
ee
c
h
is
o
n
ly
6
.
8
%
(
1
0
tr
ials
o
u
t
o
f
1
4
7
)
.
T
h
i
s
wh
o
le
test
s
h
o
ws
th
at
Dialo
g
f
lo
w'
s
in
teg
r
atio
n
with
Fire
b
ase,
No
d
e
-
R
E
D,
an
d
th
e
au
th
o
r
'
s
Go
o
g
le
Ass
i
s
ta
n
t
ac
c
o
u
n
t
h
as
b
ee
n
s
u
cc
ess
f
u
l.
Fig
u
r
e
7
.
Ses
s
io
n
f
lo
w
th
at
s
h
o
wn
th
e
s
u
cc
ess
r
ate
o
f
Go
o
g
l
e
Ass
is
tan
t
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
.
11
,
No
.
1
,
M
a
r
ch
20
22
:
1
-
9
8
4.
CO
NCLU
SI
O
N
W
e
d
esig
n
an
d
cr
ea
te
a
s
m
ar
t
d
o
o
r
p
r
o
to
ty
p
e
in
teg
r
ated
with
f
ac
e
r
ec
o
g
n
itio
n
an
d
Go
o
g
le
Ass
i
s
tan
t.
Af
ter
co
n
d
u
ctin
g
s
o
m
e
ex
p
er
i
m
en
ts
,
th
e
f
o
l
lo
win
g
co
n
clu
s
i
o
n
s
ar
e
o
b
tain
ed
th
at:
Face
r
ec
o
g
n
itio
n
u
s
in
g
Haa
r
ca
s
ca
d
e
f
ac
e
d
etec
tio
n
an
d
L
B
PH
f
ac
e
r
ec
o
g
n
itio
n
was
s
u
cc
ess
f
u
lly
in
teg
r
ated
o
n
th
e
s
m
ar
t
d
o
o
r
with
th
ese
p
ar
am
eter
s
:
th
e
ca
m
er
a
d
is
tan
ce
=3
0
cm
,
m
i
n
n
ei
g
h
b
o
r
=2
,
a
n
d
s
ca
le
f
a
cto
r
=1
.
5
.
T
h
e
n
u
m
b
er
o
f
ef
f
ec
ti
v
e
f
ac
es
s
to
r
ed
in
th
e
d
atab
ase
is
3
f
ac
es.
I
f
th
e
av
er
ag
e
co
n
f
id
e
n
ce
o
f
th
e
f
ac
e
is
m
o
r
e
th
an
6
0
%
th
e
s
m
ar
t
d
o
o
r
will
u
n
lo
ck
s
u
cc
ess
f
u
lly
.
T
h
e
in
teg
r
atio
n
o
f
Go
o
g
le
Ass
is
tan
t
with
th
e
s
m
ar
t
d
o
o
r
w
o
r
k
s
well.
Go
o
g
le
Ass
is
tan
t
ca
n
b
e
u
s
ed
to
r
etr
iev
e
in
f
o
r
m
atio
n
,
c
o
n
tr
o
l
s
m
ar
t
d
o
o
r
d
ev
ices
b
y
u
tili
zin
g
Dialo
g
f
lo
w
an
d
th
e
r
ea
l
-
tim
e
d
atab
ase
f
r
o
m
Fire
b
ase.
B
ased
o
n
th
e
s
im
u
la
tio
n
,
it
ca
n
b
e
co
n
cl
u
d
ed
th
at
Dialo
g
f
lo
w
an
d
Fire
b
ase
ar
e
r
eliab
le
en
o
u
g
h
t
o
b
e
u
tili
ze
d
an
d
in
teg
r
ated
with
s
m
ar
t d
o
o
r
s
with
a
s
u
cc
ess
r
ate
o
f
r
esp
o
n
s
e
r
ea
ch
in
g
9
3
.
2
%
.
RE
F
E
R
E
NC
E
S
[
1
]
W
.
A
l
i
,
G
.
D
u
s
t
g
e
e
r
,
M
.
A
w
a
i
s
,
a
n
d
M
.
A
.
S
h
a
h
,
“
I
o
T
b
a
se
d
sm
a
r
t
h
o
me
:
s
e
c
u
r
i
t
y
c
h
a
l
l
e
n
g
e
s,
sec
u
r
i
t
y
r
e
q
u
i
r
e
me
n
t
s
a
n
d
so
l
u
t
i
o
n
s
,
”
i
n
2
0
1
7
2
3
r
d
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
A
u
t
o
m
a
t
i
o
n
a
n
d
C
o
m
p
u
t
i
n
g
(
I
C
A
C
)
,
S
e
p
.
2
0
1
7
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
2
3
9
1
9
/
I
C
o
n
A
C
.
2
0
1
7
.
8
0
8
2
0
5
7
.
[
2
]
J.
B
u
g
e
j
a
,
A
.
Jac
o
b
ss
o
n
,
a
n
d
P
.
D
a
v
i
d
sso
n
,
“
O
n
p
r
i
v
a
c
y
a
n
d
se
c
u
r
i
t
y
c
h
a
l
l
e
n
g
e
s
i
n
sm
a
r
t
c
o
n
n
e
c
t
e
d
h
o
mes,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
2
0
1
6
Eu
r
o
p
e
a
n
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
S
e
c
u
r
i
t
y
I
n
f
o
rm
a
t
i
c
s
C
o
n
f
e
r
e
n
c
e
,
EI
S
I
C
2
0
1
6
,
A
u
g
.
2
0
1
7
,
p
p
.
1
7
2
–
1
7
5
,
d
o
i
:
1
0
.
1
1
0
9
/
EI
S
I
C
.
2
0
1
6
.
0
4
4
.
[
3
]
J.
I
.
Je
o
n
g
,
“
A
s
t
u
d
y
o
n
t
h
e
I
o
T
b
a
se
d
s
mart
d
o
o
r
l
o
c
k
s
y
st
e
m,
”
i
n
L
e
c
t
u
r
e
N
o
t
e
s
i
n
El
e
c
t
ri
c
a
l
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
3
7
6
,
S
p
r
i
n
g
e
r
V
e
r
l
a
g
,
2
0
1
6
,
p
p
.
1
3
0
7
–
1
3
1
8
.
[
4
]
M
.
B
o
a
t
w
r
i
g
h
t
a
n
d
X
.
L
u
o
,
“
W
h
a
t
d
o
w
e
k
n
o
w
a
b
o
u
t
b
i
o
met
r
i
c
s
a
u
t
h
e
n
t
i
c
a
t
i
o
n
?
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
4
t
h
a
n
n
u
a
l
c
o
n
f
e
re
n
c
e
o
n
I
n
f
o
rm
a
t
i
o
n
s
e
c
u
r
i
t
y
c
u
rri
c
u
l
u
m
d
e
v
e
l
o
p
m
e
n
t
-
I
n
f
o
S
e
c
C
D
’
0
7
,
2
0
0
7
,
p
.
1
,
d
o
i
:
1
0
.
1
1
4
5
/
1
4
0
9
9
0
8
.
1
4
0
9
9
4
2
.
[
5
]
H
.
K
.
Ek
e
n
e
l
,
J.
S
t
a
l
l
k
a
m
p
,
H
.
G
a
o
,
M
.
F
i
s
c
h
e
r
,
a
n
d
R
.
S
t
i
e
f
e
l
h
a
g
e
n
,
“
F
a
c
e
r
e
c
o
g
n
i
t
i
o
n
f
o
r
sm
a
r
t
i
n
t
e
r
a
c
t
i
o
n
s,
”
i
n
M
u
l
t
i
m
e
d
i
a
a
n
d
Ex
p
o
,
2
0
0
7
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
ren
c
e
o
n
,
J
u
l
.
2
0
0
7
,
p
p
.
1
0
0
7
–
1
0
1
0
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
M
E.
2
0
0
7
.
4
2
8
4
8
2
3
.
[
6
]
R
.
Li
m,
F
.
R
o
t
i
n
su
l
u
a
n
d
,
a
n
d
P
.
S
a
n
t
o
so
,
“
R
o
o
m
a
c
c
e
ss
c
o
n
t
r
o
l
s
y
st
e
m
u
s
i
n
g
f
a
c
i
a
l
i
ma
g
e
r
e
c
o
g
n
i
t
i
o
n
,
”
A
p
p
l
i
e
d
Me
c
h
a
n
i
c
s
a
n
d
Ma
t
e
r
i
a
l
s
,
v
o
l
.
8
1
5
,
p
p
.
3
9
8
–
4
0
2
,
N
o
v
.
2
0
1
5
,
d
o
i
:
1
0
.
4
0
2
8
/
w
w
w
.
sc
i
e
n
t
i
f
i
c
.
n
e
t
/
a
mm
.
8
1
5
.
3
9
8
.
[
7
]
R
.
S
z
a
b
o
a
n
d
A
.
G
o
n
t
e
a
n
,
“
I
n
d
u
s
t
r
i
a
l
r
o
b
o
t
i
c
a
u
t
o
ma
t
i
o
n
w
i
t
h
R
a
s
p
b
e
r
r
y
P
I
u
si
n
g
i
ma
g
e
p
r
o
c
e
ssi
n
g
,
”
i
n
2
0
1
6
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
A
p
p
l
i
e
d
El
e
c
t
ro
n
i
c
s (A
E)
, S
e
p
.
2
0
1
6
,
p
p
.
2
6
5
–
2
6
8
,
d
o
i
:
1
0
.
1
1
0
9
/
A
E.
2
0
1
6
.
7
5
7
7
2
8
7
.
[
8
]
J.
H
o
w
se
,
“
Tr
a
i
n
i
n
g
d
e
t
e
c
t
o
r
s
a
n
d
r
e
c
o
g
n
i
z
e
r
s
i
n
P
y
t
h
o
n
a
n
d
O
p
e
n
C
V
,
”
i
n
2
0
1
4
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
S
y
m
p
o
s
i
u
m
o
n
Mi
x
e
d
a
n
d
Au
g
m
e
n
t
e
d
Re
a
l
i
t
y
(
I
S
MA
R)
,
S
e
p
.
2
0
1
4
,
p
p
.
1
–
2
,
d
o
i
:
1
0
.
1
1
0
9
/
i
smar
.
2
0
1
4
.
6
9
4
8
5
1
6
.
[
9
]
N
.
R
o
sr
u
e
n
a
n
d
T
.
S
a
m
a
n
c
h
u
e
n
,
“
C
h
a
t
b
o
t
u
t
i
l
i
z
a
t
i
o
n
f
o
r
m
e
d
i
c
a
l
c
o
n
su
l
t
a
n
t
s
y
s
t
e
m,
”
i
n
2
0
1
8
3
rd
T
e
c
h
n
o
l
o
g
y
I
n
n
o
v
a
t
i
o
n
Ma
n
a
g
e
m
e
n
t
a
n
d
E
n
g
i
n
e
e
ri
n
g
S
c
i
e
n
c
e
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
(
T
I
ME
S
-
i
C
O
N
)
,
D
e
c
.
2
0
1
8
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
M
ES
-
i
C
O
N
.
2
0
1
8
.
8
6
2
1
6
7
8
.
[
1
0
]
P
.
I
.
W
i
l
s
o
n
a
n
d
J.
F
e
r
n
a
n
d
e
z
,
“
F
a
c
i
a
l
f
e
a
t
u
r
e
d
e
t
e
c
t
i
o
n
u
si
n
g
h
a
a
r
c
l
a
ssi
f
i
e
r
s,”
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
i
n
g
S
c
i
e
n
c
e
s
i
n
C
o
l
l
e
g
e
s
,
v
o
l
.
2
1
,
n
o
.
4
,
p
p
.
1
2
7
–
1
3
3
,
2
0
0
6
.
[
1
1
]
P
.
V
i
o
l
a
a
n
d
M
.
J
o
n
e
s,
“
R
a
p
i
d
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
u
si
n
g
a
b
o
o
s
t
e
d
c
a
s
c
a
d
e
o
f
si
m
p
l
e
f
e
a
t
u
r
e
s
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
I
EEE
C
o
m
p
u
t
e
r
S
o
c
i
e
t
y
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
e
r
V
i
si
o
n
a
n
d
P
a
t
t
e
r
n
R
e
c
o
g
n
i
t
i
o
n
,
2
0
0
1
,
v
o
l
.
1
,
p
p
.
I
--
5
1
1
--
I
--
5
1
8
,
d
o
i
:
1
0
.
1
1
0
9
/
c
v
p
r
.
2
0
0
1
.
9
9
0
5
1
7
.
[
1
2
]
Y.
-
Q
.
W
a
n
g
,
“
A
n
a
n
a
l
y
s
i
s
o
f
t
h
e
V
i
o
l
a
-
Jo
n
e
s
f
a
c
e
d
e
t
e
c
t
i
o
n
a
l
g
o
r
i
t
h
m,
”
I
m
a
g
e
Pro
c
e
ss
i
n
g
O
n
L
i
n
e
,
v
o
l
.
4
,
p
p
.
1
2
8
–
1
4
8
,
J
u
n
.
2
0
1
4
,
d
o
i
:
1
0
.
5
2
0
1
/
i
p
o
l
.
2
0
1
4
.
1
0
4
.
[
1
3
]
P
.
V
i
o
l
a
a
n
d
M
.
J.
J
o
n
e
s,
“
R
o
b
u
st
r
e
a
l
-
t
i
me
f
a
c
e
d
e
t
e
c
t
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
e
r
Vi
s
i
o
n
,
v
o
l
.
5
7
,
n
o
.
2
,
p
p
.
1
3
7
–
1
5
4
,
M
a
y
2
0
0
4
,
d
o
i
:
1
0
.
1
0
2
3
/
B
:
V
I
S
I
.
0
0
0
0
0
1
3
0
8
7
.
4
9
2
6
0
.
f
b
.
[
1
4
]
I
.
M
.
S
a
y
e
m
a
n
d
M
.
S
.
C
h
o
w
d
h
u
r
y
,
“
I
n
t
e
g
r
a
t
i
n
g
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
s
e
c
u
r
i
t
y
sy
s
t
e
m
w
i
t
h
t
h
e
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s,”
i
n
Pro
c
e
e
d
i
n
g
s
-
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
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
a
n
d
D
a
t
a
En
g
i
n
e
e
ri
n
g
,
i
C
MLD
E
2
0
1
8
,
D
e
c
.
2
0
1
9
,
p
p
.
1
9
–
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
i
C
M
LD
E.
2
0
1
8
.
0
0
0
1
3
.
[
1
5
]
A
.
A
h
me
d
,
J.
G
u
o
,
F
.
A
l
i
,
F
.
D
e
e
b
a
,
a
n
d
A
.
A
h
me
d
,
“
LB
P
H
b
a
se
d
i
m
p
r
o
v
e
d
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
a
t
l
o
w
r
e
s
o
l
u
t
i
o
n
,
”
i
n
2
0
1
8
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
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
B
i
g
D
a
t
a
(
I
C
AI
BD
)
,
M
a
y
2
0
1
8
,
p
p
.
1
4
4
–
1
4
7
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
I
B
D
.
2
0
1
8
.
8
3
9
6
1
8
3
.
[
1
6
]
T.
A
h
o
n
e
n
,
A
.
H
a
d
i
d
,
a
n
d
M
.
P
i
e
t
i
k
ä
i
n
e
n
,
“
F
a
c
e
d
e
s
c
r
i
p
t
i
o
n
w
i
t
h
l
o
c
a
l
b
i
n
a
r
y
p
a
t
t
e
r
n
s
:
a
p
p
l
i
c
a
t
i
o
n
t
o
f
a
c
e
r
e
c
o
g
n
i
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
rn
An
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
.
2
8
,
n
o
.
1
2
,
p
p
.
2
0
3
7
–
2
0
4
1
,
D
e
c
.
2
0
0
6
,
d
o
i
:
1
0
.
1
1
0
9
/
TPA
M
I
.
2
0
0
6
.
2
4
4
.
[
1
7
]
M
.
M
a
k
si
m
o
v
i
ć
,
V
.
V
u
j
o
v
i
ć
,
N
.
D
a
v
i
d
o
v
i
ć
,
V
.
M
i
l
o
še
v
i
ć
,
a
n
d
B
.
P
e
r
i
ši
ć
,
“
R
a
sp
b
e
r
r
y
P
i
a
s
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s
h
a
r
d
w
a
r
e
:
P
e
r
f
o
r
ma
n
c
e
s
a
n
d
C
o
n
s
t
r
a
i
n
t
s,”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
1
st
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
El
e
c
t
ri
c
a
l
,
E
l
e
c
t
r
o
n
i
c
a
n
d
C
o
m
p
u
t
i
n
g
En
g
i
n
e
e
ri
n
g
I
c
ETR
AN
2
0
1
4
,
2
0
1
4
,
v
o
l
.
3
,
n
o
.
JU
N
E,
p
.
8
.
[
1
8
]
M
.
L
e
k
i
ć
a
n
d
G
.
G
a
r
d
a
še
v
i
ć
,
“
I
o
T
sen
s
o
r
i
n
t
e
g
r
a
t
i
o
n
t
o
N
o
d
e
-
R
ED
p
l
a
t
f
o
r
m,
”
i
n
2
0
1
8
1
7
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
S
y
m
p
o
si
u
m
o
n
I
N
FO
T
EH
-
J
AH
O
RI
N
A,
I
N
FO
T
EH
2
0
1
8
-
Pr
o
c
e
e
d
i
n
g
s
,
M
a
r
.
2
0
1
8
,
v
o
l
.
2
0
1
8
-
Ja
n
u
a
r
y
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
N
F
O
TEH
.
2
0
1
8
.
8
3
4
5
5
4
4
.
[
1
9
]
Y
.
U
p
a
d
h
y
a
y
,
A
.
B
o
r
o
l
e
,
a
n
d
D
.
D
i
l
e
e
p
a
n
,
“
M
Q
TT
b
a
se
d
se
c
u
r
e
d
h
o
m
e
a
u
t
o
m
a
t
i
o
n
s
y
st
e
m,”
i
n
2
0
1
6
S
y
m
p
o
s
i
u
m
o
n
C
o
l
o
ss
a
l
D
a
t
a
A
n
a
l
y
si
s
a
n
d
N
e
t
w
o
r
k
i
n
g
(
C
D
A
N
)
,
M
a
r
.
2
0
1
6
,
p
p
.
1
–
4
,
d
o
i
:
1
0
.
1
1
0
9
/
C
D
A
N
.
2
0
1
6
.
7
5
7
0
9
4
5
.
[
2
0
]
S
.
M
i
s
c
h
i
e
,
L.
M
a
t
i
u
-
I
o
v
a
n
,
a
n
d
G
.
G
a
sp
a
r
e
sc,
“
I
mp
l
e
m
e
n
t
a
t
i
o
n
o
f
G
o
o
g
l
e
A
ss
i
st
a
n
t
o
n
R
a
sb
e
r
r
y
P
i
,
”
i
n
2
0
1
8
I
n
t
e
r
n
a
t
i
o
n
a
l
S
y
m
p
o
s
i
u
m
o
n
El
e
c
t
r
o
n
i
c
s
a
n
d
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
s (I
S
ETC)
,
N
o
v
.
2
0
1
8
,
p
p
.
1
–
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
S
ETC
.
2
0
1
8
.
8
5
8
3
8
9
9
.
[
2
1
]
R
.
L.
H
o
v
i
o
u
s,
“
Ji
t
t
e
r
i
n
i
n
s
t
r
u
m
e
n
t
s
e
r
v
o
s,”
T
r
a
n
s
a
c
t
i
o
n
s
o
f
t
h
e
Am
e
ri
c
a
n
I
n
s
t
i
t
u
t
e
o
f
El
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
rs,
Pa
r
t
I
I
:
A
p
p
l
i
c
a
t
i
o
n
s
a
n
d
I
n
d
u
s
t
ry
,
v
o
l
.
7
3
,
n
o
.
6
,
p
p
.
3
9
3
–
3
9
8
,
Ju
l
.
1
9
5
5
,
d
o
i
:
1
0
.
1
1
0
9
/
TA
I
.
1
9
5
5
.
6
3
6
7
0
8
8
.
[
2
2
]
A
.
S
.
S
a
d
u
n
,
J
.
J
a
l
a
n
i
,
a
n
d
J.
A
.
S
u
k
o
r
,
“
A
c
o
m
p
a
r
a
t
i
v
e
st
u
d
y
o
n
t
h
e
p
o
s
i
t
i
o
n
c
o
n
t
r
o
l
me
t
h
o
d
o
f
d
c
serv
o
mo
t
o
r
w
i
t
h
p
o
s
i
t
i
o
n
f
e
e
d
b
a
c
k
b
y
u
s
i
n
g
a
r
d
u
i
n
o
,
”
AR
PN
J
o
u
rn
a
l
o
f
En
g
i
n
e
e
ri
n
g
a
n
d
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
1
,
n
o
.
1
8
,
p
p
.
1
0
9
5
4
–
1
0
9
5
8
,
2
0
1
6
.
[
2
3
]
W
.
J.
L
i
,
C
.
Y
e
n
,
Y
.
S
.
Li
n
,
S
.
C
.
Tu
n
g
,
a
n
d
S
.
M
.
H
u
a
n
g
,
“
Ju
s
t
I
o
T
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s b
a
s
e
d
o
n
t
h
e
F
i
r
e
b
a
s
e
r
e
a
l
-
t
i
me
d
a
t
a
b
a
s
e
,
”
i
n
Pro
c
e
e
d
i
n
g
s
-
2
0
1
8
I
EEE
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
S
m
a
rt
M
a
n
u
f
a
c
t
u
ri
n
g
,
I
n
d
u
st
r
i
a
l
a
n
d
L
o
g
i
st
i
c
s
En
g
i
n
e
e
ri
n
g
,
S
MIL
E
2
0
1
8
,
F
e
b
.
2
0
1
8
,
v
o
l
.
2
0
1
8
-
J
a
n
u
a
,
p
p
.
4
3
–
4
7
,
d
o
i
:
1
0
.
1
1
0
9
/
S
M
I
LE.
2
0
1
8
.
8
3
5
3
9
7
9
.
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
A
s
ma
r
t d
o
o
r
p
r
o
to
typ
e
w
ith
a
fa
ce
r
ec
o
g
n
itio
n
c
a
p
a
b
ilit
y
(
I
va
n
S
u
r
ya
Hu
to
mo
)
9
[
2
4
]
J.
D
a
l
t
o
n
,
V
.
A
j
a
y
i
,
a
n
d
R
.
M
a
i
n
,
“
V
o
t
e
g
o
a
t
,
”
i
n
T
h
e
4
1
s
t
I
n
t
e
rn
a
t
i
o
n
a
l
A
C
M
S
I
G
I
R
C
o
n
f
e
r
e
n
c
e
o
n
Re
s
e
a
r
c
h
&
D
e
v
e
l
o
p
m
e
n
t
i
n
I
n
f
o
rm
a
t
i
o
n
Re
t
ri
e
v
a
l
,
J
u
n
.
2
0
1
8
,
p
p
.
1
2
8
5
–
1
2
8
8
,
d
o
i
:
1
0
.
1
1
4
5
/
3
2
0
9
9
7
8
.
3
2
1
0
1
6
8
.
[
2
5
]
S
.
Ji
y
a
l
a
n
d
R
.
K
u
mar S
a
i
n
i
,
“
A
s
u
r
v
e
y
o
n
a
i
r
p
o
l
l
u
t
i
o
n
mo
n
i
t
o
r
i
n
g
u
si
n
g
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
o
n
t
r
o
l
a
n
d
Au
t
o
m
a
t
i
o
n
,
v
o
l
.
1
3
,
n
o
.
2
,
p
p
.
1
3
7
–
1
4
6
,
2
0
2
0
.
[
2
6
]
H
.
U
.
Za
m
a
n
,
S
.
M
a
h
m
o
o
d
,
S
.
H
o
ssa
i
n
,
a
n
d
I
.
I
.
S
h
o
v
o
n
,
“
P
y
t
h
o
n
b
a
s
e
d
p
o
r
t
a
b
l
e
v
i
r
t
u
a
l
t
e
x
t
r
e
a
d
e
r
,
”
i
n
2
0
1
8
Fo
u
r
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Ad
v
a
n
c
e
s
i
n
C
o
m
p
u
t
i
n
g
,
C
o
m
m
u
n
i
c
a
t
i
o
n
&
Au
t
o
m
a
t
i
o
n
(
I
C
AC
C
A)
,
O
c
t
.
2
0
1
8
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
C
C
A
F
.
2
0
1
8
.
8
7
7
6
7
7
8
.
[
2
7
]
S
.
B
a
l
a
b
a
n
,
“
D
e
e
p
l
e
a
r
n
i
n
g
a
n
d
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
:
t
h
e
st
a
t
e
o
f
t
h
e
a
r
t
,
”
i
n
B
i
o
m
e
t
ri
c
a
n
d
S
u
r
v
e
i
l
l
a
n
c
e
T
e
c
h
n
o
l
o
g
y
f
o
r
H
u
m
a
n
a
n
d
Ac
t
i
v
i
t
y
I
d
e
n
t
i
f
i
c
a
t
i
o
n
XI
I
,
M
a
y
2
0
1
5
,
v
o
l
.
9
4
5
7
,
p
.
9
4
5
7
0
B
,
d
o
i
:
1
0
.
1
1
1
7
/
1
2
.
2
1
8
1
5
2
6
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Iv
a
n
S
u
r
y
a
H
u
t
o
m
o
re
c
e
iv
e
d
h
is
b
a
c
h
e
l
o
r'
s
d
e
g
re
e
i
n
E
lec
tri
c
a
l
En
g
in
e
e
rin
g
De
p
a
rtme
n
t
a
t
P
e
tra
Ch
risti
a
n
Un
iv
e
rsity
,
I
n
d
o
n
e
sia
in
2
0
1
9
.
He
th
e
n
c
o
n
ti
n
u
e
s
h
is
stu
d
y
o
f
a
m
a
ste
r'
s
d
e
g
re
e
in
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
a
t
Na
ti
o
n
a
l
Ch
iao
Tu
n
g
Un
iv
e
rsity
,
Taiwa
n
.
His
field
o
f
in
tere
st
in
c
lu
d
e
s
Artifi
c
ial
In
tel
li
g
e
n
c
e
,
Na
tu
ra
l
Lan
g
u
a
g
e
P
ro
c
e
ss
in
g
,
r
o
b
o
ti
c
s,
a
n
d
a
u
t
o
m
a
ti
o
n
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
h
u
t
o
m
o
iv
a
n
.
e
e
0
8
@
n
y
c
u
.
e
d
u
.
tw
.
H
a
n
d
y
Wica
k
so
n
o
is
a
se
n
io
r
lec
tu
re
r
i
n
El
e
c
tri
c
a
l
E
n
g
i
n
e
e
rin
g
De
p
a
rtme
n
t,
P
e
tra
Ch
risti
a
n
Un
iv
e
rsity
,
In
d
o
n
e
sia
.
He
re
c
e
iv
e
d
h
is
b
a
c
h
e
lo
r'
s
a
n
d
m
a
ste
r'
s
d
e
g
re
e
fro
m
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
De
p
a
rtme
n
t
(In
stit
u
t
Tek
n
o
lo
g
i
S
e
p
u
l
u
h
No
p
e
m
b
e
r),
a
n
d
a
P
h
.
D.
d
e
g
re
e
fro
m
S
c
h
o
o
l
o
f
Co
m
p
u
te
r
S
c
ien
c
e
a
n
d
En
g
in
e
e
ri
n
g
,
UN
S
W
Au
stra
li
a
.
His
re
se
a
rc
h
in
tere
sts
in
c
l
u
d
e
a
rti
ficia
l
i
n
telli
g
e
n
c
e
,
in
tell
ig
e
n
t
r
o
b
o
t,
a
n
d
i
n
d
u
s
tri
a
l
a
u
t
o
m
a
ti
o
n.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
h
a
n
d
y
@p
e
tra.
a
c
.
id
.
Evaluation Warning : The document was created with Spire.PDF for Python.