I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
15
,
No
.
5
,
Octo
b
er
20
25
,
p
p
.
4
5
8
1
~
4
5
9
2
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
5
.
pp
4
5
8
1
-
4
5
9
2
4581
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Dy
na
mic
hea
d po
se estima
tion i
n v
a
ried conditio
ns u
sing
D
lib
a
nd
M
edia
Pipe
Rus
na
ni
Ya
hy
a
1,
2
,
Ro
zit
a
J
a
i
la
ni
1
,
Nur
K
ha
lid
a
h Z
a
k
a
ria
1
,
F
a
za
h Ak
ht
a
r
H
a
na
pia
h
3
1
F
a
c
u
l
t
y
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
i
T
e
k
n
o
l
o
g
i
M
A
R
A
(
U
i
T
M
)
,
S
e
l
a
n
g
o
r
,
M
a
l
a
y
s
i
a
2
C
e
n
t
e
r
f
o
r
M
e
d
i
c
a
l
El
e
c
t
r
o
n
i
c
Te
c
h
n
o
l
o
g
y
,
P
o
l
i
t
e
k
n
i
k
S
u
l
t
a
n
S
a
l
a
h
u
d
d
i
n
A
b
d
u
l
A
z
i
z
S
h
a
h
,
S
h
a
h
A
l
a
m
,
M
a
l
a
y
s
i
a
3
F
a
c
u
l
t
y
o
f
M
e
d
i
c
i
n
e
,
U
n
i
v
e
r
s
i
t
i
T
e
k
n
o
l
o
g
i
M
A
R
A
,
S
u
n
g
a
i
B
u
l
o
h
,
M
a
l
a
y
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
2
9
,
2
0
2
4
R
ev
is
ed
Ap
r
3
0
,
2
0
2
5
Acc
ep
ted
J
u
l 3
0
,
2
0
2
5
Th
is
p
a
p
e
r
p
re
se
n
ts
th
e
f
o
rm
u
lati
o
n
a
n
d
v
a
li
d
a
ti
o
n
o
f
a
d
y
n
a
m
ic
h
e
a
d
p
o
se
e
stim
a
ti
o
n
(HPE
)
a
lg
o
r
it
h
m
,
a
d
d
re
ss
in
g
c
h
a
ll
e
n
g
e
s
re
late
d
t
o
d
i
v
e
rse
c
o
n
d
i
ti
o
n
s,
c
o
m
p
le
x
p
o
se
s,
a
n
d
p
a
rti
a
l
o
b
str
u
c
ti
o
n
s.
Th
e
st
u
d
y
a
ims
to
c
re
a
te
a
ro
b
u
st
a
lg
o
r
it
h
m
th
a
t
m
a
in
tai
n
s
h
ig
h
a
c
c
u
ra
c
y
in
re
a
l
-
ti
m
e
a
p
p
li
c
a
ti
o
n
s
a
c
ro
ss
v
a
ry
i
n
g
c
o
n
d
it
io
n
s.
Th
e
a
lg
o
rit
h
m
wa
s
im
p
lem
e
n
ted
a
n
d
a
ss
e
ss
e
d
u
sin
g
Dlib
a
n
d
M
e
d
iaPi
p
e
m
o
d
e
ls.
Th
e
stu
d
y
in
v
o
l
v
e
d
3
0
p
a
rti
c
ip
a
n
ts
in
fa
c
e
a
n
d
h
e
a
d
wit
h
o
u
t
o
b
sta
c
les
,
fa
c
e
with
o
b
sta
c
les
a
n
d
h
e
a
d
wi
th
o
b
sta
c
les
c
o
n
d
i
ti
o
n
s.
Th
e
re
su
lt
s
d
e
m
o
n
stra
ted
imp
re
ss
iv
e
p
e
rfo
rm
a
n
c
e
in
b
o
t
h
c
o
n
tro
ll
e
d
a
n
d
s
p
o
n
tan
e
o
u
s
h
e
a
d
m
o
v
e
m
e
n
t
c
a
teg
o
ries
.
Th
e
a
lg
o
rit
h
m
a
c
h
iev
e
d
a
n
a
v
e
ra
g
e
a
c
c
u
ra
c
y
o
f
9
3
%
fo
r
h
e
a
d
p
o
se
e
stim
a
ti
o
n
a
n
d
8
8
%
in
d
e
tec
ti
n
g
v
isu
a
l
a
tt
e
n
t
io
n
u
n
d
e
r
sp
o
n
ta
n
e
o
u
s
h
e
a
d
m
o
v
e
m
e
n
t
c
a
t
e
g
o
ries
.
A
c
o
rre
latio
n
c
o
e
fficie
n
t
o
f
0
.
8
6
6
i
n
d
ica
tes
a
str
o
n
g
p
o
siti
v
e
li
n
e
a
r
a
ss
o
c
iatio
n
b
e
twe
e
n
p
e
rfo
rm
a
n
c
e
a
n
d
a
tt
e
n
t
io
n
a
c
c
u
ra
c
y
,
i
n
d
ica
ti
n
g
t
h
a
t
p
e
rfo
rm
a
n
c
e
imp
ro
v
e
m
e
n
ts
a
re
in
tri
c
a
tely
l
in
k
e
d
to
p
ro
p
o
r
ti
o
n
a
l
in
c
re
a
se
s
in
a
tt
e
n
ti
o
n
a
c
c
u
ra
c
y
.
Ho
we
v
e
r,
th
is
d
o
e
s
n
o
t
n
e
c
e
ss
a
ril
y
imp
ly
c
a
u
sa
ti
o
n
.
Th
e
fin
d
i
n
g
s
p
ro
v
id
e
v
a
l
u
a
b
le i
n
sig
h
ts i
n
to
th
e
e
ffe
c
ti
v
e
n
e
ss
o
f
th
e
p
ro
p
o
se
d
a
lg
o
rit
h
m
s in
a
ss
e
ss
in
g
v
isu
a
l
a
tt
e
n
ti
o
n
a
n
d
d
e
m
o
n
stra
te
th
e
ir
p
o
ten
ti
a
l
a
p
p
li
c
a
ti
o
n
s
i
n
h
e
a
lt
h
c
a
re
m
o
n
it
o
ri
n
g
,
e
d
u
c
a
ti
o
n
a
l
i
n
terv
e
n
ti
o
n
,
a
n
d
d
ri
v
e
r
m
o
n
it
o
r
in
g
sy
ste
m
s.
Th
e
sig
n
ifi
c
a
n
c
e
o
f
th
e
se
re
su
lt
s
li
e
s
in
th
e
a
b
il
it
y
t
o
a
d
v
a
n
c
e
h
u
m
a
n
-
c
o
m
p
u
ter
in
tera
c
ti
o
n
,
e
n
h
a
n
c
e
h
e
a
lt
h
c
a
re
d
iag
n
o
stics
,
a
n
d
o
ffe
r
in
n
o
v
a
ti
v
e
so
l
u
ti
o
n
s a
c
ro
ss
v
a
ri
o
u
s d
o
m
a
in
s.
K
ey
w
o
r
d
s
:
Dlib
Face
d
etec
to
r
Face
lan
d
m
ar
k
p
r
ed
icto
r
Hea
d
p
o
s
e
esti
m
atio
n
Me
d
iaPip
e
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
:
Nu
r
Kh
alid
ah
Z
a
k
ar
ia
Facu
lty
o
f
E
lectr
ical
E
n
g
in
ee
r
in
g
,
Un
iv
er
s
iti T
ek
n
o
lo
g
i M
A
R
A
Sh
ah
Alam
,
Selan
g
o
r
,
Ma
lay
s
ia
E
m
ail: n
k
h
alid
ah
@
u
itm
.
ed
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
R
ea
l
-
tim
e
h
ea
d
p
o
s
e
esti
m
atio
n
(
HPE)
is
a
c
r
u
cial
c
o
m
p
o
n
e
n
t
in
co
m
p
u
ter
v
is
io
n
s
y
s
tem
s
d
esig
n
ed
to
in
ter
p
r
et
h
u
m
an
atten
tio
n
,
in
clu
d
in
g
ap
p
licatio
n
s
s
u
ch
a
s
d
r
iv
er
m
o
n
it
o
r
in
g
[
1
]
–
[
4
]
,
ad
ap
tiv
e
e
-
lear
n
in
g
in
ter
f
ac
es
[
5
]
,
[
6
]
,
an
d
h
u
m
a
n
-
r
o
b
o
t
in
ter
ac
tio
n
[
7
]
,
[
8
]
.
T
h
ese
s
y
s
tem
s
ca
n
in
f
er
en
g
ag
em
en
t
an
d
atten
tio
n
lev
els
b
y
tr
ac
k
in
g
h
ea
d
o
r
ien
t
atio
n
,
allo
win
g
f
o
r
d
y
n
am
ic
a
n
d
r
esp
o
n
s
iv
e
in
ter
ac
tio
n
s
.
H
o
wev
er
,
ac
h
iev
i
n
g
h
ig
h
ac
c
u
r
ac
y
in
v
ar
ie
d
c
o
n
d
i
tio
n
s
,
s
u
ch
as
ch
an
g
es
in
lig
h
tin
g
,
o
cc
l
u
s
io
n
s
s
u
ch
as
wea
r
i
n
g
g
lass
es
o
r
h
ats,
an
d
s
p
o
n
ta
n
eo
u
s
h
ea
d
m
o
v
em
en
ts
,
r
em
ain
s
a
tech
n
ical
ch
all
en
g
e.
R
ec
en
t
s
tu
d
ies
h
av
e
p
r
o
p
o
s
e
d
d
if
f
er
e
n
t
m
eth
o
d
s
to
ad
d
r
e
s
s
th
ese
ch
allen
g
es
s
u
ch
as
u
s
in
g
d
ee
p
lear
n
in
g
with
d
ata
a
u
g
m
e
n
tatio
n
to
h
an
d
le
d
i
v
er
s
e
ex
p
r
ess
io
n
s
,
o
r
ie
n
tatio
n
s
an
d
lig
h
tin
g
en
v
ir
o
n
m
en
ts
[
9
]
,
[
1
0
]
,
a
p
p
ly
in
g
atten
tio
n
m
ec
h
an
is
m
s
to
f
o
cu
s
o
n
k
e
y
f
ac
ial
r
eg
io
n
s
d
esp
ite
o
cc
lu
s
io
n
s
[
1
1
]
,
[
1
2
]
,
em
p
lo
y
in
g
th
r
ee
-
d
im
en
s
io
n
al
(
3
D)
m
o
r
p
h
ab
le
m
o
d
els
to
im
p
r
o
v
e
ac
c
u
r
ac
y
u
n
d
er
p
ar
tial
v
is
ib
ilit
y
[
1
3
]
,
[
1
4
]
,
lev
er
ag
i
n
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
5
8
1
-
4
5
9
2
4582
r
o
b
u
s
t
f
ac
ial
lan
d
m
ar
k
d
etec
tio
n
an
d
tr
ac
k
in
g
f
o
r
o
cc
lu
s
io
n
r
esil
ien
ce
[
1
5
]
,
[
1
6
]
,
i
n
co
r
p
o
r
atin
g
tem
p
o
r
al
m
o
d
els
f
o
r
h
a
n
d
lin
g
s
p
o
n
tan
e
o
u
s
m
o
v
em
e
n
ts
[
1
7
]
,
a
n
d
co
m
b
in
in
g
m
u
lti
-
m
o
d
al
d
ata
s
u
ch
as
r
ed
-
g
r
ee
n
-
b
lu
e
(
R
GB
)
an
d
d
ep
th
f
o
r
en
h
an
ce
d
r
o
b
u
s
tn
ess
[
1
8
]
,
[
1
9
]
.
So
m
e
alg
o
r
ith
m
s
em
p
lo
y
ad
v
a
n
ce
d
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
es
to
ac
c
u
r
ately
d
eter
m
in
e
an
o
r
ien
tatio
n
o
f
u
s
er
h
e
ad
b
y
an
aly
zin
g
f
ac
ial
f
e
atu
r
e
s
f
r
o
m
v
id
eo
i
n
p
u
t
[
2
0
]
,
[
2
1
]
.
T
h
e
ca
p
ab
ilit
y
is
v
ital
f
o
r
e
n
h
an
ci
n
g
i
n
ter
ac
tiv
e
s
y
s
tem
s
,
s
u
ch
as
ed
u
ca
tio
n
al
tech
n
o
lo
g
ies
an
d
s
o
p
h
is
ticated
m
o
n
ito
r
in
g
s
y
s
tem
s
[
2
2
]
,
wh
e
r
e
u
n
d
e
r
s
tan
d
in
g
g
az
e
d
ir
ec
tio
n
an
d
h
e
ad
o
r
ien
tatio
n
ca
n
s
ig
n
if
ican
tly
im
p
r
o
v
e
s
y
s
tem
r
esp
o
n
s
iv
en
ess
an
d
p
er
s
o
n
a
lizatio
n
[
2
3
]
.
W
h
ile
th
e
s
tu
d
ies
d
em
o
n
s
tr
ated
p
r
o
m
is
in
g
r
esu
lts
,
m
an
y
r
elie
d
o
n
co
n
tr
o
lled
en
v
ir
o
n
m
en
ts
o
r
r
eq
u
ir
ed
s
p
ec
ialized
h
ar
d
war
e,
s
u
ch
as
d
ep
th
ca
m
er
as
o
r
m
u
ltip
le
s
en
s
o
r
s
[
2
4
]
.
T
h
is
lim
ited
th
eir
p
r
ac
ticality
in
r
ea
l
-
wo
r
ld
s
ce
n
ar
io
s
an
d
en
ab
led
m
o
r
e
r
ef
in
ed
a
n
d
ac
cu
r
ate
u
s
er
in
t
er
ac
tio
n
ca
p
ab
ilit
ies.
Desp
ite
s
u
b
s
tan
tial
ad
v
an
ce
m
en
ts
in
th
e
f
ield
,
cr
itical
r
esear
ch
g
ap
s
r
em
ain
.
No
tab
l
y
,
f
ew
s
tu
d
y
h
av
e
ex
p
lo
r
e
d
h
ea
d
p
o
s
e
esti
m
atio
n
r
ely
in
g
s
o
lely
o
n
R
GB
v
id
eo
u
n
d
er
d
i
v
er
s
e
an
d
u
n
c
o
n
s
tr
ain
ed
r
ea
l
-
wo
r
ld
co
n
d
itio
n
s
[
2
5
]
.
Ad
d
itio
n
ally
,
th
e
r
o
b
u
s
tn
ess
o
f
ex
is
tin
g
m
eth
o
d
s
ag
ain
s
t
p
ar
tial
o
cc
lu
s
io
n
s
an
d
s
p
o
n
tan
eo
u
s
h
ea
d
m
o
v
em
en
ts
h
as
n
o
t
b
ee
n
s
u
f
f
icien
tly
v
alid
ated
[
2
6
]
.
Mo
r
eo
v
er
,
d
ir
ec
t
in
teg
r
atio
n
o
f
h
ea
d
p
o
s
e
esti
m
atio
n
with
atten
tio
n
d
etec
tio
n
u
s
in
g
l
o
w
co
s
t
h
ar
d
war
e
r
em
ain
lim
ited
[
2
7
]
,
in
d
icatin
g
a
n
ee
d
f
o
r
f
u
r
th
er
in
v
esti
g
atio
n
.
T
h
is
s
tu
d
y
ad
d
r
ess
es
th
ese
g
ap
s
b
y
p
r
o
p
o
s
in
g
a
d
y
n
am
ic
HPE
alg
o
r
ith
m
th
at
in
teg
r
ate
s
Dlib
an
d
Me
d
iaPip
e
m
o
d
els,
ev
alu
ate
d
u
n
d
er
r
ea
l
-
tim
e
co
n
d
itio
n
s
u
s
in
g
a
s
tan
d
ar
d
R
GB
web
ca
m
.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
d
em
o
n
s
tr
ates
ef
f
ec
tiv
en
ess
ac
r
o
s
s
th
r
ee
co
n
d
itio
n
s
:
i)
f
ac
e
a
n
d
h
ea
d
with
o
u
t
o
b
s
tacle
s
,
ii)
f
ac
e
with
o
b
s
tacle
s
s
u
ch
as
th
e
p
r
esen
ce
o
f
g
lass
es
,
an
d
iii)
h
ea
d
p
a
r
tially
o
b
s
tr
u
cted
b
y
wea
r
in
g
a
h
at,
u
n
d
er
b
o
th
co
n
tr
o
lled
a
n
d
s
p
o
n
tan
eo
u
s
h
e
ad
m
o
v
e
m
en
ts
co
n
d
itio
n
s
.
T
h
e
k
ey
c
o
n
tr
ib
u
tio
n
s
o
f
th
is
s
tu
d
y
ar
e
as
f
o
llo
ws:
a
d
ev
elo
p
m
e
n
t
o
f
a
r
o
b
u
s
t,
lo
w
-
co
s
t
h
ea
d
p
o
s
e
esti
m
atio
n
m
et
h
o
d
u
tili
zin
g
f
ac
ial
lan
d
m
ar
k
s
an
d
E
u
le
r
a
n
g
les;
an
ex
p
er
im
en
tal
d
esig
n
t
h
at
i
n
co
r
p
o
r
ates
b
o
t
h
c
o
n
tr
o
lled
a
n
d
s
p
o
n
tan
eo
u
s
h
ea
d
m
o
v
em
en
ts
u
n
d
e
r
v
a
r
y
in
g
o
b
s
tacle
co
n
d
itio
n
s
;
a
d
etailed
an
aly
s
is
o
f
v
is
u
al
atten
tio
n
th
r
o
u
g
h
h
ea
d
p
o
s
e
esti
m
atio
n
ac
cu
r
ac
y
;
a
n
d
a
co
r
r
elatio
n
a
n
aly
s
is
b
etwe
en
p
er
f
o
r
m
a
n
ce
an
d
atten
tio
n
d
etec
tio
n
ac
cu
r
ac
y
.
T
h
e
r
est
o
f
th
e
p
ap
er
is
s
tr
u
ctu
r
ed
as
f
o
llo
ws:
s
ec
tio
n
2
o
u
tlin
es
th
e
m
eth
o
d
o
lo
g
y
,
in
clu
d
in
g
alg
o
r
ith
m
d
ev
elo
p
m
en
t
an
d
e
x
p
er
im
en
tal
s
etu
p
.
Sectio
n
3
p
r
esen
ts
an
d
d
is
cu
s
s
es
r
esu
lts
r
eg
ar
d
in
g
d
etec
tio
n
ac
cu
r
ac
y
,
v
is
u
al
atten
tio
n
,
a
n
d
co
m
p
a
r
is
o
n
s
with
r
elate
d
w
o
r
k
s
.
Sectio
n
4
co
n
cl
u
d
es
with
im
p
licatio
n
s
an
d
r
ec
o
m
m
en
d
atio
n
s
f
o
r
f
u
tu
r
e
r
e
s
ea
r
ch
.
2.
M
E
T
H
O
D
T
h
is
s
ec
tio
n
f
o
llo
ws
a
s
tr
u
ctu
r
ed
a
p
p
r
o
ac
h
as
illu
s
tr
ated
in
Fig
u
r
e
1
,
to
s
y
s
tem
atica
lly
d
e
s
cr
ib
e
th
e
r
esear
ch
p
r
o
ce
s
s
in
a
r
ep
r
o
d
u
c
ib
le
an
d
lo
g
ical
s
eq
u
en
ce
.
Fo
u
r
s
tep
s
n
am
ely
alg
o
r
ith
m
d
e
v
e
lo
p
m
en
t,
h
ar
d
war
e
s
etu
p
,
d
ata
co
llectio
n
,
an
d
d
a
ta
an
aly
s
is
,
ar
e
d
escr
ib
ed
in
d
etail,
ac
co
m
p
an
ie
d
b
y
p
r
o
p
e
r
ju
s
tific
atio
n
s
an
d
s
tan
d
ar
d
p
r
o
ce
d
u
r
es.
T
h
e
alg
o
r
ith
m
d
ev
elo
p
m
en
t
an
d
h
a
r
d
war
e
s
etu
p
s
u
b
s
ec
tio
n
s
p
r
o
v
id
e
a
co
m
p
r
eh
en
s
iv
e
ex
p
lan
atio
n
o
f
all
to
o
ls
an
d
te
ch
n
o
lo
g
ies
u
tili
ze
d
in
th
is
r
esear
ch
.
T
h
e
ex
p
er
i
m
en
tal
s
etu
p
s
wer
e
d
esig
n
ed
to
r
ef
lect
r
ea
l
-
wo
r
ld
c
o
n
d
itio
n
s
th
u
s
,
ad
d
r
ess
in
g
th
e
id
en
tifie
d
g
ap
s
f
o
r
m
ea
n
in
g
f
u
l f
in
d
in
g
s
.
Fig
u
r
e
1
.
A
d
etailed
s
tep
-
by
-
s
tep
d
escr
ip
tio
n
o
f
th
e
r
esear
ch
p
r
o
ce
d
u
r
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Dyn
a
mic
h
ea
d
p
o
s
e
esti
ma
tio
n
in
va
r
ied
co
n
d
itio
n
s
u
s
in
g
D
lib
a
n
d
Med
ia
P
ip
e
(
R
u
s
n
a
n
i Y
a
h
ya
)
4583
2
.
1
.
Alg
o
rit
hm
dev
elo
p
m
ent
Op
en
C
V
is
a
f
r
ee
an
d
o
p
en
-
s
o
u
r
ce
lib
r
ar
y
f
o
r
co
m
p
u
ter
v
is
io
n
a
n
d
m
ac
h
in
e
lear
n
in
g
,
o
f
f
er
in
g
in
ter
f
ac
es
f
o
r
m
u
ltip
le
p
r
o
g
r
am
m
in
g
lan
g
u
ag
es,
in
clu
d
in
g
C
/C
++
,
Py
th
o
n
,
J
av
a,
an
d
MA
T
L
AB
.
I
t
is
co
m
p
atib
le
with
W
in
d
o
ws,
L
in
u
x
,
An
d
r
o
id
,
an
d
Ma
c
OS
p
latf
o
r
m
s
.
W
ith
m
o
r
e
th
a
n
2
,
5
0
0
alg
o
r
ith
m
s
f
o
r
co
m
p
u
ter
v
is
io
n
a
n
d
m
ac
h
in
e
lear
n
in
g
,
th
e
lib
r
ar
y
in
clu
d
es
f
u
n
ctio
n
alities
f
o
r
task
s
lik
e
f
ac
e
d
etec
tio
n
an
d
r
ec
o
g
n
itio
n
[
2
8
]
–
[
3
1
]
.
Dlib
i
s
a
co
m
m
u
n
ity
-
d
r
iv
en
C
++
lib
r
ar
y
th
at
o
f
f
er
s
a
v
ar
iety
o
f
to
o
ls
f
o
r
m
ac
h
in
e
lear
n
in
g
,
c
o
m
p
u
ter
v
is
io
n
,
an
d
im
ag
e
p
r
o
ce
s
s
in
g
.
I
t
in
clu
d
es f
u
n
ctio
n
alities
f
o
r
d
ev
el
o
p
in
g
co
m
p
lex
s
o
f
twar
e,
s
u
ch
as
f
ac
ial
la
n
d
m
ar
k
d
etec
tio
n
,
o
b
ject
d
etec
tio
n
an
d
d
ee
p
lear
n
i
n
g
-
b
ased
task
s
.
Dlib
is
wid
ely
u
tili
ze
d
ac
r
o
s
s
v
ar
io
u
s
f
ield
s
,
in
clu
d
in
g
r
o
b
o
tics
,
m
o
b
ile
d
ev
ices,
an
d
h
ig
h
-
p
er
f
o
r
m
a
n
ce
co
m
p
u
tin
g
en
v
ir
o
n
m
en
ts
[
3
2
]
,
[
3
3
]
.
E
s
s
en
tial
HPE
s
y
s
tem
d
ev
el
o
p
m
e
n
t
lib
r
a
r
ies
in
cl
u
d
e
Op
e
n
C
V
f
o
r
im
ag
e
p
r
o
ce
s
s
in
g
,
Dlib
f
o
r
f
ac
ial
lan
d
m
ar
k
d
etec
tio
n
,
Nu
m
Py
f
o
r
m
ath
em
atica
l
c
o
m
p
u
tatio
n
s
,
an
d
Me
d
iaPip
e
f
o
r
r
ea
l
-
tim
e
m
ac
h
in
e
lear
n
in
g
ac
r
o
s
s
m
u
ltip
le
m
o
d
alities
.
T
h
e
tim
e
lib
r
ar
y
,
C
SV
m
o
d
u
le,
Date
T
im
e,
an
d
OS
also
aid
d
ata
lo
g
g
in
g
,
tim
e
h
an
d
lin
g
,
an
d
s
y
s
tem
in
ter
ac
tio
n
s
.
Fig
u
r
e
2
s
h
o
ws
th
e
f
o
u
r
k
ey
s
tag
es
o
f
th
e
HPE,
wh
ich
in
v
o
lv
e
u
s
in
g
Dlib
an
d
Me
d
iaPip
e
m
o
d
els.
T
h
e
p
r
o
ce
s
s
s
tar
ts
with
Dlib
'
s
f
ac
e
d
etec
to
r
a
n
d
p
r
ed
ict
o
r
,
wh
ich
ar
e
a
p
p
lied
to
id
en
tif
y
f
ac
ial
lan
d
m
ar
k
s
.
Nex
t,
Me
d
iaPip
e
is
u
til
ized
to
ca
lcu
late
th
e
3
D
o
r
ien
tatio
n
o
f
th
e
h
ea
d
[
3
4
]
.
T
h
e
th
ir
d
s
ta
g
e
in
v
o
lv
es
s
o
lv
in
g
th
e
p
er
s
p
ec
tiv
e
-
n
-
p
o
in
t
(
Pn
P)
p
r
o
b
lem
to
o
b
tain
r
o
tatio
n
a
n
d
tr
a
n
s
latio
n
v
ec
to
r
s
[
3
5
]
.
Fi
n
ally
,
th
ese
v
ec
to
r
s
ar
e
tr
an
s
f
o
r
m
e
d
in
to
E
u
ler
an
g
les,
d
eter
m
in
in
g
th
e
d
ir
ec
tio
n
o
f
th
e
h
ea
d
p
o
s
e.
Fig
u
r
e
2
.
Fo
u
r
s
tag
es o
f
th
e
h
e
ad
p
o
s
e
esti
m
atio
n
(
HPE)
Face
d
etec
to
r
an
d
lan
d
m
a
r
k
p
r
ed
icto
r
ar
e
tr
ai
n
ed
m
o
d
els
d
is
tr
ib
u
ted
b
y
Dlib
th
at
d
ete
ct
d
is
tin
ct
f
ac
ial
lan
d
m
ar
k
s
.
I
n
r
ea
l
-
tim
e
,
th
e
f
ac
e
m
esh
m
o
d
el
will
c
o
m
p
lete
th
e
f
ac
e
m
ap
p
in
g
with
an
esti
m
ated
4
7
8
3
-
d
im
en
s
io
n
al
la
n
d
m
ar
k
s
.
T
h
e
Pn
P
p
r
o
b
lem
is
a
class
ic
p
r
o
b
lem
in
th
e
f
ield
o
f
v
is
u
al
co
m
p
u
tin
g
.
T
h
e
ca
m
e
r
a
p
o
s
e
is
d
eter
m
i
n
ed
u
s
in
g
a
s
e
t
o
f
3
D
p
o
in
ts
f
r
o
m
th
e
wo
r
ld
co
o
r
d
in
ate
s
y
s
tem
a
n
d
th
eir
co
r
r
esp
o
n
d
in
g
two
-
d
im
en
s
io
n
al
(
2
D)
p
r
o
jectio
n
s
o
n
th
e
im
ag
e
p
lan
e
.
I
n
HPE
,
th
e
3
D
p
o
in
ts
r
ep
r
esen
t
f
ac
ial
lan
d
m
ar
k
s
with
p
r
ed
ef
in
e
d
p
o
s
itio
n
s
,
wh
ile
th
e
2
D
p
o
in
ts
r
ef
e
r
to
th
eir
id
en
tifie
d
p
o
s
itio
n
s
in
th
e
i
m
ag
e.
T
h
e
r
o
tatio
n
v
ec
to
r
is
a
co
m
p
ac
t
r
ep
r
esen
tatio
n
o
f
th
e
r
o
tatio
n
.
I
t
u
s
es
R
o
d
r
ig
u
es'
r
o
tatio
n
f
o
r
m
u
la
to
r
ep
r
esen
t
a
3
D
r
o
tatio
n
b
y
a
s
in
g
le
v
ec
to
r
r
ath
e
r
th
an
a
m
at
r
ix
.
T
h
e
d
ir
ec
tio
n
o
f
th
is
v
ec
t
o
r
in
d
icate
s
th
e
r
o
tatio
n
ax
is
,
wh
ile
its
m
ag
n
itu
d
e
s
ig
n
if
ies
th
e
r
o
tatio
n
an
g
le,
m
ea
s
u
r
ed
in
r
ad
ia
n
s
.
T
h
e
tr
an
s
l
atio
n
v
ec
to
r
d
escr
ib
es
th
e
o
b
je
ct's
p
o
s
itio
n
,
in
th
is
ca
s
e,
th
e
h
ea
d
,
r
elativ
e
to
th
e
ca
m
er
a.
I
t
in
d
icate
s
h
o
w
f
ar
an
d
in
wh
ich
d
ir
ec
tio
n
th
e
o
b
ject
is
f
r
o
m
th
e
ca
m
er
a
in
3
D
s
p
ac
e.
T
h
e
r
o
ta
tio
n
m
atr
ix
is
a
3
×
3
m
atr
ix
th
at
co
m
p
r
eh
en
s
iv
ely
r
ep
r
esen
ts
r
o
tatio
n
.
I
t
ca
n
b
e
d
er
iv
ed
f
r
o
m
th
e
r
o
tatio
n
v
ec
to
r
u
s
in
g
R
o
d
r
ig
u
es'
f
o
r
m
u
la
an
d
is
u
s
ed
to
tr
an
s
f
o
r
m
co
o
r
d
in
ates
f
r
o
m
o
n
e
s
p
ac
e
to
an
o
t
h
er
.
T
h
e
r
o
tatio
n
m
atr
ix
R
ca
n
b
e
d
ec
o
m
p
o
s
ed
i
n
to
th
r
ee
E
u
ler
a
n
g
les:
p
itch
(
r
o
tatio
n
ar
o
u
n
d
th
e
x
-
ax
is
)
,
y
aw
(
r
o
tatio
n
a
r
o
u
n
d
t
h
e
y
-
ax
is
)
,
a
n
d
r
o
ll
(
r
o
tatio
n
a
r
o
u
n
d
th
e
z
-
a
x
is
)
,
wh
ich
p
r
o
v
i
d
e
a
m
o
r
e
i
n
tu
itiv
e
r
ep
r
esen
tatio
n
o
f
o
r
ie
n
tatio
n
.
2
.
2
.
H
a
rdwa
re
s
et
up
T
h
e
ex
p
er
im
en
t
u
tili
ze
d
a
h
ig
h
-
d
ef
in
itio
n
1
0
8
0
p
2
-
m
eg
a
p
ix
el
web
ca
m
,
p
r
o
d
u
ce
d
b
y
AUKE
Y
with
1
/2
.
9
”
C
MO
S
im
ag
e
s
en
s
o
r
a
n
d
in
teg
r
ated
s
ter
eo
m
icr
o
p
h
o
n
es.
T
h
e
f
r
am
e
r
ate
was
3
0
f
r
am
es
p
er
s
ec
o
n
d
(
f
p
s
)
.
T
h
e
s
y
s
tem
s
p
ec
if
icatio
n
s
f
o
r
r
u
n
n
in
g
t
h
e
p
r
o
g
r
a
m
in
clu
d
ed
:
W
in
d
o
ws
1
1
(
6
4
-
b
it),
a
1
3
th
Gen
I
n
tel(
R
)
C
o
r
e
(
T
M)
i7
-
1
3
7
0
0
HX
C
PU,
an
d
1
6
.
0
0
GB
o
f
m
em
o
r
y
.
Fig
u
r
e
3
illu
s
tr
ates
th
e
e
x
p
er
i
m
en
tal
s
etu
p
,
wh
er
e
a
h
i
g
h
-
r
e
s
o
lu
tio
n
web
ca
m
is
em
p
l
o
y
ed
to
d
etec
t
an
d
r
ec
o
r
d
.
T
h
e
web
ca
m
is
in
teg
r
ated
in
to
th
e
s
y
s
tem
f
r
am
ewo
r
k
to
en
s
u
r
e
en
h
an
ce
d
HPE.
T
h
r
o
u
g
h
o
u
t
th
e
ex
p
er
im
en
t,
th
e
co
m
p
u
ter
is
co
n
n
ec
ted
to
th
e
web
ca
m
to
m
o
n
ito
r
an
d
tr
ac
k
th
e
p
r
o
g
r
ess
.
No
tice
th
at
th
e
b
u
ilt
-
in
co
m
p
u
ter
web
ca
m
is
n
o
t
u
s
ed
d
u
e
to
its
lo
wer
r
eso
lu
tio
n
.
A
c
h
air
is
p
o
s
itio
n
ed
in
f
r
o
n
t
o
f
th
e
ca
m
er
a
to
f
ac
ilit
ate
s
u
b
ject
p
ar
ticip
atio
n
.
Su
b
jects
ar
e
in
s
tr
u
cted
to
s
it
co
m
f
o
r
tab
l
y
in
th
e
ch
air
b
e
f
o
r
e
b
e
g
in
n
in
g
th
e
s
tu
d
y
.
Ma
in
tain
in
g
a
d
is
tan
ce
o
f
0
.
5
m
eter
s
o
r
less
b
etwe
en
th
e
ch
air
an
d
th
e
ca
m
er
a
is
cr
u
cial
to
en
s
u
r
e
p
r
ec
is
e
f
ac
e
d
etec
tio
n
.
T
h
is
d
is
tan
ce
p
ar
am
eter
is
ca
r
ef
u
lly
s
elec
ted
to
o
p
tim
ize
s
y
s
tem
p
er
f
o
r
m
an
ce
.
T
h
e
r
esear
ch
er
o
v
er
s
ee
s
th
e
s
tu
d
y
’
s
p
r
o
g
r
ess
u
s
in
g
th
e
e
x
ter
n
al
web
ca
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
5
8
1
-
4
5
9
2
4584
Fig
u
r
e
3
.
E
x
p
er
im
e
n
t setu
p
f
o
r
p
er
f
o
r
m
in
g
h
ea
d
p
o
s
e
esti
m
atio
n
(
HPE)
2
.
3
.
Da
t
a
c
o
llect
io
n
T
h
ir
ty
s
tu
d
e
n
ts
f
r
o
m
Po
l
y
tech
n
ic
Su
ltan
Salah
u
d
d
in
Ab
d
u
l
Aziz
Sh
ah
(
PS
SAAS),
Sh
ah
Alam
,
ag
ed
1
9
an
d
2
7
,
p
ar
ticip
ated
in
th
is
s
tu
d
y
.
I
n
s
titu
tio
n
al
a
p
p
r
o
v
al
was
o
b
tain
ed
,
an
d
wr
itten
co
n
s
en
t
(
R
E
C
4
/2
0
2
0
/B
M
Pin
d
.
2
(
2
0
2
0
)
)
was
tak
en
f
r
o
m
all
s
u
b
jects
.
T
wo
ca
teg
o
r
ies
o
f
d
ata
co
llectio
n
wer
e
co
n
d
u
cte
d
f
o
r
ea
ch
s
u
b
ject.
First,
th
e
co
n
tr
o
lled
ca
teg
o
r
y
wh
er
e
th
e
s
u
b
ject
p
er
f
o
r
m
e
d
co
n
tr
o
lled
h
ea
d
m
o
v
em
en
ts
ac
co
r
d
in
g
to
th
e
in
s
tr
u
ctio
n
s
b
y
th
e
r
esear
ch
er
.
I
n
th
e
s
ec
o
n
d
p
h
ase,
th
e
s
u
b
ject
ca
r
r
ied
o
u
t
s
p
o
n
tan
eo
u
s
h
ea
d
m
o
v
em
en
ts
.
B
o
th
ca
teg
o
r
ies
wer
e
e
v
alu
at
ed
u
n
d
er
th
r
ee
d
is
tin
ct
co
n
d
itio
n
s
:
f
ac
e
a
n
d
h
ea
d
with
o
u
t
o
b
s
tacle
s
,
f
ac
e
with
o
b
s
tacle
s
,
an
d
h
ea
d
with
o
b
s
tacle
s
.
E
ac
h
co
n
d
itio
n
i
n
v
o
lv
e
d
a
r
ea
l
-
tim
e
h
ea
d
p
o
s
e
d
etec
tio
n
s
ess
io
n
last
in
g
ap
p
r
o
x
im
ately
3
0
0
s
ec
o
n
d
s
,
d
u
r
in
g
w
h
ich
th
r
ee
t
y
p
es
o
f
o
u
tp
u
ts
wer
e
s
im
u
ltan
eo
u
s
ly
g
en
er
ated
:
v
id
eo
r
ec
o
r
d
in
g
,
ex
tr
ac
ted
im
ag
e
s
,
an
d
co
r
r
esp
o
n
d
in
g
C
SV
f
il
es
co
n
tain
in
g
h
ea
d
p
o
s
e
d
ata.
I
n
th
e
co
n
tr
o
lled
ca
teg
o
r
y
,
th
e
s
u
b
jects
wer
e
ask
ed
t
o
s
it
co
m
f
o
r
ta
b
ly
o
n
th
e
p
r
o
v
id
e
d
ch
air
.
T
h
e
r
esear
ch
er
in
s
tr
u
cte
d
th
e
s
u
b
je
cts
to
p
er
f
o
r
m
h
ea
d
m
o
v
em
e
n
ts
o
n
ce
t
h
e
s
y
s
tem
p
r
o
g
r
am
was
in
itiated
.
Du
r
in
g
th
is
ca
teg
o
r
y
,
f
iv
e
s
p
ec
if
ic
h
ea
d
m
o
v
em
e
n
ts
wer
e
r
ec
o
r
d
ed
,
e
ac
h
last
in
g
b
etwe
en
2
0
an
d
3
0
s
ec
o
n
d
s
,
r
esu
ltin
g
in
th
e
co
llectio
n
o
f
m
o
r
e
th
a
n
6
0
d
ata
p
o
in
ts
.
Su
b
jects
wer
e
in
s
tr
u
cted
to
o
r
ien
t
th
eir
h
ea
d
f
o
r
war
d
,
u
p
war
d
,
d
o
wn
war
d
,
a
n
d
to
t
h
e
r
ig
h
t
an
d
lef
t,
with
h
o
r
izo
n
tal
r
o
tatio
n
s
ex
ce
ed
in
g
7
5
d
eg
r
ee
s
an
d
v
er
tical
tilt
s
ex
ce
ed
in
g
4
5
d
eg
r
ee
s
.
Su
b
je
cts
f
o
llo
wed
a
s
tr
u
ctu
r
e
d
s
eq
u
en
ce
:
b
e
g
in
n
in
g
b
y
f
ac
in
g
f
o
r
war
d
(
0
°),
t
h
en
s
lo
wly
tilt
ed
th
eir
h
ea
d
s
u
p
war
d
to
a
f
u
ll
tilt
o
f
4
5
°.
Af
ter
war
d
s
,
th
ey
tilt
ed
th
eir
h
ea
d
s
d
o
wn
war
d
to
a
f
u
ll
tilt
o
f
-
4
5
°.
T
h
e
n
ex
t
s
tep
r
eq
u
ir
e
d
th
em
to
tu
r
n
t
h
eir
h
ea
d
s
to
t
h
e
r
ig
h
t
u
n
til
r
ea
c
h
in
g
a
tilt
o
f
-
7
5
°,
an
d
f
in
ally
,
th
ey
tu
r
n
ed
th
eir
h
ea
d
s
to
th
e
lef
t
to
a
m
ax
im
u
m
tilt
o
f
7
5
°
.
I
n
th
e
s
ec
o
n
d
ca
teg
o
r
y
,
s
u
b
jects
co
u
ld
m
o
v
e
th
eir
h
ea
d
s
f
r
ee
ly
in
f
r
o
n
t o
f
th
e
ca
m
er
a
f
o
r
1
2
0
s
ec
o
n
d
s
with
o
u
t
an
y
s
p
ec
if
ied
d
ir
ec
tio
n
al
co
n
s
tr
ain
ts
.
T
h
e
f
lo
wch
ar
t
in
Fig
u
r
e
4
ill
u
s
tr
ates
d
etec
tin
g
an
d
esti
m
atin
g
h
ea
d
p
o
s
e
u
s
in
g
an
R
GB
ca
m
er
a,
Dlib
’
s
f
ac
e
d
etec
to
r
an
d
Me
d
i
aPip
e’
s
f
ac
e
m
esh
.
T
h
e
p
r
o
ce
s
s
s
tar
t
s
with
th
e
ca
m
er
a
d
etec
tin
g
a
f
ac
e.
On
ce
a
f
ac
e
is
d
etec
ted
,
Dlib
is
em
p
lo
y
ed
to
lo
ca
te
th
e
f
ac
ial
f
ea
tu
r
es.
Me
d
iaPip
e
f
ac
e
m
esh
d
etec
ts
lan
d
m
ar
k
s
,
co
n
tr
ib
u
tin
g
to
d
eter
m
in
in
g
th
e
o
r
ien
tatio
n
o
f
th
e
h
ea
d
.
T
h
e
alg
o
r
ith
m
th
en
d
eter
m
in
es
wh
eth
er
th
e
h
ea
d
p
o
s
e
is
in
th
e
s
p
ec
if
ied
p
o
s
itio
n
.
I
f
th
e
h
ea
d
p
o
s
e
is
d
etec
ted
,
th
e
s
y
s
tem
ev
alu
ates
th
e
d
ir
ec
tio
n
in
wh
ich
th
e
h
ea
d
is
o
r
ien
ted
.
Dep
en
d
i
n
g
o
n
th
e
d
ir
ec
tio
n
,
th
e
ap
p
r
o
p
r
iate
tex
t
is
d
is
p
lay
ed
:
“L
o
o
k
i
n
g
Up
”
f
o
r
h
ea
d
u
p
war
d
,
“L
o
o
k
in
g
Do
wn
”
f
o
r
h
ea
d
d
o
wn
war
d
,
“Fo
r
war
d
”
f
o
r
h
ea
d
f
o
r
war
d
,
“L
o
o
k
in
g
R
ig
h
t”
f
o
r
h
ea
d
-
tu
r
n
in
g
r
ig
h
t,
an
d
“L
o
o
k
in
g
L
ef
t”
f
o
r
h
ea
d
-
tu
r
n
in
g
lef
t.
I
f
th
e
f
ac
e
is
n
o
t
in
an
y
tr
u
e
p
o
s
itio
n
,
th
e
s
y
s
tem
d
is
p
lay
s
th
e
tex
t
“Fac
e
n
o
t
d
etec
ted
”.
Af
ter
d
e
ter
m
in
in
g
th
e
h
ea
d
o
r
ien
tatio
n
,
th
e
s
y
s
tem
s
av
es
th
e
o
u
tp
u
t
im
ag
e,
v
id
e
o
an
d
C
SV
d
ata,
wh
ich
ar
e
lik
ely
to
co
n
tain
d
etails
o
f
th
e
d
etec
ted
h
ea
d
p
o
s
es.
T
h
e
p
r
o
ce
s
s
th
en
co
n
clu
d
es
an
d
is
r
ea
d
y
to
s
tar
t o
v
er
with
n
ew
d
etec
tio
n
s
.
2
.
4
.
Da
t
a
a
na
ly
s
is
T
h
e
ef
f
ec
tiv
en
ess
o
f
th
e
s
y
s
te
m
is
ass
e
s
s
ed
b
ased
s
o
lely
o
n
th
e
ac
cu
r
ac
y
p
er
ce
n
tag
e
.
I
t
is
im
p
o
r
tan
t
to
n
o
te
th
at
th
e
p
r
ed
icted
d
ata
o
u
tp
u
t
b
y
th
e
s
y
s
tem
m
ay
n
o
t
alwa
y
s
b
e
en
tire
ly
ac
c
u
r
ate,
p
ar
ticu
lar
ly
wh
en
th
e
h
ea
d
tu
r
n
r
em
ain
s
with
i
n
a
n
a
r
r
o
w
r
an
g
e
o
f
d
eg
r
e
es.
No
n
eth
eless
,
th
e
s
y
s
tem
ca
teg
o
r
izes
th
ese
m
o
v
em
en
ts
as
u
p
,
d
o
wn
,
f
o
r
war
d
,
r
ig
h
t,
o
r
lef
t
h
ea
d
d
ir
ec
tio
n
.
T
o
f
u
r
th
er
e
v
alu
ate
th
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
s
y
s
tem
,
th
e
r
esu
lts
wer
e
class
i
f
ied
b
ased
o
n
f
o
u
r
s
tan
d
ar
d
m
etr
ics:
tr
u
e
p
o
s
itiv
e
(
T
P),
f
alse
p
o
s
itiv
e
(
FP
)
,
tr
u
e
n
eg
ativ
es
(
T
N)
an
d
f
alse
n
eg
ativ
es
(
FN)
.
A
m
an
u
al
v
er
if
icatio
n
p
r
o
ce
s
s
was
co
n
d
u
cted
b
y
co
m
p
ar
in
g
th
e
p
r
ed
icted
h
ea
d
d
ir
ec
tio
n
b
y
th
e
s
y
s
tem
ag
ain
s
t
th
e
ac
tu
al
h
e
ad
d
ir
ec
tio
n
r
ec
o
r
d
ed
in
th
e
v
i
d
eo
.
Su
b
s
eq
u
en
tly
,
th
e
p
er
f
o
r
m
an
ce
ac
cu
r
ac
y
f
o
r
ea
ch
s
u
b
ject
was
ca
lcu
lated
a
s
th
e
p
er
ce
n
tag
e
o
f
tr
u
e
d
etec
t
io
n
s
r
elativ
e
to
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Dyn
a
mic
h
ea
d
p
o
s
e
esti
ma
tio
n
in
va
r
ied
co
n
d
itio
n
s
u
s
in
g
D
lib
a
n
d
Med
ia
P
ip
e
(
R
u
s
n
a
n
i Y
a
h
ya
)
4585
to
tal
n
u
m
b
er
o
f
d
etec
tio
n
s
,
i
n
clu
d
in
g
b
o
t
h
co
r
r
ec
t
a
n
d
i
n
co
r
r
ec
t
p
r
ed
ictio
n
s
,
ac
r
o
s
s
al
l
co
n
d
itio
n
s
.
T
h
e
d
ef
in
itio
n
s
o
f
ea
c
h
m
etr
ic
ar
e
s
u
m
m
ar
ized
in
T
a
b
le
1
.
T
h
ese
m
etr
ics
p
r
o
v
id
e
a
d
etailed
v
ie
w
o
f
th
e
d
etec
tio
n
s
y
s
tem
ca
p
ab
ilit
ies an
d
h
elp
id
en
tify
s
p
ec
if
ic
er
r
o
r
s
co
n
tr
i
b
u
t
in
g
to
o
v
er
all
ac
cu
r
ac
y
an
d
s
y
s
tem
r
o
b
u
s
tn
ess
.
Fig
u
r
e
4
.
Flo
wch
ar
t
o
f
h
ea
d
p
o
s
e
esti
m
atio
n
d
ata
co
llectio
n
T
ab
le
1
.
Def
in
itio
n
s
o
f
T
P,
FP
,
T
N
an
d
FN f
o
r
h
ea
d
p
o
s
e
est
im
atio
n
ev
alu
atio
n
C
a
t
e
g
o
r
y
D
e
f
i
n
i
t
i
o
n
Tr
u
e
P
o
s
i
t
i
v
e
(
TP)
Th
e
sy
s
t
e
m
c
o
r
r
e
c
t
l
y
i
d
e
n
t
i
f
i
e
s
t
h
e
h
e
a
d
p
o
se
,
ma
t
c
h
i
n
g
t
h
e
a
c
t
u
a
l
d
i
r
e
c
t
i
o
n
.
F
a
l
se
P
o
s
i
t
i
v
e
(
F
P
)
Th
e
sy
s
t
e
m
i
n
c
o
r
r
e
c
t
l
y
p
r
e
d
i
c
t
s
a
h
e
a
d
p
o
s
e
t
h
a
t
d
i
d
n
o
t
o
c
c
u
r
.
Tr
u
e
N
e
g
a
t
i
v
e
(
TN
)
Th
e
sy
s
t
e
m
c
o
r
r
e
c
t
l
y
r
e
c
o
g
n
i
z
e
s
t
h
a
t
n
o
c
h
a
n
g
e
i
n
h
e
a
d
p
o
se
o
c
c
u
r
r
e
d
w
h
e
n
t
h
e
r
e
w
a
s
n
o
s
i
g
n
i
f
i
c
a
n
t
m
o
v
e
m
e
n
t
.
F
a
l
se
N
e
g
a
t
i
v
e
(
F
N
)
Th
e
sy
s
t
e
m
f
a
i
l
s
t
o
d
e
t
e
c
t
a
n
a
c
t
u
a
l
h
e
a
d
p
o
se
,
c
l
a
ss
i
f
y
i
n
g
i
t
i
n
c
o
r
r
e
c
t
l
y
o
r
mi
ssi
n
g
i
t
a
l
t
o
g
e
t
h
e
r
.
T
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
s
y
s
tem
was
ev
alu
ated
b
ased
o
n
th
e
ac
cu
r
ac
y
m
etr
ic.
Acc
u
r
ac
y
is
th
e
p
r
o
p
o
r
tio
n
o
f
co
r
r
ec
t
p
r
e
d
ictio
n
s
,
in
clu
d
in
g
tr
u
e
p
o
s
itiv
es
(
T
P)
an
d
tr
u
e
n
eg
ativ
es
(
T
N)
,
r
elativ
e
to
th
e
to
tal
n
u
m
b
er
o
f
p
r
ed
ictio
n
s
.
I
t is ca
lcu
lated
u
s
in
g
(
1
)
:
=
(
+
)
/
(
+
+
+
)
(
1
)
T
h
is
m
etr
ic
r
ef
lects
th
e
o
v
er
al
l
co
r
r
ec
tn
ess
o
f
th
e
h
ea
d
p
o
s
e
esti
m
atio
n
s
y
s
tem
ac
r
o
s
s
all
co
n
d
itio
n
s
an
d
p
ar
ticip
an
ts
.
On
th
e
o
th
er
h
an
d
,
ac
cu
r
ate
d
etec
tio
n
s
ar
e
wh
er
e
th
e
p
r
ed
ictio
n
b
y
th
e
s
y
s
tem
co
r
r
esp
o
n
d
s
with
th
e
e
x
ac
t
p
o
s
e,
th
u
s
en
h
an
cin
g
t
h
e
ac
c
u
r
ac
y
o
f
th
e
s
y
s
tem
.
T
h
e
p
er
f
o
r
m
an
ce
ac
cu
r
ac
y
r
elate
d
to
v
is
u
al
atten
tio
n
will
also
b
e
ca
lcu
la
ted
an
d
v
is
u
alize
d
,
p
r
o
v
id
in
g
in
s
ig
h
ts
in
to
th
e
v
is
u
al
atte
n
tio
n
lev
els
u
n
d
er
d
if
f
er
en
t
co
n
d
itio
n
s
.
Vis
u
al
atten
tio
n
was
q
u
an
tifie
d
b
y
c
alcu
latin
g
th
e
p
r
o
p
o
r
tio
n
o
f
f
o
r
war
d
h
ea
d
p
o
s
e
d
etec
tio
n
s
(
,
)
r
elativ
e
to
th
e
to
tal
n
u
m
b
er
o
f
d
etec
tio
n
s
(
,
)
r
ec
o
r
d
ed
b
y
th
e
s
y
s
tem
.
Vis
u
al
atte
n
tio
n
was
co
m
p
u
ted
u
s
in
g
(
2
)
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
5
8
1
-
4
5
9
2
4586
=
(
,
/
,
)
×
100
(
2
)
T
h
ese
m
etr
ics
wer
e
u
s
ed
to
q
u
an
tify
th
e
in
d
i
v
id
u
al
lev
el
o
f
v
is
u
al
atten
tio
n
d
u
r
in
g
e
x
p
er
im
en
tal
s
ess
io
n
s
.
T
h
is
m
eth
o
d
was
ch
o
s
en
d
u
e
to
its
lo
w
co
m
p
u
tatio
n
al
co
s
t
an
d
r
ea
l
-
tim
e
ef
f
icien
cy
,
m
ak
in
g
it
id
ea
l
f
o
r
p
r
ac
tical
ap
p
licatio
n
s
.
Un
lik
e
d
ee
p
-
lear
n
i
n
g
-
b
ased
ap
p
r
o
ac
h
es
th
at
r
eq
u
ir
e
lar
g
e
d
atasets
an
d
h
ig
h
p
r
o
c
ess
in
g
p
o
wer
,
o
u
r
alg
o
r
ith
m
lev
e
r
a
g
es
f
ac
ial
lan
d
m
a
r
k
s
an
d
E
u
ler
an
g
les
f
o
r
ac
cu
r
ate
an
d
r
o
b
u
s
t
h
ea
d
p
o
s
e
esti
m
atio
n
u
s
in
g
a
s
im
p
le
web
ca
m
s
etu
p
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
s
tu
d
y
aim
ed
to
d
ev
elo
p
a
r
ea
l
-
tim
e
h
ea
d
p
o
s
e
esti
m
atio
n
s
y
s
tem
u
s
in
g
Dlib
an
d
Me
d
i
aPip
e
th
at
r
em
ain
s
ef
f
ec
tiv
e
u
n
d
e
r
v
ar
i
o
u
s
h
ea
d
m
o
v
em
en
t
co
n
d
itio
n
s
an
d
f
ac
ial
o
b
s
tr
u
ctio
n
s
.
I
n
th
is
s
tu
d
y
,
th
ir
ty
s
tu
d
en
ts
p
ar
ticip
ated
.
T
wo
ca
teg
o
r
ies
o
f
d
ata
co
llectio
n
w
er
e
co
n
d
u
cted
f
o
r
ea
c
h
s
u
b
je
ct:
co
n
tr
o
lled
h
ea
d
m
o
v
em
en
t
a
n
d
s
p
o
n
tan
eo
u
s
h
ea
d
m
o
v
em
e
n
t.
Nex
t,
b
o
th
ca
teg
o
r
ies
wer
e
ev
alu
ated
u
n
d
e
r
th
r
ee
co
n
d
itio
n
s
:
f
ac
e
an
d
h
ea
d
with
o
u
t
o
b
s
tacle
s
,
f
ac
e
with
o
b
s
tacle
s
,
an
d
h
ea
d
with
o
b
s
tacle
s
.
Fu
r
th
er
,
t
h
is
s
ec
tio
n
p
r
o
v
id
es
an
in
-
d
ep
t
h
an
aly
s
is
o
f
th
e
s
tu
d
y
d
ata
to
ac
h
ie
v
e
th
at
o
b
jecti
v
e.
T
o
ev
al
u
ate
th
e
v
alid
ity
o
f
th
e
alg
o
r
ith
m
,
t
h
e
an
aly
s
is
f
o
cu
s
es
o
n
th
e
ac
cu
r
ac
y
r
ate,
wh
ich
is
ca
teg
o
r
ized
in
to
co
n
tr
o
lled
a
n
d
s
p
o
n
tan
e
o
u
s
h
ea
d
m
o
v
em
en
ts
.
Ad
d
itio
n
ally
,
th
e
e
f
f
ec
tiv
en
ess
o
f
th
e
alg
o
r
ith
m
i
n
d
etec
tin
g
v
is
u
al
atten
tio
n
will a
ls
o
b
e
an
aly
ze
d
.
3
.
1
.
Co
ntr
o
lled
hea
d m
o
v
e
ment
I
n
th
is
ex
p
er
im
en
t,
th
e
s
u
b
je
cts
wer
e
d
ir
ec
ted
to
m
o
v
e
t
h
eir
h
ea
d
s
to
ac
h
iev
e
f
iv
e
s
p
e
cif
ic
h
ea
d
o
r
ien
tatio
n
s
g
r
ad
u
ally
.
T
h
e
r
e
s
u
lts
s
h
o
wn
in
Fig
u
r
e
5
illu
s
tr
ate
th
at
th
e
av
er
a
g
e
p
er
f
o
r
m
an
ce
was
h
i
g
h
est,
r
ea
ch
in
g
9
9
%,
in
co
n
d
itio
n
s
wh
er
e
b
o
th
th
e
f
ac
e
an
d
h
ea
d
wer
e
v
is
ib
le
with
o
u
t
o
b
s
tacle
s
.
T
h
e
ac
cu
r
ac
y
d
ec
r
ea
s
ed
s
lig
h
tly
t
o
9
8
%
in
b
o
th
f
ac
e
an
d
h
ea
d
with
o
b
s
tacle
co
n
d
itio
n
s
,
in
d
icatin
g
th
at
o
b
s
tacle
s
m
ar
g
in
ally
im
p
ac
ted
th
e
o
v
er
all
p
e
r
f
o
r
m
an
ce
b
u
t
m
ai
n
tain
ed
h
ig
h
ac
cu
r
ac
y
lev
els
ac
r
o
s
s
all
c
o
n
d
itio
n
s
.
T
h
e
s
lig
h
t
d
ec
r
ea
s
e
in
ac
cu
r
ac
y
h
a
p
p
en
s
b
ec
au
s
e
o
b
s
tacle
s
ca
n
b
l
o
ck
lig
h
t,
ca
u
s
in
g
s
h
a
d
o
ws
o
r
u
n
e
v
en
lig
h
tin
g
o
n
th
e
f
ac
e,
wh
ich
m
a
k
es
it
h
ar
d
er
f
o
r
th
e
s
y
s
tem
to
r
ec
o
g
n
ize
h
e
ad
p
o
s
itio
n
s
co
r
r
ec
tly
.
E
v
e
n
s
o
,
th
e
s
y
s
tem
s
till
s
h
o
ws a
p
r
o
m
in
e
n
t le
v
el
o
f
ef
f
icien
cy
.
Fig
u
r
e
5
.
Av
e
r
ag
e
o
f
p
er
f
o
r
m
a
n
ce
ac
cu
r
ac
y
in
th
e
c
o
n
tr
o
lled
h
ea
d
m
o
v
em
en
t c
ateg
o
r
y
3
.
2
.
Sp
o
nta
neo
us
hea
d m
o
v
e
m
ent
T
h
is
s
ec
tio
n
will
ex
am
in
e
th
e
r
esu
lts
o
f
an
ex
p
e
r
im
en
t
in
w
h
ich
s
u
b
jects
m
o
v
e
th
ei
r
h
ea
d
f
r
ee
ly
an
d
u
n
p
r
e
d
ictab
ly
with
o
u
t
an
y
s
p
ec
if
ic
g
u
id
an
ce
.
T
h
e
ex
p
er
i
m
en
t
was
r
ep
ea
ted
th
r
ee
ti
m
es
u
n
d
er
d
if
f
er
e
n
t
co
n
d
itio
n
s
: f
ac
e
a
n
d
h
ea
d
with
o
u
t o
b
s
tacle
s
,
f
ac
e
with
o
b
s
tacle
s
,
an
d
h
ea
d
with
o
b
s
tacle
s
.
Fig
u
r
e
6
s
h
o
ws
th
e
a
v
er
ag
e
p
er
f
o
r
m
an
ce
ac
cu
r
ac
y
in
p
er
ce
n
tag
es
o
f
th
e
s
y
s
tem
u
n
d
e
r
d
if
f
er
e
n
t
co
n
d
itio
n
s
:
f
ac
e
an
d
h
ea
d
with
o
u
t
o
b
s
tacle
s
,
f
ac
e
with
o
b
s
tacle
s
,
an
d
h
ea
d
with
o
b
s
tacle
s
.
T
h
e
h
ig
h
est
ac
cu
r
ac
y
o
f
9
0
% is
o
b
s
er
v
e
d
wh
en
th
er
e
ar
e
n
o
o
b
s
tacle
s
,
in
d
icatin
g
o
p
tim
al
p
er
f
o
r
m
an
c
e
with
clea
r
v
is
ib
ilit
y
o
f
th
e
f
ac
e
an
d
h
ea
d
.
T
h
e
ac
c
u
r
ac
y
d
ec
r
ea
s
es
s
lig
h
tly
to
8
7
%
wh
en
o
b
s
tacle
s
ar
e
p
r
esen
t
o
n
th
e
f
ac
e,
s
u
ch
as
g
lass
es,
an
d
f
u
r
th
er
to
th
e
h
ea
d
with
o
b
s
tacle
s
,
s
u
ch
as
a
ca
p
.
Desp
ite
th
ese
r
e
d
u
ctio
n
s
,
th
e
s
y
s
tem
m
ain
tain
s
h
ig
h
ac
cu
r
ac
y
,
d
em
o
n
s
tr
atin
g
r
o
b
u
s
tn
ess
in
v
ar
io
u
s
r
ea
l
-
w
o
r
ld
s
ce
n
ar
io
s
.
T
h
e
s
lig
h
t
d
r
o
p
in
ac
cu
r
ac
y
with
f
ac
e
o
b
s
tacle
s
s
u
g
g
ests
th
at
t
h
ese
m
ig
h
t
h
in
d
e
r
lan
d
m
a
r
k
d
etec
tio
n
m
o
r
e
t
h
an
h
ea
d
o
b
s
tacle
s
.
Su
d
d
en
h
ea
d
m
o
v
em
en
ts
o
r
p
o
o
r
lig
h
tin
g
c
o
n
d
itio
n
s
also
af
f
ec
ted
lan
d
m
ar
k
d
etec
tio
n
.
T
h
ese
lim
itatio
n
s
h
ig
h
lig
h
t
th
e
n
ee
d
f
o
r
f
u
r
th
e
r
r
e
f
in
em
en
t,
s
u
ch
as
in
co
r
p
o
r
atin
g
m
u
lti
-
v
iew
c
am
er
as
o
r
tr
ain
in
g
with
a
m
o
r
e
d
i
v
er
s
e
d
ataset.
Ov
er
all,
8
8
%
o
f
th
e
ac
c
u
r
ac
y
f
o
r
s
p
o
n
tan
eo
u
s
h
ea
d
m
o
v
em
en
t
ca
teg
o
r
ies
i
n
d
icate
d
t
h
at
t
h
e
s
y
s
tem
is
h
ig
h
ly
r
eliab
le.
Sti
ll,
f
u
tu
r
e
im
p
r
o
v
e
m
en
ts
co
u
ld
f
o
cu
s
o
n
in
c
r
ea
s
in
g
ac
cu
r
ac
y
in
th
e
p
r
esen
ce
o
f
o
b
s
tacle
s
to
f
u
r
th
er
en
h
an
ce
p
er
f
o
r
m
an
ce
.
99
98
98
0
20
40
60
80
100
F
ac
e
&
he
ad
w
i
t
ho
ut
o
bs
t
ac
l
e
s
F
ac
e
wi
t
h
o
bs
t
ac
l
e
s
H
e
ad
w
i
t
h
o
bs
t
ac
l
e
s
P
e
r
f
o
r
m
an
c
e
Ac
c
ur
ac
y
(
%)
C
o
nd
i
t
i
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Dyn
a
mic
h
ea
d
p
o
s
e
esti
ma
tio
n
in
va
r
ied
co
n
d
itio
n
s
u
s
in
g
D
lib
a
n
d
Med
ia
P
ip
e
(
R
u
s
n
a
n
i Y
a
h
ya
)
4587
Fig
u
r
e
7
p
r
esen
ts
p
er
f
o
r
m
a
n
ce
ac
cu
r
ac
y
in
p
er
ce
n
ta
g
es
f
o
r
h
ea
d
p
o
s
e
esti
m
atio
n
ac
r
o
s
s
th
ir
ty
s
u
b
jects,
S1
to
S3
0
,
in
th
r
ee
co
n
d
itio
n
s
.
T
h
e
f
ac
e
an
d
h
e
ad
with
o
u
t
o
b
s
tacle
s
ca
teg
o
r
y
co
n
s
is
ten
tly
s
h
o
w
h
ig
h
er
p
er
f
o
r
m
an
ce
ac
r
o
s
s
m
o
s
t
s
am
p
les
th
an
th
e
o
th
er
two
co
n
d
itio
n
s
,
with
m
an
y
s
co
r
es
n
ea
r
in
g
o
r
ex
ce
ed
in
g
9
0
%.
T
h
is
d
em
o
n
s
tr
ates
th
at
th
e
s
y
s
tem
r
eliab
ly
d
etec
ts
b
o
th
f
ac
e
an
d
h
ea
d
with
n
o
o
b
s
tr
u
ctio
n
s
,
ex
h
ib
itin
g
s
tab
le
an
d
co
n
s
is
ten
t
r
esu
lts
.
T
h
e
s
co
r
es
in
th
is
c
ateg
o
r
y
ar
e
tig
h
tly
g
r
o
u
p
ed
,
in
d
icatin
g
p
r
ed
ictab
l
e
an
d
d
e
p
en
d
a
b
le
p
er
f
o
r
m
an
ce
in
ex
p
licit,
o
b
s
tacle
-
f
r
ee
s
itu
atio
n
s
.
T
h
e
f
ac
e
with
o
b
s
tacle
s
ca
teg
o
r
y
s
h
o
ws
m
o
r
e
v
ar
iatio
n
in
s
co
r
es,
r
an
g
in
g
f
r
o
m
as
lo
w
as
8
0
in
s
o
m
e
ca
s
es,
s
u
ch
as
S4
,
S5
,
an
d
S1
7
,
to
h
ig
h
e
r
v
alu
es
in
o
th
er
s
lik
e
S1
,
S2
0
,
a
n
d
S2
3
.
Per
f
o
r
m
an
ce
d
r
o
p
s
s
ig
n
if
ican
tly
f
o
r
s
o
m
e
s
u
b
ject
s
lik
e
S1
0
,
S1
7
,
an
d
S2
7
,
in
d
icatin
g
th
at
o
b
s
tacle
s
af
f
ec
t
f
ac
e
d
etec
tio
n
m
o
r
e
th
an
h
ea
d
d
etec
tio
n
.
T
h
is
s
u
g
g
ests
th
at
f
ac
e
d
etec
tio
n
is
s
u
s
ce
p
tib
le
to
v
is
u
al
o
b
s
tr
u
ctio
n
s
,
lead
in
g
to
lo
wer
ac
cu
r
ac
y
th
an
in
o
b
s
tacle
-
f
r
ee
s
itu
atio
n
s
.
Ho
wev
er
,
7
o
f
th
e
3
0
s
u
b
jects
s
u
ch
as
S1
,
S2
,
S
1
6
,
S2
0
,
S2
3
,
S2
6
,
an
d
S2
8
ac
h
iev
ed
h
i
g
h
er
ac
c
u
r
ac
y
in
th
e
f
ac
e
with
o
b
s
tacle
s
co
n
d
itio
n
,
lik
ely
b
ec
au
s
e
o
f
d
is
tin
ct
f
ac
ial
f
ea
tu
r
es,
s
u
ch
as
p
r
o
m
in
e
n
t
c
h
ee
k
b
o
n
es
o
r
jawlin
es,
wh
ich
m
ad
e
it
ea
s
ier
f
o
r
th
e
s
y
s
tem
to
r
ec
o
g
n
ize
t
h
eir
f
ac
es d
esp
ite
th
e
o
b
s
tacle
s
.
Fo
r
th
e
h
ea
d
with
o
b
s
tacle
co
n
d
itio
n
s
,
d
etec
tio
n
ac
cu
r
ac
y
f
lu
ctu
ates
s
im
ilar
ly
to
f
ac
e
d
et
ec
tio
n
b
u
t
ten
d
s
s
lig
h
tly
lo
wer
o
v
e
r
all.
H
o
wev
er
,
h
ea
d
d
etec
tio
n
o
u
tp
e
r
f
o
r
m
s
f
ac
e
d
etec
tio
n
in
s
am
p
l
es
lik
e
S7
an
d
S2
6
,
b
ec
au
s
e
o
b
s
tacle
s
s
ig
n
if
ican
tl
y
im
p
ac
t
f
ac
e
v
is
ib
ilit
y
m
o
r
e
th
an
h
ea
d
o
r
ien
tatio
n
.
T
h
is
im
p
lies
th
at
h
ea
d
d
etec
tio
n
is
m
o
r
e
r
esil
ien
t
to
o
b
s
tr
u
ctio
n
s
th
an
f
ac
e
d
etec
tio
n
,
m
ain
tain
in
g
b
etter
ac
cu
r
ac
y
in
ch
allen
g
in
g
co
n
d
itio
n
s
.
I
n
an
o
t
h
er
o
b
s
er
v
atio
n
,
u
p
to
9
8
%
o
f
th
e
h
ig
h
est
ac
cu
r
a
cies
ar
e
o
b
s
er
v
e
d
in
th
e
f
ac
e
&
h
e
ad
with
o
u
t
o
b
s
tacle
s
,
p
ar
ticu
lar
ly
f
o
r
s
u
b
jects
lik
e
S1
,
S3
,
S4
,
an
d
S8
.
T
h
is
s
u
g
g
ests
th
at
th
e
ab
s
en
ce
o
f
o
b
s
tacle
s
s
ig
n
if
ican
tly
im
p
r
o
v
es
h
ea
d
p
o
s
e
esti
m
atio
n
ac
cu
r
ac
y
.
H
o
wev
er
,
s
o
m
e
s
u
b
jects,
s
u
ch
a
s
S7
,
S1
3
,
an
d
S2
5
,
d
is
p
lay
m
o
r
e
b
alan
ce
d
ac
cu
r
ac
y
ac
r
o
s
s
all
co
n
d
itio
n
s
,
in
d
icatin
g
less
im
p
ac
t
f
r
o
m
o
b
s
tacle
s
.
C
o
n
v
er
s
ely
,
s
u
b
jects lik
e
S3
,
S6
,
an
d
S1
1
ex
p
er
ien
ce
lo
wer
ac
cu
r
ac
y
in
th
e
h
ea
d
with
o
b
s
tacle
co
n
d
itio
n
s
,
wh
er
e
ac
cu
r
ac
y
d
ip
s
to
ar
o
u
n
d
8
0
%,
alth
o
u
g
h
th
ey
s
till
p
er
f
o
r
m
well
in
o
th
er
co
n
d
itio
n
s
.
Fig
u
r
e
6
.
Av
e
r
ag
e
o
f
p
er
f
o
r
m
a
n
ce
ac
cu
r
ac
y
f
o
r
a
s
p
o
n
ta
n
eo
u
s
h
ea
d
m
o
v
e
m
en
t c
ateg
o
r
y
Fig
u
r
e
7
.
Per
f
o
r
m
an
c
e
ac
cu
r
ac
y
f
o
r
t
h
ir
ty
s
u
b
jects in
th
e
s
p
o
n
tan
eo
u
s
h
ea
d
m
o
v
em
en
t c
ate
g
o
r
y
3
.
3
.
Vis
ua
l
a
t
t
ent
io
n
T
h
e
ef
f
ec
tiv
en
ess
o
f
t
h
e
alg
o
r
ith
m
in
d
etec
tin
g
v
is
u
al
atten
tio
n
is
ev
alu
ated
u
s
in
g
t
h
e
d
at
aset
f
r
o
m
th
e
s
p
o
n
tan
e
o
u
s
h
ea
d
m
o
v
e
m
en
t
s
ettin
g
u
n
d
er
t
h
r
ee
d
i
f
f
er
en
t
co
n
d
itio
n
s
.
I
ts
ac
cu
r
a
cy
is
m
ea
s
u
r
ed
b
y
an
aly
zin
g
p
r
ed
ictio
n
o
u
tp
u
ts
wh
en
p
ar
ticip
an
ts
d
ir
ec
tly
f
a
ce
th
e
ca
m
er
a,
in
d
icatin
g
v
is
u
al
atten
tio
n
.
T
h
e
alg
o
r
ith
m
'
s
r
esu
lts
ar
e
cr
o
s
s
-
v
alid
ated
ag
ain
s
t v
id
eo
r
ec
o
r
d
i
n
g
s
to
en
s
u
r
e
ac
c
u
r
ac
y
.
90
87
87
0
20
40
60
80
100
F
ac
e
&
he
ad
w
i
t
ho
ut
o
bs
t
ac
l
e
s
F
ac
e
wi
t
h
o
bs
t
ac
l
e
s
H
e
ad
w
i
t
h
o
bs
t
ac
l
e
s
P
e
r
f
o
r
m
an
c
e
Ac
c
ur
ac
y
(
%)
C
o
nd
i
t
i
o
n
0
20
40
60
80
1
0
0
S1
S2
S3
S4
S5
S6
S7
S8
S9
S
1
0
S
1
1
S
1
2
S
1
3
S
1
4
S
1
5
S
1
6
S
1
7
S
1
8
S
1
9
S
2
0
S
2
1
S
2
2
S
2
3
S
2
4
S
2
5
S
2
6
S
2
7
S
2
8
S
2
9
S
3
0
P
e
r
f
o
r
m
an
c
e
Ac
c
ur
ac
y
(
%)
F
A
CE
&
H
E
A
D
W
I
T
H
O
U
T
O
B
S
T
A
CL
E
S
F
A
CE
W
I
T
H
O
B
S
T
A
CL
E
S
HE
A
D
W
I
T
H
O
B
S
T
A
CL
E
S
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
5
8
1
-
4
5
9
2
4588
Fig
u
r
e
8
co
m
p
ar
es
th
e
atten
tio
n
lev
els
in
p
er
ce
n
tag
e
f
o
r
t
h
ir
ty
s
u
b
jects
u
n
d
er
th
r
ee
co
n
d
itio
n
s
.
I
t
s
h
o
ws
s
ig
n
if
ican
t
v
ar
iatio
n
s
ac
r
o
s
s
s
u
b
jects
an
d
co
n
d
itio
n
s
.
Sev
er
al
s
u
b
jects,
s
u
ch
as
S7
,
S8
,
S9
,
an
d
S2
4
,
ac
h
iev
e
p
er
f
ec
t
o
r
n
ea
r
-
p
er
f
e
ct
atten
tio
n
lev
els
1
0
0
%
ac
r
o
s
s
all
co
n
d
itio
n
s
,
in
d
icatin
g
a
r
o
b
u
s
t
atten
tio
n
esti
m
atio
n
s
y
s
tem
f
o
r
th
ese
i
n
d
iv
id
u
als.
Ho
wev
e
r
,
atten
tio
n
lev
els
d
r
o
p
n
o
ticea
b
ly
f
o
r
o
th
er
s
,
s
u
ch
as
S1
4
,
S2
9
,
an
d
S3
0
,
esp
ec
ially
in
th
e
f
ac
e
with
o
b
s
tacle
s
,
wh
e
r
e
v
alu
es
d
ip
as
lo
w
as
7
0
%.
T
h
e
p
r
esen
ce
o
f
o
b
s
tacle
s
,
p
ar
ticu
lar
ly
af
f
ec
tin
g
th
e
h
ea
d
,
r
ed
u
ce
s
th
e
s
y
s
tem
'
s
ab
il
ity
to
esti
m
ate
atten
tio
n
ac
cu
r
ately
,
s
u
ch
as
f
o
r
S1
5
,
S2
4
,
an
d
S2
9
,
w
h
er
e
th
e
v
alu
e
r
ed
u
ce
s
b
y
ar
o
u
n
d
2
6
%.
I
n
co
m
p
a
r
is
o
n
,
atten
tio
n
esti
m
atio
n
r
em
ain
s
h
ig
h
in
m
o
s
t
s
u
b
jects
with
f
ac
e
an
d
h
ea
d
with
o
u
t
o
b
s
ta
cles.
T
h
e
o
b
s
tacle
s
cr
ea
te
a
m
o
r
e
c
h
allen
g
in
g
en
v
ir
o
n
m
en
t,
r
esu
ltin
g
in
lo
wer
p
er
f
o
r
m
an
ce
.
T
h
is
s
u
g
g
ests
th
e
s
y
s
tem
co
u
ld
b
e
s
en
s
itiv
e
to
v
is
u
al
o
b
s
tr
u
ctio
n
s
,
with
ac
cu
r
ac
y
d
r
o
p
p
in
g
i
n
m
o
r
e
o
cc
lu
d
ed
c
o
n
d
itio
n
s
,
esp
ec
ially
wh
e
n
th
e
h
ea
d
is
p
a
r
tially
b
lo
ck
ed
.
I
m
p
r
o
v
in
g
p
e
r
f
o
r
m
a
n
ce
u
n
d
er
th
ese
ch
alle
n
g
in
g
co
n
d
itio
n
s
c
o
u
ld
e
n
h
an
ce
t
h
e
s
y
s
tem
'
s
o
v
er
all
r
eliab
ilit
y
.
Fig
u
r
e
9
d
ep
icts
v
is
u
al
atten
ti
o
n
ac
cu
r
ac
y
f
o
r
th
r
ee
co
n
d
itio
n
s
:
f
ac
e
a
n
d
h
ea
d
with
o
u
t
o
b
s
tacle
s
is
9
0
%,
f
ac
e
with
o
b
s
tacle
s
is
8
8
%,
an
d
h
ea
d
with
o
b
s
tacle
s
is
8
6
%.
B
ased
o
n
s
p
o
n
tan
e
o
u
s
h
ea
d
m
o
v
e
m
en
t,
th
ese
r
esu
lts
in
d
icate
th
at
o
b
s
t
ac
les
s
lig
h
tly
af
f
ec
t
atten
tio
n
ac
cu
r
ac
y
,
b
u
t
th
e
v
ar
iatio
n
s
ar
e
m
in
im
al.
Ov
er
all,
8
8
%
o
f
th
e
ac
cu
r
ac
y
o
f
v
is
u
al
atten
tio
n
f
o
r
s
p
o
n
ta
n
eo
u
s
h
ea
d
m
o
v
em
e
n
t
ca
teg
o
r
ies
in
d
ica
ted
th
at
th
e
s
y
s
tem
is
h
ig
h
ly
r
eliab
le.
T
h
e
h
ig
h
ac
cu
r
ac
y
p
er
ce
n
tag
es
ac
r
o
s
s
al
l
co
n
d
itio
n
s
s
u
g
g
est
th
at
th
e
s
y
s
tem
ef
f
ec
tiv
ely
d
etec
ts
v
is
u
al
atten
tio
n
,
ev
en
wh
en
s
u
b
jects f
ac
e
o
b
s
tr
u
ctio
n
s
,
d
em
o
n
s
tr
atin
g
its
r
o
b
u
s
tn
e
s
s
an
d
r
eliab
ilit
y
.
Fig
u
r
e
8
.
Vis
u
al
atten
tio
n
ac
c
u
r
ac
y
wh
ile
th
e
s
u
b
ject'
s
f
ac
e
an
d
h
ea
d
with
o
u
t
o
b
s
tacle
s
,
f
ac
e
with
o
b
s
tacle
s
an
d
h
ea
d
with
o
b
s
tacle
s
Fig
u
r
e
9
.
Vis
u
al
atten
tio
n
ac
c
u
r
ac
y
f
o
r
th
r
ee
v
ar
y
in
g
c
o
n
d
iti
o
n
s
3
.
4
.
Co
rr
el
a
t
io
n
a
na
ly
s
is
Fig
u
r
e
1
0
s
h
o
ws
th
e
p
er
f
o
r
m
an
ce
an
d
atten
tio
n
ac
cu
r
ac
y
p
er
ce
n
tag
es
u
n
d
er
th
r
ee
co
n
d
it
io
n
s
:
f
ac
e
an
d
h
ea
d
with
o
u
t
o
b
s
tacle
s
,
f
ac
e
with
o
b
s
tacle
s
,
an
d
h
ea
d
with
o
b
s
tacle
s
.
B
o
th
v
alu
es
r
em
ain
co
n
s
is
ten
tly
h
ig
h
ac
r
o
s
s
all
co
n
d
itio
n
s
,
wit
h
p
er
f
o
r
m
a
n
ce
ac
c
u
r
ac
y
at
9
0
%
in
th
e
f
ir
s
t
co
n
d
itio
n
a
n
d
s
lig
h
tly
lo
wer
(
8
7
%)
f
o
r
th
e
o
th
e
r
two
.
Atten
tio
n
cl
o
s
ely
f
o
llo
ws
p
er
f
o
r
m
an
ce
ac
cu
r
ac
y
,
m
atch
i
n
g
it
at
9
0
%
in
th
e
f
ir
s
t
co
n
d
itio
n
,
s
lig
h
tly
s
u
r
p
ass
in
g
it
in
th
e
s
ec
o
n
d
(
8
8
%
v
s
.
8
7
%),
an
d
lo
wer
in
th
e
th
ir
d
(
8
6
%
v
s
.
8
7
%).
T
h
e
co
r
r
elatio
n
b
etwe
en
p
er
f
o
r
m
an
ce
a
n
d
att
en
tio
n
ac
cu
r
ac
y
,
ca
lcu
lated
a
t
0
.
8
6
6
,
i
n
d
icate
s
a
s
tr
o
n
g
p
o
s
itiv
e
r
elatio
n
s
h
ip
,
m
ea
n
in
g
c
h
an
g
es
in
o
n
e
v
ar
ia
b
le
ar
e
m
ir
r
o
r
ed
b
y
c
h
an
g
es
i
n
th
e
o
th
e
r
.
T
h
is
co
n
s
is
ten
cy
s
u
g
g
ests
th
e
s
y
s
tem
is
r
esil
ien
t
to
o
b
s
tacle
s
,
m
ain
tain
in
g
h
ig
h
p
er
f
o
r
m
an
ce
a
n
d
atten
tio
n
lev
els
ev
en
wh
en
t
h
e
f
ac
e
o
r
h
ea
d
is
0
20
40
60
80
1
0
0
S1
S2
S3
S4
S5
S6
S7
S8
S9
S
1
0
S
1
1
S
1
2
S
1
3
S
1
4
S
1
5
S
1
6
S
1
7
S
1
8
S
1
9
S
2
0
S
2
1
S
2
2
S
2
3
S
2
4
S
2
5
S
2
6
S
2
7
S
2
8
S
2
9
S
3
0
A
t
t
e
nt
i
o
n
(
%)
F
A
C
E
& H
E
A
D
W
IT
H
O
UT
O
B
S
T
A
C
LES
F
A
C
E
W
I
T
H
O
B
S
T
A
C
LES
H
E
A
D
W
IT
H
O
B
S
T
A
C
LE
S
90
88
86
0
20
40
60
80
100
F
ace
&
head w
i
t
hout
o
bst
ac
l
es
F
ace
w
i
t
h o
bst
acl
e
s
H
e
ad
w
i
t
h
o
bs
t
ac
l
e
s
At
t
e
n
t
i
o
n
(
%)
C
o
nd
i
t
i
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Dyn
a
mic
h
ea
d
p
o
s
e
esti
ma
tio
n
in
va
r
ied
co
n
d
itio
n
s
u
s
in
g
D
lib
a
n
d
Med
ia
P
ip
e
(
R
u
s
n
a
n
i Y
a
h
ya
)
4589
p
ar
tially
o
b
s
cu
r
e
d
.
W
h
ile
h
ea
d
o
b
s
tacle
s
h
av
e
a
s
lig
h
tly
m
o
r
e
s
u
b
s
tan
tial
ef
f
ec
t
o
n
p
e
r
f
o
r
m
an
ce
an
d
atten
tio
n
ac
cu
r
ac
y
th
a
n
f
ac
ial
o
b
s
tacle
s
,
th
e
s
y
s
tem
r
em
ain
s
r
o
b
u
s
t o
v
er
all.
T
h
e
p
r
o
p
o
s
ed
al
g
o
r
ith
m
d
em
o
n
s
tr
ates
im
p
r
o
v
ed
r
ea
l
-
tim
e
h
ea
d
p
o
s
e
esti
m
atio
n
ac
c
u
r
ac
y
u
s
in
g
o
n
l
y
R
GB
in
p
u
t
co
m
p
ar
ed
to
p
r
io
r
r
esear
ch
.
Fo
r
in
s
tan
ce
,
Owe
n
et
a
l.
[
3
2
]
ac
h
iev
e
d
8
6
.
8
5
%
ac
cu
r
ac
y
in
HPE
i
n
th
e
s
leep
in
ess
d
etec
tio
n
s
y
s
te
m
,
wh
ile
o
u
r
m
eth
o
d
ac
h
iev
ed
o
v
er
9
3
% a
cc
u
r
ac
y
.
Ham
m
ad
i
et
a
l.
[
2
4
]
r
ep
o
r
te
d
h
ig
h
p
e
r
f
o
r
m
an
ce
u
s
in
g
m
u
lti
m
o
d
al
d
ata
b
u
t
r
eq
u
ir
ed
p
o
s
e
tr
ac
k
in
g
eq
u
ip
m
en
t.
I
n
c
o
n
tr
a
s
t,
o
u
r
m
eth
o
d
u
s
es
o
n
ly
a
s
im
p
le
web
ca
m
s
etu
p
,
m
ak
in
g
it
m
o
r
e
ac
ce
s
s
ib
le.
Alth
o
u
g
h
p
r
ev
i
o
u
s
s
tu
d
ies
d
em
o
n
s
tr
ated
g
o
o
d
ac
cu
r
ac
y
u
s
in
g
Op
e
n
C
V
-
b
ased
m
eth
o
d
s
,
th
e
s
y
s
tem
s
ten
d
ed
to
b
ec
o
m
e
u
n
s
tab
le
d
u
r
in
g
f
ast
o
r
u
n
ex
p
ec
ted
h
ea
d
m
o
v
em
en
ts
[
5
]
.
I
n
t
h
is
r
esear
ch
,
in
teg
r
atin
g
Me
d
i
P
ip
e
with
its
s
tab
le
f
ac
ial
lan
d
m
ar
k
tr
ac
k
in
g
ca
p
ab
ilit
y
h
elp
ed
m
ain
tain
ac
cu
r
ac
y
,
esp
ec
ially
in
s
p
o
n
tan
e
o
u
s
h
ea
d
m
o
v
em
en
t
ca
te
g
o
r
y
.
T
h
ese
r
e
s
u
lts
alig
n
with
o
u
r
in
itial
ex
p
ec
tatio
n
th
at
co
m
b
in
in
g
Dlib
an
d
Me
d
iaPip
e
wo
u
ld
im
p
r
o
v
e
r
ea
l
-
tim
e
h
e
ad
p
o
s
e
esti
m
atio
n
ac
cu
r
ac
y
,
e
v
en
u
n
d
er
n
atu
r
al
h
ea
d
m
o
v
e
m
en
ts
an
d
m
i
n
im
al
h
ar
d
war
e
co
n
d
itio
n
s
.
Mo
r
eo
v
e
r
,
o
u
r
s
tr
o
n
g
co
r
r
elatio
n
co
ef
f
icien
t
(
0
.
8
6
6
)
b
etwe
en
h
ea
d
p
o
s
e
an
d
atten
tio
n
esti
m
atio
n
s
u
p
p
o
r
ts
s
im
ilar
f
in
d
in
g
s
b
y
L
iu
et
a
l.
[
3
6
]
an
d
Af
r
o
ze
et
a
l.
[
7
]
,
wh
o
n
o
te
d
th
e
i
m
p
o
r
tan
ce
o
f
f
ac
ial
o
r
ien
tatio
n
in
h
u
m
a
n
-
co
m
p
u
t
er
in
ter
ac
tio
n
.
T
h
ese
f
in
d
i
n
g
s
ar
e
v
alu
ab
le
f
o
r
d
ev
elo
p
in
g
ac
ce
s
s
ib
le
an
d
co
s
t
-
ef
f
ec
tiv
e
atten
tio
n
t
r
ac
k
in
g
s
y
s
tem
s
,
wh
ich
ca
n
b
en
e
f
it
ed
u
ca
to
r
s
,
th
er
ap
is
ts
,
an
d
r
esear
ch
er
s
wo
r
k
in
g
with
ch
ild
r
en
,
esp
ec
ially
th
o
s
e
with
s
p
ec
ial
n
ee
d
s
.
C
o
m
b
in
in
g
h
ig
h
ac
cu
r
ac
y
,
lo
w
h
ar
d
war
e
r
eq
u
i
r
em
en
ts
,
an
d
r
o
b
u
s
tn
ess
in
o
b
s
tacle
-
r
ich
co
n
d
itio
n
s
ca
n
h
elp
d
ev
elo
p
r
ea
l
-
tim
e
att
en
tio
n
tr
ac
k
i
n
g
s
y
s
tem
s
f
o
r
cl
ass
r
o
o
m
s
,
th
er
ap
y
s
ess
io
n
s
,
o
r
in
ter
ac
tiv
e
lear
n
in
g
en
v
ir
o
n
m
en
ts
.
Fu
tu
r
e
r
esear
c
h
s
h
o
u
ld
ex
p
lo
r
e
i
n
teg
r
atin
g
d
ee
p
lea
r
n
in
g
f
o
r
o
cc
l
u
s
io
n
r
o
b
u
s
tn
ess
,
m
u
lti
-
ca
m
er
a
s
etu
p
s
f
o
r
en
h
a
n
ce
d
tr
ac
k
in
g
,
a
n
d
e
y
e
-
tr
ac
k
i
n
g
tech
n
o
lo
g
y
to
r
ef
i
n
e
atten
tio
n
an
aly
s
is
f
u
r
th
er
.
C
o
m
b
in
in
g
h
ea
d
p
o
s
e
with
f
a
cial
ex
p
r
ess
io
n
an
aly
s
is
ca
n
a
ls
o
b
e
ex
ten
d
e
d
to
d
etec
t
em
o
tio
n
al
r
esp
o
n
s
e
o
r
en
g
ag
em
e
n
t
lev
els.
Ho
wev
er
,
th
e
s
y
s
tem
s
h
o
wed
s
o
m
e
s
en
s
itiv
ity
to
r
ap
id
lig
h
tin
g
ch
a
n
g
es
an
d
c
o
m
p
le
x
o
cc
lu
s
io
n
s
,
in
d
icatin
g
t
h
e
n
ee
d
f
o
r
f
u
r
th
e
r
r
ef
i
n
em
en
t in
m
o
r
e
d
iv
er
s
e
en
v
ir
o
n
m
en
ts
.
Fig
u
r
e
1
0
.
C
o
m
p
ar
is
o
n
o
f
p
e
r
f
o
r
m
an
ce
a
n
d
atten
tio
n
ac
cu
r
ac
y
ac
r
o
s
s
d
if
f
er
e
n
t c
o
n
d
itio
n
s
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
s
u
cc
ess
f
u
lly
ac
h
iev
ed
r
ea
l
-
tim
e
h
ea
d
p
o
s
e
esti
m
atio
n
u
s
in
g
Dlib
an
d
Me
d
iaPip
e,
d
em
o
n
s
tr
atin
g
r
eliab
le
f
ac
ial
l
an
d
m
ar
k
d
etec
tio
n
ac
r
o
s
s
a
b
r
o
ad
r
an
g
e
o
f
h
ea
d
o
r
ien
tatio
n
s
.
C
o
m
p
ar
ed
to
th
e
s
tan
d
ar
d
Op
en
C
V
alg
o
r
ith
m
,
th
e
p
r
o
p
o
s
ed
m
eth
o
d
s
h
o
wed
s
u
p
er
io
r
p
er
f
o
r
m
a
n
ce
in
ter
m
s
o
f
r
o
b
u
s
tn
ess
an
d
ad
ap
tab
ilit
y
.
T
w
o
e
x
p
er
im
e
n
t
s
etu
p
s
wer
e
u
s
ed
to
ev
al
u
ate
th
e
alg
o
r
ith
m
:
o
n
e
wit
h
co
n
tr
o
lled
h
ea
d
m
o
v
em
en
t
an
d
an
o
th
er
with
s
p
o
n
tan
e
o
u
s
h
ea
d
m
o
v
em
e
n
ts
,
b
o
th
test
ed
u
n
d
er
th
r
ee
co
n
d
itio
n
s
(
f
ac
e
an
d
h
ea
d
with
o
u
t
o
b
s
tacle
s
,
f
ac
e
with
o
b
s
tacle
s
an
d
h
ea
d
with
o
b
s
tacle
s
)
.
T
h
e
alg
o
r
ith
m
ac
h
iev
e
d
o
v
er
9
3
%
ac
cu
r
ac
y
in
h
ea
d
p
o
s
e
esti
m
atio
n
an
d
at
least
8
8
%
in
d
etec
tin
g
v
is
u
al
atten
tio
n
,
e
v
en
with
f
ac
ia
l
o
b
s
tacle
s
.
T
h
ese
f
in
d
in
g
s
s
u
g
g
est
th
at
th
e
p
r
o
p
o
s
ed
HPE
alg
o
r
ith
m
is
p
r
ac
tical
an
d
ad
a
p
tab
le,
with
m
i
n
im
al
p
er
f
o
r
m
a
n
ce
d
eg
r
ad
atio
n
u
n
d
e
r
r
ea
l
-
wo
r
ld
co
n
d
itio
n
s
,
s
u
ch
as
o
cc
lu
s
io
n
s
an
d
n
atu
r
al
m
o
v
em
en
ts
.
T
h
is
h
as
s
ig
n
if
ican
t
im
p
licatio
n
s
f
o
r
th
e
r
esear
c
h
f
ield
,
p
a
r
ticu
lar
ly
in
a
p
p
li
ca
tio
n
s
r
elate
d
t
o
h
u
m
an
-
co
m
p
u
ter
in
ter
ac
tio
n
,
ass
is
tiv
e
tech
n
o
lo
g
ies,
a
n
d
e
d
u
ca
tio
n
al
o
r
th
er
a
p
eu
tic
s
ettin
g
s
in
v
o
lv
in
g
v
is
u
al
atten
tio
n
m
o
n
ito
r
in
g
.
Fo
r
th
e
co
m
m
u
n
ity
,
p
ar
ticu
lar
ly
i
n
r
o
b
o
t
-
ass
is
ted
th
er
ap
y
o
r
class
r
o
o
m
en
g
ag
em
e
n
t
m
o
n
ito
r
in
g
co
n
te
x
ts
,
th
is
r
esear
ch
o
p
e
n
s
th
e
d
o
o
r
to
m
o
r
e
ac
ce
s
s
ib
le,
n
o
n
in
v
asiv
e
to
o
ls
f
o
r
u
n
d
er
s
tan
d
in
g
atten
tio
n
an
d
in
ter
ac
tio
n
p
atter
n
s
.
Mo
v
in
g
f
o
r
war
d
,
m
u
lti
-
v
iew
esti
m
atio
n
an
d
a
d
v
an
ce
d
f
ea
tu
r
e
e
x
tr
ac
tio
n
e
n
h
an
ce
m
e
n
ts
co
u
ld
im
p
r
o
v
e
p
er
f
o
r
m
an
ce
,
m
ak
in
g
th
e
tech
n
o
l
o
g
y
e
v
en
m
o
r
e
r
esil
ien
t
an
d
ap
p
licab
le
in
d
iv
er
s
e
s
itu
atio
n
s
an
d
u
n
co
n
tr
o
lled
en
v
ir
o
n
m
en
ts
.
U
ltima
tely
,
th
is
s
tu
d
y
co
n
t
r
ib
u
t
es
to
a
g
r
o
win
g
b
o
d
y
o
f
wo
r
k
to
b
r
id
g
e
t
h
e
g
a
p
b
etwe
en
co
m
p
u
ter
v
is
io
n
an
d
r
ea
l
-
wo
r
ld
h
u
m
a
n
b
eh
av
i
o
r
an
aly
s
is
,
o
f
f
er
in
g
p
r
ac
tical
s
o
lu
tio
n
s
with
th
e
p
o
ten
tial f
o
r
wid
e
-
r
ea
ch
i
n
g
s
o
cial
im
p
ac
t.
90
87
87
90
88
86
0
20
40
60
80
100
F
ac
e
&
he
ad
w
i
t
ho
ut
o
bs
t
ac
l
e
s
F
ac
e
wi
t
h
o
bs
t
ac
l
e
s
H
e
ad
w
i
t
h
o
bs
t
ac
l
e
s
A
v
e
r
ag
e
(
%)
C
o
nd
i
t
i
o
n
%
P
e
rfo
rman
c
e
%
A
tt
e
n
ti
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
5
8
1
-
4
5
9
2
4590
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
e
au
th
o
r
s
wo
u
l
d
lik
e
t
o
ex
p
r
ess
th
eir
s
in
ce
r
e
g
r
atitu
d
e
to
Un
iv
er
s
iti
T
ek
n
o
lo
g
i
MA
R
A
(
UiT
M)
f
o
r
p
r
o
v
id
i
n
g
r
esear
ch
s
u
p
p
o
r
t
an
d
g
r
a
n
t
f
ac
ilit
ies;
Kizz
u
Kid
s
R
eh
ab
ilit
atio
n
C
en
tr
e
f
o
r
g
en
er
o
u
s
ly
s
p
o
n
s
o
r
in
g
th
e
T
em
i
V
3
r
o
b
o
t,
wh
ich
p
la
y
ed
a
p
iv
o
tal
r
o
le
in
test
in
g
an
d
s
o
f
twar
e
d
ev
elo
p
m
en
t;
a
n
d
E
UR
E
KA
R
o
b
o
tics
C
en
tr
e,
C
ar
d
if
f
Me
tr
o
p
o
litan
Un
iv
er
s
ity
,
UK,
f
o
r
th
eir
v
alu
ab
le
r
esear
ch
c
o
llab
o
r
atio
n
.
T
h
is
s
tu
d
y
was
u
n
d
er
tak
e
n
d
u
r
in
g
th
e
s
tu
d
y
leav
e
o
f
th
e
f
ir
s
t
au
th
o
r
u
n
d
er
th
e
2
0
2
2
Fed
er
al
T
r
ain
i
n
g
(
HL
P)
s
ch
o
lar
s
h
ip
s
ch
em
e
awa
r
d
ed
b
y
th
e
MO
H
E
Ma
lay
s
ia.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
i
s
w
o
r
k
w
a
s
f
u
n
d
e
d
b
y
t
h
e
S
t
r
a
t
e
g
i
c
R
e
s
ea
r
c
h
P
a
r
t
n
e
r
s
h
ip
(
S
R
P
)
g
r
a
n
t
(
1
0
0
-
R
M
C
5
/
3
/S
R
P
I
N
T
(
0
4
7
/
2
0
2
3
)
a
n
d
1
0
0
-
R
M
C
5
/
3
/S
R
P
I
N
T
(
0
4
8
/
2
0
2
3
)
)
f
r
o
m
t
h
e
U
n
i
v
e
r
s
it
i
T
e
k
n
o
l
o
g
i
MA
R
A
(
U
i
T
M
)
,
M
al
a
y
s
i
a
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
o
en
s
u
r
e
tr
an
s
p
ar
en
c
y
an
d
cl
ar
ity
in
r
esear
ch
co
n
tr
ib
u
tio
n
s
,
th
e
r
o
les o
f
ea
ch
au
th
o
r
in
v
o
lv
ed
in
th
is
s
tu
d
y
ar
e
s
p
ec
if
ied
b
ased
o
n
th
e
C
o
n
tr
ib
u
to
r
R
o
les T
ax
o
n
o
m
y
(
C
R
ed
iT)
.
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
I
NF
O
RM
E
D
CO
NS
E
N
T
W
e
h
av
e
o
b
tain
ed
in
f
o
r
m
ed
c
o
n
s
en
t f
r
o
m
all
in
d
iv
id
u
als in
c
lu
d
ed
in
t
h
is
s
tu
d
y
.
E
T
H
I
CAL AP
P
RO
V
AL
R
esear
ch
r
elate
d
to
h
u
m
an
u
s
e
h
as
b
ee
n
co
n
d
u
cte
d
in
ac
co
r
d
an
ce
with
all
r
elev
an
t
n
atio
n
al
r
eg
u
latio
n
s
an
d
in
s
titu
tio
n
al
p
o
licies,
as
o
u
tlin
ed
in
th
e
p
r
in
cip
les
o
f
th
e
Dec
lar
atio
n
o
f
Helsin
k
i.
I
t
h
as
b
ee
n
ap
p
r
o
v
ed
b
y
th
e
R
esear
ch
E
th
ics
C
o
m
m
ittee
(
R
E
C
)
,
Un
i
v
er
s
iti
T
ek
n
o
lo
g
i
MA
R
A
(
UiT
M)
Sh
ah
Alam
,
Ma
lay
s
ia,
with
Ap
p
r
o
v
al
n
u
m
b
er
R
E
C
/0
6
/2
0
2
4
(
PG/F
B
/2
1
)
.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
s
u
p
p
o
r
tin
g
t
h
is
s
tu
d
y
'
s
f
in
d
in
g
s
ar
e
av
ailab
le
o
n
r
eq
u
est
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
au
th
o
r
.
Ho
wev
er
,
d
u
e
to
ce
r
tain
r
estrictio
n
s
,
th
e
d
ata,
wh
ich
co
n
tai
n
s
in
f
o
r
m
atio
n
th
at
co
u
ld
co
m
p
r
o
m
is
e
th
e
p
r
iv
ac
y
o
f
r
esear
ch
p
ar
ticip
an
ts
,
is
n
o
t
p
u
b
licly
av
ailab
le.
RE
F
E
R
E
NC
E
S
[
1
]
Y
.
A
l
b
a
d
a
w
i
,
A
.
A
l
R
e
d
h
a
e
i
,
a
n
d
M
.
T
a
k
r
u
r
i
,
“
R
e
a
l
-
t
i
me
mac
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
se
d
d
r
i
v
e
r
d
r
o
w
si
n
e
ss
d
e
t
e
c
t
i
o
n
u
si
n
g
v
i
su
a
l
f
e
a
t
u
r
e
s,
”
J
o
u
r
n
a
l
o
f
I
m
a
g
i
n
g
,
v
o
l
.
9
,
n
o
.
5
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
j
i
m
a
g
i
n
g
9
0
5
0
0
9
1
.
[
2
]
R
.
K
.
S
h
u
k
l
a
,
A
.
K
.
T
i
w
a
r
i
,
a
n
d
A
.
K
.
J
h
a
,
“
A
n
e
f
f
i
c
i
e
n
t
a
p
p
r
o
a
c
h
o
f
f
a
c
e
d
e
t
e
c
t
i
o
n
a
n
d
p
r
e
d
i
c
t
i
o
n
o
f
d
r
o
w
si
n
e
ss
u
s
i
n
g
S
V
M
,
”
Ma
t
h
e
m
a
t
i
c
a
l
Pr
o
b
l
e
m
s i
n
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
0
2
3
,
n
o
.
1
,
p
p
.
1
–
1
2
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
3
/
2
1
6
8
3
6
1
.
[
3
]
W
.
R
a
h
m
a
n
i
a
r
,
Q
.
M
.
U
.
H
a
q
,
a
n
d
T.
-
L.
L
i
n
,
“
W
i
d
e
r
a
n
g
e
h
e
a
d
p
o
se
e
st
i
m
a
t
i
o
n
u
si
n
g
a
si
n
g
l
e
R
G
B
c
a
m
e
r
a
f
o
r
i
n
t
e
l
l
i
g
e
n
t
su
r
v
e
i
l
l
a
n
c
e
,
”
I
EE
E
S
e
n
so
rs
J
o
u
rn
a
l
,
v
o
l
.
2
2
,
n
o
.
1
1
,
p
p
.
1
1
1
1
2
–
1
1
1
2
1
,
J
u
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
JS
EN
.
2
0
2
2
.
3
1
6
8
8
6
3
.
[
4
]
A
n
i
t
t
a
D
a
n
d
A
.
F
a
t
h
i
ma
A
,
“
H
u
m
a
n
h
e
a
d
p
o
se
e
s
t
i
m
a
t
i
o
n
b
a
se
d
o
n
H
F
met
h
o
d
,
”
Mi
c
ro
p
r
o
c
e
sso
rs
a
n
d
M
i
c
r
o
sys
t
e
m
s
,
v
o
l
.
8
2
,
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
R
u
s
n
an
i Y
ah
y
a
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
R
o
zita
J
ailan
i
✓
✓
✓
✓
✓
✓
✓
✓
Nu
r
Kh
alid
ah
Z
a
k
ar
ia
✓
✓
✓
✓
✓
✓
✓
✓
Faza
h
Ak
h
tar
Han
ap
ia
h
✓
✓
Evaluation Warning : The document was created with Spire.PDF for Python.