I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
10
,
No
.
6
,
Decem
b
er
2
0
2
0
,
p
p
.
6
2
9
2
~
6
2
9
9
I
SS
N:
2088
-
8708
,
DOI
:
1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
10
i
6
.
pp
6
2
9
2
-
6
2
9
9
6292
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m/in
d
ex
.
p
h
p
/I
JE
C
E
O
bje
ct
g
rip
ping
a
lg
o
rith
m
f
o
r robo
tic
a
ss
ista
nce
by
m
ea
ns o
f
dee
p
lea
ning
Ro
bin
s
o
n J
i
m
é
nez
-
M
o
re
no
,
Astr
id Ru
bia
no
F
o
ns
ec
a
,
J
o
s
é
L
uis
Ra
m
í
re
z
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
,
M
il
it
a
r
N
u
e
v
a
G
ra
n
a
d
a
Un
iv
e
rsit
y
,
Co
lo
m
b
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
l 1
7
,
2
0
1
9
R
ev
i
s
ed
Ma
y
28
,
2020
A
cc
ep
ted
J
u
n
7
,
2
0
2
0
T
h
is
p
a
p
e
r
e
x
p
o
se
s
th
e
u
se
o
f
re
c
e
n
t
d
e
e
p
lea
rn
i
n
g
tec
h
n
iq
u
e
s
in
t
h
e
sta
te
o
f
th
e
a
rt,
li
tt
le
a
d
d
re
ss
e
d
in
ro
b
o
t
ic
a
p
p
li
c
a
ti
o
n
s,
w
h
e
re
a
n
e
w
a
lg
o
ri
th
m
b
a
se
d
o
n
F
a
ste
r
R
-
CNN
a
n
d
CNN
re
g
re
ss
io
n
is
e
x
p
o
se
d
.
T
h
e
m
a
c
h
in
e
v
isio
n
s
y
ste
m
s
i
m
p
le
m
e
n
ted
,
ten
d
to
re
q
u
ire
m
u
lt
ip
le
sta
g
e
s
to
lo
c
a
te
a
n
o
b
jec
t
a
n
d
a
ll
o
w
a
ro
b
o
t
t
o
tak
e
it
,
in
c
re
a
sin
g
th
e
n
o
ise
in
th
e
sy
ste
m
a
n
d
th
e
p
ro
c
e
ss
in
g
ti
m
e
s.
T
h
e
c
o
n
v
o
lu
ti
o
n
a
l
n
e
tw
o
rk
s
b
a
se
d
o
n
re
g
io
n
s
a
ll
o
w
o
n
e
to
so
lv
e
th
is
p
r
o
b
l
e
m
,
i
t
i
s
u
s
e
d
f
o
r
i
t
t
w
o
c
o
n
v
o
l
u
t
i
o
n
a
l
a
r
c
h
i
t
e
c
t
u
r
e
s
,
o
n
e
f
o
r
c
l
a
s
s
i
f
i
c
a
t
i
o
n
a
n
d
lo
c
a
ti
o
n
o
f
th
re
e
t
y
p
e
s
o
f
o
b
jec
ts
a
n
d
o
n
e
to
d
e
term
in
e
th
e
g
ri
p
a
n
g
le
f
o
r
a
ro
b
o
ti
c
g
rip
p
e
r.
Un
d
e
r
t
h
e
e
sta
b
li
sh
v
irt
u
a
l
e
n
v
iro
n
m
e
n
t,
th
e
g
rip
a
lg
o
rit
h
m
w
o
rk
s
u
p
to
5
f
ra
m
e
s
p
e
r
s
e
c
o
n
d
w
it
h
a
1
0
0
%
o
b
jec
t
c
las
sif
ic
a
ti
o
n
,
a
n
d
w
it
h
th
e
im
p
le
m
e
n
tatio
n
o
f
th
e
F
a
ste
r
R
-
CNN
,
it
a
ll
o
w
s
o
b
tain
1
0
0
%
a
c
c
u
ra
c
y
in
th
e
c
las
sif
ica
ti
o
n
s
o
f
th
e
tes
t
d
a
t
a
b
a
se
,
a
n
d
o
v
e
r
a
9
7
%
o
f
a
v
e
ra
g
e
p
re
c
isio
n
l
o
c
a
t
i
n
g
t
h
e
g
e
n
e
r
a
t
e
d
b
o
x
e
s
i
n
e
a
c
h
e
l
e
m
e
n
t
,
g
r
i
p
p
i
n
g
s
u
c
c
e
s
s
f
u
l
l
y
t
h
e
o
b
j
e
c
t
s
.
K
ey
w
o
r
d
s
:
C
NN
r
eg
r
es
s
io
n
C
o
n
v
o
lu
tio
n
al
n
e
t
w
o
r
k
Ob
j
ec
t g
r
ip
p
in
g
R
o
b
o
tic
Vir
tu
al
e
n
v
ir
o
n
m
e
n
t
Co
p
y
rig
h
t
©
2
0
2
0
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
R
o
b
in
s
o
n
J
i
m
én
ez
-
Mo
r
en
o
,
Dep
ar
t
m
en
t
o
f
Me
ch
atr
o
n
ics
E
n
g
i
n
ee
r
i
n
g
,
Militar
Nu
e
v
a
Gr
an
ad
a
U
n
iv
e
r
s
it
y
,
C
r
a
.
1
1
No
.
101
-
80
,
B
o
g
o
tá
D
.
C
.
,
C
o
lo
m
b
ia
.
E
m
ail:
r
o
b
in
s
o
n
.
j
i
m
en
ez
@
u
n
i
m
ilit
ar
.
ed
u
.
co
1.
I
NT
RO
D
UCT
I
O
N
C
u
r
r
en
t
l
y
,
d
ee
p
lear
n
i
n
g
(
D
L
)
tech
n
iq
u
es
p
r
ese
n
t
g
r
ea
ter
r
o
b
u
s
tn
e
s
s
t
h
a
n
o
th
er
t
y
p
e
s
o
f
tech
n
iq
u
e
s
in
p
atter
n
r
ec
o
g
n
itio
n
in
b
o
t
h
te
m
p
o
r
ar
y
s
i
g
n
als
a
n
d
i
m
a
g
e
an
al
y
s
is
[
1
]
.
An
e
x
a
m
p
le
o
f
t
h
is
,
i
n
[
2
]
,
A
le
x
Net
p
r
esen
ts
a
co
n
v
o
lu
tio
n
al
n
e
u
r
al
n
et
w
o
r
k
(
C
NN)
,
w
h
ic
h
s
u
r
p
a
s
s
es
al
l
th
e
cl
a
s
s
ic
Ma
c
h
i
n
e
L
ea
r
n
in
g
tec
h
n
iq
u
es
i
m
p
le
m
en
ted
s
o
f
ar
in
th
e
I
m
ag
eNe
t
c
h
alle
n
g
e
[
3
]
,
o
b
tain
in
g
a
T
OP
5
er
r
o
r
o
f
1
6
.
4
%
in
t
h
e
clas
s
i
f
icatio
n
o
f
m
o
r
e
t
h
an
o
n
e
m
illi
o
n
i
m
ag
es
i
n
a
t
h
o
u
s
a
n
d
d
i
f
f
er
e
n
t
ca
teg
o
r
ies.
I
n
[
4
]
,
th
e
C
NNs
a
r
e
i
m
p
le
m
e
n
ted
b
y
r
eg
r
ess
io
n
to
esti
m
ate
t
h
e
t
r
aj
ec
to
r
y
d
is
ta
n
ce
o
f
a
r
o
b
o
tic
ar
m
t
h
at
allo
w
s
g
r
ab
b
i
n
g
a
n
ele
m
e
n
t
o
f
th
e
en
v
ir
o
n
m
e
n
t.
Ho
w
e
v
er
,
C
NN
ca
n
b
e
u
s
ed
f
o
r
s
ev
er
a
l
k
in
d
s
o
f
s
i
g
n
a
l
lik
e
s
p
ee
ch
r
ec
o
g
n
itio
n
[
5
]
o
r
co
r
r
elate
d
f
ea
tu
r
e
d
ata
an
al
y
s
i
s
[
6
]
.
A
t
t
h
e
s
a
m
e
ti
m
e,
s
e
v
er
al
C
NN
-
b
ased
D
L
tec
h
n
iq
u
es
all
o
w
t
h
e
d
etec
tio
n
o
f
o
b
j
ec
ts
in
an
i
m
a
g
e
,
a
m
o
n
g
th
e
m
t
h
e
D
A
G
-
C
N
N
[
7
]
,
th
e
R
-
C
NN
[
8
]
,
f
ast
R
-
C
NN
[
9
]
,
Yo
lo
[
1
0
]
an
d
f
aster
R
-
C
NN
[
1
1
]
.
T
h
e
latter
h
as
b
ee
n
i
m
p
le
m
e
n
t
ed
in
v
ar
io
u
s
i
n
v
est
ig
atio
n
s
,
a
n
ex
a
m
p
le
o
f
w
h
ic
h
in
[
1
2
]
,
it
is
i
m
p
l
e
m
e
n
ted
f
o
r
th
e
d
etec
tio
n
o
f
v
e
h
icles
i
n
r
e
al
-
ti
m
e,
o
b
tain
in
g
a
n
ac
c
u
r
ac
y
b
et
w
ee
n
8
5
%
-
9
5
%.
I
n
[
1
3
]
,
a
Fas
ter
R
-
C
N
N
i
s
u
s
ed
f
o
r
t
h
e
d
etec
tio
n
o
f
o
cc
l
u
d
ed
o
b
j
ec
ts
f
o
r
u
n
m
a
n
n
ed
a
er
ial
v
eh
ic
les,
i
n
w
h
ic
h
t
h
e
p
er
f
o
r
m
an
ce
o
f
th
is
n
et
w
o
r
k
i
s
co
m
p
ar
ed
w
i
th
o
t
h
er
C
NN
ar
c
h
itect
u
r
es,
o
b
tain
in
g
t
h
at
t
h
e
Fas
ter
R
-
C
N
N
r
ea
ch
ed
a
g
r
ea
ter
ac
cu
r
ac
y
in
t
h
e
d
etec
tio
n
o
f
t
h
e
ele
m
e
n
t
s
w
i
th
8
3
.
9
%.
T
h
e
R
-
C
NN
allo
w
s
to
id
en
ti
f
y
a
n
o
b
j
ec
t
in
a
r
eg
io
n
o
f
th
e
i
m
a
g
e,
t
h
e
f
a
s
t
i
n
cr
ea
s
e
s
th
e
s
p
ee
d
in
t
h
e
p
r
o
ce
s
s
i
n
g
o
f
t
h
e
n
et
w
o
r
k
a
n
d
t
h
e
f
as
ter
o
p
ti
m
izes
s
aid
p
er
f
o
r
m
a
n
ce
.
T
h
is
m
a
k
es
it
p
o
s
s
ib
le
to
id
en
tify
t
h
at
t
h
e
f
ast
er
R
-
C
N
N
is
th
e
b
est
D
L
o
p
tio
n
f
o
r
th
e
d
etec
tio
n
an
d
id
en
ti
f
icat
io
n
o
f
ele
m
e
n
ts
i
n
a
r
e
g
io
n
-
b
ased
e
n
v
ir
o
n
m
e
n
t,
a
s
i
s
t
h
e
ca
s
e
p
r
o
p
o
s
ed
.
T
o
esti
m
a
te
th
e
r
o
tatio
n
a
n
g
le
o
f
an
ele
m
en
t,
t
h
er
e
ar
e
tec
h
n
iq
u
e
s
b
ase
d
o
n
C
NNs
w
it
h
a
r
eg
r
es
s
io
n
la
y
er
,
f
o
r
e
x
a
m
p
le,
in
[
1
4
]
,
th
e
a
u
t
h
o
r
s
i
m
p
le
m
e
n
t
a
C
NN
r
eg
r
es
s
io
n
to
r
etu
r
n
t
h
e
g
r
ip
co
o
r
d
in
ates
f
r
o
m
an
R
GB
-
D
ca
m
er
a.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
Ob
ject
g
r
ip
p
in
g
a
l
g
o
r
ith
m
fo
r
r
o
b
o
tic
a
s
s
is
ta
n
ce
b
y
mea
n
s
o
f
d
ee
p
lea
n
in
g
(
R
o
b
in
s
o
n
Jimé
n
ez
-
Mo
r
en
o
)
6293
An
o
th
er
ex
a
m
p
le
is
p
r
ese
n
ted
in
[
1
5
]
,
w
h
er
e
t
h
e
C
NN
r
eg
r
ess
io
n
is
u
s
ed
t
o
est
i
m
ate
t
h
e
j
o
in
t
v
elo
citie
s
t
h
at
a
r
o
b
o
t m
u
s
t h
a
v
e
to
lau
n
ch
a
n
d
ca
tch
o
b
j
ec
ts
.
On
t
h
e
o
t
h
er
h
a
n
d
,
D
L
tec
h
n
i
q
u
es
ar
e
i
n
te
g
r
ated
in
to
th
e
co
n
tr
o
l
o
f
r
o
b
o
ts
i
n
a
s
p
ec
ts
b
ase
d
o
n
o
b
j
ec
t
r
ec
o
g
n
itio
n
[
1
6
]
an
d
allo
w
a
p
p
licatio
n
s
o
r
ien
ted
to
t
h
e
g
r
ip
o
f
o
b
j
ec
t
s
,
f
o
r
ex
a
m
p
le,
t
h
e
w
o
r
k
p
r
ese
n
ted
in
[
1
7
]
,
w
h
er
e
a
n
ap
p
licatio
n
o
f
co
n
v
e
n
tio
n
al
u
s
e
f
o
r
g
ar
m
e
n
t
g
r
ip
i
s
o
r
ien
ted
.
Mo
r
e
s
p
ec
i
alize
d
ap
p
licatio
n
s
in
v
o
l
v
e
h
u
m
a
n
-
r
o
b
o
t
in
ter
ac
tio
n
[
1
8
]
,
w
h
er
e
t
h
e
D
L
is
u
s
ed
to
id
en
ti
f
y
t
h
e
i
n
te
n
t
io
n
o
f
m
o
v
e
m
en
t.
Fo
r
ap
p
lica
tio
n
s
t
h
at
i
n
v
o
l
v
e
th
e
u
s
e
o
f
r
o
b
o
ts
in
in
te
g
r
at
ed
en
v
ir
o
n
m
e
n
ts
as
a
s
s
i
s
tan
ts
,
it
is
n
ec
es
s
ar
y
to
id
en
ti
f
y
t
h
e
o
b
j
ec
t
o
f
in
ter
es
t
an
d
g
r
a
s
p
it,
f
o
r
w
h
ic
h
C
NN
h
a
s
alr
ea
d
y
s
h
o
w
n
t
h
eir
v
er
s
atil
it
y
[
1
9
,
2
0
]
.
T
h
is
w
o
r
k
p
r
ese
n
ts
an
ad
v
a
n
ce
in
th
e
u
s
e
o
f
D
L
f
o
r
t
h
e
r
ec
o
g
n
itio
n
a
n
d
g
r
ip
o
f
o
b
j
ec
ts
i
n
m
u
lti
-
o
b
j
ec
tiv
e
en
v
ir
o
n
m
e
n
t
s
o
r
ien
ted
to
ass
is
ti
v
e
r
o
b
o
ts
u
s
i
n
g
r
ec
en
t
tech
n
iq
u
es
o
f
v
ar
iatio
n
o
f
co
n
v
e
n
tio
n
al
C
NN
ar
ch
itect
u
r
es s
u
ch
a
s
f
a
s
t
-
R
C
NN
an
d
C
NN
r
e
g
r
ess
io
n
[
2
1
]
.
C
NN
is
u
s
u
all
y
u
s
ed
f
o
r
d
etec
tin
g
g
r
asp
i
n
g
o
b
j
ec
ts
w
ith
f
i
n
a
l
r
o
b
o
tics
ef
f
ec
to
r
s
w
it
h
a
t
w
e
ez
er
f
o
r
m
,
as
it
is
e
x
p
o
s
ed
i
n
[
22
,
2
3
]
.
B
u
t
i
t
p
r
esen
ts
a
n
u
n
s
tab
le
g
r
ip
r
eq
u
ir
in
g
ad
d
itio
n
al
ti
m
e
to
f
in
d
t
h
e
b
est
w
a
y
to
g
r
ip
,
clo
s
e
to
t
h
e
g
r
a
v
it
y
ce
n
te
r
to
th
e
o
b
j
ec
t.
T
h
is
ar
ticle
p
r
esen
t
s
t
h
e
d
ev
elo
p
m
en
t
o
f
a
n
e
w
a
lg
o
r
it
h
m
b
ased
o
n
Fa
s
ter
R
-
C
NN
an
d
C
NN
r
eg
r
ess
io
n
to
p
r
o
v
id
e
to
r
o
b
o
tic
ag
e
n
t
s
,
eq
u
ip
p
ed
w
it
h
th
r
ee
-
f
in
g
er
g
r
ip
p
er
s
,
th
e
ab
ilit
y
to
g
r
a
s
p
o
b
j
ec
ts
th
at
ar
e
in
t
h
e
en
v
ir
o
n
m
e
n
t,
i
n
cr
ea
s
in
g
t
h
e
s
tab
ilit
y
,
b
u
t
its
tr
ain
i
n
g
i
m
p
lie
s
a
n
ad
d
itio
n
al
co
m
p
le
x
it
y
,
r
ea
s
o
n
f
o
r
u
s
e
b
o
th
o
f
th
e
C
N
N
k
in
d
s
.
T
h
is
p
r
o
b
le
m
e
m
er
g
es
as
a
n
ec
e
s
s
it
y
to
in
te
g
r
ate
an
e
f
f
icien
t
g
r
ip
m
et
h
o
d
w
it
h
p
r
ev
io
u
s
w
o
r
k
s
b
ase
d
o
n
h
u
m
a
n
-
r
o
b
o
t
in
ter
ac
tio
n
[
2
4
]
w
it
h
as
s
is
ta
n
t
r
o
b
o
ts
[
2
5
]
.
T
h
is
ar
ticle
is
d
iv
id
ed
in
to
th
r
ee
s
ec
tio
n
s
.
T
h
e
f
ir
s
t
s
ec
tio
n
p
r
ese
n
ts
t
h
e
e
n
v
ir
o
n
m
e
n
t
o
f
th
e
ap
p
licatio
n
th
at
f
o
c
u
s
es
o
n
t
h
e
ac
q
u
i
s
itio
n
an
d
ad
ap
tati
o
n
o
f
t
h
e
d
atab
ases
an
d
t
h
e
n
eu
r
al
ar
c
h
itect
u
r
e
i
m
p
le
m
en
ted
f
o
r
th
e
d
etec
tio
n
o
f
th
e
ele
m
e
n
ts
to
b
e
g
r
asp
ed
.
I
n
th
e
s
ec
o
n
d
s
ec
tio
n
,
t
h
e
g
r
ap
h
ic
u
s
er
in
ter
f
ac
e
th
at
f
ac
il
itates
t
h
e
ac
q
u
i
s
itio
n
o
f
d
atab
ases
,
tr
ain
i
n
g
o
f
n
et
wo
r
k
s
a
n
d
r
es
u
lts
o
b
tain
ed
i
n
a
v
ir
tu
a
l
e
n
v
ir
o
n
m
e
n
t
ar
e
ex
p
o
s
ed
.
Fin
all
y
,
t
h
e
co
n
clu
s
io
n
s
o
f
t
h
e
d
ev
elo
p
ed
s
y
s
te
m
an
d
p
o
s
s
ib
le
i
m
p
r
o
v
e
m
e
n
ts
f
o
r
f
u
tu
r
e
w
o
r
k
ar
e
p
r
esen
ted
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
o
ev
alu
ate
a
g
r
ip
al
g
o
r
ith
m
u
s
in
g
DL
u
s
i
n
g
C
NN,
3
o
b
j
ec
ts
ar
e
estab
lis
h
ed
i
n
a
v
ir
t
u
a
l
en
v
ir
o
n
m
e
n
t.
Sin
ce
th
e
a
i
m
is
to
u
s
e
a
g
r
ip
p
er
f
o
r
a
r
o
b
o
tic
ag
en
t,
th
e
ch
ar
ac
ter
is
tics
o
f
t
h
e
g
r
ip
o
b
j
ec
t
m
u
s
t
b
e
d
ef
in
ed
.
T
o
g
en
er
alize
th
e
g
eo
m
etr
ie
s
,
t
w
o
t
y
p
es
o
f
o
b
j
ec
ts
ar
e
p
r
o
p
o
s
ed
;
th
e
f
ir
s
t
t
y
p
e
h
a
v
e
in
f
i
n
ite
s
y
m
m
etr
y
ax
e
s
,
w
h
er
e
t
w
o
o
b
j
ec
ts
w
ith
t
h
at
c
h
ar
ac
ter
is
tic
a
r
e
estab
lis
h
ed
:
a
c
y
l
in
d
er
a
n
d
a
to
r
o
id
;
th
e
s
ec
o
n
d
t
y
p
e
is
d
ef
i
n
ed
w
ith
a
f
i
n
ite
n
u
m
b
er
o
f
s
y
m
m
etr
y
a
x
es,
u
s
i
n
g
a
p
ar
allelep
ip
ed
g
eo
m
etr
y
.
B
y
h
av
in
g
ele
m
en
t
s
w
it
h
a
f
i
n
ite
n
u
m
b
er
o
f
a
x
es
o
f
s
y
m
m
etr
y
,
th
eir
r
o
tatio
n
c
o
u
ld
af
f
ec
t
t
h
e
w
a
y
i
t
g
r
ab
s
w
h
e
n
c
h
an
g
i
n
g
t
h
eir
o
r
ien
tatio
n
w
it
h
r
esp
ec
t
to
th
e
Z
ax
i
s
,
r
eq
u
ir
in
g
a
test
o
f
th
i
s
t
y
p
e.
W
ith
th
e
d
ef
i
n
ed
o
b
j
ec
ts
,
t
w
o
d
atab
ases
ar
e
estab
lis
h
ed
:
t
h
e
f
ir
s
t
o
n
e,
to
tr
ain
a
n
et
w
o
r
k
f
o
r
its
d
etec
tio
n
an
d
th
e
s
ec
o
n
d
o
n
e,
to
es
ti
m
ate
t
h
e
an
g
le
at
w
h
ic
h
th
e
p
ar
allelep
ip
ed
is
r
o
tated
.
2
.
1
.
Da
t
a
ba
s
e
f
o
r
net
wo
rk
s
t
ra
ini
ng
I
n
Fig
u
r
e
1
,
s
o
m
e
ex
a
m
p
les
o
f
th
e
d
atab
ase
f
o
r
d
etec
tio
n
an
d
lo
ca
lizatio
n
ar
e
s
h
o
w
n
,
in
w
h
ic
h
th
e
p
o
s
itio
n
an
d
o
r
ien
tatio
n
o
f
th
e
ele
m
en
ts
in
t
h
e
en
v
ir
o
n
m
en
t
ar
e
ch
an
g
ed
.
A
to
tal
o
f
2
1
9
5
R
GB
im
a
g
es
w
it
h
a
r
eso
lu
t
io
n
o
f
2
2
4
x
2
2
4
p
ix
els
ar
e
estab
lis
h
ed
,
o
f
w
h
i
ch
2
0
0
im
a
g
es
ar
e
s
ep
ar
ated
f
o
r
ev
alu
atio
n
a
f
ter
tr
ain
i
n
g
a
n
d
th
e
r
est ar
e
u
s
ed
to
tr
ain
th
e
n
e
t
w
o
r
k
.
Fig
u
r
e
1
.
Sa
m
p
le
o
f
t
h
e
d
atab
ase
f
o
r
d
etec
tio
n
an
d
lo
ca
lizatio
n
o
f
ele
m
en
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
6
,
Decem
b
er
2020
:
6
2
9
2
-
6
2
9
9
6294
Fo
r
th
e
n
et
w
o
r
k
tr
ai
n
ed
to
est
i
m
ate
th
e
an
g
le
o
f
r
o
tatio
n
,
t
w
o
d
atab
ase
s
w
er
e
e
s
tab
lis
h
e
d
,
o
n
e
R
G
B
an
d
o
n
e
b
in
ar
y
,
to
e
v
al
u
ate
wh
ich
o
f
t
h
e
t
w
o
d
atab
ases
m
a
n
ag
es
to
h
a
v
e
a
b
etter
lear
n
i
n
g
.
Fro
m
th
e
p
r
ev
io
u
s
d
atab
ase,
2
0
0
0
im
a
g
es
w
er
e
t
ak
en
,
f
r
o
m
w
h
ic
h
th
e
r
e
g
io
n
s
w
h
er
e
th
e
p
ar
allelep
ip
ed
is
lo
ca
ted
ar
e
ex
tr
ac
ted
.
On
ce
t
h
e
r
e
g
i
o
n
s
ar
e
o
b
tain
e
d
,
ed
g
es
ar
e
ad
d
ed
to
th
e
i
m
a
g
es
o
f
b
o
th
d
atab
ases
to
m
a
k
e
th
e
i
m
a
g
e
s
q
u
ar
e.
T
h
is
is
d
o
n
e
s
in
ce
all
th
e
i
m
ag
es
m
u
s
t
b
e
r
esized
to
th
e
s
a
m
e
s
ize,
b
ec
au
s
e
n
e
t
w
o
r
k
in
p
u
t
s
ize
ca
n
n
o
t
b
e
v
ar
iab
le.
I
t
is
s
et
a
s
ize
o
f
5
0
x
5
0
p
ix
el
f
o
r
th
e
i
m
a
g
es,
w
h
i
ch
en
co
m
p
as
s
es
t
h
e
s
ize
o
f
th
e
p
ar
allel
ep
ip
ed
as
s
h
o
w
n
in
Fi
g
u
r
e
2
.
Fro
m
2
0
0
0
im
a
g
es,
1
0
%
o
f
t
h
e
m
,
co
r
r
esp
o
n
d
in
g
to
2
0
0
i
m
ag
e
s
,
ar
e
u
s
ed
f
o
r
test
s
af
ter
tr
ain
i
n
g
.
R
GB
d
atab
ase
B
in
ar
y
d
atab
ase
Fig
u
r
e
2
.
P
r
o
p
o
s
ed
d
ata
b
ases
f
o
r
an
g
le
e
s
ti
m
atio
n
2
.
2
.
D
L
a
rc
hite
ct
ure
s
T
h
e
p
r
o
p
o
s
ed
ar
ch
itectu
r
e
is
d
iv
id
ed
in
t
w
o
p
ar
ts
.
I
n
t
h
e
f
i
r
s
t
p
ar
t,
a
Fas
ter
R
-
C
NN
is
i
m
p
le
m
e
n
te
d
to
d
etec
t
an
d
to
lo
ca
te
th
e
el
e
m
en
ts
i
n
t
h
e
e
n
v
ir
o
n
m
e
n
t.
I
n
t
h
e
s
ec
o
n
d
p
ar
t,
an
ar
c
h
ite
ctu
r
e
p
r
o
p
o
s
ed
f
o
r
a
C
NN
w
it
h
a
r
eg
r
es
s
io
n
la
y
er
th
at
a
llo
w
s
e
s
ti
m
ati
n
g
t
h
e
an
g
le
to
w
h
ic
h
th
e
p
ar
allelep
ip
ed
is
r
o
tated
as
s
h
o
w
n
in
Fi
g
u
r
e
3
.
T
h
e
Fas
ter
R
-
C
NN,
u
n
li
k
e
a
co
n
v
e
n
tio
n
al
C
N
N,
h
as
an
R
P
N
(
r
eg
io
n
p
r
o
p
o
s
al
n
et
w
o
r
k
)
,
w
it
h
w
h
ic
h
f
r
a
m
es,
ca
l
led
A
n
c
h
o
r
s
,
ar
e
g
e
n
er
ated
i
n
t
h
e
i
m
a
g
e,
w
h
er
e
it i
s
id
e
n
ti
f
ied
i
n
w
h
ich
a
n
o
b
j
ec
t c
o
u
ld
ex
is
t.
T
h
e
lear
n
ed
ch
ar
ac
ter
is
t
ics
ar
e
lin
k
ed
w
i
th
a
R
o
I
-
P
o
o
lin
g
,
t
h
en
p
ass
e
s
th
r
o
u
g
h
Fu
ll
y
C
o
n
n
ec
ted
la
y
er
s
th
at
al
lo
w
to
g
en
er
ate
a
lear
n
in
g
o
n
t
h
e
e
x
tr
ac
ted
c
h
ar
ac
t
er
is
tics
a
n
d
f
i
n
all
y
,
to
id
e
n
ti
f
y
i
n
ea
c
h
d
etec
ted
o
b
j
ec
t
to
w
h
ich
ca
teg
o
r
y
it
b
elo
n
g
s
.
A
s
a
n
ar
c
h
itect
u
r
e
f
o
r
th
e
Fas
ter
R
-
C
NN,
t
h
e
V
GG
1
6
n
et
w
o
r
k
[
2
6
]
is
i
m
p
le
m
en
ted
.
T
h
en
,
f
r
o
m
th
e
r
eg
io
n
s
d
etec
ted
b
y
t
h
e
F
aster
R
-
C
NN,
o
n
l
y
t
h
e
o
n
e
co
r
r
esp
o
n
d
in
g
t
o
th
e
p
ar
allelep
ip
ed
is
ex
tr
ac
ted
an
d
ad
j
u
s
ted
a
s
i
n
d
icat
ed
in
th
e
d
atab
ase
f
o
r
th
e
C
NN
r
eg
r
es
s
io
n
.
T
h
is
ar
ch
itectu
r
e
co
n
s
is
ts
o
f
f
o
u
r
co
n
v
o
lu
tio
n
al
la
y
er
s
t
h
at
w
il
l
lear
n
t
h
e
f
ea
t
u
r
es
o
f
t
h
e
p
ar
allelep
ip
ed
,
to
b
e
th
en
e
n
ter
ed
in
to
t
h
e
F
u
ll
y
C
o
n
n
ec
ted
la
y
er
s
an
d
f
in
a
ll
y
,
w
it
h
t
h
e
r
eg
r
es
s
io
n
la
y
er
,
to
esti
m
ate
t
h
e
a
n
g
le.
Giv
e
n
th
e
g
eo
m
etr
y
o
f
t
h
e
o
b
ject,
th
e
an
g
le
o
f
r
o
tatio
n
w
il
l
b
e
b
etw
ee
n
0
°
an
d
1
8
0
°,
f
r
o
m
th
is
t
h
e
m
a
x
i
m
u
m
an
g
le
i
s
s
et
at
1
7
5
°,
tak
in
g
th
e
r
an
g
e
b
et
w
ee
n
1
7
5
°
an
d
1
8
0
°
eq
u
al
to
ze
r
o
,
th
at
is
,
v
ar
iatio
n
s
o
f
at
least
5
°
o
f
er
r
o
r
w
ill b
e
v
a
lid
ated
.
Fig
u
r
e
3
.
P
r
o
p
o
s
ed
ar
ch
itectu
r
e
f
o
r
th
e
d
etec
tio
n
o
f
ele
m
e
n
ts
in
th
e
e
n
v
ir
o
n
m
en
t a
n
d
ca
lcu
l
atio
n
o
f
th
e
o
r
ien
tatio
n
an
g
le
o
f
a
n
ele
m
en
t
w
it
h
f
i
n
ite
n
u
m
b
er
o
f
s
y
m
m
etr
ic
ax
e
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
Ob
ject
g
r
ip
p
in
g
a
l
g
o
r
ith
m
fo
r
r
o
b
o
tic
a
s
s
is
ta
n
ce
b
y
mea
n
s
o
f
d
ee
p
lea
n
in
g
(
R
o
b
in
s
o
n
Jimé
n
ez
-
Mo
r
en
o
)
6295
3.
RE
SU
L
T
S AN
D
AN
AL
Y
SI
S
3
.
1
.
Net
wo
rk
s
re
s
ults
Fas
ter
R
-
C
N
N
is
tr
ain
ed
w
ith
th
e
tr
ain
in
g
i
m
ag
e
s
,
th
e
co
n
f
u
s
io
n
m
atr
i
x
is
ca
lcu
la
ted
in
o
r
d
er
to
b
e
ab
le
to
d
e
m
o
n
s
tr
ate
i
t
s
p
er
f
o
r
m
an
ce
i
n
lear
n
in
g
a
s
s
h
o
w
n
i
n
Fi
g
u
r
e
4
.
I
n
Fi
g
u
r
e
4
(
a
)
an
d
(
b
)
,
th
e
co
n
f
u
s
io
n
m
atr
ices
o
f
t
h
e
tr
ain
in
g
an
d
t
esti
n
g
d
atab
ase
ar
e
p
r
esen
ted
.
T
h
e
g
r
ee
n
d
iag
o
n
al
r
ep
r
esen
ts
th
e
i
m
ag
e
s
th
a
t
w
er
e
co
r
r
ec
tl
y
cla
s
s
i
f
ied
an
d
o
u
t
o
f
t
h
is
t
h
o
s
e
t
h
at
w
er
e
cla
s
s
i
f
ied
in
a
n
i
n
co
r
r
ec
t
ca
teg
o
r
y
.
B
o
th
th
e
tr
ai
n
i
n
g
d
atab
ase
an
d
th
e
test
d
atab
ase
s
h
o
w
ed
1
0
0
% a
cc
u
r
ac
y
in
t
h
e
class
i
f
icatio
n
o
f
t
h
e
i
m
a
g
e
s.
Fig
u
r
e
4
.
C
o
n
f
u
s
io
n
m
at
r
ices
f
o
r
th
e
tr
ain
in
g
d
atab
ase
,
(
a)
an
d
test
s
an
d
(
b
)
w
h
er
e
1
=
cy
lin
d
er
/ 2
=
p
ar
alele
p
ip
ed
/ 3
=
to
r
o
i
d
/ 4
=
b
ac
k
g
r
o
u
n
d
An
o
th
er
f
ac
to
r
to
tak
e
in
to
a
cc
o
u
n
t
w
h
en
p
er
f
o
r
m
i
n
g
a
s
y
s
te
m
f
o
r
th
e
d
etec
tio
n
o
f
el
e
m
en
ts
i
n
i
m
a
g
es
i
s
t
h
e
Av
er
ag
e
P
r
ec
is
io
n
.
S
in
ce
t
h
is
w
ill
i
n
d
icate
t
h
e
p
r
ec
is
io
n
o
f
th
e
o
v
er
lap
b
et
w
ee
n
t
h
e
b
o
x
e
s
t
h
at
g
en
er
ate
t
h
e
n
et
w
o
r
k
a
n
d
th
o
s
e
s
et
in
th
e
g
r
o
u
n
d
tr
u
t
h
.
Fo
r
b
o
th
d
atab
ases
(
tr
ain
in
g
an
d
t
est),
v
alu
e
s
g
r
ea
ter
th
an
9
7
%
ac
cu
r
ac
y
ar
e
p
r
es
en
ted
,
i.e
.
t
h
e
b
o
x
es
g
e
n
er
at
ed
b
y
th
e
n
e
t
w
o
r
k
ar
e
r
elia
b
le
an
d
w
ill
allo
w
th
e
r
o
b
o
tic
ag
en
t to
m
o
v
e
co
r
r
ec
tl
y
to
g
r
ab
th
e
m
.
I
n
Fig
u
r
e
5
,
s
o
m
e
e
x
a
m
p
le
s
o
f
class
i
f
icatio
n
an
d
d
etec
tio
n
o
f
th
e
Fas
ter
R
-
C
NN
ar
e
s
h
o
w
n
.
I
t
ca
n
b
e
s
ee
n
ca
s
es
i
n
w
h
ic
h
t
h
e
ele
m
en
ts
to
b
e
id
en
ti
f
ied
ar
e
p
ar
tiall
y
o
b
s
tr
u
c
ted
an
d
ev
e
n
s
o
th
e
n
et
w
o
r
k
i
s
ab
le
to
d
etec
t
th
e
m
alt
h
o
u
g
h
w
it
h
le
s
s
r
eliab
ilit
y
.
T
h
e
n
et
w
o
r
k
i
s
te
s
ted
b
y
p
lacin
g
s
tr
an
g
e
o
b
j
ec
ts
th
at
ar
e
u
n
k
n
o
w
n
,
id
en
ti
f
y
i
n
g
th
a
t,
alth
o
u
g
h
th
er
e
ar
e
elem
e
n
t
s
s
i
m
ilar
to
th
o
s
e
tr
ain
ed
,
n
o
f
alse p
o
s
iti
v
e
s
ar
e
p
r
esen
ted
.
Fig
u
r
e
5
.
T
ests
o
f
th
e
tr
ain
ed
n
et
w
o
r
k
Fo
r
th
e
C
NN
r
e
g
r
ess
io
n
,
th
r
o
u
g
h
a
n
iter
ativ
e
p
r
o
ce
s
s
,
t
h
e
t
r
ain
in
g
p
ar
a
m
eter
s
o
f
t
h
e
n
et
w
o
r
k
w
er
e
estab
lis
h
ed
,
o
b
tain
in
g
a
b
atch
s
ize
f
o
r
th
e
tr
ai
n
i
n
g
o
f
1
0
0
,
a
lear
n
i
n
g
f
ac
to
r
o
f
1
x
1
0
-
6
an
d
1
0
0
ep
o
ch
s
o
f
tr
ain
i
n
g
,
al
lo
w
in
g
t
h
e
n
et
w
o
r
k
to
esti
m
ate
a
n
ap
p
r
o
x
i
m
ate
an
g
le
to
t
h
e
r
ea
l o
n
e
w
it
h
o
u
t
g
o
i
n
g
in
to
o
v
er
f
it
tin
g
.
I
n
Fig
u
r
e
6
,
th
e
b
o
x
d
iag
r
am
s
f
o
r
th
e
R
GB
an
d
B
in
ar
y
d
ata
b
ase
ar
e
p
r
esen
ted
.
T
h
e
b
in
ar
y
d
atab
ase
o
b
tain
ed
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
6
,
Decem
b
er
2020
:
6
2
9
2
-
6
2
9
9
6296
1
9
o
u
tlier
s
,
w
h
ile
t
h
e
R
GB
d
atab
ase
o
n
l
y
1
0
.
An
o
th
er
f
ac
to
r
to
h
ig
h
li
g
h
t
i
s
th
e
m
ea
n
er
r
o
r
f
o
r
b
o
th
b
ases
,
f
o
r
th
e
b
in
ar
y
it
co
r
r
esp
o
n
d
s
to
1
.
0
4
9
º
an
d
f
o
r
th
e
R
GB
,
0
.
7
6
9
º
.
T
h
e
b
in
ar
y
d
atab
ase
also
s
h
o
w
ed
a
g
r
ea
ter
er
r
o
r
i
n
t
h
e
r
a
n
g
e
o
f
n
o
n
-
a
t
y
p
i
c
a
l
v
a
l
u
e
s
,
b
e
i
n
g
b
e
tw
e
e
n
2
0
.
2
3
º
a
n
d
-
1
6
.
5
4
º
,
w
h
i
l
e
i
n
t
h
e
R
G
B
i
m
a
g
e
s
,
o
f
8
.
4
9
º
a
n
d
-
1
1
.
7
6
º
.
T
h
e
r
e
f
o
r
e
,
i
t
c
a
n
b
e
c
o
n
c
l
u
d
e
d
t
h
a
t
t
h
e
R
G
B
d
a
t
a
b
a
s
e
p
r
e
s
e
n
t
e
d
a
b
e
t
t
e
r
p
e
r
f
o
r
m
a
n
c
e
t
h
a
n
t
h
e
b
i
n
a
r
y
o
n
e
.
Fig
u
r
e
6
.
(
a)
B
o
x
p
lo
t o
f
th
e
te
s
t d
atab
ase
o
f
o
n
e
ch
a
n
n
el
(
b
in
ar
y
)
an
d
(
b
)
th
r
ee
ch
a
n
n
el
s
(
R
GB
)
I
n
Fig
u
r
e
7
,
s
o
m
e
ex
a
m
p
les
o
f
an
g
le
esti
m
atio
n
w
ith
R
G
B
in
p
u
t
i
m
a
g
es
ar
e
s
h
o
w
n
.
I
t
ca
n
b
e
s
ee
n
th
at
t
h
e
es
ti
m
ate
ag
r
ee
s
w
it
h
th
e
r
es
u
lt
s
ca
lcu
lated
in
th
e
b
o
x
d
iag
r
a
m
.
Alt
h
o
u
g
h
in
d
i
f
f
er
en
t
p
o
s
itio
n
s
an
d
o
r
ien
tatio
n
s
o
f
t
h
e
o
b
j
ec
t
in
th
e
en
v
ir
o
n
m
e
n
t
t
h
e
er
r
o
r
in
th
e
ca
lcu
latio
n
o
f
th
e
a
n
g
le
is
lo
w
,
t
h
er
e
ar
e
ca
s
e
s
lik
e
t
h
e
o
n
e
p
r
ese
n
ted
i
n
Fi
g
u
r
e
8
,
w
h
er
e
t
h
er
e
ar
e
s
o
m
e
p
o
s
itio
n
s
an
d
a
n
g
les
o
f
o
r
ien
tati
o
n
th
at
ca
n
g
e
n
er
ate
at
y
p
ical
r
esu
lts
.
Fig
u
r
e
7
.
E
x
a
m
p
les o
f
o
r
ien
tat
io
n
an
g
le
esti
m
atio
n
w
it
h
r
esp
ec
t to
th
e
Z
a
x
is
o
f
th
e
p
ar
allelep
ip
ed
w
it
h
R
GB
i
m
ag
e
s
Fig
u
r
e
8
.
E
r
r
o
r
in
th
e
esti
m
at
i
o
n
o
f
th
e
o
r
ien
ta
tio
n
a
n
g
le
o
f
t
h
e
p
ar
allelep
ip
ed
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
Ob
ject
g
r
ip
p
in
g
a
l
g
o
r
ith
m
fo
r
r
o
b
o
tic
a
s
s
is
ta
n
ce
b
y
mea
n
s
o
f
d
ee
p
lea
n
in
g
(
R
o
b
in
s
o
n
Jimé
n
ez
-
Mo
r
en
o
)
6297
3
.
2
.
T
ests in v
irt
ua
l e
nv
iro
nm
e
nt
No
w
ad
a
y
s
,
t
h
er
e
ar
e
s
e
v
er
al
v
ir
tu
al
e
n
v
ir
o
n
m
en
t
s
t
h
at
ar
e
u
s
ed
f
o
r
th
e
s
i
m
u
latio
n
o
f
r
o
b
o
tic
s
y
s
te
m
s
,
a
m
o
n
g
t
h
e
m
a
in
o
n
es
ar
e
Gaz
eb
o
a
n
d
V
-
R
E
P
,
w
h
er
e
i
n
[
27
]
,
th
e
m
ai
n
ad
v
an
tag
e
s
a
n
d
d
is
ad
v
an
ta
g
es
o
f
ea
c
h
ar
e
p
r
esen
ted
.
V
-
R
E
P
is
s
el
ec
ted
f
o
r
its
d
iv
er
s
it
y
o
f
s
e
n
s
o
r
s
an
d
co
u
p
li
n
g
w
it
h
d
if
f
er
en
t
p
r
o
g
r
a
m
m
in
g
lan
g
u
a
g
es.
I
n
Fi
g
u
r
e
9
,
an
e
x
a
m
p
le
o
f
th
e
v
ir
t
u
al
e
n
v
ir
o
n
m
en
t
u
s
ed
is
s
h
o
w
n
,
w
h
er
e
it
ca
n
b
e
s
ee
n
a
R
R
P
r
o
b
o
t,
w
h
ich
h
as
a
g
r
ip
p
er
as
f
i
n
al
e
f
f
ec
to
r
,
an
d
th
e
t
h
r
e
e
d
if
f
er
e
n
t
t
y
p
es
o
f
o
b
j
ec
ts
in
th
e
e
n
v
ir
o
n
m
en
t
(
cy
lin
d
er
,
p
ar
allelep
ip
ed
an
d
to
r
o
id
)
,
w
h
ich
ca
n
b
e
v
is
u
alize
d
w
it
h
a
ca
m
er
a
th
at
is
in
co
r
p
o
r
ated
in
th
e
g
r
ip
p
er
.
I
n
[
28
]
,
it
is
m
e
n
tio
n
ed
t
h
at
u
s
i
n
g
a
v
ir
tu
al
en
v
ir
o
n
m
e
n
t
w
i
ll
f
ac
i
litate
t
h
e
test
s
o
f
t
h
e
D
L
ar
ch
itect
u
r
es
f
o
r
t
h
e
d
etec
tio
n
o
f
th
e
ele
m
e
n
ts
.
I
n
th
i
s
w
a
y
,
w
h
e
n
i
m
p
le
m
e
n
ti
n
g
t
h
e
m
i
n
a
r
ea
l
en
v
ir
o
n
m
e
n
t,
it
w
ill
n
o
t
b
e
n
ec
e
s
s
ar
y
to
t
r
ain
t
h
e
n
et
w
o
r
k
f
r
o
m
s
cr
atc
h
,
it
w
i
ll
o
n
l
y
b
e
n
ec
ess
ar
y
a
f
i
n
e
t
u
n
in
g
f
o
r
th
e
n
et
w
o
r
k
s
to
b
e
co
u
p
led
to
th
e
r
ea
l e
n
v
ir
o
n
m
en
t
.
I
n
th
e
v
ir
tu
a
l
en
v
ir
o
n
m
en
t,
th
e
g
r
ip
p
er
ca
m
er
a
r
u
n
s
f
r
a
m
e
b
y
f
r
a
m
e
w
h
ile
r
u
n
n
i
n
g
t
h
e
Fa
s
t
er
R
-
C
NN
a
n
d
it
ca
n
r
ea
ch
u
p
to
5
f
p
s
w
i
th
a
s
e
v
en
th
-
g
en
er
atio
n
i7
co
m
p
u
ter
w
it
h
a
n
N
VI
DI
A
GT
X
9
6
0
M
GP
U
an
d
1
6
GB
o
f
R
A
M.
O
n
ce
th
e
s
y
s
te
m
is
r
u
n
n
in
g
,
it
ca
n
b
e
s
elec
ted
b
et
w
ee
n
th
e
o
p
tio
n
s
"
C
y
li
n
d
er
"
,
"P
ar
allelep
ip
e
d
"
an
d
"T
o
r
o
id
"
,
in
o
r
d
e
r
to
tell
t
h
e
r
o
b
o
tic
ag
en
t
w
h
ic
h
ite
m
t
o
co
llect.
I
t
is
h
ig
h
lig
h
ted
th
at
u
n
d
er
th
e
o
p
tio
n
o
f
"P
ar
allelep
ip
ed
"
th
e
an
g
le
to
w
h
ic
h
t
h
e
e
le
m
e
n
t
is
r
o
tated
i
s
s
h
o
w
n
.
I
n
ca
s
e
o
f
s
i
g
n
if
ican
t
er
r
o
r
s
in
th
is
an
g
le,
th
e
o
p
tio
n
"
A
cq
u
i
s
itio
n
"
m
ak
es
a
n
e
w
d
atab
ase
w
it
h
t
h
e
s
ec
tio
n
s
d
etec
ted
b
y
t
h
e
Fas
te
r
R
-
C
NN
i
n
w
h
ic
h
th
e
p
ar
allelep
ip
ed
is
lo
ca
ted
,
w
it
h
w
h
ich
a
n
e
w
C
NN
n
e
t
w
o
r
k
ca
n
b
e
tr
ain
ed
f
o
r
task
s
o
f
r
eg
r
es
s
io
n
o
f
th
e
o
r
ien
tatio
n
an
g
le
o
f
t
h
e
o
b
j
ec
t a
s
s
h
o
w
n
i
n
Fi
g
u
r
e
1
0
.
Fig
u
r
e
9
.
Vir
tu
al
w
o
r
k
en
v
ir
o
n
m
e
n
t i
n
V
-
RE
P
Fig
u
r
e
1
0
.
T
est s
ec
tio
n
o
f
t
h
e
n
et
w
o
r
k
s
w
it
h
th
e
v
ir
tu
a
l e
n
v
i
r
o
n
m
e
n
t in
t
h
e
g
r
ap
h
ic
u
s
er
in
ter
f
ac
e
I
n
Fi
g
u
r
e
1
1
,
s
o
m
e
g
r
ip
tes
ts
ar
e
s
h
o
w
n
f
o
r
ea
c
h
o
b
j
ec
t
w
it
h
t
w
o
a
n
d
th
r
ee
f
i
n
g
er
g
r
ip
p
er
s
.
I
n
Fi
g
u
r
e
1
1
,
s
o
m
e
g
r
ip
te
s
t
s
ar
e
s
h
o
w
n
f
o
r
ea
ch
o
b
j
ec
t
w
it
h
t
w
o
an
d
t
h
r
e
e
f
in
g
er
g
r
ip
p
er
s
.
I
n
g
e
n
er
al,
in
t
h
e
test
s
ca
r
r
ied
o
u
t,
th
e
t
h
r
ee
-
f
i
n
g
er
g
r
ip
p
er
allo
w
ed
a
g
r
ea
ter
m
ar
g
in
o
f
er
r
o
r
w
ith
r
esp
ec
t
to
th
e
t
w
o
,
b
u
t
i
n
s
o
m
e
ca
s
es,
o
n
e
o
f
th
e
ad
d
itio
n
al
f
in
g
er
s
o
f
t
h
e
t
h
r
ee
-
f
in
g
er
g
r
ip
p
er
m
a
y
n
o
t
p
er
f
o
r
m
a
u
s
ef
u
l
f
u
n
ctio
n
d
u
r
i
n
g
th
e
g
r
ip
,
as sh
o
w
n
i
n
Fi
g
u
r
e
1
1
,
w
h
en
t
h
e
t
h
r
ee
-
f
i
n
g
er
g
r
ip
p
er
g
r
ip
s
th
e
p
ar
allelep
ip
ed
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
6
,
Decem
b
er
2020
:
6
2
9
2
-
6
2
9
9
6298
Fig
u
r
e
1
1
.
E
x
a
m
p
les o
f
te
s
ts
w
it
h
t
w
o
a
n
d
th
r
ee
f
i
n
g
er
g
r
ip
p
e
rs
4.
CO
NCLU
SI
O
N
T
h
e
im
p
lem
en
t
a
ti
o
n
o
f
th
e
Fa
s
t
e
r
R
-
C
N
N
f
o
r
th
e
d
e
t
e
ct
i
o
n
o
f
e
l
em
en
t
s
o
f
in
t
e
r
es
t
in
th
e
en
v
i
r
o
n
m
en
t
m
an
ag
e
d
t
o
o
b
ta
in
1
0
0
%
a
cc
u
r
a
cy
in
t
h
e
c
l
ass
if
i
c
at
i
o
n
s
o
f
t
h
e
t
es
t
d
a
ta
b
a
s
e
,
a
n
d
o
v
e
r
a
9
7
%
o
f
av
e
r
ag
e
p
r
e
c
i
s
i
o
n
l
o
c
a
ti
n
g
th
e
g
en
e
r
at
e
d
b
o
x
es
in
e
ac
h
e
l
em
en
t
,
th
u
s
a
ll
o
w
in
g
th
e
r
o
b
o
t
i
c
ag
en
t
t
o
h
av
e
g
r
e
a
t
e
r
a
u
t
o
n
o
m
y
in
th
e
ex
e
cu
t
i
o
n
o
f
th
e
i
r
t
r
a
je
c
t
o
r
ie
s
t
o
w
a
r
d
s
th
e
o
b
je
c
t
s
th
a
t
a
r
e
w
an
t
e
d
t
o
b
e
c
o
l
le
c
t
e
d
.
T
h
e
d
e
s
ig
n
o
f
a
C
N
N
t
r
a
in
e
d
f
o
r
r
eg
r
e
s
s
i
o
n
ta
s
k
s
a
l
l
o
w
e
d
t
o
c
a
l
cu
l
a
t
e
an
a
p
p
r
o
x
im
a
t
e
an
g
l
e
t
o
t
h
e
r
e
al
o
n
e
in
m
o
s
t
c
a
s
es
,
b
u
t
f
r
o
m
th
e
r
esu
lt
s
o
b
t
ain
e
d
in
th
e
b
o
x
p
l
o
t
,
i
t
is
p
o
s
s
i
b
le
t
o
i
d
e
n
t
if
y
th
at
in
c
as
e
i
t
i
s
w
an
t
e
d
t
o
im
p
l
em
en
t
a
s
y
s
t
em
t
h
at
r
e
q
u
i
r
e
s
h
ig
h
p
r
e
c
i
s
i
o
n
an
d
a
c
c
u
r
a
cy
t
o
p
e
r
f
o
r
m
a
t
ask
,
e
r
r
o
r
s
i
n
th
e
g
r
i
p
p
in
g
t
as
k
s
m
ay
a
p
p
e
a
r
.
F
o
r
th
is
r
e
a
s
o
n
,
f
o
r
f
u
tu
r
e
d
ev
e
l
o
p
m
en
ts
,
o
th
e
r
p
o
s
s
i
b
l
e
d
a
ta
b
a
s
es
w
il
l
b
e
e
v
a
lu
at
e
d
t
o
r
e
d
u
c
e
th
e
e
r
r
o
r
o
b
t
a
i
n
e
d
.
T
a
k
i
n
g
in
t
o
ac
c
o
u
n
t
th
e
t
r
a
je
c
to
r
i
e
s
m
a
d
e
an
d
th
e
g
r
i
p
s
m
a
d
e
b
y
th
e
r
o
b
o
t
i
c
ag
en
t
,
i
t
is
p
r
o
p
o
s
e
d
f
o
r
f
u
tu
r
e
d
ev
el
o
p
m
en
t
s
t
o
c
al
cu
l
at
e
,
b
y
m
e
an
s
o
f
a
C
N
N
r
e
g
r
e
s
s
i
o
n
,
th
e
c
o
o
r
d
i
n
a
t
es
o
f
th
e
a
p
p
r
o
x
im
a
t
e
p
o
in
ts
o
f
g
r
i
p
f
o
r
e
ac
h
o
f
th
e
f
in
g
e
r
s
th
a
t
th
e
g
r
i
p
p
e
r
m
ay
h
a
v
e
,
in
o
r
d
e
r
t
h
at
a
ll
s
e
r
v
e
as
s
u
p
p
o
r
t
i
n
th
e
ex
e
cu
ti
o
n
o
f
t
h
e
t
a
s
k
.
T
h
e
c
o
m
p
a
r
is
o
n
b
e
tw
ee
n
tw
o
an
d
th
r
e
e
f
in
g
e
r
s
g
r
i
p
p
i
n
g
s
im
u
l
a
te
d
,
i
t
s
t
a
t
e
d
t
h
r
e
e
f
in
g
e
r
s
g
r
i
p
p
in
g
a
l
l
o
w
k
e
e
p
t
h
e
o
b
je
c
t
,
w
h
i
l
e
w
i
t
h
tw
o
f
i
n
g
e
r
s
it
is
g
r
i
p
p
in
g
o
n
c
l
o
s
e
t
o
th
e
g
r
av
i
ty
c
en
t
e
r
b
u
t
n
o
t
in
i
t
,
t
h
e
o
b
je
c
t
i
s
ex
p
o
s
e
d
t
o
p
o
s
s
i
b
l
e
f
a
ll
en
.
I
n
e
v
e
r
y
c
as
e
,
th
e
o
b
je
c
t
w
as
s
u
cc
e
s
s
f
u
l
ly
g
r
a
b
b
e
d
b
y
th
e
p
r
o
p
o
s
e
d
a
lg
o
r
i
th
m
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
e
au
th
o
r
s
ar
e
g
r
ate
f
u
l
to
th
e
Un
i
v
er
s
id
ad
Militar
Nu
e
v
a
G
r
an
ad
a,
w
h
ic
h
,
th
r
o
u
g
h
its
Vic
e
R
ec
to
r
y
f
o
r
r
esear
ch
s
,
f
i
n
a
n
ce
s
t
h
e
p
r
esen
t
p
r
o
j
ec
t
w
it
h
co
d
e
I
MP
-
I
NG
-
2935
(
2
0
1
9
-
2
0
2
0
)
an
d
titl
ed
"
Pro
to
tip
o
r
o
b
ó
tico
f
lex
i
b
le
p
ar
a
asis
ten
c
ia
ali
m
e
n
tar
ia,
"
f
r
o
m
w
h
ic
h
t
h
e
p
r
esen
t
w
o
r
k
is
d
er
iv
ed
.
RE
F
E
R
E
NC
E
S
[1
]
Am
in
e
Bo
u
le
m
ta
f
e
s,
A
b
d
e
lo
u
a
h
i
d
De
rh
a
b
,
Ya
c
in
e
Ch
a
ll
a
l,
“
A
re
v
ie
w
o
f
p
riv
a
c
y
-
p
re
s
e
rv
in
g
te
c
h
n
iq
u
e
s
f
o
r
d
e
e
p
lea
rn
in
g
,
”
Ne
u
ro
c
o
mp
u
ti
n
g
,
v
o
l.
3
8
4
,
p
p
.
2
1
-
4
5
,
2
0
2
0
.
[2
]
Kriz
h
e
v
sk
y
,
A
.
,
S
u
tsk
e
v
e
r,
I.
a
n
d
Hin
to
n
,
G
.
E.,
“
Im
a
g
e
n
e
t
c
las
si
f
ic
a
ti
o
n
w
it
h
d
e
e
p
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
s,”
Ad
v
a
n
c
e
s i
n
n
e
u
r
a
l
i
n
f
o
rm
a
ti
o
n
p
r
o
c
e
ss
in
g
sy
ste
ms
,
p
p
.
1
0
9
7
-
1
1
0
5
,
2
0
1
2
.
[3
]
De
n
g
,
J.,
Do
n
g
,
W
.
,
S
o
c
h
e
r,
R.
,
L
i,
L
.
J.,
L
i,
K.
a
n
d
F
e
i
-
F
e
i,
L
.
,
“
Im
a
g
e
n
e
t:
A
larg
e
-
sc
a
le
h
ier
a
rc
h
ica
l
ima
g
e
d
a
tab
a
se
.
,
”
IEE
E
c
o
n
fer
e
n
c
e
o
n
c
o
mp
u
ter
v
isi
o
n
a
n
d
p
a
tt
e
rn
re
c
o
g
n
it
io
n
,
p
p
.
2
4
8
-
2
5
5
,
2
0
0
9
.
[4
]
V
iere
c
k
,
U.,
P
a
s,
A
.
T
.
,
S
a
e
n
k
o
,
K.
a
n
d
P
latt,
R.
,
“
L
e
a
rn
in
g
a
v
isu
o
m
o
to
r
c
o
n
tr
o
ll
e
r
f
o
r
re
a
l
w
o
rld
ro
b
o
ti
c
g
ra
sp
in
g
u
sin
g
sim
u
lat
e
d
d
e
p
t
h
im
a
g
e
s,”
a
rXiv p
re
p
rin
t
a
rXiv:1
7
0
6
.
0
4
6
5
2
,
2
0
1
7
.
[5
]
P
i
n
z
ó
n
-
A
re
n
a
s
Ja
v
ier
Orla
n
d
o
,
J
i
m
é
n
e
z
-
M
o
re
n
o
R
o
b
in
so
n
,
“
C
o
m
p
a
riso
n
b
e
tw
e
e
n
h
a
n
d
w
rit
ten
w
o
rd
a
n
d
s
p
e
e
c
h
re
c
o
rd
in
re
a
l
-
ti
m
e
u
sin
g
CNN
A
rc
h
it
e
c
tu
re
s
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
Co
m
p
u
t
e
r
En
g
in
e
e
ri
n
g
(
IJ
ECE
)
,
v
o
l.
1
0
,
n
o
.
4
,
p
p
.
4
3
1
3
-
4
3
2
1
,
2
0
2
0
.
[6
]
Ya
n
m
iao
L
i,
e
t
a
l.
,
“
Ro
b
u
st
d
e
tec
ti
o
n
f
o
r
n
e
tw
o
rk
in
tru
sio
n
o
f
in
d
u
strial
Io
T
b
a
se
d
o
n
m
u
lt
i
-
CNN
f
u
sio
n
,”
M
e
a
su
re
me
n
t,
v
o
l.
1
5
4
,
2
0
2
0
.
[7
]
Jim
é
n
e
z
-
M
o
re
n
o
R.
,
a
n
d
P
in
z
ó
n
-
A
re
n
a
s
J.
Orla
n
d
o
,
“
Ob
jec
t
so
rti
n
g
in
a
n
e
x
ten
d
e
d
w
o
rk
a
re
a
u
sin
g
c
o
ll
a
b
o
ra
ti
v
e
ro
b
o
ti
c
s a
n
d
DA
G
-
CNN
,”
AR
PN
J
o
u
rn
a
l
o
f
E
n
g
i
n
e
e
rin
g
a
n
d
A
p
p
l
i
e
d
S
c
ien
c
e
s
,
v
o
l.
1
5
,
no
.
2
,
p
p
.
1
9
2
-
2
0
2
,
2
0
2
0
.
[8
]
G
irsh
ick
,
R.
,
e
t
a
l.
,
“
Rich
f
e
a
tu
re
h
iera
rc
h
ies
f
o
r
a
c
c
u
ra
te o
b
jec
t
d
e
tec
ti
o
n
a
n
d
se
m
a
n
ti
c
se
g
m
e
n
tatio
n
,
”
Pro
c
e
e
d
in
g
s
o
f
t
h
e
IEE
E
c
o
n
fer
e
n
c
e
o
n
c
o
mp
u
ter
v
isio
n
a
n
d
p
a
t
ter
n
re
c
o
g
n
it
io
n
.
,
p
p
.
5
8
0
-
5
8
7
,
2
0
1
4
.
[9
]
G
irsh
ick
,
R.
,
“
F
a
st
R
-
CNN
,
”
Pro
c
e
e
d
in
g
s
o
f
t
h
e
IEE
E
in
ter
n
a
ti
o
n
a
l
c
o
n
fer
e
n
c
e
o
n
c
o
mp
u
ter
v
isio
n
,
p
p
.
1
4
4
0
-
1
4
4
8
,
2
0
1
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
Ob
ject
g
r
ip
p
in
g
a
l
g
o
r
ith
m
fo
r
r
o
b
o
tic
a
s
s
is
ta
n
ce
b
y
mea
n
s
o
f
d
ee
p
lea
n
in
g
(
R
o
b
in
s
o
n
Jimé
n
ez
-
Mo
r
en
o
)
6299
[1
0
]
Re
d
m
o
n
,
J.,
Div
v
a
la,
S
.
,
G
irs
h
ick
,
R.
a
n
d
F
a
rh
a
d
i
,
A
.
,
“
Yo
u
o
n
ly
lo
o
k
o
n
c
e
:
Un
if
i
e
d
,
re
a
l
-
ti
m
e
o
b
jec
t
d
e
tec
ti
o
n
,
”
Pro
c
e
e
d
in
g
s
o
f
t
h
e
IEE
E
c
o
n
fer
e
n
c
e
o
n
c
o
mp
u
ter
v
isio
n
a
n
d
p
a
t
ter
n
re
c
o
g
n
i
ti
o
n
,
p
p
.
7
7
9
-
7
8
8
,
2
0
1
6
.
[1
1
]
Re
n
,
S
.
,
He
,
K.
,
G
irsh
ick
,
R.
a
n
d
S
u
n
,
J.,
“
F
a
ste
r
R
-
CNN
:
T
o
w
a
rd
s
re
a
l
-
ti
m
e
o
b
jec
t
d
e
tec
ti
o
n
w
it
h
r
e
g
io
n
p
r
o
p
o
sa
l
n
e
tw
o
rk
s,”
Ad
v
a
n
c
e
s in
n
e
u
ra
l
in
f
o
rm
a
ti
o
n
p
ro
c
e
ss
in
g
sy
ste
ms
,
p
p
.
9
1
-
9
9
,
2
0
1
5
.
[1
2
]
F
a
n
,
Q.,
Bro
w
n
,
L
.
a
n
d
S
m
it
h
,
J.,
“
A
c
lo
se
r
lo
o
k
a
t
F
a
ste
r
R
-
CNN
f
o
r
v
e
h
icle
d
e
tec
ti
o
n
,
”
IEE
E
in
tel
li
g
e
n
t
v
e
h
icle
s
sy
m
p
o
siu
m (
IV)
,
p
p
.
1
2
4
-
1
2
9
,
2
0
1
6
.
[1
3
]
L
e
e
,
J.,
Wan
g
,
J.,
Cra
n
d
a
ll
,
D.,
Š
a
b
a
n
o
v
ić,
S
.
a
n
d
F
o
x
,
G
.
,
“
Re
a
l
-
t
im
e
,
c
lo
u
d
-
b
a
se
d
o
b
jec
t
d
e
tec
ti
o
n
f
o
r
u
n
m
a
n
n
e
d
a
e
rial
v
e
h
icle
s,”
Fi
rs
t
IEE
E
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
R
o
b
o
ti
c
Co
mp
u
t
in
g
(
IRC),
p
p
.
3
6
-
4
3
,
2
0
1
7
.
[1
4
]
W
a
tso
n
,
J.,
Hu
g
h
e
s,
J.
a
n
d
Iid
a
,
F
.
,
“
Re
a
l
-
w
o
rld
,
re
a
l
-
ti
m
e
ro
b
o
ti
c
g
ra
sp
in
g
w
it
h
c
o
n
v
o
lu
t
io
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
s,”
A
n
n
u
a
l
Co
n
fer
e
n
c
e
T
o
wa
r
d
s A
u
to
n
o
mo
u
s R
o
b
o
ti
c
S
y
st
e
ms
,
p
p
.
6
1
7
-
6
2
6
,
2
0
1
7
.
[1
5
]
Zen
g
,
A
.
,
S
o
n
g
,
S
.
,
L
e
e
,
J.,
Ro
d
ri
g
u
e
z
,
A
.
a
n
d
F
u
n
k
h
o
u
se
r,
T
.
,
“
To
ss
in
g
Bo
t:
L
e
a
rn
in
g
t
o
T
h
ro
w
A
r
b
it
ra
ry
Ob
jec
ts
w
it
h
Re
sid
u
a
l
P
h
y
sic
s,”
IEE
E
T
ra
n
sa
c
ti
o
n
s o
n
R
o
b
o
ti
c
s
,
2
0
1
9
.
[1
6
]
X
i
C
h
e
n
,
Ja
n
G
u
h
l
,
“
In
d
u
strial
R
o
b
o
t
Co
n
tro
l
w
it
h
Ob
jec
t
Re
c
o
g
n
it
io
n
b
a
se
d
o
n
De
e
p
L
e
a
rn
in
g
,
”
Pro
c
e
d
ia
CIR
P,
v
o
l.
7
6
,
p
p
.
1
4
9
-
1
5
4
,
2
0
1
8
.
[1
7
]
En
ric
Co
r
o
n
a
,
G
u
il
lem
A
len
y
à
,
A
n
to
n
io
G
a
b
a
s,
Ca
r
m
e
T
o
rra
s,
“
A
c
ti
v
e
g
a
r
m
e
n
t
re
c
o
g
n
it
io
n
a
n
d
targ
e
t
g
r
a
sp
in
g
p
o
i
n
t
d
e
tec
ti
o
n
u
sin
g
d
e
e
p
lea
rn
i
n
g
,
”
Pa
tt
e
rn
Rec
o
g
n
it
io
n
,
v
o
l.
7
4
,
p
p
.
6
2
9
-
6
4
1
,
2
0
1
8
.
[1
8
]
Zi
to
n
g
L
iu
,
e
t
a
l.
,
“
De
e
p
L
e
a
rn
in
g
-
b
a
se
d
Hu
m
a
n
M
o
ti
o
n
P
re
d
ictio
n
c
o
n
si
d
e
rin
g
C
o
n
tex
t
A
wa
re
n
e
ss
f
o
r
Hu
m
a
n
-
Ro
b
o
t
Co
ll
a
b
o
ra
ti
o
n
in
M
a
n
u
f
a
c
t
u
rin
g
,
”
Pro
c
e
d
i
a
CIR
P,
v
o
l.
8
3
,
p
p
.
2
7
2
-
2
7
8
,
2
0
1
9
.
[1
9
]
J.
R
e
d
m
o
n
a
n
d
A
.
A
n
g
e
lo
v
a
,
"
Re
a
l
-
ti
m
e
g
ra
sp
d
e
tec
ti
o
n
u
sin
g
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
s,"
IEE
E
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Ro
b
o
ti
c
s a
n
d
A
u
t
o
ma
ti
o
n
(
ICRA
),
p
p
.
1
3
1
6
-
1
3
2
2
,
2
0
1
5
.
[2
0
]
Zh
ich
a
o
W
a
n
g
,
Zh
i
q
i
L
i,
Bin
W
a
n
g
,
Ho
n
g
L
iu
.
,
“
Ro
b
o
t
g
ra
sp
d
e
tec
ti
o
n
u
sin
g
m
u
lt
im
o
d
a
l
d
e
e
p
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
s,”
Ad
v
a
n
c
e
s i
n
M
e
c
h
a
n
ica
l
En
g
i
n
e
e
rin
g
,
v
o
l.
8
,
n
o
.
9
,
2
0
1
6
.
[2
1
]
G
a
ri
m
a
De
v
n
a
n
i,
e
t
a
l.
,
“
P
e
rf
o
r
m
a
n
c
e
Ev
a
lu
a
ti
o
n
o
f
F
in
e
-
t
u
n
e
d
F
a
ste
r
R
-
CNN
o
n
sp
e
c
if
ic
M
S
C
OCO
Ob
jec
ts,”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
E
lec
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
9
,
n
o
.
4
,
p
p
.
2
5
4
8
-
2
5
5
5
,
2
0
1
9
.
[2
2
]
Z.
W
a
n
g
,
Z.
L
i,
B.
W
a
n
g
,
H.
L
iu
,
“
Ro
b
o
t
g
ra
sp
d
e
tec
ti
o
n
u
si
n
g
m
u
lt
im
o
d
a
l
d
e
e
p
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
s,
”
Ad
v
a
n
c
e
s i
n
M
e
c
h
a
n
ic
a
l
E
n
g
i
n
e
e
rin
g
,
v
o
l.
8
,
n
o
9
,
2
0
1
6
.
[2
3
]
G
.
G
h
a
z
a
e
i,
e
t
a
l.
,
"
A
n
e
x
p
lo
ra
to
ry
stu
d
y
o
n
th
e
u
se
o
f
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
s
f
o
r
o
b
jec
t
g
ra
sp
c
las
si
f
ica
ti
o
n
,
"
2
n
d
IET
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
I
n
tell
ig
e
n
t
S
i
g
n
a
l
Pro
c
e
ss
in
g
(
IS
P),
p
p
.
1
-
5
,
2
0
1
5
.
[2
4
]
Jim
é
n
e
z
-
M
o
re
n
o
Ro
b
i
n
so
n
,
P
i
n
z
ó
n
-
A
re
n
a
s
Ja
v
ier
Orla
n
d
o
,
“
Ne
w
H
y
b
rid
F
u
z
z
y
-
CNN
A
rc
h
it
e
c
t
u
re
f
o
r
Hu
m
a
n
-
Ro
b
o
t
In
tera
c
ti
o
n
,
”
IREA
CO,
v
o
l
.
1
2
,
n
o
.
5
,
2
0
1
9
.
[2
5
]
P
i
n
z
ó
n
-
A
re
n
a
s
J.
Orla
n
d
o
,
e
t
a
l.
,
“
As
sist
a
n
t
ro
b
o
t
t
h
ro
u
g
h
d
e
e
p
le
a
rn
in
g
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
Co
mp
u
ter
E
n
g
in
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
1
0
,
n
o
.
1
,
p
p
.
1
0
5
3
-
1
0
6
2
,
2
0
2
0
.
[2
6
]
S
im
o
n
y
a
n
,
K.
a
n
d
Zi
ss
e
r
m
a
n
,
A
.
,
“
V
e
r
y
d
e
e
p
c
o
n
v
o
lu
ti
o
n
a
l
n
e
tw
o
rk
s
f
o
r
lar
g
e
-
sc
a
le
i
m
a
g
e
re
c
o
g
n
it
io
n
,
”
a
rXiv p
re
p
ri
n
t
a
rX
iv:1
4
0
9
.
1
5
5
6
,
2
0
1
4
.
[2
7
]
No
g
u
e
ira,
L
.
,
“
Co
m
p
a
ra
ti
v
e
a
n
a
l
y
sis
b
e
twe
e
n
g
a
z
e
b
o
a
n
d
v
-
r
e
p
ro
b
o
ti
c
sim
u
lato
rs,”
S
e
min
a
rio
In
ter
n
o
d
e
Co
g
n
ica
o
Arti
fi
c
i
a
l
-
S
ICA
,
2
0
1
4
.
[2
8
]
T
a
i,
L
.
,
P
a
o
lo
,
G
.
a
n
d
L
iu
,
M
.
,
“
V
irt
u
a
l
-
to
-
re
a
l
d
e
e
p
re
in
f
o
rc
e
m
e
n
t
lea
rn
i
n
g
:
Co
n
ti
n
u
o
u
s
c
o
n
tro
l
o
f
m
o
b
il
e
ro
b
o
ts
f
o
r
m
a
p
les
s n
a
v
ig
a
ti
o
n
,
”
IEE
E/
RS
J
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
I
n
t
e
ll
i
g
e
n
t
R
o
b
o
ts
a
n
d
S
y
ste
ms
,
p
p
.
31
-
36
,
2
0
1
7
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Ro
b
i
n
s
o
n
J
i
m
é
n
e
z
M
o
r
e
n
o
w
a
s
b
o
rn
i
n
Bo
g
o
tá,
Co
l
o
m
b
ia,
in
1
9
7
8
.
He
re
c
e
iv
e
d
th
e
En
g
in
e
e
r
d
e
g
re
e
in
El
e
c
tro
n
ics
a
t
th
e
F
ra
n
c
isc
o
Jo
sé
d
e
Ca
ld
a
s
District
Un
iv
e
rsit
y
-
U
D
-
in
2
0
0
2
,
re
sp
e
c
ti
v
e
l
y
.
M
.
S
c
.
in
In
d
u
strial
A
u
to
m
a
ti
o
n
f
ro
m
th
e
Un
iv
e
rsid
a
d
Na
c
io
n
a
l
d
e
Co
l
o
m
b
ia
-
2
0
1
2
a
n
d
P
h
D
in
E
n
g
in
e
e
rin
g
a
t
th
e
F
ra
n
c
isc
o
Jo
sé
d
e
Ca
ld
a
s
District
Un
iv
e
rsit
y
-
UD
.
He
is
c
u
rre
n
tl
y
w
o
rk
in
g
a
s
a
P
ro
f
e
ss
o
r
in
th
e
M
e
c
h
a
tro
n
ics
En
g
in
e
e
rin
g
P
ro
g
ra
m
a
t
th
e
Nu
e
v
a
G
ra
n
a
d
a
M
il
it
a
r
y
Un
iv
e
rsit
y
-
UMNG
.
He
h
a
s
e
x
p
e
rien
c
e
in
t
h
e
a
re
a
s
o
f
In
stru
m
e
n
tatio
n
a
n
d
El
e
c
tro
n
ic
Co
n
tro
l
,
a
c
ti
n
g
m
a
in
ly
in
:
Ro
b
o
ti
c
s,
c
o
n
tro
l,
p
a
tt
e
rn
re
c
o
g
n
it
i
o
n
a
n
d
im
a
g
e
p
ro
c
e
ss
in
g
.
Rub
ia
n
o
As
t
r
id
,
Bo
g
o
tá
Co
lo
m
b
ia,
P
h
D.
d
e
g
re
e
in
m
e
c
h
a
tro
n
ic
s,
e
sp
e
c
ialit
y
in
c
o
n
tro
l
o
f
so
f
t
ro
b
o
ti
c
s,
Na
n
terre
Un
iv
e
rsit
y
,
P
a
ris,
F
ra
n
c
e
,
2
0
1
6
.
M
.
S
c
.
d
e
g
re
e
e
sp
e
c
ialit
y
in
a
u
to
m
a
ti
c
s
c
o
n
tro
l
s
y
ste
m
s,
T
e
c
n
o
lo
g
ic
Un
iv
e
rsit
y
o
f
P
e
re
ira,
2
0
1
2
,
Ba
c
h
e
lo
r
d
e
g
re
e
in
M
e
c
h
a
tr
o
n
ic
E
n
g
in
e
e
rin
g
,
Nu
e
v
a
G
ra
n
a
d
a
Un
iv
e
rsit
y
,
2
0
0
6
.
S
h
e
h
a
s
p
u
b
li
c
a
ti
o
n
s
re
late
d
to
f
e
a
tu
re
s
e
x
tra
c
ti
o
n
f
ro
m
e
lec
tro
m
y
o
g
ra
p
h
ic
sig
n
a
ls,
c
o
n
tr
o
l
o
f
so
f
t
stru
c
tu
re
s,
i
m
a
g
e
s
p
ro
c
e
ss
in
g
to
w
a
rd
c
o
n
tro
l
s
y
ste
m
s
.
S
h
e
h
a
s
2
0
p
a
ten
ts
in
tec
h
n
o
l
o
g
y
f
ield
,
su
c
h
m
e
c
h
a
tro
n
ics
sy
ste
m
s
a
p
p
li
e
d
to
m
e
d
icin
e
.
Cu
rre
n
t
ly
,
sh
e
is i
n
tere
ste
d
i
n
c
o
n
tro
l
b
a
se
d
o
n
e
lec
tro
m
y
o
g
ra
p
h
ic sig
n
a
ls an
d
c
o
n
tr
o
l
o
f
so
f
t
b
o
d
ies
a
p
p
l
ied
t
o
ro
b
o
ti
c
.
Ra
m
ir
e
z
J
o
se
L
u
is
,
Bo
g
o
tá
Co
lo
m
b
ia,
P
h
D.
d
e
g
re
e
in
m
e
c
h
a
n
ics
,
e
sp
e
c
ialit
y
in
a
rti
f
icia
l
m
u
s
c
les
b
a
se
d
o
n
sm
a
rt
m
a
teria
ls,
Na
n
te
rre
Un
iv
e
rsit
y
,
P
a
ris,
F
ra
n
c
e
,
2
0
1
6
.
M
.
S
c
.
d
e
g
re
e
e
sp
e
c
ialit
y
in
a
u
to
m
a
ti
c
s
c
o
n
tro
l
sy
s
te
m
s,
Tec
n
o
lo
g
ic
Un
iv
e
rsit
y
o
f
P
e
re
ira,
2
0
1
2
,
Ba
c
h
e
lo
r
d
e
g
re
e
in
M
e
c
h
a
tro
n
ic
E
n
g
in
e
e
rin
g
,
N
u
e
v
a
G
ra
n
a
d
a
Un
iv
e
rsit
y
,
2
0
0
6
.
He
h
a
s
p
u
b
li
c
a
ti
o
n
s
re
late
d
t
o
a
rti
f
icia
l
m
u
s
c
les
,
m
o
d
e
li
n
g
o
f
s
m
a
rt
m
a
t
e
rials,
c
o
n
tro
l
o
f
sh
a
p
e
m
e
m
o
r
y
a
ll
o
y
s,
in
a
m
o
n
g
o
th
e
rs.
Cu
rre
n
tl
y
,
h
e
is
in
tere
s
ted
i
n
s
m
a
rt
m
a
teria
l
a
p
p
li
e
d
to
so
f
t
ro
b
o
ti
c
s,
d
y
n
a
m
ic
o
f
so
f
t
ro
b
o
ts,
m
o
d
e
li
n
g
o
f
s
m
a
rt
stru
c
tu
re
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.