I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
15
,
No
.
4
,
A
u
g
u
s
t 2
0
2
6
,
p
p
.
3
3
5
2
~
3
3
6
4
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
4
.
p
p
3
3
5
2
-
3
3
6
4
3352
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Intellig
ent
objec
t
so
rting sy
stem usi
ng
Do
bo
t
M
a
g
icia
n
a
nd
co
mputer vis
io
n
T
o
s
s
a
po
l J
a
ng
no
i
1
,
T
hewi
n S
a
k
un
bu
ny
o
ng
2
,
Viro
ch
Su
k
o
nta
na
k
a
rn
2
,
T
a
na
wa
t
Cha
la
rds
a
k
ul
2
1
D
e
p
a
r
t
me
n
t
o
f
M
e
c
h
a
n
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
E
n
g
i
n
e
e
r
i
n
g
,
R
a
j
a
ma
n
g
a
l
a
U
n
i
v
e
r
si
t
y
o
f
Te
c
h
n
o
l
o
g
y
I
san
,
K
h
o
n
K
a
e
n
,
Th
a
i
l
a
n
d
2
D
e
p
a
r
t
me
n
t
o
f
M
e
c
h
a
t
r
o
n
i
c
s E
n
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
En
g
i
n
e
e
r
i
n
g
,
R
a
j
a
m
a
n
g
a
l
a
U
n
i
v
e
r
si
t
y
o
f
Te
c
h
n
o
l
o
g
y
I
san
,
K
h
o
n
K
a
e
n
,
T
h
a
i
l
a
n
d
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Au
g
5
,
2
0
2
5
R
ev
is
ed
Ma
y
1
3
,
2
0
2
6
Acc
ep
ted
Ma
y
2
4
,
2
0
2
6
Th
is
stu
d
y
a
ims
to
a
n
a
l
y
z
e
th
e
re
latio
n
sh
ip
b
e
twe
e
n
o
b
jec
t
c
o
l
o
r,
s
h
a
p
e
,
a
n
d
c
o
u
n
t
a
n
d
th
e
p
e
rfo
rm
a
n
c
e
o
f
a
r
o
b
o
ti
c
o
b
jec
t
so
rt
in
g
sy
ste
m
,
m
e
a
su
re
d
b
y
e
x
e
c
u
ti
o
n
ti
m
e
a
n
d
a
c
c
u
ra
c
y
.
Th
e
Do
b
o
t
M
a
g
icia
n
r
o
b
o
t
wa
s
u
se
d
fo
r
o
b
jec
t
m
a
n
ip
u
lati
o
n
,
w
h
il
e
c
o
m
p
u
ter
v
isio
n
b
a
se
d
o
n
o
b
jec
t
d
e
tec
ti
o
n
wa
s
imp
lem
e
n
ted
u
sin
g
P
y
t
h
o
n
a
n
d
a
n
o
p
e
n
s
o
u
rc
e
c
o
m
p
u
ter
v
isi
o
n
li
b
ra
ry
(
Op
e
n
CV
)
.
C
o
lo
r
a
n
d
sh
a
p
e
se
g
m
e
n
tatio
n
we
re
p
e
rfo
rm
e
d
u
sin
g
th
e
h
u
e
,
sa
tu
ra
ti
o
n
,
a
n
d
v
a
l
u
e
(
HSV
)
c
o
l
o
r
sp
a
c
e
a
n
d
Op
e
n
CV
li
b
ra
ry
.
Ex
p
e
rime
n
tal
re
su
lt
s
in
d
ica
te
th
a
t
t
h
re
e
sh
a
p
e
s
(
c
ircle
,
tri
a
n
g
le,
a
n
d
s
q
u
a
re
)
a
n
d
f
o
u
r
c
o
lo
rs
(g
re
e
n
,
re
d
,
b
l
u
e
,
a
n
d
y
e
ll
o
w)
a
f
fe
c
t
p
ick
in
g
ti
m
e
a
n
d
a
c
c
u
ra
c
y
d
iffere
n
tl
y
.
S
q
u
a
re
s
g
e
n
e
ra
ll
y
re
q
u
ired
t
h
e
lo
n
g
e
st
ti
m
e
t
o
p
ick
,
wh
i
le
tri
a
n
g
les
o
ften
h
a
d
th
e
sh
o
r
tes
t
ti
m
e
s
a
c
ro
ss
v
a
rio
u
s
c
o
lo
rs.
Ac
c
u
ra
c
y
re
m
a
in
e
d
c
o
n
siste
n
tl
y
h
ig
h
a
c
ro
ss
a
ll
c
o
lo
rs
a
n
d
sh
a
p
e
s,
with
g
re
e
n
a
n
d
y
e
ll
o
w
o
b
jec
t
s
sh
o
win
g
slig
h
tl
y
h
ig
h
e
r
a
v
e
ra
g
e
a
c
c
u
ra
c
y
.
Th
e
se
fin
d
i
n
g
s
p
ro
v
id
e
v
a
lu
a
b
l
e
in
sig
h
ts
in
to
t
h
e
fa
c
to
rs
in
fl
u
e
n
c
in
g
th
e
p
e
rfo
rm
a
n
c
e
o
f
a
u
to
m
a
ted
r
o
b
o
ti
c
g
ra
sp
i
n
g
sy
ste
m
s,
wh
ich
c
a
n
b
e
a
p
p
li
e
d
t
o
o
p
ti
m
ize
r
o
b
o
t
d
e
sig
n
a
n
d
imp
ro
v
e
th
e
e
fficie
n
c
y
a
n
d
p
re
c
isio
n
o
f
o
b
jec
t
so
rti
n
g
tas
k
s.
K
ey
w
o
r
d
s
:
C
o
m
p
u
ter
v
is
io
n
Do
b
o
t
M
ag
ician
Ob
ject
s
o
r
tin
g
Op
en
C
V
lib
r
ar
y
Py
th
o
n
p
r
o
g
r
a
m
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
:
T
h
ewin
Sak
u
n
b
u
n
y
o
n
g
Dep
ar
tm
en
t
o
f
Me
ch
atr
o
n
ics E
n
g
in
ee
r
in
g
,
Facu
lty
o
f
E
n
g
in
ee
r
in
g
R
ajam
an
g
ala
Un
iv
er
s
ity
o
f
T
e
ch
n
o
lo
g
y
I
s
an
Kh
o
n
Kae
n
,
T
h
ailan
d
E
m
ail:
th
ewin
.
s
a@
r
m
u
ti.a
c.
th
1.
I
NT
RO
D
UCT
I
O
N
I
n
m
o
d
er
n
in
d
u
s
tr
ial
au
to
m
at
io
n
,
o
b
ject
s
o
r
tin
g
s
y
s
tem
s
[
1
]
,
[
2
]
p
lay
a
cr
u
cial
r
o
le
in
en
h
a
n
cin
g
p
r
o
d
u
ctiv
ity
,
ac
cu
r
ac
y
,
an
d
e
f
f
icien
cy
.
T
r
a
d
itio
n
al
s
o
r
tin
g
m
eth
o
d
s
r
ely
h
ea
v
ily
o
n
p
r
e
-
d
ef
in
ed
r
u
les
an
d
h
an
d
cr
a
f
ted
f
ea
tu
r
es,
wh
ich
o
f
ten
f
ail
to
g
en
er
alize
in
d
y
n
a
m
ic
o
r
co
m
p
lex
en
v
ir
o
n
m
en
ts
.
T
o
ad
d
r
ess
th
ese
lim
itatio
n
s
,
ar
tific
ial
in
tellig
en
ce
(
AI
)
—
p
a
r
ticu
lar
ly
d
ee
p
lear
n
in
g
—
h
as
em
e
r
g
ed
as
a
p
o
wer
f
u
l
s
o
lu
tio
n
,
en
ab
lin
g
m
ac
h
in
es
to
p
er
ce
iv
e
an
d
class
if
y
o
b
jects
m
o
r
e
ef
f
ec
tiv
ely
.
T
h
is
r
esear
ch
p
r
ese
n
ts
a
d
ee
p
lear
n
in
g
-
b
ased
ap
p
r
o
ac
h
[
3
]
,
[
4
]
f
o
r
o
b
ject
s
o
r
tin
g
u
s
in
g
a
r
o
b
o
ti
c
ar
m
,
with
a
s
p
ec
if
ic
f
o
c
u
s
o
n
id
en
tify
i
n
g
a
n
d
class
if
y
in
g
o
b
jects
b
ased
o
n
t
h
eir
s
h
ap
e
an
d
co
lo
r
[
5
]
–
[
7
]
.
T
h
e
s
y
s
tem
ex
tr
ac
ts
m
ea
n
in
g
f
u
l
v
is
u
al
f
ea
tu
r
es
f
r
o
m
ca
p
tu
r
ed
im
ag
es,
allo
win
g
f
o
r
r
o
b
u
s
t
o
b
ject
r
ec
o
g
n
itio
n
u
n
d
er
v
a
r
y
in
g
co
n
d
itio
n
s
.
T
h
e
class
if
ied
in
f
o
r
m
atio
n
is
th
e
n
u
s
ed
to
g
u
id
e
t
h
e
r
o
b
o
tic
ar
m
f
o
r
ac
cu
r
ate
an
d
e
f
f
icien
t
s
o
r
ti
n
g
.
T
h
e
in
teg
r
atio
n
o
f
co
m
p
u
ter
v
is
io
n
a
n
d
r
o
b
o
tic
m
an
ip
u
latio
n
o
f
f
e
r
s
s
ig
n
if
ica
n
t
p
o
ten
tial
f
o
r
a
p
p
licatio
n
s
i
n
p
ac
k
a
g
in
g
,
waste
m
an
ag
em
en
t,
m
an
u
f
ac
tu
r
in
g
,
an
d
lo
g
is
tics
[
8
]
–
[
1
0
]
.
T
h
is
s
tu
d
y
aim
s
to
d
esig
n
,
d
ev
el
o
p
,
an
d
ev
al
u
ate
a
p
r
o
to
ty
p
e
s
y
s
tem
th
at
d
em
o
n
s
tr
ates
th
e
f
ea
s
ib
ilit
y
an
d
p
er
f
o
r
m
an
ce
o
f
s
u
c
h
in
teg
r
atio
n
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
tem
n
o
t
o
n
ly
au
to
m
ates
th
e
s
o
r
tin
g
p
r
o
ce
s
s
b
u
t
also
im
p
r
o
v
es
ad
ap
tab
ilit
y
an
d
s
ca
lab
ilit
y
co
m
p
ar
ed
to
r
u
le
-
b
ased
o
r
s
en
s
o
r
-
o
n
ly
ap
p
r
o
ac
h
es
.
T
h
e
k
e
y
co
n
tr
ib
u
tio
n
s
o
f
th
is
wo
r
k
in
cl
u
d
e
t
h
e
d
esig
n
o
f
a
v
is
io
n
-
b
ased
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
I
n
tellig
en
t o
b
ject
s
o
r
tin
g
s
ystem
u
s
in
g
Do
b
o
t m
a
g
icia
n
a
n
d
co
mp
u
ter visi
o
n
(
To
s
s
a
p
o
l J
a
n
g
n
o
i)
3353
class
if
icatio
n
m
o
d
el,
th
e
im
p
lem
en
tatio
n
o
f
an
o
b
ject
-
s
o
r
tin
g
m
ec
h
a
n
is
m
u
s
in
g
a
r
o
b
o
tic
ar
m
[
1
1
]
–
[
1
3
]
,
an
d
th
e
ev
alu
atio
n
o
f
th
e
s
y
s
tem
’
s
p
er
f
o
r
m
an
ce
in
r
ea
l
-
tim
e
s
o
r
ti
n
g
task
s
.
Ob
ject
d
etec
tio
n
is
a
co
n
tin
u
o
u
s
ly
s
tu
d
ied
r
esear
ch
t
o
p
ic
in
th
e
f
ield
o
f
co
m
p
u
ter
v
is
io
n
,
aim
in
g
to
id
en
tify
a
n
d
class
if
y
o
b
jects
a
cr
o
s
s
s
eq
u
en
ce
s
o
f
f
r
am
es
.
De
tectin
g
o
b
jects
in
v
id
eo
s
eq
u
e
n
ce
s
is
p
ar
ticu
lar
ly
ch
allen
g
in
g
an
d
o
f
ten
r
eq
u
ir
e
s
s
ig
n
if
ican
t
p
r
o
ce
s
s
in
g
tim
e
.
Ob
ject
d
etec
tio
n
is
g
e
n
er
ally
co
n
s
id
er
ed
t
h
e
f
ir
s
t
s
tep
in
b
u
ild
in
g
m
o
r
e
co
m
p
l
ex
co
m
p
u
te
r
v
is
io
n
s
y
s
tem
s
[
1
4
]
,
[
1
5
]
.
E
ac
h
o
b
ject
p
o
s
s
ess
es
s
ev
er
al
g
lo
b
al
f
ea
tu
r
es,
s
u
ch
as
co
lo
r
an
d
s
h
ap
e,
wh
ich
ca
n
b
e
u
s
ed
to
d
es
cr
ib
e
its
o
v
e
r
all
ch
ar
ac
ter
is
tic
s
.
Dete
ctin
g
o
b
ject
s
h
ap
es
an
d
co
lo
r
s
[
1
6
]
–
[
1
8
]
is
a
f
u
n
d
am
en
tal
task
in
co
m
p
u
t
er
v
is
io
n
.
T
h
is
task
is
ty
p
icall
y
ap
p
r
o
ac
h
ed
u
s
in
g
tr
ad
itio
n
al
m
eth
o
d
s
with
o
p
e
n
s
o
u
r
ce
c
o
m
p
u
ter
v
is
io
n
lib
r
ar
y
(
O
p
en
C
V)
,
d
ee
p
lear
n
in
g
m
o
d
els
s
u
ch
as
co
n
v
o
l
u
tio
n
al
n
eu
r
al
n
etwo
r
k
s
(
C
NNs
)
,
o
b
ject
d
etec
to
r
s
lik
e
y
o
u
o
n
l
y
lo
o
k
o
n
ce
(
YOL
O)
,
s
in
g
le
s
h
o
t
d
etec
to
r
(
SS
D)
,
a
n
d
f
aster
r
e
g
io
n
-
b
ased
co
n
v
o
lu
tio
n
al
n
e
u
r
al
n
etwo
r
k
(
F
aster
R
-
C
NN)
,
as
well
as
h
y
b
r
id
tech
n
iq
u
es
th
at
co
m
b
i
n
e
tr
ad
i
tio
n
al
an
d
d
ee
p
lear
n
in
g
a
p
p
r
o
ac
h
es
.
Ad
d
itio
n
ally
,
s
p
ec
ialized
to
o
ls
s
u
ch
as
Me
d
iaPip
e,
s
cik
it
-
im
ag
e,
T
en
s
o
r
Flo
w,
an
d
Py
T
o
r
ch
ar
e
o
f
te
n
em
p
l
o
y
ed
.
A
s
u
m
m
ar
y
o
f
th
e
co
m
m
o
n
m
eth
o
d
s
u
s
ed
f
o
r
d
etec
tin
g
o
b
ject
s
h
ap
e
an
d
co
l
o
r
is
p
r
esen
ted
i
n
T
ab
le
1
.
R
ec
en
t
ad
v
an
ce
s
in
d
ee
p
lear
n
in
g
h
a
v
e
s
ig
n
if
ican
tly
im
p
r
o
v
ed
th
e
p
e
r
f
o
r
m
an
ce
o
f
m
ac
h
in
e
v
is
io
n
s
y
s
tem
s
u
s
ed
in
o
b
ject
d
etec
t
io
n
an
d
class
if
icatio
n
task
s
.
C
NNs
[
1
9
]
,
[
2
0
]
h
av
e
d
em
o
n
s
tr
ated
ex
ce
p
tio
n
al
ac
cu
r
ac
y
in
im
a
g
e
class
if
icatio
n
,
m
ak
in
g
th
em
well
-
s
u
ited
f
o
r
in
d
u
s
tr
ial
ap
p
licatio
n
s
in
v
o
lv
in
g
v
is
u
al
r
ec
o
g
n
itio
n
.
Sev
e
r
al
s
tu
d
ies
h
av
e
ex
p
lo
r
ed
o
b
ject
s
o
r
tin
g
u
s
in
g
d
ee
p
lear
n
i
n
g
tech
n
iq
u
es
.
Fo
r
ex
am
p
le,
o
n
e
s
tu
d
y
d
ev
elo
p
ed
a
v
is
io
n
-
b
ased
r
o
b
o
tic
s
y
s
tem
th
at
s
o
r
ts
waste
m
ater
ials
u
s
in
g
a
C
NN
to
class
if
y
d
if
f
er
en
t
ty
p
es
o
f
p
last
ic
.
T
h
e
s
y
s
tem
ac
h
iev
ed
h
ig
h
class
if
icatio
n
ac
cu
r
ac
y
u
n
d
er
co
n
tr
o
lled
lig
h
tin
g
co
n
d
itio
n
s
.
Similar
ly
,
an
o
th
er
s
tu
d
y
im
p
lem
en
ted
a
s
o
r
tin
g
m
ec
h
a
n
is
m
f
o
r
f
r
u
its
b
ased
o
n
co
l
o
r
an
d
s
ize,
u
s
in
g
a
YOL
O
-
b
ased
m
o
d
el
f
o
r
r
ea
l
-
tim
e
d
etec
tio
n
[
2
1
]
.
I
n
te
r
m
s
o
f
r
o
b
o
tic
in
teg
r
atio
n
,
r
esear
ch
er
s
h
a
v
e
d
em
o
n
s
tr
ated
s
y
s
tem
s
wh
er
e
a
r
o
b
o
tic
ar
m
is
g
u
id
e
d
b
y
i
m
ag
e
r
ec
o
g
n
itio
n
r
esu
lts
to
m
an
ip
u
late
an
d
s
o
r
t
o
b
jects
o
n
an
ass
em
b
ly
lin
e
.
T
h
ese
s
tu
d
ies
h
ig
h
lig
h
t
th
e
im
p
o
r
tan
ce
o
f
ac
cu
r
ate
o
b
ject
lo
ca
lizatio
n
an
d
th
e
r
o
le
o
f
r
o
b
o
tic
k
in
em
atics
in
ac
h
iev
in
g
ef
f
icien
t
s
o
r
tin
g
.
Ho
wev
er
,
m
an
y
ex
is
tin
g
w
o
r
k
s
f
o
cu
s
o
n
eith
er
co
lo
r
-
b
ased
o
r
s
h
ap
e
-
b
ased
s
o
r
tin
g
in
d
ep
en
d
en
tly
.
Few
s
y
s
tem
s
co
m
b
in
e
b
o
t
h
attr
ib
u
tes
to
im
p
r
o
v
e
class
if
icatio
n
r
o
b
u
s
tn
ess
,
p
ar
t
icu
lar
ly
in
en
v
ir
o
n
m
en
ts
with
v
is
u
ally
s
im
ilar
o
b
jects
.
Mo
r
eo
v
er
,
wh
ile
s
o
m
e
s
y
s
tem
s
u
s
e
tr
ad
itio
n
al
im
ag
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
es
(
e
.
g
.
,
co
lo
r
th
r
esh
o
ld
in
g
a
n
d
co
n
to
u
r
d
etec
tio
n
)
,
th
ese
ap
p
r
o
ac
h
es a
r
e
o
f
te
n
s
en
s
itiv
e
to
n
o
is
e
an
d
less
g
en
e
r
aliza
b
le
ac
r
o
s
s
v
ar
y
in
g
co
n
d
itio
n
s
.
T
h
is
r
esear
ch
em
p
lo
y
s
a
m
et
h
o
d
f
o
r
d
etec
tin
g
th
e
s
h
a
p
e
an
d
co
l
o
r
o
f
o
b
jects,
f
o
cu
s
in
g
o
n
th
r
ee
d
is
tin
ct
s
h
ap
es
:
cir
cle,
s
q
u
ar
e,
an
d
tr
ian
g
le
.
E
ac
h
s
h
ap
e
is
av
ailab
le
in
f
o
u
r
c
o
lo
r
s
:
r
ed
,
y
ello
w,
b
lu
e,
an
d
g
r
ee
n
.
T
h
e
d
etec
tio
n
p
r
o
ce
s
s
u
tili
ze
s
th
e
Op
en
C
V
lib
r
ar
y
—
s
p
ec
if
ically
h
u
e,
s
atu
r
atio
n
,
an
d
v
alu
e
(
HSV
)
co
lo
r
s
p
ac
e
an
d
co
n
to
u
r
d
et
ec
tio
n
tech
n
i
q
u
es
[
2
2
]
—
a
p
o
wer
f
u
l
t
o
o
l
wid
el
y
u
s
ed
in
co
m
p
u
ter
v
is
io
n
ap
p
licatio
n
s
.
T
h
e
m
o
d
el
is
c
ap
ab
le
o
f
s
im
u
ltan
eo
u
s
ly
id
e
n
tify
in
g
b
o
th
t
h
e
s
h
ap
e
a
n
d
co
lo
r
o
f
o
b
jects,
en
ab
lin
g
th
e
d
e
v
elo
p
m
e
n
t
o
f
a
r
ea
l
-
tim
e
co
n
tr
o
l
s
y
s
tem
f
o
r
th
e
Do
b
o
t
Ma
g
ician
r
o
b
o
tic
ar
m
[
2
3
]
–
[
2
5
]
.
T
h
is
s
y
s
tem
s
u
p
p
o
r
ts
f
ast
an
d
ef
f
icien
t
o
b
ject
s
o
r
tin
g
u
s
in
g
ea
s
ily
ac
ce
s
s
ib
le
an
d
lo
w
-
co
s
t
r
eso
u
r
ce
s
.
Fu
r
th
er
m
o
r
e,
th
e
r
esear
ch
em
p
h
asizes
a
s
elf
-
d
ev
elo
p
ed
,
co
d
e
-
b
ased
a
p
p
r
o
ac
h
u
s
in
g
Py
th
o
n
an
d
Op
e
n
C
V,
with
o
u
t
r
ely
in
g
o
n
p
r
o
p
r
ietar
y
m
ac
h
in
e
v
is
io
n
s
o
f
twar
e
p
r
o
v
id
e
d
b
y
th
e
Do
b
o
t
Ma
g
ician
m
an
u
f
ac
tu
r
er
.
T
ab
le
2
p
r
esen
ts
a
co
m
p
ar
is
o
n
o
f
p
r
o
g
r
am
m
in
g
m
eth
o
d
s
u
s
ed
to
co
n
tr
o
l th
e
D
o
b
o
t M
ag
ician
.
T
ab
le
1
.
Su
m
m
a
r
y
o
f
m
eth
o
d
s
f
o
r
d
etec
tin
g
o
b
ject
s
h
ap
e
an
d
co
lo
r
M
e
t
h
o
d
Ea
se
o
f
u
se
A
c
c
u
r
a
c
y
B
e
st
f
o
r
O
p
e
n
C
V
(HSV)
+
c
o
n
t
o
u
r
s
)
Ea
sy
M
e
d
i
u
m
B
a
si
c
s
h
a
p
e
a
n
d
c
o
l
o
r
d
e
t
e
c
t
i
o
n
D
e
e
p
l
e
a
r
n
i
n
g
(
C
N
N
s
)
C
o
m
p
l
e
x
H
i
g
h
A
d
v
a
n
c
e
d
,
p
r
e
c
i
s
e
d
e
t
e
c
t
i
o
n
H
y
b
r
i
d
a
p
p
r
o
a
c
h
M
o
d
e
r
a
t
e
H
i
g
h
B
a
l
a
n
c
e
d
s
p
e
e
d
a
n
d
a
c
c
u
r
a
c
y
T
ab
le
2
.
Me
th
o
d
s
f
o
r
co
n
tr
o
llin
g
Do
b
o
t M
ag
ician
P
r
o
g
r
a
m
mi
n
g
U
se
t
e
a
c
h
i
n
g
U
se
v
i
si
o
n
C
o
n
t
r
o
l
l
e
d
b
y
P
y
t
h
o
n
S
u
i
t
a
b
l
e
f
o
r
P
y
t
h
o
n
o
n
l
y
No
Y
e
s
Y
e
s
A
u
t
o
ma
t
i
c
i
n
s
p
e
c
t
i
o
n
s
y
st
e
m w
i
t
h
a
c
a
mera
D
o
b
o
t
S
t
u
d
i
o
o
n
l
y
Y
e
s
No
No
Te
a
c
h
i
n
g
-
b
a
se
d
t
a
s
k
s,
ma
n
u
a
l
o
p
e
r
a
t
i
o
n
H
y
b
r
i
d
(
m
ix
)
Y
e
s
Y
e
s
Y
e
s
C
a
mer
a
-
b
a
se
d
i
n
s
p
e
c
t
i
o
n
f
o
l
l
o
w
e
d
b
y
t
e
a
c
h
i
n
g
2.
CO
NCEPT
D
E
S
I
G
N
AND
CO
NT
RO
L
T
h
e
p
r
o
p
o
s
ed
o
b
ject
-
s
o
r
tin
g
s
y
s
tem
in
teg
r
ates
a
class
if
icati
o
n
m
o
d
el
with
a
r
o
b
o
tic
ar
m
to
id
en
tify
an
d
s
o
r
t
o
b
jects
b
ased
o
n
th
e
ir
s
h
ap
e
an
d
c
o
lo
r
.
T
h
e
h
a
r
d
war
e
an
d
s
o
f
twar
e
c
o
m
p
o
n
en
ts
wo
r
k
to
g
eth
er
t
o
f
o
r
m
a
r
ea
l
-
tim
e
s
o
r
tin
g
s
y
s
tem
.
T
h
e
ar
ch
itectu
r
al
wo
r
k
f
lo
w
o
f
th
is
r
o
b
o
tic
o
b
ject
-
h
an
d
lin
g
s
y
s
tem
is
illu
s
tr
ated
in
Fig
u
r
e
1
.
T
h
e
u
s
er
in
itiates
o
r
co
n
tr
o
ls
th
e
s
o
r
ti
n
g
p
r
o
ce
s
s
v
ia
a
p
er
s
o
n
al
co
m
p
u
ter
(
PC
)
.
T
h
e
PC
r
ec
eiv
es
v
is
u
al
in
p
u
t
f
r
o
m
a
ca
m
er
a
th
at
d
etec
ts
th
e
p
o
s
itio
n
o
f
th
e
wo
r
k
p
iece
[
2
6
]
.
T
h
e
im
ag
e
is
th
en
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
4
,
Au
g
u
s
t 2
0
2
6
:
3
3
5
2
-
3
3
6
4
3354
p
r
o
ce
s
s
ed
,
an
d
co
n
tr
o
l c
o
m
m
a
n
d
s
ar
e
s
en
t to
th
e
Do
b
o
t M
ag
ician
r
o
b
o
tic
ar
m
.
B
ased
o
n
th
ese
co
m
m
an
d
s
,
th
e
D
o
b
o
t M
ag
ician
p
ick
s
u
p
t
h
e
d
etec
ted
wo
r
k
p
iece
an
d
p
lace
s
it in
to
th
e
d
esig
n
ated
wo
r
k
p
ie
ce
b
o
x
.
Fig
u
r
e
1
.
C
o
n
ce
p
t o
f
t
h
e
ar
ch
it
ec
tu
r
e
m
o
d
el
2
.
1
.
M
ec
ha
nica
l a
nd
elec
t
rica
l set
up
f
o
r
t
he
Do
bo
t
M
a
g
ic
ia
n
T
h
e
Do
b
o
t
Ma
g
ician
,
s
h
o
w
n
in
Fig
u
r
e
2
,
is
a
v
er
s
atile
d
esk
to
p
r
o
b
o
tic
ar
m
eq
u
ip
p
ed
with
s
tep
p
er
m
o
to
r
s
,
d
esig
n
e
d
to
p
er
f
o
r
m
task
s
s
u
ch
as
p
ick
-
an
d
-
p
lace
o
p
er
atio
n
s
[
2
7
]
.
I
ts
wo
r
k
i
n
g
p
r
in
cip
le
co
m
b
in
es
m
ec
h
an
ical
m
o
tio
n
c
o
n
tr
o
l,
s
e
n
s
o
r
s
,
an
d
s
o
f
twar
e
p
r
o
g
r
am
m
in
g
.
T
h
e
r
o
b
o
tic
ar
m
f
ea
tu
r
e
s
f
o
u
r
jo
in
ts
(
a
x
es
)
:
b
ase
r
o
tatio
n
,
s
h
o
u
ld
er
,
elb
o
w,
an
d
wr
is
t
r
o
tatio
n
.
E
ac
h
j
o
in
t
is
p
o
wer
ed
b
y
a
s
tep
p
er
m
o
to
r
th
at
p
r
ec
is
ely
co
n
tr
o
ls
its
an
g
le
.
B
y
co
o
r
d
i
n
atin
g
th
ese
m
o
to
r
s
,
th
e
ar
m
ca
n
m
o
v
e
its
en
d
ef
f
ec
to
r
(
to
o
l
)
to
an
y
p
o
s
itio
n
with
in
its
wo
r
k
in
g
en
v
elo
p
e
.
T
ab
le
3
p
r
esen
ts
th
e
wo
r
k
in
g
r
an
g
e
a
n
d
m
a
x
im
u
m
s
p
ee
d
o
f
ea
ch
jo
i
n
t
o
f
th
e
Do
b
o
t
Ma
g
ician
r
o
b
o
tic
ar
m
.
T
h
e
r
o
b
o
t
f
ea
tu
r
es
f
o
u
r
m
ain
jo
in
ts
:
b
ase
r
o
tatio
n
(J
1
)
,
s
h
o
u
ld
er
r
o
tatio
n
(J
2
)
,
elb
o
w
r
o
tatio
n
(J
3
)
,
an
d
wr
is
t r
o
tatio
n
(J
4
)
.
Fig
u
r
e
2
.
R
o
tatio
n
a
x
es o
f
ea
c
h
jo
in
t o
f
th
e
Do
b
o
t
M
ag
ician
r
o
b
o
tic
ar
m
T
ab
le
3
.
Ar
ea
a
n
d
s
p
ee
d
o
f
t
h
e
Do
b
o
t M
ag
ician
w
o
r
k
in
g
A
x
i
s
R
a
n
g
e
M
a
x
i
m
u
m
sp
e
e
d
B
b
a
se
r
o
t
a
t
i
o
n
(
J
1
)
-
1
3
5
°
t
o
1
3
5
°
3
2
0
°
/
s
S
h
o
u
l
d
e
r
r
o
t
a
t
i
o
n
(
J
2
)
0
°
t
o
8
5
°
3
2
0
°
/
s
El
b
o
w
r
o
t
a
t
i
o
n
(
J
3
)
-
10
°
t
o
9
5
°
3
2
0
°
/
s
W
r
i
st
r
o
t
a
t
i
o
n
(
J
4
)
90
°
t
o
-
90
°
4
8
0
°
/
s
2
.
2
.
P
r
o
ce
s
s
o
f
o
bje
ct
det
ec
t
io
n
T
h
e
s
y
s
tem
s
h
o
wn
in
Fig
u
r
e
3
b
eg
in
s
with
s
tep
1
:
in
p
u
t
d
e
v
ice
(
ca
m
er
a
/
im
ag
e
)
,
wh
e
r
e
a
ca
m
er
a
o
r
im
ag
e
in
p
u
t
d
e
v
ice
ca
p
tu
r
es
im
ag
es
o
f
th
e
o
b
jects
to
b
e
d
et
ec
ted
an
d
s
o
r
ted
.
I
n
st
ep
2
:
im
ag
e
p
r
ep
r
o
ce
s
s
in
g
,
th
e
ca
p
tu
r
ed
im
ag
es
ar
e
r
esized
an
d
f
ilter
ed
to
en
h
a
n
ce
q
u
ality
an
d
r
ed
u
ce
n
o
is
e,
p
r
e
p
ar
in
g
th
em
f
o
r
f
u
r
th
er
an
aly
s
is
.
Step
3
:
f
ea
tu
r
e
ex
t
r
a
ctio
n
in
v
o
l
v
es
ex
tr
ac
tin
g
k
ey
f
ea
tu
r
es
f
r
o
m
th
e
o
b
jects,
s
u
ch
as
co
lo
r
—
u
s
in
g
co
lo
r
s
p
ac
es
li
k
e
r
e
d
,
g
r
ee
n
,
b
lu
e
(
R
GB
)
o
r
HSV
—
an
d
s
h
ap
e,
d
etec
te
d
th
r
o
u
g
h
co
n
to
u
r
o
r
ed
g
e
d
etec
tio
n
m
eth
o
d
s
.
I
n
s
te
p
4
:
o
b
ject
d
etec
tio
n
,
th
e
s
y
s
tem
id
en
tifie
s
an
d
lo
ca
tes
th
e
o
b
jects
p
r
esen
t
in
th
e
im
ag
es
.
Du
r
in
g
st
ep
5
:
o
b
ject
class
if
ic
atio
n
,
th
e
d
etec
ted
o
b
jects
ar
e
class
if
ied
b
ased
o
n
l
ab
els
d
ef
in
ed
b
y
th
eir
s
h
ap
e
an
d
co
lo
r
,
alo
n
g
with
th
eir
i
m
ag
e
co
o
r
d
in
ates
.
I
n
st
ep
6
:
co
o
r
d
in
ate
m
ap
p
i
n
g
,
th
ese
im
ag
e
co
o
r
d
in
ates
ar
e
co
n
v
er
ted
in
to
p
h
y
s
ical
co
o
r
d
in
ates
with
in
th
e
r
o
b
o
t
’
s
wo
r
k
in
g
ar
ea
(
Do
b
o
t
wo
r
k
s
p
ac
e
co
o
r
d
in
ates
)
.
Step
7
:
Do
b
o
t
co
n
tr
o
ller
s
en
d
s
co
m
m
an
d
s
to
th
e
D
o
b
o
t
r
o
b
o
tic
ar
m
to
p
ick
u
p
th
e
o
b
jects
an
d
m
o
v
e
th
e
m
to
d
esig
n
ated
lo
ca
tio
n
s
.
Fin
ally
,
in
st
ep
8
:
p
h
y
s
ical
s
o
r
tin
g
,
t
h
e
r
o
b
o
tic
ar
m
p
h
y
s
ically
p
la
ce
s
th
e
o
b
jects
in
to
s
p
ec
if
ic
b
in
s
o
r
lo
ca
tio
n
s
ac
co
r
d
in
g
to
th
eir
class
if
ied
s
h
ap
e
o
r
co
lo
r
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
I
n
tellig
en
t o
b
ject
s
o
r
tin
g
s
ystem
u
s
in
g
Do
b
o
t m
a
g
icia
n
a
n
d
co
mp
u
ter visi
o
n
(
To
s
s
a
p
o
l J
a
n
g
n
o
i)
3355
Fig
u
r
e
3
.
B
lo
ck
d
iag
r
am
o
f
s
h
ap
e
an
d
c
o
lo
r
o
b
ject
d
etec
tio
n
u
s
in
g
th
e
Do
b
o
t M
ag
ician
r
o
b
o
tic
ar
m
2
.
3
.
M
et
ho
ds
f
o
r
det
ec
t
ing
o
bje
ct
s
ha
pe
a
nd
co
lo
r
Dete
ctin
g
o
b
ject
s
h
ap
es
an
d
c
o
lo
r
s
is
a
f
u
n
d
am
en
tal
task
in
co
m
p
u
ter
v
is
io
n
,
with
v
ar
io
u
s
m
eth
o
d
s
av
ailab
le
d
ep
en
d
i
n
g
o
n
th
e
r
e
q
u
ir
ed
co
m
p
lex
ity
an
d
ac
cu
r
a
cy
.
T
h
is
r
esear
ch
em
p
lo
y
s
tr
a
d
itio
n
al
co
m
p
u
te
r
v
is
io
n
tech
n
iq
u
es
u
s
in
g
Op
e
n
C
V
to
id
en
tify
th
e
s
h
ap
e
o
f
an
o
b
ject
(
e
.
g
.
,
cir
cle,
tr
ia
n
g
le,
s
q
u
ar
e
)
an
d
its
co
lo
r
(
e
.
g
.
,
r
ed
,
g
r
ee
n
,
b
lu
e,
y
ello
w
)
.
T
h
e
p
r
o
ce
s
s
o
f
d
etec
tin
g
an
o
b
ject
’
s
s
h
ap
e
an
d
c
o
lo
r
is
as
:
i)
R
ea
d
th
e
i
m
ag
e
−
Use c
v
2
.
im
r
ea
d
(
)
to
lo
a
d
th
e
i
m
ag
e
.
−
T
h
e
im
ag
e
is
r
ea
d
as a
m
atr
ix
o
f
p
ix
els in
b
lu
e,
g
r
ee
n
,
r
ed
(
B
GR
)
co
lo
r
s
p
ac
e
.
ii)
C
o
n
v
er
t to
g
r
ay
s
ca
le
−
C
o
n
v
er
t th
e
im
ag
e
f
r
o
m
B
GR
to
g
r
ay
s
ca
le
u
s
in
g
c
v
2
.
c
v
tC
o
lo
r
(
im
ag
e,
cv
2
.
C
OL
OR
_
B
GR
2
GR
AY
).
−
T
h
is
s
im
p
lifie
s
th
e
im
ag
e
b
y
r
em
o
v
in
g
co
lo
r
i
n
f
o
r
m
atio
n
,
m
ak
in
g
s
h
ap
e
d
etec
tio
n
ea
s
ier
.
iii)
B
lu
r
an
d
t
h
r
esh
o
l
d
(
o
r
ed
g
e
d
e
tectio
n
)
−
Use c
v
2
.
Gau
s
s
ian
B
lu
r
()
to
r
e
m
o
v
e
n
o
is
e
an
d
s
m
o
o
t
h
th
e
im
ag
e
.
−
Use c
v
2
.
th
r
esh
o
ld
(
)
o
r
cv
2
.
C
a
n
n
y
(
)
to
cr
ea
te
a
b
in
ar
y
im
ag
e
(
b
lack
an
d
wh
ite
).
−
Ob
jects b
ec
o
m
e
wh
ite
.
−
B
ac
k
g
r
o
u
n
d
b
ec
o
m
es b
lack
.
iv
)
Fin
d
c
o
n
to
u
r
s
−
Use c
v
2
.
f
in
d
C
o
n
to
u
r
s
()
to
d
et
ec
t th
e
b
o
u
n
d
ar
ies o
f
o
b
jects
(
s
h
ap
es
).
−
C
o
n
to
u
r
s
ar
e
cu
r
v
es th
at
co
n
n
ec
t c
o
n
tin
u
o
u
s
p
o
in
ts
ar
o
u
n
d
a
s
h
ap
e
.
v)
Dete
ct
s
h
ap
es
−
Ap
p
r
o
x
im
ate
t
h
e
co
n
t
o
u
r
u
s
in
g
cv
2
.
a
p
p
r
o
x
Po
ly
DP
()
to
g
et
t
h
e
n
u
m
b
er
o
f
co
r
n
er
s
:
−
3
co
r
n
e
r
s
→
t
r
ian
g
le
−
4
co
r
n
e
r
s
→
s
q
u
ar
e
(
ch
ec
k
wi
d
th
/
h
eig
h
t r
atio
)
−
Mo
r
e
th
an
4
→
c
ir
cle
o
r
o
v
al
−
Use c
v
2
.
b
o
u
n
d
in
g
R
ec
t
()
to
g
et
th
e
p
o
s
itio
n
an
d
s
ize
f
o
r
lab
el
in
g
.
v
i)
Dete
ct
c
o
lo
r
−
T
ak
e
th
e
p
ix
el
v
alu
es a
t th
e
ce
n
ter
o
f
t
h
e
s
h
ap
e
(
o
r
av
e
r
ag
e
i
n
s
id
e
it
).
−
C
o
n
v
er
t
th
e
im
ag
e
to
HSV
c
o
lo
r
s
p
ac
e
u
s
in
g
cv
2
.
cv
tC
o
lo
r
(
im
ag
e,
cv
2
.
C
OL
OR
_
B
G
R
2
HSV
)
f
o
r
m
o
r
e
ac
cu
r
ate
co
lo
r
d
etec
tio
n
.
−
Def
in
e
HSV
r
an
g
es f
o
r
:
−
R
ed
:
H
ar
o
u
n
d
0
o
r
1
7
0
–
1
8
0
−
Gr
ee
n
:
H
ar
o
u
n
d
6
0
−
B
lu
e
:
H
ar
o
u
n
d
1
2
0
−
Yello
w
:
H
ar
o
u
n
d
3
0
−
Use c
v
2
.
in
R
an
g
e
()
to
class
if
y
co
lo
r
s
b
ased
o
n
HSV
v
alu
es
.
v
ii)
L
ab
el,
d
r
aw
a
n
d
d
is
p
lay
r
esu
lts
−
Use c
v
2
.
p
u
tTe
x
t
(
)
to
wr
ite
th
e
n
am
e
o
f
th
e
s
h
ap
e
a
n
d
c
o
lo
r
o
n
th
e
im
ag
e
.
−
Use c
v
2
.
d
r
awCo
n
to
u
r
s
()
to
o
u
tlin
e
th
e
s
h
ap
e
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
4
,
Au
g
u
s
t 2
0
2
6
:
3
3
5
2
-
3
3
6
4
3356
2
.
4
.
Co
o
rdina
t
e
s
y
s
t
em
in met
ho
d pro
po
s
ed
T
h
i
s
s
e
c
ti
o
n
d
is
c
u
s
s
es
t
h
e
c
o
n
c
e
p
t
s
a
n
d
m
a
t
h
e
m
at
i
c
al
f
o
u
n
d
a
t
i
o
n
s
o
f
c
o
o
r
d
i
n
a
t
e
t
r
a
n
s
f
o
r
m
a
t
i
o
n
s
[
2
8
]
f
o
r
o
b
ject
p
ic
k
-
an
d
-
p
lace
tas
k
s
u
s
in
g
a
f
ix
ed
o
v
er
h
ea
d
ca
m
er
a
with
a
Do
b
o
t
r
o
b
o
tic
a
r
m
,
p
a
r
ticu
lar
ly
f
o
r
s
o
r
tin
g
o
b
jects b
ased
o
n
s
h
ap
e
an
d
co
lo
r
.
T
h
e
ca
m
er
a
ca
p
t
u
r
es th
e
wo
r
k
s
p
ac
e
f
r
o
m
a
to
p
-
d
o
wn
f
ix
ed
p
o
s
itio
n
,
id
en
tify
in
g
o
b
jects
in
t
h
e
im
a
g
e
u
s
in
g
p
i
x
el
co
o
r
d
in
ates
.
T
o
en
ab
le
th
e
r
o
b
o
t
t
o
in
te
r
ac
t
a
cc
u
r
ately
with
th
ese
o
b
jects,
it
is
n
ec
ess
a
r
y
to
tr
an
s
f
o
r
m
th
e
p
ix
el
co
o
r
d
i
n
ates
in
to
r
ea
l
-
wo
r
ld
c
o
o
r
d
in
ates
an
d
s
u
b
s
eq
u
en
tly
in
t
o
th
e
r
o
b
o
t
’
s
c
o
o
r
d
in
ate
f
r
am
e
.
A
USB
ca
m
er
a
is
m
o
u
n
te
d
ab
o
v
e
th
e
wo
r
k
s
p
ac
e
t
o
ca
p
tu
r
e
r
ea
l
-
tim
e
im
ag
es
o
f
th
e
o
b
jects
.
T
h
is
p
r
o
ce
s
s
r
eq
u
ir
es
p
r
ec
is
e
ca
m
er
a
ca
lib
r
atio
n
an
d
c
o
o
r
d
in
ate
tr
an
s
f
o
r
m
a
tio
n
m
eth
o
d
s
.
T
h
e
s
etu
p
o
f
th
e
e
q
u
ip
m
e
n
t is sh
o
wn
in
Fig
u
r
e
4
.
Fig
u
r
e
4
.
C
o
o
r
d
in
ate
s
y
s
tem
o
f
th
e
ex
p
e
r
im
en
t setu
p
W
h
en
u
s
in
g
t
h
e
Do
b
o
t
Ma
g
ician
to
p
ick
u
p
a
n
o
b
ject,
i
t
is
ess
en
tial
to
tr
an
s
f
o
r
m
th
e
o
b
ject'
s
co
o
r
d
in
ates
f
r
o
m
t
h
e
ca
m
er
a
f
r
am
e
to
th
e
r
o
b
o
t
’
s
co
o
r
d
in
ate
s
y
s
tem
,
en
ab
lin
g
p
r
ec
is
e
m
o
v
em
en
t
to
th
e
ta
r
g
et
p
o
s
itio
n
.
Ho
m
o
g
e
n
eo
u
s
tr
an
s
f
o
r
m
atio
n
e
q
u
atio
n
s
ar
e
ap
p
li
ed
to
co
n
v
er
t
o
b
ject
p
o
s
itio
n
s
f
r
o
m
th
e
ca
m
er
a
co
o
r
d
in
ate
s
y
s
tem
to
th
e
r
o
b
o
t
’
s
co
o
r
d
i
n
ate
s
y
s
tem
,
allo
win
g
th
e
Do
b
o
t
Ma
g
ician
to
ac
cu
r
ately
p
er
f
o
r
m
p
ick
-
an
d
-
p
lace
task
s
.
Gen
er
al
ly
,
th
r
ee
c
o
o
r
d
in
ate
f
r
a
m
es
ar
e
in
v
o
lv
e
d
:
th
e
ca
m
e
r
a
f
r
a
m
e
,
th
e
wo
r
ld
f
r
am
e
,
an
d
th
e
r
o
b
o
t
f
r
am
e
.
T
h
e
g
e
n
e
r
al
tr
an
s
f
o
r
m
atio
n
is
s
h
o
wn
in
(
1
)
.
=
←
∙
←
∙
(
1
)
W
h
er
e
is
p
o
s
itio
n
o
f
th
e
o
b
ject
in
ca
m
e
r
a
c
o
o
r
d
i
n
ates
,
←
is
tr
an
s
f
o
r
m
atio
n
m
atr
ix
f
r
o
m
ca
m
er
a
f
r
am
e
to
wo
r
ld
f
r
am
e
,
←
is
tr
an
s
f
o
r
m
atio
n
f
r
o
m
wo
r
l
d
f
r
am
e
to
r
o
b
o
t
f
r
am
e
,
an
d
is
o
b
ject
p
o
s
itio
n
in
r
o
b
o
t
c
o
o
r
d
in
ates
(
in
p
u
t
f
o
r
th
e
r
o
b
o
t
).
E
ac
h
tr
an
s
f
o
r
m
atio
n
m
atr
ix
is
a
4
×4
h
o
m
o
g
e
n
eo
u
s
m
atr
ix
,
as sh
o
wn
in
(
2
)
.
=
[
0
1
]
(
2
)
W
h
er
e
=3
×
3
r
o
tatio
n
m
atr
ix
(
o
r
ien
tatio
n
b
etwe
en
f
r
am
es)
,
=3
×
1
tr
an
s
latio
n
v
ec
to
r
(
p
o
s
itio
n
o
f
f
s
et
b
etwe
en
f
r
am
es)
.
2
.
5
.
P
y
t
ho
n c
o
de
f
o
r
im
plementa
t
io
n o
f
pro
ce
s
s
Usi
n
g
P
y
D
o
b
o
t
in
v
o
lv
es
wr
itin
g
Py
th
o
n
p
r
o
g
r
am
s
[
2
9
]
t
o
c
o
n
tr
o
l
th
e
D
o
b
o
t
Ma
g
ician
r
o
b
o
tic
ar
m
v
ia
a
s
er
ial
(
C
OM
)
p
o
r
t
.
I
t
allo
ws
u
s
er
s
to
m
o
v
e
t
h
e
ar
m
t
o
s
p
ec
if
ic
p
o
s
itio
n
s
,
s
et
m
o
v
em
en
t
s
p
ee
d
s
,
tu
r
n
th
e
s
u
ctio
n
cu
p
o
n
o
r
o
f
f
,
an
d
r
e
ad
th
e
cu
r
r
en
t
p
o
s
e
o
f
th
e
ar
m
.
T
h
is
m
ak
es
it
ea
s
y
to
au
t
o
m
ate
task
s
with
th
e
Do
b
o
t
with
o
u
t
r
ely
in
g
o
n
th
e
Do
b
o
tSt
u
d
io
s
o
f
twar
e
.
T
o
co
n
n
ec
t
Do
b
o
t
Ma
g
ician
u
s
in
g
a
m
an
u
ally
s
p
ec
if
ied
p
o
r
t in
Py
Do
b
o
t
,
s
im
p
ly
p
ass
th
e
p
o
r
t
n
am
e
d
i
r
ec
tly
wh
en
c
r
ea
tin
g
th
e
Do
b
o
t o
b
ject
:
fr
om
pydo
b
ot
im
por
t
Do
b
ot
de
vic
e
=
Do
b
o
t
(
p
o
r
t
="
C
OM5
")
#
R
e
p
la
ce
C
OM5
w
ith
yo
u
r
a
ctu
a
l p
o
r
t
T
h
is
estab
lis
h
es a
s
er
ial
co
n
n
ec
tio
n
b
etwe
en
y
o
u
r
Py
t
h
o
n
s
cr
ip
t a
n
d
th
e
D
o
b
o
t M
ag
ician
u
s
in
g
s
p
ec
if
ied
p
o
r
t
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
I
n
tellig
en
t o
b
ject
s
o
r
tin
g
s
ystem
u
s
in
g
Do
b
o
t m
a
g
icia
n
a
n
d
co
mp
u
ter visi
o
n
(
To
s
s
a
p
o
l J
a
n
g
n
o
i)
3357
3.
M
E
T
H
O
DO
L
O
G
Y
AND
M
AT
E
RIA
L
T
h
is
s
ec
tio
n
o
u
tlin
es
th
e
s
y
s
te
m
wo
r
k
f
lo
w
an
d
th
e
s
etu
p
o
f
eq
u
ip
m
en
t
u
s
ed
in
th
e
ex
p
er
i
m
en
t
.
T
h
e
Do
b
o
t
Ma
g
ician
is
co
n
tr
o
lled
u
s
in
g
a
p
r
o
g
r
am
wr
itten
in
Py
th
o
n
a
n
d
Op
en
C
V,
u
tili
zin
g
th
e
Py
Do
b
o
t
lib
r
ar
y
.
T
h
e
ex
p
e
r
im
en
tal
p
r
o
ce
d
u
r
e
is
ca
r
r
ied
o
u
t in
th
e
f
o
llo
win
g
s
t
ep
s
:
3
.
1
.
Set
t
ing
o
f
t
he
re
la
t
io
n o
f
co
o
rdina
t
es
T
h
e
f
ir
s
t
s
tep
in
v
o
lv
es
ca
lib
r
a
tin
g
th
e
ca
m
er
a
co
o
r
d
in
ates,
t
h
e
s
u
r
f
ac
e
co
o
r
d
i
n
ates
wh
er
e
th
e
o
b
jects
ar
e
p
lace
d
,
a
n
d
th
e
s
u
ctio
n
h
ea
d
p
o
s
itio
n
o
f
th
e
Do
b
o
t to
en
s
u
r
e
th
ey
alig
n
co
r
r
ec
tly
.
T
h
is
i
s
d
o
n
e
b
y
wr
itin
g
a
Py
th
o
n
p
r
o
g
r
am
an
d
s
av
in
g
i
t
in
a
f
o
l
d
er
f
o
r
co
n
tin
u
o
u
s
u
s
e
in
c
o
lo
r
an
d
s
h
ap
e
d
etec
tio
n
.
As
s
h
o
w
n
in
Fig
u
r
e
5
,
th
e
co
o
r
d
in
ate
m
ap
p
in
g
p
r
o
ce
s
s
in
v
o
lv
es
id
en
tify
in
g
th
e
ca
m
er
a'
s
p
r
o
jecte
d
p
o
in
ts
o
n
th
e
s
u
r
f
ac
e
an
d
m
o
v
in
g
th
e
Do
b
o
t'
s
s
u
ctio
n
h
e
ad
t
o
th
o
s
e
p
o
in
ts
.
A
to
tal
o
f
f
o
u
r
p
o
in
ts
is
u
s
ed
,
a
n
d
th
e
d
ata
is
s
av
ed
u
s
in
g
a
m
eth
o
d
ca
lled
th
e
h
o
m
o
g
r
ap
h
y
m
atr
i
x
.
Fig
u
r
e
5
.
T
h
e
ca
lib
r
atin
g
o
f
ca
m
er
a
an
d
d
o
b
o
t h
ea
d
co
o
r
d
in
a
tes f
o
u
r
p
o
in
t
3
.
2
.
Wo
r
k
piece
p
la
ce
m
ent
First,
o
p
en
t
h
e
Do
b
o
tSt
u
d
io
p
r
o
g
r
am
.
T
h
e
n
,
a
r
r
an
g
e
th
e
wo
r
k
p
iece
s
—
f
ea
tu
r
in
g
all
f
o
u
r
c
o
lo
r
s
an
d
th
r
ee
s
h
ap
es
—
in
t
h
e
d
esire
d
p
o
s
itio
n
s
with
in
th
e
r
ea
c
h
ab
le
ar
ea
o
f
th
e
r
o
b
o
tic
ar
m
to
en
s
u
r
e
it
ca
n
o
p
er
ate
with
o
u
t
er
r
o
r
s
.
Fig
u
r
e
6
illu
s
tr
ates
th
e
ar
r
a
n
g
em
en
t
o
f
th
e
wo
r
k
p
iece
s
.
Fig
u
r
e
6
(
a
)
s
h
o
ws
t
h
e
p
lace
m
e
n
t
o
f
th
e
wo
r
k
p
iece
s
o
n
th
e
ta
b
le
s
u
r
f
a
ce
.
Fig
u
r
e
6
(
b
)
d
em
o
n
s
tr
ates
h
o
w
to
u
s
e
th
e
Do
b
o
tSt
u
d
io
p
r
o
g
r
a
m
to
p
o
s
itio
n
th
e
r
o
b
o
tic
a
r
m
o
v
er
ea
ch
wo
r
k
p
iece
an
d
s
av
e
th
e
p
o
s
itio
n
v
alu
es
at
th
o
s
e
s
p
ec
if
ic
p
o
in
ts
.
Fig
u
r
e
6
(
c
)
s
h
o
ws
h
o
w
th
e
(
x
,
y
)
co
o
r
d
in
ates o
f
e
ac
h
wo
r
k
p
iece
ar
e
en
ter
e
d
in
to
th
e
cu
s
to
m
-
d
e
v
elo
p
e
d
p
r
o
g
r
a
m
.
(
a)
(
b
)
(
c)
Fig
u
r
e
6
.
Ar
r
an
g
em
e
n
t a
n
d
lo
ca
lizatio
n
o
f
wo
r
k
p
iece
s
:
(
a
)
w
o
r
k
p
iece
p
o
s
itio
n
s
o
n
th
e
ta
b
le
s
u
r
f
ac
e
,
(
b
)
p
o
s
itio
n
in
g
th
e
D
o
b
o
t'
s
s
u
ctio
n
h
ea
d
o
v
er
ea
c
h
wo
r
k
p
iec
e
to
r
ec
o
r
d
co
o
r
d
in
ates
,
an
d
(
c
)
e
n
ter
in
g
p
o
s
itio
n
d
ata
in
to
th
e
Py
th
o
n
p
r
o
g
r
am
f
o
r
im
p
lem
en
tatio
n
3
.
3
.
P
r
o
g
ra
m
e
x
ec
utio
n t
esting
B
ef
o
r
e
s
tar
tin
g
ea
ch
o
p
e
r
atio
n
,
th
e
Do
b
o
tSt
u
d
i
o
p
r
o
g
r
am
m
u
s
t
b
e
o
p
en
ed
to
s
et
th
e
r
o
b
o
t
to
its
h
o
m
e
p
o
s
itio
n
.
On
ce
th
is
is
d
o
n
e
,
cl
o
s
e
th
e
p
r
o
g
r
a
m
an
d
r
u
n
t
h
e
m
o
d
u
le
i
n
th
e
Py
th
o
n
p
r
o
g
r
a
m
.
T
h
e
in
ter
f
ac
e
will
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
4
,
Au
g
u
s
t 2
0
2
6
:
3
3
5
2
-
3
3
6
4
3358
d
is
p
lay
two
s
ec
tio
n
s
:
o
n
e
f
o
r
co
lo
r
an
d
s
h
a
p
e
d
etec
tio
n
,
a
n
d
th
e
o
th
e
r
f
o
r
s
tar
t
/
s
to
p
b
u
tto
n
co
n
tr
o
ls
,
alo
n
g
with
a
tab
le
th
at
lo
g
s
th
e
n
u
m
b
er
o
f
item
s
s
o
r
ted
,
as sh
o
wn
i
n
Fig
u
r
e
7
.
Fig
u
r
e
7
.
Settin
g
u
p
th
e
D
o
b
o
t
Stu
d
io
p
r
o
g
r
am
t
o
m
o
v
e
th
e
r
o
b
o
tic
ar
m
t
o
th
e
h
o
m
e
p
o
s
itio
n
3
.
4
.
St
a
rt
ing
t
he
pro
g
r
a
m
f
o
r
pick
-
a
nd
-
pla
ce
o
pera
t
io
ns
B
ef
o
r
e
o
p
er
atin
g
th
e
s
y
s
tem
,
th
e
p
o
s
itio
n
s
f
o
r
p
lacin
g
th
e
o
b
jects
m
u
s
t
f
ir
s
t
b
e
d
ef
in
ed
,
as
illu
s
tr
ated
in
Fig
u
r
e
6
(
a
)
.
T
h
e
Do
b
o
tSt
u
d
io
p
r
o
g
r
am
was
u
s
ed
to
m
a
n
u
ally
m
o
v
e
th
e
r
o
b
o
tic
ar
m
to
ea
ch
p
r
e
d
ef
in
ed
o
b
ject
p
o
s
itio
n
.
T
h
ese
co
o
r
d
i
n
ates
wer
e
th
en
en
te
r
ed
in
to
a
cu
s
to
m
-
d
ev
el
o
p
ed
ap
p
licati
o
n
.
On
ce
t
h
e
s
etu
p
was c
o
m
p
lete,
th
e
s
tar
t b
u
tto
n
was p
r
ess
ed
to
in
it
iate
th
e
p
r
o
ce
s
s
.
T
h
e
p
r
o
g
r
am
was d
esig
n
ed
to
d
etec
t o
b
jects
b
ased
o
n
th
ei
r
co
lo
r
an
d
s
h
a
p
e
an
d
in
clu
d
es th
e
f
o
llo
win
g
k
e
y
f
ea
tu
r
es
:
−
Ab
ilit
y
to
click
two
p
o
i
n
ts
to
d
ef
in
e
th
e
p
ick
u
p
z
o
n
e
−
Vis
u
al
f
ee
d
b
ac
k
with
a
g
r
ee
n
b
o
r
d
er
d
u
r
in
g
z
o
n
e
s
elec
tio
n
−
Dis
p
lay
o
f
a
p
u
r
p
le
b
o
r
d
e
r
o
n
c
e
th
e
p
ick
u
p
zo
n
e
is
s
et
−
B
u
tto
n
s
f
o
r
e
x
p
o
r
t
co
m
m
a
-
s
ep
ar
ated
v
alu
es (
C
SV
)
,
r
eset c
o
u
n
t,
an
d
r
eset p
ick
u
p
ar
ea
−
C
ap
ab
ilit
y
to
s
av
e
th
e
p
ick
u
p
zo
n
e
to
a
f
ile
n
am
ed
p
ick
u
p
_
a
r
ea
.
js
o
n
−
Use
o
f
a
h
o
m
o
g
r
ap
h
y
m
atr
ix
(
h
o
m
o
g
r
ap
h
y
_
m
atr
i
x
.
n
p
y
)
to
c
o
n
v
er
t
b
etwe
en
p
ix
el
co
o
r
d
in
a
tes
an
d
r
o
b
o
t
co
o
r
d
in
ates
−
I
n
teg
r
atio
n
with
Py
Do
b
o
t
f
o
r
co
n
tr
o
llin
g
t
h
e
Do
b
o
t in
au
to
m
ated
p
ick
-
a
n
d
-
p
lace
o
p
e
r
atio
n
s
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
4
.
1
.
E
x
perim
ent
a
l
r
esu
lt
s
T
h
e
d
ataset
co
m
p
r
is
es
v
ar
io
u
s
o
b
jects
wi
th
d
if
f
er
en
t
s
h
ap
es
(
e
.
g
.
,
cir
cles,
s
q
u
ar
es,
tr
ia
n
g
les
)
an
d
co
lo
r
s
(
e
.
g
.
,
r
e
d
,
g
r
ee
n
,
b
lu
e
)
.
T
h
e
im
ag
es
wer
e
co
llected
u
n
d
er
v
ar
y
in
g
lig
h
tin
g
co
n
d
iti
o
n
s
to
en
h
an
ce
t
h
e
m
o
d
el'
s
g
en
er
aliza
tio
n
ca
p
ab
il
ity
.
E
a
ch
i
m
a
g
e
i
n
cl
u
d
es
b
o
t
h
s
h
a
p
e
a
n
d
c
o
l
o
r
att
r
i
b
u
tes
,
as
s
h
o
wn
i
n
F
ig
u
r
e
8
.
T
h
e
p
r
el
im
i
n
ar
y
tes
ti
n
g
o
f
t
h
e
o
b
je
ct
s
h
ap
e
a
n
d
c
o
l
o
r
d
e
te
cti
o
n
p
r
o
g
r
a
m
was
c
ar
r
i
ed
o
u
t,
as
s
h
o
wn
i
n
Fi
g
u
r
e
9
.
Fig
u
r
e
8
.
W
o
r
k
p
iece
s
f
ea
tu
r
in
g
4
co
l
o
r
s
an
d
3
s
h
ap
es
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
I
n
tellig
en
t o
b
ject
s
o
r
tin
g
s
ystem
u
s
in
g
Do
b
o
t m
a
g
icia
n
a
n
d
co
mp
u
ter visi
o
n
(
To
s
s
a
p
o
l J
a
n
g
n
o
i)
3359
Fig
u
r
e
9
.
Ob
ject
d
etec
tio
n
b
y
s
h
ap
e
an
d
c
o
lo
r
u
s
in
g
HSV
an
d
Op
en
C
V
I
llu
s
tr
ated
in
Fig
u
r
e
1
0
is
a
s
cr
ee
n
s
h
o
t
tak
en
f
r
o
m
a
v
i
d
eo
d
em
o
n
s
tr
atin
g
th
e
o
p
er
a
tio
n
o
f
th
e
au
to
m
atic
s
o
r
tin
g
s
y
s
tem
f
o
r
wo
r
k
p
iece
s
with
th
r
ee
s
h
ap
es
an
d
f
o
u
r
co
lo
r
s
.
T
h
e
p
r
o
ce
s
s
b
eg
in
s
b
y
lau
n
ch
i
n
g
th
e
cu
s
to
m
-
d
ev
elo
p
ed
Py
th
o
n
p
r
o
g
r
a
m
.
Nex
t,
th
e
Do
b
o
tSt
u
d
io
s
o
f
twar
e
is
u
s
ed
to
m
o
v
e
th
e
r
o
b
o
tic
ar
m
to
th
e
h
o
m
e
p
o
s
itio
n
.
Af
ter
th
at,
th
e
Py
th
o
n
p
r
o
g
r
am
is
ex
ec
u
ted
.
W
h
en
th
e
ca
m
er
a
d
etec
ts
a
wo
r
k
p
iece
with
a
s
p
ec
if
ic
s
h
ap
e
an
d
co
lo
r
with
in
th
e
d
ef
i
n
ed
ar
ea
,
it
d
r
aws
a
b
o
u
n
d
in
g
b
o
x
ar
o
u
n
d
th
e
o
b
ject
an
d
m
a
r
k
s
its
ce
n
ter
p
o
in
t
.
T
h
e
co
o
r
d
in
ates
ar
e
th
en
s
en
t
to
th
e
r
o
b
o
tic
ar
m
,
wh
ich
m
o
v
es
to
p
ick
u
p
th
e
o
b
ject
an
d
p
lace
it
in
a
p
r
ed
ef
in
ed
lo
ca
tio
n
.
T
h
e
s
y
s
tem
co
n
tin
u
es o
p
er
atin
g
u
n
til th
er
e
ar
e
n
o
m
o
r
e
wo
r
k
p
iece
s
in
th
e
d
esig
n
ated
ar
ea
o
r
th
e
p
r
o
g
r
am
is
m
an
u
ally
s
to
p
p
ed
.
Fig
u
r
e
1
0
.
Actu
al
m
o
v
e
m
en
t o
f
th
e
Do
b
o
t
Ma
g
ician
d
u
r
in
g
o
b
ject
s
o
r
tin
g
T
ab
le
4
s
h
o
ws
th
e
r
esu
lts
o
f
t
h
e
Do
b
o
t
Ma
g
ician
’
s
w
o
r
k
p
ie
ce
g
r
asp
in
g
test
,
wh
ich
in
d
ica
te
th
at
th
e
r
o
b
o
t
s
u
cc
ess
f
u
lly
g
r
asp
e
d
all
o
b
jects
in
ev
er
y
tr
ial
.
T
h
e
ac
c
u
r
ac
y
r
an
g
ed
f
r
o
m
9
5
.
0
%
to
9
9
.
2
%
,
with
th
e
r
e
d
tr
ian
g
le
ac
h
iev
i
n
g
th
e
h
ig
h
est
ac
cu
r
ac
y
o
f
9
9
.
2
%.
T
h
e
g
r
asp
in
g
tim
es
v
ar
ied
,
f
r
o
m
1
1
.
7
6
s
ec
o
n
d
s
f
o
r
th
e
r
ed
tr
ian
g
le
to
1
5
.
0
2
s
ec
o
n
d
s
f
o
r
th
e
g
r
ee
n
s
q
u
a
r
e
.
Ad
d
itio
n
al
ly
,
th
e
r
o
b
o
t
’
s
p
er
f
o
r
m
an
ce
r
em
ain
ed
co
n
s
is
ten
t
ac
r
o
s
s
d
if
f
er
en
t sh
ap
es a
n
d
co
l
o
r
s
,
with
p
ick
p
o
s
itio
n
s
v
ar
y
in
g
s
lig
h
tly
f
o
r
ea
ch
o
b
ject
.
T
h
is
b
ar
ch
ar
t
in
Fig
u
r
e
1
1
s
h
o
ws
th
e
av
er
ag
e
ac
cu
r
ac
y
p
er
ce
n
tag
es
ca
teg
o
r
ized
b
y
c
o
lo
r
an
d
s
h
ap
e
.
Fo
r
ea
ch
co
lo
r
—
b
lu
e,
g
r
ee
n
,
r
ed
,
an
d
y
ello
w
—
th
e
av
er
a
g
e
ac
cu
r
ac
y
is
p
r
esen
ted
f
o
r
t
h
r
ee
s
h
ap
es
:
cir
cle,
s
q
u
ar
e,
an
d
tr
ian
g
le
.
Ov
e
r
all,
th
e
ac
c
u
r
ac
y
v
alu
es
ar
e
v
er
y
clo
s
e
ac
r
o
s
s
all
g
r
o
u
p
s
,
with
m
o
s
t
s
h
ap
es
ac
h
iev
in
g
a
b
o
v
e
9
5
%
ac
cu
r
a
cy
.
T
r
ian
g
les
g
en
er
ally
h
av
e
th
e
h
ig
h
est
av
er
a
g
e
ac
cu
r
ac
y
with
in
ea
ch
co
lo
r
g
r
o
u
p
,
f
o
llo
wed
clo
s
ely
b
y
s
q
u
ar
es
an
d
cir
cles
.
T
h
e
c
h
ar
t
s
u
g
g
ests
th
at
ac
cu
r
ac
y
i
s
co
n
s
is
ten
tly
h
ig
h
r
eg
ar
d
less
o
f
co
l
o
r
o
r
s
h
ap
e,
w
ith
o
n
ly
s
lig
h
t v
a
r
iatio
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
4
,
Au
g
u
s
t 2
0
2
6
:
3
3
5
2
-
3
3
6
4
3360
T
ab
le
4
.
R
esu
lts
o
f
Do
b
o
t
Ma
g
ician
’
s
wo
r
k
p
iece
g
r
asp
in
g
test
ac
co
r
d
in
g
to
s
h
ap
e
an
d
co
lo
r
C
o
l
o
r
S
h
a
p
e
C
o
u
n
t
S
u
c
c
e
ss
Ti
me
(
s
)
A
c
c
u
r
a
c
y
(
%)
P
i
c
k
p
o
s
i
t
i
o
n
R
e
d
S
q
u
a
r
e
1
Y
e
s
14
.
31
97
.
8
(
2
1
9
,
-
1
5
5
)
B
l
u
e
C
i
r
c
l
e
1
Y
e
s
14
.
35
96
.
1
(
2
7
0
,
-
1
2
7
)
G
r
e
e
n
C
i
r
c
l
e
1
Y
e
s
12
.
98
98
.
6
(
2
7
3
,
-
1
1
7
)
B
l
u
e
S
q
u
a
r
e
1
Y
e
s
14
.
35
98
.
2
(
2
0
6
,
-
1
4
8
)
R
e
d
C
i
r
c
l
e
1
Y
e
s
14
.
56
95
.
2
(
2
1
2
,
-
1
4
4
)
Y
e
l
l
o
w
S
q
u
a
r
e
1
Y
e
s
13
.
71
97
.
4
(
2
6
8
,
-
1
2
0
)
R
e
d
Tr
i
a
n
g
l
e
1
Y
e
s
13
.
39
96
.
5
(
2
7
5
,
-
1
3
0
)
Y
e
l
l
o
w
Tr
i
a
n
g
l
e
1
Y
e
s
13
.
07
95
.
9
(
2
7
4
,
-
1
3
2
)
G
r
e
e
n
Tr
i
a
n
g
l
e
1
Y
e
s
12
.
71
97
.
4
(
2
4
1
,
-
72
)
Y
e
l
l
o
w
C
i
r
c
l
e
1
Y
e
s
12
.
04
95
.
7
(
2
6
3
,
-
71
)
G
r
e
e
n
Tr
i
a
n
g
l
e
2
Y
e
s
13
.
43
96
.
3
(
2
9
0
,
-
1
4
4
)
B
l
u
e
Tr
i
a
n
g
l
e
1
Y
e
s
12
.
04
97
.
3
(
2
3
5
,
-
98
)
B
l
u
e
C
i
r
c
l
e
2
Y
e
s
12
.
10
97
.
6
(
2
6
2
,
-
73
)
R
e
d
Tr
i
a
n
g
l
e
2
Y
e
s
13
.
02
99
.
2
(
2
6
4
,
-
1
4
4
)
R
e
d
S
q
u
a
r
e
2
Y
e
s
13
.
95
95
.
6
(
2
7
1
,
-
1
4
6
)
G
r
e
e
n
S
q
u
a
r
e
1
Y
e
s
15
.
02
98
.
4
(
2
1
1
,
-
1
5
7
)
G
r
e
e
n
C
i
r
c
l
e
2
Y
e
s
13
.
35
98
.
1
(
2
0
9
,
-
92
)
B
l
u
e
S
q
u
a
r
e
2
Y
e
s
13
.
29
97
.
1
(
2
6
7
,
-
86
)
Y
e
l
l
o
w
S
q
u
a
r
e
2
Y
e
s
12
.
40
96
.
2
(
2
6
6
,
-
1
4
9
)
R
e
d
C
i
r
c
l
e
2
Y
e
s
14
.
32
96
.
8
(
2
8
5
,
-
1
4
3
)
G
r
e
e
n
Tr
i
a
n
g
l
e
3
Y
e
s
13
.
05
98
.
9
(
2
2
5
,
-
93
)
Y
e
l
l
o
w
C
i
r
c
l
e
2
Y
e
s
13
.
33
96
.
2
(
2
8
0
,
-
1
3
9
)
Y
e
l
l
o
w
Tr
i
a
n
g
l
e
2
Y
e
s
13
.
66
96
.
6
(
2
3
7
,
-
1
4
8
)
R
e
d
Tr
i
a
n
g
l
e
3
Y
e
s
13
.
62
97
.
2
(
1
5
8
,
-
1
3
6
)
B
l
u
e
Tr
i
a
n
g
l
e
2
Y
e
s
12
.
66
97
.
6
(
2
1
5
,
-
1
6
0
)
R
e
d
S
q
u
a
r
e
3
Y
e
s
13
.
04
98
.
3
(
2
6
4
,
-
70
)
G
r
e
e
n
C
i
r
c
l
e
3
Y
e
s
13
.
32
95
.
9
(
2
6
2
,
-
74
)
R
e
d
Tr
i
a
n
g
l
e
4
Y
e
s
11
.
76
98
.
4
(
2
6
7
,
-
77
)
G
r
e
e
n
Tr
i
a
n
g
l
e
4
Y
e
s
13
.
03
96
.
1
(
2
0
9
,
-
1
4
7
)
B
l
u
e
S
q
u
a
r
e
3
Y
e
s
14
.
26
97
.
0
(
2
7
2
,
-
1
3
2
)
R
e
d
C
i
r
c
l
e
3
Y
e
s
13
.
96
95
.
0
(
2
6
8
,
-
1
2
5
)
B
l
u
e
C
i
r
c
l
e
3
Y
e
s
14
.
09
96
.
3
(
2
7
6
,
-
1
3
6
)
Y
e
l
l
o
w
S
q
u
a
r
e
3
Y
e
s
13
.
12
98
.
4
(
2
0
7
,
-
74
)
G
r
e
e
n
S
q
u
a
r
e
2
Y
e
s
14
.
58
97
.
9
(
2
7
0
,
-
1
3
5
)
Y
e
l
l
o
w
C
i
r
c
l
e
3
Y
e
s
13
.
72
95
.
9
(
2
1
4
,
-
1
3
3
)
B
l
u
e
Tr
i
a
n
g
l
e
3
Y
e
s
13
.
08
99
.
1
(
2
0
9
,
-
1
5
9
)
Y
e
l
l
o
w
Tr
i
a
n
g
l
e
3
Y
e
s
12
.
41
96
.
4
(
2
6
3
,
-
72
)
Fig
u
r
e
1
1
.
Av
er
ag
e
a
cc
u
r
ac
y
b
y
co
lo
r
an
d
s
h
ap
e
Fig
u
r
e
1
2
s
h
o
ws
th
e
av
er
a
g
e
tim
e
tak
en
f
o
r
ea
c
h
task
,
ca
teg
o
r
ized
b
y
co
lo
r
an
d
s
h
ap
e
.
T
h
e
f
o
u
r
m
ain
co
lo
r
s
ar
e
b
lu
e,
g
r
ee
n
,
r
ed
,
an
d
y
ello
w
.
Fo
r
ea
ch
c
o
lo
r
,
th
e
av
er
ag
e
tim
es
f
o
r
th
r
ee
s
h
ap
es
—
cir
cle,
s
q
u
ar
e,
a
n
d
t
r
ian
g
le
—
ar
e
d
is
p
lay
ed
.
Ov
e
r
all,
s
q
u
a
r
es
ten
d
t
o
tak
e
th
e
l
o
n
g
est
tim
e,
esp
ec
ially
f
o
r
th
e
g
r
ee
n
an
d
b
l
u
e
co
lo
r
s
.
T
r
ian
g
les
g
en
er
ally
r
eq
u
ir
e
th
e
s
h
o
r
test
tim
e
ac
r
o
s
s
m
o
s
t
co
lo
r
s
,
ex
ce
p
t
f
o
r
r
ed
,
wh
er
e
cir
cles
tak
e
th
e
lo
n
g
est
tim
e
.
I
n
y
ello
w,
th
e
av
er
ag
e
tim
es
f
o
r
all
th
r
ee
s
h
ap
es
ar
e
q
u
ite
s
im
ilar
.
T
h
is
ch
ar
t
h
ig
h
lig
h
ts
h
o
w
th
e
tim
e
tak
e
n
v
ar
ies d
e
p
en
d
in
g
o
n
b
o
th
s
h
ap
e
an
d
c
o
lo
r
.
Fig
u
r
e
1
3
s
h
o
ws
th
e
r
elatio
n
s
h
ip
b
etwe
en
ac
cu
r
ac
y
an
d
ti
m
e
tak
en
,
with
ea
ch
p
o
i
n
t
r
ep
r
esen
tin
g
a
d
ata
s
et
ca
teg
o
r
ized
b
y
co
lo
r
an
d
s
h
a
p
e
.
T
h
e
s
ize
o
f
ea
ch
p
o
in
t
in
d
icate
s
t
h
e
c
o
u
n
t,
o
r
h
o
w
m
an
y
tim
es
th
at
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
I
n
tellig
en
t o
b
ject
s
o
r
tin
g
s
ystem
u
s
in
g
Do
b
o
t m
a
g
icia
n
a
n
d
co
mp
u
ter visi
o
n
(
To
s
s
a
p
o
l J
a
n
g
n
o
i)
3361
d
ata
s
et
o
cc
u
r
s
.
Gen
er
ally
,
d
ata
p
o
in
ts
with
a
tim
e
o
f
less
th
an
2
s
ec
o
n
d
s
ten
d
to
h
a
v
e
h
ig
h
er
ac
c
u
r
ac
y
.
T
r
ian
g
les
m
o
s
tly
s
h
o
w
h
ig
h
a
cc
u
r
ac
y
with
s
h
o
r
ter
tim
es,
w
h
ile
s
q
u
ar
es
ten
d
to
tak
e
l
o
n
g
er
an
d
o
f
ten
h
av
e
lo
wer
ac
cu
r
ac
y
.
L
ar
g
er
p
o
in
ts
,
in
d
icatin
g
h
ig
h
e
r
co
u
n
ts
,
ar
e
s
p
r
ea
d
ac
r
o
s
s
lo
n
g
er
tim
e
r
an
g
es
with
m
o
d
er
at
e
to
lo
wer
ac
cu
r
ac
y
.
T
h
is
s
u
g
g
e
s
ts
th
at
tak
in
g
m
o
r
e
tim
e
d
o
es
n
o
t n
ec
ess
ar
ily
r
esu
lt in
b
etter
ac
cu
r
ac
y
.
Fig
u
r
e
1
2
.
Av
er
ag
e
tim
e
b
y
c
o
lo
r
an
d
s
h
a
p
e
Fig
u
r
e
1
3
.
Acc
u
r
ac
y
v
s
tim
e
o
f
co
lo
r
,
s
h
ap
e
,
an
d
co
u
n
t
4
.
2
.
Dis
cus
s
io
n
On
e
o
f
t
h
e
m
ain
ad
v
a
n
tag
es
i
s
m
o
r
e
ac
cu
r
ate
co
lo
r
s
ep
ar
ati
o
n
co
m
p
ar
ed
to
R
GB
,
as
HSV
s
ep
ar
ates
co
lo
r
in
f
o
r
m
atio
n
f
r
o
m
b
r
i
g
h
t
n
ess
.
T
h
is
allo
ws
f
o
r
m
o
r
e
p
r
ec
is
e
co
lo
r
d
etec
tio
n
,
e
v
en
u
n
d
er
u
n
ev
en
lig
h
tin
g
co
n
d
itio
n
s
.
T
h
e
h
u
e
co
m
p
o
n
e
n
t
s
p
ec
if
ically
r
ep
r
esen
ts
th
e
m
ain
co
lo
r
(
e
.
g
.
,
r
ed
,
g
r
ee
n
,
b
l
u
e
)
,
m
ak
i
n
g
it
ea
s
ier
to
class
if
y
o
b
jects
b
y
c
o
lo
r
.
An
o
th
er
ad
v
an
tag
e
is
f
ast
p
r
o
ce
s
s
in
g
with
Op
en
C
V,
wh
ich
p
r
o
v
id
es
b
u
ilt
-
in
f
u
n
ctio
n
s
s
u
ch
as
cv
2
.
i
n
R
an
g
e
()
,
c
v
2
.
f
i
n
d
C
o
n
to
u
r
s
()
,
an
d
cv
2
.
a
p
p
r
o
x
Po
ly
DP
(
)
.
T
h
ese
to
o
ls
en
ab
le
r
ap
id
an
d
ef
f
icien
t
d
etec
tio
n
o
f
b
o
t
h
co
lo
r
a
n
d
s
h
ap
e
.
HSV
an
d
Op
en
C
V
also
s
u
p
p
o
r
t
ac
cu
r
ate
s
h
ap
e
d
etec
tio
n
.
B
asic
g
eo
m
etr
ic
s
h
ap
es
lik
e
ci
r
cles,
s
q
u
ar
es,
an
d
tr
ian
g
les
ca
n
b
e
id
en
tifie
d
b
y
an
al
y
zin
g
o
b
ject
co
n
to
u
r
s
an
d
co
u
n
tin
g
th
e
n
u
m
b
er
o
f
v
er
tic
es
.
Fo
r
ex
am
p
le,
a
s
h
ap
e
with
3
v
er
tices
is
class
if
ied
as
a
tr
i
an
g
le,
4
v
er
tices
as
a
s
q
u
ar
e,
an
d
a
s
m
o
o
th
,
cu
r
v
e
d
co
n
to
u
r
as
a
cir
cle
.
T
h
e
s
y
s
t
em
is
also
ea
s
y
to
im
p
lem
en
t w
ith
o
u
t
th
e
n
ee
d
f
o
r
AI
m
o
d
els,
m
ak
in
g
it
id
ea
l
f
o
r
em
b
e
d
d
ed
ap
p
licatio
n
s
an
d
r
ea
l
-
tim
e
r
o
b
o
tic
s
y
s
tem
s
,
s
u
ch
as
th
o
s
e
u
s
in
g
th
e
Do
b
o
t
r
o
b
o
tic
ar
m
.
L
astl
y
,
HSV
-
b
ased
d
etec
tio
n
o
f
f
er
s
f
lex
i
b
ilit
y
,
as
u
s
er
s
ca
n
ad
ju
s
t
th
e
HSV
r
an
g
e
to
ad
ap
t
to
d
if
f
er
en
t
lig
h
tin
g
c
o
n
d
itio
n
s
.
T
h
is
tu
n
in
g
h
elp
s
m
ai
n
tain
h
ig
h
d
etec
tio
n
ac
c
u
r
ac
y
in
v
a
r
io
u
s
en
v
ir
o
n
m
en
ts
.
T
h
e
ac
cu
r
ac
y
o
f
o
b
ject
d
etec
tio
n
u
s
in
g
HSV
an
d
Op
e
n
C
V
d
ep
en
d
s
o
n
s
ev
er
al
k
ey
f
ac
t
o
r
s
,
in
clu
d
in
g
lig
h
tin
g
co
n
d
itio
n
s
,
ca
m
e
r
a
q
u
ality
,
HSV
r
an
g
e
s
ettin
g
s
,
an
d
th
e
clar
ity
o
f
th
e
o
b
ject
’
s
s
h
ap
e
.
B
ased
o
n
ty
p
ical
ex
p
e
r
im
en
ts
an
d
r
ea
l
-
wo
r
ld
ap
p
licatio
n
s
:
i)
C
o
lo
r
d
etec
tio
n
(
HSV
)
−
Un
d
er
n
o
r
m
al
lig
h
tin
g
:
ac
cu
r
a
cy
r
an
g
es f
r
o
m
9
0
–
98
%
.
−
Un
d
er
v
ar
ia
b
le
lig
h
tin
g
o
r
wit
h
s
h
ad
o
ws
:
ac
cu
r
ac
y
d
r
o
p
s
to
8
0
–
90
%
.
−
W
ith
well
-
ca
lib
r
ated
HSV
r
an
g
es a
n
d
co
n
tr
o
lled
lig
h
tin
g
,
ac
cu
r
ac
y
ca
n
r
ea
ch
u
p
to
9
9
%
.
Evaluation Warning : The document was created with Spire.PDF for Python.