I
AE
S
I
nte
rna
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
3
,
No
.
3
,
Sep
tem
b
er
201
4
,
p
p
.
136
~
14
4
I
SS
N:
2252
-
8938
136
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
jo
u
r
n
a
l.c
o
m/o
n
lin
e/in
d
ex
.
p
h
p
/I
J
A
I
Enha
nced Ca
m
er
a
Calibra
tion for
M
a
chine Visio
n u
sing
O
pen
CV
Sh
ub
ha
m
Ro
ha
n Ast
ha
na
C
o
m
p
u
ter
Scien
ce
a
n
d
I
n
f
o
r
m
atio
n
S
y
s
te
m
s
Dep
ar
t
m
en
t,
B
I
T
S
P
ilan
i,
K.
K
B
ir
la
Go
a
C
a
m
p
u
s
I
n
d
ia
Z
u
ar
in
a
g
ar
,
I
n
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
y
2
5
,
2
0
1
4
R
ev
i
s
ed
A
u
g
1
1
,
2
0
1
4
A
cc
ep
ted
A
u
g
2
3
,
2
0
1
4
In
se
v
e
ra
l
m
a
c
h
in
e
v
isio
n
a
p
p
l
i
c
a
ti
o
n
s,
a
f
u
n
d
a
m
e
n
tal
ste
p
is
to
p
re
c
ise
l
y
d
e
term
in
e
th
e
re
latio
n
b
e
tw
e
e
n
th
e
im
a
g
e
o
f
th
e
o
b
jec
t
a
n
d
it
s
p
h
y
sic
a
l
d
im
e
n
sio
n
b
y
p
e
r
f
o
r
m
in
g
a
c
a
li
b
ra
ti
o
n
p
ro
c
e
ss
.
T
h
e
a
i
m
is
to
d
e
v
ise
a
n
e
n
h
a
n
c
e
d
m
e
c
h
a
n
ism
f
o
r
c
a
m
e
ra
c
a
li
b
ra
t
io
n
i
n
o
rd
e
r
to
im
p
ro
v
e
th
e
a
lrea
d
y
e
x
isti
n
g
m
e
th
o
d
s
i
n
Op
e
n
CV.
A
g
o
o
d
c
a
li
b
ra
ti
o
n
is
im
p
o
rtan
t
w
h
e
n
w
e
n
e
e
d
to
re
c
o
n
stru
c
t
a
w
o
rld
m
o
d
e
l
o
r
in
tera
c
t
w
it
h
th
e
w
o
rld
a
s
in
c
a
s
e
o
f
ro
b
o
t,
h
a
n
d
-
e
y
e
c
o
o
rd
in
a
ti
o
n
.
I
n
o
r
d
e
r
to
m
e
e
t
th
e
risin
g
d
e
m
a
n
d
s
fo
r
h
ig
h
e
r
a
c
c
u
ra
c
y
v
a
rio
u
s
c
a
li
b
ra
ti
o
n
tec
h
n
i
q
u
e
s
h
a
v
e
b
e
e
n
d
e
v
e
lo
p
e
d
b
u
t
t
h
e
y
a
r
e
u
n
a
b
le
in
o
b
tain
i
n
g
p
re
c
ise
re
su
lt
s.
In
th
is
p
a
p
e
r
w
e
p
ro
p
o
se
a
n
e
n
h
a
n
c
e
d
c
a
m
e
ra
c
a
li
b
ra
ti
o
n
p
r
o
c
e
d
u
re
u
si
n
g
a
sp
e
c
ial
g
rid
p
a
tt
e
rn
o
f
c
o
n
c
e
n
t
ric circ
le
s
w
it
h
sp
e
c
ial
m
a
r
k
e
rs.
T
h
e
o
v
e
ra
l
l
o
b
jec
ti
v
e
is
to
m
in
im
ize
th
e
re
-
p
ro
jec
ti
o
n
f
o
r
g
o
o
d
c
a
m
e
ra
c
a
li
b
ra
ti
o
n
.
K
ey
w
o
r
d
:
C
a
m
er
a
C
alib
r
atio
n
C
o
n
ce
n
tr
ic
R
i
n
g
P
atter
n
Ma
ch
i
n
e
Vis
io
n
I
m
ag
e
P
r
o
ce
s
s
i
n
g
Co
p
y
rig
h
t
©
2
0
1
4
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
:
Sh
u
b
h
a
m
R
o
h
an
Ast
h
an
a,
C
o
m
p
u
ter
Scien
ce
a
n
d
I
n
f
o
r
m
atio
n
S
y
s
te
m
s
Dep
ar
t
m
en
t,
B
I
T
S
P
ilan
i,
K.
K
B
ir
la
Go
a
C
a
m
p
u
s
I
n
d
ia
Z
u
ar
in
a
g
ar
,
Go
a
-
4
0
3
7
2
6
,
I
n
d
ia
E
m
ail:
as
th
a
n
a.
s
t.
f
r
an
ci
s
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
C
a
m
er
a
ca
lib
r
atio
n
i
s
a
n
ec
es
s
ar
y
s
tep
i
n
3
D
co
m
p
u
ter
v
i
s
i
o
n
in
o
r
d
er
to
ex
tr
ac
t
m
e
tr
ic
in
f
o
r
m
atio
n
f
r
o
m
2
D
i
m
a
g
es.
I
t
h
a
s
b
ee
n
s
tu
d
ied
ex
te
n
s
iv
el
y
i
n
co
m
p
u
t
er
v
is
io
n
a
n
d
p
h
o
to
g
r
a
m
m
etr
i
c.
T
h
e
m
ai
n
ai
m
o
f
ca
m
er
a
ca
lib
r
atio
n
i
s
to
d
eter
m
i
n
e
t
h
e
p
ar
a
m
eter
s
o
f
t
h
e
tr
an
s
f
o
r
m
atio
n
b
et
w
ee
n
an
o
b
j
ec
t
in
3
D
s
p
ac
e
an
d
th
e
2
D
i
m
a
g
e
o
b
s
er
v
ed
b
y
th
e
ca
m
er
a
f
r
o
m
v
is
u
al
i
n
f
o
r
m
atio
n
s
u
c
h
as
i
m
a
g
es.
T
h
e
tr
an
s
f
o
r
m
atio
n
p
ar
am
eter
s
in
cl
u
d
e:
a.
E
x
tr
in
s
ic
p
ar
a
m
eter
s
:
T
h
e
ca
m
er
a’
s
lo
ca
tio
n
an
d
o
r
ien
tati
o
n
in
th
e
w
o
r
ld
w
h
ic
h
is
d
en
o
ted
b
y
r
o
tatio
n
an
d
tr
an
s
lat
io
n
o
f
t
h
e
ca
m
er
a.
b.
I
n
tr
in
s
ic
p
ar
a
m
eter
s
: T
h
e
r
elat
io
n
s
h
ip
b
et
w
ee
n
p
ix
el
co
o
r
d
in
ates a
n
d
ca
m
er
a
co
o
r
d
in
ates.
On
e
o
f
th
e
m
ai
n
u
s
e
s
o
f
ca
m
er
a
ca
lib
r
atio
n
is
to
f
ig
u
r
e
o
u
t
wh
er
e
a
ca
m
er
a
w
as
i
n
r
elatio
n
t
o
a
s
ce
n
e
in
a
p
h
o
to
g
r
ap
h
.
On
e
ca
n
als
o
u
s
e
ca
m
er
a
ca
lib
r
atio
n
to
t
ak
e
an
i
m
a
g
e
s
e
n
t
to
a
co
m
p
u
ter
,
an
d
f
ig
u
r
e
o
u
t
w
h
er
e
v
ar
io
u
s
co
o
r
d
in
ates
ar
e
in
th
e
r
ea
l
w
o
r
ld
.
T
h
is
t
y
p
e
o
f
d
ed
u
ctio
n
i
s
cr
u
cia
l
to
t
h
e
f
u
n
ctio
n
i
n
g
o
f
r
o
b
o
ts
th
at
ar
e
m
ea
n
t
to
i
n
ter
ac
t
v
i
s
u
all
y
w
i
th
t
h
e
p
h
y
s
ica
l
w
o
r
ld
.
T
h
ese
r
o
b
o
ts
ca
n
t
h
en
u
s
e
a
p
h
o
to
g
r
ap
h
ic
o
r
v
id
eo
in
p
u
t,
d
e
v
ice
an
d
ca
lib
r
ate
i
n
o
r
d
er
to
f
ig
u
r
e
o
u
t
w
h
er
e
o
b
j
e
cts
it
s
ee
s
m
i
g
h
t
ac
tu
all
y
b
e
i
n
t
h
e
r
ea
l
w
o
r
ld
,
i
n
ac
tu
al
ter
m
s
o
f
d
is
ta
n
ce
a
n
d
v
ec
to
r
.
C
a
m
er
a
ca
lib
r
atio
n
ca
n
also
b
e
u
s
ed
to
f
ig
u
r
e
o
u
t
o
th
er
th
in
g
s
ab
o
u
t
th
e
ca
m
er
a
in
r
e
la
tio
n
to
th
e
s
ce
n
e
[
6
]
.
Fo
r
ex
a
m
p
le,
u
s
i
n
g
f
o
r
m
u
las
w
e
ca
n
f
i
g
u
r
e
o
u
t
th
e
f
o
ca
l
len
g
th
t
h
at
t
h
e
s
ce
n
e
w
a
s
s
h
o
t
at.
W
e
ca
n
also
f
i
g
u
r
e
o
u
t t
h
e
s
k
e
w
f
ac
to
r
o
f
th
e
i
m
a
g
e,
an
d
a
n
y
len
s
d
is
to
r
tio
n
th
at
m
a
y
h
a
v
e
b
ee
n
i
n
t
r
o
d
u
ce
d
,
cr
ea
tin
g
a
p
in
cu
s
h
io
n
ef
f
ec
t.
W
e
ca
n
als
o
f
ig
u
r
e
o
u
t
w
h
et
h
er
th
e
ac
t
u
a
l
ca
m
er
a
p
ix
els
w
er
e
s
q
u
ar
e
o
r
n
o
t,
an
d
w
h
at
th
e
h
o
r
izo
n
tal
an
d
v
er
tical
s
ca
li
n
g
f
ac
to
r
s
f
o
r
th
e
p
i
x
els
m
i
g
h
t
h
a
v
e
b
ee
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
E
n
h
a
n
ce
d
C
a
mera
C
a
lib
r
a
tio
n
fo
r
Ma
ch
in
e
V
is
io
n
u
s
in
g
O
p
en
C
V
…. (
S
h
u
b
h
a
m
R
o
h
a
n
A
s
th
a
n
a
)
137
T
h
e
ca
lib
r
atio
n
p
r
o
ce
d
u
r
e
ty
p
icall
y
co
n
s
i
s
ts
o
f
eit
h
er
lo
ca
lizin
g
t
h
e
ca
lib
r
atio
n
p
atter
n
co
n
tr
o
l
p
o
in
t
s
s
u
c
h
as
s
q
u
ar
e
co
r
n
er
s
[
1
]
o
r
cir
cle
ce
n
tr
es
[
2
]
an
d
th
en
s
o
lv
in
g
f
o
r
th
e
ca
m
er
a
p
ar
a
m
e
ter
s
,
o
r
u
s
in
g
s
o
m
e
g
eo
m
etr
ic
p
r
o
p
er
ty
o
f
th
e
p
att
er
n
its
el
f
to
s
o
lv
e
f
o
r
th
e
ca
m
e
r
a
p
ar
am
eter
s
d
ir
ec
tl
y
.
Ho
w
e
v
er
,
a
m
aj
o
r
s
o
u
r
ce
o
f
er
r
o
r
th
at
af
f
ec
t
s
t
h
i
s
ca
m
er
a
ca
lib
r
atio
n
ap
p
r
o
ac
h
o
f
e
ith
er
lo
ca
lizin
g
th
e
co
n
tr
o
l
p
o
in
t
o
r
u
s
in
g
g
e
o
m
e
tr
ic
p
r
o
p
er
ties
o
f
th
e
p
atter
n
d
ir
ec
tl
y
,
is
th
a
t
th
e
i
n
p
u
t
ca
m
er
a
ca
lib
r
atio
n
i
m
a
g
es
ar
e
n
o
n
-
f
r
o
n
to
p
ar
allel
i
m
ag
e
s
(
d
if
f
er
en
t
o
r
ien
tatio
n
s
w
it
h
r
esp
ec
t
to
th
e
ca
m
er
a
)
th
at
s
u
f
f
er
f
r
o
m
n
o
n
li
n
ea
r
d
is
to
r
tio
n
d
u
e
to
ca
m
er
a
o
p
tics
an
d
th
e
p
er
s
p
ec
ti
v
e
th
e
ca
m
er
a
len
s
r
ec
eiv
e
s
.
T
h
er
ef
o
r
e,
p
r
ec
is
e
lo
ca
lizatio
n
o
f
co
n
tr
o
l
p
o
in
ts
o
r
ac
cu
r
ate
d
eter
m
in
a
tio
n
o
f
g
eo
m
etr
ic
p
r
o
p
er
ties
u
n
d
er
s
u
ch
co
n
d
itio
n
s
is
a
v
er
y
d
if
f
ic
u
lt ta
s
k
,
w
h
er
e
ev
e
n
s
m
all
er
r
o
r
s
m
a
y
lead
to
i
m
p
r
ec
is
e
ca
m
er
a
ca
lib
r
atio
n
.
I
n
t
h
is
p
ap
er
,
th
e
i
n
te
n
s
io
n
i
s
to
r
ed
u
ce
th
is
er
r
o
r
b
y
a
c
o
n
s
id
er
ab
le
a
m
o
u
n
t
b
y
u
s
i
n
g
a
g
r
id
o
f
co
n
ce
n
tr
ic
cir
cle
s
w
i
th
s
p
ec
ial
m
ar
k
er
s
.
I
t
h
elp
s
i
n
t
h
e
ac
c
u
r
ate
p
o
s
itio
n
i
n
g
o
f
co
n
tr
o
l
p
o
in
ts
.
T
h
is
u
n
i
q
u
e
n
ess
in
d
eter
m
in
i
n
g
o
r
ien
ta
tio
n
r
e
d
u
ce
s
t
h
e
er
r
o
r
th
at
ar
i
s
es
d
u
e
to
i
m
b
ala
n
ce
i
n
co
n
s
tr
u
ct
io
n
o
f
th
e
ca
lib
r
atio
n
o
b
j
ec
t.
E
d
g
e
d
etec
tio
n
,
ellip
s
e
f
itti
n
g
an
d
co
n
to
u
r
d
etec
tio
n
is
u
s
ed
to
lo
ca
te
th
ese
co
n
ce
n
tr
ic
cir
cles,
t
h
e
w
ei
g
h
ted
m
ea
n
o
f
th
eir
r
ad
ii
g
iv
e
s
th
e
cir
cle
ce
n
tr
es
as
t
h
e
co
n
tr
o
l
p
o
in
ts
.
C
a
m
er
a
p
ar
a
m
eter
s
ar
e
o
b
tain
ed
f
r
o
m
t
h
ese
ac
cu
r
ate
co
n
tr
o
l
p
o
in
ts
.
T
h
e
s
tr
u
ct
u
r
e
o
f
th
is
ar
t
icle
is
as
f
o
llo
w
s
.
I
n
s
ec
tio
n
2
w
e
s
u
m
m
ar
ize
t
h
e
r
elate
d
w
o
r
k
in
ar
ea
o
f
ca
m
er
a
ca
lib
r
atio
n
.
Nex
t,
in
Sectio
n
3
w
e
d
escr
ib
e
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
f
o
r
ca
lib
r
atin
g
t
h
e
ca
m
er
a.
Sectio
n
4
co
v
er
s
th
e
e
x
p
er
i
m
e
n
tal
r
e
s
u
lt
s
w
h
ich
ar
e
f
o
llo
w
ed
b
y
co
n
clu
s
io
n
a
n
d
f
u
t
u
r
e
w
o
r
k
co
v
er
ed
i
n
Sectio
n
5
.
2.
RE
L
AT
E
D
WO
RK
T
h
e
in
itial
w
o
r
k
in
t
h
e
f
ield
o
f
ca
m
er
a
ca
lib
r
atio
n
s
tar
ted
w
it
h
t
h
e
u
s
e
o
f
s
q
u
ar
es a
s
co
n
tr
o
l
p
o
in
ts
b
y
T
s
ai
[
3
]
in
w
h
ic
h
u
s
ed
6
0
co
n
tr
o
l
p
o
in
ts
to
d
eter
m
i
n
e
t
h
e
ca
m
er
a
p
o
s
itio
n
an
d
o
r
ien
tati
o
n
p
ar
a
m
eter
s
a
lo
n
g
w
it
h
f
o
ca
l
len
g
th
a
n
d
r
ad
ial
len
s
d
is
to
r
tio
n
.
T
s
ai’
s
ca
li
b
r
atio
n
ap
p
r
o
ac
h
p
r
esu
m
e
s
th
at
s
o
m
e
ca
m
er
a
p
ar
am
eter
s
ar
e
p
r
o
v
id
ed
b
y
m
an
u
f
ac
t
u
r
er
to
m
i
n
i
m
ize
th
e
i
n
itial
g
u
e
s
s
o
f
t
h
e
esti
m
atio
n
.
I
n
o
r
d
er
t
o
s
o
lv
e
th
e
ca
lib
r
atio
n
p
r
o
b
lem
it
r
eq
u
ir
es
n
f
ea
t
u
r
e
p
o
in
ts
p
er
i
m
a
g
e
to
s
o
lv
e
a
s
et
o
f
n
li
n
ea
r
eq
u
atio
n
s
w
h
ic
h
ar
e
b
ased
o
n
r
ad
ial
alig
n
m
e
n
t r
estra
i
n
t.
Z
h
a
n
g
[
1
]
f
ir
s
t
ti
m
e
p
r
o
p
o
s
ed
to
u
s
e
a
p
lan
ar
ch
ec
k
er
b
o
ar
d
p
atter
n
w
h
ic
h
r
eq
u
ir
ed
o
n
l
y
a
f
e
w
s
et
o
f
i
m
a
g
es
to
ca
lc
u
late
t
h
e
ca
lib
r
atio
n
p
ar
a
m
eter
s
.
T
h
e
p
r
o
p
o
s
ed
tech
n
iq
u
e
i
s
s
u
c
h
t
h
at
ei
th
er
th
e
ca
m
er
a
o
r
ca
lib
r
atio
n
p
atter
n
ca
n
b
e
m
o
v
ed
f
r
ee
l
y
ir
r
esp
ec
tiv
e
o
f
d
ir
ec
tio
n
o
f
m
o
tio
n
w
h
ic
h
i
s
in
s
i
g
n
i
f
ican
t
to
th
e
alg
o
r
ith
m
.
T
h
e
ap
p
r
o
ac
h
o
n
ly
r
eq
u
ir
es
th
e
ca
m
er
a
to
o
b
s
er
v
e
a
p
lan
ar
p
atter
n
s
h
o
w
n
at
a
m
in
i
m
u
m
o
f
t
w
o
d
if
f
er
e
n
t
o
r
ien
tatio
n
s
.
T
h
e
ap
p
r
o
ac
h
co
n
s
is
ted
o
f
an
i
n
it
ial
clo
s
ed
f
o
r
m
s
o
lu
t
io
n
o
f
t
h
e
ca
m
er
a
p
ar
a
m
eter
s
,
f
o
ll
o
w
ed
b
y
a
n
o
n
li
n
ea
r
r
ef
i
n
e
m
en
t u
s
in
g
L
ev
e
n
b
er
g
-
Ma
r
q
u
ar
d
t.
C
h
e
n
et
al.
[
4
]
d
escr
ib
es a
ca
lib
r
atio
n
p
r
o
ce
d
u
r
e
th
at
u
s
e
s
o
n
l
y
a
s
i
n
g
le
i
m
ag
e
o
f
t
w
o
co
p
lan
ar
cir
cles
w
it
h
ar
b
itra
r
y
r
ad
iu
s
.
T
h
eir
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
aim
s
to
ca
lc
u
late
b
o
th
t
h
e
f
o
ca
l
len
g
t
h
an
d
ex
t
r
in
s
ic
ca
m
er
a
p
ar
am
eter
s
s
i
m
u
l
tan
eo
u
s
l
y
.
O
n
e
d
r
a
w
b
ac
k
o
f
t
h
is
ap
p
r
o
ac
h
is
th
at
th
e
f
ea
t
u
r
es
it
r
elies
o
n
ca
n
n
o
t
h
an
d
le
t
h
e
n
o
n
-
li
n
ea
r
d
is
to
r
tio
n
b
y
it
s
el
f
b
ec
au
s
e
i
t
is
n
o
t
p
o
s
s
ib
le
to
d
is
tin
g
u
i
s
h
i
f
t
h
e
d
if
f
er
e
n
ce
in
t
h
e
f
ea
tu
r
e
p
ar
am
eter
s
co
m
es
f
r
o
m
t
h
e
d
is
to
r
tio
n
o
r
f
r
o
m
p
r
o
j
ec
tiv
e
ef
f
e
cts.
Heik
k
ila
i
n
[
5
]
u
s
e
s
s
o
lid
cir
c
les
as
co
n
tr
o
l
p
o
in
ts
a
n
d
u
s
es
a
n
o
n
r
ec
u
r
s
i
v
e
tec
h
n
iq
u
e
f
o
r
r
ev
er
s
in
g
th
e
d
is
to
r
tio
n
m
o
d
el.
T
h
e
alg
o
r
ith
m
p
er
f
o
r
m
ed
a
m
in
i
m
iza
ti
o
n
o
v
er
th
e
w
e
ig
h
ted
s
u
m
o
f
s
q
u
ar
ed
d
if
f
er
en
ce
s
b
et
w
ee
n
t
h
e
o
b
s
er
v
at
io
n
a
n
d
th
e
ca
m
er
a
m
o
d
el
u
s
in
g
L
e
v
en
b
er
g
-
Ma
r
q
u
ar
d
t.
T
h
e
tech
n
iq
u
es
e
m
p
lo
y
ed
b
y
T
s
ai,
Heik
k
ila
an
d
Z
h
an
g
’
s
al
l
u
s
e
t
h
e
p
in
h
o
le
p
r
o
j
ec
tiv
e
m
o
d
el
to
m
ap
th
r
ee
d
i
m
e
n
s
io
n
a
l
s
ce
n
es
to
t
h
e
t
w
o
d
i
m
en
s
io
n
al
ca
m
er
a
i
m
ag
e
p
la
n
e.
3.
P
RO
P
O
SE
D
AP
P
RO
ACH
T
h
er
e
ar
e
tw
o
m
aj
o
r
s
o
u
r
ce
s
o
f
er
r
o
r
th
at
h
a
v
e
ad
v
er
s
e
ef
f
ec
ts
o
n
ca
lib
r
atio
n
r
es
u
lts
.
T
h
e
f
ir
s
t
o
n
e
i
s
th
e
i
m
p
er
f
ec
tio
n
o
f
t
h
e
ca
li
b
r
atio
n
o
b
j
ec
t.
Sin
ce
th
e
as
s
u
m
p
tio
n
s
m
ad
e
f
o
r
th
e
co
n
v
e
n
tio
n
al
ca
m
er
a
ca
lib
r
atio
n
ar
e
b
ased
o
n
a
p
e
r
f
ec
t
p
lan
ar
tar
g
et
w
it
h
id
ea
l
p
atter
n
s
,
th
e
i
m
p
r
ec
is
io
n
o
f
t
h
e
ca
lib
r
atio
n
tar
g
et
m
a
y
lead
to
in
ac
c
u
r
ate
r
es
u
lts
.
T
h
e
s
ec
o
n
d
p
r
o
b
lem
i
s
th
e
u
n
ce
r
tain
t
y
i
n
lo
ca
ti
n
g
t
h
e
co
n
t
r
o
l
p
o
in
ts
d
ir
ec
tl
y
f
r
o
m
t
h
e
g
eo
m
etr
ies
o
f
t
h
e
ca
l
ib
r
atio
n
p
atter
n
s
in
t
h
e
ca
p
tu
r
ed
r
aw
i
m
a
g
es
w
h
ic
h
s
u
f
f
er
s
f
r
o
m
le
n
s
d
is
to
r
tio
n
as
w
e
ll a
s
p
er
s
p
ec
tiv
e
d
is
to
r
tio
n
[
2
]
.
I
n
o
r
d
er
to
d
ea
l
w
it
h
t
h
e
ab
o
v
e
er
r
o
r
s
w
e
p
r
o
p
o
s
e
to
u
s
e
a
len
s
d
is
to
r
tio
n
m
o
d
el
w
h
ich
tak
es
in
to
ac
co
u
n
t
ta
n
g
en
t
ial
an
d
r
ad
ial
d
is
to
r
tio
n
.
an
d
u
s
i
n
g
a
f
r
o
n
tal
i
m
a
g
e
co
n
ce
p
t
ac
h
iev
e
s
p
r
ec
is
e
lo
ca
lizat
io
n
o
f
co
n
tr
o
l
p
o
in
ts
.
W
e
tak
e
an
i
n
p
u
t
is
a
s
et
o
f
2
4
i
m
ag
e
s
,
ea
ch
h
a
v
i
n
g
d
i
f
f
er
en
t
o
r
ien
ta
tio
n
s
o
f
th
e
p
atter
n
w
it
h
r
esp
ec
t to
th
e
ca
m
er
a.
T
h
e
p
atter
n
is
o
f
s
p
ec
ial
t
y
p
e
w
h
er
ein
th
er
e
is
a
g
r
id
o
f
co
n
ce
n
tr
ic
r
i
n
g
s
.
E
ac
h
s
u
ch
u
n
it
is
m
ad
e
u
p
o
f
f
o
u
r
c
ir
cl
es
w
i
th
t
h
e
e
x
ce
p
tio
n
o
f
th
r
ee
u
n
it
s
t
h
at
h
av
e
f
iv
e
co
n
ce
n
tr
ic
ci
r
cles.
T
h
ese
t
h
r
ee
p
atter
n
s
also
ca
lled
th
e
m
ar
k
er
p
o
in
ts
o
f
t
h
e
i
m
a
g
e
an
d
ar
e
p
o
s
itio
n
ed
at
th
e
co
r
n
er
s
o
f
th
e
i
m
a
g
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
3
,
No
.
3
,
Sep
tem
b
er
20
1
4
:
1
3
6
–
1
4
4
138
E
ac
h
m
ar
k
er
p
o
in
t
ca
n
b
e
u
n
i
q
u
el
y
id
en
ti
f
ied
b
ased
o
n
th
ei
r
m
u
t
u
al
d
is
t
a
n
ce
an
d
h
en
ce
a
cts
lik
e
t
h
e
co
o
r
d
in
ate
ax
is
w
h
ich
h
elp
s
t
o
d
ef
in
e
an
o
r
ie
n
tatio
n
o
f
th
e
i
m
a
g
e.
(
R
e
f
er
Fig
u
r
e
1
)
.
S
u
c
h
a
p
atter
n
h
elp
s
to
d
is
tin
g
u
is
h
b
et
w
ee
n
t
w
o
i
m
a
g
es
m
o
r
e
ac
c
u
r
atel
y
as
i
n
t
h
is
r
i
n
g
p
atter
n
v
er
tical
an
d
h
o
r
izo
n
tal
r
o
tatio
n
s
m
ea
n
t
d
if
f
er
e
n
t i
m
ag
e
s
,
w
h
ic
h
w
a
s
n
o
t so
in
ch
es
s
b
o
ar
d
.
Fig
u
r
e
1
.
Gr
id
o
f
co
n
ce
n
tr
ic
cir
cles (
On
e
o
f
t
h
e
i
n
p
u
t i
m
a
g
es.
A
r
r
o
w
s
d
en
o
te
t
h
e
th
r
ee
m
ar
k
er
cir
cles)
Fig
u
r
e
2
.
Fau
lt
y
an
d
n
o
cir
cles
d
etec
ted
in
th
e
p
atter
n
u
s
i
n
g
c
v
Ho
u
g
h
C
ir
cle
s
Fig
u
r
e
3
.
Dete
ctin
g
cir
cles b
y
f
itti
n
g
ellip
s
e
s
an
d
m
in
i
m
u
m
b
o
u
n
d
i
n
g
b
o
x
es o
v
er
th
e
d
etec
t
ed
co
n
to
u
r
s
in
t
h
e
i
m
a
g
e.
Fig
u
r
e
4
.
Dete
cted
ce
n
ter
s
o
f
t
h
e
cir
cles i
n
th
e
p
atter
n
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
E
n
h
a
n
ce
d
C
a
mera
C
a
lib
r
a
tio
n
fo
r
Ma
ch
in
e
V
is
io
n
u
s
in
g
O
p
en
C
V
…. (
S
h
u
b
h
a
m
R
o
h
a
n
A
s
th
a
n
a
)
139
T
h
e
u
s
es
o
f
co
n
ce
n
tr
ic
cir
cle
s
h
elp
i
m
p
r
o
v
e
th
e
ca
lib
r
atio
n
p
r
o
ce
d
u
r
e.
T
h
is
is
d
u
e
to
t
h
e
f
ac
t
a
s
in
g
le,
lar
g
e
co
n
ce
n
tr
ic
cir
cle
i
m
ag
e
m
a
y
,
h
o
w
e
v
er
,
s
u
f
f
er
f
r
o
m
n
o
n
l
in
ea
r
d
is
to
r
tio
n
le
ad
in
g
to
in
ac
c
u
r
ate
d
eter
m
in
at
io
n
o
f
g
eo
m
etr
ic
p
r
o
p
er
ties
o
f
t
h
e
co
n
ce
n
tr
ic
cir
cl
e,
an
d
t
h
er
ef
o
r
e,
in
ac
c
u
r
ate
ca
m
er
a
ca
lib
r
atio
n
.
A
g
r
id
o
f
co
n
ce
n
tr
ic
cir
cle
s
,
o
n
t
h
e
o
th
er
h
a
n
d
,
is
les
s
s
u
s
ce
p
ti
b
le
to
d
is
to
r
tio
n
ef
f
ec
t
s
.
T
h
is
ap
p
r
o
ac
h
co
m
p
r
is
e
o
f
t
h
e
s
e
s
tep
s
:
1.
Dete
ctio
n
o
f
cir
cle
s
in
ea
c
h
i
m
ag
e
2.
Usi
n
g
t
h
e
d
etec
ted
cir
cles,
f
i
n
d
in
g
t
h
e
ce
n
ter
o
f
ea
c
h
o
f
t
h
e
co
n
ce
n
tr
ic
r
in
g
p
atter
n
3.
Seg
r
eg
a
tin
g
t
h
ese
ce
n
ter
s
as
m
ar
k
er
o
r
n
o
n
-
m
ar
k
er
p
o
in
t
s
4.
A
r
r
an
g
e
m
en
t o
f
all
t
h
e
ce
n
ter
p
o
in
ts
in
a
s
y
s
te
m
atic
o
r
d
er
th
at
is
u
n
i
v
er
s
all
y
f
o
llo
w
ed
f
o
r
a
ll i
m
a
g
es
5.
B
y
t
h
e
u
s
e
o
f
t
h
ese
o
r
d
er
ed
ce
n
ter
p
o
in
ts
,
ca
lib
r
ati
n
g
t
h
e
ca
m
er
a
6.
C
r
ea
tin
g
t
h
e
f
r
o
n
ta
l i
m
a
g
e
f
o
r
ea
ch
i
m
a
g
e
b
y
t
h
e
u
s
e
o
f
t
h
e
p
ar
a
m
eter
s
d
er
iv
ed
f
r
o
m
ca
m
er
a
ca
lib
r
atio
n
3
.
1
Det
ec
t
io
n o
f
Circ
les in E
a
ch
I
m
a
g
e
T
h
e
f
ir
s
t
tas
k
i
n
v
o
l
v
es
d
e
v
is
in
g
a
n
al
g
o
r
ith
m
to
d
etec
t
t
h
ese
cir
cles
w
it
h
m
i
n
i
m
u
m
p
o
s
s
ib
le
er
r
o
r
m
ar
g
i
n
.
Fo
r
th
i
s
p
u
r
p
o
s
e,
th
er
e
ar
e
t
w
o
g
e
n
er
a
l a
p
p
r
o
ac
h
es:
3
.
1
.
1
H
o
ug
h T
ra
ns
f
o
r
m
T
h
e
Ho
u
g
h
tr
an
s
f
o
r
m
[
7
]
is
a
f
ea
t
u
r
e
ex
tr
ac
tio
n
tec
h
n
iq
u
e
u
s
ed
in
i
m
a
g
e
a
n
al
y
s
i
s
,
co
m
p
u
t
er
v
is
io
n
,
an
d
d
ig
ital
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
.
T
h
e
p
u
r
p
o
s
e
o
f
th
e
tech
n
iq
u
e
is
to
f
i
n
d
i
m
p
er
f
ec
t
i
n
s
ta
n
ce
s
o
f
o
b
j
ec
ts
w
it
h
in
a
ce
r
tain
cla
s
s
o
f
s
h
ap
es
b
y
a
v
o
tin
g
p
r
o
ce
d
u
r
e.
T
h
is
v
o
tin
g
p
r
o
ce
d
u
r
e
is
ca
r
r
ied
o
u
t
i
n
a
p
ar
a
m
eter
s
p
ac
e,
f
r
o
m
w
h
ic
h
o
b
j
ec
t
ca
n
d
id
ates
ar
e
o
b
tain
ed
as
lo
ca
l
m
a
x
i
m
a
in
a
s
o
-
ca
lled
ac
cu
m
u
lato
r
s
p
ac
e
th
at
is
ex
p
licit
l
y
co
n
s
tr
u
cted
b
y
t
h
e
al
g
o
r
ith
m
f
o
r
co
m
p
u
ti
n
g
th
e
Ho
u
g
h
tr
an
s
f
o
r
m
.
W
e
u
s
ed
a
f
u
n
ctio
n
ca
lled
cv
Ho
u
g
h
C
ir
cles
w
h
ic
h
a
v
ailab
le
i
n
Op
en
C
V.
I
n
o
r
d
er
to
u
s
e
t
h
is
f
u
n
ctio
n
,
p
r
e
-
p
r
o
ce
s
s
i
n
g
i
s
r
eq
u
ir
ed
o
n
th
e
i
m
a
g
es.
T
h
is
p
r
e
-
p
r
o
ce
s
s
in
g
in
cl
u
d
es:
a.
T
h
r
esh
o
ld
in
g
,
w
h
ic
h
is
th
e
s
i
m
p
lest
m
et
h
o
d
o
f
i
m
ag
e
s
e
g
m
en
tatio
n
.
I
m
a
g
e
s
e
g
m
en
ta
ti
o
n
[
8
]
is
th
e
p
r
o
ce
s
s
o
f
p
ar
titi
o
n
i
n
g
a
d
i
g
ital
i
m
a
g
e
i
n
to
m
u
ltip
le
s
eg
m
e
n
t
s
(
s
et
s
o
f
p
ix
el
s
)
.
T
h
e
g
o
al
o
f
s
eg
m
e
n
tatio
n
is
to
s
i
m
p
li
f
y
a
n
d
/o
r
ch
an
g
e
t
h
e
r
ep
r
esen
ta
tio
n
o
f
a
n
i
m
a
g
e
i
n
to
s
o
m
e
th
i
n
g
th
at
i
s
m
o
r
e
m
ea
n
in
g
f
u
l
an
d
ea
s
ier
to
an
al
y
ze
.
Her
e
th
e
i
m
ag
e
i
s
d
iv
id
ed
in
to
f
o
r
eg
r
o
u
n
d
a
n
d
b
ac
k
g
r
o
u
n
d
s
u
p
er
p
ix
els.
Fro
m
a
g
r
e
y
s
ca
le
i
m
a
g
e,
th
r
es
h
o
ld
in
g
ca
n
b
e
u
s
ed
to
cr
ea
te
b
in
ar
y
i
m
a
g
es.
I
n
Op
e
n
C
V,
t
h
i
s
is
i
m
p
le
m
en
ted
u
s
i
n
g
cv
Th
r
esh
o
ld
fu
n
ctio
n
.
b.
E
d
g
e
d
etec
tio
n
[
9
]
is
t
h
e
n
a
m
e
f
o
r
a
s
et
o
f
m
ath
e
m
atica
l
m
eth
o
d
s
w
h
ic
h
ai
m
at
id
en
ti
f
y
i
n
g
p
o
in
ts
i
n
a
d
ig
ital
i
m
a
g
e
at
w
h
ich
t
h
e
i
m
ag
e
b
r
ig
h
t
n
ess
ch
a
n
g
es
s
h
a
r
p
ly
o
r
,
m
o
r
e
f
o
r
m
all
y
,
h
as
d
is
co
n
ti
n
u
ities
.
T
h
e
p
o
in
ts
at
w
h
ic
h
i
m
a
g
e
b
r
ig
h
t
n
e
s
s
ch
a
n
g
es
s
h
ar
p
l
y
ar
e
ty
p
ica
ll
y
o
r
g
a
n
ized
in
to
a
s
et
o
f
cu
r
v
ed
li
n
e
s
eg
m
e
n
ts
ter
m
ed
ed
g
es.
I
n
Op
en
C
V,
t
h
i
s
is
i
m
p
le
m
e
n
ted
u
s
i
n
g
cv
C
a
n
n
y
f
u
n
ctio
n
.
Af
ter
t
h
is
p
r
e
-
p
r
o
ce
s
s
i
n
g
,
w
h
e
n
Ho
u
g
h
tr
an
s
f
o
r
m
w
as
i
m
p
le
m
en
ted
f
a
u
lt
y
r
esu
lts
w
er
e
ac
h
iev
ed
lik
e
d
etec
tio
n
o
f
n
o
cir
cle
s
,
d
r
aw
i
n
g
i
n
ap
p
r
o
p
r
iate
cir
cles
w
i
th
g
r
ea
tl
y
d
ev
iated
ce
n
ter
s
o
r
d
r
a
w
i
n
g
m
u
lt
ip
les
c
ir
cles o
n
o
n
e
cir
cle.
(
R
e
f
er
to
F
ig
u
r
e
2
)
Su
ch
er
r
o
r
s
w
er
e
d
u
e
to
th
e
f
ac
t:
a.
T
h
e
f
u
n
ctio
n
cv
Ho
u
g
h
C
ir
cle
s
ask
s
f
o
r
a
p
ar
a
m
eter
w
h
ich
is
th
e
m
in
i
m
u
m
d
is
ta
n
ce
b
et
w
ee
n
ce
n
ter
s
o
f
t
w
o
c
ir
cles
to
b
e
d
et
ec
ted
a
n
d
s
h
o
u
ld
b
e
a
n
o
n
-
ze
r
o
p
o
s
iti
v
e
n
u
m
b
er
.
He
n
ce
,
s
u
c
h
p
r
o
ce
d
u
r
e
ca
n
n
o
t
b
e
u
s
ed
to
d
etec
t c
o
n
ce
n
tr
ic
cir
cl
es a
s
th
e
s
e
cir
cles
h
av
e
ze
r
o
d
is
tan
ce
b
et
w
ee
n
th
e
ir
ce
n
ter
s
.
b.
Sin
ce
th
e
i
m
ag
e
s
w
er
e
i
n
cli
n
ed
,
th
e
r
i
n
g
s
p
r
esen
t
i
n
t
h
e
i
m
ag
e
w
er
e
n
o
m
o
r
e
cir
c
u
l
ar
,
b
u
t
i
n
s
tead
ellip
tical
(
An
i
n
cli
n
ed
cir
cle
w
h
en
s
ee
n
f
r
o
m
f
r
o
n
t v
ie
w
ap
p
ea
r
s
lik
e
ellip
s
e)
.
T
h
u
s
,
an
alg
o
r
it
h
m
w
as
r
eq
u
i
r
ed
th
at
d
etec
ts
ellip
s
es
as
t
h
a
t
p
r
o
ce
d
u
r
e
w
o
u
ld
b
e
g
e
n
er
ali
ze
d
s
in
ce
cir
cles a
r
e
also
s
p
ec
ial
ca
s
es o
f
ellip
s
e
w
h
er
ein
ec
ce
n
tr
ici
t
y
=
1
(
i.e
.
m
aj
o
r
an
d
m
i
n
o
r
ax
is
ar
e
eq
u
al
to
r
ad
iu
s
)
.
3
.
1
.
2
.
E
llip
s
e
Det
ec
t
io
n
Du
e
to
th
e
d
r
a
w
b
ac
k
s
o
f
Ho
u
g
h
T
r
an
s
f
o
r
m
,
s
ec
o
n
d
ap
p
r
o
ac
h
w
as c
ar
r
ied
o
u
t f
o
r
t
h
e
p
u
r
p
o
s
e.
I
t in
v
o
lv
ed
:
a.
First
t
h
e
r
a
w
i
m
a
g
e
n
ee
d
s
t
o
b
e
lo
ad
ed
,
f
o
llo
w
ed
b
y
p
r
e
-
p
r
o
ce
s
s
i
n
g
.
T
h
e
p
r
e
-
p
r
o
ce
s
s
in
g
i
n
v
o
lv
e
s
co
n
v
er
ti
n
g
t
h
e
r
a
w
i
m
a
g
e
to
g
r
e
y
s
ca
le
(
u
s
i
n
g
cv
C
vt
C
o
lo
r
f
u
n
ctio
n
)
an
d
Gau
s
s
ia
n
b
l
u
r
s
i
t
(
u
s
i
n
g
cv
B
lu
r
)
.
b.
T
h
r
esh
o
ld
in
g
w
as
ap
p
lied
o
n
t
h
e
p
r
e
-
p
r
o
ce
s
s
ed
i
m
a
g
e
u
s
i
n
g
th
e
cv
Th
r
e
s
h
o
ld
f
u
n
ctio
n
w
it
h
a
th
r
es
h
o
ld
v
alu
e
o
f
1
0
0
.
T
h
is
v
al
u
e
w
as
u
s
ed
d
u
e
to
th
e
f
ac
t
t
h
at
in
t
h
e
i
m
a
g
es
w
h
ich
w
er
e
i
n
cli
n
ed
b
y
a
v
er
y
lar
g
e
an
g
le
w
it
h
r
esp
ec
t
to
t
h
e
p
lan
e
o
f
p
r
o
j
ec
tio
n
,
th
e
f
u
r
th
er
m
o
s
t
p
o
in
t
s
a
f
ter
t
h
r
esh
o
ld
i
n
g
w
it
h
o
th
er
v
alu
e
s
w
er
e
b
ec
o
m
in
g
al
m
o
s
t
b
lu
r
o
r
w
as g
e
tti
n
g
d
i
f
f
u
s
ed
w
ith
o
th
er
co
n
ce
n
tr
ic
r
in
g
s
.
c.
Usi
n
g
cv
F
in
d
C
o
n
to
u
r
f
u
n
ctio
n
o
n
th
e
t
h
r
es
h
o
ld
ed
i
m
ag
e,
th
e
co
n
to
u
r
s
p
r
ese
n
t
in
t
h
e
i
m
a
g
e
w
er
e
f
o
u
n
d
.
C
o
n
to
u
r
tr
ac
in
g
i
s
o
n
e
o
f
m
a
n
y
p
r
e
-
p
r
o
ce
s
s
i
n
g
tech
n
i
q
u
es
p
er
f
o
r
m
ed
o
n
d
ig
i
ta
l
i
m
a
g
es
i
n
o
r
d
er
to
ex
tr
ac
t in
f
o
r
m
atio
n
ab
o
u
t th
eir
g
en
er
al
s
h
ap
e.
T
h
ese
co
n
to
u
r
s
ar
e
s
av
ed
s
ep
ar
atel
y
in
co
n
to
u
r
v
ec
to
r
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
3
,
No
.
3
,
Sep
tem
b
er
20
1
4
:
1
3
6
–
1
4
4
140
d.
Fo
u
n
d
t
h
e
m
i
n
i
m
u
m
b
o
u
n
d
i
n
g
r
ec
tan
g
le
u
s
in
g
cv
Min
A
r
ea
R
ec
t
an
d
m
in
i
m
u
m
b
o
u
n
d
in
g
ellip
s
e
u
s
i
n
g
cv
F
itEllip
s
e
f
u
n
ctio
n
.
(
R
e
f
er
t
o
F
ig
u
r
e
3
)
e.
C
en
ter
s
o
f
th
e
s
e
f
itted
ellip
s
es
ar
e
u
s
ed
as c
en
ter
s
f
o
r
f
u
r
th
er
p
r
o
ce
s
s
.
3
.
2
.
Usi
ng
t
he
Det
ec
t
ed
Circ
les,
F
ind
ing
t
he
Cent
er
o
f
E
a
ch
o
f
t
he
Co
ncent
ric
Ring
P
a
t
t
e
rn
First
a
lin
k
ed
li
s
t
o
f
ce
n
ter
s
o
f
all
t
h
e
b
in
d
i
n
g
ellip
s
e
s
w
a
s
cr
ea
ted
h
av
i
n
g
a
u
s
er
-
d
ef
in
ed
d
ata
t
y
p
e
w
it
h
attr
ib
u
tes
as
X
an
d
Y
co
o
r
d
in
ates
o
f
th
e
ce
n
ter
,
co
u
n
t
o
f
th
e
n
u
m
b
er
o
f
cir
cles
w
h
o
s
e
w
ei
g
h
ted
m
ea
n
w
o
u
ld
b
e
tak
e
n
to
f
i
n
d
f
i
n
al
c
en
ter
v
a
lu
e
s
an
d
a
v
al
u
e
t
h
at
i
s
p
r
o
p
o
r
tio
n
al
to
cu
b
e
o
f
ar
ea
o
f
b
in
d
i
n
g
ellip
s
e
.
T
h
is
v
al
u
e
w
o
u
ld
b
e
u
s
ed
a
s
w
eig
h
t
f
o
r
f
i
n
d
i
n
g
t
h
e
w
ei
g
h
ted
m
ea
n
.
T
h
e
p
u
s
h
an
d
p
o
p
f
u
n
ctio
n
s
w
er
e
esp
ec
iall
y
d
esi
g
n
ed
f
o
r
th
e
p
u
r
p
o
s
e.
T
h
e
p
u
s
h
f
u
n
ct
io
n
w
as
i
m
p
le
m
en
ted
in
s
u
c
h
a
w
a
y
th
a
t
if
th
e
lin
k
ed
lis
t
w
as
e
m
p
t
y
t
h
e
n
j
u
s
t
ad
d
s
th
e
p
o
in
t
s
as
n
o
d
es
else
tr
av
er
s
e
alo
n
g
th
e
l
is
t
a
n
d
ch
ec
k
w
h
eth
er
an
y
alr
ea
d
y
e
x
is
t
in
g
p
o
in
t
w
as
a
t
an
ep
s
i
lo
n
d
is
tan
ce
f
r
o
m
th
e
p
o
in
t.
T
h
is
ep
s
ilo
n
v
alu
e
d
ep
en
d
s
o
n
t
h
e
i
m
ag
e,
th
at
th
is
d
is
tan
ce
is
le
s
s
th
a
n
t
h
e
d
if
f
er
en
c
e
b
et
w
ee
n
ce
n
ter
s
o
f
ad
j
ac
en
t
c
i
r
cles.
I
f
tr
u
e,
th
e
n
to
o
k
t
h
e
w
e
ig
h
ted
m
ea
n
o
f
th
e
alr
ea
d
y
e
x
i
s
tin
g
p
o
in
t
a
n
d
t
h
e
p
ass
ed
p
o
in
t
b
ased
o
n
cu
b
ic
p
o
w
er
o
f
a
v
al
u
e.
T
h
is
v
alu
e
i
s
p
r
o
p
o
r
tio
n
al
to
ar
ea
o
f
th
e
b
in
d
in
g
ellip
s
e
o
f
ea
c
h
co
n
to
u
r
.
S
u
ch
a
w
e
ig
h
t
w
a
s
ch
o
s
en
in
o
r
d
er
to
g
i
v
e
m
o
r
e
w
ei
g
h
t
to
o
u
ter
cir
cle
s
t
h
an
in
n
er
o
n
es
i
n
ea
c
h
p
atter
n
.
T
h
is
i
s
d
u
e
to
t
h
e
f
ac
t
th
at
s
i
n
ce
th
e
in
n
er
cir
cle
s
wer
e
to
o
s
m
al
l
a
n
d
i
f
t
h
e
p
la
n
e
in
cli
n
ed
,
t
h
eir
s
iz
e
s
h
r
u
n
k
f
u
r
t
h
er
.
T
h
u
s
d
etec
tio
n
o
f
o
u
ter
cir
cles
w
o
u
ld
b
e
m
o
r
e
ap
p
r
o
p
r
iate
th
an
in
n
er
o
n
es.
T
h
e
w
e
ig
h
ted
m
ea
n
is
ca
lc
u
lated
b
y
m
ain
tai
n
t
h
e
s
u
m
m
atio
n
o
f
all
th
e
cu
b
ic
w
e
ig
h
ts
a
n
d
s
u
m
m
at
io
n
o
f
co
o
r
d
in
ate
v
al
u
e
an
d
its
w
eig
h
t
d
iv
id
ed
b
y
s
u
m
m
atio
n
o
f
w
ei
g
h
ts
.
W
h
e
n
ev
er
a
n
e
w
p
o
in
t
is
p
u
s
h
ed
an
d
a
m
ea
n
n
ee
d
to
b
e
ca
lcu
l
ated
,
th
e
w
ei
g
h
ted
m
ea
n
v
alu
e
i
s
m
u
ltip
lied
b
y
t
h
e
s
u
m
m
atio
n
o
f
w
eig
h
t
s
,
th
e
n
th
e
n
e
w
p
o
in
t
is
ad
d
ed
to
th
is
v
al
u
e
a
f
ter
m
u
l
tip
l
y
i
n
g
w
i
th
th
i
s
v
alu
e.
T
h
e
s
u
m
m
ati
o
n
is
u
p
d
ated
b
y
ad
d
i
n
g
th
e
w
ei
g
h
t
o
f
th
e
n
e
w
l
y
ad
d
ed
p
o
in
t
an
d
th
e
n
e
w
m
ea
n
(
ca
lcu
lated
in
th
e
last
s
tep
)
is
d
iv
id
ed
b
y
th
i
s
s
u
m
m
atio
n
.
T
h
e
p
o
p
f
u
n
ct
io
n
w
a
s
w
r
i
tten
i
n
s
u
ch
a
w
a
y
t
h
a
t
n
o
d
es
h
av
i
n
g
co
u
n
t
v
al
u
e
th
at
is
th
e
n
u
m
b
er
o
f
cir
cles
w
h
o
s
e
w
ei
g
h
ted
m
ea
n
w
er
e
tak
e
n
to
f
i
n
d
th
e
f
i
n
al
ce
n
ter
v
al
u
es,
w
as
n
o
t
eith
er
m
a
r
k
er
_
p
o
in
ts
o
r
n
o
n
_
m
ar
k
er
_
p
o
i
n
ts
.
T
h
is
w
as
d
u
e
to
th
e
f
ac
t t
h
at
t
h
e
m
ar
k
er
p
o
in
ts
i
n
t
h
e
i
m
ag
e
w
er
e
co
m
p
o
s
ed
o
f
m
ar
k
er
_
p
o
in
ts
cir
cle
s
an
d
o
th
er
r
in
g
p
atter
n
s
h
ad
n
o
n
_
m
ar
k
er
_
p
o
in
t
s
cir
cle
s
.
T
h
u
s
b
y
f
ir
s
t
p
u
s
h
in
g
all
d
etec
ted
ce
n
ter
p
o
in
t
s
in
th
e
li
n
k
ed
li
s
t
a
n
d
th
e
n
p
o
p
p
in
g
o
u
t
t
h
e
n
o
d
es
h
a
v
i
n
g
co
u
n
t
o
th
er
t
h
an
n
o
n
_
m
ar
k
er
_
p
o
in
ts
o
r
m
ar
k
er
_
p
o
in
t
s
,
ce
n
ter
o
f
t
h
e
cir
cles
o
f
th
e
p
atter
n
w
er
e
d
etec
ted
w
i
th
s
ig
n
i
f
ican
t le
v
el
o
f
ac
cu
r
ac
y
.
(
R
ef
er
to
f
i
g
u
r
e
4
)
T
h
e
f
ir
s
t
ap
p
r
o
ac
h
is
to
f
i
n
d
t
h
e
d
is
ta
n
ce
b
et
w
ee
n
ea
ch
m
ar
k
er
,
th
e
s
e
t
h
r
ee
d
is
ta
n
ce
s
ar
e
ex
p
ec
ted
to
b
e
d
if
f
er
en
t,
an
d
h
e
n
ce
eq
u
al
it
y
ca
n
b
e
u
s
ed
to
d
is
tin
g
u
is
h
b
et
w
ee
n
m
ar
k
er
s
.
B
u
t
b
ec
au
s
e
o
f
t
h
e
d
if
f
er
e
n
t
p
r
o
j
ec
tio
n
s
an
d
p
er
s
p
ec
tiv
e
er
r
o
r
s
,
th
e
in
eq
u
ali
t
y
i
s
v
io
lated
f
o
r
i
m
a
g
es
w
i
th
e
x
tr
e
m
e
o
r
ie
n
tatio
n
s
.
T
h
e
s
ec
o
n
d
ap
p
r
o
ac
h
is
to
f
in
d
n
u
m
b
er
o
f
p
o
in
ts
b
et
w
ee
n
ea
c
h
m
ar
k
er
.
T
h
r
ee
eq
u
atio
n
s
ar
e
p
o
s
s
ib
le
f
o
r
th
r
ee
m
ar
k
er
s
.
T
h
er
e
ar
e
d
i
f
f
er
en
t
n
u
m
b
er
s
o
f
p
o
in
ts
l
y
i
n
g
o
n
ea
ch
lin
e
f
o
r
ev
er
y
i
m
a
g
e,
t
h
o
u
g
h
i
t
is
d
if
f
ic
u
lt
to
s
p
ec
if
y
a
co
n
c
r
ete
n
u
m
b
er
f
o
r
ev
er
y
i
m
ag
e
d
u
e
to
d
if
f
er
en
ce
i
n
o
r
ien
tati
o
n
,
a
co
m
m
o
n
in
eq
u
a
lit
y
e
x
is
ts
.
I
f
t
h
e
t
h
r
ee
m
ar
k
e
r
s
w
er
e
to
d
ef
i
n
e
a
co
o
r
d
in
at
e
s
y
s
te
m
:
Y
-
O
-
X
,
th
en
th
e
n
u
m
b
er
o
f
p
o
in
t
s
l
y
in
g
o
n
OX
is
m
o
r
e
t
h
an
th
e
n
u
m
b
er
o
f
p
o
in
t
s
l
y
i
n
g
o
n
OY
wh
ich
is
in
tu
r
n
m
o
r
e
th
an
t
h
e
p
o
in
t
s
l
y
in
g
o
n
YX.
I
t
is
i
m
p
o
r
tan
t
to
tak
e
i
n
to
ac
c
o
u
n
t
th
e
p
o
s
s
ib
ilit
y
o
f
an
ep
s
i
lo
n
d
ev
iat
io
n
w
h
ile
test
i
n
g
w
h
et
h
er
a
p
o
in
t
lies
o
n
a
lin
e
o
r
n
o
t.
A
f
ter
d
is
ti
n
g
u
is
h
in
g
t
h
e
d
if
f
er
en
t
p
o
in
t
s
f
r
o
m
ea
ch
o
th
er
,
th
e
y
ar
e
s
to
r
ed
in
a
t
w
o
d
i
m
e
n
s
io
n
al
ar
r
ay
.
T
h
ese
ar
e
f
u
r
th
er
u
s
ed
f
o
r
ca
lcu
lati
n
g
s
lo
p
e
f
o
r
ar
r
an
g
i
n
g
th
e
ce
n
ter
s
.
3
.
3
.
Arr
a
ng
e
m
e
nt
o
f
All
t
he
Cen
t
er
P
o
ints
in
a
Sy
s
t
e
m
a
t
ic
O
rder
t
ha
t
is
un
iv
er
s
a
lly
f
o
llo
w
ed
F
o
r
All
I
m
a
g
es
Af
ter
u
n
iq
u
e
l
y
id
en
t
if
y
i
n
g
ea
ch
m
ar
k
er
p
o
in
t,
ea
ch
i
m
a
g
e
h
as
a
f
i
x
ed
o
r
ien
tatio
n
w
h
ic
h
aid
es
in
d
eter
m
in
i
n
g
t
h
e
d
ir
ec
tio
n
in
w
h
ich
t
h
e
p
o
in
t
s
n
ee
d
to
b
e
tr
a
v
er
s
ed
an
d
s
to
r
ed
.
T
h
e
alg
o
r
ith
m
r
eq
u
ir
es
t
h
e
f
ir
s
t
s
tep
to
b
e
a
Dela
un
a
y
T
ria
ng
ula
t
io
n
o
v
er
all
ce
n
ter
s
d
etec
ted
.
I
n
g
eo
m
etr
y
,
tr
ian
g
u
latio
n
is
th
e
s
u
b
d
iv
is
io
n
o
f
a
2
D
g
eo
m
etr
ic
o
b
j
ec
t
in
to
tr
ian
g
les.
A
Dela
u
n
a
y
tr
ia
n
g
u
latio
n
[
1
0
]
f
o
r
a
s
et
P
o
f
p
o
in
ts
in
a
p
lan
e
is
a
tr
ian
g
u
lat
io
n
DT
(
P)
s
u
ch
th
at
n
o
p
o
in
t
in
P
is
in
s
id
e
th
e
cir
cu
m
-
cir
cle
o
f
a
n
y
tr
ia
n
g
le
i
n
DT
(
P
)
Dela
u
n
a
y
tr
ian
g
u
lat
io
n
s
m
a
x
i
m
ize
t
h
e
m
in
i
m
u
m
a
n
g
le
o
f
a
ll
t
h
e
an
g
le
s
o
f
th
e
tr
ian
g
les
in
th
e
tr
ian
g
u
l
atio
n
;
t
h
e
y
te
n
d
to
av
o
id
s
k
i
n
n
y
tr
ia
n
g
les.
T
h
e
o
u
tp
u
t
o
f
Dela
u
n
a
y
tr
ia
n
g
u
la
tio
n
u
s
i
n
g
p
r
ed
ef
i
n
ed
p
r
o
ce
d
u
r
es
o
f
Op
en
C
V
is
a
s
et
o
f
ed
g
es.
Fo
llo
w
ed
b
y
Dela
u
n
a
y
tr
ia
n
g
u
latio
n
,
t
h
e
p
o
in
ts
o
n
th
e
OY
ax
is
ar
e
o
r
d
er
e
d
b
ased
o
n
th
eir
d
is
tan
ce
f
r
o
m
th
e
o
r
ig
in
m
ar
k
er
an
d
ar
e
s
to
r
ed
in
an
ar
r
a
y
.
Fo
r
ea
ch
ele
m
en
t
in
th
i
s
ar
r
a
y
in
o
r
d
er
,
th
e
w
h
o
le
r
o
w
o
f
ce
n
ter
s
alo
n
g
t
h
e
OX
ax
is
is
tr
a
v
er
s
ed
.
Fo
r
th
is
,
in
itiall
y
a
ll
ce
n
ter
s
ar
e
in
clu
d
ed
in
a
lin
k
ed
lis
t.
Acc
o
r
d
in
g
to
Y
-
O
-
X
o
r
ien
tatio
n
,
t
h
e
o
r
d
er
in
g
n
ee
d
s
to
s
tar
t
f
r
o
m
t
h
e
o
r
ig
i
n
m
a
r
k
er
.
A
f
ter
th
e
o
r
ig
i
n
m
ar
k
er
,
i
ts
ad
j
ac
en
t
m
ar
k
er
s
n
ee
d
to
b
e
ad
d
ed
; to
ac
co
m
p
lis
h
t
h
i
s
,
th
e
ap
p
licatio
n
tr
av
er
s
es th
r
o
u
g
h
all
t
h
e
ed
g
e
s
o
f
Del
au
n
a
y
tr
ia
n
g
u
lat
io
n
to
f
in
d
ed
g
es
w
ith
s
o
u
r
ce
o
r
d
esti
n
a
tio
n
as t
h
e
o
r
ig
i
n
m
ar
k
er
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
E
n
h
a
n
ce
d
C
a
mera
C
a
lib
r
a
tio
n
fo
r
Ma
ch
in
e
V
is
io
n
u
s
in
g
O
p
en
C
V
…. (
S
h
u
b
h
a
m
R
o
h
a
n
A
s
th
a
n
a
)
141
A
ll
th
e
s
e
ed
g
es
ar
e
s
elec
ted
an
d
th
eir
o
t
h
er
en
d
p
o
in
ts
(
w
h
i
ch
ca
n
b
e
a
s
o
u
r
ce
o
r
d
esti
n
at
io
n
f
o
r
th
e
ed
g
e)
ar
e
p
u
t
in
an
o
t
h
er
lin
k
ed
lis
t.
Fro
m
th
is
li
n
k
ed
lis
t,
o
n
l
y
t
h
o
s
e
p
o
in
t
s
ar
e
s
elec
te
d
w
h
o
s
e
r
esp
ec
tiv
e
ed
g
es
h
a
v
e
s
lo
p
e
s
i
m
ilar
to
OX
lin
e
(
w
i
th
a
r
eq
u
ir
ed
ep
s
ilo
n
d
ev
iatio
n
)
.
A
m
o
r
e
ef
f
icie
n
t
m
e
th
o
d
is
to
m
a
tch
th
e
x
an
d
y
co
m
p
o
n
e
n
t
s
o
f
t
h
e
OX
l
in
e,
a
s
t
h
is
ta
k
es
in
t
o
co
n
s
id
er
atio
n
t
h
e
er
r
o
r
in
d
u
ce
d
b
y
d
if
f
er
e
n
tl
y
o
r
ien
ted
i
m
ag
e
s
.
I
t
also
h
elp
s
to
d
ea
l
w
it
h
v
er
tical
li
n
e
s
as
tan
g
en
t
o
f
9
0
d
eg
r
ee
s
ten
d
s
to
in
f
i
n
it
y
,
h
e
n
ce
d
iv
id
in
g
i
n
to
s
i
n
e
a
n
d
co
s
i
n
e
co
m
p
o
n
e
n
t
s
h
elp
s
to
g
et
r
id
o
f
t
h
is
p
r
o
b
lem
as
t
h
e
v
al
u
es
l
i
e
b
et
w
ee
n
-
1
an
d
1
.
An
o
th
er
r
o
u
n
d
o
f
f
ilter
i
n
g
i
s
m
ad
e
o
f
t
h
e
s
elec
ted
p
o
in
t
s
.
T
h
e
s
elec
ted
p
o
in
ts
in
t
h
e
li
n
k
ed
lis
t
ar
e
m
ad
e
to
tr
av
er
s
e
t
h
r
o
u
g
h
t
h
e
b
i
g
li
n
k
ed
lis
t.
I
f
t
h
e
p
o
in
t
is
p
r
ese
n
t,
th
en
th
a
t
is
th
e
n
e
x
t
p
o
in
t.
T
h
e
o
r
ig
i
n
al
s
tar
tin
g
p
o
in
t
is
p
o
p
p
ed
o
u
t
f
r
o
m
t
h
e
b
ig
li
n
k
ed
l
is
t
a
n
d
s
tar
tin
g
p
o
i
n
t
i
s
s
h
i
f
ted
to
t
h
e
d
etec
ted
p
o
in
t.
T
h
is
p
r
o
ce
d
u
r
e
is
iter
ativ
e
l
y
ap
p
lied
o
n
all
ce
n
ter
p
o
in
ts
.
I
n
t
h
is
w
a
y
,
o
n
e
r
o
w
i
s
co
m
p
leted
.
Af
ter
co
m
p
leti
n
g
o
n
e
r
o
w
,
t
h
e
n
ex
t
p
o
in
t
o
n
th
e
ar
r
a
y
o
f
OY
p
o
in
ts
is
p
u
s
h
ed
in
to
th
e
f
i
n
al
ar
r
an
g
ed
lis
t
an
d
th
e
s
i
m
ilar
p
r
o
ce
d
u
r
e
is
iter
ativ
el
y
ap
p
lied
.
T
h
is
is
to
b
e
d
o
n
e
o
n
all
p
o
in
ts
o
n
OY
lin
e.
T
h
e
alg
o
r
ith
m
ai
m
s
to
ar
r
an
g
e
a
ll
t
h
e
p
o
in
ts
f
r
o
m
o
r
ig
i
n
i
n
t
h
e
r
i
g
h
t
w
ar
d
d
ir
ec
tio
n
(
T
ak
en
t
h
e
f
ac
t
th
a
t
t
h
e
o
r
ig
i
n
lie
s
i
n
t
h
e
b
o
tto
m
le
f
t
co
r
n
er
)
.
T
h
er
ea
f
ter
th
ese
ar
r
an
g
ed
ce
n
ter
p
o
in
ts
ar
e
s
to
r
ed
in
th
e
ar
r
ay
ca
lled
co
r
n
er
s
h
av
i
n
g
t
y
p
e
C
v
P
o
in
t2
D3
2
f
.
T
h
is
is
th
e
r
eq
u
ir
ed
f
o
r
m
at
f
o
r
ca
lib
r
atio
n
.
On
ce
th
e
ce
n
ter
p
o
in
ts
ar
e
o
r
d
e
r
ed
in
a
u
n
iv
er
s
al
l
y
f
o
llo
w
ed
m
a
n
n
er
f
o
r
ea
ch
im
ag
e,
w
h
ic
h
is
t
h
e
f
o
r
m
at
r
eq
u
ir
ed
b
y
cv
C
alib
r
ateCa
m
er
a2
p
r
o
ce
d
u
r
e,
th
e
Op
en
C
V
p
r
o
ce
d
u
r
e
cv
Dra
w
C
h
ess
b
o
a
r
d
C
o
r
n
ers
i
s
u
s
ed
to
j
o
in
t
h
e
d
etec
ted
ce
n
ter
s
in
o
r
d
er
l
y
f
o
r
m
at.
(
R
e
f
er
to
F
ig
u
r
e
5
)
T
h
ese
ar
r
an
g
ed
p
o
in
ts
ac
t
as
i
m
a
g
e
p
o
in
ts
n
e
ed
ed
f
o
r
th
e
ca
l
ib
r
atio
n
p
r
o
ce
d
u
r
e.
(
T
h
e
ar
r
ay
o
f
co
r
n
er
p
o
in
ts
is
s
a
v
ed
as
t
h
e
i
m
a
g
e
p
o
in
t
s
)
.
T
h
e
p
r
o
g
r
am
u
s
e
s
th
e
d
i
m
e
n
s
io
n
s
o
f
t
h
e
ca
lib
r
atio
n
p
atter
n
to
o
b
tai
n
th
e
o
b
j
ec
t p
o
in
ts
.
(
R
ef
e
r
to
F
ig
u
r
e
5
)
Fig
ur
e
5
.
Dr
a
w
i
n
g
t
h
e
ar
r
an
g
e
d
ce
n
ter
p
o
in
ts
s
tar
ti
n
g
f
r
o
m
t
h
e
o
r
ig
i
n
m
ar
k
er
p
o
in
ts
m
o
v
i
n
g
lef
t
w
ar
d
s
w
it
h
r
esp
ec
t to
im
a
g
e
f
r
a
m
e.
3
.
4
.
Usi
ng
O
rder
ed
Cent
er
s
,
T
o
Ca
lib
ra
t
e
t
he
Ca
m
er
a
Af
ter
d
eter
m
i
n
i
n
g
th
e
i
m
a
g
e
p
o
in
ts
a
n
d
o
b
j
ec
t
p
o
i
n
ts
t
h
e
ca
m
er
a
is
ca
lib
r
a
ted
u
s
i
n
g
cv
C
a
lib
r
a
teC
a
mera
2
p
r
o
ce
d
u
r
e.
T
h
is
f
u
n
ctio
n
ca
lc
u
late
s
r
e
-
p
r
o
j
ec
tio
n
er
r
o
r
(
eq
u
al
to
ap
p
r
o
x
i
m
ate
l
y
0
.
2
9
7
in
th
e
f
ir
s
t
ca
s
e)
.
I
t
al
s
o
ca
lcu
lates
th
e
i
n
tr
i
n
s
ic
m
atr
i
x
a
n
d
d
is
to
r
tio
n
co
ef
f
icie
n
t
s
.
U
s
in
g
t
h
e
d
is
to
r
tio
n
co
ef
f
icie
n
t
s
,
ea
ch
i
m
ag
e
i
s
u
n
d
is
to
r
ted
.
T
h
is
u
n
d
is
to
r
ted
i
m
a
g
e
is
u
s
ed
f
o
r
f
i
n
d
i
n
g
t
h
e
f
r
o
n
t
al
i
m
a
g
e.
3
.
5
.
Cre
a
t
ing
t
he
F
ro
nta
l
I
m
a
g
e
f
o
r
E
a
ch
I
m
a
g
e
by
t
he
U
s
e
o
f
t
he
P
a
ra
m
et
er
s
Der
iv
ed
F
r
o
m
Ca
m
er
a
Ca
lib
ra
t
io
n
T
h
e
o
r
ien
tatio
n
o
f
th
e
o
b
j
ec
t
r
elativ
e
to
th
e
ca
m
er
a
co
o
r
d
in
ate
s
y
s
te
m
i
s
d
escr
ib
ed
in
ter
m
s
o
f
a
r
o
tatio
n
an
d
a
tr
an
s
latio
n
.
Usi
n
g
cv
F
in
d
E
xtri
n
s
icC
a
me
r
a
P
a
r
a
ms2
f
u
n
ctio
n
,
t
h
e
ap
p
licatio
n
f
i
n
d
s
t
h
e
r
o
ta
tio
n
V
ec
to
r
&
t
r
a
n
s
la
tio
n
V
ec
to
r
f
o
r
ea
c
h
i
m
a
g
e
b
y
p
a
s
s
i
n
g
th
e
i
n
tr
in
s
ic
m
atr
i
x
a
n
d
d
is
to
r
tio
n
co
ef
f
icie
n
ts
.
On
ce
th
e
ca
m
er
a
is
ca
lib
r
ated
,
th
e
ca
m
er
a
in
tr
i
n
s
ic
p
ar
a
m
e
te
r
s
ar
e
u
s
ed
to
o
b
tain
th
e
ex
tr
in
s
ic
p
ar
a
m
eter
s
f
o
r
ea
ch
i
m
a
g
e
.
T
h
ese
ex
tr
i
n
s
ic
p
ar
a
m
eter
s
i.e
.
R
o
tatio
n
v
ec
to
r
an
d
T
r
an
s
latio
n
Vec
to
r
ar
e
r
e
q
u
ir
ed
to
o
b
tain
th
e
tr
an
s
f
o
r
m
atio
n
m
atr
i
x
.
R
o
tati
o
n
m
atr
i
x
is
o
b
tain
ed
f
r
o
m
r
o
t
atio
n
v
ec
to
r
u
s
in
g
R
o
d
r
ig
u
es
T
r
an
s
f
o
r
m
w
h
ich
i
s
ap
p
lied
v
ia
cv
R
o
d
r
ig
u
es2
f
u
n
ctio
n
.
T
h
en
t
h
e
tr
an
s
f
o
r
m
atio
n
m
atr
i
x
is
co
m
p
u
ted
m
an
u
all
y
b
y
a
u
g
m
en
ti
n
g
t
h
e
r
o
tatio
n
m
atr
ix
a
n
d
tr
an
s
lat
io
n
v
ec
to
r
.
T
h
e
u
n
d
is
to
r
ted
i
m
ag
e
w
h
ic
h
w
a
s
o
b
tain
e
d
u
s
in
g
d
is
to
r
tio
n
co
ef
f
icie
n
t
s
,
is
p
ass
ed
to
cv
W
a
r
p
P
ers
p
ec
tive
f
u
n
ctio
n
,
w
h
ich
g
e
n
er
ates
t
h
e
f
r
o
n
tal
i
m
ag
e
b
y
ap
p
l
y
i
n
g
t
h
e
tr
an
s
f
o
r
m
atio
n
m
atr
i
x
o
n
ea
c
h
i
m
ag
e.
(
R
e
f
er
to
F
i
g
u
r
e
6
)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
3
,
No
.
3
,
Sep
tem
b
er
20
1
4
:
1
3
6
–
1
4
4
142
Fig
u
r
e
6
.
Fro
n
tal
I
m
a
g
e
o
f
R
i
n
g
P
atter
n
T
h
e
q
u
alit
y
o
f
t
h
e
f
r
o
n
ta
l
i
m
a
g
e
o
b
tain
ed
b
y
ap
p
licatio
n
o
f
cv
W
ar
p
P
er
s
p
ec
tiv
e
p
r
o
ce
d
u
r
e
d
ep
en
d
s
a
lo
t o
n
th
e
in
ter
p
o
latio
n
m
et
h
o
d
ad
o
p
te
d
.
I
nte
rpo
la
t
io
n
[
1
1
]
is
w
a
y
th
r
o
u
g
h
w
h
ic
h
i
m
ag
e
s
ar
e
en
lar
g
ed
.
I
t
is
th
e
p
r
o
ce
s
s
o
f
d
e
ter
m
i
n
in
g
t
h
e
v
alu
e
s
o
f
a
f
u
n
ctio
n
at
p
o
s
iti
o
n
s
l
y
in
g
b
et
w
ee
n
it
s
s
a
m
p
le
s
.
I
t
ac
h
iev
e
s
th
i
s
p
r
o
ce
s
s
b
y
f
itti
n
g
a
co
n
ti
n
u
o
u
s
f
u
n
ctio
n
th
r
o
u
g
h
th
e
d
is
cr
ete
in
p
u
t
s
a
m
p
les.
T
h
is
p
er
m
its
i
n
p
u
t
v
al
u
es
to
b
e
ev
alu
ated
at
ar
b
itra
r
y
p
o
s
itio
n
s
i
n
th
e
i
n
p
u
t,
n
o
t
j
u
s
t
t
h
o
s
e
d
ef
i
n
ed
at
th
e
s
a
m
p
le
p
o
in
ts
.
T
h
u
s
it
is
b
est
i
f
t
h
e
q
u
a
lit
y
,
o
r
v
i
s
ib
le
d
is
ti
n
ctio
n
f
o
r
ea
ch
p
ix
el,
is
r
etai
n
ed
th
r
o
u
g
h
o
u
t th
e
e
n
lar
g
e
m
e
n
t p
r
o
ce
s
s
.
T
h
e
p
r
o
ce
s
s
o
f
i
n
ter
p
o
latio
n
i
s
o
n
e
o
f
t
h
e
f
u
n
d
a
m
e
n
tal
o
p
e
r
atio
n
s
i
n
i
m
a
g
e
p
r
o
ce
s
s
in
g
.
T
h
e
i
m
a
g
e
q
u
a
lit
y
h
i
g
h
l
y
d
ep
en
d
s
o
n
t
h
e
u
s
ed
in
ter
p
o
latio
n
tech
n
i
q
u
e.
Sev
er
al
in
ter
p
o
latio
n
tech
n
iq
u
es
h
av
e
b
ee
n
d
ev
elo
p
ed
an
d
th
e
m
o
s
t c
o
m
m
o
n
l
y
u
s
ed
m
e
th
o
d
s
ar
e
th
e
n
ea
r
est n
ei
g
h
b
o
u
r
,
li
n
ea
r
,
ar
ea
an
d
cu
b
ic
tech
n
iq
u
es.
1.
Nea
r
est Ne
ig
h
b
o
u
r
T
h
e
s
i
m
p
lest
in
ter
p
o
latio
n
f
r
o
m
a
co
m
p
u
tatio
n
al
s
ta
n
d
p
o
in
t
i
s
th
e
n
ea
r
es
t
n
ei
g
h
b
o
u
r
,
w
h
er
e
ea
ch
in
ter
p
o
lated
o
u
tp
u
t
p
i
x
el
i
s
as
s
ig
n
ed
t
h
e
v
al
u
e
o
f
t
h
e
n
ea
r
e
s
t
s
a
m
p
le
p
o
i
n
t
i
n
t
h
e
i
n
p
u
t
i
m
ag
e.
T
h
is
tec
h
n
iq
u
e
is
al
s
o
k
n
o
w
n
as
p
o
in
t
s
h
i
f
t
a
lg
o
r
ith
m
a
n
d
p
i
x
el
r
ep
licatio
n
.
T
h
is
tec
h
n
iq
u
e
ac
h
ie
v
es
m
a
g
n
i
f
ica
tio
n
b
y
p
i
x
el
r
ep
licatio
n
an
d
m
in
i
m
is
atio
n
b
y
s
p
ar
s
e
p
o
i
n
t
s
a
m
p
li
n
g
.
Fo
r
lar
g
e
-
s
ca
le
c
h
a
n
g
e
s
,
n
ea
r
est
n
ei
g
h
b
o
u
r
in
ter
p
o
latio
n
p
r
o
d
u
ce
s
i
m
a
g
es
w
it
h
b
lo
ck
y
e
f
f
ec
t
s
.
2.
L
i
n
ea
r
I
n
ter
p
o
latio
n
A
b
etter
alg
o
r
ith
m
th
a
n
“
n
ea
r
est
n
ei
g
h
b
o
u
r
”;
t
h
at
tak
e
s
in
t
o
ac
co
u
n
t
th
e
g
r
ad
u
al
tr
an
s
iti
o
n
o
f
p
ix
el
co
lo
u
r
v
alu
e
s
.
B
y
f
i
n
d
in
g
th
e
m
ea
n
s
b
et
w
ee
n
t
w
o
p
ix
el
v
alu
es,
t
h
e
f
il
ler
p
ix
el
is
b
ette
r
s
u
ited
f
o
r
o
v
er
all
i
m
a
g
e
en
h
a
n
ce
m
en
t.
I
n
o
th
er
w
o
r
d
s
,
it
j
u
s
t
lo
o
k
s
p
lai
n
b
ett
er
.
L
in
ea
r
i
n
ter
p
o
latio
n
i
s
a
f
i
r
s
t
d
eg
r
ee
m
e
th
o
d
th
at
p
ass
e
s
a
s
tr
ai
g
h
t lin
e
t
h
r
o
u
g
h
e
v
er
y
t
w
o
co
n
s
ec
u
ti
v
e
p
o
in
ts
o
f
th
e
i
n
p
u
t i
m
a
g
e.
Af
ter
li
n
ea
r
in
ter
p
o
latio
n
s
,
ed
g
es
ar
e
b
lu
r
r
ed
.
T
o
r
em
ed
y
th
is
,
s
p
li
n
e
in
ter
p
o
latio
n
is
u
s
e
d
.
A
f
ter
in
ter
p
o
latio
n
,
th
e
ed
g
es
ar
e
m
o
r
e
v
is
ib
le
s
o
ed
g
e
e
n
h
a
n
ce
m
en
t
is
m
u
c
h
m
o
r
e
s
u
cc
es
s
f
u
l
a
n
d
v
is
ib
le.
E
d
g
e
d
etec
tio
n
w
o
r
k
s
b
y
tak
i
n
g
a
w
ei
g
h
ted
s
u
m
o
f
p
ix
els ar
o
u
n
d
a
s
i
n
g
le
p
i
x
el
to
d
eter
m
i
n
e
its
n
e
w
v
a
lu
e.
3.
A
r
ea
I
n
ter
p
o
latio
n
I
t
is
r
e
-
s
a
m
p
li
n
g
th
e
i
m
a
g
e
u
s
in
g
p
ix
el
ar
ea
r
elatio
n
.
I
t
is
p
r
ef
er
r
ed
m
eth
o
d
f
o
r
i
m
a
g
e
d
ec
i
m
ati
o
n
th
at
g
iv
e
s
m
o
ir
é
-
f
r
ee
r
es
u
lt
s
.
I
n
ca
s
e
o
f
zo
o
m
i
n
g
it is
s
i
m
ilar
to
n
ea
r
est n
ei
g
h
b
o
u
r
i
n
ter
p
o
latio
n
m
et
h
o
d
.
4.
C
u
b
ic
I
n
ter
p
o
latio
n
C
u
b
ic
i
n
ter
p
o
latio
n
i
s
t
h
e
s
i
m
p
lest
m
et
h
o
d
th
a
t
o
f
f
er
s
tr
u
e
c
o
n
tin
u
it
y
b
et
w
ee
n
t
h
e
s
e
g
m
en
ts
.
A
s
s
u
c
h
it r
eq
u
ir
es
m
o
r
e
th
a
n
j
u
s
t t
h
e
t
w
o
en
d
p
o
in
t
s
o
f
t
h
e
s
e
g
m
e
n
t b
u
t a
ls
o
t
h
e
t
w
o
p
o
in
ts
o
n
eit
h
e
r
s
id
e
o
f
th
e
m
.
I
n
i
m
ag
e
p
r
o
ce
s
s
i
n
g
,
cu
b
ic
in
ter
p
o
latio
n
i
s
o
f
te
n
c
h
o
s
e
n
o
v
er
li
n
ea
r
i
n
ter
p
o
latio
n
o
r
n
ea
r
est
n
eig
h
b
o
u
r
in
i
m
a
g
e
r
e
-
s
a
m
p
li
n
g
,
w
h
en
s
p
ee
d
is
n
o
t
an
is
s
u
e.
I
n
co
n
tr
ast
to
l
in
ea
r
in
ter
p
o
latio
n
,
w
h
ic
h
o
n
l
y
tak
es
4
p
ix
els
(
2
x
2
)
in
to
ac
co
u
n
t,
c
u
b
ic
in
ter
p
o
latio
n
co
n
s
i
d
er
s
1
6
p
ix
els
(
4
x
4
)
.
I
m
a
g
es
r
e
-
s
a
m
p
led
w
it
h
b
i
cu
b
ic
in
ter
p
o
latio
n
ar
e
s
m
o
o
t
h
er
an
d
h
av
e
f
e
w
er
i
n
ter
p
o
lati
o
n
ar
tef
ac
t
s
.
T
h
e
in
ter
p
o
lated
s
u
r
f
ac
e
is
s
m
o
o
t
h
er
th
an
c
o
r
r
esp
o
n
d
in
g
s
u
r
f
ac
es
o
b
tain
ed
b
y
li
n
ea
r
in
ter
p
o
latio
n
o
r
n
ea
r
est
n
e
ig
h
b
o
u
r
i
n
ter
p
o
latio
n
.
C
u
b
ic
in
ter
p
o
latio
n
ca
n
b
e
ac
co
m
p
li
s
h
ed
u
s
i
n
g
eit
h
er
L
a
g
r
an
g
e
’
s
p
o
ly
n
o
m
ial
o
r
cu
b
ic
co
n
v
o
l
u
tio
n
alg
o
r
it
h
m
.
4.
E
XP
E
R
I
M
E
NT
A
L
RE
SUL
T
S
W
h
en
t
h
e
tr
ad
itio
n
al
ca
lib
r
ati
n
g
ap
p
r
o
ac
h
w
as
ap
p
lied
o
n
t
h
e
R
i
n
g
Gr
id
p
atter
n
a
r
e
-
p
r
o
jectio
n
er
r
o
r
o
f
0
.
2
9
7
6
w
as
f
o
u
n
d
alo
n
g
w
i
th
t
h
e
in
tr
in
s
ic
m
a
tr
ix
a
n
d
d
is
t
o
r
tio
n
co
ef
f
icie
n
t
s
.
I
t
is
w
o
r
th
n
o
tin
g
t
h
at
t
h
e
r
e
-
p
r
o
j
ec
tio
n
er
r
o
r
o
f
th
e
tr
ad
iti
o
n
al
ca
lib
r
a
tio
n
o
v
er
R
i
n
g
g
r
id
p
atter
n
w
as
s
i
g
n
i
f
ican
tl
y
m
o
r
e
th
a
n
th
at
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
E
n
h
a
n
ce
d
C
a
mera
C
a
lib
r
a
tio
n
fo
r
Ma
ch
in
e
V
is
io
n
u
s
in
g
O
p
en
C
V
…. (
S
h
u
b
h
a
m
R
o
h
a
n
A
s
th
a
n
a
)
143
ch
es
s
b
o
ar
d
w
h
ich
w
e
w
er
e
a
b
le
to
o
b
tain
ar
o
u
n
d
0
.
2
1
8
.
T
h
is
is
d
u
e
to
d
ev
iatio
n
o
f
co
n
tr
o
l
p
o
in
t
s
i.e
.
t
h
e
ce
n
ter
s
o
f
th
e
co
n
ce
n
tr
ic
cir
cl
es
f
r
o
m
th
e
ce
n
ter
s
o
f
t
h
e
d
ete
cted
ellip
s
es
b
ec
au
s
e
o
f
n
o
n
-
f
r
o
n
talit
y
o
f
i
m
a
g
es.
An
o
th
er
r
ea
s
o
n
f
o
r
t
h
is
er
r
o
r
co
u
ld
b
e
th
e
lack
o
f
s
u
b
-
p
i
x
el
a
cc
u
r
ac
y
.
T
h
is
is
b
ec
au
s
e
i
n
t
h
e
r
a
w
i
m
ag
e
w
h
ich
h
as
v
ar
io
u
s
o
r
ie
n
tatio
n
s
a
n
d
th
e
p
er
s
p
ec
ti
v
e
v
ie
w
th
a
t
t
h
e
ca
m
er
a
r
ec
ei
v
es,
th
e
ce
n
ter
s
o
f
t
h
e
co
n
ce
n
tr
ic
cir
cles
d
o
n
o
t
co
i
n
cid
e.
T
h
e
ce
n
ter
s
o
f
t
h
e
co
n
ce
n
tr
ic
c
ir
cles
o
f
a
s
i
n
g
le
s
et
ar
e
p
er
ce
iv
ed
as
t
w
o
d
i
f
f
er
e
n
t
p
o
in
ts
b
ec
au
s
e
o
f
n
o
n
-
l
in
ea
r
d
is
to
r
tio
n
s
.
T
h
e
d
if
f
er
en
t
ce
n
t
er
s
d
o
n
o
t
ev
en
co
in
cid
e
w
ith
th
e
ac
tu
al
co
n
tr
o
l
p
o
in
t.
T
o
p
r
ev
en
t
th
i
s
,
f
r
o
n
tal
i
m
a
g
es
ar
e
o
b
tain
e
d
w
h
ic
h
a
r
e
f
r
ee
o
f
d
is
to
r
tio
n
s
,
t
h
u
s
g
i
v
in
g
u
s
t
h
e
ac
c
u
r
ate
co
n
tr
o
l p
o
in
t.
Giv
e
n
b
elo
w
ar
e
th
e
x
m
l
f
il
es
o
f
th
e
in
tr
i
n
s
ic
p
ar
a
m
eter
s
an
d
d
is
to
r
tio
n
p
ar
am
eter
s
ac
h
iev
ed
b
y
ca
lib
r
atin
g
r
i
n
g
g
r
id
p
atter
n
.
(
Fig
u
r
e
7
an
d
Fig
u
r
e
8
)
Fig
u
r
e
7
.
Sn
ap
s
h
o
t o
f
th
e
x
m
l
f
ile
o
f
i
n
tr
i
n
s
ic
p
ar
a
m
eter
s
ac
h
iev
ed
b
y
ca
lib
r
atin
g
r
in
g
g
r
id
p
atter
n
Fig
u
r
e
8
.
Sn
ap
s
h
o
t o
f
th
e
x
m
l
f
ile
o
f
d
is
to
r
tio
n
p
ar
a
m
eter
s
ac
h
iev
ed
b
y
ca
lib
r
ati
n
g
r
in
g
g
r
id
p
atter
n
5.
CO
NCLU
SI
O
N
AND
F
U
T
U
RE
WO
RK
T
h
e
ca
lib
r
atio
n
p
r
o
ce
d
u
r
e
s
u
g
g
e
s
ted
in
t
h
is
p
ap
er
u
tili
ze
s
co
n
ce
n
tr
ic
cir
cu
lar
co
n
tr
o
l
p
o
in
ts
an
d
p
er
f
o
r
m
s
m
ap
p
in
g
f
r
o
m
w
o
r
l
d
co
o
r
d
in
ates
in
to
i
m
ag
e
co
o
r
d
in
ates
a
n
d
b
ac
k
w
ar
d
f
r
o
m
i
m
ag
e
co
o
r
d
in
ates
to
th
e
t
h
r
ee
d
i
m
e
n
s
io
n
al
p
la
n
e.
W
ith
t
h
is
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
w
e
h
a
v
e
b
ee
n
ab
le
to
ac
h
ie
v
e
a
r
e
-
p
r
o
j
ec
tio
n
er
r
o
r
o
f
0
.
2
9
7
.
I
n
o
r
d
er
to
im
p
r
o
v
e
o
u
r
r
esu
lt
s
an
d
as
a
f
u
tu
r
e
w
o
r
k
to
th
i
s
w
e
p
r
o
p
o
s
e
to
u
s
e
it
er
ativ
e
ca
lib
r
atio
n
th
at
u
tili
ze
s
t
h
e
p
ar
a
m
eter
s
o
b
tain
ed
f
r
o
m
in
d
i
g
e
n
o
u
s
ca
lib
r
atio
n
alg
o
r
ith
m
s
a
s
in
itial
izatio
n
to
p
er
f
o
r
m
u
n
d
i
s
to
r
tio
n
an
d
u
n
p
r
o
j
ec
tio
n
o
f
ca
lib
r
atio
n
i
m
ag
e
s
to
o
b
tain
a
f
r
o
n
tal
i
m
a
g
e.
T
h
is
f
r
o
n
tal
i
s
th
e
n
u
s
ed
to
lo
ca
lize
th
e
ca
lib
r
atio
n
p
atter
n
co
n
tr
o
l
p
o
in
ts
,
r
ep
r
o
j
ec
t
th
e
m
b
ac
k
o
n
r
a
w
i
m
ag
e
an
d
r
ec
o
m
p
u
ted
t
h
e
ca
m
er
a
p
ar
am
eter
s
in
an
iter
ati
v
e
r
ef
i
n
e
m
e
n
t
u
n
t
il
co
n
v
er
g
en
ce
.
U
n
d
is
to
r
tin
g
a
n
d
u
n
p
r
o
j
ec
tin
g
t
h
e
ca
lib
r
atio
n
p
atter
n
to
th
e
f
r
o
n
tal
p
lan
e
i
n
cr
ea
s
es
th
e
ac
cu
r
ac
y
o
f
co
n
tr
o
l
p
o
in
t
lo
ca
lizatio
n
an
d
co
n
s
e
q
u
en
tl
y
o
f
ca
m
er
a
ca
lib
r
atio
n
.
Af
ter
o
b
tain
in
g
t
h
e
f
r
o
n
tal
i
m
ag
e
s
,
th
e
ca
lcu
la
ted
p
o
s
itio
n
s
o
f
th
e
co
n
tr
o
l
p
o
in
ts
in
t
h
e
f
r
o
n
tal
i
m
a
g
es a
r
e
u
s
ed
as in
it
ial
g
u
es
s
to
r
ef
in
e
t
h
e
p
o
s
itio
n
s
u
s
in
g
t
h
e
iter
ati
v
e
ca
lib
r
atio
n
m
et
h
o
d
.
T
h
is
is
b
ec
au
s
e
th
e
y
ar
e
f
r
o
n
to
-
p
ar
allel
an
d
d
o
n
o
t
s
u
f
f
er
f
r
o
m
d
is
to
r
tio
n
ef
f
ec
t
s
.
T
h
en
r
ev
er
s
el
y
p
r
o
j
ec
t
th
e
d
etec
te
d
co
n
tr
o
l
p
o
in
ts
i
n
t
h
e
f
r
o
n
ta
l
i
m
a
g
e
s
b
ac
k
to
th
e
r
a
w
i
m
ag
e
s
.
R
e
-
o
p
ti
m
ize
t
h
e
ca
m
er
a
p
ar
am
eter
s
to
g
et
h
er
w
it
h
t
h
e
w
o
r
ld
co
o
r
d
in
ates
o
f
t
h
e
co
n
t
r
o
l
p
o
in
ts
.
T
h
is
iter
ativ
e
r
e
f
i
n
e
m
en
t
ap
p
r
o
ac
h
is
b
o
o
ts
tr
ap
p
e
d
u
s
in
g
s
tan
d
ar
d
ca
lib
r
atio
n
r
o
u
tin
e
o
f
Op
en
C
V,
w
h
i
ch
p
r
o
v
id
e
i
n
itial
e
s
ti
m
ates
f
o
r
r
ad
ial
d
is
to
r
tio
n
an
d
ca
m
er
a
p
ar
a
m
et
er
s
.
Ou
r
w
o
r
k
h
as
h
elp
ed
to
d
er
iv
e
th
e
in
e
f
f
icie
n
c
y
o
f
Ho
u
g
h
T
r
an
s
f
o
r
m
alg
o
r
it
h
m
f
o
r
cir
cle
d
etec
tio
n
.
T
h
e
alg
o
r
ith
m
ca
n
n
o
t b
e
u
s
ed
to
d
eter
m
i
n
e
co
n
ce
n
tr
ic
cir
cle
s
b
ec
au
s
e
i
t r
eq
u
ir
es a
m
i
n
i
m
u
m
p
o
s
iti
v
e
d
is
ta
n
c
e
b
et
w
ee
n
th
e
ce
n
ter
s
o
f
t
h
e
s
et
o
f
cir
cles
to
b
e
d
etec
ted
.
Mo
r
eo
v
er
,
m
o
s
t
o
f
t
h
e
i
m
a
g
es
ar
e
ac
tu
all
y
p
er
ce
i
v
ed
as
ellip
s
es
d
u
e
to
th
eir
o
r
ien
ta
tio
n
.
Hen
ce
,
th
o
u
g
h
th
e
ca
lib
r
atin
g
o
b
j
ec
t
is
a
r
in
g
g
r
id
p
atter
n
,
Ho
u
g
h
C
ir
cle
T
r
an
s
f
o
r
m
d
o
es
n
o
t
a
s
s
i
s
t
i
n
th
e
ca
lib
r
atio
n
p
r
o
ce
d
u
r
e.
Hen
ce
t
h
e
al
g
o
r
ith
m
d
e
s
i
g
n
ed
b
y
o
u
r
p
r
o
j
ec
t
tea
m
w
o
u
ld
b
e
b
en
ef
icial
i
n
f
in
d
i
n
g
th
e
cir
cles
w
it
h
al
m
o
s
t
n
eg
li
g
ib
le
er
r
o
r
m
ar
g
i
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
3
,
No
.
3
,
Sep
tem
b
er
20
1
4
:
1
3
6
–
1
4
4
144
RE
F
E
R
E
NC
E
S
[1
]
Z.
Zh
a
n
g
.
A
f
le
x
ib
l
e
n
e
w
tec
h
n
iq
u
e
f
o
r
c
a
m
e
ra
c
a
li
b
ra
ti
o
n
P
A
M
I
2
2
(1
1
),
2
0
0
0
.
[2
]
A
n
k
u
r
Da
tt
a
,
Ju
n
-
S
ik
Kim
,
T
a
k
e
o
Ka
n
a
d
e
,
A
c
c
u
ra
te
Ca
m
e
r
a
C
a
li
b
ra
ti
o
n
u
si
n
g
Itera
ti
v
e
Re
f
in
e
m
e
n
t
o
f
Co
n
tr
o
l
P
o
in
ts
[3
]
R.
T
sa
i.
A
v
e
rsa
ti
le
c
a
m
e
ra
c
a
li
b
ra
ti
o
n
tec
h
n
i
q
u
e
f
o
r
h
ig
h
-
a
c
c
u
r
a
c
y
3
d
m
a
c
h
in
e
v
isio
n
m
e
tro
lo
g
y
u
sin
g
o
ff
-
th
e
-
sh
e
lf
T
V
c
a
m
e
ra
s an
d
len
se
s.
IEE
E
J
RA
,
3
(4
),
1
9
8
7
.
[4
]
Q.
Ch
e
n
,
H.W
u
,
a
n
d
T
.
W
a
d
a
.
Ca
m
e
ra
c
a
li
b
ra
ti
o
n
w
it
h
tw
o
a
rb
it
ra
r
y
c
o
p
lan
a
r
c
ircle
s.
In
ECCV,
2
0
0
4
.
[5
]
J.
He
ik
k
il
a
.
,
Ge
o
m
e
tri
c
Ca
m
e
r
a
C
a
li
b
ra
ti
o
n
u
si
n
g
c
ircu
lar co
n
tro
l
p
o
i
n
ts.
P
A
M
I,
2
2
(
1
0
)
,
2
0
0
0
.
[6
]
Jo
h
a
n
C.
v
a
n
d
e
n
He
u
v
e
l,
Ja
n
C
.
M
.
Kle
ij
w
e
g
,
Wan
n
e
s
v
a
n
d
e
r
M
a
rk
,
Ch
risti
a
a
n
M
.
L
iev
e
rs,L
e
o
n
J.H.M
.
Ke
ste
r,
Ob
sta
c
le De
tec
ti
o
n
F
o
r
P
e
o
p
le M
o
v
e
rs Usin
g
V
isio
n
A
n
d
Ra
d
a
r
.
[7
]
h
tt
p
:
//
e
n
.
w
ik
ip
e
d
ia.o
rg
/w
ik
i/
Ho
u
g
h
_
tran
sf
o
rm
[8
]
h
tt
p
:
//
e
n
.
w
ik
ip
e
d
ia.o
rg
/w
ik
i/
S
e
g
m
e
n
tatio
n
_
%
2
8
im
a
g
e
_
p
ro
c
e
ss
in
g
%
2
9
[9
]
h
tt
p
:
/
/en
.
w
ik
ip
e
d
ia.o
rg
/w
ik
i/
Ed
g
e
_
d
e
tec
ti
o
n
[1
0
]
h
tt
p
:
//
e
n
.
w
ik
ip
e
d
ia.o
rg
/w
ik
i/
De
la
u
n
a
y
_
tri
a
n
g
u
latio
n
[1
1
]
h
tt
p
:
//
e
n
.
w
ik
ip
e
d
ia.o
rg
/w
ik
i/
In
terp
o
lati
o
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.