I
n
t
ern
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
E
l
ect
ri
ca
l
a
n
d
C
o
m
p
u
t
er E
n
g
i
n
eeri
n
g
(
I
J
E
C
E
)
V
o
l.
8
,
No
.
5
,
O
c
t
obe
r
20
1
8
,
p
p.
32
96~
3
303
I
S
S
N
:
2088
-
8708
,
D
O
I
:
10.
11
591/
i
j
ece
.
v8
i
5
.
pp
329
6
-
3303
3296
Jou
r
n
al
h
om
e
p
age
:
h
ttp
:
//ia
e
s
c
o
r
e
.
c
o
m/
j
our
nal
s
/
i
nde
x
.
php/
I
J
E
C
E
New
Appro
a
ch f
o
r Det
ect
ing
a
nd
T
ra
ck
ing
a
M
o
v
ing
O
b
j
ect
H.
H
a
t
i
mi
1
, M
.
F
a
ki
r
2
, M
.
C
ha
bi
3
, M
.
N
a
j
i
mi
4
1,
3
L
ab
o
r
at
o
r
y
o
f
M
at
h
e
m
at
i
cs
an
d
A
p
p
l
i
cat
i
o
n
s
,
F
acu
l
t
y
o
f
S
ci
en
ce
s
an
d
T
ech
n
i
cs
,
U
n
i
v
er
s
i
t
y
S
u
l
t
an
M
o
u
l
ay
S
l
i
m
an
e,
M
o
r
o
cco
2
L
a
bor
a
t
or
y
of
I
n
f
or
m
a
t
i
on
P
r
oc
e
s
s
i
ng
a
nd D
e
c
i
s
i
on
S
u
pp
or
t
(
T
I
A
D
)
,
F
a
c
ul
t
y
of
S
c
i
e
nc
e
s
a
nd T
e
c
h
ni
c
s
,
U
ni
v
e
r
s
i
t
y
S
u
l
t
a
n M
ou
l
ay
S
l
i
m
an
e,
M
o
r
o
cco
4
L
a
bor
a
t
or
y
of
B
i
ol
og
i
c
a
l
E
ng
i
ne
e
r
i
ng
,
F
a
c
ul
t
y
of
S
c
i
e
nc
e
a
nd T
e
c
hno
l
og
y
,
S
ul
t
a
n
M
o
ul
a
y
S
l
i
m
a
ne
U
ni
v
e
r
s
i
t
y
,
M
o
r
o
cco
A
rt
i
cl
e I
n
f
o
AB
S
T
RAC
T
A
r
tic
le
h
is
to
r
y
:
R
ecei
v
ed
No
v
12
,
201
7
Re
v
i
se
d
J
an
4
,
201
8
A
ccep
t
ed
J
an
20
,
2
01
8
T
h
is
a
r
tic
le
p
r
e
s
e
n
ts
th
e
im
p
le
m
e
n
ta
tio
n
o
f
a
tr
a
c
k
in
g
s
y
s
te
m
f
o
r
a
m
o
v
in
g
t
ar
g
et
u
s
i
n
g
a f
i
x
ed
ca
m
er
a.
T
h
e o
b
j
ect
i
v
e o
f
t
h
i
s
w
o
r
k
i
s
t
h
e ab
i
l
i
t
y
t
o
d
et
ect
a
m
ov
i
ng
obj
e
c
t
a
nd
l
oc
a
t
e
t
he
i
r
pos
i
t
i
o
ns
.
I
n
pi
c
t
ur
e
pr
oc
e
s
s
i
n
g
,
t
r
a
c
k
i
ng
m
ov
i
ng
obj
e
c
t
s
i
n a
k
no
w
n or
un
k
now
n e
nv
i
r
onm
e
nt
i
s
c
o
m
m
onl
y
s
t
udi
e
d.
I
t
i
s
b
as
ed
o
n
i
n
v
ar
i
an
ce p
r
o
p
er
t
i
es
o
f
o
b
j
ect
s
o
f
i
n
t
er
es
t
.
T
h
e i
n
v
ar
i
an
ce can
a
f
f
e
c
t
t
he
ge
o
m
e
t
r
y
of
t
he
s
c
e
ne
or
t
he
obj
e
c
t
s
.
T
he
pr
opos
e
d a
ppr
oa
c
h i
s
c
om
pos
e
d of
s
e
v
e
r
a
l
s
t
e
ps
;
t
he
f
i
r
s
t is
th
e
e
x
tr
a
c
tio
n
o
f
p
o
in
ts
o
f
in
te
r
e
s
t in
t
h
e cu
r
r
en
t
i
m
ag
e.
T
h
en
,
t
h
es
e p
o
i
n
t
s
w
i
l
l
b
e t
r
ack
ed
i
n
t
h
e f
o
l
l
o
w
i
n
g
i
m
a
g
e
b
y
u
s
in
g
te
c
h
n
iq
u
e
s
f
o
r
c
a
lc
u
la
tin
g
th
e
o
p
tic
a
l f
lo
w
.
A
f
te
r
th
is
s
te
p
,
th
e
s
ta
tic
poi
nt
s
w
i
l
l
be
r
e
m
ove
d t
o f
oc
us
on m
ov
i
ng
obj
e
c
t
s
,
T
h
a
t is
to
s
a
y
,
th
e
r
e
is
onl
y
t
he
c
ha
r
a
c
t
e
r
i
s
t
i
c
poi
nt
s
be
l
ong
i
ng
t
o m
ov
i
ng
obj
e
c
t
s
.
N
ow
,
t
o de
t
e
c
t
m
ov
i
ng
t
a
r
g
e
t
s
us
i
ng
i
m
a
g
e
s
o
f
t
he
v
i
de
o,
t
he
ba
c
k
g
r
ound i
s
f
i
r
s
t
e
x
t
r
a
c
t
e
d
f
r
o
m
t
h
e s
u
cces
s
i
v
e i
m
ag
es
.
I
n
o
u
r
ap
p
r
o
ach
,
a m
et
h
o
d
o
f
t
h
e av
e
r
ag
e
v
al
u
es
of
e
v
e
r
y
pi
x
e
l
ha
s
be
e
n de
v
e
l
op
e
d f
or
m
ode
l
i
ng
ba
c
k
g
r
ound.
T
h
e
l
a
s
t
s
t
e
p
w
hi
c
h s
t
a
y
s
be
f
or
e
s
w
i
t
c
hi
ng
t
o
t
r
a
c
k
i
ng
m
ov
i
ng
obj
e
c
t
i
s
t
he
s
e
gm
e
nt
a
t
i
on
w
hi
c
h a
l
l
ow
s
i
de
nt
i
f
y
i
ng
e
ve
r
y
m
ov
i
ng
obj
e
c
t
.
A
nd by
us
i
ng
t
he
ch
ar
act
er
i
s
t
i
c p
o
i
n
t
s
i
n
t
h
e p
r
ev
i
o
u
s
s
t
ep
s
.
K
e
y
wo
r
d
:
B
a
c
k
g
r
oun
d m
ode
l
i
ng
M
o
vi
n
g t
a
r
ge
t
O
p
tic
a
l f
lo
w
S
e
g
m
e
n
ta
tio
n
T
r
ack
i
n
g
o
b
j
ect
C
opy
r
i
g
ht
©
201
8
I
ns
t
i
t
ut
e
o
f
A
d
v
anc
e
d E
ngi
ne
e
r
i
ng
an
d
Sc
i
e
nc
e
.
A
l
l
ri
g
h
t
s re
se
rv
e
d
.
Co
rre
sp
o
n
d
i
n
g
Au
t
h
o
r
:
H
.
H
a
ti
m
i,
L
a
bor
a
t
or
y
of
M
a
t
h
e
m
a
t
i
c
s
a
nd A
ppl
i
c
a
t
i
on
s
,
F
acu
l
t
y
o
f
S
c
i
en
ce
s
an
d
T
ech
n
i
cs
,
U
ni
ve
r
s
i
t
y S
ul
t
a
n M
o
ul
a
y S
l
i
m
a
ne
,
B
en
i
M
el
l
al
,
Mo
r
o
cco
.
E
m
a
il: h
.
h
a
ti
m
i
@
u
s
m
s
.
m
a
1.
I
NT
RO
D
UCT
I
O
N
T
r
ack
i
n
g
a
m
o
v
i
n
g
o
b
j
ect
i
s
t
h
e s
u
b
j
ect
o
f
act
i
v
e r
es
ear
ch
i
n
co
m
p
u
t
er
v
i
s
i
o
n
[1
]
.
S
ev
er
a
l
m
et
h
o
d
s
ar
e u
s
ed
f
o
r
t
h
e d
et
ect
i
o
n
a
n
d
t
r
ack
i
n
g
o
f
a
m
o
v
i
n
g
o
b
j
ec
t
[2
]
,
[
3
]
,
[
4
]
,
u
s
in
g
o
p
tic
a
l f
lo
w
[
5
]
,
[
6
]
.
S
o
me
m
et
h
o
d
s
ar
e b
as
ed
o
n
act
i
v
e
co
n
t
o
u
r
s
w
h
i
c
h
o
r
i
g
i
n
at
e
el
as
t
i
c
m
o
d
el
s
h
a
v
e t
h
ei
r
o
r
i
g
i
n
s
f
r
o
m
e
l
as
t
i
c
m
o
d
el
s
[
7
]
,
o
r
b
a
c
kgr
o
und
s
u
b
t
r
act
i
o
n
.
B
ack
g
r
o
u
n
d
s
u
b
t
r
act
i
o
n
i
s
g
en
er
al
l
y
u
s
ed
t
o
d
et
ect
m
o
v
i
n
g
o
b
j
ect
s
i
n
a s
cen
e
[
8
]
.
T
h
i
s
m
e
t
h
o
d
i
s
t
o
co
m
p
ar
e t
h
e c
u
r
r
en
t
i
m
ag
e
t
o
a s
t
at
i
c
m
o
d
el
o
f
t
h
e
s
ce
n
e,
cal
l
ed
t
h
e r
ef
er
en
ce
i
m
a
g
e,
an
d
an
y
el
e
m
en
t
p
r
es
e
n
t
i
n
t
h
e cu
r
r
en
t
i
m
a
g
e an
d
ab
s
en
t
i
n
t
h
e r
ef
er
en
ce i
m
a
g
e i
s
co
n
s
i
d
er
ed
m
o
b
i
l
e.
T
h
er
e
ar
e ev
en
m
et
h
o
d
s
t
h
at
h
av
e b
een
p
r
o
p
o
s
ed
f
o
r
t
h
e d
et
ect
i
o
n
o
f
m
o
v
i
n
g
t
ar
g
et
s
b
y
m
i
n
i
m
i
zi
n
g
t
h
e s
t
o
c
h
as
t
i
c
c
o
m
p
l
e
xi
t
y
[9
]
.
A
s
r
eg
ar
d
s
t
h
e t
r
ack
i
n
g
o
f
a
m
o
v
i
n
g
o
b
j
ect
i
n
t
h
e 2
D
i
m
a
g
e,
s
e
v
er
al
m
et
h
o
d
s
h
av
e b
ee
n
pr
opos
e
d.
F
o
r
ex
a
m
p
l
e,
t
h
er
e ar
e
m
et
h
o
d
s
w
h
i
c
h
co
n
s
i
s
t
i
n
d
es
cr
i
b
i
n
g
t
h
e o
b
j
ect
t
o
b
e t
r
ack
ed
u
s
i
n
g
g
eo
m
e
t
r
i
c
p
r
im
iti
v
e
s
a
s
p
a
r
tic
u
la
r
p
o
in
t
s
[1
0
]
,
[1
1
],
a
ngl
e
s
,
c
o
nt
o
ur
s
[
12]
,
[
13]
,
se
g
m
e
n
t
s
[1
4
],
o
r
e
llip
s
e
s
[
15]
.
A
c
tiv
e
c
o
nt
o
ur
s
o
r
s
na
ke
s
c
a
n a
l
s
o
b
e
u
s
ed
t
o
d
et
er
m
i
n
e a co
m
p
l
e
x
f
o
r
m
[
16]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
le
c
&
C
o
m
p E
ng
I
S
S
N
:
2088
-
8708
N
e
w
A
ppr
oac
h f
or
D
e
t
e
c
t
i
ng a
nd T
r
ac
k
i
ng a
M
ov
i
ng O
bj
e
c
t
(
H.
Ha
t
i
mi
)
3297
T
o f
i
l
t
e
r
s
m
a
l
l
pe
r
i
odi
c
m
o
t
i
on
s
i
n t
h
e
ba
c
kg
r
oun
d,
f
or
e
x
a
m
p
l
e
l
i
gh
t
i
n
g c
on
t
r
ol
,
G
a
u
s
s
i
a
n
m
i
x
t
u
r
e
m
ode
l
[
17]
,
an
d
t
h
e b
a
y
es
i
an
m
o
d
el
[1
8
]
ar
e co
m
m
o
n
l
y
u
s
ed
.
I
n i
m
a
ge
p
r
o
c
e
s
s
i
n
g a
nd
c
o
m
p
ut
e
r
vi
s
i
o
n,
t
r
a
c
ki
n
g
m
o
vi
n
g o
b
j
e
c
t
s
i
n a
k
no
w
n o
r
u
n
kno
w
n
e
nvi
r
o
n
m
e
nt
i
s
c
o
m
m
o
nl
y s
t
ud
i
e
d
.
I
t
i
s
b
a
s
e
d
o
n i
n
va
r
i
a
nc
e
p
r
o
p
er
t
i
es
o
f
o
b
j
ect
s
o
f
i
n
t
e
r
es
t
.
T
h
e i
n
v
ar
i
a
n
ce ca
n
af
f
ect
t
h
e
g
eo
m
et
r
y
o
f
t
h
e
s
ce
n
e o
r
o
b
j
ect
s
,
t
h
e
ap
p
ear
an
ce o
f
o
b
j
ect
s
(
t
h
at
i
s
t
o
s
a
y
p
h
o
t
o
m
et
r
y
o
r
co
l
o
r
)
o
r
k
i
n
e
m
a
tic
(
s
u
c
h
a
s
s
p
a
tia
l a
n
d
te
m
p
o
r
a
l
c
o
n
s
tr
a
in
ts
)
.
T
h
e o
b
j
ect
o
f
t
h
i
s
p
ap
er
i
s
t
h
e d
et
ect
i
o
n
a
n
d
l
o
cat
i
o
n
o
f
a d
ef
o
r
m
ab
l
e o
b
j
ect
i
n
m
o
t
i
o
n
f
r
o
m
a
s
eq
u
en
ce
o
f
i
m
ag
e
s
.
T
h
i
s
r
es
ear
ch
al
l
o
w
s
d
et
er
m
i
n
i
n
g
w
i
t
h
a
n
e
f
f
ect
i
v
e a
n
d
p
r
eci
s
e
m
e
t
h
o
d
,
i
t
s
p
o
s
i
t
i
o
n
i
n
each
i
m
a
ge
a
nd
d
e
t
e
r
m
i
ni
ng
i
t
s
m
o
ve
m
e
n
t
o
r
a
p
p
a
r
e
nt
m
o
ve
m
e
nt
f
r
o
m
o
ne
i
m
a
ge
t
o
a
no
t
he
r
.
F
o
r
go
o
d
r
es
u
l
t
s
,
w
as
u
s
ed
a ca
m
er
a p
o
i
n
t
ed
d
o
w
n
w
ar
d
,
i
t
s
o
p
t
i
c
al
ax
i
s
i
s
al
i
g
n
ed
w
i
t
h
t
h
e
v
er
t
i
cal
.
T
h
e r
at
i
n
m
o
ve
m
e
nt
s
ho
ul
d
b
e
p
ut
i
n a
d
e
vi
c
e
a
t
t
he
b
o
t
t
o
m
o
f
t
he
c
a
m
e
ra
in
F
i
gur
e
1
.
T
he
p
r
o
b
l
e
m
t
o
s
o
l
ve
i
s
ho
w
t
o
co
l
l
ect
i
n
f
o
r
m
at
i
o
n
ab
o
u
t
t
h
e
m
o
v
i
n
g
o
b
j
ect
d
u
r
i
n
g
a cap
t
u
r
e s
eq
u
en
ce.
T
h
i
s
i
n
f
o
r
m
at
i
o
n
w
i
l
l
b
e t
h
e n
u
m
b
er
o
f
acces
s
e
s
t
o
ev
er
y
zo
n
e o
f
t
h
e
o
p
en
f
i
el
d
,
t
h
e
m
o
b
i
l
i
t
y
o
f
r
at
(
t
h
e t
i
m
e
w
h
e
n
t
h
e r
at
i
n
m
o
v
e
m
e
n
t
)
a
nd
i
m
m
o
b
i
l
i
t
y
(
t
he
t
i
m
e
w
he
n t
he
r
a
t
s
t
a
y
s
w
i
t
ho
ut
m
o
ve
m
e
nt
)
.
F
i
g
ur
e
1
.
M
o
tio
n
cap
t
u
r
e s
y
s
t
e
m
s
T
h
is
p
a
p
e
r
is
o
r
g
a
n
iz
e
d
a
s
f
o
llo
w
s
: I
n
th
e
s
e
c
tio
n
I
I
y
o
u
w
i
ll s
e
e
th
e
s
te
p
s
to
f
o
llo
w
to
d
e
te
c
t a
n
d
t
r
ack
a
m
o
v
i
n
g
o
b
j
ect
.
I
n
t
h
i
s
s
ect
i
o
n
t
h
er
e i
s
a
n
e
x
p
l
an
at
i
o
n
o
f
t
h
e d
i
f
f
er
en
t
s
t
ep
s
o
f
o
u
r
ap
p
r
o
ach
.
T
h
e f
i
r
s
t
p
a
r
t o
f
th
is
s
e
c
tio
n
d
e
a
ls
w
i
th
e
x
tr
a
c
tio
n
o
f
i
n
t
er
es
t
p
o
i
n
t
s
.
T
h
e s
eco
n
d
p
ar
t
d
eal
s
w
i
t
h
m
et
h
o
d
o
f
cal
cu
l
at
i
n
g
th
e
o
p
tic
f
lo
w
.
T
h
e
n
e
x
t p
a
r
t
d
e
a
ls
w
i
th
m
e
th
o
d
s
to
r
e
m
o
v
e
i
m
m
o
b
ile
i
n
te
r
e
s
t
p
o
in
t.
N
e
x
t,
t
h
e
f
o
llo
w
i
n
g
s
e
c
t
i
on
di
s
c
us
s
e
s
t
h
e
ba
c
kg
r
ou
n
d
m
ode
l
i
ng
m
e
t
h
od.
F
i
na
l
l
y
,
t
h
e
l
a
s
t
t
w
o
of
t
h
e
s
e
c
tio
n
I
I
d
is
c
u
s
s
e
s
s
eg
m
e
n
t
at
i
o
n
m
et
h
o
d
s
an
d
T
r
ack
i
n
g
t
h
e
m
o
v
i
n
g
o
b
j
ect
.
S
ect
i
o
n
I
I
I
r
ep
r
es
en
t
s
t
h
e r
es
u
l
t
s
o
f
e
x
p
er
i
m
e
n
t
s
co
n
d
u
ct
ed
i
n
t
h
e l
ab
o
r
at
o
r
y
,
i
n
t
h
e en
d
a co
n
cl
u
s
i
o
n
.
2.
R
ES
EA
R
C
H
M
ETH
O
D
T
he
s
t
e
p
f
o
r
d
e
t
e
c
t
i
ng a
nd
t
r
a
c
k t
he
m
o
vi
n
g o
b
j
ect
ar
e
illu
s
tr
a
te
d
i
n
F
i
g
u
r
e
2
.
T
h
i
s
ap
p
r
o
ach
i
s
c
om
pos
e
d of
6 s
t
e
ps
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SSN
:
20
88
-
8708
In
t
J
E
l
e
c
&
C
o
m
p
E
n
g
,
V
o
l.
8
, N
o
.
5
,
O
c
t
obe
r
20
18
:
329
6
-
3303
3
298
F
ig
u
r
e
2
.
E
f
f
e
c
t
s
o
f
s
e
le
c
tin
g
d
if
f
e
r
e
n
t s
w
i
tc
h
i
n
g
u
n
d
e
r
d
y
n
a
m
ic
c
o
n
d
itio
n
2
.1
.
E
x
tr
a
c
ti
n
g
P
o
i
n
ts
o
f I
n
te
r
e
s
t
E
x
t
r
act
i
o
n
o
f
i
n
t
er
es
t
p
o
i
n
t
s
i
n
an
i
m
ag
e i
s
t
o
f
i
n
d
t
h
e p
o
i
n
t
s
t
h
at
can
b
e eas
i
l
y
r
eco
g
n
i
zed
an
d
f
o
l
l
o
w
e
d
b
y
a
n i
m
a
ge
t
o
a
no
t
he
r
i
n
F
i
gu
r
e
3.
M
a
ny
m
e
t
hods
h
a
v
e
be
e
n
pr
opos
e
d f
or
t
h
i
s
s
i
m
pl
e
c
or
n
e
r
d
et
ect
o
r
[1
9
]
w
i
th
m
u
ltis
c
a
le
m
e
t
h
o
d
s
,
in
v
a
r
ia
n
t i
n
t
h
e
r
o
t
a
t
i
o
ns
a
nd
i
n t
he
c
ha
nge
s
o
f
p
e
r
s
p
e
c
t
i
ve
.
A
nu
m
b
e
r
of
m
e
t
h
ods
h
a
v
e
a
l
s
o be
e
n
pr
opos
e
d t
o a
s
s
e
s
s
t
h
e
r
obu
s
t
n
e
s
s
of
t
h
e
s
e
e
x
t
r
a
c
t
or
s
.
F
o
r
t
h
i
s
p
r
o
b
l
e
m
,
t
h
e i
n
p
u
t
d
at
a o
f
t
h
e
s
y
s
t
e
m
i
s
al
w
a
y
s
acq
u
i
r
ed
b
y
t
h
e ca
m
er
a.
H
o
w
ev
er
,
d
at
a
o
u
tp
u
t
h
e
r
e
is
a
li
s
t o
f
p
o
i
nt
s
.
I
t
i
s
t
h
e
r
e
f
or
e
n
e
c
e
s
s
a
r
y
t
o
de
f
i
n
e
on
e
or
m
or
e
ope
r
a
t
or
s
t
o bu
i
l
d a
l
i
s
t
of
poi
n
t
s
.
T
h
e m
o
s
t
co
m
m
o
n
l
y
u
s
ed
f
o
r
t
h
i
s
i
s
t
o
ex
t
r
act
l
o
cal
m
ax
i
m
a
o
f
an
i
m
ag
e.
I
t
i
s
al
s
o
n
ece
s
s
a
r
y
t
o
t
r
a
n
s
f
o
r
m
t
h
e
i
np
ut
i
m
a
ge
i
n o
r
d
e
r
t
o
i
d
e
nt
i
f
y p
o
i
nt
s
o
f
i
nt
e
r
e
s
t
.
W
e
u
s
e
t
h
e H
ar
r
i
s
co
r
n
er
d
et
ect
o
r
[1
9
]
t
o
ex
t
r
act
t
h
e
f
eat
u
r
e
p
o
i
nt
s
w
h
i
c
h e
xi
s
t
o
n
t
he
i
m
a
ge
s
o
f
t
he
vi
d
e
o
i
n
F
ig
u
r
e
3
.
N
o
w
w
e
m
u
s
t
e
li
m
i
n
a
te
th
e
p
o
in
ts
t
h
a
t a
r
e
m
o
tio
n
le
s
s
,
ite
m
s
t
h
a
t d
o
n
o
t b
e
lo
n
g
to
th
e
m
o
v
in
g
o
b
j
e
c
t in
th
e
v
id
e
o
u
s
in
g
o
p
tic
a
l f
lo
w
.
F
ig
u
r
e
3
.
E
x
tr
a
c
tio
n
o
f
i
n
te
r
e
s
t p
o
in
t
2
.2
.
C
a
l
c
ul
a
t
i
o
n
a
nd P
r
o
pe
r
t
i
e
s
o
f
t
he
O
pt
i
c
a
l
F
l
o
w
T
h
e
m
o
tio
n
e
s
ti
m
a
tio
n
i
s
to
d
e
te
r
m
i
n
e
th
e
m
o
tio
n
v
e
c
to
r
s
f
o
r
p
r
e
d
ic
tin
g
t
h
e
p
r
o
c
e
s
s
in
g
o
f
a
n
i
m
a
g
e
t
o
an
o
t
h
er
i
m
ag
e i
n
a v
i
d
eo
s
eq
u
en
ce.
Mo
t
i
o
n
v
ect
o
r
s
m
a
y
b
e f
o
r
t
h
e en
t
i
r
e i
m
a
g
e o
r
a p
ar
t
o
f
t
h
e i
m
a
g
e.
T
h
es
e
m
o
t
i
o
n
v
ect
o
r
s
m
a
y
co
r
r
es
p
o
n
d
t
o
a s
i
m
p
l
e t
r
an
s
l
at
i
o
n
o
r
g
en
er
al
l
y
a
n
y
p
at
t
er
n
cap
ab
l
e o
f
ap
p
r
o
ach
i
n
g
t
h
e act
u
a
l
m
o
v
e
m
e
n
t
o
f
t
h
e ca
m
er
a o
r
m
o
v
e
m
en
t
o
f
o
b
j
ect
s
i
n
t
h
e
s
cen
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
le
c
&
C
o
m
p E
ng
I
S
S
N
:
2088
-
8708
N
e
w
A
ppr
oac
h f
or
D
e
t
e
c
t
i
ng a
nd T
r
ac
k
i
ng a
M
ov
i
ng O
bj
e
c
t
(
H.
Ha
t
i
mi
)
3299
I
n
th
i
s
w
o
r
k
,
th
e
o
p
tic
a
l f
lo
w
p
la
y
s
a v
er
y
i
m
p
o
r
t
an
t
r
o
l
e i
n
t
h
e d
et
ect
i
o
n
o
f
t
h
e
m
o
v
i
n
g
t
ar
g
et
.
T
h
e
pu
r
pos
e
of
t
h
i
s
s
e
c
t
i
on i
s
t
o
i
n
t
r
odu
c
e
t
h
e
c
o
n
c
e
pt
of
opt
i
c
a
l
f
l
o
w
,
pr
ope
r
t
i
e
s
a
n
d
m
e
t
h
ods
of
c
a
l
c
u
l
a
t
i
on
as
s
o
ci
at
ed
,
an
d
d
ef
i
n
e al
s
o
s
o
m
e p
r
o
p
er
t
i
es
o
f
t
h
e o
p
t
i
cal
f
l
u
x
u
s
ed
i
n
t
h
e f
i
e
l
d
o
f
vi
s
i
o
n.
T
hi
s
w
o
r
k c
o
nt
a
i
ns
ta
x
o
n
o
m
y
o
f
t
h
e
v
a
r
io
u
s
m
e
th
o
d
s
o
f
o
p
tic
a
l
f
lo
w
c
a
lc
u
la
tio
n
d
e
v
e
lo
p
e
d
s
in
c
e
th
e
e
a
r
l
y
8
0
'
s
u
n
til
n
o
w
.
F
i
n
al
l
y
,
t
h
e a
u
t
h
o
r
s
d
et
er
m
i
n
e
w
h
at
ar
e
t
h
e
m
o
s
t
ap
p
r
o
p
r
i
at
e
m
et
h
o
d
s
a
n
d
t
h
e
m
o
s
t
r
el
ev
an
t
p
r
o
p
er
t
i
es
t
o
s
ol
v
e
ou
r
pr
obl
e
m
.
T
h
e o
p
t
i
cal
f
l
o
w
ca
n
b
e d
ef
i
n
ed
as
t
h
e
m
o
v
e
m
en
t
o
f
t
h
e i
m
ag
e
o
n
t
h
e r
et
i
n
a (
h
u
m
an
o
r
ar
t
i
f
i
ci
al
)
,
m
o
r
e p
r
eci
s
el
y
,
i
t
i
s
t
h
e
f
i
el
d
o
f
r
et
i
n
al
v
el
o
ci
t
y
:
t
h
e
v
el
o
ci
t
y
o
f
t
h
e p
r
o
j
ect
i
o
n
s
p
ace o
n
t
h
e r
et
i
n
a.
I
t
d
ep
en
d
s
o
n s
e
ve
r
a
l
f
a
c
t
o
r
s
,
s
uc
h a
s
t
he
s
ha
p
e
s
o
f
o
b
j
ect
s
,
t
h
ei
r
o
w
n
s
p
eed
,
t
h
e d
i
s
t
a
n
ce o
r
t
h
e r
el
a
t
i
v
e
s
p
eed
b
et
w
ee
n
t
h
e o
b
j
ect
an
d
t
h
e cam
er
a (
o
r
t
h
e e
y
e)
.
I
t
i
s
a v
al
u
ab
l
e cl
u
e
i
n
h
u
m
an
p
er
cep
t
i
o
n
t
o
a
m
o
n
g
o
t
h
er
s
es
t
i
m
at
e a
ti
m
e
b
e
f
o
r
e
c
o
llis
io
n
.
F
ig
u
r
e
4
.
E
x
tr
a
c
tio
n
o
f
t
h
e
o
p
tic
a
l f
lo
w
I
n t
hi
s
s
e
c
t
i
o
n,
t
he
a
ut
ho
r
s
gi
ve
a
n o
ve
r
vi
e
w
o
f
d
i
f
f
e
r
e
nt
t
e
c
hni
q
ue
s
f
o
r
c
o
m
p
ut
i
n
g t
he
o
p
t
i
c
a
l
f
l
o
w
w
i
t
h
a
de
t
a
i
l
e
d t
a
x
on
o
m
y
.
A
c
om
pr
e
h
e
ns
i
v
e
r
e
v
i
e
w
of
m
e
t
hods
de
v
e
l
ope
d i
n
t
h
e
80
-
9
0
y
e
ar
s
w
as
co
n
d
u
ct
ed
b
y B
a
r
r
o
n,
F
l
e
e
t
a
nd
B
e
a
uc
h
e
m
i
n
[
20]
.
I
t
d
es
cr
i
b
es
i
n
d
et
ai
l
s
o
m
e o
f
t
h
e
m
et
h
o
d
s
p
r
es
en
t
ed
b
el
o
w
.
T
h
e
au
t
h
o
r
s
w
i
d
el
y
u
s
e t
h
i
s
s
t
u
d
y
t
o
d
es
cr
i
b
e t
h
e o
l
d
es
t
m
et
h
o
d
s
,
an
d
w
i
l
l
co
m
p
l
et
e b
y
t
h
e
m
o
s
t
r
ecen
t
r
es
u
l
t
s
.
In
1981 H
or
n
a
n
d S
c
h
un
c
k
[
21]
,
f
o
r
m
u
la
te
w
h
a
t
w
i
ll b
e
t
h
e
b
a
s
is
o
f
a
ll
d
if
f
e
r
e
n
tia
l
m
e
t
h
o
d
s
: s
tr
e
s
s
g
r
a
d
i
e
nt
.
T
h
i
s
co
n
s
t
r
ai
n
t
f
o
l
l
o
w
s
d
i
r
ect
l
y
f
r
o
m
t
h
e h
y
p
o
t
h
es
i
s
ab
o
v
e.
H
er
e i
s
a q
u
i
ck
d
em
o
:
D
i
f
f
e
r
e
n
tia
l tr
a
n
s
la
tio
n
o
f
t
he
h
yp
o
t
he
s
i
s
i
s
:
=
0
(1
)
T
h
a
t is
to
s
a
y
+
+
=
0
(2
)
+
+
=
0
(3
)
T
h
e eq
u
at
i
o
n
(
3
)
can
b
e r
e
w
r
i
t
t
en
i
n
an
o
t
h
er
ex
p
r
es
s
i
o
n
g
i
v
en
i
n
eq
u
at
i
o
n
(
4
)
.
T
h
i
s
n
e
w
eq
u
at
i
o
n
i
s
cal
l
ed
"
s
tr
a
in
g
r
a
d
ie
n
t"
.
∇
⃗
.
⃗
+
=
0
(4
)
E
q
u
a
tio
n
(
4
)
c
o
n
s
tr
a
in
s
th
e
o
p
tic
a
l f
lo
w
f
ie
ld
~
v
a
c
c
o
r
d
in
g
t
o
th
e
g
r
a
d
ie
n
t o
f
t
h
e
li
g
h
t in
te
n
s
it
y
∇
⃗
=
(
,
)
(5
)
T
h
i
s
eq
u
at
i
o
n
(
3
)
g
i
v
es
o
n
l
y
o
n
e co
n
s
t
r
ai
n
t
an
d
t
h
er
ef
o
r
e n
o
t
p
o
s
s
i
b
l
e t
o
cal
cu
l
at
e t
h
e t
w
o
c
om
pon
e
n
t
s
of
t
h
e
opt
i
c
a
l
f
l
o
w
di
r
e
c
t
l
y
.
T
ha
t
i
s
w
h
y
H
o
r
n a
nd
S
c
hu
nc
k
[
21]
i
m
p
o
s
e
a s
ec
o
nd
c
o
ns
t
r
a
i
nt
(
c
a
lle
d
a
c
c
r
u
a
ls
)
o
n
th
e
o
p
tic
a
l f
lo
w
f
ie
ld
.
T
h
is
n
e
w
c
o
n
s
tr
a
in
t i
m
p
o
s
e
s
a
f
ie
ld
o
f
m
o
r
e
r
e
g
u
la
r
o
p
tic
a
l
f
lo
w
.
T
h
e
c
a
lc
u
la
tio
n
o
f
t
h
e
o
p
tic
a
l f
lo
w
f
ie
ld
in
t
h
is
c
a
s
e
a
m
o
u
n
t
s
to
m
i
n
i
m
iz
e
t
h
e
f
o
llo
w
i
n
g
q
u
a
n
tit
y
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SSN
:
20
88
-
8708
In
t
J
E
l
e
c
&
C
o
m
p
E
n
g
,
V
o
l.
8
, N
o
.
5
,
O
c
t
obe
r
20
18
:
329
6
-
3303
3300
∇
⃗
.
⃗
+
λ
2
∇
⃗
2
2
+
∇
⃗
2
2
(6
)
I
n
eq
u
at
i
o
n
(
6
)
,
t
h
e r
es
ear
ch
er
s
[
21]
f
i
n
d
t
h
e co
n
s
t
r
ai
n
t
t
er
m
an
d
a g
r
ad
i
en
t
acco
r
d
i
n
g
t
o
t
h
e s
p
at
i
a
l
v
a
r
ia
tio
n
o
f
th
e
o
p
tic
a
l f
lo
w
f
ie
ld
2
2
2
2
y
x
v
v
∇
+
∇
,
w
ei
g
h
t
ed
b
y
co
ef
f
i
ci
e
n
t
λ
.
I
nt
ui
t
i
ve
l
y
,
m
i
ni
m
i
z
i
n
g t
h
e
e
q
u
a
tio
n
(
6
)
b
a
c
k
,
f
ir
s
t to
m
i
n
i
m
iz
e
t
h
e
g
r
a
d
ie
n
t o
f
th
e
e
q
u
a
tio
n
,
a
n
d
th
e
s
p
a
tia
l
v
a
r
ia
tio
n
o
f
th
e
o
p
tic
a
l f
lo
w
f
ie
ld
.
T
h
e
c
a
lc
u
la
tio
n
o
f
o
p
tic
a
l f
lo
w
t
h
e
r
e
f
o
r
e
r
e
tu
r
n
s
to
th
e
a
p
p
lic
a
tio
n
o
f
a
n
o
p
ti
m
iz
a
t
io
n
m
e
th
o
d
m
in
im
i
z
in
g
th
i
s
d
o
u
b
le
in
te
g
r
a
l.
2
.3
.
T
ra
ck
i
n
g
P
o
i
n
t
s
o
f
I
n
t
eres
t
T
h
e m
aj
o
r
p
r
o
b
l
em
f
o
r
t
r
ack
i
n
g
a
n
o
b
j
ect
b
et
w
een
t
w
o
i
m
ag
e
s
i
s
t
o
d
et
er
m
i
n
e t
h
e
p
o
i
n
t
s
o
f
r
es
e
m
b
l
an
ce b
et
w
ee
n
t
h
e d
i
f
f
er
en
t
i
m
a
g
es
.
T
h
e i
d
ea i
s
t
o
d
et
er
m
i
n
e t
h
e
f
eat
u
r
e p
o
i
n
t
s
(
co
r
n
er
)
[1
9
]
i
n
each
i
m
a
ge
a
nd
t
he
n
f
i
nd
t
he
r
e
l
a
t
i
o
ns
hi
p
b
e
t
w
e
e
n t
he
p
o
i
nt
s
f
o
u
n
d
i
n e
a
c
h i
m
a
ge
.
T
h
es
e s
t
ep
s
a
r
e u
s
ed
t
o
ex
t
r
act
a
s
et
o
f
p
o
i
n
t
s
o
f
i
n
t
er
es
t
f
r
o
m
a
n
i
m
ag
e o
f
t
h
e
v
i
d
eo
s
eq
u
e
n
ce
u
s
i
n
g
t
h
e
m
et
h
o
d
d
es
cr
i
b
ed
i
n
[
19]
.
A
ll p
o
in
ts
o
f
in
te
r
e
s
t
in
th
e
i
m
a
g
e
a
r
e
t
r
a
c
k
e
d i
n
t
h
e
f
ol
l
o
w
i
n
g i
m
a
g
e
us
i
ng
t
h
e
a
l
g
or
i
t
hm
o
f
H
or
n
a
n
d S
c
hun
c
k
[2
1
]
o
r
o
p
tic
a
l f
lo
w
[
10]
.
T
h
e
r
e
s
u
lt o
f
th
is
o
p
e
r
a
tio
n
a
t th
e
i
n
s
ta
n
t t
is
a
s
e
t o
f
v
e
c
to
r
s
V
i
:
=
{
,
}
W
h
er
e X
i
a
nd
Y
i
a
r
e
t
h
e
c
o
o
r
d
in
a
te
s
o
f
p
o
in
t i
r
e
la
tiv
e
to
th
e
r
e
f
e
r
en
ce
i
m
a
g
e I
t
;
N
o
w
t
he
a
ut
ho
r
s
m
u
s
t
c
a
lc
u
la
te
t
h
e
d
is
ta
n
c
e
b
e
t
w
e
e
n
th
e
p
o
s
itio
n
o
f
t
h
e
p
o
in
t i i
n
t
h
e
i
m
a
g
e
I
t a
n
d
it
s
n
e
w
p
o
s
iti
o
n
in
t
h
e
i
m
a
g
e
I
t
+
1
.
T
h
is
s
te
p
r
e
m
o
v
e
s
th
e
s
ta
ti
c
in
te
r
e
s
t p
o
in
ts
t
h
a
t h
a
v
e
a
m
a
g
n
it
u
d
e
o
f
m
o
v
e
m
e
n
t b
e
lo
w
a
m
in
i
m
u
m
m
a
g
ni
t
ud
e
.
2
.4
.
E
x
t
r
ac
t
i
on
of
t
h
e
B
ac
k
gr
ou
n
d
T
o d
e
t
e
c
t
m
o
vi
n
g t
a
r
ge
t
s
us
i
ng p
a
no
r
a
m
i
c
i
m
a
ge
s
,
t
he
b
a
c
kgr
o
u
nd
s
c
e
ne
i
s
f
i
r
s
t
e
xt
r
a
c
t
e
d
f
r
o
m
s
u
cce
s
s
i
v
e i
m
a
g
es
.
T
h
e
m
et
h
o
d
i
s
i
n
t
e
n
d
ed
t
o
i
m
p
r
o
v
e
t
h
e
q
u
al
i
t
y
o
f
t
h
e
t
r
eat
m
e
n
t
co
m
p
ar
ed
w
i
t
h
t
h
e b
as
i
c
m
e
t
h
od,
bu
t
a
l
s
o t
o
l
i
m
i
t
t
he
i
m
p
a
c
t
o
f
c
ha
n
ge
s
i
n
t
he
b
r
i
ght
ne
s
s
o
f
a
r
e
s
ul
t
o
f
e
xt
r
a
c
t
i
o
n
o
f
b
a
c
k
gr
o
und
.
T
hus
,
t
he
q
ua
l
i
t
y
o
f
t
he
r
e
s
ul
t
i
s
s
ub
s
t
a
n
t
i
a
l
l
y e
n
ha
nc
e
d
.
T
he
r
e
s
ul
t
o
f
t
he
m
e
t
ho
d
i
s
s
ho
w
n
i
n t
he
F
i
g
ur
e
5
.
′
(
,
)
=
(
,
)
=
1
(
7)
(
a)
(b
)
F
i
g
ur
e
5
.
E
xt
r
a
c
t
i
n
g b
a
c
k
gr
o
u
nd
;
(
a
)
O
r
i
gi
na
l
i
m
a
ge
;
(
b
)
B
a
c
kgr
o
u
nd
2
.5
.
S
e
gm
e
n
t
at
i
on
S
e
gm
e
nt
a
t
i
on
i
s
o
n
e
of
t
h
e
m
o
s
t
s
t
u
di
e
d pr
obl
e
m
s
i
n
i
m
a
g
e
pr
oc
e
s
s
i
n
g
[2
2
],
[
23]
.
I
ts
g
o
a
l
is
th
e
s
e
p
a
r
a
tio
n
o
f
th
e
i
m
a
g
e
i
n
to
r
e
g
io
n
s
w
h
o
s
e
p
i
x
e
ls
h
a
v
e
s
i
m
ila
r
c
h
a
r
a
c
te
r
is
t
ic
s
.
T
h
is
p
a
r
tit
io
n
in
g
p
r
o
b
le
m
c
a
n
b
e
f
o
r
m
ul
a
t
e
d
a
s
f
o
l
l
o
w
s
:
gi
ve
n
a
c
l
o
ud
o
f
N
p
o
i
nt
s
i
n
t
he
i
m
a
ge
,
t
he
a
ut
ho
r
s
t
r
y t
o
f
i
nd
t
he
k c
l
o
ud
s
c
or
r
e
s
pon
di
n
g
t
o
t
h
e
k
cl
as
s
e
s
o
f
p
i
x
el
s
.
O
b
j
ect
s
a
f
t
er
t
h
i
s
s
t
ep
w
i
l
l
cl
a
s
s
i
f
y
m
o
v
i
n
g
o
b
j
ect
an
d
s
t
at
i
o
n
ar
y
o
b
j
ect
u
s
i
n
g
o
p
t
i
cal
f
l
o
w
cal
c
u
l
at
ed
at
eac
h
p
o
i
n
t
o
f
i
n
t
er
es
t
.
T
he
m
e
t
ho
d
us
e
d
i
n t
hi
s
p
a
p
e
r
c
o
ns
t
r
uc
t
s
t
he
r
eg
i
o
n
s
,
r
at
h
er
t
h
a
n
ch
ar
act
e
r
i
zi
n
g
t
h
e b
o
u
n
d
ar
i
es
b
et
w
een
r
e
gi
o
n
s
.
W
i
t
h t
hi
s
m
e
t
ho
d
,
t
he
a
ut
ho
r
s
w
i
l
l
co
n
s
t
r
u
ct
a
n
i
n
i
t
i
al
s
t
at
e i
n
w
h
i
ch
each
p
i
x
el
o
f
t
h
e i
m
ag
e i
s
a u
n
i
t
r
eg
i
o
n
,
an
d
t
h
e
n
t
o
g
r
ad
u
al
l
y
m
er
g
e r
el
at
ed
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
le
c
&
C
o
m
p E
ng
I
S
S
N
:
2088
-
8708
N
e
w
A
ppr
oac
h f
or
D
e
t
e
c
t
i
ng a
nd T
r
ac
k
i
ng a
M
ov
i
ng O
bj
e
c
t
(
H.
Ha
t
i
mi
)
3301
r
eg
i
o
n
s
t
h
at
s
a
t
i
s
f
y
a
cer
t
ai
n
cr
i
t
er
i
o
n
o
f
h
o
m
o
g
e
n
ei
t
y
.
A
s
an
ex
a
m
p
l
e
o
f
s
i
m
p
l
e
t
es
t
,
w
e
ca
n
co
n
s
id
e
r
th
e
d
i
f
f
er
e
n
ce b
et
w
ee
n
t
h
e
m
ea
n
v
al
u
e
s
o
f
p
i
x
el
s
i
n
t
h
e t
w
o
r
eg
i
o
n
s
.
I
f
t
h
i
s
d
i
f
f
er
e
n
ce i
s
l
es
s
t
h
a
n
a cer
t
ai
n
t
hr
e
s
ho
l
d
,
t
he
a
u
t
ho
r
s
m
e
r
ge
t
he
t
w
o
r
e
gi
o
ns
i
nt
o
o
ne
.
T
he
r
e
s
ul
t
i
s
a
n
i
m
a
ge
i
n
w
h
i
c
h a
l
l
p
i
xe
l
s
o
f
a
r
e
gi
o
n
ar
e i
d
en
t
i
f
i
ed
b
y
t
h
e
s
a
m
e
v
al
u
e.
I
t
i
s
m
o
r
e n
a
t
u
r
al
t
o
t
a
k
e
f
o
r
each
r
eg
i
o
n
t
h
e a
v
er
ag
e
v
al
u
e o
f
i
t
s
p
i
x
el
s
i
n
t
he
o
r
i
gi
na
l
i
m
a
ge
.
W
e
c
a
n a
l
s
o
p
r
o
d
uc
e
a
c
c
o
r
d
i
ng t
o
t
he
c
o
l
o
r
i
ng
nu
m
b
e
r
o
f
t
he
r
e
gi
o
n.
M
o
r
e d
et
a
ils
c
a
n
b
e
f
o
u
n
d
in
t
h
e
a
r
tic
le
[
24]
.
T
he
r
e
s
ul
t
o
f
t
hi
s
s
t
e
p
i
s
s
ho
w
n
i
n t
he
F
i
gur
e
6
.
F
ig
u
r
e
6
.
D
e
te
c
tio
n
o
f
t
h
e
ta
r
g
e
t
m
o
b
ile
2
.6
.
M
o
t
i
o
n
D
et
ect
i
o
n
I
n
o
u
r
w
o
r
k
,
t
h
e a
u
t
h
o
r
s
w
i
l
l
u
s
e a
r
ef
er
en
ce
i
m
ag
e.
T
h
e i
d
ea i
s
t
o
u
s
e a
n
i
m
a
g
e o
f
t
h
e s
c
en
e d
ev
o
i
d
o
f
o
b
j
ect
s
an
d
u
s
e t
h
e
m
as
r
e
f
er
en
ce i
m
a
g
e
[
25]
.
S
t
ep
m
o
t
i
o
n
d
et
ect
i
o
n
i
s
i
m
p
o
r
t
an
t
b
eca
u
s
e al
l
p
r
o
ces
s
es
t
h
at
f
o
l
l
o
w
,
i
nc
l
ud
i
n
g
m
o
ni
t
o
r
i
ng
a
r
e
d
i
r
e
c
t
l
y
d
e
p
e
nd
e
nt
o
n
t
he
s
e
r
e
s
ul
t
s
.
I
n
t
hi
s
s
t
ud
y
,
t
he
a
ut
ho
r
s
c
ho
s
e
a
m
o
d
e
l
b
as
ed
p
i
x
el
,
w
h
i
c
h
r
ep
r
es
en
t
s
a g
o
o
d
co
m
p
r
o
m
i
s
e b
et
w
ee
n
c
o
m
p
u
t
at
i
o
n
t
i
m
e /
q
u
al
i
t
y
i
n
F
i
gur
e
7.
(
a)
(b
)
(
c)
F
i
g
u
r
e 7
.
D
i
f
f
er
en
ce i
m
ag
e b
e
t
w
ee
n
t
h
e i
n
i
t
i
al
i
m
ag
e a
n
d
t
h
e b
ack
g
r
o
u
n
d
;
(
a)
I
n
i
t
i
al
i
m
a
g
e;
(
b
)
B
ack
g
r
o
u
n
d
;
(
c)
I
m
a
g
e d
i
f
f
er
en
ce
2
.7
.
O
b
j
ect
T
ra
ck
i
n
g
T
h
e t
r
ack
i
n
g
m
et
h
o
d
w
i
l
l
b
e
u
s
ed
i
n
t
h
i
s
w
o
r
k
i
s
b
as
ed
o
n
t
h
e d
et
ect
i
o
n
o
f
r
el
at
i
o
n
s
h
i
p
s
b
et
w
ee
n
o
b
j
ect
s
i
n
t
h
e c
u
r
r
en
t
i
m
a
g
e
an
d
t
h
e o
b
j
ect
s
o
f
t
h
e p
r
ev
i
o
u
s
i
m
ag
e,
t
h
at
i
s
t
o
s
a
y
,
o
n
ce t
h
e o
b
j
ect
s
ar
e
d
et
ect
ed
,
t
h
e
f
l
o
w
o
p
t
i
cs
i
s
ca
l
cu
l
at
ed
f
o
r
each
f
eat
u
r
e
poi
nt
be
l
on
g
i
ng
t
o t
h
e
obj
e
c
t
a
n
d t
h
e
c
e
n
t
e
r
.
S
e
c
on
d,
t
h
er
e
m
u
s
t
b
e co
r
r
es
p
o
n
d
en
ce
b
et
w
ee
n
t
h
e o
b
j
ect
s
i
n
t
h
e p
r
ev
i
o
u
s
i
m
a
g
e a
n
d
t
h
e cu
r
r
e
n
t
i
m
ag
e
i
n
F
i
g
ur
e
8.
(
a)
(b
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SSN
:
20
88
-
8708
In
t
J
E
l
e
c
&
C
o
m
p
E
n
g
,
V
o
l.
8
, N
o
.
5
,
O
c
t
obe
r
20
18
:
329
6
-
3303
3302
F
i
g
u
r
e 8
.
M
o
n
i
t
o
r
i
n
g
t
h
e i
m
a
g
e;
(
a)
I
m
a
g
e at
t
i
m
e t
;
(
b
)
I
m
a
g
e at
ti
m
e
t+
1
2
.8
.
T
ra
j
ect
o
ry
O
u
r
d
e
te
c
tio
n
s
y
s
te
m
a
n
d
m
o
n
ito
r
in
g
n
o
t o
n
l
y
a
llo
w
s
to
f
o
l
lo
w
t
h
e
m
o
v
i
n
g
o
b
j
e
c
t,
b
u
t a
ls
o
to
tr
a
c
e
t
h
e p
at
h
t
r
a
v
el
ed
b
y
t
h
e o
b
j
ect
i
n
F
i
gur
e
9
.
F
i
g
u
r
e 9
.
D
r
a
w
i
n
g
t
h
e t
r
aj
ect
o
r
y
3.
RE
S
U
L
T
S
AND
D
I
SC
U
SS
I
O
N
T
o s
ho
w
t
he
p
o
w
e
r
of
ou
r
m
e
t
h
od,
w
e
di
d t
e
s
t
s
w
i
t
h
t
h
e
m
e
t
h
ods
us
i
n
g
m
u
ltip
le
f
eat
u
r
es
a
d
a
p
tiv
e
f
us
i
on
[
3]
,
a
n
d
m
e
t
h
od u
s
i
ng
i
m
pr
o
v
e
d de
t
e
c
t
or
of
obj
e
c
t
s
s
i
m
i
l
a
r
t
o
t
a
r
ge
t
[
4
]
.
O
ur
s
ys
t
e
m
ha
s
be
e
n
t
e
s
t
e
d on
v
ar
i
o
u
s
s
eq
u
en
ce
s
.
E
s
p
eci
al
l
y
,
o
n
v
i
d
eo
s
acq
u
i
r
ed
i
n
o
u
r
l
ab
o
r
at
o
r
y
.
T
h
e
a
u
t
h
or
s
c
ondu
c
t
e
d t
w
o s
e
t
s
of
e
xp
e
r
i
m
e
nt
s
i
nd
o
o
r
s
t
o
a
s
s
e
s
s
t
he
r
o
b
us
t
ne
s
s
o
f
t
he
a
l
go
r
i
t
h
m
t
o
o
c
c
l
us
i
o
ns
a
nd
t
o
c
ha
nge
s
i
n t
he
s
c
e
ne
.
M
o
r
eo
v
er
,
t
h
e s
ce
n
es
i
n
w
h
i
ch
t
h
e ap
p
l
i
cat
i
o
n
w
i
l
l
b
e i
m
p
l
e
m
e
n
t
ed
m
ai
n
l
y
i
n
d
o
o
r
s
cen
es
a
w
a
y
f
r
o
m
p
r
o
b
l
e
m
s
s
u
c
h
a
s
l
ar
g
e l
i
g
h
t
i
n
g
v
ar
i
at
i
o
n
s
.
O
u
r
i
n
t
er
es
t
t
h
er
ef
o
r
e r
el
at
es
s
p
eci
f
i
cal
l
y
o
n
p
r
o
ces
s
es
ad
ap
t
ed
t
o
t
he
s
e
c
o
nd
i
t
i
o
ns
.
T
h
e
pr
o
pos
e
d m
e
t
h
od i
n
t
hi
s
w
or
k
h
e
l
pe
d de
t
e
c
t
de
f
or
m
a
bl
e
m
ov
i
ng
obj
e
c
t
s
f
r
o
m
a
v
i
de
o.
T
o
f
ul
l
y
te
s
t th
e
f
u
n
c
tio
n
a
lit
y
o
f
o
u
r
p
r
o
g
r
a
m
,
we
h
a
v
e m
ad
e
s
e
v
e
r
a
l
te
s
te
d
w
i
th
v
id
e
o
s
f
r
o
m
1
0
to
3
0
m
i
n
u
te
s
.
I
n
a
ll
cas
es
,
o
u
r
al
g
o
r
i
t
h
m
w
a
s
ab
l
e
t
o
l
o
cat
e t
h
e
m
o
v
i
n
g
o
b
j
ect
p
er
f
ect
l
y
.
T
h
e d
et
ect
i
o
n
p
h
as
e g
i
v
es
g
o
o
d
v
i
s
u
al
r
e
s
u
l
t
s
i
n
F
i
g
ur
e
1
0
,
w
h
i
c
h
he
l
p
s
a
l
o
t
d
ur
i
ng t
he
m
o
ni
t
o
r
i
n
g
p
ha
s
e
.
(
a)
(b
)
(
c)
F
ig
u
r
e
1
0
.
P
r
o
c
e
s
s
f
o
r
d
e
te
c
tin
g
th
e
m
o
b
ile
ta
r
g
e
t; (
a
)
E
x
tr
a
c
tin
g
p
o
in
ts
o
f
i
n
te
r
e
s
t; (
b
)
E
lim
i
n
a
tio
n
o
f
p
o
in
ts
o
f
i
n
t
er
es
t
;
(
c)
S
eg
m
en
t
at
i
o
n
a
n
d
t
r
ack
i
n
g
o
f
t
h
e
m
o
v
i
n
g
o
b
j
ect
.
T
h
e
f
in
a
l
i
m
p
le
m
e
n
ta
tio
n
o
f
th
e
p
r
o
j
e
c
t
is
to
o
p
e
r
a
te
in
m
in
i
m
u
m
t
i
me
a
s
s
ho
w
n
i
n
T
ab
l
e
1
,
t
he
a
ut
ho
r
s
l
o
o
ke
d
a
t
u
s
i
ng
s
i
m
p
l
e
a
nd
i
ne
xp
e
ns
i
ve
m
e
t
ho
d
s
o
f
c
o
m
p
ut
a
t
i
o
n
t
i
m
e
.
T
he
p
r
o
gr
a
m
ha
s
b
e
e
n
t
e
s
t
e
d
o
n
a co
m
p
u
t
er
w
i
t
h
a C
o
r
e I
5
p
r
o
ces
s
o
r
w
i
t
h
4
G
B
o
f
r
a
m
.
A
s
w
e ca
n
s
ee i
n
t
ab
l
e ex
ec
u
t
i
o
n
t
i
m
e i
s
t
o
o
s
m
a
l
l
.
4.
CO
NCL
U
S
I
O
N
T
h
e
w
o
r
k
s
p
r
e
s
e
n
te
d
i
n
t
h
is
a
r
tic
le
h
a
n
d
le
th
e
p
r
o
b
le
m
o
f
d
e
te
c
tio
n
a
n
d
lo
c
a
tio
n
o
f
a
m
o
b
ile
ta
r
g
e
t.
T
h
e
m
ai
n
i
d
ea o
f
t
h
i
s
ar
t
i
cl
e
i
s
t
o
r
eal
i
ze o
f
a
n
ap
p
r
o
ach
f
o
r
d
et
ect
i
n
g
a
u
t
o
m
at
i
cal
l
y
a
m
o
v
i
n
g
o
b
j
ect
f
r
o
m
a
s
et
o
f
i
m
a
g
e
s
,
f
r
o
m
a
f
i
x
ed
c
a
m
er
a
.
I
t c
o
n
ta
i
n
s
a
s
e
t o
f
s
t
e
p
to
ta
k
e
i
n
o
r
d
e
r
to
d
e
te
c
t a
n
d
tr
a
c
k
m
u
ltip
le
m
o
v
i
n
g
o
b
j
ect
s
.
T
h
i
s
ap
p
r
o
ac
h
can
al
s
o
i
d
en
t
i
f
y
t
h
e p
at
h
t
r
av
el
ed
b
y
each
o
b
j
ect
,
t
o
an
al
y
ze an
d
u
n
d
er
s
t
a
n
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
le
c
&
C
o
m
p E
ng
I
S
S
N
:
2088
-
8708
N
e
w
A
ppr
oac
h f
or
D
e
t
e
c
t
i
ng a
nd T
r
ac
k
i
ng a
M
ov
i
ng O
bj
e
c
t
(
H.
Ha
t
i
mi
)
3303
t
he
b
e
ha
vi
o
r
o
f
t
he
o
b
j
e
c
t
.
T
o i
m
p
r
o
ve
t
he
q
ua
l
i
t
y
o
f
o
ur
r
e
s
ul
t
s
,
a
s
e
t
o
f
t
e
s
t
s
w
er
e o
r
g
an
i
zed
t
o
v
al
i
d
at
e t
h
e
ap
p
l
i
cat
i
o
n
.
T
h
e p
er
f
o
r
m
a
n
ce
s
i
n
t
i
m
e
s
o
f
cal
c
u
l
at
i
o
n
w
er
e
as
s
es
s
ed
an
d
g
i
v
e
n
r
i
s
e t
o
s
o
m
e o
p
t
i
m
i
zat
i
o
n
s
a
s
s
ho
w
n i
n
T
ab
l
e 1
.
T
a
bl
e
1.
R
u
n
T
i
m
e
of
E
v
e
r
y
O
pe
r
a
t
i
on
A
c
c
or
di
ng
t
o t
h
e
R
e
s
ol
u
t
i
on
O
p
e
r
a
t
io
n
6
4
0
*
48
0
7
0
4
*
57
6
D
e
t
e
c
tio
n
o
f
p
o
in
ts
o
f
in
te
r
e
s
t
0
.
0
0
2
s
0
.
0
3
C
a
lc
u
la
t
i
o
n
o
f
o
p
t
i
c
a
l f
lo
w
0
.
0
1
s
0
.
0
2
s
S
e
g
m
e
n
t
a
tio
n
0
.
0
0
5
s
0
.
0
0
7
s
O
b
j
e
ct
T
r
ack
i
n
g
0
.
0
0
1
s
0
.
0
0
2
s
R
EF
ER
EN
C
ES
[
1]
X
.Z
h
o
u
, W
.H
u
, Y
.C
h
e
n
, a
n
d
W
.H
u
.
M
a
r
k
ov
r
a
ndom
f
i
e
l
d
m
ode
l
e
d l
e
v
e
l
s
e
t
s
m
e
t
hod f
or
obj
e
c
t
t
r
a
c
k
i
ng
w
i
t
h
m
o
v
i
n
g
c
a
m
e
r
a
s
.
A
s
i
a
n C
onf
.
C
o
m
put
e
v
i
s
i
on
.
20
07
;
p
p.
83
2
–
84
2.
[
2]
D
a
ode
Z
ha
ng
,
C
he
ng
X
u,
Y
ua
n
z
hong
L
i
.
R
o
b
u
s
t
T
r
ack
i
n
g
b
as
e
d
o
n
F
ai
l
u
r
e R
eco
v
er
y
.
T
el
k
o
m
n
i
k
a I
n
d
o
n
es
i
an
J
our
na
l
of
E
l
ect
r
i
cal
E
n
g
i
n
eer
i
n
g
.
20
14;
V
ol
.
12
,
N
o.
2
:
1
00
5
-
10
11
.
[
3]
J
i
e C
ao
,
L
e
ile
i G
u
o
,
J
i
nh
ua
W
a
ng
,
D
i
W
u
.
O
bj
e
c
t
T
r
a
c
k
i
ng
B
a
s
e
d on M
ul
t
i
pl
e
F
e
a
t
ur
e
s
A
da
pt
i
v
e
F
u
s
i
on
.
T
e
l
k
om
ni
k
a
I
ndone
s
i
a
n J
our
na
l
of
E
l
e
c
t
r
i
c
a
l
E
ng
i
ne
e
r
i
ng
.
201
4;
12(
9)
,
68
11
-
68
18
[
4]
S
h
in
ji F
u
k
u
i,
R
y
uj
i
N
i
s
hi
y
a
m
a
,
Y
uj
i
I
w
a
hor
i
,
M
.
K
.
B
h
uy
a
n,
R
ob
e
r
t
J
.
W
oodha
m
.
O
bj
e
c
t
T
r
a
c
k
i
ng
w
i
t
h I
m
pr
ov
e
d
D
et
ect
o
r
o
f
O
b
j
ect
s
S
i
m
i
l
ar
t
o
T
a
r
g
et
.
P
r
o
ced
i
a C
o
m
p
u
t
er
S
ci
en
ce.
2
0
1
5
;
V
o
l
6
0
,
P
ag
es
7
4
0
-
74
9
[
5]
S
hoi
c
hi
A
r
a
k
i
,
T
a
k
a
s
hi
M
a
t
s
uoa
k
a
,
N
a
ok
azu
Y
o
k
o
y
a an
d
H
ar
u
a
T
ak
e
m
u
r
a.
R
e
a
lti
m
e
tr
a
c
k
in
g
o
f
m
u
ltip
le
m
o
v
in
g
o
b
j
ect
co
n
t
o
u
r
s
i
n
a m
o
v
i
n
g
ca
m
e
r
a i
m
a
g
e s
eq
u
en
ce.
IE
ICE
T
ra
n
s
.
In
f
.
&
S
y
s
t
.
2000
;
V
o
l
. E
8
3
-
D
, N
o
. 7
.
[
6]
J
.
F
.
B
o
u
l
an
g
er
,
F
.
G
al
l
an
d
,
P
.
M
a
r
t
i
n
,
et
P
.
R
éf
r
ég
i
er
.
S
t
o
ch
as
t
i
c co
m
p
l
ex
i
t
y
i
n
t
eg
r
al
i
m
a
g
e b
as
ed
t
ech
n
i
q
u
e f
o
r
f
as
t
vi
d
e
o
t
r
a
c
ki
n
g.
O
p
tic
s
L
e
tte
r
s
.
20
08
;
V
ol
.
33
(
2
1)
,
pp.
2
52
1
-
25
23
.
[
7]
D
.
J
.
Bu
rr.
Ela
s
tic
M
a
tc
h
i
n
g
o
f
lin
e
d
r
a
w
in
g
s
.
I
E
E
E
t
r
an
s
act
i
o
n
o
n
P
at
t
er
n
an
al
y
s
i
s
an
d
m
ach
i
n
e i
n
t
el
l
i
g
en
ce
.
1
981
;
v
ol
.
3,
n°
6
:
p
p.
70
8
-
7
13
.
[
8]
M
a
ha
m
uni
P
. D
, R
.
P
.
P
a
t
i
l
, H
.S
. T
h
a
k
a
r
.
M
ov
i
ng
obj
e
c
t
de
t
e
c
t
i
o
n us
i
ng
ba
c
k
g
r
oun
d
s
u
b
tr
a
c
tio
n
a
lg
o
r
ith
m
u
s
in
g
s
i
m
ul
i
nk
.
I
nt
e
r
na
t
i
o
na
l
j
our
na
l
of
r
e
s
e
a
r
c
h i
n e
ng
i
ne
e
r
i
ng
a
nd
t
e
c
hn
ol
og
y
.
201
4
;
v
ol
03
.
[
9]
J.
R
i
ssa
n
e
n
.
S
t
o
c
h
a
s
tic
C
o
m
p
le
x
ity
in
S
ta
tis
tic
a
l I
n
q
u
ir
y
.
T
e
an
eck
,
N
J
:
W
o
r
l
d
S
ci
en
t
i
f
i
c,
198
9
.
[
1
0]
B
.
L
u
cas
,
T
.
K
an
ad
e.
A
n
ite
r
a
tiv
e
im
a
g
e
r
e
g
is
tr
a
tio
n
te
c
h
n
iq
u
e
w
ith
a
n
a
p
p
lic
a
tio
n
to
s
te
r
e
o
v
is
io
n
.
P
r
oc
e
e
di
ng
s
of
I
m
a
g
i
ng
U
nde
r
s
t
a
ndi
ng
W
or
k
s
ho
p
.
19
81
;
p
p.
12
1
–
13
0.
[
1
1]
J
. S
h
i
a
n
d
C
. T
o
m
a
s
i
.
G
o
o
d
f
eat
u
r
es
t
o
t
r
ack
.
C
o
m
put
e
r
V
i
s
i
on a
nd
P
a
t
t
e
r
n R
e
c
og
ni
t
i
o
n,
P
r
o
ceed
i
n
g
s
C
V
P
R
’
9
4
,
W
a
s
h
in
g
to
n
: S
e
a
ttle
.
19
94
;
pp
.
59
3
–
60
0.
[
1
2]
M
.
O
.
Be
rg
e
r.
H
ow
t
o t
r
a
c
k
e
f
f
i
c
i
e
nt
l
y
pi
e
c
e
w
i
s
e
c
ur
ve
d c
ont
o
u
r
s
w
i
t
h a
v
i
e
w
t
o r
e
c
ons
t
r
uc
t
i
ng
3D
obj
e
c
t
s
.
In
ICP
R’
9
4
.
19
94
;
pp.
3
2
–
36
.
[
1
3]
F
ar
i
d
ah
,
B
al
za A
ch
m
ad
,
B
i
n
ar
L
i
s
t
y
an
a S
.
L
i
p
I
m
a
g
e F
eat
u
r
e
Ex
tr
a
c
tio
n
U
tiliz
in
g
S
n
a
k
e
’
s
C
o
n
tr
o
l
P
o
in
ts
f
or
L
i
p
R
e
a
di
ng
A
ppl
i
c
a
t
i
ons
.
I
nt
e
r
na
t
i
ona
l
J
our
na
l
of
E
l
e
c
t
r
i
c
a
l
a
nd C
om
put
e
r
E
ng
i
ne
e
r
i
ng
(
I
J
E
C
E
)
;
2015
.
V
ol
.
5,
N
o.
4:
p
p.
72
0
-
72
8
.
[
1
4]
S
.
B
ouk
i
r
,
P
.
B
o
ut
he
m
y
,
F
.
C
ha
um
e
t
t
e
,
a
nd D
.
J
uv
i
n.
A
l
oc
a
l
m
e
t
hod f
or
c
ont
our
m
at
ch
i
n
g
an
d
i
t
s
p
ar
al
l
el
im
p
le
m
e
n
ta
tio
n
.
M
a
c
hi
ne
V
i
s
i
o
n
a
nd A
ppl
i
c
a
t
i
o
ns
.
19
98
;
pp
.
3
21
–
330
.
[
1
5]
M
.
V
i
n
cze
.
R
o
b
u
s
t
t
r
ack
i
n
g
o
f
el
l
i
p
s
es
at
f
r
a
m
e r
at
e.
P
a
tte
r
n
R
e
c
o
g
n
itio
n
.
20
01
;
pp
.
48
7
–
49
8
.
[
1
6]
G
.
H
ag
er
an
d
P
.
B
el
h
u
m
eu
r
.
E
f
f
i
ci
en
t
r
eg
i
o
n
t
r
ack
i
n
g
w
i
t
h
p
ar
a
m
et
r
ic
m
o
d
e
ls
o
f
g
e
o
m
e
tr
y
a
n
d
illu
m
in
a
tio
n
.
I
E
E
E
T
r
a
ns
,
on
P
a
t
t
e
r
n A
na
l
y
s
i
s
a
nd M
a
c
hi
ne
I
n
t
el
l
i
g
en
ce.
19
98
;
p
p.
10
25
–
10
39
.
[
1
7]
D
.
Le
e
.
E
f
f
e
c
t
i
ve
G
a
us
s
i
a
n
m
i
x
t
ur
e
l
e
a
r
ni
ng
f
or
v
i
de
o ba
c
k
g
r
ound
s
ubt
r
a
c
t
i
o
n.
I
E
E
E
T
r
an
s
.
P
at
t
er
n
A
n
al
.
200
5
;
p
p
.
827
–
83
2.
[
1
8]
Y
. S
h
e
i
k
h
, M
.
S
ha
h.
B
ay
es
i
an
m
o
d
el
i
n
g
o
f
d
y
n
a
m
i
c s
cen
es
f
o
r
o
b
j
ect
d
et
ect
i
o
n
.
I
E
E
E
T
r
a
n
s
. P
a
t
t
e
r
n
A
n
a
l
.
2005
;
pp.
17
78
–
17
92
.
[
1
9]
C
.
H
ar
r
i
s
,
M
.
S
t
ep
h
en
s
.
A
C
om
bi
ne
d C
or
ne
r
a
n
d E
dg
e
D
e
t
e
c
t
or
.
P
r
oc
e
e
di
ng
s
of
4t
h A
l
v
e
y
V
i
s
i
o
n C
o
nf
e
r
e
nc
e
,
198
8
.
[
2
0]
J
. L
. B
a
r
r
o
n
, D
. J
.
F
l
eet
,
an
d
S
.
S
.
B
eau
ch
em
i
n
.
P
e
r
f
or
m
a
nc
e
of
opt
i
c
a
l
f
l
ow
t
e
c
hni
que
s
.
I
nt
e
r
na
t
i
ona
l
J
o
ur
na
l
of
C
om
put
e
r
V
i
s
i
on
.
19
94
p
p.
43
–
77.
[
2
1]
B
.
K
.
P
.
H
or
n e
t
B
.
G
.
S
c
hunk
.
D
e
t
e
r
m
in
in
g
O
p
tic
a
l F
l
o
w
.
A
r
ti
f
ic
ia
l I
n
te
llig
e
n
c
e
, p
p
.
18
5
–
20
3
,
19
81
.
[
2
2]
T
ah
i
r
S
ag
,
M
eh
m
et
Ç
u
n
k
aş
.
C
o
l
o
r
i
m
a
g
e
s
eg
m
en
t
a
tio
n
b
a
s
e
d
o
n
m
u
ltio
b
je
c
tiv
e
a
r
ti
f
ic
ia
l b
e
e
c
o
lo
n
y
o
p
tim
i
z
a
tio
n
.
A
ppl
i
e
d S
of
t
C
om
put
i
ng
.
20
15
;
V
o
l
34
:
pp
38
9
–
40
1
.
[
2
3]
W
e
n S
hi
,
R
ui
-
bi
a
o Z
ou
,
,
F
a
ng
W
a
ng
,
L
e
S
u.
A
ne
w
i
m
a
g
e
s
e
gm
e
nt
a
t
i
on m
e
t
hod
ba
s
e
d on m
ul
t
i
f
r
a
c
t
a
l
de
t
r
e
nde
d
m
o
vi
n
g a
ve
r
a
ge
a
n
a
l
y
s
i
s
.
P
h
ys
i
c
a
A
: S
ta
tis
tic
a
l
M
e
c
ha
ni
c
s
a
nd i
t
s
A
ppl
i
c
a
t
i
ons
.
20
15
;
V
ol
43
2
:
pp.
197
–
20
5
.
[
2
4]
Y
.
L
.
T
i
a
n a
nd A
.
H
a
m
pa
pur
.
R
obus
t
s
a
l
i
e
nt
m
ot
i
o
n
de
t
e
c
t
i
on
w
i
t
h c
om
pl
e
x
ba
c
kg
r
ound
f
or
r
e
a
l
-
t
i
m
e v
i
d
eo
s
u
r
v
ei
l
l
an
ce.
I
E
E
E
W
or
k
s
hop
o
n
M
ot
i
on a
nd
V
i
de
o C
om
put
i
ng
.
20
05
;
pp
.
30
-
35
.
[
2
5]
T.
Y
a
n
g
, S
.Z
. L
i
, Q
.
P
a
n
,
J
. L
i
. R
e
a
l
-
t
i
m
ean
d
accu
r
at
e s
eg
m
en
t
at
i
o
n
o
f
m
o
v
i
n
g
o
b
j
ect
s
i
n
d
y
n
am
i
c s
cen
e.
A
C
M
I
n
t
.
W
or
k
s
hop o
n v
i
de
o
S
ur
v
e
i
l
l
a
nc
e
&
S
e
ns
or
N
e
t
w
or
k
s
.
200
4;
pp.
1
3
6
-
1
43.
Evaluation Warning : The document was created with Spire.PDF for Python.