T
E
L
KO
MNIK
A
, V
ol
.
1
7
,
No.
6
,
Dec
e
mb
er
201
9
, p
p.
3
00
3
~
3009
IS
S
N: 1
69
3
-
6
93
0
,
accr
ed
ited
F
irst
Gr
ad
e b
y K
em
en
r
istekdikti,
Decr
ee
No: 2
1/E/
K
P
T
/20
18
DOI:
10.12928/TE
LK
OM
N
IK
A
.v
1
7
i
6
.
12710
â—¼
30
03
Rec
ei
v
ed
Ma
r
c
h
19
,
20
1
9
;
Rev
i
s
ed
J
u
l
y
2
,
20
1
9
;
A
c
c
ep
ted
J
u
l
y
19
, 2
0
1
9
T
ransfo
rm
atio
n
and
dyn
a
mic vi
sualiza
ti
on
of
i
mag
es
from
co
mp
u
ter t
hrou
gh
a
n F
P
G
A in a
mat
rix
of
LED
E
d
w
ar
Ja
cint
o
G
ó
mez
*
1
,
F
er
n
and
o
M
ar
t
Ãnez
S
ant
a
2
, Holm
an Mon
t
i
el
Ar
iz
a
3
Uni
v
e
r
s
i
d
a
d
Di
s
tri
t
a
l
F
r
a
n
c
i
s
c
o
J
o
s
é
d
e
Ca
l
d
a
s
,
Fa
c
u
l
ta
d
Te
c
n
o
l
ó
g
i
c
a
,
Cll
6
8
D B
i
s
A
S
u
r No
.
4
9
F
–
7
0
,
Bo
g
o
t
á
D.C.,
Co
l
o
m
b
i
a
,
So
u
t
h
Am
e
r
i
c
a
*C
o
rre
s
p
o
n
d
i
n
g
a
u
th
o
r,
e
-
m
a
i
l
:
e
j
a
c
i
n
t
o
g
@ud
i
s
tr
i
ta
l
.e
d
u
.c
o
1
,
fm
a
rti
n
e
z
s
@ud
i
s
tr
i
ta
l
.e
d
u
.c
o
2
,
h
m
o
n
ti
e
l
a
@ud
i
s
tr
i
ta
l
.e
d
u
.c
o
3
Ab
strac
t
Th
i
s
a
rt
i
c
l
e
s
h
o
w
s
t
h
e
i
m
p
l
e
m
e
n
ta
t
i
o
n
o
f
a
s
y
s
te
m
t
h
a
t
u
s
e
s
a
g
ra
p
h
i
c
i
n
te
rf
a
c
e
t
o
l
o
a
d
a
d
i
g
i
ta
l
i
m
a
g
e
i
n
to
a
p
ro
g
ra
m
m
a
b
l
e
l
o
g
i
c
d
e
v
i
c
e
,
whi
c
h
i
s
s
t
o
re
d
i
n
i
t
s
i
n
te
rn
a
l
RAM
m
e
m
o
ry
a
n
d
i
s
re
s
p
o
n
s
i
b
l
e
fo
r
v
i
s
u
a
l
i
z
i
n
g
i
t
i
n
a
m
a
tri
x
o
f
RG
B
L
EDs
,
s
o
th
a
t
T
h
i
s
way
,
t
h
e
L
EDs
s
h
o
w
a
n
e
q
u
i
v
a
l
e
n
t
to
th
e
i
m
a
g
e
t
h
a
t
was
s
e
n
t
fr
o
m
th
e
PC,
c
o
n
s
e
rv
i
n
g
a
n
a
s
p
e
c
t
ra
t
i
o
a
n
d
r
e
s
p
e
c
ti
n
g
a
s
m
u
c
h
a
s
p
o
s
s
i
b
l
e
th
e
c
o
l
o
r
o
f
th
e
o
r
i
g
i
n
a
l
i
m
a
g
e
.
To
c
a
rr
y
o
u
t
th
i
s
ta
s
k
,
a
M
a
tl
a
b
s
c
ri
p
t
w
a
s
d
e
s
i
g
n
e
d
to
l
o
a
d
t
h
e
i
m
a
g
e
,
c
o
n
v
e
rt
a
n
d
fo
rm
a
t
th
e
d
a
t
a
,
wh
i
c
h
a
re
tra
n
s
m
i
tt
e
d
to
th
e
FPGA
u
s
i
n
g
t
h
e
RS23
2
p
ro
to
c
o
l
.
Th
e
FPGA
i
s
i
n
c
h
a
r
g
e
o
f
re
c
e
i
v
i
n
g
th
e
m
,
s
to
r
i
n
g
th
e
m
a
n
d
g
e
n
e
ra
t
i
n
g
a
l
l
t
h
e
s
i
g
n
a
l
s
o
f
c
o
n
tro
l
a
n
d
s
y
n
c
h
ro
n
i
z
a
ti
o
n
o
f
th
e
s
y
s
te
m
i
n
c
l
u
d
i
n
g
t
h
e
c
o
n
tr
o
l
o
f
th
e
P
WM
s
i
g
n
a
l
s
n
e
c
e
s
s
a
r
y
to
c
o
n
s
e
rv
e
th
e
b
ri
g
h
tn
e
s
s
o
f
e
a
c
h
o
n
e
o
f
th
e
L
EDs
.
Th
i
s
s
y
s
t
e
m
a
l
l
o
ws
th
e
v
i
s
u
a
l
i
z
a
ti
o
n
o
f
s
ta
t
i
c
i
m
a
g
e
s
i
n
s
ta
n
d
a
rd
fo
rm
a
ts
a
n
d
,
i
n
a
d
d
i
ti
o
n
,
t
h
a
n
k
s
t
o
th
e
f
l
e
x
i
b
i
l
i
ty
o
f
t
h
e
h
a
rd
ware
u
s
e
d
,
i
t
a
l
l
o
w
s
t
h
e
v
i
s
u
a
l
i
z
a
t
i
o
n
o
f
m
o
v
i
n
g
i
m
a
g
e
s
ty
p
e
GIF.
Key
w
ords
:
d
i
g
i
t
a
l
i
m
a
g
e
p
ro
c
e
s
s
i
n
g
,
d
y
n
a
m
i
c
v
i
s
u
a
l
i
z
a
ti
o
n
,
FPGA
,
L
ED a
rra
y
Copy
righ
t
©
2
0
1
9
Uni
v
e
rsi
t
a
s
Ahm
a
d
D
a
hl
a
n.
All
rig
ht
s
r
e
s
e
rve
d
.
1.
Int
r
o
d
u
ctio
n
T
he
proc
es
s
i
ng
an
d
v
i
s
ua
l
i
z
ati
on
of
di
gi
t
al
i
ma
g
es
us
i
ng
c
om
pl
ex
c
om
p
ute
r
al
go
r
i
thm
s
ma
k
es
i
t
i
mp
erat
i
v
e
to
us
e
F
P
G
A
's
[1
,
2
],
th
e
pe
r
f
orm
an
c
e
of
t
hi
s
ty
pe
of
d
ev
i
c
e
s
i
s
c
r
uc
i
al
for
the
c
orr
ec
t
fun
c
t
i
on
i
n
g
o
f
the
d
i
ffe
r
e
nt
hu
ma
n
m
a
c
hi
ne
i
nte
r
fac
es
[3]
,
wh
ere
i
nfo
r
m
ati
on
proc
es
s
i
ng
i
s
r
e
qu
i
r
e
d
wi
th
hi
gh
s
p
ee
d
of
r
efres
h
me
n
t,
qu
a
l
i
ty
a
nd
us
e
of
c
om
pl
ex
al
g
orit
h
ms
wi
th
l
o
w
d
el
ay
[4]
,
wh
i
c
h
c
au
s
es
t
he
m
to
be
u
s
ed
i
n
h
i
g
h
s
pe
ed
i
m
ag
e
ma
na
ge
m
en
t
ap
p
l
i
c
at
i
on
s
.
In
v
i
s
ua
l
i
z
a
ti
o
n
s
y
s
tem
s
th
at
r
eq
u
i
r
e
c
o
m
pl
ex
c
a
l
c
ul
ati
on
s
[
5],
wi
t
h
c
ha
ng
es
of
v
i
e
w
of
t
he
i
ma
g
e
t
o
be
d
i
s
pl
ay
ed
[
6],
wr
i
t
es
m
us
t
be
ma
de
i
n
th
e
i
nt
erna
l
me
m
ory
of
th
e
de
v
i
c
e
wi
th
ou
t
l
os
i
ng
proc
es
s
i
n
g
s
pe
ed
[7
,
8
]
,
t
og
et
he
r
wi
th
the
p
os
s
i
bi
l
i
ty
of
ha
v
i
ng
a
b
l
oc
k
o
f
i
nfo
r
ma
t
i
on
of
v
aria
bl
e
s
i
z
e
s
o
tha
t
th
e
i
mp
l
em
en
ta
ti
o
n
i
s
v
i
ab
l
e
[9]
,
c
ha
r
ac
teri
s
t
i
c
s
tha
t
on
l
y
ha
s
a rec
on
f
i
gu
r
a
bl
e s
y
s
tem
ty
p
e FP
G
A
[10
].
A
r
ou
n
d
the
tr
a
ns
forma
ti
on
s
[11
],
ex
tr
ac
ti
o
n
of
c
ha
r
a
c
teri
s
ti
c
s
[12
]
or
an
y
ot
he
r
ty
pe
of
ma
s
s
i
v
e
m
atri
x
op
erati
o
n,
ob
j
ec
t
d
ete
c
ti
on
an
d
r
ec
og
ni
t
i
o
n
an
d
r
o
ute
p
l
an
ni
n
g,
P
r
og
r
a
mm
a
bl
e
Lo
g
i
c
D
ev
i
c
es
(
P
LD)
h
av
e
be
e
n
us
ed
,
s
i
nc
e
t
he
y
r
e
qu
i
r
e
l
ow
p
ow
er
an
d
a
s
m
al
l
am
ou
nt
of
s
p
ac
e
to
w
ork
[13
,
14]
i
n
a
dd
i
ti
on
to
ha
v
i
n
g
the
ab
i
l
i
ty
to
pe
r
form
r
ea
l
-
t
i
m
e
i
mp
l
e
me
nt
ati
on
s
,
wor
k
i
n
g
wi
th
s
tat
i
c
a
nd
mo
v
i
ng
i
m
ag
es
[
15
],
w
hi
c
h
r
eq
u
i
r
es
tho
us
an
ds
of
i
terat
i
on
s
pe
r
s
ec
on
d,
w
i
th
ma
x
i
mu
m
us
e
of
F
P
G
A
r
es
ou
r
c
es
,
bo
t
h
i
n
t
he
c
o
m
bi
n
ato
r
i
al
pa
r
t
(
LUT)
as
i
n
i
ts
s
tora
ge
p
art
(
me
mo
r
y
ba
nk
)
,
ma
k
i
ng
ef
fi
c
i
en
t
t
he
i
mp
l
em
en
t
ati
on
s
ma
de
wi
t
h
th
i
s
ty
pe
of
de
v
i
c
es
[
16
,
17].
T
he
ac
q
ui
s
i
t
i
o
n
of
r
ea
l
-
t
i
m
e
i
m
ag
es
ha
s
b
ec
om
e
an
ev
ery
da
y
tas
k
,
us
i
ng
c
o
nv
en
t
i
on
al
c
a
me
r
as
an
d
s
tere
o
c
am
eras
f
or
c
ap
turi
ng
i
n
3D
[
18
,
19
],
i
n
wh
i
c
h
ap
p
l
i
c
at
i
on
s
wi
th
di
gi
t
al
progr
am
ma
b
l
e
d
ev
i
c
es
h
av
e
b
ee
n
m
ad
e
t
o
pe
r
fo
r
m
h
i
gh
-
s
pe
ed
proc
es
s
i
ng
,
ac
h
i
ev
i
ng
s
o
l
ut
i
on
s
wh
ere
a
s
i
ng
l
e
F
P
G
A
i
s
us
ed
th
at
r
ep
l
ac
es
s
y
s
tem
s
of
mu
l
ti
pl
e
arc
hi
tec
tures
tha
t
r
eq
ui
r
ed
c
on
ne
c
ti
on
s
a
n
d c
o
nv
ers
i
o
ns
of
i
nf
ormat
i
on
, s
l
o
wi
n
g d
own
ac
ti
o
ns
on
proc
es
s
es
i
n j
ob
s
w
he
r
e s
h
ort r
es
po
ns
e
ti
m
es
are r
e
qu
i
r
ed
[
20
,
21].
T
he
f
l
ex
i
bi
l
i
ty
an
d
pe
r
for
ma
nc
e
of
h
ardwar
e
d
ev
el
op
me
nt
us
i
n
g
s
t
an
d
ard
h
ardwar
e
de
s
c
r
i
pti
on
l
a
ng
u
ag
es
,
r
e
ga
r
dl
es
s
of
t
he
s
i
z
e
an
d
arc
h
i
tec
tures
of
di
ff
erent
F
P
G
A
's
,
of
fers
the
po
s
s
i
b
i
l
i
ty
to
tes
t
an
d
c
om
pa
r
e
d
i
ffe
r
en
t
a
l
go
r
i
th
m
r
es
ol
ut
i
on
me
th
od
s
,
wh
i
c
h
c
ou
l
d
gi
v
e
di
ff
erent
s
ol
u
ti
o
ns
an
d
i
nd
i
c
ate
w
ha
t
fa
mi
l
y
an
d
w
ha
t
arc
hi
tec
ture
wo
ul
d
be
th
e
m
o
s
t
ap
pro
pria
t
e
to
us
e
i
n
di
g
i
t
al
i
ma
ge
pro
c
es
s
i
ng
ap
pl
i
c
at
i
on
s
[
22
,
2
3],
us
i
ng
t
he
c
o
mb
i
na
t
i
o
n
of
S
oft
C
ores
tog
et
he
r
w
i
t
h
h
ardwar
e
d
es
i
gn
ed
to
ac
c
el
era
te
i
nf
o
r
ma
ti
on
proc
es
s
i
ng
.
A
n
a
pp
l
i
c
ati
on
was
Evaluation Warning : The document was created with Spire.PDF for Python.
â—¼
IS
S
N: 16
93
-
6
93
0
T
E
L
KO
MNIK
A
V
ol
.
1
7
,
No
.
6
,
D
ec
em
b
er
20
19
:
30
0
3
-
3009
3004
de
s
i
g
ne
d
th
at
al
l
ows
v
i
s
ua
l
i
z
ati
on
of
a
r
es
i
de
nt
i
m
ag
e
i
n
a
p
ers
on
a
l
c
o
mp
ut
er,
whi
c
h,
thro
ug
h
a
s
i
m
pl
e
ap
pl
i
c
ati
on
an
d
a
c
us
tom
d
es
i
gn
ed
ha
r
dw
are
wi
th
a
l
ow
en
ergy
c
on
s
um
pti
o
n
[2
4
,
25
],
al
l
ows
i
ts
v
i
s
u
al
i
z
at
i
on
i
n
a
ma
tr
i
x
s
y
s
tem
o
f L
E
Ds
of
a
c
on
s
i
de
r
a
bl
e s
i
z
e.
2.
Me
t
h
o
d
o
log
y
In
t
hi
s
ap
p
l
i
c
at
i
o
n,
a
me
t
h
od
o
l
og
y
tha
t
c
om
pl
i
es
wi
t
h
th
e
T
o
p
-
Dow
n
ph
i
l
os
o
p
hy
ha
s
be
en
c
o
ns
i
d
ered
as
on
e
of
the
mo
s
t
us
ed
i
n
r
ec
o
nfi
g
urab
l
e
h
ardwar
e
s
y
s
tem
s
,
the
r
ef
ore,
a
ge
ne
r
a
l
b
l
oc
k
d
i
ag
r
a
m
h
as
be
e
n
m
ad
e
of
the
i
mp
l
e
me
nt
ed
s
o
l
ut
i
o
n
a
nd
fr
o
m
t
hi
s
,
e
ac
h
o
ne
of
the
fun
c
t
i
on
al
bl
oc
k
s
ha
s
be
e
n
de
s
i
gn
ed
,
s
e
e
F
i
g
ure
1.
T
he
wor
k
do
ne
b
eg
i
ns
wi
th
t
he
de
s
i
gn
of
a
s
oft
war
e
s
c
r
i
pt
on
t
h
e
pe
r
s
on
a
l
c
om
pu
ter,
w
hi
c
h
s
en
ds
the
d
ata
o
f
the
di
g
i
ta
l
i
m
ag
e
i
n
bi
na
r
y
-
as
c
i
i
f
ormat
th
r
ou
gh
a
s
eria
l
p
ort
em
ul
at
ed
tow
ards
th
e
F
P
G
A
,
aft
er
tha
t
,
the
pro
gram
ma
b
l
e
l
og
i
c
de
v
i
c
e
proc
es
s
es
the
i
nfo
r
m
ati
o
n,
s
en
ds
the
d
ata
t
o
a
po
wer
s
y
s
tem
tha
t
s
u
pp
orts
t
he
el
ec
tr
i
c
al
r
eq
ui
r
e
me
nts
at
the
s
pe
e
d
r
eq
ui
r
e
d
by
the
arr
ay
of
L
E
Ds
an
d
i
n
th
i
s
way
th
e c
orr
ec
t v
i
s
u
al
i
z
ati
o
n o
f t
he
i
nf
ormat
i
on
i
s
m
ad
e.
F
i
gu
r
e
1.
G
e
ne
r
a
l
i
z
ed
di
ag
r
am
of
th
e
ap
pl
i
c
ati
on
3.
Imp
lem
ent
atio
n
and
R
e
sult
s
T
he
fi
r
s
t
pa
r
t
o
f
the
w
ork
i
s
s
ho
wn
i
n
the
f
ol
l
ow
i
n
g
c
od
e,
th
e
s
c
r
i
pt
r
ea
ds
d
i
ffe
r
en
t
formats
of
i
m
ag
es
(
j
pg
,
pn
g
an
d
gi
f)
,
i
t
w
i
l
l
m
ak
e
th
e
c
on
v
ers
i
on
t
o
a
m
atri
x
of
v
al
or
to
c
r
ea
t
e
the
RO
M
fi
l
e,
i
t w
i
l
l
b
e rea
d
for the
F
P
G
A
an
d p
u
t i
n t
o
LE
D
ma
tr
i
x
.
im
read () /imshow () to verify that it is in full form for processing.
im = imread('Mario_8bits.PNG');
figure ()
imshow(im)
In
the
f
ol
l
ow
i
n
g
c
od
e
s
e
gm
en
t,
to
s
c
a
l
e
th
e
i
ma
g
e
th
e
i
mres
i
z
e
(
)
fu
nc
ti
o
n
i
s
us
ed
,
whi
c
h
gi
v
es
us
th
e
fac
i
l
i
ty
of
s
c
a
l
i
n
g
th
e
v
al
ue
of
a
s
qu
are
or
r
ec
tan
g
ul
ar
ma
tr
i
x
to
t
he
s
i
z
e
t
o
b
e
v
i
s
ua
l
i
z
ed
i
n
th
e
arr
ay
of
LE
Ds
,
a
bi
c
u
bi
c
i
nt
erpo
l
at
i
on
al
g
orit
hm
was
us
ed
,
a
proc
es
s
th
at
gu
ara
nte
es
t
ha
t
d
o
no
t
dras
ti
c
al
l
y
c
ha
n
ge
t
he
i
nfo
r
ma
t
i
on
th
at
w
i
l
l
b
e s
en
t
to
t
he
F
P
G
A
.
im_small = imresize(im, [32 32], 'cubic');
figure ()
imshow(im_small)
T
he
n
ex
t
c
o
de
s
h
own
th
at
t
he
ma
tr
i
c
es
for
the
i
ma
g
es
tha
t
are
en
t
ered
wer
e
de
fi
n
ed
f
or
a
s
i
z
e
of
32
x
32
be
i
ng
th
i
s
a
s
qu
are
ma
tr
i
x
,
the
s
e
l
ec
t
i
on
of
t
he
s
i
z
e
i
s
b
as
ed
on
the
s
pa
c
e
to
oc
c
up
y
wi
th
i
n
t
he
RO
M
me
m
orie
s
th
at
w
i
l
l
b
e
of
10
24
bi
ts
ma
x
i
mu
m
s
i
z
e
of
e
ac
h
bl
oc
k
of
me
m
ory
of
a
s
tan
da
r
d
F
P
G
A
,
wh
i
c
h
ha
s
a
c
ap
ac
i
ty
of
8
ti
me
s
t
he
v
al
u
e
o
f
ea
c
h
bl
oc
k
ge
ne
r
at
ed
.
im_small_r = im_small(:,:,1);
im_small_g = im_small(:,:,2);
im_small_b = im_small(:,:,3);
T
he
i
ma
g
e
a
l
r
ea
dy
s
c
al
ed
i
s
brok
en
d
own
i
nt
o
th
e
3
m
at
r
i
c
es
of
the
c
h
an
n
el
s
t
ha
t
ma
k
e
up
a
di
g
i
ta
l
i
ma
g
e
R
(
ne
tw
ork
)
,
G
(
gree
n)
a
nd
B
(
bl
ue
)
,
ma
i
nt
ai
ni
n
g
t
he
i
nte
ns
i
ty
c
ha
r
ac
teri
s
ti
c
s
to
c
on
form
t
he
d
i
ffe
r
e
nt
c
ol
or
po
s
s
i
b
i
l
i
t
i
es
,
i
n
e
ac
h
ma
tr
i
x
th
e
v
al
u
es
of
e
ac
h
pi
x
e
l
ha
v
e
a
ma
gn
i
tud
e
b
etwe
en
0
a
nd
2
55
.
T
h
e
c
om
bi
na
t
i
on
of
th
es
e
c
ha
n
ne
l
s
c
on
for
ms
the
s
c
al
ed
i
ma
ge
,
w
hi
c
h
w
i
l
l
be
us
ed
to
oc
c
up
y
v
al
u
e
by
v
al
u
e
the
arr
ay
of
LE
Ds
f
or
the
i
r
r
es
pe
c
t
i
v
e
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KO
MNIK
A
IS
S
N: 1
69
3
-
6
93
0
â—¼
T
r
an
s
format
i
on
an
d d
y
n
am
i
c
v
i
s
ua
l
i
z
a
ti
o
n o
f
i
ma
g
es
from c
om
pu
t
er
... (
E
dwar J
ac
i
nto
G
ó
me
z
)
3005
v
i
s
ua
l
i
z
ati
on
.
F
i
gu
r
e
2
s
h
ows
the
m
atri
c
es
or
c
ha
nn
e
l
s
R,
G
an
d
B
i
n
w
hi
c
h
th
e
mo
s
t
c
ha
r
ac
teri
s
ti
c
v
a
l
ue
s
o
f
th
e
i
m
ag
e
to
be
d
i
s
p
l
ay
ed
c
an
be
ob
s
erv
ed
.
If
th
ey
are
c
om
p
ared,
the
fi
r
s
t
arr
ay
ha
s
a
prom
i
n
en
t
wh
i
te
v
a
l
ue
,
wh
i
c
h
me
a
ns
a
25
5
ma
g
ni
t
ud
e
or
a
s
tr
on
g
r
ed
c
o
l
or,
i
n
the
i
ma
ge
wh
ere
i
t
i
s
ob
s
erv
ed
c
om
pl
e
tel
y
an
d
wi
t
h
da
r
k
er
ton
es
b
l
ac
k
s
are
0
or
a
r
ed
v
al
ue
i
n a
bl
ue
r
e
pres
en
t
ati
on
i
m
ag
e.
F
i
gu
r
e
1
. RG
B
c
ha
nn
e
l
s
of
the
i
ma
ge
t
ha
t w
i
l
l
be
s
c
al
e
d a
n
d s
en
t
to
t
he
F
P
G
A
3.1.
T
r
ansmi
ss
ion
of
Inf
o
r
mat
i
o
n
Blocks
f
r
o
m M
atlab
t
o
F
P
G
A
-
s
end
in RG
B
F
or
the
r
ec
ep
t
i
on
of
the
d
ata
i
s
do
ne
wi
t
h
a
CO
RE
pe
r
forme
d
di
r
ec
tl
y
by
X
i
l
i
n
x
[17
],
as
on
e
of
t
he
mo
d
ul
es
i
m
pl
e
me
nt
ed
for
th
e
8
B
i
t
P
I
CO
B
l
az
e
proc
es
s
or,
s
i
nc
e
thi
s
CO
R
E
i
s
pe
r
forme
d
at
v
ery
l
ow
l
ev
el
o
nl
y
us
es
2
2
S
l
i
c
es
of
the
o
ne
F
P
G
A
S
pa
r
t
an
ty
pe
to
pe
r
form
the
da
ta
r
ec
ep
t
i
o
n.
F
i
g
ure
3
s
ho
ws
the
b
l
oc
k
di
a
gra
m
of
the
r
ec
e
pti
on
d
es
i
g
n
for
RS
23
2
on
a X
i
l
i
nx
s
FPG
A
ma
de
by
M
r
. Cha
p
ma
n
.
F
i
gu
r
e
2
. R
S
2
32
r
ec
ep
ti
on
bl
oc
k
;
c
ore pr
ov
i
de
d b
y
X
i
l
i
nx
fo
r
P
i
c
oB
l
az
e [
26
]
T
he
i
np
ut
c
h
an
n
el
of
th
e
m
od
u
l
e
(
serial_in
)
r
ec
ei
v
e
s
the
da
t
a
t
o
wor
k
w
i
th
the
wai
t
i
ng
of
a
r
i
s
i
ng
ed
g
e
for
the
tr
an
s
mi
s
s
i
o
n
of
the
8
b
i
t
s
.
(
data_out
)
i
s
the
p
aral
l
el
ou
t
pu
t
of
the
r
ec
e
i
v
ed
d
ata
.
(
read_buffer
)
i
n
hi
gh
s
tat
e
of
r
es
p
on
s
i
b
l
e
for
t
he
tr
an
s
m
i
s
s
i
on
of
the
da
ta
to
a
F
IFO
me
mo
r
y
.
(
reset_b
uffer
)
i
n
ac
t
i
v
e
s
tat
e
de
l
e
te
t
he
da
t
a
s
av
e
d
un
d
er
t
h
e
c
ou
nt
of
16
da
ta
b
l
oc
k
s
.
(
en_16_x_baud
)
i
n
ac
ti
v
e
s
tat
e
m
ak
es
the
c
ou
nt
i
n
g
of
16
c
y
c
l
es
of
8
bi
ts
wh
i
c
h
c
ul
mi
na
t
es
the
s
torag
e
s
o
t
ha
t
t
he
en
t
i
r
e
b
l
oc
k
c
r
ea
te
d
i
n
th
e
16
x
8
me
mo
r
y
w
i
l
l
be
tr
a
ns
mi
tt
ed
.
(
buffer_data_present
)
gi
v
es
an
i
n
pu
t
pro
mp
t
or
tha
t
the
r
e
i
s
i
nfo
r
m
ati
on
b
l
oc
k
i
n
th
e
me
mo
r
y
.
(
buffer_full
or
buffer_half_full
)
i
nd
i
c
ate
s
i
n
h
i
gh
mo
d
e
th
e
fu
l
l
s
ta
te
of
the
m
em
ory
,
i
nd
i
c
ate
s
h
ow
t
he
i
r
na
me
s
s
ay
ful
l
or
h
al
f
f
ul
l
1
6x
8/8
x
8
when
i
t
i
s
fu
l
l
me
mo
r
y
c
om
mu
n
i
c
ate
s
th
i
s
s
tat
e
a
nd
ac
ti
v
at
es
th
e
c
o
mp
l
ete
tr
an
s
fer
of
t
he
me
mo
r
y
bl
oc
k
wherev
er
y
ou
r
proc
es
s
i
ng
i
s
ne
c
es
s
ary
. (
clk
)
s
y
s
tem
c
l
oc
k
fo
r
a
s
y
nc
hrono
us
mu
l
ti
pl
e s
y
s
tem
.
Evaluation Warning : The document was created with Spire.PDF for Python.
â—¼
IS
S
N: 16
93
-
6
93
0
T
E
L
KO
MNIK
A
V
ol
.
1
7
,
No
.
6
,
D
ec
em
b
er
20
19
:
30
0
3
-
3009
3006
3.2.
Rece
p
t
ion
and
S
t
o
r
ag
e
of
Blo
ck
s
of
Inf
o
r
mat
ion
in
RAM
In
the
d
es
i
g
n
an
d
i
m
pl
em
en
tat
i
o
n
of
th
e
s
y
s
tem
i
t
i
s
ob
s
erv
ed
ho
w
the
CO
RE
of
the
U
art
pr
ov
i
de
d
by
X
i
l
i
nx
i
s
c
on
tr
o
l
l
ed
,
by
m
ea
ns
of
a
fi
ni
t
e
s
tat
e
ma
c
h
i
ne
,
th
i
s
i
s
i
n
c
ha
r
g
e
o
f
r
ea
di
ng
th
e
da
ta
fr
o
m
th
e
F
IFO
me
m
ory
an
d
p
as
s
i
n
g
i
t
to
th
e
i
nte
r
na
l
R
A
M
me
mo
r
y
of
the
F
P
G
A
,
i
n
th
i
s
way
i
t
i
s
po
s
s
i
b
l
e
to
r
e
ad
bl
oc
k
s
of
i
nf
ormat
i
o
n
fr
o
m
t
he
U
S
B
-
S
eria
l
po
r
t
of
the
c
o
mp
u
ter
t
o
t
he
i
n
t
ernal
m
em
ory
,
whi
c
h
w
i
l
l
the
n
be
r
es
po
ns
i
bl
e
f
or
di
s
p
l
ay
i
ng
the
i
nfo
r
ma
t
i
on
,
as
s
ho
w
n i
n
F
i
g
ure 4.
F
i
gu
r
e
3
.
B
l
oc
k
d
i
a
gram
of
t
he
s
eria
l
r
ec
e
pti
on
s
y
s
tem
3.3.
G
ener
atio
n
and
Co
n
t
r
o
l
o
f
P
W
M
Nex
t,
on
e
of
t
he
m
os
t
i
m
po
r
tan
t
ha
r
dw
are
b
l
oc
k
s
i
s
de
s
c
r
i
be
d
,
wh
i
c
h
al
l
o
ws
to
r
ea
d
the
v
a
l
ue
of
ea
c
h
of
t
he
pi
x
el
s
i
n
al
l
i
ts
c
ha
n
ne
l
s
an
d
c
on
v
ert
th
em
i
nt
o
a
brig
ht
ne
s
s
i
nt
en
s
i
ty
v
al
ue
of
the
po
i
nts
(
L
E
D
S
)
i
n
t
he
ma
tr
i
x
,
v
ary
i
ng
fr
om
dy
na
m
i
c
al
l
y
th
e
p
ul
s
e
wi
dt
h,
a
l
l
th
i
s
mu
s
t
be
do
ne
at
th
e
fr
eq
ue
nc
y
a
t
whi
c
h
the
dy
na
m
i
c
d
i
s
pl
a
y
wor
k
s
,
i
n
oth
er
wor
ds
,
a
t
the
s
am
e
ti
me
tha
t
th
e
da
ta
ar
e
be
i
ng
e
n
ab
l
ed
to
be
s
h
own
on
t
he
di
s
pl
ay
,
the
pu
l
s
e
wi
dth
m
u
s
t
be
c
ha
ng
e
d.
It
gi
v
es
th
e
i
nte
ns
i
ty
to
e
ac
h
of
th
e
po
i
nts
o
f
the
RG
B
ma
tr
i
x
.
T
he
f
ol
l
ow
i
ng
bl
oc
k
of
c
od
e
de
s
c
r
i
be
s
th
e
8
-
b
i
t
P
W
M
mo
du
l
e
i
n
the
V
H
DL
l
an
g
ua
ge
,
a
hi
g
hl
y
us
ed
l
an
gu
ag
e,
s
i
nc
e
i
t
i
s
a s
tan
d
ard l
an
gu
a
ge
t
ha
t
al
l
ows
th
e d
es
c
r
i
pti
on
o
f h
ar
d
war
e a
t
a h
i
g
h l
ev
el
of
a
bs
tr
ac
ti
on
.
entity PWM_01 is
generic (generic : width := 8);
Port ( clk,reset : in
STD_LOGIC
;
Duty
: in
STD_LOGIC_VECTOR
(width
-
1 downto 0);
PWM_out
: out
STD_LOGIC
);
end PWM_01;
In
thi
s
s
ec
ti
on
of
c
od
e,
the
de
c
l
arat
i
o
n
of
th
e
i
n
pu
ts
an
d
ou
tp
uts
of
the
s
y
s
tem
i
s
ma
de
;
a
c
l
oc
k
an
d
r
es
et
as
ba
s
e
s
i
gn
al
s
i
n
an
y
de
s
c
r
i
p
ti
on
of
a
s
e
qu
e
nti
al
c
i
r
c
u
i
t
are
o
bta
i
ne
d,
i
n a
dd
i
ti
on
to
t
he
D
uty
i
np
u
t
th
at
c
om
es
fr
om
t
he
RA
M
me
m
ory
, whe
r
e
th
ey
are s
t
ored e
v
ery
o
ne
of
th
e
v
a
l
ue
s
of
th
e
i
nt
en
s
i
ty
of
t
he
pi
x
e
l
s
to
be
di
s
pl
ay
ed
i
n
th
e
L
E
D
's
m
at
r
i
x
an
d
fi
na
l
l
y
the
ou
tp
ut
of
t
he
pu
l
s
e
w
i
dt
h
mo
du
l
at
i
on
,
wh
i
c
h
w
i
l
l
be
the
l
as
t
s
i
gn
al
to
be
di
s
p
l
a
y
ed
i
n
e
ac
h
o
f
the
p
oi
nts
of
t
he
ma
tr
i
x
.
architecture Behavioral of PWM_01 is
signal counter :
STD_LOGIC_V
s
ECTOR
(width
-
1 downto 0);
begin
process(clk,reset)
begin
if reset = '1' then
counter <= (others => '0');
PWM_out <= '0';
elsif
rising_edge
(clk) then
counter <= counter + 1;
if counter < Duty then
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KO
MNIK
A
IS
S
N: 1
69
3
-
6
93
0
â—¼
T
r
an
s
format
i
on
an
d d
y
n
am
i
c
v
i
s
ua
l
i
z
a
ti
o
n o
f
i
ma
g
es
from c
om
pu
t
er
... (
E
dwar J
ac
i
nto
G
ó
me
z
)
3007
PWM_out <= '1';
else
PWM_out <= '0';
end if;
end if;
end process;
end Behavioral;
In
th
e
arc
h
i
tec
ture
th
e
d
e
s
c
r
i
pti
on
of
a
c
ou
nte
r
i
s
s
ho
wn,
bu
t
i
n
th
i
s
pa
r
t
i
c
u
l
ar
c
as
e
i
t
i
s
c
om
pa
r
e
d w
i
th
t
he
i
n
pu
t
of
Duty
, wh
i
c
h g
i
v
es
th
e v
a
l
ue
th
at
th
e
us
ef
ul
c
y
c
l
e
of
t
he
s
y
s
tem
wi
l
l
be
gi
v
en
an
d
wi
l
l
gi
v
e
th
e
i
n
ten
s
i
ty
of
bri
gh
t
ne
s
s
of
e
ac
h o
ne
of
t
he
LE
D
’
s
.
3.4.
Dynam
ic
V
i
sualiz
atio
n
o
n
LED
A
r
r
a
y
W
he
n
p
erfor
m
i
ng
a
dy
na
mi
c
v
i
s
u
al
i
z
ati
on
i
n
a
LE
D
arr
ay
,
t
he
v
a
l
u
e
of
th
e
c
urr
en
t
ne
c
es
s
ary
to
s
ee
ea
c
h
of
t
he
po
i
nts
c
orr
ec
tl
y
an
d
h
av
e
the
ne
c
es
s
ary
brig
htn
es
s
to
ha
nd
l
e
a
n
RG
B
m
atri
x
m
us
t
be
tak
en
i
nto
a
c
c
ou
nt
.
A
c
i
r
c
ui
t
mu
s
t
be
m
ad
e
to
de
l
i
v
er
th
e
n
ec
es
s
ary
c
urr
en
t
wi
th
th
e
r
e
qu
i
r
ed
s
p
ee
d
,
i
n
th
i
s
c
as
e,
s
om
e
t
es
ts
w
ere
p
erfor
me
d
wi
t
h
t
he
i
nt
eg
r
ate
d
c
i
r
c
u
i
t
MA
X
72
19
,
driv
er
for
8x
8
LE
D
arr
ay
ma
na
g
em
e
nt,
whi
c
h
de
l
i
v
ers
an
ou
t
pu
t
of
5
00
mi
l
l
i
A
mp
eres
,
bu
t
th
e
r
e
fr
es
h
r
ate
of
t
he
s
y
s
tem
i
s
no
t
ac
hi
ev
e
d,
s
i
nc
e,
al
t
ho
u
gh
t
he
wor
k
i
ng
s
p
ee
d
i
s
10
Mh
z
f
or
i
ts
S
P
I
i
nte
r
f
ac
e,
i
t
on
l
y
ac
h
i
ev
es
a
r
e
f
r
es
h
r
ate
of
8
00
Hz
.
F
or
t
he
s
e
r
e
as
on
s
,
i
t
w
as
d
ec
i
d
ed
to
m
ak
e
a
c
i
r
c
ui
t
w
i
th
a
Mo
s
fet
N
c
h
an
ne
l
an
d
i
ts
r
es
p
ec
ti
v
e
dr
i
v
er,
s
i
nc
e
t
hi
s
po
wer
e
l
em
en
t
gi
v
es
a
m
a
x
i
mu
m
c
urr
en
t
of
1
2
A
m
ps
c
on
ti
n
uo
us
l
y
a
nd
u
p
to
3
0
A
mp
s
pe
ak
s
an
d
a
wor
k
i
n
g
s
pe
ed
ov
er
30
0
K
hz
,
r
e
me
m
be
r
i
ng
t
o
r
es
pe
c
t
the
m
i
ni
mu
m
on
an
d
off
t
i
m
es
of
the
d
ev
i
c
e,
av
oi
d
i
n
g t
h
at
th
e s
w
i
tc
h
i
s
i
n
s
ho
r
t c
i
r
c
ui
t o
r
i
n
an
i
nd
ete
r
m
i
na
te
s
tat
e.
Hav
i
ng
a
s
y
s
tem
tha
t
r
e
q
ui
r
es
ha
nd
l
i
n
g
32
r
ows
a
n
d
32
c
ol
um
ns
to
us
e
th
e
l
owes
t
nu
mb
er
o
f
o
utp
uts
of
th
e
F
P
G
A
,
the
c
ol
um
ns
wer
e
ha
nd
l
ed
wi
t
h
t
wo
s
h
i
ft
r
e
gi
s
ters
,
w
hi
c
h
on
l
y
r
eq
u
i
r
e
the
i
np
ut
o
f
D
in
an
d
Clk
to
pe
r
f
orm
s
a
i
d
tas
k
,
th
e
c
l
oc
k
m
us
t
h
a
v
e
a
wor
k
i
n
g
fr
eq
ue
nc
y
of
17
.2
k
Hz
to
ac
hi
ev
e
a
r
efres
h
r
at
e
of
ea
c
h
of
the
c
ol
u
mn
s
at
4
5
Hz
,
thi
s
c
i
r
c
ui
t
wi
t
h
s
hi
fti
ng
r
eg
i
s
ters
i
s
ha
nd
l
e
d
wi
th
a
Dar
l
i
n
gto
n
-
ty
pe
c
urr
en
t
s
wi
tc
h
of
1.5
a
mp
s
ou
t
pu
t
for
ea
c
h
o
f
the
3
2
c
ol
um
ns
an
d
a
m
a
x
i
mu
m
wor
k
i
n
g
s
pe
ed
o
f
4
0
K
hz
,
av
oi
di
ng
h
av
i
n
g
pu
l
s
e
wi
dt
hs
l
es
s
tha
n
10
%
an
d
great
er th
an
90
%.
O
n
the
oth
er
ha
n
d,
th
ere
w
ere
8
o
utp
uts
of
P
W
M,
wh
i
c
h
wer
e
"
de
mu
l
ti
p
l
ex
e
d"
to
ha
nd
l
e
the
3
2
r
ows
,
ea
c
h
of
t
he
m
ha
s
a
po
w
er
c
i
r
c
ui
t
wi
th
a
Mo
s
fet
Ch
an
n
el
N
i
n
s
i
nk
c
on
fi
gu
r
at
i
on
.
In
oth
er
wor
ds
,
the
c
urr
e
nt
i
s
i
nj
ec
te
d
throu
gh
th
e
c
ol
um
ns
a
nd
th
e
P
W
M
mo
du
l
e
c
o
ntrol
s
the
pa
s
s
ag
e
o
f
t
he
c
urr
en
t
t
hroug
h
ea
c
h
L
E
D
an
d
tow
ards
th
e
grou
nd
,
i
t
i
s
r
eq
u
i
r
ed
th
at
the
fr
e
qu
e
nc
y
of
th
i
s
P
W
M
i
s
at
l
ea
s
t
1
0
ti
me
s
o
f
the
s
pe
ed
of
v
i
s
u
al
i
z
ati
on
of
th
e
c
ol
um
ns
,
th
at
i
s
why
th
e
P
W
M
mo
du
l
e
of
17
6
K
hz
w
as
c
on
f
i
gu
r
e
d
wi
th
an
8
b
i
t
r
es
o
l
ut
i
on
,
th
e
pu
l
s
e
wi
dth
i
s
r
ea
d
fr
o
m
th
e
RA
M
m
em
ory
where
t
he
c
ha
nn
e
l
s
o
f
the
i
m
ag
e
to
b
e
d
i
s
pl
ay
ed
are
s
t
ored.
F
i
gu
r
e
5
s
ho
ws
a
bl
oc
k
d
i
ag
r
am
de
t
ai
l
i
ng
t
he
s
y
s
te
m.
It
i
s
i
mp
ort
an
t
to
em
p
h
as
i
z
e
th
at
b
oth
the
fr
eq
ue
nc
y
of
t
he
P
W
M
of
ea
c
h
c
h
an
n
el
,
t
he
mu
l
ti
p
l
ex
i
ng
s
p
ee
d
of
th
e
s
i
gn
al
s
an
d
t
he
s
pe
ed
of
r
ea
di
ng
of
t
he
me
mo
r
y
,
wou
l
d
be
d
i
ffi
c
u
l
t
to
ac
hi
ev
e
wi
t
h
oth
er
ty
pe
s
o
f
de
v
i
c
es
t
ha
n
an
FPG
A
.
F
i
gu
r
e
5.
D
eta
i
l
e
d b
l
oc
k
d
i
a
gram
Evaluation Warning : The document was created with Spire.PDF for Python.
â—¼
IS
S
N: 16
93
-
6
93
0
T
E
L
KO
MNIK
A
V
ol
.
1
7
,
No
.
6
,
D
ec
em
b
er
20
19
:
30
0
3
-
3009
3008
4.
Co
n
clus
ion
s
T
he
tr
e
atm
en
t
of
i
ma
g
es
o
n
th
e
arc
hi
tec
t
ure
of
F
P
G
A
'
s
i
s
fac
i
l
i
tat
ed
by
h
av
i
n
g
t
h
e
a
bi
l
i
ty
to
pe
r
f
orm
pr
oc
es
s
es
i
n
pa
r
al
l
e
l
,
bo
t
h
for
prepr
oc
es
s
i
ng
a
nd
f
or
th
e
v
i
s
ua
l
i
z
a
ti
o
n
of
an
i
m
ag
e,
tog
et
he
r
w
i
th
s
o
me
al
g
orit
h
ms
tha
t
r
e
qu
i
r
e
h
i
g
h
de
ma
nd
for
em
b
ed
d
ed
p
r
oc
es
s
i
n
g,
bu
t
wi
t
h
l
ow
am
ou
nt
of
ha
r
dw
are,
th
i
s
ad
v
an
t
ag
e
i
s
ev
i
d
en
c
ed
i
n
the
r
efres
h
r
at
e
of
t
he
fr
a
me
s
s
ho
wn
i
n
the
arr
ay
of
L
E
Ds
pe
r
s
ec
on
d,
at
th
i
s
p
oi
nt
i
t
i
s
i
m
p
ortant
to
e
mp
h
as
i
z
e
t
ha
t
i
t
wou
l
d
b
e
v
ery
di
ff
i
c
ul
t
to
i
nc
r
ea
s
e
the
s
p
e
ed
of
work
of
t
h
e s
y
s
tem
i
f
y
ou
were
no
t
wor
k
i
ng
wi
th
a FP
G
A
.
T
ha
nk
s
to
th
e
m
ul
t
i
p
l
e
h
ard
war
e
to
ol
s
of
the
F
P
G
A
,
i
t
i
s
po
s
s
i
bl
e
to
w
ork
i
n
c
on
j
u
nc
ti
on
wi
th
th
e
c
om
pu
t
er
to
p
erfor
m
a
fu
nd
a
me
nta
l
p
art
o
f
the
i
mp
l
e
me
nt
ati
on
i
n
th
e
r
ea
di
n
g
an
d
s
torage
o
f
F
IFO
m
em
or
i
e
s
,
throug
h
th
e
U
S
B
po
r
t
to
th
e
F
P
G
A
a
nd
t
he
n
ha
v
e
d
ata
f
or
the
v
i
s
u
al
i
z
ati
on
i
n
the
arr
ay
of
L
E
Ds
.
T
h
e
gr
ea
t
de
ma
nd
of
po
w
er
i
n
th
i
s
ty
pe
of
a
pp
l
i
c
at
i
on
s
r
eq
ui
r
es
a
c
o
ntrol
for
t
he
i
n
j
ec
ti
on
of
c
urr
en
t
to
ea
c
h
o
ne
o
f
th
e
po
i
nts
of
th
e
m
atr
i
x
of
LE
D
,
f
or
tha
t
r
e
as
o
n
the
c
ap
ac
i
ty
of
ha
nd
l
i
ng
of
t
he
s
i
gn
al
s
o
f
c
on
tr
ol
an
d
f
ee
d
i
n
g
i
s
r
e
qu
i
r
ed
,
t
he
F
P
G
A
ful
f
i
l
l
s
wi
t
h
the
tec
hn
i
c
al
s
pe
c
i
f
i
c
ati
on
s
of
t
hi
s
ty
pe
o
f
i
mp
l
e
me
n
tat
i
on
s
.
A
c
i
r
c
ui
t
for
dy
na
mi
c
v
i
s
ua
l
i
z
ati
on
i
s
s
ho
wn,
w
he
r
e
i
t
was
n
ec
es
s
ary
to
de
s
i
gn
a
h
i
g
h
-
s
pe
ed
c
urr
e
nt
am
pl
i
fi
er
c
i
r
c
u
i
t
to
pe
r
form
th
e
c
orr
ec
t
v
i
s
ua
l
i
z
ati
o
n
of
the
i
ma
g
es
a
l
r
ea
dy
proc
es
s
ed
ac
c
ordi
ng
to
th
e
th
eo
r
et
i
c
al
l
y
pl
a
nn
e
d f
orm
.
Ackno
w
ledg
men
t
T
hi
s
wor
k
was
s
up
po
r
t
ed
by
the
Un
i
v
ers
i
da
d
Di
s
t
r
i
tal
F
r
a
nc
i
s
c
o
J
os
é
de
Cal
d
as
T
ec
hn
ol
og
i
c
al
F
ac
ul
ty
.
T
h
e
v
i
ews
ex
pres
s
ed
i
n
t
hi
s
pa
p
er
are
no
t
ne
c
es
s
ari
l
y
en
do
r
s
ed
by
the
Uni
v
ers
i
ty
.
T
h
e
au
th
ors
tha
nk
t
he
r
es
ea
r
c
h
group
A
RMO
S
f
or
t
he
ev
al
ua
t
i
on
c
arr
i
ed
ou
t
on
prototy
pe
s
of
i
de
as
an
d
s
tr
ate
g
i
es
.
Ref
er
en
ce
s
[1
]
Zh
a
n
g
H.
Rea
l
i
z
a
ti
o
n
o
n
i
m
a
g
e
2
D
-
DC
T
s
p
a
r
s
e
tra
n
s
fo
r
m
b
a
s
e
d
o
n
FPGA
.
1
4
t
h
In
t
e
rn
a
ti
o
n
a
l
Com
p
u
t
e
r
Con
f
e
re
n
c
e
o
n
Wa
v
e
l
e
t
A
c
ti
v
e
M
e
d
i
a
Te
c
h
n
o
l
o
g
y
a
n
d
I
n
fo
r
m
a
t
i
o
n
P
ro
c
e
s
s
i
n
g
(ICCWAM
TI
P).
Ch
e
n
g
d
u
.
2
0
1
7
:
175
–
1
7
8
.
[2
]
Zh
a
n
g
S,
Zh
u
J
,
Wa
n
g
C.
A
p
p
l
i
c
a
t
i
o
n
o
f
TEXT
IO
i
n
t
h
e
Si
m
u
l
a
ti
o
n
o
f
FPGA
Im
a
g
e
Pro
c
e
s
s
i
n
g
Al
g
o
ri
t
h
m
.
3
rd
I
n
te
rn
a
ti
o
n
a
l
C
o
n
fe
re
n
c
e
o
n
In
fo
rm
a
ti
o
n
Sc
i
e
n
c
e
a
n
d
Co
n
tro
l
E
n
g
i
n
e
e
ri
n
g
(ICISCE)
.
Be
i
j
i
n
g
.
2
0
1
6
:
235
-
238
.
[3
]
Rup
a
n
i
A,
W
h
i
g
P,
Su
j
e
d
i
y
a
G, Vy
a
s
P.
A ro
b
u
s
t
te
c
h
n
i
q
u
e
f
o
r i
m
a
g
e
p
ro
c
e
s
s
i
n
g
b
a
s
e
d
o
n
i
n
te
rfa
c
i
n
g
o
f
Ras
p
b
e
rr
y
-
Pi
a
n
d
FPGA
u
s
i
n
g
I
o
T
.
2
0
1
7
I
n
t
e
rn
a
ti
o
n
a
l
Co
n
fe
re
n
c
e
o
n
Com
p
u
te
r,
Com
m
u
n
i
c
a
ti
o
n
s
a
n
d
El
e
c
tr
o
n
i
c
s
(Co
m
p
t
e
l
i
x
).
J
a
i
p
u
r.
2
0
1
7
:
3
5
0
-
3
5
3
.
[4
]
Hu
T,
Ik
e
n
a
g
a
T.
FPGA
i
m
p
l
e
m
e
n
ta
ti
o
n
o
f
h
i
g
h
fra
m
e
ra
t
e
a
n
d
u
l
t
ra
-
l
o
w
d
e
l
a
y
v
i
s
i
o
n
s
y
s
te
m
wit
h
l
o
c
a
l
a
n
d
g
l
o
b
a
l
p
a
ra
l
l
e
l
b
a
s
e
d
m
a
tc
h
i
n
g
.
2
0
1
7
Fi
ft
e
e
n
th
IA
PR
In
te
rn
a
ti
o
n
a
l
Con
fe
re
n
c
e
o
n
M
a
c
h
i
n
e
Vi
s
i
o
n
Ap
p
l
i
c
a
ti
o
n
s
(M
VA)
.
N
a
g
o
y
a
.
2
0
1
7
:
2
8
6
-
2
8
9
.
[5
]
M
o
ra
l
e
s
-
Ro
m
e
ro
J
J
,
G
o
m
e
z
-
Cas
ta
n
e
d
a
F,
M
o
re
n
o
-
Cad
e
n
a
s
J
A,
Re
y
e
s
-
B
a
rra
n
c
a
M
A,
Fl
o
re
s
-
Nav
a
L
M
.
Ti
m
e
-
m
u
l
t
i
p
l
e
x
i
n
g
c
e
l
l
u
l
a
r
n
e
u
ra
l
n
e
two
rk
i
n
FPGA
fo
r
i
m
a
g
e
p
ro
c
e
s
s
i
n
g
.
2
0
1
7
1
4
th
I
n
te
rn
a
t
i
o
n
a
l
Con
fe
re
n
c
e
o
n
El
e
c
tr
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
Co
m
p
u
t
i
n
g
Sc
i
e
n
c
e
a
n
d
A
u
to
m
a
ti
c
Con
tro
l
(CC
E)
.
M
e
x
i
c
o
.
2017:
1
-
5.
[6
]
Zh
a
n
g
C,
L
i
a
n
g
T,
M
o
k
PK
T,
Yu
W.
FPGA
I
m
p
l
e
m
e
n
ta
t
i
o
n
o
f
th
e
Cou
p
l
e
d
Fi
l
t
e
ri
n
g
M
e
th
o
d
a
n
d
th
e
Aff
i
n
e
Wa
rp
i
n
g
M
e
th
o
d
.
IEEE
Tra
n
s
N
a
n
o
b
i
o
s
c
i
e
n
c
e
.
2
0
1
7
;
1
6
(5
):
3
1
4
–
3
2
5
.
[7
]
Fu
n
a
s
a
k
a
T,
Iwa
s
e
M
,
Fu
j
i
s
a
wa
K,
Hat
a
k
e
y
a
m
a
S.
V
i
s
u
a
l
i
z
a
t
i
o
n
o
f
St
a
b
i
l
i
t
y
o
f
Dy
n
a
m
i
c
a
l
S
y
s
te
m
s
b
y
3
D
G
ra
p
h
i
c
s
Su
p
p
o
rte
d
b
y
Cl
u
s
te
r
Co
m
p
u
ti
n
g
.
Wo
r
k
In
te
l
l
Dat
a
Ac
q
u
i
s
A
d
v
Com
p
u
t
S
y
s
t
Te
c
h
n
o
l
Ap
p
l
.
2
0
1
5
:
5
8
8
–
5
9
2
.
[8
]
L
i
u
H,
Yu
F.
Res
e
a
r
c
h
a
n
d
I
m
p
l
e
m
e
n
ta
ti
o
n
o
f
Col
o
r
Im
a
g
e
Pro
c
e
s
s
i
n
g
Pi
p
e
l
i
n
e
Ba
s
e
d
o
n
FPGA
.
2
0
1
6
9
th
In
t
e
rn
a
t
i
o
n
a
l
Sy
m
p
o
s
i
u
m
o
n
Co
m
p
u
ta
ti
o
n
a
l
I
n
te
l
l
i
g
e
n
c
e
a
n
d
Des
i
g
n
(ISCID)
.
Han
g
z
h
o
u
.
2
0
1
6
:
3
7
2
-
375.
[9
]
So
n
TN,
Hoa
n
g
TM
,
Dz
u
n
g
N
T,
G
i
a
n
g
NH
.
Fa
s
t
FPGA
i
m
p
l
e
m
e
n
ta
ti
o
n
o
f
YUV
-
b
a
s
e
d
fra
c
ta
l
i
m
a
g
e
c
o
m
p
re
s
s
i
o
n
.
2
0
1
4
IEEE
F
i
ft
h
In
t
e
rn
a
t
i
o
n
a
l
C
o
n
fe
r
e
n
c
e
o
n
Com
m
u
n
i
c
a
ti
o
n
s
a
n
d
E
l
e
c
tro
n
i
c
s
(ICCE
)
.
Dan
a
n
g
.
2
0
1
4
:
4
4
0
-
4
4
5
.
[1
0
]
Rah
a
n
g
d
a
l
e
S,
K
e
i
j
z
e
r
P,
Kr
u
i
t
P.
M
BSEM
i
m
a
g
e
a
c
q
u
i
s
i
ti
o
n
a
n
d
i
m
a
g
e
p
ro
c
e
s
s
i
n
g
i
n
L
a
b
Vi
e
w
FPGA
.
2
0
1
6
I
n
te
rn
a
ti
o
n
a
l
C
o
n
fe
re
n
c
e
o
n
Sy
s
te
m
s
,
Si
g
n
a
l
s
a
n
d
I
m
a
g
e
Pro
c
e
s
s
i
n
g
(IW
SSIP)
.
Bra
ti
s
l
a
v
a
.
2
0
1
6
:
1
-
4.
[1
1
]
Ak
k
a
d
G
,
El
h
a
s
s
a
n
M
,
Ay
o
u
b
i
R.
FPGA
h
a
rd
ware
a
rc
h
i
te
c
t
u
re
fo
r
s
t
e
re
o
s
c
o
p
i
c
i
m
a
g
e
c
o
m
p
re
s
s
i
o
n
b
a
s
e
d
o
n
b
l
o
c
k
m
a
tc
h
i
n
g
,
wa
te
rm
a
rk
i
n
g
a
n
d
h
a
m
m
i
n
g
c
o
d
e
.
2
0
1
6
I
n
te
rn
a
ti
o
n
a
l
I
m
a
g
e
Pro
c
e
s
s
i
n
g
,
Ap
p
l
i
c
a
ti
o
n
s
a
n
d
Sy
s
te
m
s
(
IPAS).
Ham
m
a
m
e
t.
2
0
1
6
:
1
-
5.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KO
MNIK
A
IS
S
N: 1
69
3
-
6
93
0
â—¼
T
r
an
s
format
i
on
an
d d
y
n
am
i
c
v
i
s
ua
l
i
z
a
ti
o
n o
f
i
ma
g
es
from c
om
pu
t
er
... (
E
dwar J
ac
i
nto
G
ó
me
z
)
3009
[1
2
]
Dha
n
a
b
a
l
R
,
Sa
h
o
o
SK,
Bh
a
ra
th
i
V,
Dowl
u
ri
K,
Va
r
m
a
BSRP
,
Sa
s
i
ra
j
u
V.
FPGA
b
a
s
e
d
i
m
a
g
e
p
ro
c
e
s
s
i
n
g
u
n
i
t
u
s
a
g
e
i
n
c
o
i
n
d
e
t
e
c
t
i
o
n
a
n
d
c
o
u
n
ti
n
g
.
2
0
1
5
In
t
e
rn
a
ti
o
n
a
l
Co
n
fe
re
n
c
e
o
n
Cir
c
u
i
t
s
,
Po
wer
a
n
d
Co
m
p
u
ti
n
g
T
e
c
h
n
o
l
o
g
i
e
s
[
ICCPC
T
-
2015]
.
Nag
e
rc
o
i
l
.
2
0
1
5
:
1
-
5.
[1
3
]
Ata
y
M
,
Ya
l
c
i
n
M
E.
A
p
a
r
a
l
l
e
l
i
z
e
d
d
i
s
t
a
n
c
e
tra
n
s
fo
rm
a
t
i
o
n
a
rc
h
i
te
c
tu
re
fo
r
FPGA
s
.
2
0
1
3
Eu
ro
p
e
a
n
Con
fe
re
n
c
e
o
n
Ci
r
c
u
i
t
Th
e
o
ry
a
n
d
De
s
i
g
n
(ECCTD).
Dres
d
e
n
.
2
0
1
3
:
1
-
4.
[1
4
]
So
n
TN.
Eff
i
c
i
e
n
t
i
m
p
l
e
m
e
n
t
a
t
i
o
n
o
f
a
fra
c
ta
l
c
o
l
o
r
i
m
a
g
e
c
o
m
p
re
s
s
i
o
n
o
n
FPGA
.
2
0
1
3
I
n
t
e
rn
a
ti
o
n
a
l
Con
fe
re
n
c
e
o
n
So
ft
Co
m
p
u
t
i
n
g
a
n
d
P
a
tt
e
r
n
Re
c
o
g
n
i
ti
o
n
(So
CPaR)
.
Han
o
i
.
2
0
1
3
:
1
8
4
-
1
8
9
.
[1
5
]
M
a
n
u
KS,
Re
k
h
a
KR,
Nat
a
r
a
j
KR.
FPGA
Im
p
l
e
m
e
n
ta
t
i
o
n
o
f
Im
a
g
e
Bl
o
c
k
G
e
n
e
ra
t
i
o
n
a
n
d
Co
l
o
r
Sp
a
c
e
Co
n
v
e
r
s
i
o
n
fo
r
th
e
G
a
u
s
s
i
a
n
M
i
x
t
u
re
M
o
d
e
l
.
2
0
1
7
In
te
r
n
a
ti
o
n
a
l
Co
n
fe
r
e
n
c
e
o
n
Rec
e
n
t
Ad
v
a
n
c
e
s
i
n
El
e
c
tro
n
i
c
s
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(I
C
RAEC
T).
Ba
n
g
a
l
o
re
.
2
0
1
7
:
2
4
-
28.
[1
6
]
Ry
o
o
J
R,
L
e
e
ES,
Pa
rk
HK.
Rea
l
-
ti
m
e
i
m
p
l
e
m
e
n
ta
t
i
o
n
o
f
a
n
L
UT
-
b
a
s
e
d
i
m
a
g
e
warp
i
n
g
s
y
s
te
m
.
IEEE
ISR 2
0
1
3
.
Se
o
u
l
.
2
0
1
3
:
1
-
4.
[1
7
]
Ki
ra
n
S,
Na
d
h
i
n
i
S,
J
a
y
a
J
.
De
s
i
g
n
a
n
d
i
m
p
l
e
m
e
n
t
a
ti
o
n
o
f
FP
G
A
b
a
s
e
d
i
n
v
i
s
i
b
l
e
i
m
a
g
e
wat
e
rm
a
rk
i
n
g
e
n
c
o
d
e
r
u
s
i
n
g
wav
e
l
e
t
tr
a
n
s
fo
rm
a
ti
o
n
.
2
0
1
3
In
te
rn
a
ti
o
n
a
l
Con
fe
r
e
n
c
e
o
n
Curr
e
n
t
Tre
n
d
s
i
n
En
g
i
n
e
e
ri
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
(I
CC
TET
)
.
Coi
m
b
a
to
r
e
.
2
0
1
3
:
3
2
3
-
3
2
5
.
[1
8
]
M
i
c
h
a
l
i
k
S,
M
i
c
h
a
l
i
k
S,
Nag
h
m
o
u
c
h
i
J
,
Be
r
e
k
o
v
i
c
M
.
R
e
a
l
-
Ti
m
e
s
m
a
rt
s
te
r
e
o
c
a
m
e
ra
b
a
s
e
d
o
n
FPGA
-
So
C
.
2
0
1
7
IEEE
-
RAS
1
7
th
In
te
r
n
a
ti
o
n
a
l
Con
fe
re
n
c
e
o
n
Hum
a
n
o
i
d
Ro
b
o
ti
c
s
(H
u
m
a
n
o
i
d
s
)
.
Bi
rm
i
n
g
h
a
m
.
2
0
1
7
:
3
1
1
-
3
1
7
.
[1
9
]
J
i
n
KC,
L
e
e
KS,
K
i
m
G
H.
Hi
g
h
-
s
p
e
e
d
FPGA
-
G
PU
p
ro
c
e
s
s
i
n
g
fo
r
3
D
-
O
CT
i
m
a
g
i
n
g
.
2
0
1
7
3
rd
IEE
E
In
te
rn
a
ti
o
n
a
l
Co
n
fe
re
n
c
e
o
n
C
o
m
p
u
te
r a
n
d
Co
m
m
u
n
i
c
a
ti
o
n
s
(ICCC
)
.
Che
n
g
d
u
.
2
0
1
7
:
2
0
8
5
-
2088.
[2
0
]
Xu
Y,
Zh
o
u
Q
,
G
o
n
g
L
,
Zh
u
M
,
Din
g
X,
Te
n
g
RKF.
Hi
g
h
-
Sp
e
e
d
S
i
m
u
l
ta
n
e
o
u
s
I
m
a
g
e
Dis
to
rt
i
o
n
Corre
c
ti
o
n
Tra
n
s
fo
r
m
a
ti
o
n
s
fo
r
a
M
u
l
t
i
c
a
m
e
r
a
Cy
l
i
n
d
ri
c
a
l
P
a
n
o
ra
m
a
Re
a
l
-
t
i
m
e
Vi
d
e
o
S
y
s
te
m
U
s
i
n
g
FPGA
.
IEEE
Tra
n
s
a
c
ti
o
n
s
o
n
Cir
c
u
i
t
s
a
n
d
S
y
s
t
e
m
s
f
o
r V
i
d
e
o
T
e
c
h
n
o
l
o
g
y
.
2
0
1
4
;
2
4
(6
)
:
1
0
6
1
–
1
0
6
9
.
[2
1
]
M
a
z
i
n
a
n
AH,
Es
m
a
e
i
l
i
A.
A
n
a
l
g
o
r
i
th
m
fo
r
e
x
tr
a
c
t
i
n
g
th
e
p
h
a
s
e
o
f
th
e
fri
n
g
e
p
a
tt
e
r
n
s
wit
h
i
t
s
a
p
p
l
i
c
a
t
i
o
n
s
to
th
re
e
-
d
i
m
e
n
s
i
o
n
a
l
i
m
a
g
i
n
g
th
ro
u
g
h
FPGA
b
a
s
e
d
i
m
p
l
e
m
e
n
t
a
ti
o
n
.
2
0
1
6
I
n
te
rn
a
t
i
o
n
a
l
Con
fe
re
n
c
e
o
n
I
n
d
u
s
tri
a
l
I
n
fo
r
m
a
ti
c
s
a
n
d
C
o
m
p
u
te
r S
y
s
t
e
m
s
(CII
CS).
Sh
a
rj
a
h
.
2
0
1
6
:
1
-
5.
[2
2
]
Fri
d
N,
M
l
i
n
a
ri
c
H,
Kn
e
z
o
v
i
c
J
.
Ac
c
e
l
e
ra
ti
o
n
o
f
D
CT
tra
n
s
fo
r
m
a
ti
o
n
i
n
J
PEG
i
m
a
g
e
c
o
n
v
e
r
s
i
o
n
.
2
0
1
3
36
th
In
te
r
n
a
ti
o
n
a
l
Con
v
e
n
ti
o
n
o
n
In
f
o
rm
a
t
i
o
n
a
n
d
Co
m
m
u
n
i
c
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
El
e
c
tr
o
n
i
c
s
a
n
d
M
i
c
r
o
e
l
e
c
tr
o
n
i
c
s
(
M
IPRO
)
.
O
p
a
ti
j
a
.
2
0
1
3
:
1
2
9
2
-
1
2
9
5
.
[2
3
]
Pa
d
m
a
v
a
t
i
S,
M
e
s
h
r
a
m
V,
J
a
y
a
d
e
v
a
p
p
a
.
A
h
a
rd
ware
i
m
p
l
e
m
e
n
t
a
ti
o
n
o
f
d
i
s
c
re
te
wav
e
l
e
t
tra
n
s
fo
rm
fo
r
c
o
m
p
re
s
s
i
o
n
o
f
a
n
a
tu
ra
l
i
m
a
g
e
.
2
0
1
7
In
te
r
n
a
ti
o
n
a
l
Con
fe
re
n
c
e
o
n
Al
g
o
r
i
th
m
s
,
M
e
th
o
d
o
l
o
g
y
,
M
o
d
e
l
s
a
n
d
A
p
p
l
i
c
a
ti
o
n
s
i
n
E
m
e
rg
i
n
g
T
e
c
h
n
o
l
o
g
i
e
s
(I
CA
M
M
AET)
.
Che
n
n
a
i
.
2
0
1
7
:
1
-
5.
[2
4
]
Ta
h
e
r
F,
Za
k
i
A,
E
l
s
i
m
a
r
y
H
.
Des
i
g
n
o
f
l
o
w
p
o
wer
FPGA
a
rc
h
i
te
c
tu
r
e
o
f
i
m
a
g
e
u
n
i
t
fo
r
s
p
a
c
e
a
p
p
l
i
c
a
t
i
o
n
s
.
2
0
1
6
IEEE
5
9
th
I
n
te
rn
a
t
i
o
n
a
l
M
i
d
we
s
t
Sy
m
p
o
s
i
u
m
o
n
Cir
c
u
i
ts
a
n
d
Sy
s
te
m
s
(
M
WSCAS)
.
Ab
u
Dh
a
b
i
.
2
0
1
6
:
1
-
4.
[2
5
]
Ba
b
u
L
,
Nm
L
.
FPGA
Im
p
l
e
m
e
n
ta
ti
o
n
o
f
En
e
rg
y
Eff
i
c
i
e
n
t
A
p
p
ro
x
i
m
a
te
M
u
l
t
i
p
l
i
e
r
wit
h
Im
a
g
e
Pro
c
e
s
s
i
n
g
.
2
0
1
8
2
nd
I
n
te
rn
a
t
i
o
n
a
l
Con
fe
re
n
c
e
o
n
Tre
n
d
s
i
n
El
e
c
tr
o
n
i
c
s
a
n
d
In
f
o
rm
a
ti
c
s
(ICO
EI)
.
Ti
ru
n
e
l
v
e
l
i
.
2
0
1
8
:
6
3
7
-
6
4
1
.
[2
6
]
Cha
p
m
a
n
K.
P
i
c
o
B
l
a
z
e
DS2
4
3
2
Co
m
m
u
n
i
c
a
to
r.
X
i
l
i
n
x
L
td
.
6
th
Ap
ri
l
2
0
0
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.