AIBO VISION

builderanthologyAI and Robotics

Oct 19, 2013 (3 years and 10 months ago)

87 views

AIBO VISION

by


Utku Tatlıdede

Kemal Kaplan

AIBO ROBOT


Specifications:


ERS
-
210


CPU clock speed of 192MHZ


20 degrees of freedom


Temperature,Infrared Distance,
Acceleration, Pressure, Vibration
Sensors


CMOS Image Sensor


Miniature Microphones, Miniature
Speaker, LCD Display



Dimensions and Weight:



Size (WxHxL) 6.06" (W) x 10.47" (H) x 10.79" (L)



Weight 3.3 lbs. (1.5kg)


CCD camera


16.8 million colors

(24 bit)


176x144 pixel image


Field

of view 57.6
°

wide and 47.8
°

tall


Up

to 25
fps


Stores
information in
the YUV color space

AIBO VISION


Color Segmentation


-
Representations


-
Algorithms


Region Building and Merging


-

Region Growing


-

Edge detection


Object Recognition



-

Classification



-

Template matching



-

Sanity

check


Bounding Box Creation

PROCESSING OUTLINE


CIE
-
XYZ


RGB


CMY, CMYK


HSV, HSI,
HLS


YIQ


YUV,
YCbCr


LUT

COLOR REPRESENTATION

Color can be physically described
as a spectrum

which is

the
intensity of light at each
wavelength
.




Radiance
:

Energy (W) from light source



Luminance
:

Energy perceived by observer



Brightness
:

Subjective
descriptor


Additive

color
space


Three

primaries
:
red, green, and
blue


Cannot

always
produce a color
equivalent to any
wavelength

RGB (Red, Green, Blue)


Similar to HSV
(Hue,
Saturation,
Value)


Represents
colors
similarly how
the human
eye senses
colors.


HSI (Hue
,
Saturation
,
Intensity)


Similar to
YIQ

and
YCbCr


Used

for the PAL

and SECAM

broadcast
television
system


Amount

of
information
needed to define
a color is greatly
reduced

YUV (
Luminance
,
Chrominance
)

CONVERSIONS

Y

=


.299R + .587G + .114B


U

=
-
.147R
-

.289G + .437B


V

=


.615R
-

.515G
-

.100B



H

=

cos
-
1
([(R
-
B)+(R
-
G)]/2
*
[(R
-
G)
2
+(R
-
B)(G
-
B)]
1/2
)


S

= 1


3[min(R,G,B)]/(R+G+B)


V

= (R+G+B)/3

RGB TO YUV

RGB TO HSV


Can we reduce the color space by using unsupervised
dimension reduction techniques (like PCA)?


Can we use different domains?


For each object, find
the most accurate
subspaces of the
color space to
represent the object.



YUV seems the most
promising color
representation for
our real time
applicaiton.

AIM OF COLOR SEGMENTATION

First label images, then use supervised
pattern recognition techniques. Most
common ones:




C4.5



MLP



KNN

FINDING THE SUBSPACES


Forms a decision tree for classification.


Uses the concept of information gain
(effective decrease in entropy).

C4.5


The MLP network

is suited to a wide range of
applications such as pattern classification

and
recognition
,
interpolation, prediction and
forecasting.

MLP (Multi
-
Layer Perceptron)


K
NN

is a simple algorithm that stores all
available examples and classifies new
instances of the example language based on
a similarity measure.


KNN (
K
-
Nearest Neighbor
)


Condensed
K
NN
: We can reduce the training
set by removing the samples that introduce
no extra information to the system.


CONDENSED KNN


PCA
is

a mathematical procedure that
converts
a number of possibly correlated
variables into a
hopefully
smaller number of
uncorrelated variables called
principal
components
.

PCA (Principal Component Analysis)

REGION BUILDING AND MERGING


RLE

encodes multiple appearances of the
same value
.

RLE (Run Length Encoding)

REGION GROWING


This method
depends on the
satisfactory
selection of a
number of seed
pixels.


This method
may be
performed
before color
segmentation.


Merging algorithms:

in which
neighboring regions are
compared and merged if
they are
similar

enough in
some
features
.



Splitting Algorithms:

in
which large non
-
uniform
regions are broken up into
smaller
regions

which
is
hopefully

uniform.

REGION MERGING AND SPLITTING

OBJECT RECOGNITION

BALL

BEACON

OPPONENT
GOAL



Already done by color segmentation.


Ball: The biggest blob with “ball color”,


Beacons: Two adjecentblobs with beacon
colors, etc.



Unclassified blobs are discarded.


Each object is classified with a
certainty.

CLASSIFICATION


Accomplished by
using convolution or
correlation.


Only
works for
translation

of the
template.


In case of rotation or
size changes, it is
ineffective.


Also

fails
for

partial
views of objects.

TEMPLATE MATCHING


A
series of
sanity check

inspections are
performed by the
AIBO
vision
module
to ensure the
object classification is
logically correct.


Ball cannot be above the goal,


Goals cannot be below the field,


There cannot be two balls, etc.


SANITY CHECK


Requires affine transformations (translation,
rotation, scaling)


Required for calculating distance and position
information


The final products of the vision module are
the bounding boxes of each visible object.

BOUNDING BOX CREATION


Cerberus RoboCup 2002 Team Report


rUNSWift RoboCup 2002 Team Report


NUBots RoboCup 2002 Team Report


CMPack

RoboCup 2002 Team Report


MACHINE LEARNING, Mitchell


MACHINE VISION, Jain, Kasturi, Schunk


REFERENCES

Any Question?

REFERENCES