Learning Object Representation Andrej Lúčny Department of Applied Informatics
description
Transcript of Learning Object Representation Andrej Lúčny Department of Applied Informatics
Learning Object Representation
Andrej Lúčny
Department of Applied Informatics
Faculty of Mathematics, Physics and Informatics
Comenius University, Bratislava
www.microstep-mis.com/~andy
Regular objects
few parameters fully describe the object
recognize object = specify its parameters
Regular objects
e.g. Hough transformConversion of image to parameters
Image
Three arrays r[h,w], g[h,w], b[h,w], values 0..255 corresponding to color ingredients
Red ingredient
Green ingredient
Blue ingredient
Intensity map
bw[i,j] = 0.3*r[i,j] + 0.59*g[i,j] + 0.11*b[i,j]
• Looking for edges:one line can be represented as a function
column
inte
nsit
y
• Edges corresponds to sharp sectors
Sobel operator
ai-1,j-1 ai-1,j ai-1,j+1
ai,j-1 ai,j ai,j+1
ai+1,j-1 ai+1,j ai+1,j+1
bi,j
-1 0 1
-2 0 2
-1 0 1
º =
dxi,j = ai-1,j+1 + 2ai,j+1 + ai+1,j+1 - ai-1,j-1 - 2ai,j-1 - ai+1,j-1
ai-1,j-1 ai-1,j ai-1,j+1
ai,j-1 ai,j ai,j+1
ai+1,j-1 ai+1,j ai+1,j+1
bi,j
-1 -2 -1
0 0 0
1 2 1
º =
dyi,j = ai+1,j-1 + 2ai+1,j + ai+1,j+1 - ai-1,j-1 - 2ai-1,j – ai-1,j+1
Sobel operator approximated image derivation (gradient)Concerning a threshold Sobel operator indicates us edges
threshold
Sobel operator
|dx| |dy|
Sobel operator
|grad| = √ (dx + dy )2 2
Binary image
Thinning
? ??
?? ?
?
?
?
? ? ?
? ?
?
??
?
? ?
Thinning
Hough transform
Example: Circle
Task: how to turn thinned image to circle parameters
Paramaters:• center x-coordinate • center y-coordinate• radius
x
y
r
Hough transform
Each parameter has a particular range
E.g. for image with resolution 320 x 240 :• Range of center x-coordinate is 0..319• Range of center y-coordinate is 0..239• Range of radius is 10..200
We evaluate probability of each tupple (x,y,r)
from the given range
Hough transform
x
y
• The probability P[x,y,r] is given by number of witnesses, i.e. white pixels on thinned image which would be white if one draws circle with parameters x,y,r.
r
Hough transform
Circle is recognized !
Irregular objects
Parameters of irregular objects are not clear !
It is better look an universal method how to learn their representation
Irregularobjects
e.g. Dominant orientation templates
How such objects are
represented?
• Simple but fast and efficient method
Dominant orientation templates (DOT)
Motivation
template
image dealing with thinned edges
Edges detector Canny
intensity
|gradient| orientations
|dx|
thinned edges
|dy|
Orientations
(dx, dy)
01
23456
7
Template
• based on the orientations
Template
• object is covered by non-overlapping regions
Template• We concern orientation of any pixel in region,
which lies on edge
Template• We select set of dominant (prevailing)
orientations
Template• We have such set of few dominant
templates for each region
Template• The sets of dominant orientations form the
representation of the object
How to use the template• We cover image by regions and select one most
dominant orientation for each region
template
image
How to use template• Object is found if for the most of regions the dominant
orientation from image is an element of the set of dominant orientations in template
template image
Basic formal expression
I – current imageO – image from which the template is createdc – position on the image IR – region c + R – corresponding region put to position cDO(O,R) : set of (maximally k) dominant orientations in region R in template, i.e. on the image Odo(I,R) : dominant orientation in region R in the current image I do(X, R ) = DO(X, R ) for k = 1 δ(x) = x ? 1 : 0 where x is true or false
Does it work ?• Yes, if we put region R to proper position c• No, otherwise
Therefore we will need more templates for various positioning of regions
templates
positions…
Advanced formal expression
I – current imageO – image from which the template is createdw(O,M) – image O shifted by Mc – position on the image IR – region, c + R – corresponding region put to position cDO(O,R) : set of (maximally k) dominant orientations in region R in template, i.e. on the image Odo(I,R) : dominant orientation in region R in the current image Iδ(x) = x ? 1 : 0 where x is true or false
More effective but less precise approach• We can summarize more overlapping templates to one.• We simply add orientations from overlapping regions.• Such template must fit regardless shifting, but can detect also phantoms
integrated templatetemplates
…
Formalism of the efficient approach
I – current imageO – image from which the template is createdw(O,M) – image O shifted by Mc – position on the image IR – region, c + R – corresponding region put to position cDO(O,R) : set of (maximally k) dominant orientations in region R in template, i.e. on the image Odo(I,R) : dominant orientation in region R in the current image Iδ(x) = x ? 1 : 0 where x is true or false
=
More viewpoints• Still one template represents the object from one viewpoint only• Therefore we need to create more templates from various viewpoints• Again we can integrate more templates which are similar enough to one (in
the same way as shifted templates)
DOT efficiency• Belonging of orientation to a template can be represented by bits
0 or 1 and all DOT can be expressed in form of bit operations • Therefore DOT is very fast and running in real time
Object border• DOT can provide also approximate border of the object.• It is created by those edge pixels for which we have found
their orientation in the template
How to get template?
• Scan object put to contrast scene by camera from various viewpoints (i.e. not in the natural scene but under specific conditions)
or• separate object from scene by another method (e.g. by movement detector)
Failure of recognition
pattern
1.
2.
Failure or creativity ?
phantom
Further study
Hinterstoisser, S. - Lepetit, V. - Ilic, S. - Fua, P. - Navab, N.: Dominant Orientation Templates for Real-Time Detection of Texture-Less Objects. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, California (USA), June 2010
Thank you !
Andrej LúčnyDepartment of Applied Informatics
Faculty of Mathematics, Physics and Informatics
Comenius University, Bratislava
www.microstep-mis.com/~andy