1 / 47

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 andy @microstep-mis.com www.microstep-mis.com/~andy. Regular objects. few parameters fully describe the object

una
Download Presentation

Learning Object Representation Andrej Lúčny Department of Applied Informatics

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Learning Object Representation Andrej Lúčny Department of Applied Informatics Faculty of Mathematics, Physics and Informatics Comenius University, Bratislava andy@microstep-mis.com www.microstep-mis.com/~andy

  2. Regular objects few parameters fully describe the object recognize object = specify its parameters

  3. Regular objects e.g. Hough transform Conversion of image to parameters

  4. Image Threearrays r[h,w], g[h,w], b[h,w], values 0..255 corresponding to color ingredients

  5. Red ingredient

  6. Green ingredient

  7. Blue ingredient

  8. bw[i,j] = 0.3*r[i,j] + 0.59*g[i,j] + 0.11*b[i,j] Intensity map

  9. Looking for edges:one line can be represented as a function

  10. intensity column • Edges corresponds to sharp sectors

  11. Sobel operator ai-1,j-1 ai-1,j ai-1,j+1 -1 0 1 = ai,j-1 ai,j ai,j+1 -2 0 2 bi,j º ai+1,j-1 ai+1,j ai+1,j+1 -1 0 1 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 -1 -2 -1 = ai,j-1 ai,j ai,j+1 0 0 0 bi,j º ai+1,j-1 ai+1,j ai+1,j+1 1 2 1 dyi,j= ai+1,j-1+ 2ai+1,j+ai+1,j+1-ai-1,j-1- 2ai-1,j–ai-1,j+1

  12. Sobel operator approximated image derivation (gradient) Concerning a threshold Sobel operator indicates us edges threshold

  13. Sobel operator |dx| |dy|

  14. Sobel operator |grad| = √ (dx + dy ) 2 2

  15. Binary image

  16. Thinning ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ?

  17. Thinning

  18. Hough transform Example: Circle Task: how to turn thinned image to circle parameters Paramaters: • center x-coordinate • center y-coordinate • radius x y r

  19. Hough transform Each parameter has a particular range E.g. for imagewith 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

  20. Hough transform • 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. y r x

  21. Hough transform Circle is recognized !

  22. Irregular objects Parameters of irregular objects are not clear ! It is better look an universal method how to learn their representation

  23. Irregularobjects How such objects are represented? e.g. Dominant orientation templates

  24. Dominant orientation templates (DOT) • Simple but fast and efficient method

  25. Motivation template dealing with thinned edges image

  26. Edges detector Canny intensity |dx| |dy| |gradient| orientations thinned edges

  27. Orientations (dx, dy) 4 3 2 5 6 1 7 0

  28. Template • based on the orientations

  29. Template • object is covered by non-overlapping regions

  30. Template • We concern orientation of any pixel in region, which lies on edge

  31. Template • We select set of dominant (prevailing) orientations

  32. Template • We have such set of few dominant templates for each region

  33. Template • The sets of dominant orientations form the representation of the object

  34. How to use the template • We cover image by regions and select one most dominant orientation for each region template image

  35. How to use template • Object is found if for the most of regions the dominant orientation from image is an element of the setof dominant orientations in template template image

  36. Basic formal expression I – current image O – image from which the template is created c – position on the imageI R – region c + R – corresponding region put to position c DO(O,R) : set of (maximally k) dominant orientations in region R in template, i.e. on the image O do(I,R) : dominant orientation in region R in the current image I do(X, R ) = DO(X, R ) fork = 1 δ(x) = x ? 1 : 0 where x is true or false

  37. 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 …

  38. Advanced formal expression I – current image O – image from which the template is created w(O,M) – image O shifted by M c – position on the imageI R – region, c + R – corresponding region put to position c DO(O,R) : set of (maximally k) dominant orientations in region R in template, i.e. on the image O do(I,R) : dominant orientation in region R in the current image I δ(x) = x ? 1 : 0 where x is true or false

  39. 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 template templates

  40. Formalism of the efficient approach = I – current image O – image from which the template is created w(O,M) – image O shifted by M c – position on the imageI R – region, c + R – corresponding region put to position c DO(O,R) : set of (maximally k) dominant orientations in region R in template, i.e. on the image O do(I,R) : dominant orientation in region R in the current image I δ(x) = x ? 1 : 0 where x is true or false

  41. 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)

  42. 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

  43. 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

  44. 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)

  45. Failure of recognition 1. pattern phantom 2. Failure or creativity ?

  46. 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

  47. Thank you ! Andrej Lúčny Department of Applied Informatics Faculty of Mathematics, Physics and Informatics Comenius University, Bratislava andy@microstep-mis.com www.microstep-mis.com/~andy

More Related