1 / 35

Computer Vision and Robotics

Computer Vision and Robotics. Introduction to Artificial Intelligence CS440/ECE448 Lecture 27 1-unit projects for grad students: Get in touch with me ! Last homework out today!! Next Tuesday: Review (everything since mid-term) Final: May 8, 1:30 to 3pm, here. Last lecture.

nedra
Download Presentation

Computer Vision and Robotics

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. Computer Visionand Robotics Introduction to Artificial Intelligence CS440/ECE448 Lecture 27 1-unit projects for grad students: Get in touch with me ! Last homework out today!! Next Tuesday: Review (everything since mid-term) Final: May 8, 1:30 to 3pm, here

  2. Last lecture • Support vectors machines This lecture • Computer vision • Robotics Reading • Chapters 24 and 25

  3. support hyperplanes Linearly Separable Classes support vectors What is the maximum-margin separating plane?

  4. w.x+b = 1 w.x+b = -1 Support Vector Machines (Boser, Guyon & Vapnik, 1992; Vapnik 1995) w.x+b = 0 positive examples negative examples What is the maximum-margin separating plane?

  5. Support vector machines ctd • Examples are of the form ( xi, yi ), where yi = ¨ 1. • They all verify yi ( w.xi + b ) ≥ 1. • The distance between the separating plane is 2 / | w |. • Thus finding the maximum margin plane amounts to • Minimizing: ½ | w |^2 • subject to: yi ( w.xi + b ) ≥ 1 for i = 1, … ,n. • A quadratic programming problem!

  6. Support Vector Machines ctd The dual formulation of the problem is: • Maximize: i=1ni -1/2 i,j=1nyiyjij ( xi¢xj ) • subject to: i=1nyii =0, and i≥ 0 for i=1, … , n. Note 1: The weitghts i are nonzero only for support vectors. Note 2: The data points only appear in the optimization problem via their dot product K( xi , xj ) = xi¢xj . Note 3: This allows classes that are not linearly separable to be handled via nonlinear mappings and appropriate kernelsK.

  7. non-linear mapping ( X1, X2, X3 ) Kernel Machines x12+x22=1 X1+X2=1 ( x1, x2)

  8. Computer Vision

  9. Computer Vision Tasks • Stereo, structure from motion, shape from X: What is the 3D shape of the objects present in the image? • Segmentation: Separate objects from background. • Recognition: Identify the objects present in the image.

  10. Pompei painting, 2000 years ago. Brunelleschi, 1415 Van Eyk, XIVth Century Massaccio’s Trinity, 1425

  11. Pinhole Perspective Equation NOTE:z is always negative..

  12. Affine projection models: Weak perspective projection is the magnification. When the scene relief is small compared its distance from the Camera, m can be taken constant: weak perspective projection.

  13. Affine projection models: Orthographic projection When the camera is at a (roughly constant) distance from the scene, take m=1.

  14. What is the image of a sphere? Planar pinhole perspective Orthographic projection Spherical pinhole perspective

  15. Diffraction effects in pinhole cameras. Shrinking pinhole size Use a lens!

  16. Lenses Snell’s law n1 sina1 = n2 sin a2 Descartes’ law

  17. E=(P/4) [ (d/z’)2 cos4a ] L

  18. Vignetting

  19. Photography (Niepce, “La Table Servie,” 1822) Milestones: • Daguerréotypes (1839) • Photographic Film (Eastman, 1889) • Cinema (Lumière Brothers, 1895) • Color Photography (Lumière Brothers, 1908) • Television (Baird, Farnsworth, Zworykin, 1920s) CCD and CMOS Devices (1970)

  20. Image Formation: Radiometry The light source(s) The sensor characteristics The surface normal The surface properties The optics What determines the brightness of an image pixel?

  21. How do we perceive depth?

  22. (Binocular) Fusion

  23. 2 Minimize |w-w’|. Correlation Methods (1970--) Slide the window along the epipolar line until w.w’ is maximized. Normalized Correlation: minimize q instead.

  24. (Devernay and Faugeras, 1994)

  25. (Furukawa & Ponce, 2006)

  26. Koenderink (1984)

  27. (Rousson and Deriche, 2002)

  28. Human/Felix Bug Barbara Steele Face Joe Camel Problem: Recognizing instances Recognizing categories

  29. What we can do today (Rothganger et al. 2004)

  30. Candidate parts Matching Response scores Part dictionary Validation images Learning validation images Classifier Valildation parts Test image Part detection Testing response vector Decision First steps toward category-level object recognition (Lazebnik et al., 2006) Training pairs … … … …

  31. What is an object?

  32. The interaction of light and matter

  33. ILM Toyota What is it all for?

  34. Copan Courtesy of S. Leigh Courtesy of G. Robinson & M.S. Sharma

More Related