1 / 72

Lecture 15-16 Pose Estimation – Gaussian Process

EE4-62 MLCV. Lecture 15-16 Pose Estimation – Gaussian Process. Tae-Kyun Kim. EE4-62 MLCV. MS KINECT http://www.youtube.com/watch?v=p2qlHoxPioM. The KINECT body pose estimation is achieved by randomised regression forest techniques. EE4-62 MLCV.

zinna
Télécharger la présentation

Lecture 15-16 Pose Estimation – Gaussian Process

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. EE4-62 MLCV Lecture 15-16 Pose Estimation – Gaussian Process Tae-Kyun Kim

  2. EE4-62 MLCV MS KINECThttp://www.youtube.com/watch?v=p2qlHoxPioM The KINECT body pose estimation is achieved by randomised regression forest techniques.

  3. EE4-62 MLCV We learn pose estimation as a regression problem, and Gaussian process as a cutting edge regression method. We see it through the case study (slide credits to): Semi-supervised Multi-valued Regression, Navaratnam, Fitzgibbon, Cipolla, ICCV07, wherepractical challenges addressed are 1)multi-valued regression and 2)sparsity of data.

  4. EE4-62 MLCV A mapping function is learnt from the input image I to the pose vector , which is taken as a continuous variable.

  5. Given an image (top left) , e.g. a silhouette (top right) is obtained by background subtraction techniques (http://en.wikipedia.org/wiki/Background_subtraction). The estimated 3d pose is shown at two camera angels (bottom left and right). EE4-62 MLCV

  6. We attempt to map 2D image space to 3D pose space. There is inherent ambiguity in pose estimation (as an example in the above). EE4-62 MLCV

  7. Eye tracking can be tackled as a regression problem, where the input is an image I and the output is a eye location. EE4-62 MLCV

  8. Typical image processing steps: Given an image, a silhouette is segmented. A shape descriptor is applied to the silhouette to yield a finite dimensional vector. (Belongie and Malik, Matching with Shape Contexts, 2000) EE4-62 MLCV

  9. The output is a vector of m joint angles. EE4-62 MLCV

  10. EE4-62 MLCV

  11. EE4-62 MLCV

  12. EE4-62 MLCV

  13. EE4-62 MLCV

  14. EE4-62 MLCV

  15. EE4-62 MLCV Gaussian Process

  16. EE462 MLCV Review of Gaussian density estimation(lecture 1,2) i.i.d. (independent identical distributed) We want to find the Gaussian parameters from the given data. The problem is to find the parameters by maximising the posterior probability

  17. EE462 MLCV Review of Gaussian density estimation(lecture 1,2) We do not have priors on the parameters and data, thus we maximise the (log) likelihood function instead. Maximum Likelihood (ML) vs Maximum A Posterior (MAP) solutions: P(X|Y)P(Y) (e.g. Gaussian Process) P(X|Y)

  18. EE462 MLCV Review of polynomial curve fitting (lecture 1,2) We want to fit a polynomial curve to given data pairs (x,t). = = where The objective ftn to minimise is

  19. EE4-62 MLCV Gaussian Processes

  20. EE4-62 MLCV

  21. EE4-62 MLCV

  22. EE4-62 MLCV

  23. EE4-62 MLCV Gaussian Processes for Regression

  24. EE4-62 MLCV

  25. EE4-62 MLCV

  26. EE4-62 MLCV

  27. EE4-62 MLCV

  28. EE4-62 MLCV

  29. EE4-62 MLCV

  30. EE4-62 MLCV

  31. Gaussian Process MatlabToolboxhttp://www.lce.hut.fi/research/mm/gpstuff/install.shtml(try demo_regression_robust.m, demo_regression1.m)

  32. EE4-62 MLCV Learning Hyperparameters

  33. EE4-62 MLCV Automatic Relevance Determination

  34. Back to the pose estimation problem

  35. EE4-62 MLCV

  36. It’ll never work… • is multivalued • and live in high dimensions EE4-62 MLCV

  37. EE4-62 MLCV

  38. EE4-62 MLCV

  39. EE4-62 MLCV

  40. EE4-62 MLCV

  41. EE4-62 MLCV

  42. EE4-62 MLCV

  43. GMM : Gaussian Mixture Model GPLVM : Gaussian Process Latent Variable Model EE4-62 MLCV

  44. EE4-62 MLCV

  45. EE4-62 MLCV

  46. EE4-62 MLCV

More Related