1 / 28

Optimization & Learning for Registration of Moving Dynamic Textures

Optimization & Learning for Registration of Moving Dynamic Textures. Junzhou Huang 1 , Xiaolei Huang 2 , Dimitris Metaxas 1 Rutgers University 1 , Lehigh University 2. Outline. Background Goals & Problems Related Work Proposed Method Experimental Results Discussion & Conclusion.

Download Presentation

Optimization & Learning for Registration of Moving Dynamic Textures

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. Optimization & Learning for Registration of Moving Dynamic Textures Junzhou Huang1, Xiaolei Huang2, Dimitris Metaxas1 Rutgers University1, Lehigh University2

  2. Outline • Background • Goals & Problems • Related Work • Proposed Method • Experimental Results • Discussion & Conclusion

  3. Background • Dynamic Textures (DT) • static camera, exhibiting certain stationary properties • Moving Dynamic Textures (MDT) • dynamic textures captured by a moving camera DT [Kwatra et al. SIGGRAPH’03] MDT [Fitzgibbbon ICCV’01]

  4. Background • Video registration • Required by many video analysis applications • Traditional assumption • Static, rigid, brightness constancy • Bergen et al. ECCV’92, Black et al. ICCV’93 • Relaxing rigidity assumption • Dynamic textures • Fitzgibbon, ICCV’01; Doretto et al. IJCV’03; Yuan et al. ECCV’04; Chan et al. NIPS’05; Vidal et al. CVPR’05; Lin et al. PAMI’07; Rav-Acha et al. Dynamic Vision Workshop at ICCV’05; Vidal et al. ICCV’07

  5. Our Goal • Registration of Moving Dynamic Textures • Recover the camera motion and register image frames in the MDT image sequence Translation to the left Translation to the right

  6. Complex Optimization Problem • Complex optimization • W.r.t. camera motion, dynamic texture model • Chicken-and-Egg Problem • Challenges • About the mean images • About Linear Dynamic System (LDS) model • About the camera motion

  7. Related Works • Fitzgibbon, ICCV’01 • Pioneering attempt • Stochastic rigidity • Non-linear optimization • Vidal et al. CVPR’05 • Time varying LDS model • Static assumption in small time windows • Simple and general framework but often under-estimate motion

  8. Formulation • Registration of MDT • I(t), the video frame • , camera motion parameters • y0 , the desired average image of the video • y(t), appearance of DT • x(t), dynamics of DT

  9. Generative Model Generative image model for a MDT

  10. First Observation • Good registration • A good registration according to the accurate camera motion should simplify the dynamic texture model while preserving all useful information • Used by Fitzgibbon, ICCV’01, Minimizing the entropy function of an auto regressive process • Used by Vidal, CVPR’05, optimizing time varying LDS model by optimizing piecewise LDS model

  11. Second Observation • Good registration • A good registration according to the accurate camera motion should lead to a sharp average image whose statistics of derivative filters are similar to those of the input image frames. • Statistics of derivative filters in images • Student-t distribution/heavy-tailed image priors • Huang et al. CVPR’99, Roth et al. CVPR’05

  12. Prior Models • The Average Image Prior • The Motion Prior • The Dynamics Prior

  13. Average Image Priors • Student-t distribution • Model parameters / contrastive divergence method (a) Before registration, (b) In the middle of registration (c) After registration

  14. Motion / Dynamics Priors • Gaussian Perturbation (Motion) • Uncertainty in the motion is modeled by a Gaussian perturbation about the mean estimation M0 with the covariance matrix S ( a diagonal matrix) • Motivated by the work [Pickup et al. NIPS’06] • GPDM / MAR model (Dynamic) • Marginalizing over all possible mappings between appearance and dynamics • Motivated by the work [Wang et al. NIPS’05], [Moon et al. CVPR’06]

  15. Joint Optimization • Generative image model • Optimization • Final marginal likelihood • Scaled conjugate gradients algorithm (SCG)

  16. Procedures • Obtaining image derivative prior model • Dividing the long sequence into many short image sequences • Initialization for video registration • Performing model optimization with the proposed prior models until model convergence. • With estimated y0, Y and X, the camera motion is then obtained iteratively by Maximum Likelihood estimation using SCG optimization

  17. Obtaining Data • Three DT video sequences • DT data [Kwatra et al. SIGGRAPH’03] • Synthesized MDT video sequence • 60 frames each, no motion from 1st to 20th frame and from 41st to 60th • Camera motion with speed [1, 0] from 21st to 40th

  18. Grass MDT Video • The average image (a) One frame, (b) the average image after registration, (c) average image before registration

  19. Grass MDT Video • The statistics of derivative filter responses

  20. Evaluation / Comparison • False Estimation Fraction • Comparison with two classical methods • Hybrid method, [Bergen et al. ECCV’92] [Black et al. ICCV’93] • Vidal’method, [Vidal et al. CVPR’05]

  21. Waterfall MDT Video • Motion estimation • Ground truth, (b) by hybrid method, (c) by Vidal’s, (d) by our method

  22. Waterfall MDT Video • The average Image and its statistics The average image and its derivative filter response distribution after registration by: (a) our method, (b) Vidal’s method, (c) hybrid method

  23. FEF Comparison • On three synthesized MDT video

  24. Experiment on real MDT Video • Moving flower bed video • 554 frames total • Ground truth motion 110 pixels • Estimation 104.52 pixels ( FEF 4.98%)

  25. Conclusions • Proposed: • Powerful priors for MDT registration • Solution for: • Camera motion, Average image of video, Dynamic texture model • What have we learned? • Correct registration simplifies DT model while preserving useful information • Better registration leads to sharper average image

  26. Thank you !

  27. Future work • More complex camera motion • Different metrics for performance evaluation • Multiple dynamic texture segmentation

  28. Experiment on real MDT Video • Moving flower bed video • Our method • 554 frames total • Ground truth motion 110 pixels • Estimation 104.52 pixels ( FEF 4.98%) • Vidal’s method • 250 frames [Vidal et al. CVPR’05] • Ground truth motion 85 pixels • Estimation 60 pixels (FEF 29.41%)

More Related