1 / 25

Image Registration

Image Registration. Vlad Magdin York University December 7, 2007. Motivation. Two sources for difference between frames Object motion Camera motion Motion is a powerful cue for detection Can detect moving objects if camera motion is eliminated via frame differencing. Motivation.

vervin
Download Presentation

Image Registration

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. Image Registration • Vlad Magdin • York University • December 7, 2007

  2. Motivation • Two sources for difference between frames • Object motion • Camera motion • Motion is a powerful cue for detection • Can detect moving objects if camera motion is eliminated via frame differencing

  3. Motivation Video Frame F(t) Video Frame F(t+1)

  4. Without Registration Frame Difference {F(t+1)-F(t)}

  5. With Registration Frame Difference {F(t+1)-F(t)}

  6. Registration Approaches • Global - directly compute transformation parameters • e.g. Direct Optimization • Feature-based - compute transformation parameters from a set of matching points • e.g. Optic Flow (Lucas Kanade)

  7. Implemented Methods • Search methods: • Direct Optimization • SIFT-based Feature Registration • Lucas-Kanade Optic Flow • Transformation types • Affine • Projective • 2nd Order

  8. Transformation Types • Affine transformation - 6 parameters

  9. Transformation Types • Projective transformation - 8 parameters

  10. Transformation Types • 2nd Order transformation - 8 parameters

  11. Transformation of Choice • 2nd Order transformation - 8 parameters

  12. Error Measure Frame Difference {F(t+1)-F(t)}

  13. Optimization Approach • Algorithm • Given two video frames • Use an optimization routine to iteratively compute a transformation matrix based on an error measure (SSD)

  14. SIFT-Based Method • SIFT (Scale Invariant Feature Transform, Lowe 2004) • Invariant to scale, rotation, illumination change • Feature Selection Algorithm • Laplacian Pyramid - compute a multi-resolution representation of an image • Keypoints - locate extrema in the Laplacian Pyramid • SIFT Descriptors - compute histograms of gradients around each keypoint

  15. SIFT-Based Approach

  16. Optic Flow Approach • Algorithm • Estimate displacement vectors of pixels from spatial and temporal image gradients • Compute a transformation matrix by thinking of each pixel as a feature

  17. Optic Flow Approach • Algorithm • Estimate displacement vectors of windows from spatial and temporal image gradients • Compute a transformation matrix by thinking of each window as a feature

  18. Optic Flow Approach • For each window, compute: • Ix, Iy : spatial gradientsIt : temporal gradient • v = Ge

  19. Optic Flow Approach

  20. Optic Flow Approach • For each window, compute: • Not all windows are kept: • Windows that lead to ill-posed solutions to “v = Ge” (2nd eigenvalue of G is too small) • Windows that lead to large errors • Windows that fall within boundaries of better windows

  21. Quantitative Comparison

  22. Qualitative Comparison Video Frame F(t) Video Frame F(t+1)

  23. Qualitative Comparison

  24. Final Comments • Optimization Approach+ relatively good performance- poor speed- initial parameter guess is important • Feature-based Approach+ (relatively) fast- can sometimes select moving objects as features • Optic Flow Approach+ (relatively) fast+ best performance

  25. Demo

More Related