1 / 20

Motion Detection in Vision Processing

Exploring how motion is perceived in computer vision through concepts like counterphase sin grating and spatio-temporal patterns. Discusses the Reichardt detector, gradient correlation, spatiotemporal filters, and Gabor functions. Unifying models for motion perception are detailed with a focus on spatial and temporal responses. Highlights the importance of evolutionary motion detection and the complexity of higher processing levels.

akurt
Download Presentation

Motion Detection in Vision Processing

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. Sensing and Perceiving Motion Cmput 610 Martin Jagersand 2001

  2. How come perceived as motion? Im = sin(t)U5+cos(t)U6 Im = f1(t)U1+…+f6(t)U6

  3. Counterphase sin grating • Spatio-temporal pattern • Time t, Spatial x,y

  4. Counterphase sin grating • Spatio-temporal pattern • Time t, Spatial x,y Ignoring Phi: = +

  5. Notes: • Only one term: Motion left or right • Mixture of both: Standing wave • Direction can flip between left and right

  6. QT movie Reichardt detector

  7. Gradient: in Computer Vision Correlation: In bio vision Spatiotemporal filters: Unifying model Severalmotion models

  8. Spatial response:Gabor function • Definition:

  9. Temporal response: Adelson, Bergen ’85 Note: Terms from taylor of sin(t) Spatio-temporal D=DsDt

  10. Receptor response toCounterphase grating • Separable convolution

  11. Simplified: • For our grating: (Theta=0) • Write as sum of components: = exp(…)*(acos… + bsin…)

  12. Space-time receptive field

  13. Combined cells • Spat: Temp: • Both: • Comb:

  14. Result: • More directionally specific response

  15. Energy model: • Sum odd and even phase components • Quadrature rectifier

  16. Adaption:Motion aftereffect

  17. Where is motion processed?

  18. Higher effects:

  19. Equivalence:Reich and Spat

  20. Conclusion • Evolutionary motion detection is important • Early processing modeled by Reichardt detector or spatio-temporal filters. • Higher processing poorly understood

More Related