1. Computer Vision Spring 2006 15-385,-685 Instructor: S. Narasimhan Wean 5403 T-R 3:00pm – 4:20pm Lecture #16

2. Announcements Homework 4 due today. Homework 5 will be out tonight, due in two weeks. Use bboard frequently and visit us during OH.

3. Optical Flow and Motion Lecture #16

4. Optical Flow and Motion We are interested in finding the movement of scene objects from time-varying images (videos). Lots of uses –Track object behavior –Correct for camera jitter (stabilization) –Align images (mosaics) –3D shape reconstruction –Special effects

5. Tracking – Rigid Objects (Simon Baker, CMU)

6. Tracking – Non-rigid Objects (Comaniciu et al, Siemens)

7. Face Tracking (Simon Baker et al, CMU)

8. Applications of Face Tracking User Interfaces: –Mouse Replacement: Head Pose and Gaze Estimation –Automotive: Windshield Displays, Smart Airbags, Driver Monitoring Face Recognition: –Pose Normalization –Model-Based Face Recognition Lipreading/Audio-Visual Speech Recognition Expression Recognition and Deception Detection Rendering and Animation: –Expression Animations and Transfer –Low-Bandwidth Video Conferencing –Audio-Visual Speech Synthesis (Simon Baker, CMU)

9. 3D Structure from Motion (David Nister, Kentucky)

10. 3D Structure from Motion (David Nister, Kentucky)

11. Behavior Analysis (Michal Irani, Weizmann) Query Result

12. Motion Field Image velocity of a point moving in the scene Perspective projection: Motion field Scene point velocity: Image velocity:

13. Optical Flow Motion of brightness pattern in the image Ideally Optical flow = Motion field

14. Optical Flow Motion Field Motion field exists but no optical flow No motion field but shading changes

15. Problem Definition: Optical Flow How to estimate pixel motion from image H to image I? –Find pixel correspondences Given a pixel in H, look for nearby pixels of the same color in I Key assumptions –color constancy: a point in H looks “the same” in image I For grayscale images, this is brightness constancy –small motion: points do not move very far

16. Optical Flow Constraint Equation –Assume brightness of patch remains same in both images: –Assume small motion: (Taylor expansion of LHS upto first order) Optical Flow: Velocities Displacement:

17. Optical Flow Constraint Equation Divide by and take the limit Constraint Equation NOTE: must lie on a straight line We can compute using gradient operators! But, (u,v) cannot be found uniquely with this constraint!

18. Finding Gradients in X-Y-T k k+1 ii+1 j j+1 time x y

19. Optical Flow Constraint Intuitively, what does this constraint mean? –The component of the flow in the gradient direction is determined –The component of the flow parallel to an edge is unknown

20. Optical Flow Constraint

21. Aperture Problem

23. Computing Optical Flow Formulate Error in Optical Flow Constraint: We need additional constraints! Smoothness Constraint (as in shape from shading and stereo): Usually motion field varies smoothly in the image. So, penalize departure from smoothness: Find (u,v) at each image point that MINIMIZES: weighting factor

24. Discrete Optical Flow Algorithm Consider image pixel Departure from Smoothness Constraint: Error in Optical Flow constraint equation: We seek the set that minimize: NOTE: show up in more than one term

25. Discrete Optical Flow Algorithm Differentiating w.r.t and setting to zero: are averages of around pixel Update Rule:

26. Example

27. Optical Flow Result

28. Low Texture Region - Bad – gradients have small magnitude

29. Edges – so,so (aperture problem) – large gradients, all the same

30. High Textured Region - Good – gradients are different, large magnitudes

31. Focus of Expansion (FOE) Motion of object = - (Motion of Sensor) For a given translatory motion and gaze direction, the world seems to flow out of one point (FOE). After time t, the scene point moves to:

32. Focus of Expansion (FOE) As t varies the image point moves along a straight line in the image Focus of Expansion: Lets backtrack time or

33. Focus of Expansion (FOE) - Example http://homepages.inf.ed.ac.uk/rbf/BOOKS/BANDB/LIB/bandb7_12.pdf

34. Revisiting the Small Motion Assumption Is this motion small enough? –Probably not—it’s much larger than one pixel (2 nd order terms dominate) –How might we solve this problem?

35. Reduce the Resolution!

36. image I image H Gaussian pyramid of image HGaussian pyramid of image I image I image H u=10 pixels u=5 pixels u=2.5 pixels u=1.25 pixels Coarse-to-fine Optical Flow Estimation

37. image I image J Gaussian pyramid of image HGaussian pyramid of image I image I image H run iterative OF upsample...... Coarse-to-fine Optical Flow Estimation

38. Image Alignment Goal: Estimate single (u,v) translation (transformation) for entire image

39. Mosaicing (Michal Irani, Weizmann)

40. Mosaicing (Michal Irani, Weizmann)

41. Next Class Structured Light and Range Imaging Reading  Notes