lecture motion
play

Lecture: Motion Juan Carlos Niebles and Ranjay Krishna Stanford - PowerPoint PPT Presentation

Motion Lecture: Motion Juan Carlos Niebles and Ranjay Krishna Stanford Vision and Learning Lab 19-Nov-2019 1 St Stanfor ord University CS 131 Roadmap Motion Pixels Segments Images Videos Web Neural networks Convolutions Recognition


  1. Motion Lecture: Motion Juan Carlos Niebles and Ranjay Krishna Stanford Vision and Learning Lab 19-Nov-2019 1 St Stanfor ord University

  2. CS 131 Roadmap Motion Pixels Segments Images Videos Web Neural networks Convolutions Recognition Resizing Motion Convolutional Edges Detection Segmentation Tracking neural networks Descriptors Machine learning Clustering 19-Nov-2019 2 St Stanfor ord University

  3. What will we learn today? • Optical flow • Lucas-Kanade method • Pyramids for large motion Motion • Horn-Schunk method • Common fate • Applications 19-Nov-2019 Reading: [Szeliski] Chapters: 8.4, 8.5 [Fleet & Weiss, 2005] http://www.cs.toronto.edu/pub/jepson/teaching/vision/2503/opticalFlow.pdf 3 St Stanfor ord University

  4. What will we learn today? • Optical flow • Lucas-Kanade method • Pyramids for large motion Motion • Horn-Schunk method • Common fate • Applications 19-Nov-2019 Reading: [Szeliski] Chapters: 8.4, 8.5 [Fleet & Weiss, 2005] http://www.cs.toronto.edu/pub/jepson/teaching/vision/2503/opticalFlow.pdf 4 St Stanfor ord University

  5. From images to videos • A video is a sequence of frames captured over time • Now our image data is a function of space (x, y) and time (t) Motion 19-Nov-2019 5 St Stanfor ord University

  6. Why is motion useful? Motion 19-Nov-2019 6 St Stanfor ord University

  7. Why is motion useful? Motion 19-Nov-2019 7 St Stanfor ord University

  8. Optical flow • Definition: optical flow is the apparent motion of brightness patterns in the image Motion • Note: apparent motion can be caused by lighting changes without any actual motion – Think of a uniform rotating sphere under fixed lighting vs. a stationary sphere under moving illumination 19-Nov-2019 Source: Silvio Savarese GOAL: Recover image motion at each pixel from optical flow 8 St Stanfor ord University

  9. Optical flow Vector field function of the spatio-temporal image brightness variations Motion 19-Nov-2019 Picture courtesy of Selim Temizer - Learning and Intelligent Systems (LIS) Group, MIT 9 St Stanfor ord University

  10. Estimating optical flow Motion I ( x , y , t ) I ( x , y , t+1 ) • Given two subsequent frames, estimate the apparent motion field u(x,y), v(x,y) between them • Key assumptions 19-Nov-2019 Source: Silvio Savarese • Brightness constancy: projection of the same point looks the same in every frame • Small motion: points do not move very far • Spatial coherence: points move like their neighbors 10 St Stanfor ord University

  11. Key Assumptions: small motions Motion 19-Nov-2019 11 St Stanfor ord University * Slide from Michael Black, CS143 2003

  12. Key Assumptions: spatial coherence Motion 19-Nov-2019 12 St Stanfor ord University * Slide from Michael Black, CS143 2003

  13. Key Assumptions: brightness Constancy Motion 19-Nov-2019 𝐽 𝑦, 𝑧, 𝑢 = 𝐽(𝑦 + 𝑣 𝑦, 𝑧 , 𝑧 + 𝑤 𝑦, 𝑧 , 𝑢 + 1) 13 St Stanfor ord University * Slide from Michael Black, CS143 2003

  14. The brightness constancy constraint I ( x , y , t ) I ( x , y , t+1 ) Motion • Brightness Constancy Equation: 𝐽 𝑦, 𝑧, 𝑢 = 𝐽(𝑦 + 𝑣, 𝑧 + 𝑤, 𝑢 + 1) Linearizing the right side using Taylor expansion: Image derivative along x Image derivative along t 19-Nov-2019 𝐽 𝑦 + 𝑣, 𝑧 + 𝑤, 𝑢 + 1 ≈ 𝐽 𝑦, 𝑧, 𝑢 + 𝐽 . / 𝑣 + 𝐽 0 / 𝑤 + 𝐽 1 Source: Silvio Savarese 𝐽 𝑦 + 𝑣, 𝑧 + 𝑤, 𝑢 + 1 − 𝐽 𝑦, 𝑧, 𝑢 ≈ 𝐽 . / 𝑣 + 𝐽 0 / 𝑤 + 𝐽 1 T + I t = 0 × + × + » Hence, I u I v I 0 [ ] → ∇ I ⋅ u v x y t 14 St Stanfor ord University

  15. Filters used to find the derivatives Motion 𝐽 . 𝐽 0 𝐽 1 19-Nov-2019 15 St Stanfor ord University

  16. The brightness constancy constraint Can we use this equation to recover image motion (u,v) at each pixel? T + I t = 0 [ ] ∇ I ⋅ u v Motion • How many equations and unknowns per pixel? •One equation (this is a scalar equation!), two unknowns (u,v) The component of the flow perpendicular to the gradient (i.e., parallel to the edge) cannot be measured ∇𝐽 gradient 19-Nov-2019 ( u , v ) Source: Silvio Savarese If ( u , v ) satisfies the equation, ( u + u ’, v + v ’) ( u ’, v ’) so does ( u+u’ , v+v’ ) if T = 0 edge [ ] ∇ I ⋅ u ' v ' 16 Stanfor St ord University

  17. The aperture problem Motion 19-Nov-2019 Source: Silvio Savarese Actual motion 17 St Stanfor ord University

  18. The aperture problem Motion 19-Nov-2019 Source: Silvio Savarese 18 St Stanfor ord University

  19. The aperture problem Motion 19-Nov-2019 Source: Silvio Savarese Perceived motion 19 St Stanfor ord University

  20. The aperture problem Motion 19-Nov-2019 Source: Silvio Savarese Actual motion 20 St Stanfor ord University

  21. The aperture problem Motion 19-Nov-2019 Source: Silvio Savarese Perceived motion 21 St Stanfor ord University

  22. The barber pole illusion Motion 19-Nov-2019 http://en.wikipedia.org/wiki/Barberpole_illusion 22 St Stanfor ord University

  23. The barber pole illusion Motion 19-Nov-2019 Source: Silvio Savarese http://en.wikipedia.org/wiki/Barberpole_illusion 23 St Stanfor ord University

  24. What will we learn today? • Optical flow • Lucas-Kanade method • Pyramids for large motion Motion • Horn-Schunk method • Common fate • Applications 19-Nov-2019 Reading: [Szeliski] Chapters: 8.4, 8.5 [Fleet & Weiss, 2005] http://www.cs.toronto.edu/pub/jepson/teaching/vision/2503/opticalFlow.pdf 24 St Stanfor ord University

  25. Solving the ambiguity… • How to get more equations for a pixel? • Spatial coherence constraint: Assume the pixel’s neighbors have the same (u,v) • – If we use a 5x5 window, that gives us 25 equations per pixel Motion 19-Nov-2019 Source: Silvio Savarese B. Lucas and T. Kanade. An iterative image registration technique with an application to stereo 25 vision. In Proceedings of the International Joint Conference on Artificial Intelligence , pp. 674– St Stanfor ord University 679, 1981.

  26. Lucas-Kanade flow • Overconstrained linear system: Motion 19-Nov-2019 Source: Silvio Savarese 26 St Stanfor ord University

  27. Lucas-Kanade flow • Overconstrained linear system Motion Least squares solution for d given by 19-Nov-2019 Source: Silvio Savarese The summations are over all pixels in the K x K window 27 St Stanfor ord University

  28. Conditions for solvability – Optimal (u, v) satisfies Lucas-Kanade equation Motion When is This Solvable? • A T A should be invertible • A T A should not be too small due to noise 19-Nov-2019 – eigenvalues l 1 and l 2 of A T A should not be too small Source: Silvio Savarese • A T A should be well-conditioned – l 1 / l 2 should not be too large ( l 1 = larger eigenvalue) Does this remind anything to you? 28 St Stanfor ord University

  29. M = A T A is the second moment matrix ! (Harris corner detector…) Motion • Eigenvectors and eigenvalues of A T A relate to edge direction and magnitude • The eigenvector associated with the larger eigenvalue points in 19-Nov-2019 the direction of fastest intensity change Source: Silvio Savarese • The other eigenvector is orthogonal to it 29 St Stanfor ord University

  30. Interpreting the eigenvalues Classification of image points using eigenvalues of the second moment matrix: l 2 “Edge” l 2 >> l 1 Motion “Corner” l 1 and l 2 are large, l 1 ~ l 2 19-Nov-2019 Source: Silvio Savarese l 1 and l 2 are small “Edge” “Flat” l 1 >> l 2 region l 1 30 St Stanfor ord University

  31. Edge Motion 19-Nov-2019 Source: Silvio Savarese – gradients very large or very small – large l 1 , small l 2 31 St Stanfor ord University

  32. Low-texture region Motion 19-Nov-2019 Source: Silvio Savarese – gradients have small magnitude – small l 1 , small l 2 32 St Stanfor ord University

  33. High-texture region Motion 19-Nov-2019 Source: Silvio Savarese – gradients are different, large magnitudes – large l 1 , large l 2 33 St Stanfor ord University

  34. Errors in Lukas-Kanade What are the potential causes of errors in this procedure? – Assumed A T A is easily invertible Motion – Assumed there is not much noise in the image • When our assumptions are violated – Brightness constancy is not satisfied – The motion is not small 19-Nov-2019 – A point does not move like its neighbors • window size is too large • what is the ideal window size? 34 Stanfor St ord University * From Khurram Hassan-Shafique CAP5415 Computer Vision 2003

  35. Improving accuracy • Recall our small motion assumption I t-1 (x,y) I t-1 (x,y) Motion • This is not exact – To do better, we need to add higher order terms back in: I t-1 (x,y) • This is a polynomial root finding problem 19-Nov-2019 – Can solve using Newton’s method (out of scope for this class) – Lukas-Kanade method does one iteration of Newton’s method • Better results are obtained via more iterations 35 St Stanfor ord University * From Khurram Hassan-Shafique CAP5415 Computer Vision 2003

Recommend


More recommend