object tracking
play

Object Tracking Computer Vision Fall 2018 Columbia University - PowerPoint PPT Presentation

Object Tracking Computer Vision Fall 2018 Columbia University Homework 5 Released last night Due November 26th Start it today no extensions! Optical Flow Optical flow field: assign a flow vector to each pixel Visualize:


  1. Object Tracking Computer Vision Fall 2018 Columbia University

  2. Homework 5 • Released last night • Due November 26th • Start it today— no extensions!

  3. Optical Flow • Optical flow field: assign a flow vector to each pixel • Visualize: flow magnitude as saturation, 
 orientation as hue Visualization code Input two frames Ground-truth flow field [Baker et al. 2007]

  4. Optical Flow Constraint I u I v I 0 + + = x y t • Brightness/color is constant • Small motions • Also assume neighboring pixels have same motion

  5. Solving the aperture problem • How to get more equations for a pixel? • Spatial coherence constraint: pretend the pixel’s neighbors have the same (u,v) • If we use a 5x5 window, that gives us 25 equations per pixel Slide credit: Steve Seitz

  6. Solving the aperture problem Problem: we have more equations than unknowns Solution: solve least squares problem • minimum least squares solution given by solution (in d) of: • The summations are over all pixels in the K x K window • This technique was first proposed by Lucas & Kanade (1981) Slide credit: Steve Seitz

  7. Solving the aperture problem Problem: we have more equations than unknowns Solution: solve least squares problem • minimum least squares solution given by solution (in d) of: • The summations are over all pixels in the K x K window • This technique was first proposed by Lucas & Kanade (1981) Slide credit: Steve Seitz

  8. Aperture Problem Which way did the line move?

  9. Aperture Problem Which way did the line move?

  10. Motion Fields Zoom out Zoom in Pan right to left

  11. Can we do more? Scene flow Combine spatial stereo & temporal constraints Recover 3D vectors of world motion Stereo view 1 Stereo view 2 t y x t-1 z 3D world motion vector per pixel

  12. Scene flow example for human motion Estimating 3D Scene Flow from Multiple 2D Optical Flows, Ruttle et al., 2009

  13. Scene Flow https://www.youtube.com/watch?v=RL_TK_Be6_4 https://vision.in.tum.de/research/sceneflow [Estimation of Dense Depth Maps and 3D Scene Flow from Stereo Sequences, M. Jaimez et al., TU Munchen]

  14. Motion Analysis

  15. Motion Magnification

  16. Motion Magnification

  17. Motion Magnification

  18. Motion Magnification

  19. Learning optic flow Synthetic Training data Fischer et al. 2015. https://arxiv.org/abs/1504.06852

  20. Time

  21. What color is that pixel? Time

  22. Temporal Coherence of Color RGB Color Channels Quantized Color

  23. Obvious exceptions…

  24. Obvious exceptions… Edward Adelson, 1995

  25. Obvious exceptions…

  26. Color is mostly temporally coherent

  27. Self-supervised Tracking Reference Frame Gray-scale Video Vondrick, Shrivastava, Fathi, Guadarrama, Murphy. ECCV 2018

  28. What color is this?

  29. Where to copy color?

  30. Want to be safe!

  31. Where to copy color?

  32. Color can be robust to occlusion

  33. Input Frame Vondrick, Shrivastava, Fathi, Guadarrama, Murphy. ECCV 2018

  34. Colorize by Pointing Reference Frame Input Frame Reference Colors Target Colors Vondrick, Shrivastava, Fathi, Guadarrama, Murphy. ECCV 2018

  35. Reference Frame Input Frame A ij f i f j Reference Colors Target Colors Vondrick, Shrivastava, Fathi, Guadarrama, Murphy. ECCV 2018

  36. ! f T � � i f j exp X L c j , A ij c i where A ij = min � f T � P k f j k exp f i Reference Frame Input Frame A ij f i f j Reference Colors Target Colors Vondrick, Shrivastava, Fathi, Guadarrama, Murphy. ECCV 2018

  37. ! f T � � i f j exp X L c j , A ij c i where A ij = min ˆ c j = � f T � P k f j k exp f i Reference Frame Input Frame A ij f i f j c i Reference Colors Target Colors Vondrick, Shrivastava, Fathi, Guadarrama, Murphy. ECCV 2018

  38. ! f T � � i f j exp X L c j , A ij c i where A ij = min � f T � P k f j k exp f i Reference Frame Input Frame A ij f i f j c j c i Reference Colors Target Colors Vondrick, Shrivastava, Fathi, Guadarrama, Murphy. ECCV 2018

  39. Lumière Brothers Inventors of motion picture, 1895 Inventors of first practical color camera, 1903

  40. Georges Méliès “Discovered” special effects, 1898

  41. Video Colorization Ground T Reference Frame Gray-scale Video Predicted Color Vondrick, Shrivastava, Fathi, Guadarrama, Murphy. ECCV 2018

  42. Video Colorization Ground T Reference Frame Gray-scale Video Predicted Color Vondrick, Shrivastava, Fathi, Guadarrama, Murphy. ECCV 2018

  43. Tracking Emerges! Reference Frame Input Frame Vondrick, Shrivastava, Fathi, Guadarrama, Murphy. ECCV 2018

  44. Tracking Emerges! Reference Frame Input Frame Reference Mask Predicted Mask Vondrick, Shrivastava, Fathi, Guadarrama, Murphy. ECCV 2018

  45. ! � f T � i f j exp X L c j , A ij c i where A ij = min c j = ˆ � � f T P k f j k exp f i Reference Frame Input Frame A ij f i f j c i ˆ c j Reference Mask Predicted Mask Vondrick, Shrivastava, Fathi, Guadarrama, Murphy. ECCV 2018

  46. Segment Tracking Results Only the first frame is given. Colors indicate di ff erent instances. Vondrick, Shrivastava, Fathi, Guadarrama, Murphy. ECCV 2018

  47. Segment Tracking Results Only the first frame is given. Colors indicate di ff erent instances. Vondrick, Shrivastava, Fathi, Guadarrama, Murphy. ECCV 2018

  48. Pose Tracking Results Only the skeleton in the first frame is given. Vondrick, Shrivastava, Fathi, Guadarrama, Murphy. ECCV 2018

  49. Tracking Performance 80 Average Performance (Segment Overlap) Identity Optic Flow 60 Colorization 40 20 0 2 9 16 23 30 37 44 51 58 64 Frame Number Vondrick, Shrivastava, Fathi, Guadarrama, Murphy. ECCV 2018

  50. Tracking Performance Scale-Variation Identity Shape Complexity Optic Flow Appearance Change Colorization Heterogeneus Object Out-of-view Interacting Objects Motion Blur Occlusion Fast Motion Dynamic Background Low Resolution Deformation Edge Ambiguity Out-of-Plane Rotation Background Clutter Camera-Shake 0 12.5 25 37.5 50 Average Performance (Segment Overlap) Vondrick, Shrivastava, Fathi, Guadarrama, Murphy. ECCV 2018

  51. Visualizing Embeddings Project embedding to 3 dimensions and visualize as RGB l a n i g o i e r O d i V g n n i d o d i t e a b z m i l a E u s i V Vondrick, Shrivastava, Fathi, Guadarrama, Murphy. ECCV 2018

  52. Colorization and tracking fail together Reference Predicted Colors Colors Reference Predicted Mask Mask Vondrick, Shrivastava, Fathi, Guadarrama, Murphy. ECCV 2018

Recommend


More recommend