1 / 73

Motivation

Motivation. Where is my W-2 Form?. Video-based Tracking. Camera. Camera view of the desk. Overhead video camera. Example. 40 minutes, 1024x768 @ 15 fps. System Overview. User. Input Video. System Overview. Internal Representation. User. Input Video. Desk. Desk. Video Analysis. T.

sknaack
Download Presentation

Motivation

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. Motivation Where is my W-2 Form?

  2. Video-based Tracking Camera Camera view of the desk Overhead video camera

  3. Example 40 minutes, 1024x768 @ 15 fps

  4. System Overview User Input Video

  5. System Overview Internal Representation User Input Video Desk Desk Video Analysis T T+1 Vision Engine

  6. System Overview Internal Representation Query (where is my W-2 form?) User Input Video Desk Desk Video Analysis T T+1 Query Interface

  7. System Overview Internal Representation Query (where is my W-2 form?) User Input Video Desk Desk Video Analysis Answer T T+1 Query Interface

  8. System Overview Internal Representation User Input Video Desk Desk Video Analysis T T+1 Vision Engine

  9. … Vision Problem

  10. … Vision Problem Event

  11. … Vision Problem Event … Desk

  12. … Vision Problem Event … … Desk Desk

  13. … Vision Problem Event sanders01.pdf lowe04sift.pdf tut-article.pdf … … objectspaces.pdf kidd94.pdf Desk Desk

  14. … Vision Problem Event Scene Graph (DAG) sanders01.pdf lowe04sift.pdf tut-article.pdf … … objectspaces.pdf kidd94.pdf Desk Desk

  15. Assumptions • Simplifying • Corresponding electronic copy exists

  16. Assumptions • Simplifying • Corresponding electronic copy exists • 3 event types: move/entry/exit • One document at a time • Only topmost document can move • No duplicate copies of same document

  17. Assumptions • Simplifying • Corresponding electronic copy exists • 3 event types: move/entry/exit • One document at a time • Only topmost document can move • No duplicate copies of same document • Other • Desk need not be initially empty

  18. Algorithm Overview Input Frames … … Event Detection Event Interpretation Document Recognition Scene Graph Update

  19. Algorithm Overview Input Frames … … Event Detection before after Event Interpretation Document Recognition Scene Graph Update

  20. Algorithm Overview Input Frames … … Event Detection before after Event Interpretation “A document moved from (x1,y1) to (x2,y2)” Document Recognition Scene Graph Update

  21. Algorithm Overview Input Frames … … Event Detection before after Event Interpretation “A document moved from (x1,y1) to (x2,y2)” File1.pdf Document Recognition File2.pdf File3.pdf Scene Graph Update

  22. Algorithm Overview Input Frames … … Event Detection before after Event Interpretation “A document moved from (x1,y1) to (x2,y2)” File1.pdf Document Recognition File2.pdf File3.pdf Scene Graph Update

  23. Algorithm Overview Input Frames … … Event Detection before after Event Interpretation “A document moved from (x1,y1) to (x2,y2)” File1.pdf Document Recognition File2.pdf File3.pdf Scene Graph Update

  24. … Event Detection

  25. … Event Detection Frame Difference time

  26. … Event Detection Event Frames Frame Difference Threshold time time

  27. … Event Detection Event Frames before after

  28. Algorithm Overview Input Frames … … Event Detection before after Event Interpretation “A document moved from (x1,y1) to (x2,y2)” File1.pdf Document Recognition File2.pdf File3.pdf Scene Graph Update

  29. Event Interpretation before after Move

  30. Event Interpretation before after Move Entry

  31. Event Interpretation before after Move Entry Exit

  32. Event Interpretation before after Move Motion: (x,y,θ) Entry Exit

  33. Event Interpretation before after Move 1. Move vs. Entry/Exit Entry Exit

  34. Event Interpretation before after Move Entry 2. Entry vs. Exit Exit

  35. Event Interpretation • Use SIFT [Lowe 99] • Scale Invariant Feature Transform • Distinctive feature descriptor • Reliable object recognition

  36. Move vs. Entry/Exit after before

  37. Move vs. Entry/Exit after before

  38. Move vs. Entry/Exit after before

  39. Move vs. Entry/Exit after before

  40. Move vs. Entry/Exit after before

  41. Move vs. Entry/Exit after before

  42. Move vs. Entry/Exit after before

  43. Move vs. Entry/Exit after before

  44. Move vs. Entry/Exit after before

  45. Move vs. Entry/Exit after before

  46. Move vs. Entry/Exit after before

  47. Move vs. Entry/Exit Motion: (x,y,θ) after before

  48. Entry vs. Exit Example 1 (entry) before after

  49. Entry vs. Exit Example 1 (entry) before after

  50. Entry vs. Exit Example 1 (entry) before after

More Related