1 / 34

Tutorial: Breakthroughs in 3-D Reconstruction and Motion Analysis

Tutorial: Breakthroughs in 3-D Reconstruction and Motion Analysis. Jana Kosecka (CS, GMU) Yi Ma (ECE, UIUC) Shankar Sastry (EECS, Berkeley) Stefano Soatto (CS, UCLA) Rene Vidal (Berkeley, John Hopkins) Omid Shakernia (EECS, Berkeley). PRIMARY REFERENCE.

collin
Download Presentation

Tutorial: Breakthroughs in 3-D Reconstruction and Motion Analysis

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. Tutorial: Breakthroughs in 3-D Reconstruction and Motion Analysis Jana Kosecka (CS, GMU) Yi Ma (ECE, UIUC) Shankar Sastry (EECS, Berkeley) Stefano Soatto (CS, UCLA) Rene Vidal (Berkeley, John Hopkins) Omid Shakernia (EECS, Berkeley) ICRA2003, Taipei

  2. PRIMARY REFERENCE ICRA2003, Taipei

  3. Breakthroughs in 3D Reconstruction and Motion Analysis Lecture A: Overview and Introduction Yi Ma Perception & Decision Laboratory Decision & Control Group, CSL Image Formation & Processing Group, Beckman Electrical & Computer Engineering Dept., UIUC http://decision.csl.uiuc.edu/~yima ICRA2003, Taipei

  4. TUTORIAL LECTURES • A. Overview and introduction (Ma) • B. Preliminaries: geometry & image formation (Ma) • C. Image primitives & correspondence (Kosecka) • D. Two-view geometry (Kosecka) • E. Uncalibrated geometry and stratification (Ma) • F. Multiview recon. from points and lines (Kosecka) • G. Reconstruction from scene knowledge (Ma) • H. Step-by-step building of 3-D model (Kosecka) • I. Landing of unmanned aerial vehicles (Kosecka) • J. Multiple motion estimation (Ma) ICRA2003, Taipei

  5. TUTORIAL LOGICAL FLOW IMAGING and VISION:From 3D to 2D and then back again GEOMETRY FOR TWO VIEWS GEOMETRY FOR MULTIPLE VIEWS MULTIVIEW GEOMETRY WITH SYMMETRY APPLICATIONS: Image based modeling, vision based control ICRA2003, Taipei

  6. Reconstruction from images – The Fundamental Problem Input: Corresponding “features” in multiple perspective images. Output: Camera pose, calibration, scene structure representation. ICRA2003, Taipei

  7. surface curve line point practice projective algorithm affine theory Euclidean 2 views algebra 3 views geometry 4 views optimization m views Fundamental Problem: An Anatomy of Cases ICRA2003, Taipei

  8. VISION AND GEOMETRY – An uncanny deja vu? “The rise of projective geometry made such an overwhelming impression on the geometers of the first half of the nineteenth century that they tried to fit all geometric considerations into the projective scheme. ... The dictatorial regime of the projective idea in geometry was first successfully broken by the German astronomer and geometer Mobius, but the classical document of the democratic platform in geometry establishing the group of transformations as the ruling principle in any kind of geometry and yielding equal rights to independent consideration to each and any such group, is F. Klein's Erlangen program.” -- Herman Weyl, Classic Groups, 1952 Synonyms: Group = Symmetry ICRA2003, Taipei

  9. APPLICATIONS – Autonomous Highway Vehicles ICRA2003, Taipei Image courtesy of California PATH

  10. Rate: 10Hz; Accuracy: 5cm, 4o APPLICATIONS – Unmanned Aerial Vehicles (UAVs) ICRA2003, Taipei Courtesy of Berkeley Robotics Lab

  11. APPLICATIONS – Real-Time Virtual Object Insertion ICRA2003, Taipei UCLA Vision Lab

  12. APPLICATIONS – Real-Time Sports Coverage First-down line and virtual advertising ICRA2003, Taipei Courtesy of Princeton Video Image, Inc.

  13. APPLICATIONS – Image Based Modeling and Rendering ICRA2003, Taipei Image courtesy of Paul Debevec

  14. APPLICATIONS – Image Alignment, Mosaicing, and Morphing ICRA2003, Taipei

  15. GENERAL STEPS – Feature Selection and Correspondence • Small baselines versus large baselines • Point features versus line features ICRA2003, Taipei

  16. GENERAL STEPS – Structure and Motion Recovery • Two views versus multiple views • Discrete versus continuous motion • General versus planar scene • Calibrated versus uncalibrated camera • One motion versus multiple motions ICRA2003, Taipei

  17. GENERAL STEPS – Image Stratification and Dense Matching Left Right ICRA2003, Taipei

  18. GENERAL STEPS – 3-D Surface Model and Rendering • Point clouds versus surfaces (level sets) • Random shapes versus regular structures ICRA2003, Taipei

  19. Breakthroughs in 3D Reconstruction and Motion Analysis Lecture B: Rigid-Body Motion and Imaging Geometry Yi Ma Perception & Decision Laboratory Decision & Control Group, CSL Image Formation & Processing Group, Beckman Electrical & Computer Engineering Dept., UIUC http://decision.csl.uiuc.edu/~yima ICRA2003, Taipei

  20. OUTLINE • 3-D EUCLIDEAN SPACE & RIGID-BODY MOTION • Coordinates and coordinate frames • Rigid-body motion and homogeneous • coordinates • GEOMETRIC MODELS OF IMAGE FORMATION • Pinhole camera model • CAMERA INTRINSIC PARAMETERS • From metric to pixel coordinates SUMMARY OF NOTATION ICRA2003, Taipei

  21. Coordinates of a point in space: Standard base vectors: 3-D EUCLIDEAN SPACE - Cartesian Coordinate Frame ICRA2003, Taipei

  22. Coordinates of the vector : 3-D EUCLIDEAN SPACE - Vectors A “free” vector is defined by a pair of points : ICRA2003, Taipei

  23. Cross product between two vectors: 3-D EUCLIDEAN SPACE – Inner Product and Cross Product Inner product between two vectors: ICRA2003, Taipei

  24. Coordinates are related by: RIGID-BODY MOTION – Rotation Rotation matrix: ICRA2003, Taipei

  25. Coordinates are related by: Velocities are related by: RIGID-BODY MOTION – Rotation and Translation ICRA2003, Taipei

  26. Homogeneous coordinates: Homogeneous coordinates/velocities are related by: RIGID-BODY MOTION – Homogeneous Coordinates 3-D coordinates are related by: ICRA2003, Taipei

  27. IMAGE FORMATION – Perspective Imaging “The Scholar of Athens,” Raphael, 1518 ICRA2003, Taipei Image courtesy of C. Taylor

  28. Frontal pinhole IMAGE FORMATION – Pinhole Camera Model Pinhole ICRA2003, Taipei

  29. Homogeneous coordinates IMAGE FORMATION – Pinhole Camera Model 2-D coordinates ICRA2003, Taipei

  30. metric coordinates Linear transformation pixel coordinates CAMERA PARAMETERS – Pixel Coordinates ICRA2003, Taipei

  31. Calibration matrix (intrinsic parameters) Projection matrix Camera model CAMERA PARAMETERS – Calibration Matrix and Camera Model Pinhole camera Pixel coordinates ICRA2003, Taipei

  32. Projection of a 3-D point to an image plane IMAGE FORMATION – Image of a Point Homogeneous coordinates of a 3-D point Homogeneous coordinates of its 2-D image ICRA2003, Taipei

  33. Homogeneous representation of its 2-D image Projection of a 3-D line to an image plane IMAGE FORMATION – Image of a Line Homogeneous representation of a 3-D line ICRA2003, Taipei

  34. SUMMARY OF NOTATION – Multiple Images . . . • Images are all “incident” at the corresponding features in space; • Features in space have many types of incidence relationships; • Features in space have many types of metric relationships. ICRA2003, Taipei

More Related