1 / 18

Lecture 3 Image Primitives and Correspondence

Lecture 3 Image Primitives and Correspondence. Image Primitives and Correspondence. Given an image point in left image, what is the (corresponding) point in the right image, which is the projection of the same 3-D point . Matching - Correspondence. Lambertian assumption.

jaxon
Download Presentation

Lecture 3 Image Primitives and Correspondence

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. Lecture 3 Image Primitives and Correspondence Invitation to 3D vision

  2. Image Primitives and Correspondence Given an image point in left image, what is the (corresponding) point in the right image, which is the projection of the same 3-D point Invitation to 3D vision

  3. Matching - Correspondence Lambertian assumption Rigid body motion Correspondence Invitation to 3D vision

  4. Local Deformation Models • Translational model • Affine model • Transformation of the intensity values and occlusions Invitation to 3D vision

  5. Feature Tracking and Optical Flow • Translational model • Small baseline • RHS approx. by first two terms of Taylor series • Brightness constancy constraint Invitation to 3D vision

  6. Aperture Problem • Normal flow Invitation to 3D vision

  7. Optical Flow • Integrate around over image patch • Solve Invitation to 3D vision

  8. Optical Flow, Feature Tracking Conceptually: rank(G) = 0 blank wall problem rank(G) = 1 aperture problem rank(G) = 2 enough texture – good feature candidates In reality: choice of threshold is involved Invitation to 3D vision

  9. Optical Flow • Previous method - assumption locally constant flow • Alternative regularization techniques (locally smooth flow fields, • integration along contours) • Qualitative properties of the motion fields Invitation to 3D vision

  10. Feature Tracking Invitation to 3D vision

  11. 3D Reconstruction - Preview Invitation to 3D vision

  12. Point Feature Extraction • Compute eigenvalues of G • If smalest eigenvalue  of G is bigger than  - mark pixel as candidate • feature point • Alternatively feature quality function (Harris Corner Detector) Invitation to 3D vision

  13. Harris Corner Detector - Example Invitation to 3D vision

  14. Wide Baseline Matching Invitation to 3D vision

  15. Region based Similarity Metric • Sum of squared differences • Normalize cross-correlation • Sum of absolute differences Invitation to 3D vision

  16. Edge Detection original image gradient magnitude Canny edge detector • Compute image derivatives • if gradient magnitude >  and the value is a local maximum along gradient • direction – pixel is an edge candidate Invitation to 3D vision

  17. y   x Line fitting Non-max suppressed gradient magnitude • Edge detection, non-maximum suppression • (traditionally Hough Transform – issues of resolution, threshold • selection and search for peaks in Hough space) • Connected components on edge pixels with similar orientation • - group pixels with common orientation Invitation to 3D vision

  18. Line Fitting second moment matrix associated with each connected component • Line fitting Lines determined from eigenvalues and eigenvectors of A • Candidate line segments - associated line quality Invitation to 3D vision

More Related