1 / 64

Local features: detection and description

Local features: detection and description . Monday March 7 Prof. Kristen Grauman UT-Austin. Midterm Wed. Covers material up until 3/1 Solutions to practice exam handed out today Bring a 8.5”x11” sheet of notes if you want

hoshi
Download Presentation

Local features: detection and description

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. Local features:detection and description Monday March 7 Prof. Kristen Grauman UT-Austin

  2. Midterm Wed. • Covers material up until 3/1 • Solutions to practice exam handed out today • Bring a 8.5”x11” sheet of notes if you want • Review the outlines and notes on course website, accompanying reading in textbook

  3. Last time • Image warping based on homography • Detecting corner-like points in an image

  4. Today • Local invariant features • Detection of interest points • (Harris corner detection) • Scale invariant blob detection: LoG • Description of local patches • SIFT : Histograms of oriented gradients

  5. Local features: main components • Detection: Identify the interest points • Description:Extract vector feature descriptor surrounding each interest point. • Matching: Determine correspondence between descriptors in two views Kristen Grauman

  6. Goal: interest operator repeatability • We want to detect (at least some of) the same points in both images. • Yet we have to be able to run the detection procedure independently per image. No chance to find true matches!

  7. Goal: descriptor distinctiveness • We want to be able to reliably determine which point goes with which. • Must provide some invariance to geometric and photometric differences between the two views. ?

  8. Local features: main components • Detection: Identify the interest points • Description:Extract vector feature descriptor surrounding each interest point. • Matching: Determine correspondence between descriptors in two views

  9. Recall: Corners as distinctive interest points 2 x 2 matrix of image derivatives (averaged in neighborhood of a point). Notation:

  10. Recall: Corners as distinctive interest points Since Mis symmetric, we have The eigenvalues of M reveal the amount of intensity change in the two principal orthogonal gradient directions in the window.

  11. “flat”region “edge”: “corner”: Recall: Corners as distinctive interest points 1 >> 2 1 and 2 are small; 1 and 2 are large,1 ~ 2; 2 >> 1 One way to score the cornerness:

  12. Harris corner detector • Compute M matrix for image window surrounding each pixel to get its cornernessscore. • Find points with large corner response (f > threshold) • Take the points of local maxima, i.e., perform non-maximum suppression

  13. Harris Detector: Steps

  14. Harris Detector: Steps Compute corner response f

  15. Harris Detector: Steps Find points with large corner response: f > threshold

  16. Harris Detector: Steps Take only the points of local maxima of f

  17. Harris Detector: Steps

  18. Properties of the Harris corner detector • Rotation invariant? • Scale invariant? Yes

  19. Properties of the Harris corner detector • Rotation invariant? • Scale invariant? Yes No All points will be classified as edges Corner !

  20. Scale invariant interest points How can we independently select interest points in each image, such that the detections are repeatable across different scales?

  21. f f Image 1 Image 2 s1 s2 region size region size Automatic scale selection • Intuition: • Find scale that gives local maxima of some function f in both position and scale.

  22. What can be the “signature” function?

  23. Recall: Edge detection Edge f Derivativeof Gaussian Edge = maximumof derivative Source: S. Seitz

  24. Recall: Edge detection Edge f Second derivativeof Gaussian (Laplacian) Edge = zero crossingof second derivative Source: S. Seitz

  25. maximum From edges to blobs • Edge = ripple • Blob = superposition of two ripples Spatial selection: the magnitude of the Laplacianresponse will achieve a maximum at the center ofthe blob, provided the scale of the Laplacian is“matched” to the scale of the blob Slide credit: Lana Lazebnik

  26. Blob detection in 2D • Laplacian of Gaussian: Circularly symmetric operator for blob detection in 2D

  27. Blob detection in 2D: scale selection • Laplacian-of-Gaussian = “blob” detector filter scales img2 img1 img3 Bastian Leibe

  28. Blob detection in 2D • We define the characteristic scale as the scale that produces peak of Laplacian response characteristic scale Slide credit: Lana Lazebnik

  29. Example Original image at ¾ the size Kristen Grauman

  30. Original image at ¾ the size Kristen Grauman

  31. Kristen Grauman

  32. Kristen Grauman

  33. Kristen Grauman

  34. Kristen Grauman

  35. Kristen Grauman

  36. Scale invariant interest points Interest points are local maxima in both position and scale. s5 s4 scale s3 s2  List of(x, y, σ) s1 Squared filter response maps

  37. Scale-space blob detector: Example Image credit: Lana Lazebnik

  38. Technical detail • We can approximate the Laplacian with a difference of Gaussians; more efficient to implement. (Laplacian) (Difference of Gaussians)

  39. Local features: main components • Detection: Identify the interest points • Description:Extract vector feature descriptor surrounding each interest point. • Matching: Determine correspondence between descriptors in two views

  40. Geometric transformations e.g. scale, translation, rotation

  41. Photometric transformations Figure from T. Tuytelaars ECCV 2006 tutorial

  42. Raw patches as local descriptors The simplest way to describe the neighborhood around an interest point is to write down the list of intensities to form a feature vector. But this is very sensitive to even small shifts, rotations.

  43. p 2 0 SIFT descriptor [Lowe 2004] • Use histograms to bin pixels within sub-patches according to their orientation. Why subpatches? Why does SIFT have some illumination invariance?

  44. Making descriptor rotation invariant CSE 576: Computer Vision • Rotate patch according to its dominant gradient orientation • This puts the patches into a canonical orientation. Image from Matthew Brown

  45. SIFT descriptor [Lowe 2004] • Extraordinarily robust matching technique • Can handle changes in viewpoint • Up to about 60 degree out of plane rotation • Can handle significant changes in illumination • Sometimes even day vs. night (below) • Fast and efficient—can run in real time • Lots of code available • http://people.csail.mit.edu/albert/ladypack/wiki/index.php/Known_implementations_of_SIFT Steve Seitz

  46. Example NASA Mars Rover images

  47. Example NASA Mars Rover images with SIFT feature matchesFigure by Noah Snavely

  48. SIFT properties • Invariant to • Scale • Rotation • Partially invariant to • Illumination changes • Camera viewpoint • Occlusion, clutter

  49. Local features: main components • Detection: Identify the interest points • Description:Extract vector feature descriptor surrounding each interest point. • Matching: Determine correspondence between descriptors in two views

  50. Matching local features Kristen Grauman

More Related