1 / 90

Line Features

CS 636 Computer Vision. Line Features. Nathan Jacobs. review. What properties should feature points have? discriminant easy to localize robust to viewpoint/photometric changes What local properties can you use to find them? all the same thing: second moment matrix, structure tensor, .

jeanne
Télécharger la présentation

Line Features

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. CS 636 Computer Vision Line Features Nathan Jacobs

  2. review • What properties should feature points have? • discriminant • easy to localize • robust to viewpoint/photometric changes • What local properties can you use to find them? • all the same thing: second moment matrix, structure tensor,

  3. overview • traditional edge detection • where do they come from? • depth and texture • classifying edges • edge algorithms • extended topics • straight line edges • learned edge detection • live coding

  4. Edge Detection • Convert a 2D image into a set of curves • Extracts salient features of the scene • More compact than pixels S. Narasimhan

  5. Origin of Edges • Edges are caused by a variety of factors surface normal discontinuity depth discontinuity surface color discontinuity illumination discontinuity

  6. How can you tell that a pixel is on an edge?

  7. Edge Types Step Edges Line Edges Roof Edge

  8. Real Edges • Edge Magnitude • Edge Orientation • High Detection Rate and Good Localization Noisy and Discrete! We want an Edge Operator that produces:

  9. Gradient • Gradient equation: • Represents direction of most rapid change in intensity • Gradient direction: • The edge strength is given by the gradient magnitude

  10. Ideal edge Unit step function: Image intensity (brightness): Theory of Edge Detection

  11. Partial derivatives (gradients): • Squared gradient: Edge Magnitude: (normal of the edge) Edge Orientation: Rotationally symmetric, non-linear operator Theory of Edge Detection • Image intensity (brightness):

  12. Partial derivatives (gradients): • Laplacian: Rotationally symmetric, linear operator zero-crossing Theory of Edge Detection • Image intensity (brightness):

  13. Discrete Edge Operators • How can we differentiate a discrete image? Finite difference approximations: Convolution masks :

  14. Second order partial derivatives: • Laplacian : Convolution masks : or Discrete Edge Operators (more accurate)

  15. The Sobel Operators • Better approximations of the gradients exist • The Sobel operators below are commonly used

  16. Comparing Edge Operators Good Localization Noise Sensitive Poor Detection Gradient: Roberts (2 x 2): Sobel (3 x 3): Sobel (5 x 5): Poor Localization Less Noise Sensitive Good Detection

  17. Where is the edge?? Effects of Noise • Consider a single row or column of the image • Plotting intensity as a function of position gives a signal

  18. Look for peaks in Solution: Smooth First Where is the edge?

  19. Derivative Theorem of Convolution …saves us one operation.

  20. Laplacian of Gaussian (LoG) Laplacian of Gaussian Laplacian of Gaussian operator Where is the edge? Zero-crossings of bottom graph !

  21. 2D Gaussian Edge Operators Gaussian Derivative of Gaussian (DoG) Laplacian of Gaussian Mexican Hat (Sombrero) • is the Laplacian operator:

  22. Canny Edge Operator • Smooth image I with 2D Gaussian: • Find local edge normal directions for each pixel • Compute edge magnitudes • Locate edges by finding zero-crossings along the edge normal directions (non-maximum suppression)

  23. Non-maximum Suppression • Check if pixel is local maximum along gradient direction • requires checking interpolated pixels p and r

  24. Edge Thresholding • Standard Thresholding: • Can only select “strong” edges. • Does not guarantee “continuity”. • Hysteresis based Thresholding (use two thresholds) Example: For “maybe” edges, decide on the edge if neighboring pixel is a strong edge.

  25. The Canny Edge Detector original image (Lena)

  26. The Canny Edge Detector magnitude of the gradient

  27. The Canny Edge Detector After non-maximum suppression

  28. Canny Edge Operator original Canny with Canny with • The choice of depends on desired behavior • large detects large scale edges • small detects fine features

  29. larger The effect of scale on edge detection larger Scale space (Witkin 83)

  30. Difference of Gaussians (DoG) • Laplacian of Gaussian can be approximated by the difference between two different Gaussians

  31. (a) (b) DoG Edge Detection (b)-(a)

  32. recap so far… • simple, bottom up, edge detection • What else could we do? • find lines • other low level cues • How could we incorporate top down information?

  33. finding lines Hough Transform or RANSAC

  34. Supervised Learning ofEdges and Object Boundaries, CVPR 2006 Piotr Dollár Zhuowen Tu Serge Belongie

  35. The problem ?

  36. Outline • I. Motivation • II. Problem formulation • III. Learning architecture (BEL) • IV. Results

  37. Outline • I. Motivation • Why edges? • Why not edges? • Why learning? • II. Problem formulation • III. Learning architecture (BEL) • IV. Results

  38. Why edges? • Reduce dimensionality of data • Preserve content information • Useful in applications such as: • object detection • structure from motion • tracking

  39. Why not edges? But, not that useful, why? Difficulties: • Modeling assumptions • Parameters • Multiple sources of information (brightness, color, texture, …) • Real world conditions Is edge detection even well defined?

  40. 1. smooth 2. gradient 3. thresh, suppress, link Canny edge detection Canny is optimal w.r.t. some model.

  41. Canny edge detection 1. smooth 2. gradient 3. thresh, suppress, link And yet…

  42. Canny difficulties • Modeling assumptions • Step edges, junctions, etc. • Parameters • Scales, threshold, etc. • Multiple sources of information • Only handles brightness • Real world conditions • Gaussian iid noise? Texture…

  43. Modern methods • Modeling assumptions • Complex models, computationally prohibitive • Parameters • Many, may use learning to help tune • Multiple sources of information • Typically brightness, color, and texture cues • Real world conditions • Aimed at real images

  44. Modern methods (Pb) Pb – Martin et al. PAMI04

  45. Why learning? • Modeling assumptions • minimal • Parameters • none • Multiple sources of information • Automatically incorporated • Real world conditions • training data

  46. Outline • I. Motivation • II. Problem formulation • III. Learning architecture (BEL) • IV. Results

  47. Problem formulation (general) image scene interpretation that can include spatial location and extent of objects, regions, object boundaries, curves, etc. 0/1 function that encodes spatial extent of a component of W Obtaining optimal or likely W or SW can be difficult. Let: We seek to learn this distribution directly from image data. To further reduce complexity, we can discard the absolute coordinates of S: where N(c) is the neighborhood of I centered at c.

  48. Problem formulation (edges) • image segmentation • 1 on boundaries of segments, 0 elsewhere

  49. Discriminative framework Goal is to learn from human labeled images Given an image I and n interpretations W obtained by manual annotation, we can compute: Sample positive and negative patches according to above: Finally train a classifier!

More Related