1 / 43

Photo Stitching Panoramas from Multiple Images

04/06/10. Photo Stitching Panoramas from Multiple Images. Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem. So far, we’ve looked at what can be done with one image. Recover basic geometry using vanishing points Find image boundaries and segment objects

lani
Télécharger la présentation

Photo Stitching Panoramas from Multiple Images

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. 04/06/10 Photo StitchingPanoramas from Multiple Images Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem

  2. So far, we’ve looked at what can be done with one image • Recover basic geometry using vanishing points • Find image boundaries and segment objects • Categorize images • Find specific objects and detect objects that are part of some category

  3. What can we get from multiple images?

  4. What can we get from multiple images? • Bigger, Better, Brighter, Sharper images • Panoramas • Increased dynamic range • Super-resolution • Reduced noise/blur Product example: http://www.vreveal.com/

  5. What can we get from multiple images? • Bigger, Better, Brighter, Sharper images • Panoramas • Increased dynamic range • Super-resolution • Reduced noise/blur today Product example: http://www.vreveal.com/

  6. What can we get from multiple images? • Depth and 3D structure • Two-view stereo • Multi-view stereo • Shape carving • Structure from motion Thursday + Next Tuesday

  7. What can we get from multiple images? • Motion • Optical flow • Tracking • Action/activity recognition Tracking (from Deva Ramanan) Optical flow (source: http://www.borisfx.com/avid/bccavx/classic_features.php)

  8. What can we get from multiple images? • Motion • Optical flow • Tracking • Action/activity recognition April 15 Tracking (from Deva Ramanan) Optical flow (source: http://www.borisfx.com/avid/bccavx/classic_features.php)

  9. What can we get from multiple images? • Motion • Optical flow • Tracking • Action/activity recognition April 20 Tracking (from Deva Ramanan) Optical flow (source: http://www.borisfx.com/avid/bccavx/classic_features.php)

  10. Today: Image Stitching • Combine two or more overlapping images to make one larger image Add example Slide credit: Vaibhav Vaish

  11. Example Camera Center

  12. Problem basics • Do on board

  13. Basic problem • x = K [R t] X • x’ = K’ [R’ t’] X’ • t=t’=0 • x‘=Hxwhere H = K’ R’ R-1 K-1 • Typically only R and f will change (4 parameters), but, in general, H has 8 parameters . X x x' f f'

  14. Image Stitching Algorithm Overview • Detect keypoints • Match keypoints • Estimate homography with four matched keypoints (using RANSAC) • Combine images

  15. Computing homography • Assume we have four matched points: How do we compute homographyH? Direct Linear Transformation (DLT) Only these two provide unique constraints

  16. Computing homography Direct Linear Transform • Apply SVD: UDVT= A • h = Vsmallest (column of V corr. to smallest singular value)

  17. Computing homography • Assume we have four matched points: How do we compute homographyH? Normalized DLT • Normalize coordinates for each image • Translate for zero mean • Scale so that average distance to origin is sqrt(2) • This makes problem better behaved numerically (see HZ p. 107-108) • Compute H using DLT in normalized coordinates • Unnormalize:

  18. Computing homography • Assume we have matched points with outliers: How do we compute homographyH? Automatic Homography Estimation with RANSAC • Choose number of samples N HZ Tutorial ‘99

  19. Computing homography • Assume we have matched points with outliers: How do we compute homographyH? Automatic Homography Estimation with RANSAC • Choose number of samples N • Choose 4 random potential matches • Compute H using normalized DLT • Project points from x to x’ for each potentially matching pair: • Count points with projected distance < t • t ~= 6 σ ; σ is measurement error (1-3 pixels) • Repeat steps 2-5 N times • Choose H with most inliers HZ Tutorial ‘99

  20. Automatic Image Stitching • Compute interest points on each image • Find candidate matches • Estimate homographyH using matched points and RANSAC with normalized DLT • Transform second image and blend the two images • Matlab: maketform, imtransform Some details from a class project

  21. Recognizing Panoramas Brown and Lowe 2003, 2007 Some of following material from Brown and Lowe 2003 talk

  22. Recognizing Panoramas Input: N images • Extract SIFT points, descriptors from all images • Find K-nearest neighbors for each point (K=4) • For each image • Select M candidate matching images by counting matched keypoints (m=6) • Solve homographyHij for each matched image

  23. Recognizing Panoramas Input: N images • Extract SIFT points, descriptors from all images • Find K-nearest neighbors for each point (K=4) • For each image • Select M candidate matching images by counting matched keypoints (m=6) • Solve homographyHij for each matched image • Decide if match is valid (ni > 8 + 0.3 nf ) # features in overlapping area # inliers

  24. RANSAC for Homography Initial Matched Points

  25. RANSAC for Homography Final Matched Points

  26. Verification

  27. RANSAC for Homography

  28. Recognizing Panoramas (cont.) (now we have matched pairs of images) • Find connected components

  29. Finding the panoramas

  30. Finding the panoramas

  31. Recognizing Panoramas (cont.) (now we have matched pairs of images) • Find connected components • For each connected component • Perform bundle adjustment to solve for rotation (θ1, θ2, θ3) and focal length f of all cameras • Project to a surface (plane, cylinder, or sphere) • Render with multiband blending

  32. Bundle adjustment for stitching • Non-linear minimization of re-projection error • whereH = K’ R’ R-1K-1 • Solve non-linear least squares (Levenberg-Marquardt algorithm) • See paper for details

  33. Bundle Adjustment • New images initialised with rotation, focal length of best matching image

  34. Bundle Adjustment • New images initialised with rotation, focal length of best matching image

  35. Straightening • Rectify images so that “up” is vertical

  36. Blending • Gain compensation: minimize intensity difference of overlapping pixels • Blending • Pixels near center of image get more weight • Multiband blending to prevent blurring

  37. Multi-band Blending • Burt & Adelson 1983 • Blend frequency bands over range l

  38. Multiband blending

  39. Blending comparison (IJCV 2007)

  40. Blending Comparison

  41. Further reading • DLT algorithm: HZ p. 91 (alg 4.2), p. 585 • Normalization: HZ p. 107-109 (alg 4.2) • RANSAC: HZ Sec 4.7, p. 123, alg 4.6 • Recognising Panoramas: Brown and Lowe, IJCV 2007 (also bundle adjustment)

  42. Things to remember • Homography relates rotating cameras • Recover homography using RANSAC and normalized DLT • Bundle adjustment minimizes reprojection error for set of related images • Details to make it look nice (straightening, blending)

  43. Next class • How to relate images taken from cameras with different centers

More Related