1 / 63

Image Stitching

Image Stitching. Shangliang Jiang Kate Harrison. What is image stitching?. What is image stitching?. Introduction. Are you getting the whole picture? Compact Camera FOV = 50 x 35°. Introduction. Are you getting the whole picture? Compact Camera FOV = 50 x 35°

whitcomb
Download Presentation

Image Stitching

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. Image Stitching Shangliang Jiang Kate Harrison

  2. What is image stitching?

  3. What is image stitching?

  4. Introduction • Are you getting the whole picture? • Compact Camera FOV = 50 x 35°

  5. Introduction • Are you getting the whole picture? • Compact Camera FOV = 50 x 35° • Human FOV = 200 x 135°

  6. Introduction • Are you getting the whole picture? • Compact Camera FOV = 50 x 35° • Human FOV = 200 x 135° • Panoramic Mosaic = 360 x 180°

  7. Recognizing Panoramas • 1D Rotations (q) • Ordering  matching images

  8. Recognizing Panoramas • 1D Rotations (q) • Ordering  matching images

  9. Recognizing Panoramas • 1D Rotations (q) • Ordering  matching images

  10. 2D Rotations (q, f) • Ordering  matching images Recognizing Panoramas • 1D Rotations (q) • Ordering  matching images

  11. 2D Rotations (q, f) • Ordering  matching images Recognizing Panoramas • 1D Rotations (q) • Ordering  matching images

  12. 2D Rotations (q, f) • Ordering  matching images Recognizing Panoramas • 1D Rotations (q) • Ordering  matching images

  13. Recognizing Panoramas

  14. Overview • Feature Matching • Image Matching • Bundle Adjustment • Image Compositing • Conclusions

  15. Overview • Feature Matching • Image Matching • Bundle Adjustment • Image Compositing • Conclusions

  16. Overview • Feature Matching • SIFT Features • Nearest Neighbor Matching • Image Matching • Bundle Adjustment • Image Compositing • Conclusions

  17. SIFT Features • SIFT features are… • Geometrically invariant to similarity transforms, • some robustness to affine change • Photometrically invariant to affine changes in intensity

  18. Overview • Feature Matching • SIFT Features • Nearest Neighbor Matching • Image Matching • Bundle Adjustment • Image Compositing • Conclusions

  19. Nearest Neighbor Matching • Find k nearest neighbors for each feature • k  number of overlapping images (we use k = 4) • Use k-d tree • k-d tree recursively bi-partitions data at mean in the dimension of maximum variance • Approximate nearest neighbors found in O(nlogn)

  20. Overview • Feature Matching • SIFT Features • Nearest Neighbor Matching • Image Matching • Bundle Adjustment • Image Compositing • Conclusions

  21. Overview • Feature Matching • Image Matching • Bundle Adjustment • Image Compositing • Conclusions

  22. Overview • Feature Matching • Image Matching • Bundle Adjustment • Image Compositing • Conclusions

  23. Overview • Feature Matching • Image Matching • Random Sample Consensus (RANSAC) for Homography • Probabilistic model for verification • Bundle Adjustment • Image Compositing • Conclusions

  24. Overview • Feature Matching • Image Matching • Random Sample Consensus (RANSAC) for Homography • Probabilistic model for verification • Bundle Adjustment • Image Compositing • Conclusions

  25. RANSAC for Homography

  26. RANSAC for Homography • SIFT features of two similar images

  27. RANSAC for Homography • SIFT features common to both images

  28. RANSAC for Homography • Select random subset of features (e.g. 6) • Compute motion estimate • Apply motion estimate to all SIFT features • Compute error: feature pairs not described by motion estimate • Repeat many times (e.g. 500) • Keep estimate with best error

  29. RANSAC for Homography

  30. Overview • Feature Matching • Image Matching • Random Sample Consensus (RANSAC) for Homography • Probabilistic model for verification • Bundle Adjustment • Image Compositing • Conclusions

  31. Probabilistic model for verification • Potential problem: • Two images don’t match… • … but RANSAC found a motion estimate • Do a quick check to make sure the images do match • MAP for inliers vs. outliers

  32. Finding the panoramas

  33. Finding the panoramas

  34. Finding the panoramas

  35. Overview • Feature Matching • Image Matching • RANSAC for Homography • Probabilistic model for verification • Bundle Adjustment • Image Compositing • Conclusions

  36. Overview • Feature Matching • Image Matching • Bundle Adjustment • Image Compositing • Conclusions

  37. Overview • Feature Matching • Image Matching • Bundle Adjustment • Image Compositing • Conclusions

  38. Overview • Feature Matching • Image Matching • Bundle Adjustment • Error function • Image Compositing • Conclusions

  39. Overview • Feature Matching • Image Matching • Bundle Adjustment • Error function • Image Compositing • Conclusions

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

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

  42. Error function • Sum of squared projection errors • n = #images • I(i) = set of image matches to image i • F(i, j) = set of feature matches between images i,j • rijk = residual of kth feature match between images i,j • Robust error function

  43. Overview • Feature Matching • Image Matching • Bundle Adjustment • Error function • Image Compositing • Conclusions

  44. Overview • Feature Matching • Image Matching • Bundle Adjustment • Image Compositing • Conclusions

  45. Overview • Feature Matching • Image Matching • Bundle Adjustment • Image Compositing • Conclusions

  46. Blending

  47. Gain compensation

  48. How do we blend? Linear blending Multi-band blending

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

More Related