Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Computer Vision: Image mosiacs project

Jamie Ly
December 05, 2010

Computer Vision: Image mosiacs project

A presentation on the results of a image mosiac project from Computer Vision class.

Jamie Ly

December 05, 2010
Tweet

More Decks by Jamie Ly

Other Decks in Technology

Transcript

  1. Decisions • ANMS ◦ Not really working until we used

    imregionalmax. • Descriptors ◦ Rotations using atan Iy./Ix • Ransac ◦ 50 random pulls of 4 points • Mosaic merging ◦ Homography applied to all pixels of source image ◦ Results in holes in destination
  2. Tips • Skipped ANMS by using other code for non-maximal

    suppression in order to work on other tasks • Did not implement inverse homography to copy pixels ◦ Results in holes in image, especially when there are perspective transformations (Quad Mosaic) ◦ (Later implemented.) • Perseverance!
  3. Problems • ANMS slow. • Crashed matlab by not setting

    bounds on images ◦ Too much memory consumed • Did not implement inverse homography to copy pixels ◦ Results in holes in image, especially when there are perspective transformations (Quad Mosaic) ◦ (Implemented later using inpolygon) • Ran out of time!