1 / 12

Panorama Composition Toolbox for Image Stitching and Blending

This project guides users on creating panoramic images by converting, aligning, and blending a set of images taken from the same optical center. It includes steps on cylindrical coordinates, radial distortion removal, alignment parameter computation, and blending techniques using various weight assignments.

ericalopez
Download Presentation

Panorama Composition Toolbox for Image Stitching and Blending

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. Making Panoramas

  2. … Input: Output:

  3. Input: • A set of images taken from the same optical center. • For this project, theimages will also havethe same horizontalorientation.

  4. Steps • Convert each image to cylindrical coordinates. • Remove radial distortion. • Find the alignment parameters between each adjacent pair of images. • Blend the images into a single panorama.

  5. Convert each image to cylindrical coordinates. • The image plane is z = 1. • We compute the inversetransformation of (θ,y,1)onto the image plane: • x = tan θ • y = y / cos θ • z = 1

  6. Remove radial distortion. • Again, perform the inverse transformation on (x,y): • x´ = x + κ1r2x + κ2r4x • y´ = y + κ1r2y + κ2r4y

  7. Find the alignment parameters between each adjacent pair of images. • The images lie on a cylinder and have the same horizontal orientation. • Therefore we can represent the alignment by a single (u,v) offset. (u,v)

  8. Find the alignment parameters between each adjacent pair of images. • The Lucas-Kanade optical flow algorithm can discover this offset. • Ixu + Iyv = -It at each pixel. • We have two unknowns and many equations, so we can solve this with a 2-by-2 least-squares system. • We do this for each level of the image pyramid, traversing coarse-to-fine.

  9. Blend the images into a single panorama. • What do we do with pixels shared by multiple images?

  10. Blend the images into a single panorama. • Have each image i assign a weight αito each pixel. Then, the color of a pixel (r,g,b) in the panorama is:

  11. Blend the images into a single panorama. • Assigning weights: • Uniform weights (αi = 1 for all i). • Horizontal hat function (αi inversely proportional to distance from horizontal center,within some window. • Something else? 1 0

  12. Project 4 • For Project 4, you will make a panorama. • Most of the code has been given to you. You only need to write code for: • Forming and solving the matrix equation in Lucas-Kanade flow estimation. • Image blending. • This project should be less time-consuming than the last.

More Related