CS 766 Computer Vision Assignment 2: Panorama & Mosaics

 Saikat R. Gomes (saikat@cs.wisc.edu) & Stephen Lazzaro (slazzaro@cs.wisc.edu)

Contents

  1. Home
  2. Introduction
  3. Image Acquisition
  4. Cylindrical Coordinates
  5. SIFT Feature detection
  6. Ransac Translation
  7. Stitching: Translastion
  8. Image Blending
  9. Results
    1. Monona Terrace
    2. University
    3. CS Lobby (iPhone)
  10. Datasets
  11. Code
  12. Git Logs
  13. References

Cylindrical Coordinates

First, we warped our images into cylindrical coordinates using the following two equations:

theta = arctan(x / f);
h = y / sqrt(x^2 + f^2);

In the above equations, f is the focal length, x is the x coordinate of the 2-d image representation, and y is the y coordinate of the 2-d image representation. This gave us a cylindrical coordinate for each of our x,y positions in our images. After this conversion, we warped our images back into cylindrical image coordinates using the following equations.
new_x = f * theta + x_center;
new_y = f * h + y_center;

In the above equations, the terms x_center and y_center represent the center of the unwrapped cylinder for the cylindrical coordinates. We used these new_x and new_y values to recreate our original images as cylindrical images. Below, we show our original image (left) and its cylindrical image representation (right).