ECE 564 Computer Vision Assignment 3

This assignment uses images taken in class 6 Feb 2017. They may be downloaded from Isidore resources (CV2017_0206.zip). The various image sequences are explained in this overview.

Submit HTML documentation and MATLAB files on Isidore.

Do not include a copy of rvctools or the Bouguet calibration toolkit in your submission.

  1. Using group1 images from 6 Feb 2017, find the effective focal length of the camera and the horizontal field of view.

  2. Using group2 images from 6 Feb 2017 run a camera calibration. Follow the steps in this example from the Camera Calibration Toolbox for Matlab® by Jean-Yves Bouguet. Compare the focal lengths to the previous problem.

    Do not submit a copy of the calibration toolbox. I do not need 11 more copies of the toolbox. Just submit the published MATLAB summary using calib_publish.m.

  3. Use the Computer Vision calibration toolkit with the same group2 checkerboard images from 6 Feb 2017. Document the instrinsic calibration matrix and intrinsic parameters for the camera. Compare the focal lengths to those obtained in the previous problems. Modify the MATLAB script you can generate from cameraCalibrator so you can nicely publish the results.

  4. Use either calibration toolkit with the images from group4 and compare the results to the previous problems.

  5. Extract the top row of corner points from the calibration results each for group4 image (either toolkit). Find the angle θ for each of the lines minimizing the perpendicular distance to the lines. Transform the points to the (u, v) coordinate system for each line and plot v vs. u. If you see a quadratic deviation, fit a quadratic polynomial to the transformed points

  6. Generate a photo montage showing various views of the cube from the last assignment. Include several views showing the effect of perspective projection with the camera angle varying from large (maybe 60-degrees to small 10-degrees).

  7. Read chapter 2 from Peter Corke, Robotics, vision and control: fundamental algorithms in MATLAB,
    Springer, c2011. ISBN 978-3-642-20143-1 [UD library electronic resource]
    Use the rvctools from the previous assignment.

    Download the MATLAB chapter 2 code. Please create a MATLAB script, that generates a nicely formatted version of this code, including explanations from the textbook as necessary to understand the theory behind the code.


Maintained by John Loomis, last updated 7 February 2017