ECE 564 Computer Vision Assignment 8

Submit HTML documentation and MATLAB code on Isidore.

  1. Use an image set (two images) of your product. Use cpselect to choose matching points from each image. Use estimateFundamentalMatrix to calculate the Fundamental matrix and verify that imgA*F*imgB' = 0 for matching image points. Calculate the Essential matrix from the fundamental matrix, using your intrinsic matrix from an earlier calibration.

  2. Use the same image set. Find the extrinsics (R and T) using the checkerboard corners. Use the extrinsics to find the Essential matrix. Verify that xA*E*xB' = 0 for matching normalized camera points. Then calculate the Fundamental matrix from the Essential matrix. Compare to the fundamental matrix calculated in the previous problem.

  3. Use the same image set and extrinsics. Triangulate (back project) to find significant coordinates (top corners, for example) of your product. Compute the back projection errors for each case. Compare the back-projected dimensions to known, measured values of your product box.

  4. Use the same image set and fundamental matrices deterined earlier. Select a feature in image A and its corresponding image point (imgA) to determine the epipolar line in image B. Draw the line on image B and verify that it passes through (or very close to) the matching point in image B. Draw two such epipolar lines and calculate their intersection. Show that this point (epipole) can be obtained from null(F).

  5. Write MATLAB programs to reproduce the figures below

    1. Shading examples using lighting

    2. Variations of diffuse and specular reflection

    3. Varying the SpecularExponent

    4. Varying the SpecularColorReflectance


Maintained by John Loomis, last updated 18 April 2016