ECE 564 Computer Vision Assignment 7

Submit HTML documentation on Isidore.

  1. Identify the photograph taken of your product on a checkerboard (see sample below) and the corresponding empty checkerboard. Calculate the extrinsics of the checkerboard image you used (Rotation matrix and translation vector).

  2. Use MATLAB to reproduce the photograph taken of your empty checkerboard background. You may establish the view angle either by calculation or trial-and-error.

  3. Construct a MATLAB 3D model of your object on the checkerboard. Try to create an image as close as you can to your selected photograph (but with only your product present).

  4. Use the image script5a.jpg produced by script5a.m and directed homography to determine the location of the photographs and the location of the camera relative to the the walls of the model hallway. Note that the photographs are scaled to be the same size as the target board. Also find the hallway vanishing point(s).

  5. Use the fifth image from CV2017-03-20 (shown below) to construct a directed homography as demonstrated in class showing the hallway as would be seen from directly above (parallel hall walls)

  6. Use the fourteenth image from CV2017-03-20 (shown below) to construct a homography showing the view from above. Use the resulting image to verify the width of the hallway (in feet). Construct a map of the hallway and determine the location and viewing angle of the camera on the map.

  7. Use images 14-20 from CV2016-03-20 and the homography above to determine the location and look direction of the camera as it changes from image to image. Plot the results on a copy of the above map.


Maintained by John Loomis, last updated 21 March 2017