Work of Camera Calibration (7) : Running the re-setup experiment

I. Save figure function in MATLAB:

http://www.mathworks.co.uk/help/matlab/ref/print.html
http://stackoverflow.com/questions/12160184/how-to-save-a-figure-in-matlab-in-from-the-command-line

II. Experimental setup:

。Target

。First scenario - near

。Second scenario - medium

。Third scenario - Far

III. We collect these datas:

      * 'k-Img' means a Kinect frame; 'hh-Img' represents a Hand-held camera image

。3 k-Imgs under near, medium, and far distance to the target ...  (for matching tasks)
。3 sets of k-Imgs under near, medium, far, which are taking under different perspective 
    around 360 degree ...  (for stitching tasks)

。5 hh-Imgs with different scales
。5 sets of hh-Imgs under 5 different scales, which are taking under different perspective 
    around 360 degree
。10 hh-Imgs with simple affine transformation
。16 hh-Imgs under 2 different scales, which are taking under different perspective 
    around 360 degree

IV. Running the re-setup experiment: (matching tasks - for checking SIFT descriptors capability in  
      our cases)

     * 'k-Img' means a Kinect frame; 'hh-Img' represents a Hand-held camera image

。1 k-Img (totals are 3 under different scales) V.S. 5 hh-Imgs (under 5 different scales)
。1 k-Img (totals are 3 under different scales) V.S. 10 hh-Imgs  (with simple affine)
。1 k-Img (totals are 3 under different scales) V.S. 16 hh-Imgs under different 
     perspective (per dataset; totals are 2 sets of hh_Imgs under 2 different scales)
。1 k-Img (totals are 3 under different scales) V.S. 
    24 hh-Imgs with rotation (per dataset; totals are 5 sets of hh_Imgs under 5 different scales)

IV. Results... paste tomorrow: